基于CNN的粒子滤波目标跟踪算法研究

Wei Xing Li, Wei Liang Ma, Hui Tian, Feng Pan, Yu Feng Ji

科研成果: 期刊稿件文章同行评审

3 引用 (Scopus)

摘要

In object tracking algorithms, the target drift and missing are easy to happen in complex environments. A robust tracking algorithm was proposed based on convolutional neural network(CNN) under the particle filter framework. In this algorithm, CNN was utilized to get high-level semantic features of targets and a offline pre-train method was used to learn the general feature representation and improve the training efficiency. Using particle filter framework, the algorithm was arranged to get the reliable target motion state. In addition, two kinds of online updating procedure, long-time and short time, were introduced to deal with the target postures change and some other situations. An online hard example mining strategy was also used to improve the online learning efficiency. The simulation results show that the proposed algorithm can be effectively adapt to complex background, such as occluded, illumination changes, pose variations. Furthermore, we evaluate the proposed algorithm on some challenging videos compared with the state-of-the-art algorithms.

投稿的翻译标题Particle Filter for Object Tracking Based on CNN Feature
源语言繁体中文
页(从-至)1256-1262
页数7
期刊Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
38
12
DOI
出版状态已出版 - 1 12月 2018

关键词

  • Convolutional neural network (CNN)
  • Object tracking
  • Particle filter

指纹

探究 '基于CNN的粒子滤波目标跟踪算法研究' 的科研主题。它们共同构成独一无二的指纹。

引用此

Li, W. X., Ma, W. L., Tian, H., Pan, F., & Ji, Y. F. (2018). 基于CNN的粒子滤波目标跟踪算法研究. Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 38(12), 1256-1262. https://doi.org/10.15918/j.tbit1001-0645.2018.12.008