期刊文献+

一种改进的运动目标检测算法 被引量:4

Improved Algorithm for Moving Target Detection
下载PDF
导出
摘要 提出一种改进的运动目标检测算法,首先将视频序列中的一整幅画面进行分割,对分割产生的每块图像进行连续检测,一旦检测到有变化,即提取运动目标。接着将连续2帧差图像和背景差图像直接相乘,再将相乘的结果进行二值化处理得到运动检测结果,从而将运动目标从背景图像中分离出来,最终得到视频序列图像中运动存在与否的一个二值运动模板,由此提高运动目标检测的效果。 An improved algorithm for moving target detection is introduced. First, one image is segmented into several units, and then each of them is detected sequent. Once there is a change, the moving target can be got. Second, the result image of two successive frames and background are directly multiplied and the result is binary operated to get the moving result. Consequently, the moving target can be separated from the background image. Finally, a binaries motion template which included the motive information of the target is got, and the effect of moving target detection can be improved.
出处 《兵工自动化》 2008年第1期37-38,45,共3页 Ordnance Industry Automation
基金 北华航天工业学院科研基金资助项目(KY_2006_24)
关键词 运动目标检测 二值化 背景图像 运动目标 Moving target detection Binaries Background image Moving target
  • 相关文献

参考文献8

  • 1冈萨雷斯.数字图像处理[M].北京:电子工业出版社,2003..
  • 2Haritaoglu I, Harwood D, David L S. W4: Real-Time Surveillance of People and Their Activities [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (8): 809-830. W
  • 3ren C, Azarbayejani A, Darrell T, etal. Pfinder: Real-Time Tracking of the Human Body [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 780-785.
  • 4Barron J, Fleet D, Beauchemin S, Performance of Optical Flow Techniques [J]. International Journal of Computer Vision, 1994, 12 (1): 43-47.
  • 5王宾,潘建寿,梁雁冰.基于Matrox卡的视频图像运动检测[J].西北大学学报(自然科学网络版),2004,2(3):145.
  • 6RAFAEL C G,RICHARD E W.数字图像处理[M].阮秋琦,阮宇智译.北京:电子工业出版社,2004.
  • 7刘教民,孙壮志,黄风荣,等.动态图像的高速采集与处理研究[A].自动化理论、技术与应用-中国自动化学会第十四届青年学术会议论文集[C].北京:西苑出版社,1999.404-408.
  • 8Jong Bae Real-Time Adaptive Australian 2001, 213- Kim, Hye Sun Park, Min Ho Park, etc. A Region-Based Motion Segmentation Using Thresholding and K-means Clustering [A], Joint Conference on Artificial Intelligence [C]. 224.

共引文献137

同被引文献15

引证文献4

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部