摘要
为了解决目标跟踪过程中出现的目标遮挡和光照变化问题,提出一种基于粒子滤波和压缩感知的目标跟踪算法。算法融合颜色特征和纹理特征来描述目标,增强算法在光照变化和复杂环境下的鲁棒性;利用压缩感知理论对特征进行降维,提高算法实时性;最后,根据粒子滤波原理估计目标状态,得到目标位置。实验结果表明,本算法在有效减少算法运行时间的前提下,能够准确跟踪遮挡和光照变化情况下的目标。
In order to solve the problem of object occlusion and illumination change in the process of target tracking,a target tracking algorithm based on particle filter and compressive sensing is proposed in this paper.The color feature and texture feature are fused to describe the object to improve the robustness of the algorithm under the illumination change and complex environment.The theory of compressive sensing is used to reduce the dimension of the feature,and it can improves the real-time performance of the algorithm.Finally,the target condition is estimated according to the principle of particle filter,and then the target position is obtained.The experimental results show that the algorithm can effectively reduce the running time of the algorithm,and can accu-rately track the target under occlusion and illumination changes.
出处
《电子技术应用》
北大核心
2016年第7期130-133,共4页
Application of Electronic Technique
关键词
粒子滤波
压缩感知
目标遮挡
光照变化
particle filter
compressive sensing
target occlusion
illumination changes