J4

• 计算机科学 • 上一篇    下一篇

基于对称差分算法的视频运动目标分割

肖丽君1,2, 于哲舟1, 周栩1, 郑尚1, 李海峰1   

  1. 1. 吉林大学 计算机科学与技术学院, 长春 130012; 2. 北华大学 教育技术中心, 吉林 吉林 132013
  • 收稿日期:2008-01-18 修回日期:1900-01-01 出版日期:2008-07-26 发布日期:2008-07-26
  • 通讯作者: 于哲舟

Moving Object Segmentation Based on Symmetrical DifferencingAlgorithm in Video Sequences

XIAO Lijun1,2, YU Zhezhou1, ZHOU Xu1, ZHENG Shang1, LI Haifeng1   

  1. 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;2. The Center of Educational Technology, Beihua University, Jilin 132013, Jilin Province, China
  • Received:2008-01-18 Revised:1900-01-01 Online:2008-07-26 Published:2008-07-26
  • Contact: YU Zhezhou

摘要: 提出一种视频运动目标分割的改进算法, 该算法综合帧间差分算法及背景减算法获得的信息分割运动物体, 利用对称差分算法获得中间帧运动目标的轮廓信息, 以该轮廓的外接矩形为分界, 再对其外部进行动态背景更新处理, 并对其内部进行减背景运算. 实验结果表明, 该改进算法解决了帧间差分算法在运动物体缺乏足够表面纹理时, 易产生空洞和边缘缺失的问题, 具有计算速度快、 抗噪声能力强和分割效果好等优点.

关键词: 视频, 运动目标, 分割, 对称差分, 背景减

Abstract: This paper presents a new algorithm of moving object segmentation in video sequences, the algorithm integrates the data of moving object that are obtained from symmetrical differencing algorithm and background differencing algorithm, that is, the outline data of the middle frame movement object are obtained by symmetry differencing algorithm and the outline becomes the dividing line, while the exterior is dealt with dynamic background refresh method, and the interior is dealt with background differencing algorithm. The improvedalgorithm solves the hole and hollow when the moving object is short of sufficient surface texture by symmetrical differencing algorithm. The experimental result shows that the algorithm has the advantages of both the two algorithms. The algorithm has simple and accurate physical significance, fast calculation velocity,robust to noise, and can extract the moving body correctly.

Key words: video frequency, movement object, segmentation, symme trical difference, background subtraction

中图分类号: 

  • TP391.41