Camshift算法中搜索区域像素筛选的研究与改进

Research and ImprovementconcerningPix Selecting at the Tracking Areas in CAMSHIFT Algorithm

近年来Camshift由于具有对目标形变不敏感,实时性好等特点而倍受青睐。然而传统的camshift算法仍存在一些缺陷,由于图像质量等原因,需要对目标区域的像素进行选取,以消除这一干扰对生成的颜色直方图带来的误差,本文提出了对搜索窗口大小的调整设置保护措施以及采用自适应筛选阈值的方法防止上述问题。通过实验对比,相比于传统camshift算法,改进的cam-shift算法在对目标跟踪的稳定性和准确性方面有明显的提高,对背景的适应能力更强。

Camshift is a very wonderful object in tracking algorithm, due to the non-sensitive for the object deformation and the real-time characteristics.However, the pixels of the object area need to be fltered due to image quality issue. This paper proposed an adjustable size of the searching window that function according to an adaptive filter threshold method to protect the stability of tracking system that may affect by the disordered change of searching window. Verified by experimentation, compared to the traditional Camshift algorithm the improved algorithm significantly improvedthestability and accuracy of objecttracking.