摘要
针对受到光照、遮挡及姿态变化等引起的目标外观发生变化时,目标跟踪的鲁棒性和准确性较差的问题,将稀疏表示引入到粒子滤波框架进行目标跟踪,提出一种稀疏协同模型。首先,在目标运动定位模型中,使用灰度强度值表示目标对象;其次,判别模型通过训练正负模板集获得最优分类特征,并在生成模型中对目标直方图加权以提高目标生成效率;然后,将分类判别模型和生成模型集成在协同模型中,利用重构误差确定目标;最后,通过各模块独立更新,减少目标外观变化对目标跟踪的影响。实验结果表明,所提方法的平均中心误差仅为7.5像素,且具备良好的抗噪性和实时性。
When the target apperance is influenced by the change of illumination, occlusion or attitude, the robustness and accuracy of target tracking system are usually frangible. In order to solving this problem, sparse representation was introduced into the particle filter framework for target tracking and a sparse cooperative model was proposed. Firstly, the target object was represented by intensity in the target motion positioning model. Secondly, the optimal classification features were extracted by training the positive template set and negative template set in the discriminant classification model, then the target was weighted by the histogram in the generative model. Subsequently, diseriminant classification model and generative model were cooperated in a collaborative model, and the target was determined by the reconstruction error. Finally, every module was updated independently to mitigate the effects of changes in the appearance of the target. The experimental results show that the average center location error of the proposed model is only 7.5 pixels, meanwhile the model has good performance in anti-noise and real-time.
出处
《计算机应用》
CSCD
北大核心
2016年第11期3152-3160,共9页
journal of Computer Applications
基金
国家自然科学基金资助项目(U1304607)
河南省高等学校重点项目(15A520080)
河南师范大学博士科研启动基金资助项目(qd12138)~~
关键词
稀疏表示
目标跟踪
协同模型
似然函数
重构误差
sparse representation
target tracking
collaborative model
likelihood function
reconstruction error
