基于颜色块重检的自适应抗遮挡目标跟踪算法

为了解决目标跟踪过程中目标遇到遮挡物容易跟丢的问题，提出了基于颜色块重检的自适应抗遮挡目标跟踪算法。通过计算获取初始帧目标的颜色块，当发生遮挡时基于该颜色块信息对丢失帧进行颜色分割、形态学处理得到候选颜色块，并对候选颜色块进行匹配和定位，最终定位到实际目标。相比于LCT+的支持向量机检测器，基于颜色块的自适应目标重检测实现了对全局图像的目标重检测，有效避免了目标丢失的情况。在OTB50和OTB100上对所提算法的跟踪性能进行了评估，结果表明相比于LCT+和其他的主流跟踪算法，所提算法具有较好的抗遮挡性能。

Adaptive Anti-Occlusion Target Tracking Algorithm Based on Color Block Re-Detection

In order to solve the problem that the target is easy to be lost when encountering occlusions in the target tracking process, an adaptive anti-occlusion target tracking algorithm based on color block re-detection is proposed. Firstly, the color block information of the target intheinitial frame is obtained by calculation. When occlusion occurs, the candidate color block is obtained by color segmentation and morphological processing of the lost frame based on that color block information. Then, the candidate color block is matched and located, and finally the actual target is located.Compared with LCT+ support vector machine detector, the adaptive target re-detection of lost frames based on color blocks realizes the target re-detection of global image, effectively avoiding target loss. The tracking performance of the algorithm is evaluated on the OTB50 and OTB100. Experimental results show that the proposed algorithm has better performance in comparison with LCT+ and other mainstream tracking algorithms.