基于分层光流场的运动车辆检测与跟踪

摘要

Because LK(Lucas Kanade) algorithm can't be stable tracking the fast moving target,this paper proposes a tracking method based on image Layered optical flow algorithm, which can obtain a better result for the large scale of the movement. In the feature extraction,using Harris corner detection method can achieve a high efficiency target detection with angular point as the feature. Experimental results show that in this way the corner points are always steady and reliable when a vehicle is steering and moving,and the tracking algorithm proposed can provide an accurate and real time match for the feature points.%针对LK(Lucas Kanade)算法不能稳定跟踪快速移动目标的局限性,采用一种图像分层光流的跟踪方法,能获得针对目标的大尺度运动的较好预测结果.为了减少计算量,提出一种基于特征角点的光流跟踪技术,首先提取运动车辆的特征角点,计算其光流场,对角点实施跟踪极大地减少了光流计算量,可以满足目标检测实时性的要求.实验表明,当运动车辆转弯和移动时,角点始终稳定可靠,并且跟踪算法能够快速、准确地匹配特征焦点,实现了复杂交通场景下对运动车辆的实时稳定跟踪.