Stereo matching: performance study of two global algorithms

Techniques such as clinometry, stereoscopy, interferometry, and polarimetry are used for Digital Elevation Model (DEM) generation from Synthetic Aperture Radar (SAR) images. The choice of technique depends on the SAR configuration, the means used for image acquisition, and the relief type. The most popular techniques are interferometry for regions of high coherence and stereoscopy for regions such as steep forested mountain slopes. Stereo matching, which is finds the disparity map or correspondence points between two images acquired from different sensor positions, is a core process in stereoscopy. Additionally, automatic stereo processing, which involves stereo matching, is an important process in other applications including vision-based obstacle avoidance for unmanned air vehicles (UAVs), extraction of weak targets in clutter, and automatic target detection. Due to its high computational complexity, stereo matching has traditionally been, and continues to be, one of the most heavily investigated topics in computer vision. A stereo matching algorithm performs a subset of the following four steps: cost computation, cost (support) aggregation, disparity computation/optimization, and disparity refinement. Based on the method used for cost computation, the algorithms are classified into feature-, phase-, and area-based algorithms; and they are classified as local or global based on how they perform disparity computation/optimization. We present a comparative performance study of two pairs, i.e., four versions, of global stereo matching codes. Each pair uses a different minimization technique: a simulated annealing or graph cut algorithm. And, the codes of a pair differ in terms of the employed global cost function: absolute difference (AD) or a variation of normalized cross correlation (NCC). The performance comparison is in terms of execution time, the global minimum cost achieved, power and energy consumption, and the quality of generated output. The results of this preliminary study provide insights into the suitability and relative merits of these algorithms and cost functions for execution on field-deployable and on-board computer systems with size, weight, and power (SWaP) constraints. The results show that for 12 out of 14 instances the graph cut codes, compared to their simulated annealing counterparts provided a 35-85% improvement in energy consumption and, therefore, are promising candidates for use in field-deployable and on-board systems.

[1]  Roger V. Bostelman,et al.  RoboCrane Project:: An Advanced Concept for Large Scale Manufacturing , 1996 .

[2]  David S. Wettergreen,et al.  Robotic Planetary Exploration by Sun-Synchronous Navigation , 2001 .

[3]  Alexander Zelinsky,et al.  An algorithm for real-time stereo vision implementation of head pose and gaze direction measurement , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[4]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Richard Szeliski,et al.  Prediction error as a quality metric for motion and stereo , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[6]  Reid G. Simmons,et al.  Stereo vision based navigation for Sun-synchronous exploration , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Wolfgang Förstner,et al.  PHOTOGRAMMETRIC STANDARD METHODS AND DIGITAL IMAGE MATCHING TECHNIQUES FOR HIGH PRECISION SURFACE MEASUREMENTS , 1986 .

[8]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[9]  Martin D. Levine,et al.  Computer determination of depth maps , 1973, Comput. Graph. Image Process..

[10]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[11]  Yuan C. Hsieh,et al.  Performance Evaluation of Scene Registration and Stereo Matching for Artographic Feature Extraction , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Saygin Abdikan,et al.  COMPARING A STEREOSCOPIC DEM WITH AN INTERFEROMETRIC DEM USING THE SAME RADARSAT DATA PAIR , 2006 .

[13]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[14]  Thierry Toutin,et al.  State-of-the-art of elevation extraction from satellite SAR data , 2000 .

[15]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Richard Szeliski,et al.  An Experimental Comparison of Stereo Algorithms , 1999, Workshop on Vision Algorithms.

[17]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  Masatsugu Kidode,et al.  An iterative prediction and correction method for automatic stereocomparison , 1973, Comput. Graph. Image Process..

[19]  Vladimir Kolmogorov,et al.  Minimizing Nonsubmodular Functions with Graph Cuts-A Review , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Margrit Gelautz,et al.  A COMPARATIVE STUDY OF RADAR STEREO AND INTERFEROMETRY FOR DEM GENERATION , 2004 .

[22]  Andrew E. Johnson,et al.  Computer Vision on Mars , 2007, International Journal of Computer Vision.

[23]  Volkan Isler,et al.  Performance evaluation of stereo for tele-presence , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[24]  Annika Kuhl,et al.  Comparison of Stereo Matching Algorithms for Mobile Robots , 2004 .

[25]  J.Y. Fourniols,et al.  A 3D real-time vision system based on passive stereovision algorithms: Application to laparoscopic surgical manipulations , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[26]  John K. Antonio,et al.  Optimal Configuration of Compute Nodes for Synthetic Aperture Radar Processing , 1998, IPPS/SPDP Workshops.

[27]  Kimberly J. Shillcutt,et al.  Solar-based navigation for robotic explorers , 2000 .

[28]  John Iselin Woodfill,et al.  Tyzx DeepSea High Speed Stereo Vision System , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[29]  LeRoy A. Gorham,et al.  SAR image formation toolbox for MATLAB , 2010, Defense + Commercial Sensing.

[30]  B. Roberts,et al.  A system for obstacle detection during rotorcraft low-altitude flight , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[31]  Dale Shires.  Exploiting Parallelism in a Monte Carlo Image-Matching Algorithm. , 1995 .

[32]  R. B. Perlow,et al.  Automatic stereo processing of high resolution radar imagery , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[33]  Franz Leberl,et al.  Automated radar image matching experiment , 1994 .

[34]  LeRoy A. Gorham,et al.  A challenge problem for 2D/3D imaging of targets from a volumetric data set in an urban environment , 2007, SPIE Defense + Commercial Sensing.

[35]  Bruno Schneuwly,et al.  Dynamic workspace monitoring , 1994, Other Conferences.

[36]  Thierry Toutin,et al.  Impact of terrain slope and aspect on radargrammetric DEM accuracy , 2002 .

[37]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..