Automated Sewer Inspection Using Image Processing and a Neural Classifier

Size: px
Start display at page:

Download "Automated Sewer Inspection Using Image Processing and a Neural Classifier"

Transcription

1 Automated Sewer Inspection Using Image Processing and a Neural Classifier Olga Duran, Kaspar Althoefer, Lakmal D. Seneviratne Department of Mechanical Engineering King's College London Strand, London WCR LS, UK olga.duran@kcl.ac.uk Abstract: - The focus of the research presented here is on the automated assessment of sewer pipe conditions using a laserbased sensor. The proposed method involves image and data processing algorithms categorising signals acquired from the internal pipe surface. Fault identification is carried out using a neural network. Experimental results are presented. I. INTRODUCTION The degradation of sewer networks, mainly due to its age, is becoming a serious issue in most industrialised countries. According to a study by a UK-based company, there are approximately 5,000 collapses and 00,000 blockages per year in the United Kingdom and around 0% of sewer networks are damaged [1]-[]. Considering that only 0.1 % of the sewer system is replaced every year, these figures are expected to increase by 3% every year. Early detection of pipe faults may prevent severe failures that can involve environmental damage and high economic costs. Closed circuit television (CCTV) surveys are widely used to assess pipe condition when direct human access is not possible. A camera fitted on a mobile and remotely controlled platform travels through the pipe recording images onto a videotape. The videotapes are assessed off-line by an engineer. One of the major drawbacks of this technique is the exorbitant amount of information generated, that can reach about 3 hours of video for the inspection of 1Km of line [3]. Moreover, the time required by the engineer to assess the pipe condition depends on the number of defects. Owing to the variability and the time consumption incurred by the humanbased assessment process, automation of this part of the inspection task becomes an important target. Some relevant research has been carried out in the field of automated sewer inspection. For instance, the Civil and Environmental Engineering group, at Concordia University (Canada), is developing a model which will help to automate the process of identifying and classifying several surface defects from digitised video images of underground water and waste pipes, using image analysis, pattern recognition and neural networks [4]-[5]. The Department of Systems Design Engineering, at the University of Waterloo (Canada), have developed a neuro-fuzzy algorithm to recognise and classify cracks in underground pipes [6]. Another example, is PIRAT (Pipe Inspection Real-Time Assessment Technique), an experimental system developed by CSIRO (Commonwealth Scientific and Industrial Research Organisation) and Melbourne Water, Australia. The PIRAT platform measures and analyses the internal geometry of the sewer. Automatic recognition, rating and classification of pipe defects are carried out by means of artificial intelligence software tools. Images are segmented into potentially defective regions and characteristic geometric features. Region classification is performed by a feed-forward, off-line trained neural network classifier [7]. In this paper, the defect detection method, based on camera images, tries to cope with some CCTV drawbacks, mainly related to illumination. Another drawback of current CCTVbased inspection systems is that only non-flooded pipes can be inspected. Considering that typically, the lowest water level is around 5% in a combined sewer during dry weather, other sensors are needed to inspect the flooded part of the pipe. The investigation reported in this paper is part of a research programme that aims to develop automated sewer inspection methods. The objective of this project is to study and develop multi-sensor systems and to create intelligent sensor fusion and sensor data processing algorithms. A sonar has been found most suitable in order to inspect the flooded areas [8]-[9], while an optical-based sensor is appropriate for inspecting the area above the water level. It is envisaged that a laser-profiler-ccd camera system scans the inner wall of the drained part of a sewer. This paper presents research progress on the inspection and automated condition assessment of the non-flooded part of the pipe. The method described makes use of image processing techniques and intelligent classification algorithms, providing an identification of defective pipe segments. The different

2 processing stages such as data acquisition, image processing and classification are described in the following sections. In Section II, the experimental set-up together with the transducer that is used to acquire the images is described. Image segmentation into regions of interest and feature extraction will be shown in Section III. The classification step is shown in Section IV. Finally, conclusions are given in Section V. II. EXPERIMENTAL SET-UP (a) (b) In this work, a laser-based profiler, which can easily be incorporated into existing camera-based systems, is used to inspect the areas above the water level. The transducer consists of an optical pattern generator that projects rings of laser light onto the pipe wall, illuminating an entire circular pipe section. The optical ring generator is made of an assembly of a laser generator and diffractive diffuser optics. The experimental rig used consists of a 1mW-semiconductor laser diode of 635nm wavelength and a diffractive diffuser for the generation of ring patterns. The projected circular patterns of light are read by a calibrated CCD camera, and stored in a computer via a frame grabber (fig. 1). Tests were conducted on PVC pipe sections with inner diameters of 60 and 300 mm. Holes and cracks of different sizes were pierced into the walls of the pipe segments in order to simulate defects. (c) Figure : Images of a pipe with a mm hole. The location of the hole is marked with a small circle. a) Image acquired using the laser-based transducer, where the crack can be easily identified. b) Image acquired with a conventional CCD camera and lighting system. Note that the white spot next to the circle is created by a light reflection; it is not a defect, but could be wrongly identified as one. c) Image acquired using the laser-based transducer, corresponding to the location of the non-defective point caused by light reflection as referred to in b). This image shows that the proposed method correctly presents this point as non-defective. Figure 1: Experimental set-up, where a camera and a laser projector are placed next to each other. The camera images are read into a PC by means of a frame-grabber. An important advantage of this method is that the processed and normalised signal can be fused together with sonar data from below the sewer liquid in order to create a full picture of the internal walls of the pipe. Furthermore, as the geometric characteristics of the cone of light are fixed for a given diffuser optic, the location of the surface under investigation relative to the platform is known. Consequently discontinuities and their location can be determined. This kind of sensor has been successfully used to measure pipe deflection or change of shape comparing consecutive images using the triangulation method. Besides that, local discontinuities, such as cracks or holes can be detected by analysing the light intensity of the projected rings in the same images. At points where discontinuities occur, the laser light is scattered resulting in changes of intensity levels in the acquired camera image (fig. ). Analysing these intensity levels, defects can be detected. III. FEATURE EXTRACTION A set of image processing stages is used to identify the ring profile and to extract it from the image background. Once a ring profile is properly extracted, a feature extraction algorithm scans the profile only, instead of searching the

3 entire and potentially very large pipe wall image for defects. This process is repeated for each of the pipe profiles. This locally approach has been shown to considerably reduce the amount of data to be processed, and consequently the computation time. Prior to applying the conic-fitting algorithm, image quality needs to be enhanced. Histogram equalisation and a median filter are applied, so that noise is attenuated and edges are preserved. Finally, a canny edge detector has been found most efficient to pre-segment the image by finding the edges of the ring of light [10]. 4 B. Intensity transform b = 1 ac (6) In this stage, the extraction of intensity information along the ellipse is carried out. In order to achieve this, a signal representing a partial histogram of the image is created using local averages of intensity along the ring profile. The intensity transform algorithm computes local averages of intensity along a defined number of segments of the ellipse. The local average intensity is computed using the equation (7): A. Ellipse extraction conic fitting The method has been used in this work to efficiently fit the image to a conic. It is based on the ellipse fitting method proposed by Fitzgibbon [11], improved by a method suggested by Halýr [1]. The approach is a non-iterative algorithm based on a least squares minimisation of the algebraic distance between the data points and the ellipse. A quadratic constraint guarantees an ellipse-specific solution even for scattered or noisy data, or for a partial occlusion condition, which can occur when the sewer is partially flooded. Also to improve the behaviour of the algorithm in the presence of noise, a weighted function is applied to the points before starting the computation. µ x µ Where x is the grey level of a certain image point, and µ the frequency of that grey level. (7) This method is based on the representation of a conic by an implicit second order polynomial: ( a, x) = a x= a x + b x y+ c y + d x+ e y+ f = 0 F (1) Where, a [ a b c d e f ] T = () x [ x x. y y x y 1] T = (3) ( a, x) F (4) Figure 3: Feature extraction algorithm; a sliding window is applied along the ellipse. The peak indicates the location of a potential discontinuity. In the current experiment, a pipe with a diameter of 60 mm is used. A mm hole has been pierced at 1 degrees from the horizontal axis. The partial histograms have been computed with steps of one degree along the ellipse segments. Equation (4) is the algebraic distance of a point (x, y) to the conic. The fitting consists of minimising the squares of the distances, in equation (5), subject to the equality in constraint (6), which incorporates both scaling and ellipse-specific conditions. ( a, x) = 0 F (5) These averages are computed over a sliding window covering areas along individual ellipse segments. Figure 3 shows the results of the feature extraction process displayed as a partial image histogram. Figure 4 shows the open-up representation of the inner surface of a pipe. This is created with successive histograms computed from the pipe surface images when a platform holding the transducer is travelling along the pipe.

4 1) Emphasising intensity variations: The differential of the signal is computed in order to emphasise intensity variations. This operation effectively attenuates small changes in intensity, that are primarily due to minor differences in illumination across the section under study. Figure 4: Open-up representation of the inner surface of the pipe. The intensity peak shows the location of a potential defect. IV. CLASSIFICATION USING A NEURAL NETWORK ) Signature generation: Although the data resulting from the previous operation could be used to feed the NN, one more step is taken in order to further enhance the data supplied to the network. The data received form each pipe section is made up of individual samples, which are sorted by signal amplitude in descending order, using the quicksort algorithm. This means that any defective section, having one or more intensity peaks, will be converted into a monotonically decreasing sequence. A normalisation step is now applied, by subtracting the values representing each section to their respective maximum value. The resulting signal is a monotonically increasing sequence starting from zero, where non-defective sections will appear as fairly flat signal. On the other hand, signals representing a defective section will present a sharp slope reaching then a fairly flat region at a higher amplitude (see figure 5). We will call these sorted signals signatures. The aim of this research is to use a neural network for the identification of defective and non-defective pipe sections and for the classification of different defects in the surface of the pipe. A binary approach is taken in this work, where pipe sections are classified as defective or non-defective. In further work, defects will be classified into different categories such as longitudinal cracks, radial cracks, holes and obstacles and a fault severity rating will be given as well. The input to the NN is a pre-processed signal that highlights the characteristics of defective versus non-defective pipe sections. The network employed here is a multi-layer perceptron (MLP). The training algorithm used in this work is based on backpropagation, which is widely used for solving classification problems [13]-[14]. A. Pre-processing A first pre-processing stage is used to normalise and reduce the amount of data supplied to the network. In order to identify potential defects in the surface of the pipe, the target data has to be prepared in order to show great variations in intensity levels. It has to be considered that the main difficulty is to discard the points where the intensity changes are caused by variations in the lighting conditions. Before feeding the neural network, the raw data is pre-processed and normalised as follows: Amplitude [intensity] Defective sections Non-defective sections Sorted values Figure 5: Normalised signature of defective and non-defective sections: Defective sections with faults at different spatial locations along the profile with different widths have similar signatures. In previous work, for the classification of holes, a different approach has been used for the signature creation. In that case a Fourier transform (FFT) of the signal was used as a signature [15]. Figure 6 shows Fourier transforms of defective and non-defective pipe profiles. The peaks that can be observed in the mid-frequency range of the Fourier domain correspond to intensity variations due to physical defects. Although both the FFT and the quicksort have a computational complexity of O(n log(n)), where n is the

5 number of samples, the algorithm proposed here for signature creation has been found computationally more efficient than the FFT-based algorithm, reducing the computation time by 50%. This is believed to be due to the large number of complex products that have to be computed for the Fourier Transform. Besides that, in the FFT-based algorithm used, a low-pass moving average filter is applied to remove highfrequency noise. This step leads to an increase in computation time investigation may show that it is possible to achieve comparable results with a single hidden layer [13]. The best performance was achieved with a multi-layer perceptron with four layers: The first layer with 50 input nodes, the second with 100 hidden nodes, the third with 0 hidden nodes and finally one output node in the fourth layer. Sigmoidal activation functions were used for the hidden nodes. The data used during algorithm was a stream of normalised signatures, as shown in section 4.1, containing both faulty and non-faulty pipe sections. The training behaviour shows that this algorithm is able to classify the training data bringing the error down to 1E-8 after 1518 epochs (fig. 7). Amplitude Defective sections Non defective sections Frequency 10-6 Figure 6: FFT of defective and non-defective sections Figure 5 shows normalised signatures of defective and nondefective pipe profiles. The peaks that can be observed in the first data points correspond to intensity variations due to physical defects. A neural network can be trained with this normalised data and it will recognise all defects, regardless of their position in the spatial domain and its width along a certain profile (since the differential has been applied previously). In other words, by using these normalising steps, the NN does not need to be trained with a stream of sections that contain defects of all sizes and at all possible points in the pipe section. B. Experimental results Experiments with different configurations of NN architectures, different numbers of hidden layers, nodes and training parameters were carried out. A scaled conjugate gradient (SCG) algorithm has been found more time- and performance-efficient than conventional backpropagation algorithms [16]. The selection of training parameters such as number of nodes, learning rate or activation function, is done in a trial and error procedure. Networks with two hidden layers were found to respond slightly better at the generalisation stage, although training took longer. Considering that a trial and error procedure was used, further Epochs Figure 7: Training error with a two-hidden-layer Network Epochs Figure 8: Training error with a single-hidden-layer Network

6 The best performance, using a single hidden-layer and the same training data as above, was achieved with 100 hidden nodes. After 944 epochs, the error was also down to 1E-8 (fig. 8). The training time is shorter and the number of epochs is reduced using a single- instead of a two-hidden-layer network. The ability of the trained networks to cope with unseen data is also tested. As an example, Table 1 and summarise the output results for the five pipe profiles shown in figure 4, which were not seen during the training. Table 1 contains the results when using two hidden layers while in table, the results using a single layer are shown. The target column specifies the value 1 or 0 corresponding to non-defective and defective sections respectively. The output column represents the output node. The error is the absolute difference between the desired target and the output values. These results show that both networks are able to identify irregularities in the data (related to defective sections) even though the data was not seen by the network beforehand. TABLE 1: NN RESPONSE TO UNSEEN DATA USING TWO HIDDEN LAYERS Pipe Section Target Result Error Non-defective Non-defective Defective Non-defective Non-defective TABLE : NN RESPONSE TO UNSEEN DATA USING A SINGLE HIDDEN LAYER Pipe Section Target Result Error Non-defective Non-defective Defective Non-defective Non-defective V. CONCLUSIONS In this paper, a method for the detection of pipe defects using NNs is presented. The proposed method uses a new laser-based inspection system. The methods is based on the projection and analysis of a laser-generated pattern onto the pipe walls. Defects in the inner surface of pipes are located by analysing the light intensity of the projected rings. Imageprocessing techniques combined with an MLP trained using backpropagation provide the classification between defective and non-defective pipe sections. Experiments have been conducted in a realistic environment and results have been presented. Future work will focus on the classification of defects such as longitudinal or radial cracks and holes. The long-term objective of this research is to assess partially flooded pipes using a multi-sensor system. The transducer described in this paper inspects the non-flooded surface, while an ultrasonic sensor will inspect the flooded parts. In order to get a complete image representing the condition of the entire surface of the pipe, sensor fusion can be carried out at the pixel, signal or feature level. VI. REFERENCES [1] Roth, H, Schilling, K. Navigation and Control for Pipe Inspection and Repair Robots : Proc of IFAC World Congress, [] WEF Manuals & Reports FD-6, ASCE Manuals & reports on engineering, Existing sewer evaluation and rehabilitation, No. 6, [3] Pace, NG. Ultrasonic surveying of fully charged sewage pipes, Electronics and Communications Engineering Journal, pp 87-9, [4] Moselhi, O. Shehab-Eldeen, T. Automated detection of surface defects in water and sewer pipes. Automation in Construction 8, pp , [5] Moselhi, O. Shehab-Eldeen, T. Classification of defects in sewer pipes using neural networks. Journal of infrastructure systems 6, 3, pp , 000. [6] Sinha, K.S, Karray, F. Fieguth, P.W. Underground Pipe Cracks Classification Using Image Analysis and Neuro-Fuzzy Algorithm : Proceedings of the International Symposium on Intelligent Control/ Intelligent Systems and Semiotic, Cambridge, MA, pp , 1999 [7] Campbell, G. Rogers, K. Gilbert, J. Pirat a system for quantitative sewer assessment, International No Dig 95, Dresden, Germany, [8] Bin Hussen, M. P. Althoefer, K. A. Seneviratne, L. D. Automated Inspection of Sewers Using Ultrasonic Sensors, Proc. EUREL European Advanced Robotics Systems Masterclass and Conf., Vol.1, Salford, UK, 000. [9] Bin Hussen, M. P. Althoefer, K. A. Seneviratne, L. D. "Automatic sewer defect detection and classification using a neural network", Neural Network World, Vol. 10, No. 4, pp , 000. [10] Gonzalez R.C. Digital Image Processing. Addison-Wesley, MA, [11] Fitzgibbon, A. Pilu, M. Fisher R. Direct Least Square Fitting of Ellipses. Pattern analysis and machine intelligence, Vol. 1 Issue 5, pp , [1] Halir, R. Flusser J. Numerically stable direct least squares fitting of ellipses. The Sixth International Conference in Central Europe on Computer Graphics and Visualization, Plzeò, pp , [13] Hush, D.R. Horne, B.G. Progress in supervised Neural Networks. IEEE Signal Processing Magazine, pp 8-39, [14] Haykin, S. Neural Networks. A Comprehensive Foundation. Macmillan College Publishing Company, NY, [15] Duran, O. Althoefer, K. Seneviratne, L.D. Automated Laser-based Profiler for Sewer Inspection. Proceedings of the 7th International Conference on Intelligent Autonomous Systems (IAS-7), Marina del Rey, California, USA, 00 (Accepted for publication). [16] Moller, M. F. "A scaled conjugate gradient algorithm for fast supervised learning," Neural Networks, vol. 6, pp , 1993.

Rotating optical geometry sensor for inner pipe-surface reconstruction

Rotating optical geometry sensor for inner pipe-surface reconstruction Rotating optical geometry sensor for inner pipe-surface reconstruction Moritz Ritter and Christian W. Frey Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Fraunhoferstraße

More information

DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER

DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER S17- DEVELOPMENT OF POSITION MEASUREMENT SYSTEM FOR CONSTRUCTION PILE USING LASER RANGE FINDER Fumihiro Inoue 1 *, Takeshi Sasaki, Xiangqi Huang 3, and Hideki Hashimoto 4 1 Technica Research Institute,

More information

MOBILE INSPECTION SYSTEM FOR HIGH-RESOLUTION ASSESSMENT OF TUNNELS

MOBILE INSPECTION SYSTEM FOR HIGH-RESOLUTION ASSESSMENT OF TUNNELS MOBILE INSPECTION SYSTEM FOR HIGH-RESOLUTION ASSESSMENT OF TUNNELS M. Gavilán*, F. Sánchez, J.A. Ramos and O. Marcos EUROCONSULT GROUP Avenida Montes de Oca 9-11, 28703, Madrid, Spain *Corresponding author:

More information

COMPUTER-BASED WORKPIECE DETECTION ON CNC MILLING MACHINE TOOLS USING OPTICAL CAMERA AND NEURAL NETWORKS

COMPUTER-BASED WORKPIECE DETECTION ON CNC MILLING MACHINE TOOLS USING OPTICAL CAMERA AND NEURAL NETWORKS Advances in Production Engineering & Management 5 (2010) 1, 59-68 ISSN 1854-6250 Scientific paper COMPUTER-BASED WORKPIECE DETECTION ON CNC MILLING MACHINE TOOLS USING OPTICAL CAMERA AND NEURAL NETWORKS

More information

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile.

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile. Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Blobs and Cracks

More information

A Nondestructive Bump Inspection in Flip Chip Component using Fuzzy Filtering and Image Processing

A Nondestructive Bump Inspection in Flip Chip Component using Fuzzy Filtering and Image Processing A Nondestructive Bump Inspection in Flip Chip Component using Fuzzy Filtering and Image Processing 103 A Nondestructive Bump Inspection in Flip Chip Component using Fuzzy Filtering and Image Processing

More information

A Digital-geometry-based Framework used in an Omnidirectional Laser-Optics Technology for Inspecting Pipes

A Digital-geometry-based Framework used in an Omnidirectional Laser-Optics Technology for Inspecting Pipes Available online www.ejaet.com European Journal of Advances in Engineering and Technology, 2015, 2(6): 1-9 Research Article ISSN: 2394-658X A Digital-geometry-based Framework used in an Omnidirectional

More information

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment L.-M. CHANG and Y.A. ABDELRAZIG School of Civil Engineering, Purdue University,

More information

IRIS SEGMENTATION OF NON-IDEAL IMAGES

IRIS SEGMENTATION OF NON-IDEAL IMAGES IRIS SEGMENTATION OF NON-IDEAL IMAGES William S. Weld St. Lawrence University Computer Science Department Canton, NY 13617 Xiaojun Qi, Ph.D Utah State University Computer Science Department Logan, UT 84322

More information

A Neural Network Model Of Insurance Customer Ratings

A Neural Network Model Of Insurance Customer Ratings A Neural Network Model Of Insurance Customer Ratings Jan Jantzen 1 Abstract Given a set of data on customers the engineering problem in this study is to model the data and classify customers

More information

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network International Journal of Computer Science & Communication Vol. 1, No. 1, January-June 2010, pp. 91-95 Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network Raghuraj

More information

Auto-focusing Technique in a Projector-Camera System

Auto-focusing Technique in a Projector-Camera System 2008 10th Intl. Conf. on Control, Automation, Robotics and Vision Hanoi, Vietnam, 17 20 December 2008 Auto-focusing Technique in a Projector-Camera System Lam Bui Quang, Daesik Kim and Sukhan Lee School

More information

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Utkarsh Dwivedi 1, Pranjal Rajput 2, Manish Kumar Sharma 3 1UG Scholar, Dept. of CSE, GCET, Greater Noida,

More information

Detecting Ellipses via Bounding Boxes

Detecting Ellipses via Bounding Boxes Detecting Ellipses via Bounding Boxes CHUN-MING CHANG * Department of Information and Design, Asia University, Taiwan ABSTRACT A novel algorithm for ellipse detection based on bounding boxes is proposed

More information

An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant

An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant An Algorithm to Determine the Chromaticity Under Non-uniform Illuminant Sivalogeswaran Ratnasingam and Steve Collins Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, United Kingdom

More information

Comparison between 3D Digital and Optical Microscopes for the Surface Measurement using Image Processing Techniques

Comparison between 3D Digital and Optical Microscopes for the Surface Measurement using Image Processing Techniques Comparison between 3D Digital and Optical Microscopes for the Surface Measurement using Image Processing Techniques Ismail Bogrekci, Pinar Demircioglu, Adnan Menderes University, TR; M. Numan Durakbasa,

More information

Ch 22 Inspection Technologies

Ch 22 Inspection Technologies Ch 22 Inspection Technologies Sections: 1. Inspection Metrology 2. Contact vs. Noncontact Inspection Techniques 3. Conventional Measuring and Gaging Techniques 4. Coordinate Measuring Machines 5. Surface

More information

Digital Image Correlation of Stereoscopic Images for Radial Metrology

Digital Image Correlation of Stereoscopic Images for Radial Metrology Digital Image Correlation of Stereoscopic Images for Radial Metrology John A. Gilbert Professor of Mechanical Engineering University of Alabama in Huntsville Huntsville, AL 35899 Donald R. Matthys Professor

More information

Complex Sensors: Cameras, Visual Sensing. The Robotics Primer (Ch. 9) ECE 497: Introduction to Mobile Robotics -Visual Sensors

Complex Sensors: Cameras, Visual Sensing. The Robotics Primer (Ch. 9) ECE 497: Introduction to Mobile Robotics -Visual Sensors Complex Sensors: Cameras, Visual Sensing The Robotics Primer (Ch. 9) Bring your laptop and robot everyday DO NOT unplug the network cables from the desktop computers or the walls Tuesday s Quiz is on Visual

More information

IMAGING SPECTROMETER DATA CORRECTION

IMAGING SPECTROMETER DATA CORRECTION S E S 2 0 0 5 Scientific Conference SPACE, ECOLOGY, SAFETY with International Participation 10 13 June 2005, Varna, Bulgaria IMAGING SPECTROMETER DATA CORRECTION Valentin Atanassov, Georgi Jelev, Lubomira

More information

HIGH RESOLUTION VISUAL PIPE CHARACTERIZATION SYSTEM USING AN OMNIDIRECTIONAL CAMERA

HIGH RESOLUTION VISUAL PIPE CHARACTERIZATION SYSTEM USING AN OMNIDIRECTIONAL CAMERA HIGH RESOLUTION VISUAL PIPE CHARACTERIZATION SYSTEM USING AN OMNIDIRECTIONAL CAMERA A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the

More information

Accurate 3D Face and Body Modeling from a Single Fixed Kinect

Accurate 3D Face and Body Modeling from a Single Fixed Kinect Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this

More information

TUNNELINGS SYSTEM Inspection of brick tunnels and covered ways SSL (Circle, Hammersmith & City and District Lines) LONDON UNDERGROUND LIMITED

TUNNELINGS SYSTEM Inspection of brick tunnels and covered ways SSL (Circle, Hammersmith & City and District Lines) LONDON UNDERGROUND LIMITED TUNNELINGS SYSTEM Inspection of brick tunnels and covered ways SSL (Circle, Hammersmith & City and District Lines) LONDON UNDERGROUND LIMITED Inspection date: July 6 th 2014 Report date: September 22 nd

More information

Ellipse fitting using orthogonal hyperbolae and Stirling s oval

Ellipse fitting using orthogonal hyperbolae and Stirling s oval Ellipse fitting using orthogonal hyperbolae and Stirling s oval Paul L. Rosin Abstract Two methods for approximating the normal distance to an ellipse using a) its orthogonal hyperbolae, and b) Stirling

More information

In this assignment, we investigated the use of neural networks for supervised classification

In this assignment, we investigated the use of neural networks for supervised classification Paul Couchman Fabien Imbault Ronan Tigreat Gorka Urchegui Tellechea Classification assignment (group 6) Image processing MSc Embedded Systems March 2003 Classification includes a broad range of decision-theoric

More information

Ultrasonic Robot Eye for Shape Recognition Employing a Genetic Algorithm

Ultrasonic Robot Eye for Shape Recognition Employing a Genetic Algorithm 7 XVII IMEKO World Congress Metrology in the 3rd Millennium June 22 27, 2003, Dubrovnik, Croatia Ultrasonic Robot Eye for Shape Recognition Employing a Genetic Algorithm Kozo Ohtani* and Mitsuru Baba**

More information

A 3-D Scanner Capturing Range and Color for the Robotics Applications

A 3-D Scanner Capturing Range and Color for the Robotics Applications J.Haverinen & J.Röning, A 3-D Scanner Capturing Range and Color for the Robotics Applications, 24th Workshop of the AAPR - Applications of 3D-Imaging and Graph-based Modeling, May 25-26, Villach, Carinthia,

More information

Looming Motion Segmentation in Vehicle Tracking System using Wavelet Transforms

Looming Motion Segmentation in Vehicle Tracking System using Wavelet Transforms Looming Motion Segmentation in Vehicle Tracking System using Wavelet Transforms K. SUBRAMANIAM, S. SHUKLA, S.S. DLAY and F.C. RIND Department of Electrical and Electronic Engineering University of Newcastle-Upon-Tyne

More information

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N.

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. Dartmouth, MA USA Abstract: The significant progress in ultrasonic NDE systems has now

More information

STEREO VISION AND LASER STRIPERS FOR THREE-DIMENSIONAL SURFACE MEASUREMENTS

STEREO VISION AND LASER STRIPERS FOR THREE-DIMENSIONAL SURFACE MEASUREMENTS XVI CONGRESO INTERNACIONAL DE INGENIERÍA GRÁFICA STEREO VISION AND LASER STRIPERS FOR THREE-DIMENSIONAL SURFACE MEASUREMENTS BARONE, Sandro; BRUNO, Andrea University of Pisa Dipartimento di Ingegneria

More information

Laser Eye a new 3D sensor for active vision

Laser Eye a new 3D sensor for active vision Laser Eye a new 3D sensor for active vision Piotr Jasiobedzki1, Michael Jenkin2, Evangelos Milios2' Brian Down1, John Tsotsos1, Todd Campbell3 1 Dept. of Computer Science, University of Toronto Toronto,

More information

Non-rigid body Object Tracking using Fuzzy Neural System based on Multiple ROIs and Adaptive Motion Frame Method

Non-rigid body Object Tracking using Fuzzy Neural System based on Multiple ROIs and Adaptive Motion Frame Method Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Non-rigid body Object Tracking using Fuzzy Neural System based on Multiple ROIs

More information

A Simple Automated Void Defect Detection for Poor Contrast X-ray Images of BGA

A Simple Automated Void Defect Detection for Poor Contrast X-ray Images of BGA Proceedings of the 3rd International Conference on Industrial Application Engineering 2015 A Simple Automated Void Defect Detection for Poor Contrast X-ray Images of BGA Somchai Nuanprasert a,*, Sueki

More information

Exploring Curve Fitting for Fingers in Egocentric Images

Exploring Curve Fitting for Fingers in Egocentric Images Exploring Curve Fitting for Fingers in Egocentric Images Akanksha Saran Robotics Institute, Carnegie Mellon University 16-811: Math Fundamentals for Robotics Final Project Report Email: asaran@andrew.cmu.edu

More information

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

Small-scale objects extraction in digital images

Small-scale objects extraction in digital images 102 Int'l Conf. IP, Comp. Vision, and Pattern Recognition IPCV'15 Small-scale objects extraction in digital images V. Volkov 1,2 S. Bobylev 1 1 Radioengineering Dept., The Bonch-Bruevich State Telecommunications

More information

Performance Improvement of a 3D Stereo Measurement Video Endoscope by Means of a Tunable Monochromator In the Illumination System

Performance Improvement of a 3D Stereo Measurement Video Endoscope by Means of a Tunable Monochromator In the Illumination System More info about this article: http://www.ndt.net/?id=22672 Performance Improvement of a 3D Stereo Measurement Video Endoscope by Means of a Tunable Monochromator In the Illumination System Alexander S.

More information

Coarse-to-Fine Search Technique to Detect Circles in Images

Coarse-to-Fine Search Technique to Detect Circles in Images Int J Adv Manuf Technol (1999) 15:96 102 1999 Springer-Verlag London Limited Coarse-to-Fine Search Technique to Detect Circles in Images M. Atiquzzaman Department of Electrical and Computer Engineering,

More information

Adaptive Focusing Technology for the Inspection of Variable Geometry. Composite Material

Adaptive Focusing Technology for the Inspection of Variable Geometry. Composite Material More info about this article: http://www.ndt.net/?id=22711 Adaptive Focusing Technology for the Inspection of Variable Geometry Composite Material Etienne GRONDIN 1 1 Olympus Scientific Solutions Americas,

More information

CCTV Sewer Imaging Technology Update

CCTV Sewer Imaging Technology Update SARBS Collections Training Seminar Jan. 26, 2012 CCTV Sewer Imaging Technology Update Lori S. Weiss City of Santa Barbara, CA Public Works Department, Wastewater Treatment Gary N. Skipper, P.E. Vice President

More information

Lab2: Single Photon Interference

Lab2: Single Photon Interference Lab2: Single Photon Interference Xiaoshu Chen* Department of Mechanical Engineering, University of Rochester, NY, 14623 ABSTRACT The wave-particle duality of light was verified by multi and single photon

More information

NDT OF SPECIMEN OF COMPLEX GEOMETRY USING ULTRASONIC ADAPTIVE

NDT OF SPECIMEN OF COMPLEX GEOMETRY USING ULTRASONIC ADAPTIVE NDT OF SPECIMEN OF COMPLEX GEOMETRY USING ULTRASONIC ADAPTIVE TECHNIQUES - THE F.A.U.S.T. SYSTEM INTRODUCTION O. Roy, S. Mahaut, M. Serre Commissariat a I'Energie Atomique CEAlCEREM, CE Saclay France Phased

More information

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai COMPUTER VISION Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai 600036. Email: sdas@iitm.ac.in URL: //www.cs.iitm.ernet.in/~sdas 1 INTRODUCTION 2 Human Vision System (HVS) Vs.

More information

A COMPREHENSIVE SIMULATION SOFTWARE FOR TEACHING CAMERA CALIBRATION

A COMPREHENSIVE SIMULATION SOFTWARE FOR TEACHING CAMERA CALIBRATION XIX IMEKO World Congress Fundamental and Applied Metrology September 6 11, 2009, Lisbon, Portugal A COMPREHENSIVE SIMULATION SOFTWARE FOR TEACHING CAMERA CALIBRATION David Samper 1, Jorge Santolaria 1,

More information

A threshold decision of the object image by using the smart tag

A threshold decision of the object image by using the smart tag A threshold decision of the object image by using the smart tag Chang-Jun Im, Jin-Young Kim, Kwan Young Joung, Ho-Gil Lee Sensing & Perception Research Group Korea Institute of Industrial Technology (

More information

Measurements using three-dimensional product imaging

Measurements using three-dimensional product imaging ARCHIVES of FOUNDRY ENGINEERING Published quarterly as the organ of the Foundry Commission of the Polish Academy of Sciences ISSN (1897-3310) Volume 10 Special Issue 3/2010 41 46 7/3 Measurements using

More information

Outdoor Scene Reconstruction from Multiple Image Sequences Captured by a Hand-held Video Camera

Outdoor Scene Reconstruction from Multiple Image Sequences Captured by a Hand-held Video Camera Outdoor Scene Reconstruction from Multiple Image Sequences Captured by a Hand-held Video Camera Tomokazu Sato, Masayuki Kanbara and Naokazu Yokoya Graduate School of Information Science, Nara Institute

More information

Model-based segmentation and recognition from range data

Model-based segmentation and recognition from range data Model-based segmentation and recognition from range data Jan Boehm Institute for Photogrammetry Universität Stuttgart Germany Keywords: range image, segmentation, object recognition, CAD ABSTRACT This

More information

COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING

COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING Saulat Farooque and Lakhmi Jain School of Electrical and Information Engineering, University of South Australia, Adelaide, Australia saulat.farooque@tenix.com,

More information

Character Recognition Using Convolutional Neural Networks

Character Recognition Using Convolutional Neural Networks Character Recognition Using Convolutional Neural Networks David Bouchain Seminar Statistical Learning Theory University of Ulm, Germany Institute for Neural Information Processing Winter 2006/2007 Abstract

More information

ADVANCED ULTRASOUND WAVEFORM ANALYSIS PACKAGE FOR MANUFACTURING AND IN-SERVICE USE R. A Smith, QinetiQ Ltd, Farnborough, GU14 0LX, UK.

ADVANCED ULTRASOUND WAVEFORM ANALYSIS PACKAGE FOR MANUFACTURING AND IN-SERVICE USE R. A Smith, QinetiQ Ltd, Farnborough, GU14 0LX, UK. ADVANCED ULTRASOUND WAVEFORM ANALYSIS PACKAGE FOR MANUFACTURING AND IN-SERVICE USE R. A Smith, QinetiQ Ltd, Farnborough, GU14 0LX, UK. Abstract: Users of ultrasonic NDT are fundamentally limited by the

More information

Motion Detection Algorithm

Motion Detection Algorithm Volume 1, No. 12, February 2013 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Motion Detection

More information

ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall Midterm Examination

ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall Midterm Examination ECE 172A: Introduction to Intelligent Systems: Machine Vision, Fall 2008 October 29, 2008 Notes: Midterm Examination This is a closed book and closed notes examination. Please be precise and to the point.

More information

A fast algorithm for detecting die extrusion defects in IC packages

A fast algorithm for detecting die extrusion defects in IC packages Machine Vision and Applications (1998) 11: 37 41 Machine Vision and Applications c Springer-Verlag 1998 A fast algorithm for detecting die extrusion defects in IC packages H. Zhou, A.A. Kassim, S. Ranganath

More information

Research on Evaluation Method of Product Style Semantics Based on Neural Network

Research on Evaluation Method of Product Style Semantics Based on Neural Network Research Journal of Applied Sciences, Engineering and Technology 6(23): 4330-4335, 2013 ISSN: 2040-7459; e-issn: 2040-7467 Maxwell Scientific Organization, 2013 Submitted: September 28, 2012 Accepted:

More information

J. Yim, S. S. Udpa, L. Udpa, M. Mina, and W. Lord Department of Electrical Engineering and Computer Engineering Iowa State University Ames, la, 50011

J. Yim, S. S. Udpa, L. Udpa, M. Mina, and W. Lord Department of Electrical Engineering and Computer Engineering Iowa State University Ames, la, 50011 NEURAL NETWORK APPROACHES TO DATA FUSION INTRODUCTION J. Yim, S. S. Udpa, L. Udpa, M. Mina, and W. Lord Department of Electrical Engineering and Computer Engineering Iowa State University Ames, la, 50011

More information

OBSTACLE DETECTION WITH ACTIVE LASER TRIANGULATION

OBSTACLE DETECTION WITH ACTIVE LASER TRIANGULATION Advances in Production Engineering & Management 2 (2007) 2, 79-90 ISSN 1854-6250 Original scientific paper OBSTACLE DETECTION WITH ACTIVE LASER TRIANGULATION Klančnik, S. * ; Balič, J. * & Planinšič, P.

More information

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation K. Roy, U. Pal and B. B. Chaudhuri CVPR Unit; Indian Statistical Institute, Kolkata-108; India umapada@isical.ac.in

More information

Plane Wave Imaging Using Phased Array Arno Volker 1

Plane Wave Imaging Using Phased Array Arno Volker 1 11th European Conference on Non-Destructive Testing (ECNDT 2014), October 6-10, 2014, Prague, Czech Republic More Info at Open Access Database www.ndt.net/?id=16409 Plane Wave Imaging Using Phased Array

More information

Jo-Car2 Autonomous Mode. Path Planning (Cost Matrix Algorithm)

Jo-Car2 Autonomous Mode. Path Planning (Cost Matrix Algorithm) Chapter 8.2 Jo-Car2 Autonomous Mode Path Planning (Cost Matrix Algorithm) Introduction: In order to achieve its mission and reach the GPS goal safely; without crashing into obstacles or leaving the lane,

More information

COMBINING NEURAL NETWORKS FOR SKIN DETECTION

COMBINING NEURAL NETWORKS FOR SKIN DETECTION COMBINING NEURAL NETWORKS FOR SKIN DETECTION Chelsia Amy Doukim 1, Jamal Ahmad Dargham 1, Ali Chekima 1 and Sigeru Omatu 2 1 School of Engineering and Information Technology, Universiti Malaysia Sabah,

More information

Collecting outdoor datasets for benchmarking vision based robot localization

Collecting outdoor datasets for benchmarking vision based robot localization Collecting outdoor datasets for benchmarking vision based robot localization Emanuele Frontoni*, Andrea Ascani, Adriano Mancini, Primo Zingaretti Department of Ingegneria Infromatica, Gestionale e dell

More information

Journal of Asian Scientific Research AN APPLICATION OF STEREO MATCHING ALGORITHM FOR WASTE BIN LEVEL ESTIMATION

Journal of Asian Scientific Research AN APPLICATION OF STEREO MATCHING ALGORITHM FOR WASTE BIN LEVEL ESTIMATION Journal of Asian Scientific Research journal homepage: http://aessweb.com/journal-detail.php?id=5003 AN APPLICATION OF STEREO MATCHING ALGORITHM FOR WASTE BIN LEVEL ESTIMATION Md. Shafiqul Islam 1 M.A.

More information

True Advancements for Longitudinal Weld Pipe Inspection in PA

True Advancements for Longitudinal Weld Pipe Inspection in PA NDT in Canada 2016 & 6th International CANDU In-Service Inspection Workshop, Nov 15-17, 2016, Burlington, ON (Canada) www.ndt.net/app.ndtcanada2016 True Advancements for Longitudinal Weld Pipe Inspection

More information

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

More information

An Accurate Method for Skew Determination in Document Images

An Accurate Method for Skew Determination in Document Images DICTA00: Digital Image Computing Techniques and Applications, 1 January 00, Melbourne, Australia. An Accurate Method for Skew Determination in Document Images S. Lowther, V. Chandran and S. Sridharan Research

More information

Condenser Optics for Dark Field X-Ray Microscopy

Condenser Optics for Dark Field X-Ray Microscopy Condenser Optics for Dark Field X-Ray Microscopy S. J. Pfauntsch, A. G. Michette, C. J. Buckley Centre for X-Ray Science, Department of Physics, King s College London, Strand, London WC2R 2LS, UK Abstract.

More information

Bread Water Content Measurement Based on Hyperspectral Imaging

Bread Water Content Measurement Based on Hyperspectral Imaging 93 Bread Water Content Measurement Based on Hyperspectral Imaging Zhi Liu 1, Flemming Møller 1.2 1 Department of Informatics and Mathematical Modelling, Technical University of Denmark, Kgs. Lyngby, Denmark

More information

New Edge Detector Using 2D Gamma Distribution

New Edge Detector Using 2D Gamma Distribution Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 New Edge Detector Using 2D Gamma Distribution Hessah Alsaaran 1, Ali El-Zaart

More information

Environment-Aware Design For Underwater 3D-Scanning Application

Environment-Aware Design For Underwater 3D-Scanning Application Environment-Aware Design For Underwater 3D-Scanning Application Josephine Antoniou and Charalambos Poullis 1 Immersive and Creative Technologies Lab, Cyprus University of Technology November 22, 2012 1

More information

SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS

SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS J. KORNIS, P. PACHER Department of Physics Technical University of Budapest H-1111 Budafoki út 8., Hungary e-mail: kornis@phy.bme.hu, pacher@phy.bme.hu

More information

Draft SPOTS Standard Part III (7)

Draft SPOTS Standard Part III (7) SPOTS Good Practice Guide to Electronic Speckle Pattern Interferometry for Displacement / Strain Analysis Draft SPOTS Standard Part III (7) CALIBRATION AND ASSESSMENT OF OPTICAL STRAIN MEASUREMENTS Good

More information

Multipath Clamp-On Acoustic Flow Meter. Ing. Jürgen Skripalle HydroVision GmbH, Germany

Multipath Clamp-On Acoustic Flow Meter. Ing. Jürgen Skripalle HydroVision GmbH, Germany Dr.-Ing Ing. Jürgen Skripalle HydroVision GmbH, Germany Content Motivation Project Kopswerk II / Austria Signal Coupling Path Angle / Wall Thickness Optical 3D-System / Determination of Positions Discharge

More information

MEASURING SURFACE PROFILE WITH LOW-RESOLUTION DISPLACEMENT LASER SENSORS

MEASURING SURFACE PROFILE WITH LOW-RESOLUTION DISPLACEMENT LASER SENSORS MEASURING SURFACE PROFILE WITH LOW-RESOLUTION DISPLACEMENT LASER SENSORS J. Chen, R. Ward and G. Waterworth Leeds Metropolitan University, Faculty of Information & Engineering Systems Calverley Street,

More information

Mobile Human Detection Systems based on Sliding Windows Approach-A Review

Mobile Human Detection Systems based on Sliding Windows Approach-A Review Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg

More information

BUILDING MODEL RECONSTRUCTION FROM DATA INTEGRATION INTRODUCTION

BUILDING MODEL RECONSTRUCTION FROM DATA INTEGRATION INTRODUCTION BUILDING MODEL RECONSTRUCTION FROM DATA INTEGRATION Ruijin Ma Department Of Civil Engineering Technology SUNY-Alfred Alfred, NY 14802 mar@alfredstate.edu ABSTRACT Building model reconstruction has been

More information

CONTRIBUTION TO THE INVESTIGATION OF STOPPING SIGHT DISTANCE IN THREE-DIMENSIONAL SPACE

CONTRIBUTION TO THE INVESTIGATION OF STOPPING SIGHT DISTANCE IN THREE-DIMENSIONAL SPACE National Technical University of Athens School of Civil Engineering Department of Transportation Planning and Engineering Doctoral Dissertation CONTRIBUTION TO THE INVESTIGATION OF STOPPING SIGHT DISTANCE

More information

Digital Image Processing. Prof. P. K. Biswas. Department of Electronic & Electrical Communication Engineering

Digital Image Processing. Prof. P. K. Biswas. Department of Electronic & Electrical Communication Engineering Digital Image Processing Prof. P. K. Biswas Department of Electronic & Electrical Communication Engineering Indian Institute of Technology, Kharagpur Lecture - 21 Image Enhancement Frequency Domain Processing

More information

Experiments with Edge Detection using One-dimensional Surface Fitting

Experiments with Edge Detection using One-dimensional Surface Fitting Experiments with Edge Detection using One-dimensional Surface Fitting Gabor Terei, Jorge Luis Nunes e Silva Brito The Ohio State University, Department of Geodetic Science and Surveying 1958 Neil Avenue,

More information

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 6, Ver. VI (Nov Dec. 2014), PP 29-33 Analysis of Image and Video Using Color, Texture and Shape Features

More information

Drywall state detection in image data for automatic indoor progress monitoring C. Kropp, C. Koch and M. König

Drywall state detection in image data for automatic indoor progress monitoring C. Kropp, C. Koch and M. König Drywall state detection in image data for automatic indoor progress monitoring C. Kropp, C. Koch and M. König Chair for Computing in Engineering, Department of Civil and Environmental Engineering, Ruhr-Universität

More information

NATIONWIDE POINT CLOUDS AND 3D GEO- INFORMATION: CREATION AND MAINTENANCE GEORGE VOSSELMAN

NATIONWIDE POINT CLOUDS AND 3D GEO- INFORMATION: CREATION AND MAINTENANCE GEORGE VOSSELMAN NATIONWIDE POINT CLOUDS AND 3D GEO- INFORMATION: CREATION AND MAINTENANCE GEORGE VOSSELMAN OVERVIEW National point clouds Airborne laser scanning in the Netherlands Quality control Developments in lidar

More information

CS4758: Moving Person Avoider

CS4758: Moving Person Avoider CS4758: Moving Person Avoider Yi Heng Lee, Sze Kiat Sim Abstract We attempt to have a quadrotor autonomously avoid people while moving through an indoor environment. Our algorithm for detecting people

More information

Measurement of Residual Thickness in Case of Corrosion Close to the Welds with an Adaptive Total Focusing Method

Measurement of Residual Thickness in Case of Corrosion Close to the Welds with an Adaptive Total Focusing Method 19 th World Conference on Non-Destructive Testing 2016 Measurement of Residual Thickness in Case of Corrosion Close to the Welds with an Adaptive Total Focusing Method Olivier ROY 1, hilippe BENOIST 1,

More information

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation Obviously, this is a very slow process and not suitable for dynamic scenes. To speed things up, we can use a laser that projects a vertical line of light onto the scene. This laser rotates around its vertical

More information

The Analysis of Animate Object Motion using Neural Networks and Snakes

The Analysis of Animate Object Motion using Neural Networks and Snakes The Analysis of Animate Object Motion using Neural Networks and Snakes Ken Tabb, Neil Davey, Rod Adams & Stella George e-mail {K.J.Tabb, N.Davey, R.G.Adams, S.J.George}@herts.ac.uk http://www.health.herts.ac.uk/ken/vision/

More information

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS Setiawan Hadi Mathematics Department, Universitas Padjadjaran e-mail : shadi@unpad.ac.id Abstract Geometric patterns generated by superimposing

More information

DAMAGE INSPECTION AND EVALUATION IN THE WHOLE VIEW FIELD USING LASER

DAMAGE INSPECTION AND EVALUATION IN THE WHOLE VIEW FIELD USING LASER DAMAGE INSPECTION AND EVALUATION IN THE WHOLE VIEW FIELD USING LASER A. Kato and T. A. Moe Department of Mechanical Engineering Chubu University Kasugai, Aichi 487-8501, Japan ABSTRACT In this study, we

More information

Measurement of droplets temperature by using a global rainbow technique with a pulse laser

Measurement of droplets temperature by using a global rainbow technique with a pulse laser , 23rd Annual Conference on Liquid Atomization and Spray Systems, Brno, Czech Republic, September 2010 Measurement of droplets temperature by using a global rainbow technique with a pulse laser S. Saengkaew,

More information

Practice Exam Sample Solutions

Practice Exam Sample Solutions CS 675 Computer Vision Instructor: Marc Pomplun Practice Exam Sample Solutions Note that in the actual exam, no calculators, no books, and no notes allowed. Question 1: out of points Question 2: out of

More information

International Journal of the Korean Society of Precision Engineering, Vol. 1, No. 1, June 2000.

International Journal of the Korean Society of Precision Engineering, Vol. 1, No. 1, June 2000. International Journal of the Korean Society of Precision Engineering, Vol. 1, No. 1, June 2000. Jae-Yeol Kim *, Gyu-Jae Cho * and Chang-Hyun Kim ** * School of Mechanical Engineering, Chosun University,

More information

SYNTHETIC SCHLIEREN. Stuart B Dalziel, Graham O Hughes & Bruce R Sutherland. Keywords: schlieren, internal waves, image processing

SYNTHETIC SCHLIEREN. Stuart B Dalziel, Graham O Hughes & Bruce R Sutherland. Keywords: schlieren, internal waves, image processing 8TH INTERNATIONAL SYMPOSIUM ON FLOW VISUALIZATION (998) SYNTHETIC SCHLIEREN Keywords: schlieren, internal waves, image processing Abstract This paper outlines novel techniques for producing qualitative

More information

Flexible Visual Inspection. IAS-13 Industrial Forum Horizon 2020 Dr. Eng. Stefano Tonello - CEO

Flexible Visual Inspection. IAS-13 Industrial Forum Horizon 2020 Dr. Eng. Stefano Tonello - CEO Flexible Visual Inspection IAS-13 Industrial Forum Horizon 2020 Dr. Eng. Stefano Tonello - CEO IT+Robotics Spin-off of University of Padua founded in 2005 Strong relationship with IAS-LAB (Intelligent

More information

A Neural Network for Real-Time Signal Processing

A Neural Network for Real-Time Signal Processing 248 MalkofT A Neural Network for Real-Time Signal Processing Donald B. Malkoff General Electric / Advanced Technology Laboratories Moorestown Corporate Center Building 145-2, Route 38 Moorestown, NJ 08057

More information

Surface Defect Inspection of a Cutting Tool by Image Processing with Neural Networks

Surface Defect Inspection of a Cutting Tool by Image Processing with Neural Networks Memoirs of the Faculty of Engineering, Okayama University, Vol. 43, pp. 55-6, January 29 Surface Defect Inspection of a Cutting Tool by Image Processing with Neural Networks Shinichiro INOUE Division of

More information

Defect Inspection of Liquid-Crystal-Display (LCD) Panels in Repetitive Pattern Images Using 2D Fourier Image Reconstruction

Defect Inspection of Liquid-Crystal-Display (LCD) Panels in Repetitive Pattern Images Using 2D Fourier Image Reconstruction Defect Inspection of Liquid-Crystal-Display (LCD) Panels in Repetitive Pattern Images Using D Fourier Image Reconstruction Du-Ming Tsai, and Yan-Hsin Tseng Department of Industrial Engineering and Management

More information

CoE4TN4 Image Processing. Chapter 5 Image Restoration and Reconstruction

CoE4TN4 Image Processing. Chapter 5 Image Restoration and Reconstruction CoE4TN4 Image Processing Chapter 5 Image Restoration and Reconstruction Image Restoration Similar to image enhancement, the ultimate goal of restoration techniques is to improve an image Restoration: a

More information

Worksheet Answer Key: Scanning and Mapping Projects > Mine Mapping > Investigation 2

Worksheet Answer Key: Scanning and Mapping Projects > Mine Mapping > Investigation 2 Worksheet Answer Key: Scanning and Mapping Projects > Mine Mapping > Investigation 2 Ruler Graph: Analyze your graph 1. Examine the shape formed by the connected dots. i. Does the connected graph create

More information

Laserscanner Based Cooperative Pre-Data-Fusion

Laserscanner Based Cooperative Pre-Data-Fusion Laserscanner Based Cooperative Pre-Data-Fusion 63 Laserscanner Based Cooperative Pre-Data-Fusion F. Ahlers, Ch. Stimming, Ibeo Automobile Sensor GmbH Abstract The Cooperative Pre-Data-Fusion is a novel

More information