A corner matching method based on feature optical flow and weighted Hausdorff distance

This paper presents a corner matching method based on feature optical flow estimation and weighted Hausdorff distance. First of all, the feature corners are extracted. In order to make the corners distribute evenly, image partitioning and neighboring corner being eliminated are adopted. Secondly, judging from the improved approach of feature optical flow estimation, the local optical flow estimation on the corners can be calculated, rough optical flow vectors are gained and approximate matching of the corners is achieved. At the last, through the introduction of the corner response function, a weighted Hausdorff distance method is proposed. In this way, the corners of the two images can be accurately matched. The experimental results show that the presented method can reduce the computational complexity and raise matching precision, and then the precise moving object tracking is realized.