Text Block Detection and Segmentation for Mobile Robot Vision System Applications

Size: px
Start display at page:

Download "Text Block Detection and Segmentation for Mobile Robot Vision System Applications"

Transcription

1 Proc. of Int. Conf. onmultimedia Processing, Communication and Info. Tech., MPCIT Text Block Detection and Segmentation for Mobile Robot Vision System Applications Too Boaz Kipyego and Prabhakar C. J. Department of Computer Science, Kuvempu University, Karnataka, India Abstract We proposed a technique to detect and segment text block from natural scene based on stereo disparity map. The literature survey reveals that the techniques developed for scene text extraction are using an image of a scene of interest which is captured by monocular camera. In order to make robot to take decisions based on semantic information like text in an image, monocular camera based text extraction techniques cannot be employed because robot is fitted with two identical stereo cameras. Therefore, we proposed a technique to detect and extract scene text blocks using stereo images. The main application of the proposed technique is to make robot to detect and segment text blocks in a scene using stereo images of the scene, which will further enable robot to recognize the text written on the boards. The proposed technique comprises three major phases such as estimation of Disparity map using stereo images, detection of candidate planar surfaces from the disparity space using gradient derivative; finally segmentation of candidate text block by mapping connected component analysis of homograph image with detected candidate planes. The experiments are carried out using our dataset, which consists of stereo images captured in outdoor environment. The experimental results are evaluated for text detection using recall, precision and f-measure. The results indicate outstanding improvement in areas with complex background where conventional method fails. Index Terms disparity map, scene text, text detection, homograph image, Stereo images. I. INTRODUCTION The extraction of semantic information in an image is very essential for mobile robot to make high level decisions while it is navigating. The natural images contain semantic information like text of various languages written on sign or advertisement board. This semantic information is useful for mobile robot to take high level decisions based on meaning of text written on the board. In order to make robot to recognize the text contained in the natural scene images, the first step is to detect and extract the text from the image. In recent years, the automatic detection of texts from natural images has gained increasing attention due to its wide range of applications like content-based multimedia indexing and OCR; text information embedded in digital images is considered to be an important aspect of overall image understanding. Texts in natural scene images usually contains useful summarized information regarding the scene and if we are able to extract image objects accurately in real time we can design vision systems that aid the navigation of moving robots or the blinds [1]. Nonetheless, extracting text information from natural scene images has many challenging issues. Lots of efforts have been put on to address these challenges. The approaches [2] [5] developed for natural scene text detection and extraction are solely based on images captured using monocular camera. The researchers DOI: 03.AETS Association of Computer Electronics and Electrical Engineers, 2013

2 have attained high accuracy for text detection and extraction in natural scenes. However, these techniques cannot be adapted for robot applications and as per our knowledge no one has attempted to develop text detection and extraction technique meant for mobile robot applications. Therefore, in this paper, we proposed a technique to build text detection and segmentation vision system application for mobile robot. Outdoor images containing sign or advertisement boards, walls, sidewalks, roads, roofs and other objects like vehicles can appear planar when viewed from a distance. This has heavily drawn research for its detection and segmentation. Many researchers have used stereo disparity [6], [7] to design vision systems using stereo images in order to detect these objects by mobile robot. Putting this in mind a greater research area has been proposed to equip robots with applications embedded on stereo cameras that performs computational disparity map for the reconstruction of 3D images based on the 2D stereo images. The applications require accurate labeling of the scene [8] to perform high level decisions based on the image semantic information, and are mostly applicable to mobile robot localization. The Building Facade labelling model is proposed by Jeffrey A. D. et al [9], they introduce the concept of detecting, segmenting and finding parameter estimates in a bid to identify individual facades for localization and guidance of a robot. They sampled and cluster candidate planes with Random sample Consensus (RANSAC) using local normal estimates calculated from principal Component Analysis (PCA) to inform the planar model. Dongil H. et al [10], Presented an algorithm for real-time object segmentation of a noisy disparity map obtained with stereo matching algorithm. Jarson C. et al [8], Presented a plane tracking algorithm that maintained iteratively least square approximation of the plane parameters with sub-pixel accuracy based on stereo images. Extension to Boosting on Multi-level Aggregate (BMA) methods to incorporate features based on stereo images for building facade detection on mobile stereo vision platforms has been proposed by Jeffrey A. [11]. Their method incorporates BMA with an extension to working with disparity map and its associated features. Konolige et al [12] used stereo images to integrate appearance and disparity information for object avoidance and used AdaBoost to learn colour and geometry models for ideal routes of travel along the ground. The stereo information was used to detect the ground plane and distinguish it with obstacles, but, not for classification or labelling the objects. Luo et al. [13] used algebraic constraint on planar surfaces for the purpose of correcting disparity, and they relied upon the assumption that all urban scenes will be planes, so their geometric properties was used to enhance occlusion and poor disparity calculations. Li et al [14] proposed an AdaBoost template to recognize human upper body pose from disparity images for natural robot interaction with the advantage of performing both classification and segmentation. Walk et al [15], incorporated object specific features into a combination of classifiers for the detection of pedestrians by putting bounding boxes. We have proposed a method for detection and segmentation of candidate text blocks based on disparity map that will be incorporated to build vision systems that enables the robot to navigate with precision by identifying the name of places and finding surrounding information. Figure 1 is a workflow diagram of our proposed technique showing the major steps that we followed in order to achieve our goal of detecting and segmenting text blocks from stereo images. We have exploited the property that plane surfaces have constant gradient [11] to identify plane regions. The disparity map is computed in a bid to aid plane surface segmentation against those that do not constitute planes, this is done by computing directional gradient on the disparity map, those planar surfaces will have a constant gradient in both vertical and horizontal directions while the other non-planar surfaces does not have this property. The technique employs three major phases; First, Depth map, we generated disparity map using Region-based stereo matching algorithm by global error energy minimization. Second, plane detection using gradient images of disparity map to detect and identify plane surfaces. Third, Segmentation, we estimated a labelled field based on detected planes and connected component analysis result of homograph image. The paper is organized as follows; Section II, III and IV present our detailed proposed work. Section V provides the evaluation metrics and the experimental results, while Section VI concludes the paper with challenges and, an outlook on future work. II. CANDIDATE PLANE DETECTION We obtain stereo images using two similar configured cameras placed horizontally to each other and at a distance of 10 cm apart. We estimate the disparity map using Region-based stereo matching algorithm by global error energy minimization using captured stereo images, though our aim is not a full 3D 252

3 reconstruction. As we assume that outdoor scene text are contained in a single or multiple plane-like surfaces. Planar surfaces exhibit some properties when viewed from non-verged stereo cameras. Based on the work done by Jeffrey A. D. [11] to build facade features, we extract planar surfaces from the disparity map of the outdoor scene images. The disparity specific features intended to help discriminate between planar and non-planar pixels. By measuring the uniformity of the disparity gradient across an aggregate, we can separate the candidate planar surface, which may contain text block and background scene by the property that planar surfaces will have constant gradient [11] in disparity space. We compute the x gradient images of the disparity map by filtering with the directional derivative of a 1-D Gaussian distribution in the x-direction (similarly for y): (1) Left imagestereo Right imagestereo Disparity map Homograph image X-derivative Y-derivative CC Analysis Planar image Mapping Text/non-Text plane Classification Figure 1: Proposed system workflow (a) (b) (c) (d) Figure 2. (a) Left Image (b) Right Image (c) Filtered Disparity Image (d) Gradient Map III. EXTRACTING CONNECTED COMPONENTS We consider original input stereo images to generate projective homograph image using Random Sample Consensus (RANSAC) [16]. The Figure 3 (a) shows the generated homograph image for pair of stereo images shown in the Figure 2. We adopted the method in [17] to extract connected components from our generated projective homograph image in a bid to achieve robust extraction of text candidate blocks. The binarization is applied on a small colour image region and a searching is done to its neighbouring areas. An image binarization technique with a seed colour is conducted in the RGB colour space to classify the area into regions; those that have similar colours to the seed and to those others with different colours. The 253

4 binarization method can effectively separate scene text candidate blocks from complex background in the case that the text pixels have similar RGB colour values distinguishable from the background. Furthermore, it has a tendency to extract the text block regions as a single component even though the text colour varies smoothly due to the light reflection or uneven illumination. (a) (b) (c) Figure 3. (a) Homograph Image (b) Connected component Analysis (c) Binarization IV. SEGMENTATION OF CANDIDATE TEXT BLOCK From the Figure 2 (d), it is observed that the Gradient map of the disparity space shows the candidate planar surfaces, which may or may not contain text. The extraction of connected component analysis presented in section III, yields decomposition of the components in the scene. These components may belong to background and some of the components may be having planar property. We wanted to keep the components which are planar because we assume that text contain in planar surface. We discard non planar components by mapping the estimated components with the gradient map of the disparity map (Figure 2(d)). The Figure 4(a) shows the mapping of connected component analysis result with gradient map. The mapping detects the candidate planar surfaces. Based on the location of detected candidate surface planes, the candidate planar surfaces are segmented in the homograph image. The Figure 4(b) shows the segmented candidate planar surfaces in the homograph image. The image may contain more than one candidate planar surfaces. Therefore, segmented planes are further classified into text and non-text planes to detect planar surface which contain text area. The Figure 4(c) shows the detected textured planar surface. (a) (b) (c) Figure 4. (a) Mapping (b) Segmentation (c) Textured Image V. EXPERIMENTAL RESULTS We have performed an experiment using our own collected dataset taken from the outdoor scene. For the best of our knowledge this is the first work done for text detection and segmentation based on computed disparity map from stereo images. There has been no research work done using this technique and thus there is no bench mark stereo dataset for text detection is available. Our dataset consist of two pairs (Dataset#1, Dataset#2) of RGB stereo images taken from two cameras having the same calibration and are horizontally aligned with a distance of about 10cm apart. All the images are 360x200 resolutions and all these were used for testing. The images were taken only focusing on outdoor scene, where sign boards that contain text are available and are taken with a cameras positioned just perpendicular to the object of interest. We tested our results using this type of images and we were able to achieve outstanding results since the complex background consisting mainly trees and some other non-planar objects are evident. The experimental results obtained for Dataset#1 using proposed method is shown in the Figure 2, 3 and 4. The experimental results obtained for Dataset#2 is shown in the Figure

5 A. Evaluation Metrics We have adapted two metrics for the evaluation of the experimental results of proposed method for text block detection and segmentation. The evaluation metrics considered are Precision and Recall. The Precision is the fraction of detections that are positives where as Recall is the fraction of positives that are detected rather than missed. Ground truth results are obtained by marking the bounding box by hand which surround the entire text block on the stereo image data sets. Given the marked ground truth and detected result by the algorithm, we can automatically calculate the Recall and Precision. The precision and recall rates have been computed based on the area ratio r of the bounding box between ground truth and result of our algorithm as shown in Figure 6.. (a) (b) (c) (d) (e) (f) (g) (h) (i) (j) Figure 5. Results for Dataset#2: (a) Left Image (b) Right Image (c) Filtered Disparity Image (d) Gradient Map (e) Homograph Image (f) Connected component Analysis (g) Binarization, (h) Mapping (i) Segmentation and (j) Textured Image. Figure 6. Illustration of the overlap of a ground truth box and detected bounding box TABLE I. RESULTS ON RECALL, PRECISION AND F-MEASURE Dataset # Precision Recall f- measure Dataset # Dataset # B. Experimental Results and Discussion We have conducted experiments on some types of outdoor scene images shown above. Table 1 shows the recall, precision rates and f-measure for these outdoor images. The experimental results shows that, our algorithm has excellent performances in recall (R), precision (P), and f- measure. Among our experiments, the worst experimental result was due to domination of one colour over the others. The proposed method was implemented using MATLAB. Though, our method performed poorly with respect to computation time, for the outdoor stereo scene images on a PC with a 2.93 GHz core 2duo processor and 256MB memory. VI. CONCLUSIONS We have presented a method to localize and segment text blocks from the stereo images for mobile robot vision system applications. We computed the directional 1D gradient derivative on both x and y directions from the disparity space. Since the plane surfaces had constant gradients, regions that satisfy our target 255

6 features and later on classify textured and non-textured planes. We only used our own dataset obtained with two cameras having the same configuration and horizontally aligned with approximate distance of 10cm apart. Our test data was taken by positioning the cameras perpendicular to the object of interest making it easier to detect plane features because they will be at the same level on a disparity depth map. We achieve best results on a complex background as they are successfully removed due to depth levels and the fact that their gradient derivative was highly inconsistent. The main advantage for this technique is to build a vision system application for moving robot which is equipped with stereo cameras. The classification result to obtain textured planes is the input for the extraction algorithm to extract text from the localized text blocks. We propose to use standardized data in our next work to include all types of text orientations in order to achieve excellent results of the text candidate block in the scene images and as well improve the time it takes by incorporating faster algorithms. REFERENCES [1] Byun, H. R., Roh, M. C., Kim, K. C., Choi, Y. W., & Lee, S. W. (2002). Scene text extraction in complex images. In Document Analysis Systems V (pp ). Springer Berlin Heidelberg [2] N. Ezaki, M. Bulacu, and L. Schomaker. Text Detection from Natural Scene Images: Towards a System for Visually Impaired Persons. In International Conference on Pattern Recognition, pages , [3] B. Gatos, I. Pratikakis, K. Kepene, and S. Perantonis. Text detection in indoor/outdoor scene images. In Proc. First Workshop of Camera-based Document Analysis and Recognition, pages , [4] K. Kim, H. Byun, Y. Song, Y. Choi, S. Chi, K. Kim, and Y. Chung. Scene Text Extraction in Natural Scene Images Using Hierarchical Feature Combining and Verification. In Proceedings of the 17th International Conference on Pattern Recognition, volume 2, pages , [5] J. Park, H. Yoon, and G. Lee. Automatic Segmentation of Natural Scene Images Based on Chromatic and Achromatic Components. Lecture Notes In Computer Science, 4418:482, 2007 [6] K. Okada, S. Kagami, M. Inaba, and H. Inoue. Plane segment finder: algorithm, implementation and applications. In IEEE International Conference on Robotics and Automation, volume 2, pages vol.2, [7] E. Trucco, F. Isgro, and F. Bracchi. Plane detection in disparity space. In International Conference on Visual Information Engineering, pages 73 76, 2003 [8] Corso, Jason, Darius Burschka, and Gregory Hager. "Direct plane tracking in stereo images for mobile navigation." Robotics and Automation, Proceedings. ICRA'03. IEEE International Conference on. Vol. 1. IEEE, 2003 [9] Delmerico, Jeffrey A., Philip David, and Jason J. Corso. "Building facade detection, segmentation, and parameter estimation for mobile robot localization and guidance." Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on. IEEE, [10] Han, Dongil, et al. "Real-time object segmentation using disparity map of stereo matching." Applied Mathematics and Computation (2008): [11] Delmerico, Jeffrey A., Jason J. Corso, and Philip David. "Boosting with stereo features for building facade detection on mobile platforms." Image Processing Workshop (WNYIPW), 2010 Western New York. IEEE, 2010 [12] Konolige, K., Agrawal, M., Bolles, R. C., Cowan, C., Fischler, M., & Gerkey, B. (2008, January). Outdoor mapping and navigation using stereo vision. In Experimental Robotics (pp ). Springer Berlin Heidelberg [13] Luo, W., and H. Maitre. "Using surface model to correct and fit disparity data in stereo vision." Pattern Recognition, Proceedings., 10th International Conference on. Vol. 1. IEEE, [14] Li, Liyuan, et al. "Human upper body pose recognition using adaboost template for natural human robot interaction." Computer and Robot Vision (CRV), 2010 Canadian Conference on. IEEE, [15] D. Doermann, J. Liang, and H. Li. Progress in camera based document image analysis. In Document Analysis and Recognition, Proceedings. Seventh International Conference on, pages , 2003 [16] M. A. Fischler and R. C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Commun. ACM, vol. 24, no. 6, pp , [17] Kim, Egyul, SeongHun Lee, and JinHyung Kim. "Scene text extraction using focus of mobile camera." Document Analysis and Recognition, ICDAR'09. 10th International Conference on. IEEE,

Measurement of Pedestrian Groups Using Subtraction Stereo

Measurement of Pedestrian Groups Using Subtraction Stereo Measurement of Pedestrian Groups Using Subtraction Stereo Kenji Terabayashi, Yuki Hashimoto, and Kazunori Umeda Chuo University / CREST, JST, 1-13-27 Kasuga, Bunkyo-ku, Tokyo 112-8551, Japan terabayashi@mech.chuo-u.ac.jp

More information

Scene Text Detection Using Machine Learning Classifiers

Scene Text Detection Using Machine Learning Classifiers 601 Scene Text Detection Using Machine Learning Classifiers Nafla C.N. 1, Sneha K. 2, Divya K.P. 3 1 (Department of CSE, RCET, Akkikkvu, Thrissur) 2 (Department of CSE, RCET, Akkikkvu, Thrissur) 3 (Department

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES

URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES An Undergraduate Research Scholars Thesis by RUI LIU Submitted to Honors and Undergraduate Research Texas A&M University in partial fulfillment

More information

Bus Detection and recognition for visually impaired people

Bus Detection and recognition for visually impaired people Bus Detection and recognition for visually impaired people Hangrong Pan, Chucai Yi, and Yingli Tian The City College of New York The Graduate Center The City University of New York MAP4VIP Outline Motivation

More information

I. INTRODUCTION. Figure-1 Basic block of text analysis

I. INTRODUCTION. Figure-1 Basic block of text analysis ISSN: 2349-7637 (Online) (RHIMRJ) Research Paper Available online at: www.rhimrj.com Detection and Localization of Texts from Natural Scene Images: A Hybrid Approach Priyanka Muchhadiya Post Graduate Fellow,

More information

Text Detection in Indoor/Outdoor Scene Images

Text Detection in Indoor/Outdoor Scene Images Text Detection in Indoor/Outdoor Scene Images B. Gatos, I. Pratikakis, K. Kepene and S.J. Perantonis Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center

More information

Extraction of Scene Text in HSI Color Space using K-means Clustering with Chromatic and Intensity Distance

Extraction of Scene Text in HSI Color Space using K-means Clustering with Chromatic and Intensity Distance Extraction of Scene Text in HSI Color Space using K-means Clustering with Chromatic and Intensity Distance MATKO SARIC, MAJA STELLA, PETAR SOLIC Faculty of electrical engineering, mechanical engineering

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,

More information

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 17 (2014), pp. 1839-1845 International Research Publications House http://www. irphouse.com Recognition of

More information

Stereo-Based Obstacle Avoidance in Indoor Environments with Active Sensor Re-Calibration

Stereo-Based Obstacle Avoidance in Indoor Environments with Active Sensor Re-Calibration Stereo-Based Obstacle Avoidance in Indoor Environments with Active Sensor Re-Calibration Darius Burschka, Stephen Lee and Gregory Hager Computational Interaction and Robotics Laboratory Johns Hopkins University

More information

DEPTH AND GEOMETRY FROM A SINGLE 2D IMAGE USING TRIANGULATION

DEPTH AND GEOMETRY FROM A SINGLE 2D IMAGE USING TRIANGULATION 2012 IEEE International Conference on Multimedia and Expo Workshops DEPTH AND GEOMETRY FROM A SINGLE 2D IMAGE USING TRIANGULATION Yasir Salih and Aamir S. Malik, Senior Member IEEE Centre for Intelligent

More information

An ICA based Approach for Complex Color Scene Text Binarization

An ICA based Approach for Complex Color Scene Text Binarization An ICA based Approach for Complex Color Scene Text Binarization Siddharth Kherada IIIT-Hyderabad, India siddharth.kherada@research.iiit.ac.in Anoop M. Namboodiri IIIT-Hyderabad, India anoop@iiit.ac.in

More information

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points Tomohiro Nakai, Koichi Kise, Masakazu Iwamura Graduate School of Engineering, Osaka

More information

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai Traffic Sign Detection Via Graph-Based Ranking and Segmentation Algorithm C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT

More information

Calibration of a Different Field-of-view Stereo Camera System using an Embedded Checkerboard Pattern

Calibration of a Different Field-of-view Stereo Camera System using an Embedded Checkerboard Pattern Calibration of a Different Field-of-view Stereo Camera System using an Embedded Checkerboard Pattern Pathum Rathnayaka, Seung-Hae Baek and Soon-Yong Park School of Computer Science and Engineering, Kyungpook

More information

Robot localization method based on visual features and their geometric relationship

Robot localization method based on visual features and their geometric relationship , pp.46-50 http://dx.doi.org/10.14257/astl.2015.85.11 Robot localization method based on visual features and their geometric relationship Sangyun Lee 1, Changkyung Eem 2, and Hyunki Hong 3 1 Department

More information

Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques

Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques Partha Sarathi Giri Department of Electronics and Communication, M.E.M.S, Balasore, Odisha Abstract Text data

More information

Segmentation and Tracking of Partial Planar Templates

Segmentation and Tracking of Partial Planar Templates Segmentation and Tracking of Partial Planar Templates Abdelsalam Masoud William Hoff Colorado School of Mines Colorado School of Mines Golden, CO 800 Golden, CO 800 amasoud@mines.edu whoff@mines.edu Abstract

More information

Segmentation Framework for Multi-Oriented Text Detection and Recognition

Segmentation Framework for Multi-Oriented Text Detection and Recognition Segmentation Framework for Multi-Oriented Text Detection and Recognition Shashi Kant, Sini Shibu Department of Computer Science and Engineering, NRI-IIST, Bhopal Abstract - Here in this paper a new and

More information

Seminar Heidelberg University

Seminar Heidelberg University Seminar Heidelberg University Mobile Human Detection Systems Pedestrian Detection by Stereo Vision on Mobile Robots Philip Mayer Matrikelnummer: 3300646 Motivation Fig.1: Pedestrians Within Bounding Box

More information

From Orientation to Functional Modeling for Terrestrial and UAV Images

From Orientation to Functional Modeling for Terrestrial and UAV Images From Orientation to Functional Modeling for Terrestrial and UAV Images Helmut Mayer 1 Andreas Kuhn 1, Mario Michelini 1, William Nguatem 1, Martin Drauschke 2 and Heiko Hirschmüller 2 1 Visual Computing,

More information

Touch TT: Scene Text Extractor Using Touchscreen Interface

Touch TT: Scene Text Extractor Using Touchscreen Interface Touch TT: Scene Text Extractor Using Touchscreen Interface Jehyun Jung, SeongHun Lee, Min Su Cho, and Jin Hyung Kim In this paper, we present the Touch Text extractor (Touch TT), an interactive text segmentation

More information

Direct Plane Tracking in Stereo Images for Mobile Navigation

Direct Plane Tracking in Stereo Images for Mobile Navigation Direct Plane Tracking in Stereo Images for Mobile Navigation Jason Corso, Darius Burschka,Greg Hager Computational Interaction and Robotics Lab 1 Input: The Problem Stream of rectified stereo images, known

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

Vehicle Detection Method using Haar-like Feature on Real Time System

Vehicle Detection Method using Haar-like Feature on Real Time System Vehicle Detection Method using Haar-like Feature on Real Time System Sungji Han, Youngjoon Han and Hernsoo Hahn Abstract This paper presents a robust vehicle detection approach using Haar-like feature.

More information

Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki

Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki 2011 The MathWorks, Inc. 1 Today s Topics Introduction Computer Vision Feature-based registration Automatic image registration Object recognition/rotation

More information

Epipolar geometry-based ego-localization using an in-vehicle monocular camera

Epipolar geometry-based ego-localization using an in-vehicle monocular camera Epipolar geometry-based ego-localization using an in-vehicle monocular camera Haruya Kyutoku 1, Yasutomo Kawanishi 1, Daisuke Deguchi 1, Ichiro Ide 1, Hiroshi Murase 1 1 : Nagoya University, Japan E-mail:

More information

Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation

Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation ÖGAI Journal 24/1 11 Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation Michael Bleyer, Margrit Gelautz, Christoph Rhemann Vienna University of Technology

More information

DEVELOPMENT OF A ROBUST IMAGE MOSAICKING METHOD FOR SMALL UNMANNED AERIAL VEHICLE

DEVELOPMENT OF A ROBUST IMAGE MOSAICKING METHOD FOR SMALL UNMANNED AERIAL VEHICLE DEVELOPMENT OF A ROBUST IMAGE MOSAICKING METHOD FOR SMALL UNMANNED AERIAL VEHICLE J. Kim and T. Kim* Dept. of Geoinformatic Engineering, Inha University, Incheon, Korea- jikim3124@inha.edu, tezid@inha.ac.kr

More information

Human Detection. A state-of-the-art survey. Mohammad Dorgham. University of Hamburg

Human Detection. A state-of-the-art survey. Mohammad Dorgham. University of Hamburg Human Detection A state-of-the-art survey Mohammad Dorgham University of Hamburg Presentation outline Motivation Applications Overview of approaches (categorized) Approaches details References Motivation

More information

Monocular Vision Based Autonomous Navigation for Arbitrarily Shaped Urban Roads

Monocular Vision Based Autonomous Navigation for Arbitrarily Shaped Urban Roads Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August 14-15, 2014 Paper No. 127 Monocular Vision Based Autonomous Navigation for Arbitrarily

More information

DETECTION AND ROBUST ESTIMATION OF CYLINDER FEATURES IN POINT CLOUDS INTRODUCTION

DETECTION AND ROBUST ESTIMATION OF CYLINDER FEATURES IN POINT CLOUDS INTRODUCTION DETECTION AND ROBUST ESTIMATION OF CYLINDER FEATURES IN POINT CLOUDS Yun-Ting Su James Bethel Geomatics Engineering School of Civil Engineering Purdue University 550 Stadium Mall Drive, West Lafayette,

More information

Ensemble of Bayesian Filters for Loop Closure Detection

Ensemble of Bayesian Filters for Loop Closure Detection Ensemble of Bayesian Filters for Loop Closure Detection Mohammad Omar Salameh, Azizi Abdullah, Shahnorbanun Sahran Pattern Recognition Research Group Center for Artificial Intelligence Faculty of Information

More information

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009 Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

Efficient Acquisition of Human Existence Priors from Motion Trajectories

Efficient Acquisition of Human Existence Priors from Motion Trajectories Efficient Acquisition of Human Existence Priors from Motion Trajectories Hitoshi Habe Hidehito Nakagawa Masatsugu Kidode Graduate School of Information Science, Nara Institute of Science and Technology

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Extrinsic camera calibration method and its performance evaluation Jacek Komorowski 1 and Przemyslaw Rokita 2 arxiv:1809.11073v1 [cs.cv] 28 Sep 2018 1 Maria Curie Sklodowska University Lublin, Poland jacek.komorowski@gmail.com

More information

A Summary of Projective Geometry

A Summary of Projective Geometry A Summary of Projective Geometry Copyright 22 Acuity Technologies Inc. In the last years a unified approach to creating D models from multiple images has been developed by Beardsley[],Hartley[4,5,9],Torr[,6]

More information

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines 2011 International Conference on Document Analysis and Recognition Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines Toru Wakahara Kohei Kita

More information

CS 4758: Automated Semantic Mapping of Environment

CS 4758: Automated Semantic Mapping of Environment CS 4758: Automated Semantic Mapping of Environment Dongsu Lee, ECE, M.Eng., dl624@cornell.edu Aperahama Parangi, CS, 2013, alp75@cornell.edu Abstract The purpose of this project is to program an Erratic

More information

Practical Camera Auto-Calibration Based on Object Appearance and Motion for Traffic Scene Visual Surveillance

Practical Camera Auto-Calibration Based on Object Appearance and Motion for Traffic Scene Visual Surveillance Practical Camera Auto-Calibration Based on Object Appearance and Motion for Traffic Scene Visual Surveillance Zhaoxiang Zhang, Min Li, Kaiqi Huang and Tieniu Tan National Laboratory of Pattern Recognition,

More information

3D object recognition used by team robotto

3D object recognition used by team robotto 3D object recognition used by team robotto Workshop Juliane Hoebel February 1, 2016 Faculty of Computer Science, Otto-von-Guericke University Magdeburg Content 1. Introduction 2. Depth sensor 3. 3D object

More information

Optimizing Monocular Cues for Depth Estimation from Indoor Images

Optimizing Monocular Cues for Depth Estimation from Indoor Images Optimizing Monocular Cues for Depth Estimation from Indoor Images Aditya Venkatraman 1, Sheetal Mahadik 2 1, 2 Department of Electronics and Telecommunication, ST Francis Institute of Technology, Mumbai,

More information

Automatic Shadow Removal by Illuminance in HSV Color Space

Automatic Shadow Removal by Illuminance in HSV Color Space Computer Science and Information Technology 3(3): 70-75, 2015 DOI: 10.13189/csit.2015.030303 http://www.hrpub.org Automatic Shadow Removal by Illuminance in HSV Color Space Wenbo Huang 1, KyoungYeon Kim

More information

Data-driven Depth Inference from a Single Still Image

Data-driven Depth Inference from a Single Still Image Data-driven Depth Inference from a Single Still Image Kyunghee Kim Computer Science Department Stanford University kyunghee.kim@stanford.edu Abstract Given an indoor image, how to recover its depth information

More information

Self Lane Assignment Using Smart Mobile Camera For Intelligent GPS Navigation and Traffic Interpretation

Self Lane Assignment Using Smart Mobile Camera For Intelligent GPS Navigation and Traffic Interpretation For Intelligent GPS Navigation and Traffic Interpretation Tianshi Gao Stanford University tianshig@stanford.edu 1. Introduction Imagine that you are driving on the highway at 70 mph and trying to figure

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

Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video

Vehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video Workshop on Vehicle Retrieval in Surveillance (VRS) in conjunction with 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance Vehicle Dimensions Estimation Scheme Using

More information

Computing the relations among three views based on artificial neural network

Computing the relations among three views based on artificial neural network Computing the relations among three views based on artificial neural network Ying Kin Yu Kin Hong Wong Siu Hang Or Department of Computer Science and Engineering The Chinese University of Hong Kong E-mail:

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

More information

Restoring Warped Document Image Based on Text Line Correction

Restoring Warped Document Image Based on Text Line Correction Restoring Warped Document Image Based on Text Line Correction * Dep. of Electrical Engineering Tamkang University, New Taipei, Taiwan, R.O.C *Correspondending Author: hsieh@ee.tku.edu.tw Abstract Document

More information

Face Alignment Under Various Poses and Expressions

Face Alignment Under Various Poses and Expressions Face Alignment Under Various Poses and Expressions Shengjun Xin and Haizhou Ai Computer Science and Technology Department, Tsinghua University, Beijing 100084, China ahz@mail.tsinghua.edu.cn Abstract.

More information

Estimating Camera Position And Posture by Using Feature Landmark Database

Estimating Camera Position And Posture by Using Feature Landmark Database Estimating Camera Position And Posture by Using Feature Landmark Database Motoko Oe 1, Tomokazu Sato 2 and Naokazu Yokoya 2 1 IBM Japan 2 Nara Institute of Science and Technology, Japan Abstract. Estimating

More information

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Anil K Goswami 1, Swati Sharma 2, Praveen Kumar 3 1 DRDO, New Delhi, India 2 PDM College of Engineering for

More information

Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments

Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments Proc. 2001 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems pp. 31-36, Maui, Hawaii, Oct./Nov. 2001. Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments Hiroshi

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision

Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision What Happened Last Time? Human 3D perception (3D cinema) Computational stereo Intuitive explanation of what is meant by disparity Stereo matching

More information

Automated Super-Voxel Based Features Classification of Urban Environments by Integrating 3D Point Cloud and Image Content

Automated Super-Voxel Based Features Classification of Urban Environments by Integrating 3D Point Cloud and Image Content Automated Super-Voxel Based Features Classification of Urban Environments by Integrating 3D Point Cloud and Image Content Pouria Babahajiani #1, Lixin Fan *2, Joni Kamarainen #3, Moncef Gabbouj #4 # Department

More information

Multiple View Geometry

Multiple View Geometry Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric

More information

ROBUST LINE-BASED CALIBRATION OF LENS DISTORTION FROM A SINGLE VIEW

ROBUST LINE-BASED CALIBRATION OF LENS DISTORTION FROM A SINGLE VIEW ROBUST LINE-BASED CALIBRATION OF LENS DISTORTION FROM A SINGLE VIEW Thorsten Thormählen, Hellward Broszio, Ingolf Wassermann thormae@tnt.uni-hannover.de University of Hannover, Information Technology Laboratory,

More information

Research on an Adaptive Terrain Reconstruction of Sequence Images in Deep Space Exploration

Research on an Adaptive Terrain Reconstruction of Sequence Images in Deep Space Exploration , pp.33-41 http://dx.doi.org/10.14257/astl.2014.52.07 Research on an Adaptive Terrain Reconstruction of Sequence Images in Deep Space Exploration Wang Wei, Zhao Wenbin, Zhao Zhengxu School of Information

More information

CS 223B Computer Vision Problem Set 3

CS 223B Computer Vision Problem Set 3 CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.

More information

AN EFFICIENT BINARY CORNER DETECTOR. P. Saeedi, P. Lawrence and D. Lowe

AN EFFICIENT BINARY CORNER DETECTOR. P. Saeedi, P. Lawrence and D. Lowe AN EFFICIENT BINARY CORNER DETECTOR P. Saeedi, P. Lawrence and D. Lowe Department of Electrical and Computer Engineering, Department of Computer Science University of British Columbia Vancouver, BC, V6T

More information

On Road Vehicle Detection using Shadows

On Road Vehicle Detection using Shadows On Road Vehicle Detection using Shadows Gilad Buchman Grasp Lab, Department of Computer and Information Science School of Engineering University of Pennsylvania, Philadelphia, PA buchmag@seas.upenn.edu

More information

Accurate Motion Estimation and High-Precision 3D Reconstruction by Sensor Fusion

Accurate Motion Estimation and High-Precision 3D Reconstruction by Sensor Fusion 007 IEEE International Conference on Robotics and Automation Roma, Italy, 0-4 April 007 FrE5. Accurate Motion Estimation and High-Precision D Reconstruction by Sensor Fusion Yunsu Bok, Youngbae Hwang,

More information

A Survey of Light Source Detection Methods

A Survey of Light Source Detection Methods A Survey of Light Source Detection Methods Nathan Funk University of Alberta Mini-Project for CMPUT 603 November 30, 2003 Abstract This paper provides an overview of the most prominent techniques for light

More information

Manhattan-World Assumption for As-built Modeling Industrial Plant

Manhattan-World Assumption for As-built Modeling Industrial Plant Manhattan-World Assumption for As-built Modeling Industrial Plant Tomohiro Mizoguchi 1, Tomokazu Kuma 2, Yoshikazu Kobayashi 3 and Kenji Shirai 4 Department of Computer Science, College of Engineering,

More information

Connected Component Clustering Based Text Detection with Structure Based Partition and Grouping

Connected Component Clustering Based Text Detection with Structure Based Partition and Grouping IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 5, Ver. III (Sep Oct. 2014), PP 50-56 Connected Component Clustering Based Text Detection with Structure

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

An Image Based Approach to Compute Object Distance

An Image Based Approach to Compute Object Distance An Image Based Approach to Compute Object Distance Ashfaqur Rahman * Department of Computer Science, American International University Bangladesh Dhaka 1213, Bangladesh Abdus Salam, Mahfuzul Islam, and

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

CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning

CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning Justin Chen Stanford University justinkchen@stanford.edu Abstract This paper focuses on experimenting with

More information

Building Facade Detection, Segmentation, and Parameter Estimation for Mobile Robot Stereo Vision

Building Facade Detection, Segmentation, and Parameter Estimation for Mobile Robot Stereo Vision Building Facade Detection, Segmentation, and Parameter Estimation for Mobile Robot Stereo Vision Jeffrey A. Delmerico 1a, Philip David b, Jason J. Corso a a SUNY Buffalo, Department of Computer Science

More information

A Robust Two Feature Points Based Depth Estimation Method 1)

A Robust Two Feature Points Based Depth Estimation Method 1) Vol.31, No.5 ACTA AUTOMATICA SINICA September, 2005 A Robust Two Feature Points Based Depth Estimation Method 1) ZHONG Zhi-Guang YI Jian-Qiang ZHAO Dong-Bin (Laboratory of Complex Systems and Intelligence

More information

Recognition of Object Contours from Stereo Images: an Edge Combination Approach

Recognition of Object Contours from Stereo Images: an Edge Combination Approach Recognition of Object Contours from Stereo Images: an Edge Combination Approach Margrit Gelautz and Danijela Markovic Institute for Software Technology and Interactive Systems, Vienna University of Technology

More information

Proc. 14th Int. Conf. on Intelligent Autonomous Systems (IAS-14), 2016

Proc. 14th Int. Conf. on Intelligent Autonomous Systems (IAS-14), 2016 Proc. 14th Int. Conf. on Intelligent Autonomous Systems (IAS-14), 2016 Outdoor Robot Navigation Based on View-based Global Localization and Local Navigation Yohei Inoue, Jun Miura, and Shuji Oishi Department

More information

Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization

Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization Journal of Computer Science 6 (9): 1008-1013, 2010 ISSN 1549-3636 2010 Science Publications Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization

More information

Visualization 2D-to-3D Photo Rendering for 3D Displays

Visualization 2D-to-3D Photo Rendering for 3D Displays Visualization 2D-to-3D Photo Rendering for 3D Displays Sumit K Chauhan 1, Divyesh R Bajpai 2, Vatsal H Shah 3 1 Information Technology, Birla Vishvakarma mahavidhyalaya,sumitskc51@gmail.com 2 Information

More information

Viewpoint Invariant Features from Single Images Using 3D Geometry

Viewpoint Invariant Features from Single Images Using 3D Geometry Viewpoint Invariant Features from Single Images Using 3D Geometry Yanpeng Cao and John McDonald Department of Computer Science National University of Ireland, Maynooth, Ireland {y.cao,johnmcd}@cs.nuim.ie

More information

FAST HUMAN DETECTION USING TEMPLATE MATCHING FOR GRADIENT IMAGES AND ASC DESCRIPTORS BASED ON SUBTRACTION STEREO

FAST HUMAN DETECTION USING TEMPLATE MATCHING FOR GRADIENT IMAGES AND ASC DESCRIPTORS BASED ON SUBTRACTION STEREO FAST HUMAN DETECTION USING TEMPLATE MATCHING FOR GRADIENT IMAGES AND ASC DESCRIPTORS BASED ON SUBTRACTION STEREO Makoto Arie, Masatoshi Shibata, Kenji Terabayashi, Alessandro Moro and Kazunori Umeda Course

More information

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,

More information

Real-time target tracking using a Pan and Tilt platform

Real-time target tracking using a Pan and Tilt platform Real-time target tracking using a Pan and Tilt platform Moulay A. Akhloufi Abstract In recent years, we see an increase of interest for efficient tracking systems in surveillance applications. Many of

More information

THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM

THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM Kuo-Hsin Tu ( 塗國星 ), Chiou-Shann Fuh ( 傅楸善 ) Dept. of Computer Science and Information Engineering, National Taiwan University, Taiwan E-mail: p04922004@csie.ntu.edu.tw,

More information

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM Karthik Krish Stuart Heinrich Wesley E. Snyder Halil Cakir Siamak Khorram North Carolina State University Raleigh, 27695 kkrish@ncsu.edu sbheinri@ncsu.edu

More information

IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS. Kirthiga, M.E-Communication system, PREC, Thanjavur

IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS. Kirthiga, M.E-Communication system, PREC, Thanjavur IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS Kirthiga, M.E-Communication system, PREC, Thanjavur R.Kannan,Assistant professor,prec Abstract: Face Recognition is important

More information

Sensor Fusion-Based Parking Assist System

Sensor Fusion-Based Parking Assist System Sensor Fusion-Based Parking Assist System 2014-01-0327 Jaeseob Choi, Eugene Chang, Daejoong Yoon, and Seongsook Ryu Hyundai & Kia Corp. Hogi Jung and Jaekyu Suhr Hanyang Univ. Published 04/01/2014 CITATION:

More information

Human Motion Detection and Tracking for Video Surveillance

Human Motion Detection and Tracking for Video Surveillance Human Motion Detection and Tracking for Video Surveillance Prithviraj Banerjee and Somnath Sengupta Department of Electronics and Electrical Communication Engineering Indian Institute of Technology, Kharagpur,

More information

A novel point matching method for stereovision measurement using RANSAC affine transformation

A novel point matching method for stereovision measurement using RANSAC affine transformation A novel point matching method for stereovision measurement using RANSAC affine transformation Naiguang Lu, Peng Sun, Wenyi Deng, Lianqing Zhu, Xiaoping Lou School of Optoelectronic Information & Telecommunication

More information

LIGHT STRIPE PROJECTION-BASED PEDESTRIAN DETECTION DURING AUTOMATIC PARKING OPERATION

LIGHT STRIPE PROJECTION-BASED PEDESTRIAN DETECTION DURING AUTOMATIC PARKING OPERATION F2008-08-099 LIGHT STRIPE PROJECTION-BASED PEDESTRIAN DETECTION DURING AUTOMATIC PARKING OPERATION 1 Jung, Ho Gi*, 1 Kim, Dong Suk, 1 Kang, Hyoung Jin, 2 Kim, Jaihie 1 MANDO Corporation, Republic of Korea,

More information

Homographies and RANSAC

Homographies and RANSAC Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position

More information

CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep

CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships

More information

Unique Journal of Engineering and Advanced Sciences Available online: Research Article

Unique Journal of Engineering and Advanced Sciences Available online:  Research Article ISSN 2348-375X Unique Journal of Engineering and Advanced Sciences Available online: www.ujconline.net Research Article DETECTION AND RECOGNITION OF THE TEXT THROUGH CONNECTED COMPONENT CLUSTERING AND

More information

Color Structure Recovering in Strong Specular Text Regions

Color Structure Recovering in Strong Specular Text Regions Color Structure Recovering in Strong Specular Text Regions Tam Nguyen Saigon Technology University tam.nguyenthi@stu.edu.vn GueeSang Lee Chonnam National University Gwangju, Korea, 500-757 gslee@jnu.ac.kr

More information

Fingertips Tracking based on Gradient Vector

Fingertips Tracking based on Gradient Vector Int. J. Advance Soft Compu. Appl, Vol. 7, No. 3, November 2015 ISSN 2074-8523 Fingertips Tracking based on Gradient Vector Ahmad Yahya Dawod 1, Md Jan Nordin 1, and Junaidi Abdullah 2 1 Pattern Recognition

More information

2 OVERVIEW OF RELATED WORK

2 OVERVIEW OF RELATED WORK Utsushi SAKAI Jun OGATA This paper presents a pedestrian detection system based on the fusion of sensors for LIDAR and convolutional neural network based image classification. By using LIDAR our method

More information

CS 231A Computer Vision (Fall 2012) Problem Set 3

CS 231A Computer Vision (Fall 2012) Problem Set 3 CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest

More information

Organized Segmenta.on

Organized Segmenta.on Organized Segmenta.on Alex Trevor, Georgia Ins.tute of Technology PCL TUTORIAL @ICRA 13 Overview Mo.va.on Connected Component Algorithm Planar Segmenta.on & Refinement Euclidean Clustering Timing Results

More information

Direct Methods in Visual Odometry

Direct Methods in Visual Odometry Direct Methods in Visual Odometry July 24, 2017 Direct Methods in Visual Odometry July 24, 2017 1 / 47 Motivation for using Visual Odometry Wheel odometry is affected by wheel slip More accurate compared

More information

Three-Dimensional Computer Vision

Three-Dimensional Computer Vision \bshiaki Shirai Three-Dimensional Computer Vision With 313 Figures ' Springer-Verlag Berlin Heidelberg New York London Paris Tokyo Table of Contents 1 Introduction 1 1.1 Three-Dimensional Computer Vision

More information