基于HVS的视频监控目标提取方法研究

HVS-based object detection algorithm for surveillance video

目标识别是实现视频监控智能分析的基础,但在光照、阴影以及杂乱背景等场景中,往往会出现目标误判以及不合理聚类等问题。针对上述问题,提出一种基于人类视觉系统(HVS)的视频监控目标提取方法。结合HVS视觉关注原理,优化背景差法检测结果中存在的重复检测和错误分割问题,并根据HVS的跟踪特点以及目标运动的连续性,结合相邻帧检测结果以达到目标区域的完整准确提取。最后,基于实际采集视频进行仿真实验,证明所提目标检测算法结果准确性更高,在复杂背景下也有良好的检测效果。

Object detection is the basis of intelligent analysis, however, in the scene of illumination, shadow and clutter background, the problems of object misjudgment and unreasonable clustering are often appeared. Aiming at the above problems, this paper proposed a HVS-based object detection algorithm, which could optimize the error judgment and segmentation. According to the tracking characteristic of HVS and the continuity of object movement, the algorithm combined the detection results of adjacent frames to extract object area completely and accurately. Finally, the simulation experiment based on the actual acquisition videos shows that the proposed algorithm is more accurate and has good effect in complex background.