ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (12): 2785-2793.doi: 10.7544/issn1000-1239.2018.20170327

• 图形图像 • 上一篇    下一篇

一种结合时空上下文的在线卷积网络跟踪算法

柳培忠1,3,汪鸿翔1,骆炎民2,杜永兆1   

  1. 1(华侨大学工学院 福建泉州 362021);2(华侨大学计算机科学与技术学院 福建厦门 361021);3(华侨大学现代应用统计与大数据研究中心 福建厦门 361021) (pzliu@hqu.edu.cn)
  • 出版日期: 2018-12-01
  • 基金资助: 
    国家自然科学基金项目(61203242,61605048);福建省自然科学基金项目(2016J01300,2015J01256);华侨大学研究生科研创新能力培育计划资助项目(1511422004)

Online Convolutional Network Tracking via Spatio-Temporal Context

Liu Peizhong1,3, Wang Hongxiang1, Luo Yanmin2, Du Yongzhao1   

  1. 1(College of Engineering, Huaqiao University, Quanzhou, Fujian 362021);2(College of Computer Science and Technology, Huaqiao University, Xiamen, Fujian 361021);3(Research Center for Applied Statistics and Big Data, Huaqiao University, Xiamen, Fujian 361021)
  • Online: 2018-12-01

摘要: 基于卷积神经网络提取抽象特征缺乏时空信息的问题,结合时空上下文模型作为卷积神经网络的各阶滤波器,提出一种在线卷积神经网络的视觉跟踪算法.首先对初始目标进行归一化处理并提取目标置信图,跟踪过程中结合时空信息更新得到时空上下文模型,第1层使用更新后的模型对输入进行卷积,并对卷积结果进行滑动窗口取片,第2层再使用时空模型分别对取片结果进行卷积,提取目标简单抽象特征,然后叠加简单层的卷积结果得到目标的深层次表达,最后结合粒子滤波跟踪框架实现目标跟踪.实验表明:结合时空上下文模型的在线卷积网络结构提取的深度抽象特征,保留相关时空信息,提高复杂背景下的跟踪效率.

关键词: 视觉跟踪, 时空上下文, 卷积神经网络, 粒子滤波, 在线更新

Abstract: Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However, the features of the convolutional neural network abstraction algorithm are lack of spatio-temporal context information and the offline training is time-consuming. To tackle the above issues, an online convolution network tracking via spatio-temporal context is proposed, adopting the spatio-temporal context as the every order filter in convolutional neural network. Firstly, the initial target is normalized and the target confidence map is extracted. In the process of tracking, the spatio-temporal information is updated to obtain the spatio-temporal context model. The first layer utilizes the updated model to convolve the input and performs sliding window on the convolution result. The second layer convolves the fetch results by spatio-temporal model respectively, extracts the simple target abstract features, and then the convolution result of the simple layer is superposed to the deep level target expression. Finally, the target tracking is realized by the particle filter tracking framework. Our convolutional networks have a lightweight structure and perform favorably against several state-of-the-art methods on OTB-2013 and OTB-2015. As documented in the experimental results, the deep abstract feature extracted by online convolution network structure combining with spatio-temporal context model, can preserve related spatio-temporal information and then the tracking efficiency under complex background is improved.

Key words: visual tracking, spatio-temporal context, convolutional neural network, particle filter, online update

中图分类号: