复杂场景中基于变块差分的运动目标检测

朱娟娟; 郭宝龙

doi:10.3788/OPE.20111901.0183

您当前的位置：

首页 >

文章列表页 >

复杂场景中基于变块差分的运动目标检测

信息科学 | 更新时间：2020-08-12

- 复杂场景中基于变块差分的运动目标检测
- Moving object detection based on variant block difference in complex scenes
- 光学精密工程 2011年19卷第1期页码：183-191
- 作者机构：
  
  西安电子科技大学机电工程学院,陕西西安,710071
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61003196)();高校基本科研业务费专项资助项目(No.K50510040004)()
- DOI：10.3788/OPE.20111901.0183
  中图分类号： TP391.4
- 收稿日期：2010-04-01，
  
  修回日期：2010-06-25，
  
  网络出版日期：2011-01-22，
  
  纸质出版日期：2011-01-22
- 稿件说明：
移动端阅览
朱娟娟, 郭宝龙. 复杂场景中基于变块差分的运动目标检测[J]. 光学精密工程, 2010,19(1): 183-191

ZHU Juan-juan, GUO Bao-long. Moving object detection based on variant block difference in complex scenes[J]. Editorial Office of Optics and Precision Engineering, 2010,19(1): 183-191
朱娟娟, 郭宝龙. 复杂场景中基于变块差分的运动目标检测[J]. 光学精密工程, 2010,19(1): 183-191 DOI： 10.3788/OPE.20111901.0183.

ZHU Juan-juan, GUO Bao-long. Moving object detection based on variant block difference in complex scenes[J]. Editorial Office of Optics and Precision Engineering, 2010,19(1): 183-191 DOI： 10.3788/OPE.20111901.0183.

摘要

针对复杂场景中包含的摄像机扫描运动、随机抖动和目标运动

提出一种基于帧间可变块差分的运动目标检测算法。首先

利用全局特征点估计运动参数对帧间背景进行补偿

提取图像的全局特征点并匹配

以特征点集的最小位置误差和作为目标进行迭代

获取误差不大于0.5 pixel的全局运动参数

并精确补偿当前帧实现背景校正。然后

利用可变块差分实现运动目标的检测。先用大尺寸对差分图像进行分割

将整幅图像粗略区分为背景区域、运动目标区域和边界区域

通过阈值判定来进一步细分

最后对运动目标区域进行准确标定。这种由粗到细的检测步骤

在保证精度的同时能够提高检测速度。实验结果表明

该算法能够准确检测含摄像机扫描和抖动的复杂运动场景中的前景运动目标

且处理速度达到25 frame/s。

Abstract

A fast moving-object detection algorithm based on inter-frame Variant Compensated Blocks Difference(VCBD) is presented to deal with the complex scenes with camera scan

dithering and object moving. Firstly

the global motion estimation is performed based on feature points to compensate the inter-frame background. The global feature points in a reference image are selected and matched in a current image. Then

the iteration is applied to realize the minimum sum of position errors of all matched points and to obtain the global motion parameter with the accuracy less than 0.5 pixel. Accordingly

the current frame is compensated to match the background area. Finally

the adaptive variant block difference is proposed to detect moving objects. The whole image is classified into background

foreground and boundary areas and the block is then judged with the threshold and divided into four blocks. These coarse-to-fine steps can greatly improve the velocity and veracity of detection. Experimental results show that the algorithm can detect moving objects in camera scan and dithering sequences and the processing speed achieves 25 frame/s.

关键词

Keywords

references

SCHMUDDERICH J, WILLERT V. Estimating object proper motion using optical flow, kinematics and depth information [J]. IEEE Trans. On Systems, Man, and Cybernetics,2008,38(4):1139-1151.[2] HARITAOGLU I, HARWOOD D, DAVIS L. W4: real-time surveillance of people and their activities [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.[3] MEIER T, NGUN K N. Video segmentation for content-based coding [J]. IEEE Trans. on Circuits and Systems for Video Technology, 1999,9(8):1190-1203.[4] EBISAWA Y. Robust pupil detection by image difference with positional compensation . VECIMS,2009, 11-13:143-148.[5] 姜永林, 屈桢深, 王常虹. 基于纹理及统计特征的视频背景提取 [J]. 光学精密工程, 2008,16(1):172-177. JIANG Y L, QU ZH SH, WANG CH H. Video background extraction based on textural and statistical feature s[J]. Opt. Precision Eng., 2008,16(1):172-177. (in Chinese)[6] CHENG J R,FOO S W. Dynamic directional gradient vector flow for snakes [J]. IEEE Trans. on Image Processing,2006,15(6):1563-1571.[7] WU G, EU CH F, HOU Q Y, et al.. Target location method based on invariable moment feature matching [J]. Opt. Precision Eng., 2009,17(2):230-238.[8] WEI ZH H,TIAN J,LIU CH G, et al.. An updating algorithm of self-adaptive background based on energy method . IEEE International Conference on Automation and Logistics, 2008:848-852.[9] ZHU J J,GUO B L. Electronic image stabilization system based on global feature tracking[J]. Journal of Systems Engineering and Electronics, 2008,19(2):228-233.[10] PHAM T D. Image segmentation using probabilistic fuzzy C-means clustering . Proceeding of International Conference on Image processing, 2001,21(3):722-725.[11] FU Y,ERDEM A T,MURAT TEKALP A. Tracking visible boundary of objects using occlusion adaptive motion snake [J]. IEEE Trans. on Image Processing,2000,9(12):2051-2060.[12] 薛陈,朱明,陈爱华. 鲁棒的基于改进Mean-shift的目标跟踪[J]. 光学精密工程, 2010, 18(1):234-239. XUE CH, ZHU M, CHEN A H. Robust object tracking based on improved Mean-shift algorithm [J]. Opt. Precision Eng., 2010,18(1):234-239. (in Chinese)[13] MADDALENA L, PETROSINO A. Moving object detection for real-time applications . International Conference on Image Analysis and Processing, 2007:542-547.[14] ZHU S,MA K K. A new diamond search algorithm for fast block-matching motion estimation [J]. IEEE Trans. on Image Processing,2000,9(2):287-290.

浏览量

535

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

改进的ViBe算法及其在交通视频处理中的应用

基于多模板回归加权均值漂移的人体目标跟踪

权重系数自适应光流法运动目标检测

CenSurE特征和时空信息相结合的运动目标检测

稳定运动物体视频的特征方法