电子学报 ›› 2017, Vol. 45 ›› Issue (10): 2355-2361.DOI: 10.3969/j.issn.0372-2112.2017.10.007

• 学术论文 • 上一篇    下一篇

一种快速鲁棒的视频序列运动目标检测方法

秦晓燕1, 袁广林1, 李从利2, 张旭1   

  1. 1. 解放军陆军军官学院十一系, 安徽合肥 230031;
    2. 解放军陆军军官学院三系, 安徽合肥 230031
  • 收稿日期:2016-02-24 修回日期:2016-08-12 出版日期:2017-10-25
    • 作者简介:
    • 秦晓燕,女,1980年2月出生,安徽淮北人.2004年毕业于解放军炮兵学院获工学硕士学位、讲师.主要研究方向为图像处理、目标检测、机器学习及应用.E-mail:70853559@qq.com;袁广林,男,1973年8月出生,河南周口人.2013年毕业于合肥工业大学获博士学位,副教授.研究方向为图像处理、计算机视觉、机器学习及其应用.E-mail:yuanguanglin1008@sina.com
    • 基金资助:
    • 安徽省自然科学基金 (No.1508085QF114,No.1608085QF144); 国家自然科学基金 (No.61379105); 中国博士后科学基金 (No.2014M562535)

An Approach to Fast and Robust Detecting of Moving Target in Video Sequences

QIN Xiao-yan1, YUAN Guang-lin1, LI Cong-li2, ZHANG Xu1   

  1. 1. Eleventh Department, Army Officer Academy of PLA, Hefei, Anhui 230031, China;
    2. Third Department, Army Officer Academy of PLA, Hefei Anhui 230031, China
  • Received:2016-02-24 Revised:2016-08-12 Online:2017-10-25 Published:2017-10-25
    • Supported by:
    • National Natural Science Foundation of Anhui Province,  China (No.1508085QF114, No.1608085QF144); National Natural Science Foundation of China (No.61379105); China Postdoctoral Science Foundation (No.2014M562535)

摘要: 稀疏表示已经成为运动目标检测的有效方法之一,但其还没有很好地解决目标检测的快速性和鲁棒性.本文基于最大后验概率提出了一种快速鲁棒的运动目标检测模型,并设计了该模型的求解算法.该算法包括两个阶段:在第一阶段利用编码迁移实现稀疏系数的快速求解;在第二阶段基于运动目标的空间连续性结构,利用图切实现目标检测.在多个具有挑战性的图像序列上的实验结果表明,与其他经典运动目标检测算法相比,本文方法在快速性和鲁棒性方面具有较优的性能.

关键词: 运动目标检测, 稀疏表示, 编码迁移, 图切

Abstract: Sparse representation is one of effective methods in dealing with the moving object detection.However,the quickness and robustness of object detection are far from being solved in the existing methods.In this paper,a fast and robust moving object detection model based on the maximum posteriori probability is proposed,and a two-stage detection algorithms is designed.At the first stage,sparse coefficient is quickly solved by using coding transfer; At the second stage,based on spatial continuity structure,moving object detection is achieved by using graph cut.The experimental results on several challenging image sequences show that the proposed method has better performance than the existing classical moving object detection algorithms in rapidity and robustness.

Key words: moving object detection, sparse representation, coding transfer, graph cut

中图分类号: