Real-Time Stereo Vision on a Reconfigurable System

Size: px
Start display at page:

Download "Real-Time Stereo Vision on a Reconfigurable System"

Transcription

1 Real-Time Stereo Vision on a Reconfigurable System SungHwan Lee, Jongsu Yi, and JunSeong Kim School of Electrical and Electronics Engineering, Chung-Ang University, 221 HeukSeok-Dong DongJak-Gu, Seoul, Korea {lshcau, xmxm2718}@wm.cau.ac.kr, junkim@cau.ac.kr Abstract. Real-time three-dimensional vision would support various applications including a passive system for collision avoidance. It is a good alternative of active systems, which are subject to interference in noisy environments. In this paper, we investigate the optimization of real-time stereo vision with respect to resource usage. Correlation techniques using a simple sum of absolute differences(sad) is popular having good performance. However, processing even a small image takes seconds. In order to provide depth maps at frame rate around 30fps, which typical cameras can provide, hardware accelerations are necessary. Regular structures, linear data flow and abundant parallelism make the correlation algorithm a good candidate for reconfigurable hardware. We implemented versions of SAD algorithms in VHDL and synthesized them to determine resource requirements and performance. By decomposing a SAD correlator into column SAD calculator and row SAD calculator with buffers in between we showed around 50% savings in resource usage. By altering the shape of correlation windows we found that a short and wide rectangular window reduced storage requirements without sacrificing quality compared to a square one. 1 Introduction A collision avoidance system for a device with mobility requires the ability to build a three-dimensional map of its environment. Traditionally, this has been accomplished by active sensors, which send a pulse - either electromagnetic or sonar - and detect the reflected return[1, 2]. Such active systems work well in the environments with small number of moving devices and thus the probability that active sensors will interfere is low. However, when the density of moving objects becomes high, active systems are easily left in noisy environments. Lots of moving objects with a wide range of speeds and directions create that many reflections at various strengths. A sensor could easily be confused by extremely weak reflections of its own and strong pulses from other objects. Passive systems, on the other hand, are much less sensitive to environmental interference. Stereo vision is one of the representative passive systems. Typical cameras can provide 30 or more images per second and each pair of images can provide a complete three-dimensional map of the environment. However, processing even small low resolution images takes more than a second in software. This is well below the frame rates obtainable with commodity cameras and may be far too slow to enable even relatively slow moving objects to avoid colliding each other. Thus, hardware accelerators are required in order to obtain real-time 3D environment maps. Software simulations T.D. Hämäläinen et al. (Eds.): SAMOS 2005, LNCS 3553, pp , c Springer-Verlag Berlin Heidelberg 2005

2 300 S. Lee, J. Yi, and J. Kim have determined that correlation techniques using a simple sum of absolute differences (SAD) algorithm perform well [3, 4]. In our previous work [5], we showed that accurate real-time three-dimensional maps are feasible with modern FPGA technology. A SAD correlator with its associated accuracy and speed requirements could be fitted onto a single commercially available FPGA. In this paper, we present versions of optimization of the SAD correlator with respect to resource usage. By decomposing the original SAD correlator into column SAD calculator and row SAD calculator with buffers in between we reduced the number of adders from the original SAD correlator. Also, by utilizing rectangular windows instead of traditional square windows we saved more resources without sacrificing accuracy. In the remainder of the paper, Section 2 briefly surveys the stereo image matching techniques, Section 3 provides the concept of the SAD algorithm and Section 4 introduces our SAD correlators. Section 5 then provides the results of our experiments. Finally, Section 6 summarizes our results and conclusions. 2 Stereo Image Matching Stereo vision refers the problem of extracting 3-dimensional structure from two(or more) images taken from different viewpoints[6]. Image matching is an important part in stereo vision system involving two main problems: correspondence and reconstruction. The correspondence problem consists of determining, given a pair of stereo images, which parts in the left(right) image correspond to which parts in the right(left) image. Since there are parts of a scene projected on a single image only it must be able to tell the parts in each image that should not be matched. The reconstruction problem consists of determining, given a set of corresponding parts of a pair of stereo images, 3-dimensional location and structure of the observed objects. Ideally, we want to find all matching pixels of a pair of stereo images. However, the value of brightness of a single pixel is too low to determine its correspondence. Instead, sets of pixels are used for real stereo matching algorithms. Correlation-based methods and feature-based methods are the two representation stereo matching classification [6, 7]. In correlation-based methods, image windows, arrays of neighboring pixels, of fixed size are used. Given a pair of stereo images, one window is fixed in the left(right) image and the other window is moving in the right(left) image. By comparing the windows from the pair of images correlation is measured and the window, that maximizes the similarity criterion, is determined. Normalized Cross-Correlation(NCC), Sum of Squared Differences(SSD), Sum of Absolute Differences(SAD), Census, and Rank algorithms are popular matching metrics[7, 8]. Feature-based methods use a sparse set of features instead of image windows. These include occlusion edges, vertices of linear structures, prominent surface markings, zero crossings and patches by the Moravec operator[9]. Corresponding elements from a pair of stereo images are given by the most similar feature pair, the one associated to the minimum distance. Feature-based methods cannot detect small changes in stereo images and is not suitable when images have no boundary.

3 Real-Time Stereo Vision on a Reconfigurable System SAD Algorithm Area-based correlation algorithms attempt to find the best match between a window of pixels in one image and a window in the other image[6]. The matching process is illustrated in Figure 1. The window centerd on pixel P in the left image is moved through the disparity range until the best match is found with a windwos centerd at P in the right image. aligning the two cameras to meet the epipdar constraint ensures that P must lie on the same scan line in each image [6, 7]. Fig. 1. Correlation based matching In the SAD algorithm, the criterion for the best match is minimization of the sum of the absolute differences of corresponding pixels in a window. The correlation algorithm has a regular structure and simple data flow making it good for implementation in reconfigurable hardware. The SAD function is defined to be C(x,y,δ)= wh 1 y=0 ww 1 I R (x,y) I L (x + δ,y) (1) x=0 The SAD function C(x,y,δ) is evaluated for all possible values of the disparity, δ, and the minimum is chosen. In the equation, I R () and I L () mean right image and left image respectively. The x, y represent coordinates in pixel in a single image, ww and wh represent window width and height, and δ represents disparity number. For parallel camera axes, δ ranges from 0 for objects at infinity to for objects at the closest possible to the camera. The correlation algorithm has regular structures having abundant parallelism - C(x,y,δ) can be evaluated in parallel for each δ [0, ]. The SAD function requires only adders and comparators for which modern FPGAs provide good supports. However, accurate depth maps require large disparity ranges and high resolution images - both of which provide challenges to fitting a full correlator on a single FPGA. 4 SAD Correlator We have implemented versions of the SAD correlation algorithm in VHDL and synthesized them to determine their resource requirements and performance. Each version completely accomplishes the SAD correlation algorithm and has the following features:

4 302 S. Lee, J. Yi, and J. Kim Fig. 2. Block diagram for the SAD correlator v1.2 Table 1. SAD Correlator Resource requirements SAD correlator Object Count Size shift register register 2 sl (wh 1)+ + 1 buffer maker subtractor + 1 wh adder + 1 wh 1 buffer buffer 1 ww ( + 1) disparity calculator adder + 1 ww 1 minimum detector comparator 1 SAD correlator v1.0[5] fully implements the SAD correlation algorithm without any optimization SAD correlator v1.1 decomposes SAD correlator into column SAD calculator (buffer maker) and row SAD calculator (disparity calculator) placing buffers in between reducing the number of adders from the SAD correlator v1.0 SAD correlator v1.2 does a certain approximation in SAD calculation by ignoring the least significant bit (reducing the number of bits in adders): at the cost of accuracy fo further save space from the SAD correlator v1.1 A block diagram of the SAD correlator v1.2 is shown in Figure 2. Pixels stream in from both cameras into the long left and right shift registers, which store sufficient

5 Real-Time Stereo Vision on a Reconfigurable System 303 pixels so that all the pixels in a correlation window are available to the buffer maker at the same time. The key parameters determining the size and performance of an SAD correlator are 1 the scan line length, sl, 2 the window width, ww, 3 the window height, wh, and 4 the maximum disparity,. Basic resource requirements are indicated in Table 1. To a first approximation, the resource requirements for an SAD correlator are given by: cost SAD 2 (sl (wh 1)+ + 1) c reg (shi ft register) +( + 1) (wh c AD +(wh 1) c sum (bu f f er maker) +ww ( + 1) c reg (bu f f er) +( + 1) (ww 1) c sum (disparity calculator) + c comp (comparator) +c overheads (control, etc.) Where c AD is the cost of absolute difference circuit, c sum is the cost of an adder, c comp is the cost of a comparator, c reg is the cost of a pixel register, c overheads is the cost of control and steering logic. This relation should be a good predictor for low values of all the application parameters, where all overheads can be lumped effectively into the single overheads term. Key contributors to the delay of the correlator are from the (wh 1) adders in buffer makers and the (ww 1) adders in disparity calculators. A simple VHDL model which performs the additions in a loop adds a delay of O(wh + ww 2) to the circuit. However, for better performance we use a tree adder, which costs delay of O(log(wh + ww 2)). Note that the synthesizer is able to produce a compact circuit with the tree adder using the + operator, despite the triangular shape of the tree. (2) 5 Experimental Results For this experiment we use Xilinx Virtex-II XC2V8000 FPGAs[10] with scan line length, sl = 320 and the maximum disparity, = 32 (accuracy depends on the disparity value, so we ran trials to determine the value of ). Figure 3 shows the hardware Fig. 3. Resource usage vs. window size (ww wh) for versions of the SAD correlator

6 304 S. Lee, J. Yi, and J. Kim resource usage for the SAD correlators with various window sizes. The X-axis represents the square window sizes used in the experiment and Y-axis is the number of slices occupied. (a) original left-image (b) original right-image Fig. 4. A pair of Tsukuba images for test inputs Figure 5 shows samples of resulting depth maps of versions of SAD correlator with windows size of 8 8(ww wh). A pair of the input images in figure 4 - Tsukuba image [3, 11] - consisting of pixels was used as a test inputs. From the figure 5, we can see that there is little difference in depth map among the versions of SAD correlator. (a) SAD correlator v1.0 (b) SAD correlator v1.1 (c) SAD correlator v1.2 Fig. 5. Sample depth maps of versions of the SAD correlator with 8 8 window Figure 6 shows the simulation waveform using the Tsukuba image. The process time of one frame image is less than 120,000 c.c. The table 2 summarizes the performance of the SAD correlator v1.0 with various test images including the Tsukuba images, when it works in 10 MHz. It is unnecessarily common to use square matching windows in correlation-style stereo algorithms. If you carefully look at the algorithm you can see that matching

7 Real-Time Stereo Vision on a Reconfigurable System 305 Fig. 6. The simulation waveform using the Tsukuba images Table 2. The performance of the SAD correlator v1.0 in various environments Image size maximum disparity window size rate (pixel) ( ) (ww wh) (frame/sec) process only uses a small part of each scan line at any time - specifically, ww from the left image and ww+ +1 from the right image. The remaining pixels are stored in shift registers for use in subsequent cycles. Pixels in surrounding scan lines are only used to support matching by reducing noise effects. Figure 7 shows samples of depth maps of SAD correlator v1.2 for the same Tsukuba input images with various rectangular windows. We can find that a short and wide (wh < ww) window produces similar matching quality to the square one. However, We can see that a considerable amount of space can be saved in an FPGA by using rectangular (wh < ww) windows. Figure 8 shows a FPGA resource usage for various rectangular window sizes as well as square ones. We can conclude that a rectangular window in SAD correlators is worth utilizing, especially when ww is sufficiently large, since it saves lots of space (nearly 50% profit) without sacrificing quality. (a) 16 4 window (b) 16 8 window (c) window Fig. 7. Sample depth maps of the SAD correlator v1.2 with various window sizes (ww wh)

8 306 S. Lee, J. Yi, and J. Kim 6 Conclusion Fig. 8. Resource usage vs. window size (ww wh) for various disparities Accurate real-time 3D depth maps are feasible with modern FPGA technology. While the feasibility of a proposed application can be testified, in principle, by simply counting circuit elements needed to implement a module and using those counts in equation 2, place and route tools have to work from high level models and may have problems allocating and laying out circuits that a human engineer may not. FPGA implementations are also constrained by availability of routing resources and this factor is much harder to estimate than logic cell needs, thus practical trials of the type we carried out here are counts to determine real cost factors. Decomposing a SAD correlator into column SAD calculator and row SAD calculator with buffers in between reduces number of adders: easily saving around 50% in resource usage. Simulation results show that altering the shape of the correlation window can further reduce the number of cells needed for inactive parts of scan lines. The SAD correlator v1.2 described in this paper will provide real-time performance at pixel clock rates up to 10 MHz. Acknowledgements This research was partially supported by the MIC(Ministry of Information and Communication), Korea, under the Chung-Ang University HNRC-ITRC(Home Network Research Center) support program supervised by the IITA(Institute of Information Technology Assessment). References 1. Olson, C.F.: Maximum-likelihood image matching. IEEE Trans. Pattern Anal. Mach. Intell. 24 (2002) Sebe, N., Lew, M.S.: Maximum likelihood stereo matching. In: ICPR 00: Proceedings of the International Conference on Pattern Recognition (ICPR 00)-Volume 1, Washington, DC, USA, IEEE Computer Society (2000) 1900

9 Real-Time Stereo Vision on a Reconfigurable System Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47 (2002) Leclercq, P., Morris, J.: Assessing stereo algorithm accuracy. In: IVCNZ 02: Proceedings of Image and Vision Computing 02, University of Auckland, Auckland, New Zealand (2002) Yi, J., Kim, J., Li, L., Morris, J., Lee, G., Leclercq, P.: Real-time three dimensional vision. In Yew, P.C., Xue, J., eds.: Asia-Pacific Computer Systems Architecture Conference. Volume 3189 of Lecture Notes in Computer Science., Springer (2004) Barnard, S.T., Fischler, M.A.: Computational stereo. ACM Comput. Surv. 14 (1982) Brown, M.Z., Burschka, D., Hager, G.D.: Advances in computational stereo. IEEE Trans. Pattern Anal. Mach. Intell. 25 (2003) Leclercq, P., Morris, J.: Robustness to noise of stereo matching. In: ICIAP 03: Proceedings of the 12th International Conference on Image Analysis and Processing, Washington, DC, USA, IEEE Computer Society (2003) Grimson, E.L.: Computatoinal experiments with a feature based stereo algorithm. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-7 (1985) Virtex- platform fpgas : Complete data sheet (2002) Middlebury stereo vision page (2005)

A Platform-Based SoC Design for Real-Time Stereo Vision

A Platform-Based SoC Design for Real-Time Stereo Vision http://dx.doi.org/10.5573/jsts.2012.12.2.212 JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, VOL.12, NO.2, JUNE, 2012 A Platform-Based SoC Design for Real-Time Stereo Vision Jongsu Yi*, Jaehwa Park**,

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 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational

More information

Stereo Video Processing for Depth Map

Stereo Video Processing for Depth Map Stereo Video Processing for Depth Map Harlan Hile and Colin Zheng University of Washington Abstract This paper describes the implementation of a stereo depth measurement algorithm in hardware on Field-Programmable

More information

Hardware implementation of an SAD based stereo vision algorithm

Hardware implementation of an SAD based stereo vision algorithm Hardware implementation of an SAD based stereo vision algorithm Kristian Ambrosch Austrian Research Centers GmbH - ARC A-1220 Vienna, Austria kristian.ambrosch@arcs.ac.at Wilfried Kubinger Austrian Research

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem

More information

Design Considerations for Embedded Stereo Vision Systems

Design Considerations for Embedded Stereo Vision Systems Design Considerations for Embedded Stereo Vision Systems AMBROSCH, Kristian; HUMENBERGER, Martin & KUBINGER, Wilfried Abstract: This Paper describes our current work on a novel hardware architecture for

More information

Real-Time Disparity Map Computation Based On Disparity Space Image

Real-Time Disparity Map Computation Based On Disparity Space Image Real-Time Disparity Map Computation Based On Disparity Space Image Nadia Baha and Slimane Larabi Computer Science Department, University of Science and Technology USTHB, Algiers, Algeria nbahatouzene@usthb.dz,

More information

Announcements. Stereo Vision Wrapup & Intro Recognition

Announcements. Stereo Vision Wrapup & Intro Recognition Announcements Stereo Vision Wrapup & Intro Introduction to Computer Vision CSE 152 Lecture 17 HW3 due date postpone to Thursday HW4 to posted by Thursday, due next Friday. Order of material we ll first

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction

More information

Lecture 14: Computer Vision

Lecture 14: Computer Vision CS/b: Artificial Intelligence II Prof. Olga Veksler Lecture : Computer Vision D shape from Images Stereo Reconstruction Many Slides are from Steve Seitz (UW), S. Narasimhan Outline Cues for D shape perception

More information

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

Real Time Object Visual Inspection Based On Template Matching Using FPGA

Real Time Object Visual Inspection Based On Template Matching Using FPGA Real Time Object Visual Inspection Based On Template Matching Using FPGA SANDHYA P Asst Professor in MTIET Palamaner, India OMKAR NAIDU V Asst Professor in MTIET Palamaner, India Abstract In similarity

More information

Range Image Registration with Edge Detection in Spherical Coordinates

Range Image Registration with Edge Detection in Spherical Coordinates Range Image Registration with Edge Detection in Spherical Coordinates Olcay Sertel 1 and Cem Ünsalan2 Computer Vision Research Laboratory 1 Department of Computer Engineering 2 Department of Electrical

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

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

IJSER. Real Time Object Visual Inspection Based On Template Matching Using FPGA

IJSER. Real Time Object Visual Inspection Based On Template Matching Using FPGA International Journal of Scientific & Engineering Research, Volume 4, Issue 8, August-2013 823 Real Time Object Visual Inspection Based On Template Matching Using FPGA GURURAJ.BANAKAR Electronics & Communications

More information

Real-Time Stereo Image Matching on FPGA

Real-Time Stereo Image Matching on FPGA Real-Time Stereo Image Matching on FPGA Carlos Resende DEEC, FEUP ee04022@fe.up.pt João C. Ferreira INESC Porto, FEUP jcf@fe.up.pt Abstract Real-time stereo image matching is an important computer vision

More information

Correspondence and Stereopsis. Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]

Correspondence and Stereopsis. Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri] Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri] Introduction Disparity: Informally: difference between two pictures Allows us to gain a strong

More information

Computer Vision, Lecture 11

Computer Vision, Lecture 11 Computer Vision, Lecture 11 Professor Hager http://www.cs.jhu.edu/~hager Computational Stereo Much of geometric vision is based on information from (or more) camera locations hard to recover 3D information

More information

There are many cues in monocular vision which suggests that vision in stereo starts very early from two similar 2D images. Lets see a few...

There are many cues in monocular vision which suggests that vision in stereo starts very early from two similar 2D images. Lets see a few... STEREO VISION The slides are from several sources through James Hays (Brown); Srinivasa Narasimhan (CMU); Silvio Savarese (U. of Michigan); Bill Freeman and Antonio Torralba (MIT), including their own

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

Multi-view stereo. Many slides adapted from S. Seitz

Multi-view stereo. Many slides adapted from S. Seitz Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window

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

A virtual tour of free viewpoint rendering

A virtual tour of free viewpoint rendering A virtual tour of free viewpoint rendering Cédric Verleysen ICTEAM institute, Université catholique de Louvain, Belgium cedric.verleysen@uclouvain.be Organization of the presentation Context Acquisition

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

Computer Vision I. Dense Stereo Correspondences. Anita Sellent 1/15/16

Computer Vision I. Dense Stereo Correspondences. Anita Sellent 1/15/16 Computer Vision I Dense Stereo Correspondences Anita Sellent Stereo Two Cameras Overlapping field of view Known transformation between cameras From disparity compute depth [ Bradski, Kaehler: Learning

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

Occlusion Detection of Real Objects using Contour Based Stereo Matching

Occlusion Detection of Real Objects using Contour Based Stereo Matching Occlusion Detection of Real Objects using Contour Based Stereo Matching Kenichi Hayashi, Hirokazu Kato, Shogo Nishida Graduate School of Engineering Science, Osaka University,1-3 Machikaneyama-cho, Toyonaka,

More information

Triangular Mesh Segmentation Based On Surface Normal

Triangular Mesh Segmentation Based On Surface Normal ACCV2002: The 5th Asian Conference on Computer Vision, 23--25 January 2002, Melbourne, Australia. Triangular Mesh Segmentation Based On Surface Normal Dong Hwan Kim School of Electrical Eng. Seoul Nat

More information

A Robust and Efficient Motion Segmentation Based on Orthogonal Projection Matrix of Shape Space

A Robust and Efficient Motion Segmentation Based on Orthogonal Projection Matrix of Shape Space A Robust and Efficient Motion Segmentation Based on Orthogonal Projection Matrix of Shape Space Naoyuki ICHIMURA Electrotechnical Laboratory 1-1-4, Umezono, Tsukuba Ibaraki, 35-8568 Japan ichimura@etl.go.jp

More information

An Implementation of Spatial Algorithm to Estimate the Focus Map from a Single Image

An Implementation of Spatial Algorithm to Estimate the Focus Map from a Single Image An Implementation of Spatial Algorithm to Estimate the Focus Map from a Single Image Yen-Bor Lin and Chung-Ping Young Department of Computer Science and Information Engineering National Cheng Kung University

More information

Detecting motion by means of 2D and 3D information

Detecting motion by means of 2D and 3D information Detecting motion by means of 2D and 3D information Federico Tombari Stefano Mattoccia Luigi Di Stefano Fabio Tonelli Department of Electronics Computer Science and Systems (DEIS) Viale Risorgimento 2,

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

Implementation Of Harris Corner Matching Based On FPGA

Implementation Of Harris Corner Matching Based On FPGA 6th International Conference on Energy and Environmental Protection (ICEEP 2017) Implementation Of Harris Corner Matching Based On FPGA Xu Chengdaa, Bai Yunshanb Transportion Service Department, Bengbu

More information

On-line and Off-line 3D Reconstruction for Crisis Management Applications

On-line and Off-line 3D Reconstruction for Crisis Management Applications On-line and Off-line 3D Reconstruction for Crisis Management Applications Geert De Cubber Royal Military Academy, Department of Mechanical Engineering (MSTA) Av. de la Renaissance 30, 1000 Brussels geert.de.cubber@rma.ac.be

More information

TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA

TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi 1, Francois de Sorbier 1 and Hideo Saito 1 1 Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi,

More information

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science. Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Stereo Vision 2 Inferring 3D from 2D Model based pose estimation single (calibrated) camera Stereo

More information

Iterative Estimation of 3D Transformations for Object Alignment

Iterative Estimation of 3D Transformations for Object Alignment Iterative Estimation of 3D Transformations for Object Alignment Tao Wang and Anup Basu Department of Computing Science, Univ. of Alberta, Edmonton, AB T6G 2E8, Canada Abstract. An Iterative Estimation

More information

Developing a Data Driven System for Computational Neuroscience

Developing a Data Driven System for Computational Neuroscience Developing a Data Driven System for Computational Neuroscience Ross Snider and Yongming Zhu Montana State University, Bozeman MT 59717, USA Abstract. A data driven system implies the need to integrate

More information

Specular 3D Object Tracking by View Generative Learning

Specular 3D Object Tracking by View Generative Learning Specular 3D Object Tracking by View Generative Learning Yukiko Shinozuka, Francois de Sorbier and Hideo Saito Keio University 3-14-1 Hiyoshi, Kohoku-ku 223-8522 Yokohama, Japan shinozuka@hvrl.ics.keio.ac.jp

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

Chaplin, Modern Times, 1936

Chaplin, Modern Times, 1936 Chaplin, Modern Times, 1936 [A Bucket of Water and a Glass Matte: Special Effects in Modern Times; bonus feature on The Criterion Collection set] Multi-view geometry problems Structure: Given projections

More information

Fast correlation-based stereo matching with the reduction of systematic errors

Fast correlation-based stereo matching with the reduction of systematic errors Pattern Recognition Letters 26 (2005) 2221 2231 www.elsevier.com/locate/patrec Fast correlation-based stereo matching with the reduction of systematic errors Sukjune Yoon *, Sung-Kee Park, Sungchul Kang,

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

Lecture 10: Multi view geometry

Lecture 10: Multi view geometry Lecture 10: Multi view geometry Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Stereo vision Correspondence problem (Problem Set 2 (Q3)) Active stereo vision systems Structure from

More information

A FAST SEGMENTATION-DRIVEN ALGORITHM FOR ACCURATE STEREO CORRESPONDENCE. Stefano Mattoccia and Leonardo De-Maeztu

A FAST SEGMENTATION-DRIVEN ALGORITHM FOR ACCURATE STEREO CORRESPONDENCE. Stefano Mattoccia and Leonardo De-Maeztu A FAST SEGMENTATION-DRIVEN ALGORITHM FOR ACCURATE STEREO CORRESPONDENCE Stefano Mattoccia and Leonardo De-Maeztu University of Bologna, Public University of Navarre ABSTRACT Recent cost aggregation strategies

More information

Towards Accurate Hardware Stereo Correspondence:

Towards Accurate Hardware Stereo Correspondence: Towards Accurate Hardware Stereo Correspondence: A Real-Time FPGA Implementation of a Segmentation-Based Adaptive Support Weight Algorithm C. Ttofis and T. Theocharides KIOS Research Center for Intelligent

More information

FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS

FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS 1 RONNIE O. SERFA JUAN, 2 CHAN SU PARK, 3 HI SEOK KIM, 4 HYEONG WOO CHA 1,2,3,4 CheongJu University E-maul: 1 engr_serfs@yahoo.com,

More information

COMP 102: Computers and Computing

COMP 102: Computers and Computing COMP 102: Computers and Computing Lecture 23: Computer Vision Instructor: Kaleem Siddiqi (siddiqi@cim.mcgill.ca) Class web page: www.cim.mcgill.ca/~siddiqi/102.html What is computer vision? Broadly speaking,

More information

hsgm: Hierarchical Pyramid Based Stereo Matching Algorithm

hsgm: Hierarchical Pyramid Based Stereo Matching Algorithm hsgm: Hierarchical Pyramid Based Stereo Matching Algorithm Kwang Hee Won and Soon Ki Jung School of Computer Science and Engineering, College of IT Engineering, Kyungpook National University, 1370 Sankyuk-dong,

More information

Maximum-Likelihood Stereo Correspondence using Field Programmable Gate Arrays

Maximum-Likelihood Stereo Correspondence using Field Programmable Gate Arrays Maximum-Likelihood Stereo Correspondence using Field Programmable Gate Arrays Siraj Sabihuddin & W. James MacLean Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario,

More information

VHDL Description of a Synthetizable and Reconfigurable Real-Time Stereo Vision Processor

VHDL Description of a Synthetizable and Reconfigurable Real-Time Stereo Vision Processor VHDL Description of a Synthetizable and Reconfigurable Real-Time Stereo Vision Processor CARLOS CUADRADO AITZOL ZULOAGA JOSÉ L. MARTÍN JESÚS LÁZARO JAIME JIMÉNEZ Dept. of Electronics and Telecommunications

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

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

Stereo Vision II: Dense Stereo Matching

Stereo Vision II: Dense Stereo Matching Stereo Vision II: Dense Stereo Matching Nassir Navab Slides prepared by Christian Unger Outline. Hardware. Challenges. Taxonomy of Stereo Matching. Analysis of Different Problems. Practical Considerations.

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

Accelerating Pattern Matching or HowMuchCanYouSlide?

Accelerating Pattern Matching or HowMuchCanYouSlide? Accelerating Pattern Matching or HowMuchCanYouSlide? Ofir Pele and Michael Werman School of Computer Science and Engineering The Hebrew University of Jerusalem {ofirpele,werman}@cs.huji.ac.il Abstract.

More information

TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA

TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi, Francois de Sorbier and Hideo Saito Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku,

More information

CS5670: Computer Vision

CS5670: Computer Vision CS5670: Computer Vision Noah Snavely, Zhengqi Li Stereo Single image stereogram, by Niklas Een Mark Twain at Pool Table", no date, UCR Museum of Photography Stereo Given two images from different viewpoints

More information

Pattern Feature Detection for Camera Calibration Using Circular Sample

Pattern Feature Detection for Camera Calibration Using Circular Sample Pattern Feature Detection for Camera Calibration Using Circular Sample Dong-Won Shin and Yo-Sung Ho (&) Gwangju Institute of Science and Technology (GIST), 13 Cheomdan-gwagiro, Buk-gu, Gwangju 500-71,

More information

Perceptual Grouping from Motion Cues Using Tensor Voting

Perceptual Grouping from Motion Cues Using Tensor Voting Perceptual Grouping from Motion Cues Using Tensor Voting 1. Research Team Project Leader: Graduate Students: Prof. Gérard Medioni, Computer Science Mircea Nicolescu, Changki Min 2. Statement of Project

More information

A Low Power, High Throughput, Fully Event-Based Stereo System: Supplementary Documentation

A Low Power, High Throughput, Fully Event-Based Stereo System: Supplementary Documentation A Low Power, High Throughput, Fully Event-Based Stereo System: Supplementary Documentation Alexander Andreopoulos, Hirak J. Kashyap, Tapan K. Nayak, Arnon Amir, Myron D. Flickner IBM Research March 25,

More information

A novel 3D torso image reconstruction procedure using a pair of digital stereo back images

A novel 3D torso image reconstruction procedure using a pair of digital stereo back images Modelling in Medicine and Biology VIII 257 A novel 3D torso image reconstruction procedure using a pair of digital stereo back images A. Kumar & N. Durdle Department of Electrical & Computer Engineering,

More information

Beyond Bags of Features

Beyond Bags of Features : for Recognizing Natural Scene Categories Matching and Modeling Seminar Instructed by Prof. Haim J. Wolfson School of Computer Science Tel Aviv University December 9 th, 2015

More information

Asymmetric 2 1 pass stereo matching algorithm for real images

Asymmetric 2 1 pass stereo matching algorithm for real images 455, 057004 May 2006 Asymmetric 21 pass stereo matching algorithm for real images Chi Chu National Chiao Tung University Department of Computer Science Hsinchu, Taiwan 300 Chin-Chen Chang National United

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

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

Lecture 16: Computer Vision

Lecture 16: Computer Vision CS442/542b: Artificial ntelligence Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field Methods

More information

Lecture 16: Computer Vision

Lecture 16: Computer Vision CS4442/9542b: Artificial Intelligence II Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field

More information

Computer Vision. 3D acquisition

Computer Vision. 3D acquisition è Computer 3D acquisition Acknowledgement Courtesy of Prof. Luc Van Gool 3D acquisition taxonomy s image cannot currently be displayed. 3D acquisition methods Thi passive active uni-directional multi-directional

More information

Stereo-Matching Techniques Optimisation Using Evolutionary Algorithms

Stereo-Matching Techniques Optimisation Using Evolutionary Algorithms Stereo-Matching Techniques Optimisation Using Evolutionary Algorithms Vitoantonio Bevilacqua, Giuseppe Mastronardi, Filippo Menolascina, and Davide Nitti Dipartimento di Elettrotecnica ed Elettronica,

More information

Real-time Corner and Polygon Detection System on FPGA. Chunmeng Bi and Tsutomu Maruyama University of Tsukuba

Real-time Corner and Polygon Detection System on FPGA. Chunmeng Bi and Tsutomu Maruyama University of Tsukuba Real-time Corner and Polygon Detection System on FPGA Chunmeng Bi and Tsutomu Maruyama University of Tsukuba Outline Introduction Algorithms FPGA Implementation Experimental Results Conclusions and Future

More information

Disparity Search Range Estimation: Enforcing Temporal Consistency

Disparity Search Range Estimation: Enforcing Temporal Consistency MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Disparity Search Range Estimation: Enforcing Temporal Consistency Dongbo Min, Sehoon Yea, Zafer Arican, Anthony Vetro TR1-13 April 1 Abstract

More information

Wikipedia - Mysid

Wikipedia - Mysid Wikipedia - Mysid Erik Brynjolfsson, MIT Filtering Edges Corners Feature points Also called interest points, key points, etc. Often described as local features. Szeliski 4.1 Slides from Rick Szeliski,

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

Epipolar Geometry CSE P576. Dr. Matthew Brown

Epipolar Geometry CSE P576. Dr. Matthew Brown Epipolar Geometry CSE P576 Dr. Matthew Brown Epipolar Geometry Epipolar Lines, Plane Constraint Fundamental Matrix, Linear solution + RANSAC Applications: Structure from Motion, Stereo [ Szeliski 11] 2

More information

OpenCL-Based Design of an FPGA Accelerator for Phase-Based Correspondence Matching

OpenCL-Based Design of an FPGA Accelerator for Phase-Based Correspondence Matching 90 Int'l Conf. Par. and Dist. Proc. Tech. and Appl. PDPTA'15 OpenCL-Based Design of an FPGA Accelerator for Phase-Based Correspondence Matching Shunsuke Tatsumi, Masanori Hariyama, Mamoru Miura, Koichi

More information

Local invariant features

Local invariant features Local invariant features Tuesday, Oct 28 Kristen Grauman UT-Austin Today Some more Pset 2 results Pset 2 returned, pick up solutions Pset 3 is posted, due 11/11 Local invariant features Detection of interest

More information

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

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

More information

Dominant plane detection using optical flow and Independent Component Analysis

Dominant plane detection using optical flow and Independent Component Analysis Dominant plane detection using optical flow and Independent Component Analysis Naoya OHNISHI 1 and Atsushi IMIYA 2 1 School of Science and Technology, Chiba University, Japan Yayoicho 1-33, Inage-ku, 263-8522,

More information

A SXGA 3D Display Processor with Reduced Rendering Data and Enhanced Precision

A SXGA 3D Display Processor with Reduced Rendering Data and Enhanced Precision A SXGA 3D Display Processor with Reduced Rendering Data and Enhanced Precision Seok-Hoon Kim KAIST, Daejeon, Republic of Korea I. INTRODUCTION Recently, there has been tremendous progress in 3D graphics

More information

Error Analysis of Feature Based Disparity Estimation

Error Analysis of Feature Based Disparity Estimation Error Analysis of Feature Based Disparity Estimation Patrick A. Mikulastik, Hellward Broszio, Thorsten Thormählen, and Onay Urfalioglu Information Technology Laboratory, University of Hannover, Germany

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

Stereo Vision. MAN-522 Computer Vision

Stereo Vision. MAN-522 Computer Vision Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in

More information

Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement

Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement Integration of Multiple-baseline Color Stereo Vision with Focus and Defocus Analysis for 3D Shape Measurement Ta Yuan and Murali Subbarao tyuan@sbee.sunysb.edu and murali@sbee.sunysb.edu Department of

More information

Computer Vision I. Announcements. Random Dot Stereograms. Stereo III. CSE252A Lecture 16

Computer Vision I. Announcements. Random Dot Stereograms. Stereo III. CSE252A Lecture 16 Announcements Stereo III CSE252A Lecture 16 HW1 being returned HW3 assigned and due date extended until 11/27/12 No office hours today No class on Thursday 12/6 Extra class on Tuesday 12/4 at 6:30PM in

More information

Light Field Occlusion Removal

Light Field Occlusion Removal Light Field Occlusion Removal Shannon Kao Stanford University kaos@stanford.edu Figure 1: Occlusion removal pipeline. The input image (left) is part of a focal stack representing a light field. Each image

More information

Understanding Clustering Supervising the unsupervised

Understanding Clustering Supervising the unsupervised Understanding Clustering Supervising the unsupervised Janu Verma IBM T.J. Watson Research Center, New York http://jverma.github.io/ jverma@us.ibm.com @januverma Clustering Grouping together similar data

More information

HIGH-SPEED IMAGE FEATURE DETECTION USING FPGA IMPLEMENTATION OF FAST ALGORITHM

HIGH-SPEED IMAGE FEATURE DETECTION USING FPGA IMPLEMENTATION OF FAST ALGORITHM HIGH-SPEED IMAGE FEATURE DETECTION USING FPGA IMPLEMENTATION OF FAST ALGORITHM Marek Kraft, Adam Schmidt and Andrzej Kasiński Institute of Control and Information Engineering, Poznań University of Technology,

More information

Computer Vision I - Appearance-based Matching and Projective Geometry

Computer Vision I - Appearance-based Matching and Projective Geometry Computer Vision I - Appearance-based Matching and Projective Geometry Carsten Rother 01/11/2016 Computer Vision I: Image Formation Process Roadmap for next four lectures Computer Vision I: Image Formation

More information

Inexpensive Construction of a 3D Face Model from Stereo Images

Inexpensive Construction of a 3D Face Model from Stereo Images Inexpensive Construction of a 3D Face Model from Stereo Images M. Shahriar Hossain, Monika Akbar and J. Denbigh Starkey Department of Computer Science, Montana State University, Bozeman, MT 59717, USA.

More information

Stereo Vision Image Processing Strategy for Moving Object Detecting

Stereo Vision Image Processing Strategy for Moving Object Detecting Stereo Vision Image Processing Strategy for Moving Object Detecting SHIUH-JER HUANG, FU-REN YING Department of Mechanical Engineering National Taiwan University of Science and Technology No. 43, Keelung

More information

Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-baseline Stereo Using a Hand-held Video Camera

Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-baseline Stereo Using a Hand-held Video Camera Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-baseline Stereo Using a Hand-held Video Camera Tomokazu Satoy, Masayuki Kanbaray, Naokazu Yokoyay and Haruo Takemuraz ygraduate School of Information

More information

Stereo imaging ideal geometry

Stereo imaging ideal geometry Stereo imaging ideal geometry (X,Y,Z) Z f (x L,y L ) f (x R,y R ) Optical axes are parallel Optical axes separated by baseline, b. Line connecting lens centers is perpendicular to the optical axis, and

More information

High Performance Hardware Architectures for A Hexagon-Based Motion Estimation Algorithm

High Performance Hardware Architectures for A Hexagon-Based Motion Estimation Algorithm High Performance Hardware Architectures for A Hexagon-Based Motion Estimation Algorithm Ozgur Tasdizen 1,2,a, Abdulkadir Akin 1,2,b, Halil Kukner 1,2,c, Ilker Hamzaoglu 1,d, H. Fatih Ugurdag 3,e 1 Electronics

More information

High Speed Pipelined Architecture for Adaptive Median Filter

High Speed Pipelined Architecture for Adaptive Median Filter Abstract High Speed Pipelined Architecture for Adaptive Median Filter D.Dhanasekaran, and **Dr.K.Boopathy Bagan *Assistant Professor, SVCE, Pennalur,Sriperumbudur-602105. **Professor, Madras Institute

More information

Scalable Hierarchical Summarization of News Using Fidelity in MPEG-7 Description Scheme

Scalable Hierarchical Summarization of News Using Fidelity in MPEG-7 Description Scheme Scalable Hierarchical Summarization of News Using Fidelity in MPEG-7 Description Scheme Jung-Rim Kim, Seong Soo Chun, Seok-jin Oh, and Sanghoon Sull School of Electrical Engineering, Korea University,

More information

Geometric Reconstruction Dense reconstruction of scene geometry

Geometric Reconstruction Dense reconstruction of scene geometry Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual

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

Applying Synthetic Images to Learning Grasping Orientation from Single Monocular Images

Applying Synthetic Images to Learning Grasping Orientation from Single Monocular Images Applying Synthetic Images to Learning Grasping Orientation from Single Monocular Images 1 Introduction - Steve Chuang and Eric Shan - Determining object orientation in images is a well-established topic

More information