Robust Model-Based Detection of Gable Roofs in Very-High-Resolution Aerial Images

Size: px
Start display at page:

Download "Robust Model-Based Detection of Gable Roofs in Very-High-Resolution Aerial Images"

Transcription

1 Robust Model-Based Detection of Gable Roofs in Very-High-Resolution Aerial Images Lykele Hazelhoff 1,2 and Peter H.N. de With 2 1 CycloMedia Technology B.V., The Netherlands lhazelhoff@cyclomedia.com 2 Eindhoven University of Technology, The Netherlands p.h.n.de.with@tue.nl Abstract. This paper describes an improved version of our system for robust detection of buildings with a gable roof in varying rural areas from very-high-resolution aerial images. The algorithm follows a custom-made design, extracting key features close to modeling, such as roof ridges and gutters, in order to allow a large freedom in roof appearances. It starts by detecting straight line-segments as roof-ridge hypotheses, and for each of them, the likely roof-gutter positions are estimated. Supervised classification is employed to select the optimal gutter pair and to reject unlikely detections. Afterwards, overlapping detections are merged. Experiments on a large dataset containing 220 images, covering different rural regions with significant variation in both building appearance and surroundings, show that the system is able to detect over 87% of the present buildings, thereby handling common distortions, such as occlusions by trees. Keywords: Building detection, Object detection, Remote sensing. 1 Introduction Very-high-resolution aerial images are captured from The Netherlands at a yearly basis, providing a recent overview of the country infrastructure. Updating of civil community databases based on aerial images is time consuming when performed manually, leading to a demand for automated interpretation of these images. This is of particular interest in rural areas, since these cover a widespread area together with a low population density, increasing the cost per citizen. Since buildings are dominant features in those images, accurate extraction of their locations is important. However, accurate and large-scale detection of buildings in aerial images is a complicated problem, since buildings vary considerably in appearance, may feature complex compositions and occlusions by trees occur frequently. Besides this, large variations also exist in the source data due to varying capturing conditions, illumination circumstances and sensor differences. This causes large variations in both visual appearance and statistical properties. Therefore, development of a building-detection solution that is able to handle these issues is a rather complicated problem. A. Berciano et al. (Eds.): CAIP 2011, LNCS 6854, pp , c Springer-Verlag Berlin Heidelberg 2011

2 Robust Model-Based Detection of Gable Roofs 599 In literature, localization of buildings in remote sensing data is researched for decades, based on many different types of source data, including satellite and aerial images, lidar data, etc. As the information content of these sources varies from 2D grayscale images to 3D structural information, the proposals vary from building localization to automatic 3D city reconstruction. However, our country-covering datasets only contain color aerial images, disabling the use of any 3D information. Relevant proposals in literature for detection of buildings in single color images are e.g. based on image segmentation [1]. There, the input image is segmented using a range of parameters, resulting in multi-layer segmented images. This is analyzed with a tree structure by means of rooftop constraints. Potential buildings are evaluated relying on shadow information and a fixed height. Other strategies include searching of closed loops [2]. In this work, after mean-shift segmentation, edge pixels that form closed loops are converted into polygons. These polygons are used to deduce the building shape. Nosrati et al. [3] apply dynamic programming to line intersections for searching of closed loops. Both rely on the visibility of the outer edges, which possibly disables detection of buildings in low-contrast situations. A combination of multiple information sources is followed by Jin et al. [4], where three different detectors, focusing at structural, contextual and spectral information, are applied for localization of buildings in high-resolution satellite images. They report a significant increase in detection performance by combining these detectors. Benedek et al. [5] apply a probabilistic approach for building extraction, where building footprints are represented by combinations of rectangular segments. The optimal building configuration is retrieved based on a global optimization process. Although many proposals report accurate results, the test data is often limited in both numbers and in-set variety. In contrast, we focus on robustness to the above-described variations, and we have described a novel, specific algorithm for localization of buildings with a gable roof in rural areas [6]. Whereas we aim at applying the algorithm at a large-scale database, we have designed the algorithm for robustness against both variations in building appearance, variations in the source data and commonly occurring distortions, such as overhanging trees. These constraints have guided us to design a more generic system, aiming at an high overall score, instead of a very high score in a specific situation, which is a different approach compared to many proposals in literature. In this paper, we describe an improved version of the original algorithm, which still operates under the above-mentioned conditions. Next to this, we will also present new and more accurate results obtained with this system, where we used an extended version of our test set, now containing more images and captured in three different years. 2 Algorithm Description 2.1 Preprocessing Figure 1 portrays the schematic overview of our algorithm, based on [6]. Prior to image analysis, the image is segmented using a region-segmentation procedure similar to [7]. Vegetated and large, uniform farmland areas are then

3 600 L. Hazelhoff and P.H.N. de With Fig. 1. Schematic overview of our building detection system discarded using vegetation detection and a minimum size constraint of 500 m 2. Pixels (represented by RGB values) are marked as vegetation when they satisfy the following empirically determined rule: G min (1.175 B,0.975 R). (1)

4 2.2 Roof-Ridge Hypothesis Generation Robust Model-Based Detection of Gable Roofs 601 Within the accepted regions of interest, hypotheses of occurring roof ridges are generated by detection of straight line segments. For this, a Canny edge detector is applied on a single-channel version O of the input RGB image, where the employed color transformation is chosen such that clear transitions are expected along roof ridges. Since roofs are usually either red or gray, and often contain a shadowed roof side, the following transformation is selected: O =0.5 (R + B). (2) Connected edge pixels forming straight lines are extracted based on a technique described in [8], resulting in a set of line pieces. To enable by-passing of lineinterrupting objects, like chimneys, individual line pieces having a position and orientation such that they jointly form a straight line are combined when they are located near the same region segment. 2.3 Roof Gutter Position Estimation For all hypotheses of occurring roof ridges, the set of likely roof-gutter positions is estimated for both sides of the ridge. This results in a set of hypotheses of the roof configuration, given by each combination of gutter positions at both ridge sides, as displayed in Box 3 Fig. 1. To identify the likely gutter positions, two rectangular regions located parallel to the ridge are analyzed, where the region size is inferred from training data. For ease of description, we assume that the ridge is oriented vertically. Within the regions, vertical Sobel filters are applied to both the red and blue color channels, since roofs are usually red or gray. Per color channel and for each column, the resulting edge energy is sorted by magnitude, and divided into 4 groups, each containing the sum of the represented 25% of the pixels. The resulting signal matrix ES containing 8 features per column i is represented with a Gaussian model. This model is trained from the first 10 columns, i.e. the columns closest to the roof ridge. The distance towards the center of the ellipsoid is calculated, which is proportional to: D (ES (i)) e 1 2([ES(i) µ ES ] T C 1 ES [ES(i) µ ES ]), (3) where µ ES and C ES denote the mean and covariance matrix extracted from the 10 training samples. Column i with D (ES (i)) satifying (1) local maximality, (2) higher than twice the running average, and (3) larger than 66% of the running maximum, is identified as roof-gutter position. 2.4 Roof Analysis Each roof-configuration hypothesis is validated, where at first infeasible candidates are rejected, and second, machine learning is employed to classify each remaining configuration between roof half and non roof-half. This results in a

5 602 L. Hazelhoff and P.H.N. de With likelihood value for each configuration, used to select the optimal roof configuration for each ridge hypothesis and to discard low-valued detections. The first step aims at rejecting very unlikely configurations by checking a number of loose constraints on size, aspect ratio, shadow profile and vegetation coverage. This step exploits physical properties of gable roofs, and is described in detail [6]. All remaining configurations are subject to classification based on supervised classification. For each of both roof halves, the following features are extracted. 1. Roof-Gutter Edge Orientation Histogram: a gradient orientation histogram is extracted along the gutters, indicating the deviation in orientation w.r.t. the ridge orientation. This histogram contains 6 bins representing 15 each. 2. Segmentation Features: The five largest clusters covering each roof half are expressed as a percentage of the total amount of roof-half pixels. 3. Color Similarity Histogram: patch-based similarity analysis is employed to investigate roof similarities. For each patch, the most similar patch is searched (with a minimum distance constraint), and after sorting, the values for which 20%, 40%, etc. of the pixels are lower, are extracted. Next to these features, also the ridge length, aspect ratio and ratio of roof-half widths are extracted. The total feature vector consists of 51 features, containing the 3 global features, 2 16 features for each roof half, appended by their sum. Note that during the training phase, we have also included the samples with reversed roof halves. Classification is performed using a Support Vector Machine (SVM) with radial basis function kernel, which outputs the distance towards the decision bound, as a kind of likelihood information. For each ridge hypothesis, the configuration with the highest value is selected as optimal configuration, while configurations with a low SVM output value are discarded. 2.5 Detection Merging Each physical roof may contain several detections, where at most one detection corresponds to the actual roof ridge, as shown in Box 5 in Fig. 1. Therefore, overlapping detections are fused using supervised classification, where we have found that multiple classifiers rejecting detections in specific situations outperform a single, large classifier. As a result, we have installed multiple linear SVM classifiers, each of them set up to analyze a specific situation. These situations include differences in red profile, compliance with the expected shadow profile, detections with complete overlap, etc. For each situation, we extract relevant features, and append this by features representing the differences in likelihood, length and angle between the ridges. The continuous output of each classifier is subject to a threshold such that at most 0.5% of the positive training samples are rejected. This threshold setting gives a trade-off between detections and false alarms. Note that each classifier fuses a small fraction of the overlapping detections. In some cases, the optimal fusion process does not satisfy our generic principles, so that not all overlapping detections are fused. Even then, the amount of detections is reduced significantly.

6 3 Experiments and Results 3.1 Dataset Description and Test Setup Robust Model-Based Detection of Gable Roofs 603 The algorithm is tested on 220 ortho-rectified aerial images, captured in 2008, 2009 and 2010 during spring and fall time. All images are normalized such that each pixel corresponds to 0.1 m on the ground plane. The set contains 1, 523 buildings, including houses, garages, barns and small sheds, which are all marked manually for evaluation purposes. The set is randomly divided in two equal parts, denoted as SetA and SetB, where for each test, the other set is used for training. The performance of our system is analyzed in two ways. First, we have evaluated the detection accuracy of the system, i.e. how accurate our algorithm indicates the presence of a gable roof. Second, we have analyzed the accuracy of the estimated building dimensions, i.e. how well the algorithm indicates the building size. These two aspects are separated since we concentrate on detection of buildings, where we consider the size estimate as a byproduct. The detection performance is assessed using the following metrics: Recall: R = TP TP+FN 100%, Precision: P = TP TP+FP 100%. We count a detection as a True Positive (detected building) when it overlaps the roof ridge for at least 51%, all other detections are treated as False Positives (falsely detected buildings). Since we aim at localizing the somewhat larger buildings in rural areas, we have neglected buildings smaller than 5 3 meters based on a minimum roof-ridge length and building width. These minimum sizes are chosen such that typical side-buildings, like e.g. garages, are still detected. 3.2 Results The recall-precision curves for both sets are shown in Fig. 2. As follows from this graph, our system is capable of detecting over 87% of the target buildings, where for a detection rate of 80%, around 77% of the detections are correct. For this specific working point, we have analyzed the performance in more detail. Buildings are missed due to large occlusions by trees, or shadows from trees on the roof. We have already reported in [6] that about 15% of the buildings are covered by trees to a certain extent, where we add that about 2% of the buildings have at least one roof half covered completely by trees (as in e.g. Fig. 3(h)). In numerous cases, we still find a detection on the outer building border, but these are counted as false detections. Other causes of misdetections are e.g. low-contrast roof ridges, which especially occur at completely black roofs. Such special cases may be handled by additional detectors, as e.g. applied in [4]. False detections are mainly located at the outer building borders of missed buildings and on gable-roof-like objects, including road segments. For both categories, the SVM output is relative low, but not smaller than some detected buildings. Fig. 3 displays some examples of correct detections, false detections and missed buildings; more examples can be found on our website 1.

7 604 L. Hazelhoff and P.H.N. de With % of correct detections % of buildings detected Set A Set B Fig. 2. Recall-precision curve for our system, shown for both seta and setb (a) (b) (c) (d) (e) (f) (g) (h) Fig. 3. Examples of correct detections (a)-(d), false detection (e)-(f) and missed building (f)-(h). The estimated ridge positions are drawn green (TP), yellow (FP) or red (FN); corresponding gutter positions are drawn dotted white. We have also assessed the modeling capabilities of our algorithm by comparing the estimated length and width against the ground-truth dimensions. The found roof ridge is often smaller than the real roof length, due to chimneys and roofs where the ridge ends in a triangular shape, as in e.g. Fig. 3(d). The main cause for inaccurately found building widths are low-contrast gutters. Quantitatively, 80.2% of the detected ridges deviate less than 10% from the ground-truth length, 83.7% of the estimated widths deviate less than 10% and 61.8% of the detections have an area deviation smaller than 10%. We consider this as a reason- 1 See

8 Robust Model-Based Detection of Gable Roofs 605 ably accurate result as our system is primarily targeting at localizing buildings with a diverse test set, where numerous buildings are overlapped by trees. 4 Conclusions and Future Work We have presented an improved version of our algorithm for detection of gable roofs in very-high-resolution aerial images, focusing on rural areas. Our system aims at detecting buildings with a high robustness in a generic way, and is therefore designed with special attention to the large existing variations in both building appearance and source data. This deviates from the common practice to pursue high scores in a specific number of cases. A specific novel aspect of our algorithm is the example-based detection-merging step, based on multiple linear SVM classifiers. Tests on a diverse dataset, containing numerous geographical locations, have shown that our system is able to localize over 87% of the buildings larger than 5 3 m, where for a recall of 80%, a precision of around 77% is obtained. The reported system is able to detect around 8% more buildings than our previously described system. Considering that our test set contains large variations in both source data and target objects, and no height information is incorporated in the detection process, we consider this as an accurate result. Improvement of the modeling capabilities is part of our future work. References 1. Izadi, M., Saeed, P.: Automatic building detection in aerial images using a hierarchical feature based image segmentation. In: 20th International Conference on Pattern Recognition, pp (2010) 2. Ok, A.O.: Automated description of 2-d building boundaries from a single color aerial ortho-image. In: Proceedings of ISPRS, High Res. Earth Imag. for Geospat. Inf., pp (2009) 3. Nosrati, M.S., Saeedi, P.: A novel approach for polygonal rooftop detection in satellite/aerial imageries. In: Int. Conf. on Image Processing (ICIP), pp (2009) 4. Jin, X., Davis, C.H.: Automated building extraction from high-resolution satellite imagery in urban areas using structural, contextual, and spectral information. EURASIP Journal on Applied Signal Processing, (2005) 5. Benedek, C., Descombes, X., Zerubia, J.: Building detection in a single remotely sensed image with a point process of rectangles. In: 20th International Conference on Pattern Recognition (2010) 6. Hazelhoff, L., De With, P.: Localizations of buildings with a gable roof in very-highresolution aerial images. In: Proceedings of IS&T SIE Electronic Imaging, Visual Information Processing and Communication II (2011) 7. Comanicu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, (2002) 8. Guru, D.S., Shekar, B.H., Nagabhushan, P.: A simple and robust line detection algorithm based on small eigenvalue analysis. Pattern Recognition Letters 25, 1 13 (2004)

Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey

Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey Evangelos MALTEZOS, Charalabos IOANNIDIS, Anastasios DOULAMIS and Nikolaos DOULAMIS Laboratory of Photogrammetry, School of Rural

More information

Detection of Rooftop Regions in Rural Areas Using Support Vector Machine

Detection of Rooftop Regions in Rural Areas Using Support Vector Machine 549 Detection of Rooftop Regions in Rural Areas Using Support Vector Machine Liya Joseph 1, Laya Devadas 2 1 (M Tech Scholar, Department of Computer Science, College of Engineering Munnar, Kerala) 2 (Associate

More information

AUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY S ORTHOGONAL AND OBLIQUE IMAGES

AUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY S ORTHOGONAL AND OBLIQUE IMAGES AUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY S ORTHOGONAL AND OBLIQUE IMAGES Yandong Wang Pictometry International Corp. Suite A, 100 Town Centre Dr., Rochester, NY14623, the United States yandong.wang@pictometry.com

More information

IMPROVING 2D CHANGE DETECTION BY USING AVAILABLE 3D DATA

IMPROVING 2D CHANGE DETECTION BY USING AVAILABLE 3D DATA IMPROVING 2D CHANGE DETECTION BY USING AVAILABLE 3D DATA C.J. van der Sande a, *, M. Zanoni b, B.G.H. Gorte a a Optical and Laser Remote Sensing, Department of Earth Observation and Space systems, Delft

More information

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html

More information

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification DIGITAL IMAGE ANALYSIS Image Classification: Object-based Classification Image classification Quantitative analysis used to automate the identification of features Spectral pattern recognition Unsupervised

More information

Logical Templates for Feature Extraction in Fingerprint Images

Logical Templates for Feature Extraction in Fingerprint Images Logical Templates for Feature Extraction in Fingerprint Images Bir Bhanu, Michael Boshra and Xuejun Tan Center for Research in Intelligent Systems University of Califomia, Riverside, CA 9252 1, USA Email:

More information

Lab 9. Julia Janicki. Introduction

Lab 9. Julia Janicki. Introduction Lab 9 Julia Janicki Introduction My goal for this project is to map a general land cover in the area of Alexandria in Egypt using supervised classification, specifically the Maximum Likelihood and Support

More information

Building Extraction from Satellite Images

Building Extraction from Satellite Images IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 12, Issue 2 (May. - Jun. 2013), PP 76-81 Building Extraction from Satellite Images A.S. Bhadauria, H.S. Bhadauria,

More information

Figure 1: Workflow of object-based classification

Figure 1: Workflow of object-based classification Technical Specifications Object Analyst Object Analyst is an add-on package for Geomatica that provides tools for segmentation, classification, and feature extraction. Object Analyst includes an all-in-one

More information

Using Structural Features to Detect Buildings in Panchromatic Satellite Images

Using Structural Features to Detect Buildings in Panchromatic Satellite Images Using Structural Features to Detect Buildings in Panchromatic Satellite Images Beril Sırmaçek German Aerospace Center (DLR) Remote Sensing Technology Institute Weßling, 82234, Germany E-mail: Beril.Sirmacek@dlr.de

More information

Textural Features for Image Database Retrieval

Textural Features for Image Database Retrieval Textural Features for Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington Seattle, WA 98195-2500 {aksoy,haralick}@@isl.ee.washington.edu

More information

Automatic generation of 3-d building models from multiple bounded polygons

Automatic generation of 3-d building models from multiple bounded polygons icccbe 2010 Nottingham University Press Proceedings of the International Conference on Computing in Civil and Building Engineering W Tizani (Editor) Automatic generation of 3-d building models from multiple

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

Structural Analysis of Aerial Photographs (HB47 Computer Vision: Assignment)

Structural Analysis of Aerial Photographs (HB47 Computer Vision: Assignment) Structural Analysis of Aerial Photographs (HB47 Computer Vision: Assignment) Xiaodong Lu, Jin Yu, Yajie Li Master in Artificial Intelligence May 2004 Table of Contents 1 Introduction... 1 2 Edge-Preserving

More information

Prof. Jose L. Flores, MS, PS Dept. of Civil Engineering & Surveying

Prof. Jose L. Flores, MS, PS Dept. of Civil Engineering & Surveying Prof. Jose L. Flores, MS, PS Dept. of Civil Engineering & Surveying Problem One of the challenges for any Geographic Information System (GIS) application is to keep the spatial data up to date and accurate.

More information

A DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS

A DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS A DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS A. Mahphood, H. Arefi *, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran,

More information

Frequency Distributions

Frequency Distributions Displaying Data Frequency Distributions After collecting data, the first task for a researcher is to organize and summarize the data so that it is possible to get a general overview of the results. Remember,

More information

EE368 Project: Visual Code Marker Detection

EE368 Project: Visual Code Marker Detection EE368 Project: Visual Code Marker Detection Kahye Song Group Number: 42 Email: kahye@stanford.edu Abstract A visual marker detection algorithm has been implemented and tested with twelve training images.

More information

Building detection from disparity of edges

Building detection from disparity of edges Building detection from disparity of edges C. Beumier SIC Dpt, Royal Military Academy, Brussels, Belgium beumier@elec.rma.ac.be Keywords: Remote sensing, building detection, security, disparity, stereo,

More information

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints Last week Multi-Frame Structure from Motion: Multi-View Stereo Unknown camera viewpoints Last week PCA Today Recognition Today Recognition Recognition problems What is it? Object detection Who is it? Recognizing

More information

Category vs. instance recognition

Category vs. instance recognition Category vs. instance recognition Category: Find all the people Find all the buildings Often within a single image Often sliding window Instance: Is this face James? Find this specific famous building

More information

Global Probability of Boundary

Global Probability of Boundary Global Probability of Boundary Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues Martin, Fowlkes, Malik Using Contours to Detect and Localize Junctions in Natural

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

INCREASING CLASSIFICATION QUALITY BY USING FUZZY LOGIC

INCREASING CLASSIFICATION QUALITY BY USING FUZZY LOGIC JOURNAL OF APPLIED ENGINEERING SCIENCES VOL. 1(14), issue 4_2011 ISSN 2247-3769 ISSN-L 2247-3769 (Print) / e-issn:2284-7197 INCREASING CLASSIFICATION QUALITY BY USING FUZZY LOGIC DROJ Gabriela, University

More information

ROBUST BUILDING DETECTION IN AERIAL IMAGES

ROBUST BUILDING DETECTION IN AERIAL IMAGES In: Stilla U, Rottensteiner F, Hinz S (Eds) CMRT05. IAPRS, Vol. XXXVI, Part 3/W24 --- Vienna, Austria, August 29-30, 2005 ROBUST BUILDING DETECTION IN AERIAL IMAGES Sönke Müller, Daniel Wilhelm Zaum Institut

More information

A NEW ALGORITHM FOR AUTOMATIC ROAD NETWORK EXTRACTION IN MULTISPECTRAL SATELLITE IMAGES

A NEW ALGORITHM FOR AUTOMATIC ROAD NETWORK EXTRACTION IN MULTISPECTRAL SATELLITE IMAGES Proceedings of the 4th GEOBIA, May 7-9, 2012 - Rio de Janeiro - Brazil. p.455 A NEW ALGORITHM FOR AUTOMATIC ROAD NETWORK EXTRACTION IN MULTISPECTRAL SATELLITE IMAGES E. Karaman, U. Çinar, E. Gedik, Y.

More information

Robust PDF Table Locator

Robust PDF Table Locator Robust PDF Table Locator December 17, 2016 1 Introduction Data scientists rely on an abundance of tabular data stored in easy-to-machine-read formats like.csv files. Unfortunately, most government records

More information

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang Extracting Layers and Recognizing Features for Automatic Map Understanding Yao-Yi Chiang 0 Outline Introduction/ Problem Motivation Map Processing Overview Map Decomposition Feature Recognition Discussion

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

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

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

Object Classification Using Tripod Operators

Object Classification Using Tripod Operators Object Classification Using Tripod Operators David Bonanno, Frank Pipitone, G. Charmaine Gilbreath, Kristen Nock, Carlos A. Font, and Chadwick T. Hawley US Naval Research Laboratory, 4555 Overlook Ave.

More information

Automatic Segmentation of Semantic Classes in Raster Map Images

Automatic Segmentation of Semantic Classes in Raster Map Images Automatic Segmentation of Semantic Classes in Raster Map Images Thomas C. Henderson, Trevor Linton, Sergey Potupchik and Andrei Ostanin School of Computing, University of Utah, Salt Lake City, UT 84112

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

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

Classifying Images with Visual/Textual Cues. By Steven Kappes and Yan Cao

Classifying Images with Visual/Textual Cues. By Steven Kappes and Yan Cao Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao Motivation Image search Building large sets of classified images Robotics Background Object recognition is unsolved Deformable shaped

More information

Data: a collection of numbers or facts that require further processing before they are meaningful

Data: a collection of numbers or facts that require further processing before they are meaningful Digital Image Classification Data vs. Information Data: a collection of numbers or facts that require further processing before they are meaningful Information: Derived knowledge from raw data. Something

More information

Video shot segmentation using late fusion technique

Video shot segmentation using late fusion technique Video shot segmentation using late fusion technique by C. Krishna Mohan, N. Dhananjaya, B.Yegnanarayana in Proc. Seventh International Conference on Machine Learning and Applications, 2008, San Diego,

More information

VEHICLE QUEUE DETECTION IN SATELLITE IMAGES OF URBAN AREAS

VEHICLE QUEUE DETECTION IN SATELLITE IMAGES OF URBAN AREAS VEHICLE QUEUE DETECTION IN SATELLITE IMAGES OF URBAN AREAS J. Leitloff 1, S. Hinz 2, U. Stilla 1 1 Photogrammetry and Remote Sensing, 2 Remote Sensing Technology Technische Universitaet Muenchen, Arcisstrasse

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 09 130219 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Feature Descriptors Feature Matching Feature

More information

Road-Sign Detection and Recognition Based on Support Vector Machines. Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789

Road-Sign Detection and Recognition Based on Support Vector Machines. Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789 Road-Sign Detection and Recognition Based on Support Vector Machines Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789 Outline Introduction Support Vector Machine (SVM) Algorithm Results

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

Connected Component Analysis and Change Detection for Images

Connected Component Analysis and Change Detection for Images Connected Component Analysis and Change Detection for Images Prasad S.Halgaonkar Department of Computer Engg, MITCOE Pune University, India Abstract Detection of the region of change in images of a particular

More information

Object Category Detection: Sliding Windows

Object Category Detection: Sliding Windows 04/10/12 Object Category Detection: Sliding Windows Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical

More information

COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION

COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION COMBINING HIGH SPATIAL RESOLUTION OPTICAL AND LIDAR DATA FOR OBJECT-BASED IMAGE CLASSIFICATION Ruonan Li 1, Tianyi Zhang 1, Ruozheng Geng 1, Leiguang Wang 2, * 1 School of Forestry, Southwest Forestry

More information

Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010

Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010 1. Introduction Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010 The demand for janitorial robots has gone up with the rising affluence and increasingly busy lifestyles of people

More information

Introduction to digital image classification

Introduction to digital image classification Introduction to digital image classification Dr. Norman Kerle, Wan Bakx MSc a.o. INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Purpose of lecture Main lecture topics Review

More information

Corner Detection. Harvey Rhody Chester F. Carlson Center for Imaging Science Rochester Institute of Technology

Corner Detection. Harvey Rhody Chester F. Carlson Center for Imaging Science Rochester Institute of Technology Corner Detection Harvey Rhody Chester F. Carlson Center for Imaging Science Rochester Institute of Technology rhody@cis.rit.edu April 11, 2006 Abstract Corners and edges are two of the most important geometrical

More information

Flood-survivors detection using IR imagery on an autonomous drone

Flood-survivors detection using IR imagery on an autonomous drone Flood-survivors detection using IR imagery on an autonomous drone Sumant Sharma Department of Aeronautcs and Astronautics Stanford University Email: sharmas@stanford.edu Abstract In the search and rescue

More information

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes 2009 10th International Conference on Document Analysis and Recognition Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes Alireza Alaei

More information

Three-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients

Three-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an

More information

Postprint.

Postprint. http://www.diva-portal.org Postprint This is the accepted version of a paper presented at 14th International Conference of the Biometrics Special Interest Group, BIOSIG, Darmstadt, Germany, 9-11 September,

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

THE USE OF ANISOTROPIC HEIGHT TEXTURE MEASURES FOR THE SEGMENTATION OF AIRBORNE LASER SCANNER DATA

THE USE OF ANISOTROPIC HEIGHT TEXTURE MEASURES FOR THE SEGMENTATION OF AIRBORNE LASER SCANNER DATA THE USE OF ANISOTROPIC HEIGHT TEXTURE MEASURES FOR THE SEGMENTATION OF AIRBORNE LASER SCANNER DATA Sander Oude Elberink* and Hans-Gerd Maas** *Faculty of Civil Engineering and Geosciences Department of

More information

Title: Adaptive Region Merging Segmentation of Airborne Imagery for Roof Condition Assessment. Abstract:

Title: Adaptive Region Merging Segmentation of Airborne Imagery for Roof Condition Assessment. Abstract: Title: Adaptive Region Merging Segmentation of Airborne Imagery for Roof Condition Assessment Abstract: In order to perform residential roof condition assessment with very-high-resolution airborne imagery,

More information

Adaptive Learning of an Accurate Skin-Color Model

Adaptive Learning of an Accurate Skin-Color Model Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin

More information

Knowledge-Based Modeling of Buildings in Dense Urban Areas by Combining Airborne LiDAR Data and Aerial Images

Knowledge-Based Modeling of Buildings in Dense Urban Areas by Combining Airborne LiDAR Data and Aerial Images Remote Sens. 2013, 5, 5944-5968; doi:10.3390/rs5115944 Article OPEN ACCESS Remote Sensing ISSN 2072-4292 www.mdpi.com/journal/remotesensing Knowledge-Based Modeling of Buildings in Dense Urban Areas by

More information

Object Category Detection. Slides mostly from Derek Hoiem

Object Category Detection. Slides mostly from Derek Hoiem Object Category Detection Slides mostly from Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical template matching with sliding window Part-based Models

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

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

1. Introduction. A CASE STUDY Dense Image Matching Using Oblique Imagery Towards All-in- One Photogrammetry

1. Introduction. A CASE STUDY Dense Image Matching Using Oblique Imagery Towards All-in- One Photogrammetry Submitted to GIM International FEATURE A CASE STUDY Dense Image Matching Using Oblique Imagery Towards All-in- One Photogrammetry Dieter Fritsch 1, Jens Kremer 2, Albrecht Grimm 2, Mathias Rothermel 1

More information

OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images

OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images Deepak Kumar and A G Ramakrishnan Medical Intelligence and Language Engineering Laboratory Department of Electrical Engineering, Indian

More information

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image

More information

Chapter 4. Clustering Core Atoms by Location

Chapter 4. Clustering Core Atoms by Location Chapter 4. Clustering Core Atoms by Location In this chapter, a process for sampling core atoms in space is developed, so that the analytic techniques in section 3C can be applied to local collections

More information

Multi-ray photogrammetry: A rich dataset for the extraction of roof geometry for 3D reconstruction

Multi-ray photogrammetry: A rich dataset for the extraction of roof geometry for 3D reconstruction Multi-ray photogrammetry: A rich dataset for the extraction of roof geometry for 3D reconstruction Andrew McClune, Pauline Miller, Jon Mills Newcastle University David Holland Ordnance Survey Background

More information

INTELLIGENT transportation systems have a significant

INTELLIGENT transportation systems have a significant INTL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS, 205, VOL. 6, NO. 4, PP. 35 356 Manuscript received October 4, 205; revised November, 205. DOI: 0.55/eletel-205-0046 Efficient Two-Step Approach for Automatic

More information

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract

More information

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality

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

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,

More information

Table of Contents (As covered from textbook)

Table of Contents (As covered from textbook) Table of Contents (As covered from textbook) Ch 1 Data and Decisions Ch 2 Displaying and Describing Categorical Data Ch 3 Displaying and Describing Quantitative Data Ch 4 Correlation and Linear Regression

More information

Clustering will not be satisfactory if:

Clustering will not be satisfactory if: Clustering will not be satisfactory if: -- in the input space the clusters are not linearly separable; -- the distance measure is not adequate; -- the assumptions limit the shape or the number of the clusters.

More information

Face detection and recognition. Detection Recognition Sally

Face detection and recognition. Detection Recognition Sally Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification

More information

Data mining with Support Vector Machine

Data mining with Support Vector Machine Data mining with Support Vector Machine Ms. Arti Patle IES, IPS Academy Indore (M.P.) artipatle@gmail.com Mr. Deepak Singh Chouhan IES, IPS Academy Indore (M.P.) deepak.schouhan@yahoo.com Abstract: Machine

More information

Automatic updating of urban vector maps

Automatic updating of urban vector maps Automatic updating of urban vector maps S. Ceresola, A. Fusiello, M. Bicego, A. Belussi, and V. Murino Dipartimento di Informatica, Università di Verona Strada Le Grazie 15, 37134 Verona, Italy Abstract.

More information

Developing an intelligent sign inventory using image processing

Developing an intelligent sign inventory using image processing icccbe 2010 Nottingham University Press Proceedings of the International Conference on Computing in Civil and Building Engineering W Tizani (Editor) Developing an intelligent sign inventory using image

More information

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S Radha Krishna Rambola, Associate Professor, NMIMS University, India Akash Agrawal, Student at NMIMS University, India ABSTRACT Due to the

More information

Selective Search for Object Recognition

Selective Search for Object Recognition Selective Search for Object Recognition Uijlings et al. Schuyler Smith Overview Introduction Object Recognition Selective Search Similarity Metrics Results Object Recognition Kitten Goal: Problem: Where

More information

Robust Shape Retrieval Using Maximum Likelihood Theory

Robust Shape Retrieval Using Maximum Likelihood Theory Robust Shape Retrieval Using Maximum Likelihood Theory Naif Alajlan 1, Paul Fieguth 2, and Mohamed Kamel 1 1 PAMI Lab, E & CE Dept., UW, Waterloo, ON, N2L 3G1, Canada. naif, mkamel@pami.uwaterloo.ca 2

More information

Component-based Face Recognition with 3D Morphable Models

Component-based Face Recognition with 3D Morphable Models Component-based Face Recognition with 3D Morphable Models B. Weyrauch J. Huang benjamin.weyrauch@vitronic.com jenniferhuang@alum.mit.edu Center for Biological and Center for Biological and Computational

More information

AUTOMATIC GENERATION OF DIGITAL BUILDING MODELS FOR COMPLEX STRUCTURES FROM LIDAR DATA

AUTOMATIC GENERATION OF DIGITAL BUILDING MODELS FOR COMPLEX STRUCTURES FROM LIDAR DATA AUTOMATIC GENERATION OF DIGITAL BUILDING MODELS FOR COMPLEX STRUCTURES FROM LIDAR DATA Changjae Kim a, Ayman Habib a, *, Yu-Chuan Chang a a Geomatics Engineering, University of Calgary, Canada - habib@geomatics.ucalgary.ca,

More information

Including the Size of Regions in Image Segmentation by Region Based Graph

Including the Size of Regions in Image Segmentation by Region Based Graph International Journal of Emerging Engineering Research and Technology Volume 3, Issue 4, April 2015, PP 81-85 ISSN 2349-4395 (Print) & ISSN 2349-4409 (Online) Including the Size of Regions in Image Segmentation

More information

CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS

CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS 85 CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS 5.1 GENERAL Urban feature mapping is one of the important component for the planning, managing and monitoring the rapid urbanized growth. The present conventional

More information

City-Modeling. Detecting and Reconstructing Buildings from Aerial Images and LIDAR Data

City-Modeling. Detecting and Reconstructing Buildings from Aerial Images and LIDAR Data City-Modeling Detecting and Reconstructing Buildings from Aerial Images and LIDAR Data Department of Photogrammetrie Institute for Geodesy and Geoinformation Bonn 300000 inhabitants At river Rhine University

More information

Chapter 3 Image Registration. Chapter 3 Image Registration

Chapter 3 Image Registration. Chapter 3 Image Registration Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation

More information

Towards Knowledge-Based Extraction of Roads from 1m-resolution Satellite Images

Towards Knowledge-Based Extraction of Roads from 1m-resolution Satellite Images Towards Knowledge-Based Extraction of Roads from 1m-resolution Satellite Images Hae Yeoun Lee* Wonkyu Park** Heung-Kyu Lee* Tak-gon Kim*** * Dept. of Computer Science, Korea Advanced Institute of Science

More information

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK 1 Po-Jen Lai ( 賴柏任 ), 2 Chiou-Shann Fuh ( 傅楸善 ) 1 Dept. of Electrical Engineering, National Taiwan University, Taiwan 2 Dept.

More information

Supplementary Materials for DVQA: Understanding Data Visualizations via Question Answering

Supplementary Materials for DVQA: Understanding Data Visualizations via Question Answering Supplementary Materials for DVQA: Understanding Data Visualizations via Question Answering Kushal Kafle 1, Brian Price 2 Scott Cohen 2 Christopher Kanan 1 1 Rochester Institute of Technology 2 Adobe Research

More information

APPLICATION OF AERIAL VIDEO FOR TRAFFIC FLOW MONITORING AND MANAGEMENT

APPLICATION OF AERIAL VIDEO FOR TRAFFIC FLOW MONITORING AND MANAGEMENT Pitu Mirchandani, Professor, Department of Systems and Industrial Engineering Mark Hickman, Assistant Professor, Department of Civil Engineering Alejandro Angel, Graduate Researcher Dinesh Chandnani, Graduate

More information

Tri-modal Human Body Segmentation

Tri-modal Human Body Segmentation Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

Car Detecting Method using high Resolution images

Car Detecting Method using high Resolution images Car Detecting Method using high Resolution images Swapnil R. Dhawad Department of Electronics and Telecommunication Engineering JSPM s Rajarshi Shahu College of Engineering, Savitribai Phule Pune University,

More information

OBJECT IDENTIFICATION AND FEATURE EXTRACTION TECHNIQUES OF A SATELLITE DATA: A REVIEW

OBJECT IDENTIFICATION AND FEATURE EXTRACTION TECHNIQUES OF A SATELLITE DATA: A REVIEW OBJECT IDENTIFICATION AND FEATURE EXTRACTION TECHNIQUES OF A SATELLITE DATA: A REVIEW Navjeet 1, Simarjeet Kaur 2 1 Department of Computer Engineering Sri Guru Granth Sahib World University Fatehgarh Sahib,

More information

Real-Time Human Detection using Relational Depth Similarity Features

Real-Time Human Detection using Relational Depth Similarity Features Real-Time Human Detection using Relational Depth Similarity Features Sho Ikemura, Hironobu Fujiyoshi Dept. of Computer Science, Chubu University. Matsumoto 1200, Kasugai, Aichi, 487-8501 Japan. si@vision.cs.chubu.ac.jp,

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

(Refer Slide Time: 0:51)

(Refer Slide Time: 0:51) Introduction to Remote Sensing Dr. Arun K Saraf Department of Earth Sciences Indian Institute of Technology Roorkee Lecture 16 Image Classification Techniques Hello everyone welcome to 16th lecture in

More information

INF 4300 Classification III Anne Solberg The agenda today:

INF 4300 Classification III Anne Solberg The agenda today: INF 4300 Classification III Anne Solberg 28.10.15 The agenda today: More on estimating classifier accuracy Curse of dimensionality and simple feature selection knn-classification K-means clustering 28.10.15

More information

BUILDING DETECTION IN VERY HIGH RESOLUTION SATELLITE IMAGE USING IHS MODEL

BUILDING DETECTION IN VERY HIGH RESOLUTION SATELLITE IMAGE USING IHS MODEL BUILDING DETECTION IN VERY HIGH RESOLUTION SATELLITE IMAGE USING IHS MODEL Shabnam Jabari, PhD Candidate Yun Zhang, Professor, P.Eng University of New Brunswick E3B 5A3, Fredericton, Canada sh.jabari@unb.ca

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