A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.

Slides:



Advertisements
Similar presentations
CSE473/573 – Stereo and Multiple View Geometry
Advertisements

Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting IEEE Computer Society Conference on Computer Vision and Pattern Recognition Jiaya.
Efficient High-Resolution Stereo Matching using Local Plane Sweeps Sudipta N. Sinha, Daniel Scharstein, Richard CVPR 2014 Yongho Shin.
Vision REU Week 3. Image registration  Used mutual information-based registration from ITK Ben SchoepkeREU Week 36/8/07 Fixed imageMoving image Pre-registrationPost-registration.
Spatial-Temporal Consistency in Video Disparity Estimation ICASSP 2011 Ramsin Khoshabeh, Stanley H. Chan, Truong Q. Nguyen.
M.S. Student, Hee-Jong Hong
Real-Time Accurate Stereo Matching using Modified Two-Pass Aggregation and Winner- Take-All Guided Dynamic Programming Xuefeng Chang, Zhong Zhou, Yingjie.
Stereo Matching Segment-based Belief Propagation Iolanthe II racing in Waitemata Harbour.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
On Constrained Optimization Approach To Object Segmentation Chia Han, Xun Wang, Feng Gao, Zhigang Peng, Xiaokun Li, Lei He, William Wee Artificial Intelligence.
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
Computer Vision : CISC 4/689 Adaptation from: Prof. James M. Rehg, G.Tech.
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 11, NOVEMBER 2011 Qian Zhang, King Ngi Ngan Department of Electronic Engineering, the Chinese university.
Manhattan-world Stereo Y. Furukawa, B. Curless, S. M. Seitz, and R. Szeliski 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.
Graph-based consensus clustering for class discovery from gene expression data Zhiwen Yum, Hau-San Wong and Hongqiang Wang Bioinformatics, 2007.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’04) /04 $20.00 c 2004 IEEE 1 Li Hong.
Joint Histogram Based Cost Aggregation For Stereo Matching Dongbo Min, Member, IEEE, Jiangbo Lu, Member, IEEE, Minh N. Do, Senior Member, IEEE IEEE TRANSACTION.
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Stereo Matching Low-Textured Survey 1.Stereo Matching-Based Low-Textured Scene Reconstruction for Autonomous Land Vehicles (ALV) Navigation 2.A Robust.
Stereo Matching Information Permeability For Stereo Matching – Cevahir Cigla and A.Aydın Alatan – Signal Processing: Image Communication, 2013 Radiometric.
Computer Vision James Hays, Brown
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space Yong Seok Heo, Kyoung Mu Lee, and Sang Uk Lee.
ICPR/WDIA-2012 High Quality Novel View Synthesis Based on Low Resolution Depth Image and High Resolution Color Image Jui-Chiu Chiang, Zheng-Feng Liu, and.
Mean-shift and its application for object tracking
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Characterizing activity in video shots based on salient points Nicolas Moënne-Loccoz Viper group Computer vision & multimedia laboratory University of.
A Local Adaptive Approach for Dense Stereo Matching in Architectural Scene Reconstruction C. Stentoumis 1, L. Grammatikopoulos 2, I. Kalisperakis 2, E.
Joint Depth Map and Color Consistency Estimation for Stereo Images with Different Illuminations and Cameras Yong Seok Heo, Kyoung Mu Lee and Sang Uk Lee.
Rohith MV, Gowri Somanath, Chandra Kambhamettu Video/Image Modeling and Synthesis(VIMS) Lab, Dept. of Computer and Information Sciences Cathleen Geiger.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
Takuya Matsuo, Norishige Fukushima and Yutaka Ishibashi
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
A Non-local Cost Aggregation Method for Stereo Matching
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
Scientific Writing Abstract Writing. Why ? Most important part of the paper Number of Readers ! Make people read your work. Sell your work. Make your.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 34, NO. 2, FEBRUARY Leonardo De-Maeztu, Arantxa Villanueva, Member, IEEE, and.
Object Detection with Discriminatively Trained Part Based Models
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
EECS 274 Computer Vision Segmentation by Clustering II.
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
1 Markov Random Fields with Efficient Approximations Yuri Boykov, Olga Veksler, Ramin Zabih Computer Science Department CORNELL UNIVERSITY.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
18 th August 2006 International Conference on Pattern Recognition 2006 Epipolar Geometry from Two Correspondences Michal Perďoch, Jiří Matas, Ondřej Chum.
Real-Time Tracking with Mean Shift Presented by: Qiuhua Liu May 6, 2005.
CSSE463: Image Recognition Day 23 Midterm behind us… Midterm behind us… Foundations of Image Recognition completed! Foundations of Image Recognition completed!
Segmentation- Based Stereo Michael Bleyer LVA Stereo Vision.
Journal of Visual Communication and Image Representation
Stereo Vision Local Map Alignment for Robot Environment Mapping Computer Vision Center Dept. Ciències de la Computació UAB Ricardo Toledo Morales (CVC)
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Photoconsistency constraint C2 q C1 p l = 2 l = 3 Depth labels If this 3D point is visible in both cameras, pixels p and q should have similar intensities.
Detection of nerves in Ultrasound Images using edge detection techniques NIRANJAN TALLAPALLY.
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
南台科技大學 資訊工程系 Region partition and feature matching based color recognition of tongue image 指導教授:李育強 報告者 :楊智雁 日期 : 2010/04/19 Pattern Recognition Letters,
Local Stereo Matching Using Motion Cue and Modified Census in Video Disparity Estimation Zucheul Lee, Ramsin Khoshabeh, Jason Juang and Truong Q. Nguyen.
A Plane-Based Approach to Mondrian Stereo Matching
Summary of “Efficient Deep Learning for Stereo Matching”
Semi-Global Matching with self-adjusting penalties
CSSE463: Image Recognition Day 21
Markov Random Fields with Efficient Approximations
SoC and FPGA Oriented High-quality Stereo Vision System
A segmentation and tracking algorithm
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
CSSE463: Image Recognition Day 23
CSSE463: Image Recognition Day 23
CSSE463: Image Recognition Day 23
CSSE463: Image Recognition Day 23
Presentation transcript:

A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer Vision and Pattern Recognition,

Outline Introduction Algorithmn Experimental Results Conclusion 2

Introduction The stereo correspondence problem is a key point in computer vision. Goal : Find a more reasonable disparity map that closes to the ground truth data. 3

Outline Introduction Algorithmn Experimental Results Conclusion 4

Algorithmn 5

6

Mean-shift algorithm [19] No assumptions about probability distributions. Find local maxima clusters close in space and range correspond to classes. 7 [19] D. Comanicu, P. Meer : “Mean shift: A robust approach toward feature space analysis”, IEEE Trans. Pattern Anal. Machine Intell., May 2002.

Mean-shift algorithm [19] 8 [19] D. Comanicu, P. Meer : “Mean shift: A robust approach toward feature space analysis”, IEEE Trans. Pattern Anal. Machine Intell., May 2002.

Algorithmn 9

Window stereo matching Step 1 Compute a matching cost for each pixel at each disparity Step 2 Aggregate the costs across pixels at the same disparity Step 3 Calculating the best disparities based on the aggregated costs Step 4 Optionally refine the disparities 10

Adaptive correlation window stereo matching algorithm [16] Assumption : depth discontinuities occur at colour boundaries Reduce the outliers wieght A variation window sizes on the recurrsive moving average implementation 11 [16] Mark Gerrits and Philippe Bekaert. “Local Stereo Matching with Segmentation-based Outlier Rejection. ” Third Canadian Conference on Computer and Robot Vision, June 2006.

Adaptive correlation window stereo matching algorithm [16] 12 [16] Mark Gerrits and Philippe Bekaert. “Local Stereo Matching with Segmentation-based Outlier Rejection. ” Third Canadian Conference on Computer and Robot Vision, June 2006.

Algorithmn 13

Disparity plane fitting 14

Disparity plane fitting algorithm based on voting 15

Disparity plane fitting algorithm based on voting (parameter a) 16 Step 1 Do the similar calculations for all possible point pairs on the same lines belonging to the region. Step 2 Make a histogram by a voting operation, where the - coordinate is and the -coordinate is the count number of. Step 3 Do a smoothness operation by a Gaussian filter. Step 4 The maximum of the histogram will be the estimation of.

Disparity plane fitting algorithm comparison 17 The comparison of the plane fitting results based on the RANSAC algorithm(blue) and the voting algorithm(red).

Disparity plane fitting algorithm based on voting 18 The disparities obtained by the plane fitting algorithm based on voting

Algorithmn 19

The cooperative optimization Goal : To optimize the disparity plane parameters of each region such that the disparity plane parameters of the adjacent regions keep consistent. The total energy function E(x) of all regions is defined as E(x) = E 1 (x) + E 2 (x) E n (x) E i (x) : the energy function of the ith region 20

The cooperative optimization 21 The sketch map for optimization of sub-targets

Energy functional of each region 22

Energy functional of each region 23

Energy functional of each region 24

Energy functional of each region 25

Energy functional of each region 26, otherwise

The cooperative optimization 27

The cooperative optimization  The optimization is carried out until the algorithm converges or the number of iteration is reached. 28

The cooperative optimization 29

The cooperative optimization 30

Algorithmn 31

Outline Introduction Algorithmn Experimental Results Conclusion 32

Experimental Results Device : A notebook with CPU of PM1.6G Settings parameters: = 0.5, = 0.5, = 0.5 are set according to [17] Source : Middlebury Time : 20s ( 4 iterations ) Segmentation : 8s 33 [17] Xiaofei Huang. “Cooperative Optimization for Energy Minimization: A Case Study of Stereo Matching”, cs.CV/ , Jan

Experimental Results 34

Experimental Results 35 Black : occluded border regions White : discontinuities

Experimental Results 36

37

Experimental Results 38

Outline Introduction Algorithmn Experimental Results Conclusion 39

Conclusion Contributions Combine some known techniques to obtain the high quality disparity map. The algorithm only requests the initial estimation of disparities is roughly correct. Future works Improve the plane fitting by introducing B-spline fitting technique. Develop a more efficient segmentation algorithm. 40