Joint Histogram Based Cost Aggregation For Stereo Matching Dongbo Min, Member, IEEE, Jiangbo Lu, Member, IEEE, Minh N. Do, Senior Member, IEEE IEEE TRANSACTION.

Slides:



Advertisements
Similar presentations
An Adaptive Learning Method for Target Tracking across Multiple Cameras Kuan-Wen Chen, Chih-Chuan Lai, Yi-Ping Hung, Chu-Song Chen National Taiwan University.
Advertisements

Improved Census Transforms for Resource-Optimized Stereo Vision
People Counting and Human Detection in a Challenging Situation Ya-Li Hou and Grantham K. H. Pang IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART.
Spatial-Temporal Consistency in Video Disparity Estimation ICASSP 2011 Ramsin Khoshabeh, Stanley H. Chan, Truong Q. Nguyen.
Xin Zhang, Zhichao Ye, Lianwen Jin, Ziyong Feng, and Shaojie Xu
Cuong Cao Pham and Jae Wook Jeon, Member, IEEE
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.
Vision Based Control Motion Matt Baker Kevin VanDyke.
Adviser:Ming-Yuan Shieh Student:shun-te chuang SN:M
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Chih-Hsing Lin, Jia-Shiuan Tsai, and Ching-Te Chiu
Yung-Lin Huang, Yi-Nung Liu, and Shao-Yi Chien Media IC and System Lab Graduate Institute of Networking and Multimedia National Taiwan University Signal.
{ Fast Disparity Estimation Using Spatio- temporal Correlation of Disparity Field for Multiview Video Coding Wei Zhu, Xiang Tian, Fan Zhou and Yaowu Chen.
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
1 Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion (IEEE 2009) Junlan Yang University of Illinois,Chicago.
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
Adaptive Rao-Blackwellized Particle Filter and It’s Evaluation for Tracking in Surveillance Xinyu Xu and Baoxin Li, Senior Member, IEEE.
Object Recognition Using Geometric Hashing
Effective Gaussian mixture learning for video background subtraction Dar-Shyang Lee, Member, IEEE.
Aleixo Cambeiro Barreiro 광주과학기술원 컴퓨터 비전 연구실
100+ Times Faster Weighted Median Filter [cvpr ‘14]
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 11, NOVEMBER 2011 Qian Zhang, King Ngi Ngan Department of Electronic Engineering, the Chinese university.
Fast Cost-volume Filtering For Visual Correspondence and Beyond Asmaa Hosni, Member, IEEE, Christoph Rhemann, Michael Bleyer, Member, IEEE, Carsten Rother,
Stereo Matching Information Permeability For Stereo Matching – Cevahir Cigla and A.Aydın Alatan – Signal Processing: Image Communication, 2013 Radiometric.
Tracking Pedestrians Using Local Spatio- Temporal Motion Patterns in Extremely Crowded Scenes Louis Kratz and Ko Nishino IEEE TRANSACTIONS ON PATTERN ANALYSIS.
Noise-Robust Spatial Preprocessing Prior to Endmember Extraction from Hyperspectral Data Gabriel Martín, Maciel Zortea and Antonio Plaza Hyperspectral.
Fast Approximate Energy Minimization via Graph Cuts
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
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.
Graph Cut 韋弘 2010/2/22. Outline Background Graph cut Ford–Fulkerson algorithm Application Extended reading.
1 Color-Based Image Salient Region Segmentation Using Novel Region Merging Strategy IEEE Transaction on Multimedia 2008 Yu-Hsin Kuan, Chung Ming Kuo, and.
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.
Cross-Based Local Multipoint Filtering
A Non-local Cost Aggregation Method for Stereo Matching
Marco Pedersoli, Jordi Gonzàlez, Xu Hu, and Xavier Roca
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
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
A New Fingertip Detection and Tracking Algorithm and Its Application on Writing-in-the-air System The th International Congress on Image and Signal.
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
1 Real-Time Stereo-Matching for Micro Air Vehicles Pascal Dufour Master Thesis Presentation.
Window-based Approach For Fast Stereo Correspondence Raj Kumar Gupta, Siu-Yeung Cho IET Computer Vision,
DSP final project proosal From Bilateral-filter to Trilateral-filter : A better improvement on denoising of images R 張錦文.
Fingertip Detection with Morphology and Geometric Calculation Dung Duc Nguyen ; Thien Cong Pham ; Jae Wook Jeon Intelligent Robots and Systems, IEEE/RSJ.
Fast Cost-volume Filtering For Visual Correspondence and Beyond Asmaa Hosni, Member, IEEE, Christoph Rhemann, Michael Bleyer, Member, IEEE, Carsten Rother,
Improved Census Transforms for Resource-Optimized Stereo Vision
Jeong Kanghun CRV (Computer & Robot Vision) Lab..
Journal of Visual Communication and Image Representation
Efficient Stereo Matching Based on a New Confidence Metric
A global approach Finding correspondence between a pair of epipolar lines for all pixels simultaneously Local method: no guarantee we will have one to.
Stereo Video 1. Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos 2. Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral.
Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation Dah-Chung Chang* and Wen-Rong Wu, Member, IEEE IEEE TRANSACTIONS.
An H.264-based Scheme for 2D to 3D Video Conversion Mahsa T. Pourazad Panos Nasiopoulos Rabab K. Ward IEEE Transactions on Consumer Electronics 2009.
WLD: A Robust Local Image Descriptor Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, Wen Gao 报告人:蒲薇榄.
A Fast Video Noise Reduction Method by Using Object-Based Temporal Filtering Thou-Ho (Chao-Ho) Chen, Zhi-Hong Lin, Chin-Hsing Chen and Cheng-Liang Kao.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
Local Stereo Matching Using Motion Cue and Modified Census in Video Disparity Estimation Zucheul Lee, Ramsin Khoshabeh, Jason Juang and Truong Q. Nguyen.
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
A. M. R. R. Bandara & L. Ranathunga
Summary of “Efficient Deep Learning for Stereo Matching”
Efficient Image Classification on Vertically Decomposed Data
SoC and FPGA Oriented High-quality Stereo Vision System
Student: Wanli Ouyang (歐陽萬里) Supervisor: Prof. W.K. Cham
Efficient Image Classification on Vertically Decomposed Data
Using Association Rules as Texture features
Presentation transcript:

Joint Histogram Based Cost Aggregation For Stereo Matching Dongbo Min, Member, IEEE, Jiangbo Lu, Member, IEEE, Minh N. Do, Senior Member, IEEE IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013

Outline Introduction Related Works Proposed Method : Improve Cost Aggregation Experimental Results Conclusion

Introduction

Goal : Perform efficient cost aggregation. Solution : Joint histogram + reduce redundancy Advantage : Low complexity but keep high-quality.

Related Works

Complexity of aggregation : O(NBL) Reduce complexity approach Scale image [8] Bilateral filter [9,10] Geodesic diffusion [11] Guided filter [12] =>O(NL) N : all pixels (W*H) B : window size L : disparity level

Reference Paper [8] D. Min and K. Sohn, “Cost aggregation and occlusion handling with WLS in stereo matching,” IEEE Trans. on Image Processing, [9] C. Richardt, D. Orr, I. P. Davies, A. Criminisi, and N. A. Dodgson, “Real-time spatiotemporal stereo matching using the dual-cross- bilateral grid,” in European Conf. on Computer Vision, 2010 [10] S. Paris and F. Durand, “A fast approximation of the bilateral filter using a signal processing approach,” International Journal of Computer Vision, [11] L. De-Maeztu, A. Villanueva, and R. Cabeza, “Near real-time stereo matching using geodesic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell., [12] C.Rhemann,A.Hosni,M.Bleyer,C.Rother,andM.Gelautz,“Fast cost-volume filtering for visual correspondence and beyond,” in IEEE Conf. on Computer Vision and Pattern Recognition, 2011

Proposed Method

Local Method Algorithm Cost initialization=>Truncated Absolute Difference => Cost aggregation=>Weighted filter Disparity computation=>Winner take all [4,8] [4] K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 4, pp. 650–656, [8] D. Min and K. Sohn, “Cost aggregation and occlusion handling with WLS in stereo matching,” IEEE Trans. on Image Processing, vol. 17, no. 8, pp. 1431–1442, 2008.

Improve Cost Aggregation New formulation for aggregation Remove normalization Joint histogram representaion Compact representation for search range Reduce disparity levels Spatial sampling of matching window Regularly sampled neighboring pixels Pixel-independent sampling

New formulation for aggregation Remove normalization => Joint histogram representaion

Compact Search Range Reason The complexity of non-linear filtering is very high. Lower cost values do NOT provide really influence. Solution Choose the local maximum points. Only select D c (<<D) with descending order to be disparity candidates.

Compact Search Range Cost aggregation => M C (q) : a subset of disparity levels whose size is D c. O( NBD ) O( NBD c ) N : all pixels (W*H) B : window size D : disparity level

D c = 60 Final acc. = 93.7% D c = 60 Final acc. = 93.7% Compact Search Range Non-occluded region of ‘Teddy’ image D c = 6 Include GT = 91.8% Final acc. = 94.1% D c = 6 Include GT = 91.8% Final acc. = 94.1% D c = 5 (Best) Final acc. = 94.2% D c = 5 (Best) Final acc. = 94.2%

Spatial Sampling of Matching Window Reason A large matching window and a well-defined weighting function leads to high complexity. Pixels should aggregate in the same object, NOT in the window. Solution Color segmentation => time comsuming Spatial sampling => easy but powerful ●●● ●●●●● ● ●●● ●●●●● ● ●●● ●●●●● ● ●●● ●●●

Spatial Sampling of Matching Window Cost aggregation => S : sampling ratio O( NBD c ) O( NBD c / S 2 )

Parameter definition N : size of image B : size of matching window N(p)=W×W M D : disparity levels size=D M C : The subset of disparity size=D C <<D S : Sampling ratio Pre-procseeing

Experimental Results

Pre-processing 5*5 Box filter Post-processing Cross-checking technique Weighted median filter (WMF) Device : Intel Xeon 2.8-GHz CPU (using a single core only) and a 6-GB RAM Parameter setting ( ) = (1.5, 1.7, 31*31, 0.11, 13.5, 2.0)

Experimental Results (a)(b) (c)(d)

Experimental Results Using too large box windows (7×7, 9×9) deteriorates the quality, and incurs more computational overhead. Pre-filtering can be seen as the first cost aggregation step and serves the removal of noise.

Experimental Results Fig. 5. Performance evaluation: average percent (%) of bad matching pixels for ‘nonocc’, ‘all’ and ‘disc’ regions according to Dc and S. 2 better than 1 The smaller S, the better

Experimental Results The smaller S, the longer The bigger Dc, the longer

Experimental Results APBP : Average Percentage of Bad Pixels

Ground truth Error maps ResultsOriginal images

Experimental Results

Conclusion

Contribution Re-formulate the problem with the relaxed joint histogram. Reduce the complexity of the joint histogram-based aggregation. Achieved both accuracy and efficiency. Future work More elaborate algorithms for selecting the subset of label hypotheses. Estimate the optimal number Dc adaptively. Extend the method to an optical flow estimation.