手势
计算机科学
人工智能
算法
跟踪(教育)
计算机视觉
磁道(磁盘驱动器)
心理学
教育学
操作系统
作者
Lisi Wang,Hua Li,Cheng Han
标识
DOI:10.1109/icvrv51359.2020.00010
摘要
Aiming at the situation that the traditional Camshift algorithm fails to track gestures under complicated backgrounds or short-term occlusions, an improved Camshift algorithm combined with SURF algorithm is proposed to track gestures in real time. In this method, the SURF algorithm is used to initially locate the gesture target. An improved TLD gesture tracking algorithm based on SURF and Camshift is proposed to solve the problem of large calculation amount of TLD algorithm and poor real-time tracking. The experimental results verify that the algorithm has higher accuracy and real-time performance than the traditional Camshift algorithm and the traditional TLD algorithm.
科研通智能强力驱动
Strongly Powered by AbleSci AI