动态目标识别中的实时复杂巡航场景运动检测

武治国; 李桂菊

doi:10.3788/YJYXS20142905.0844

您当前的位置：

首页 >

文章列表页 >

动态目标识别中的实时复杂巡航场景运动检测

成像技术与图像处理 | 更新时间：2020-08-12

- 动态目标识别中的实时复杂巡航场景运动检测
- Real-time complex cruise scene detection technology in target recognition
- 液晶与显示 2014年29卷第5期页码：844-849
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
- 作者简介：
  
  [ "武治国（1978-），男，吉林长春人，博士，副研究员，硕士生导师，主要研究方向为图像处理，模式识别。E-mail：wu78zg@163.com" ]
  [ "李桂菊（1964-），女，吉林长春人，硕士，研究员，博士生导师，主要研究方向为数字图像处理。" ]
- 基金信息：
  
  吉林省科技发展计划项目（No.20130102017JC）();国家高技术研究发展计划（863）（No.2006AA703405F）()
- DOI：10.3788/YJYXS20142905.0844
  中图分类号： TP391.41
- 收稿日期：2014-04-14，
  
  修回日期：2014-04-25，
  
  纸质出版日期：2014-10-05
- 稿件说明：
移动端阅览
武治国, 李桂菊. 动态目标识别中的实时复杂巡航场景运动检测[J]. 液晶与显示, 2014,29(5): 844-849

WU Zhi-guo, LI Gui-ju. Real-time complex cruise scene detection technology in target recognition[J]. , 2014,29(5): 844-849
武治国, 李桂菊. 动态目标识别中的实时复杂巡航场景运动检测[J]. 液晶与显示, 2014,29(5): 844-849 DOI： 10.3788/YJYXS20142905.0844.

WU Zhi-guo, LI Gui-ju. Real-time complex cruise scene detection technology in target recognition[J]. , 2014,29(5): 844-849 DOI： 10.3788/YJYXS20142905.0844.

摘要

设计并实现了一种适合于工程中动态目标识别应用的实时的复杂巡航场景运动检测技术。首先，对背景和当前帧两幅图像进行卷积处理，提取边缘图像。然后分块计算背景边缘图像的局部熵，根据局部熵大小合理选取配准模型组。采用模型组与当前帧边缘图像的相关性强度及运动偏移量结果，完成场景的运动估计。实验结果表明，本文方法用于红外和可见光图像均十分有效，在分辨率为320256，帧频50 Hz的红外图像以及分辨率为768576，帧频25 Hz的可见光图像中运行时间分别为13、24 ms，达到了工程中应用的实时性处理要求。同时，在后续的图像处理中场景运动检测有效剔除了复杂背景图像对目标识别的干扰，可准确检测出运动变化目标。

Abstract

This paper designs and realizes a real-time motion detection technology for complex cruise scene. The technology is suitable for dynamic target recognition in engineering application. First of all

two images of the background and the current frame are processed by convolution operation and extract the edge images. Then we put parts of background edge image and compute their local entropy. According to the value of the local entropies

we can select reasonable registration model group and compute correlation strength and the value of movement offset. The value is the offset of the model group and the current edge image. We complete scene motion estimation by them. The experimental results show that the method can be used in the infrared and visible images. The infrared image processing time is 13 ms. Its resolution is 320256 and frame rate is 50 Hz. The optical image processing time is 24 ms. Its resolution is 768576 and frame rate is 25 Hz. They reach real-time processing requirement of the engineering application. Meanwhile

motion detection of scene effectively excludes the interference of target recognition which is produced by the complex background image. We can accurately detect the movement and changing target.

关键词

Keywords

references

刘文萍,贺娜. 一种新的背景减运动目标检测方法[J]. 计算机工程与应用, 2011,47(22):175-179. LIU W P, HE N. Moving object detection method based on background subtraction[J].Computer Engineering and Applications,2011,47(22):175-179.(in Chinese)[2] 梅跃松,于剑桥,陈曦. 移动背景下的运动目标跟踪[J]. 红外与激光工程, 2011,40(4):757-761. Mei Y S, Yu J Q, Chen X. Moving object tracking in the moving background[J].Infrared and Laser Engineering,2011,40(4):757-761. (in Chinese)[3] Guan Y P. Spatio-temporal motion-based foreground segmentation and shadow suppression[C].Proceedings of Computer Vision,2010:50-60.[4] Hafiz F. Foreground segmentation-based human detection with shadow removal[C].Proceedings of International Conference on Computer and Communication Engineering, 2010:1-6.[5] Bayona A. Stationary foreground detection using background sub-traction and temporal difference in video surveillance[C].Proceedings of the 17th IEEE International Conference on Image Processing,2010: 4657-4660.[6] Huang M.A study of moving object detection based on combining background profile difference algorithm[C].Proceedings of the 2nd International Conference on Industrial and Information Systems, 2010: 425-428.[7] 吴本涛,吴敏渊,曾霖. 自适应搜索的快速分块跟踪[J]. 光学精密工程, 2011,19(3):703-708. Wu B T, Wu M Y, Zeng L. Fast fragment based tracking using adaptive search[J].Optics and Precision Engineering, 2011,19(3):703-708. (in Chinese)[8] 侯晴宇,张伟,武春风,等. 改进的均值移位红外目标跟踪[J]. 光学精密工程, 2010,18(3):764-770. Hou Q Y, Zhang W, Wu C F,et al.Improved mean-shift based IR target tracking algorithm[J]. Optics and Precision Engineering,2010,18(3):764-770. (in Chinese)[9] 吴君钦,刘昊,罗勇. 静态背景下的运动目标检测算法[J]. 液晶与显示, 2012,27(5):682-685. Wu J Q, LIU H, Luo Y. Algorithm of moving object detection in static background[J].Chinese Journal of Liquid Crystals and Displays,2012, 27(5):682-685. (in Chinese)[10] 孙辉. 相位相关技术实现离焦模糊图像运动估计[J]. 液晶与显示, 2012,27(2):223-228. Sun H. Estimation of displacement for out-of-focus blurred image using phase-only correlation[J].Chinese Journal of Liquid Crystals and Displays, 2012, 27(2):223-228.(in Chinese)[11] 卢官明,谢双. 自适应背景更新及运动目标检测算法[J]. 南京邮电大学学报:自然科学版, 2013,33 (3):12-17. Lu G M, Xie S.Adaptive background update and moving object detection[J].Journal of Nanjing University of Posts and Telecommunications:Natural Science,2013,33(3):12-17.(in Chinese)[12] Denman S, Fookes C, Sridharan S. Improved simultaneous computation of motion detection and optical flow for object tracking[C].Proceedings of Digital Image Computing: Techniques and Applications,2009:175-182.[13] Xiao B X. Moving object detection and recognition based on the frame difference algorithm and moment invariant features[C].Proceedings of the 27th Chinese Control Conference,2008:578-581.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多干扰成像条件下的钻孔内壁图像鲁棒拼接方法

高精度视频配准算法中的静态图像配准算法

一种基于相位相关与子图像的偏振图像配准方法

一种用于图像拼接的改进ORB算法

面向多区域视频监控的运动目标检测系统