基于深度稀疏滤波的目标跟踪  

Target Tracking Based on Deep Sparse Filtering

作　　者：邱立达[1] 刘天键[1] 傅平[1] Qiu Lida;Liu Tianjian;Fu Ping(Department of Physics and Electronic Information Engineering, Minjiang University, Fuzhou 350108)

机构地区：[1]闽江学院物理学与电子信息工程系,福州350108

出　　处：《计算机辅助设计与图形学学报》2017年第3期459-468,共10页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(51277091);中国博士后科学基金(2013T60637);福建省中青年教师教育科研项目(A15415);福州市科技计划重点项目(2013-G-86)

摘　　要：为了在复杂环境下更好地区分被跟踪目标和背景,设计了一种基于2l范数归一化和1l范数最小化的深度稀疏滤波模型,通过深度学习获取样本稀疏特征并对其进行分类,将该模型和粒子滤波框架结合,提出一种目标跟踪算法.首先使用离线训练集对深度稀疏滤波模型进行逐层无监督预训练得到权值参数的初始值,然后在跟踪过程中利用标签样本对模型在线更新,通过有监督微调优化其权值参数使得模型能够更好地适应目标外观变化,最后利用训练好的深度稀疏滤波模型对经由粒子滤波算法给出的候选区域进行观测,以确定跟踪目标.在不同视频序列中的实验表明,文中算法在复杂条件下具有良好的跟踪精度和鲁棒性.To better distinguish tracked target from background in the complex environment, a deep sparse filtering model based on l2-norm normalization and l1-norm minimization was designed to learn sparse sample features and the classification by deep learning is carried out. Additionally, a tracking algorithm combining this model with particle filter framework was proposed. Firstly, the deep sparse filtering model ispre-trained layer by layer on the offline training samples set without supervision to get the initial value of weight parameters. Then, during the tracking process, the model is updated online with the labeled samples by supervised fine-tuning to further optimize the weight parameters for better adaptability to target appearance changes. Finally, the full-trained deep sparse filtering model is used to observe candidate areas calculatedby particle filter algorithm to determine the tracked target. The experimental results on different video sequences show that the proposed algorithm has the superior performance on tracking precision and robustness under the complex environment.

关 键 词：目标跟踪 深度学习 稀疏滤波 粒子滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]