计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (1): 173-174.

• 工程与应用 • 上一篇    下一篇

基于腐蚀滤波的运动目标检测的图像处理

苑益军1,2,兰昆艳3   

  1. 1.地下信息探测技术与仪器教育部重点实验室(中国地质大学),北京 100083
    2.中国地质大学(北京) 地球物理与信息技术学院,北京 100083
    3.北京邮电大学 信息工程学院,北京 100876
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-01-01 发布日期:2008-01-01
  • 通讯作者: 苑益军

Image processing of moving objects detection based on erosion filter

YUAN Yi-jun1,2,LAN Kun-yan3   

  1. 1.Laboratory Key Geo-detection(China University of Geosciences),Ministry of Education of China,Beijing 100083,China
    2.School of Geophysics and Information Technology,China University of Geosciences,Beijing 100083,China
    3.School of Information Engineering,Beijing University of Posts & Telecommunications,Beijing 100876,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-01 Published:2008-01-01
  • Contact: YUAN Yi-jun

摘要: 在智能化数字视频监控系统中,获得的运动目标检测结果,经常存在一定程度的噪声。如果不对其去除,就会影响后续的图像处理质量。论文在对传统均值滤波研究的基础上,提出了一种形态学处理中的腐蚀滤波方法,对图像进行去噪,来改善检测结果的质量,以提高运动目标检测的精确度和视觉效果。通过对实际运动目标检测结果进行去噪处理,图像中的噪声点基本被删除,达到了预期的效果,防止了误检测。实验结果表明,该方法具有实用性和有效性。

关键词: 运动目标检测, 噪声, 腐蚀滤波

Abstract: In the intelligent video surveillance system,the results of moving objects detection involve some noise.If they are not removed,the quality of image will be influenced.After studying on the traditional mean filter method,this paper points to a kind of erosion filter method based on morphology processing.The method can remove the noise of images to improve the quality of detection results,so that it can enhance the accuracy of moving objects detection and visual effect.Through processing the real detection of moving objects,the noisy points are canceled.The processing results reach the expecting goal and prevent wrong detection.The experimental results show that the methods in the paper are practicability and availability.

Key words: moving object detection, noise, erosion filter