The amount of computation for detecting moving objects by the optical flow\nalgorithm is large. The optical flow information in the smooth region cannot\nbe detected by the optical flow algorithm, and it is susceptible to noise in a\ncomplicated environment. In this study, an optimized Horn-Schunck (HS)\noptical flow algorithm based on motion estimation is proposed. To detect\nHarris corner in the image, the proposed algorithm is used in combination\nwith the motion estimation algorithm based on macroblock to determine the\nregion of interest (ROI) [1]. The ROI is then used as the initial motion vector\nfor HS calculation to obtain the optical flow information. Filtering is conducted\nto eliminate the background noise. Experimental result shows that the\napplication of the proposed algorithm improves the computational speed,\navoids the interference of background noise, and enhances the robustness of\nHS. Moreover, the algorithm solves the problem rooted in the inability of the\nHS algorithm to detect the smooth part of optical flow information [2].
Loading....