Stereo Matching Algorithm for Improved Acquisition of Disparity Of Tiny Objects

Deep-learning algorithms have an excellent nonlinear fitting ability. However, tiny objects in images do not approach the general properties of the fit, which causes the algorithms to have problems acquiring disparity for tiny objects. In addition, the results suffer from problems such as disparity inflation and warping variation. To address the shortcomings of deep learning algorithms, we propose an improved deep learning algorithm based on traditional algorithms. First, the algorithm divides the image into segments based on edges. Second, the edge error disparity and disparity expansion is corrected. Third, it finds the wrong disparity in a small segment, and removes it. The adjacent pixels with disparity removed are grouped into clusters. The matching relationship is established by combining the cluster’s gray, gradient, and feature-point information into matching elements. Finally, removal of disparity warping variation and post-processing is performed. The algorithm can effectively correct error disparity, detect the disparity of tiny objects, and can be applied to practical scenarios where tiny objects are detected.