250 likes | 540 Views
Stereo Matching. Aleixo Cambeiro Barreiro 광주과학기술원 컴퓨터 비전 연구실. Index. Abstract Algorithms used Results Conclusion Bibliography. Abstract. Stereo Matching. Process of generation of a depth map for one scene having several pictures of it
E N D
Stereo Matching Aleixo Cambeiro Barreiro 광주과학기술원 컴퓨터 비전 연구실
Index • Abstract • Algorithms used • Results • Conclusion • Bibliography
Stereo Matching • Process of generation of a depth map for one scene having several pictures of it • Achieved by comparing the disparities of the objects’ positions between pixels • Takes into account cameras’ conic fields of vision
Goals • In this experiment we intend to compare several dense stereo matching algorithms • To this end, we have considered: • Time elapsed during computation • Results accuracy
Pixel-wise Matching • Intensity, Winner Takes All pixel-to-pixel comparison Target image Base image O Matching pixel Matching candidates * Current candidate
Patch-wise Matching (I) • Similar to pixel-wise matching • Also takes into account neighbors of the matching pixels to improve accuracy Target image Base image O Matching pixel Matching candidates * Current candidate x Current neighbor
Patch-wise Matching (II) • It can be subdivided according to the way the patches are compared • We have tested the following two comparison methods: • Sum of Absolute Differences (SAD): • Sums differences between corresponding pixels in both patches • This absolute differences sum is used as matching cost • Doesn’t take into account depth differences between pixels in the same patch • Adaptive Support-Weight: • Similar to SAD, but weights are added to intensity differences to take into account depth disparities between pixels in the same patch, according to next equation:
Semi-Global Matching (SGM) • Uses pixel-wise matching as a base cost • Adds an one-dimensional, multidirectional smoothness constraint • This generates an energy function that should be minimized • The minimization can be efficiently achieved through dynamic programming • Cost is propagated according to the next equation:
Depth maps (Cones) Base image Ground truth Pixel-wise SAD 11x11 SAD 35x35 ASW 11x11 SGM ASW 35x35
Depth maps (Teddy) SAD 11x11 Base image Ground truth Pixel-wise SGM SAD 35x35 ASW 11x11 ASW 35x35
Depth maps (Tsukuba) Base image Ground truth Pixel-wise SAD 11x11 ASW 35x35 SGM SAD 35x35 ASW 11x11
Depth maps (Venus) Base image Ground truth Pixel-wise SAD 11x11 ASW 35x35 SGM SAD 35x35 ASW 11x11
Pixel-wise Matching • Offers very poor results, for one-to-one, intensity based comparison is not robust against: • Image noise • Illumination changes • Groups of pixels with similar intensities • Etc. • It is very fast, but extremely inaccurate
Patch-wise Matching (SAD) • Great improvement of accuracy with respect to Pixel-wise Matching • Problems regarding patch sizing: • Small patches: • The smaller the patch is, the less information we can acquire from neighboring pixels • The Pixel-wise Matching issues are not fully overcome • Big patches: • Disparities discontinuities at object’s edges are not taken into account • Fattening effect • For each match, we have to compare two whole patches • Slower than Pixel-wise Matching, proportionally to the window size (WxH)
Patch-wise Matching (ASW) • Weights make possible to have big size patches without remarkable negative effects • Fattening effect disappears and accuracy is improved • Weights have to be calculated for each neighbor • Slower than SAD matching, but generally more accurate and allows big window sizes
Semi-Global Matching • Obtaining the base cost from the Pixel-wise Matching makes it very fast • Dynamic programming: • Contributes to the speed of processing • Slightly increases the use of memory • The smoothness constraint grants accuracy • This constraint being multidirectional prevents streaking • As a result, this algorithm is very fast and accurate
Bibliography • D. Scharstein, R. Szeliski, R. Zabih, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms“, SMBV’01, 2001. • Kuk-Jin Yoon, In So Kweon, “Adaptive Support-Weight Approach for Correspondence Search”, IEEE transactions on Pattern Analysis and Machine Intelligence, 2006. • HeikoHirschmüller, “Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information”, CVPR, 2005.