High efficiency and accuracy of semi-global matching (SGM) make it widely used in many stereo vision applications. However, SGM not only struggles in dealing with pixels in homogeneous area, but also suffers from streak artifacts. In this paper, we propose a novel omni-directional SGM (OmniSGM) with a cost volume update scheme to aggregate costs from paths along all directions and to encourage reliable information to propagate across entire image. Specifically, we perform SGM along four tree structures, namely trees in the left, right, top and bottom of root node, and then fuse the outputs to obtain final result. The contributions of pixels on each tree can be recursively computed from leaf nodes to root node, ensuring our method has linear time computational complexity. Moreover, An iterative cost volume update scheme is proposed using aggregated cost in the last pass to enhance the robustness of initial matching cost. Thus, useful information is more likely to propagate in a long distance to handle the ambiguities in low textural area. Finally, we present an efficient strategy to propagate disparities of stable pixels along the minimum spanning tree (MST) for disparity refinement. Extensive experiments in stereo matching on Middlebury and KITTI datasets demonstrate that our method outperforms typical traditional SGM-based cost aggregation methods.

Surface mounted device-type light emitting diodes (SMD-LEDs) are commonly utilized as feature points in target-based vision measurement systems (T-VMSs) due to their high luminance. The non-uniform characteristics of said luminance introduce deviation errors in image center extraction, however, which degrades the positioning precision of the T-VMS. In this study, we first analyzed two factors responsible for deviation errors: The deflection angle between the LED's normal direction and the observation direction, and the distance between the LED and the observer. We then established a correction method based on a lookup table to compensate for deviation errors according to these two factors. We also analyzed the correction direction of the deviation error. We applied the proposed method in an actual T-VMS to confirm its feasibility and effectiveness, and found that it does indeed correct deviation errors effectively.