Real-time Target Human Tracking using Camshift and LucasKanade Optical Flow Algorithm
Van‐Truong Nguyen, Anh‐Tu Nguyen, Viet-Thang Nguyen, Huy‐Anh Bui, Xuan-Thuan Nguyen · Advances in Science Technology and Engineering Systems Journal · 2021
In this paper, a novel is proposed for real-time tracking human targets in cases of high influence from complexity environment with a normal camera.Firstly, based on Oriented FAST and Rotated BRIEF features, the Lucas-Kanade Optical Flow algorithm is used to track reliable keypoints.This method represents a valuable performance to decline the effect of the illumination or displacement of human targets.Secondly, the area of the human target in the frame is determined more precise by using the Camshift algorithm.Compared to the existing approaches, the proposed method has some merits to some extents including rapid calculations in implementation, high accuracy in case of similar objects detection, the ability to deploy easily on mobile devices.Finally, the effectiveness of the proposed tracking algorithm is demonstrated via experimental results.