[1]柳培忠,阮晓虎,田震,等.一种基于多特征融合的视频目标跟踪方法[J].智能系统学报,2014,9(3):319-324.[doi:10.3969/j.issn.1673-4785.201309085]
LIU Peizhong,RUAN Xiaohu,TIAN Zhen,et al.A video tracking method based on object multi-feature fusion[J].CAAI Transactions on Intelligent Systems,2014,9(3):319-324.[doi:10.3969/j.issn.1673-4785.201309085]
点击复制
LIU Peizhong,RUAN Xiaohu,TIAN Zhen,et al.A video tracking method based on object multi-feature fusion[J].CAAI Transactions on Intelligent Systems,2014,9(3):319-324.[doi:10.3969/j.issn.1673-4785.201309085]
一种基于多特征融合的视频目标跟踪方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
9
期数:
2014年第3期
页码:
319-324
栏目:
学术论文—智能系统
出版日期:
2014-06-25
- Title:
- A video tracking method based on object multi-feature fusion
- Keywords:
- video tracking; background modeling; foreground detection; feature extraction; multi-feature fusion
- 分类号:
- TP391
- 摘要:
- 在预警系统和目标记录方面, 传统的视频跟踪方法无法很好地解决目标重现和遮挡等问题, 针对此类问题提出了一种融合多特征的视频目标跟踪方法, 首先用背景建模的方法检测运动前景, 分离目标图像, 通过目标连续帧间的位移信息实现跟踪, 对多目标帧间位移相近的情况, 融合目标SIFT和彩色直方图特征进行目标匹配, 并记录目标各帧的运动状态, 最终实现目标运动的跟踪。实验结果表明, 该方法对多目标缓慢变化的监控视频有较好的跟踪效果。
- Abstract:
- Video tracking is a vital technique for the application of intelligent video surveillance. In terms of pre-warning systems and event recording, traditional video tracking methods cannot solve the problems of object reappearance and shadows very well. To tackle these problems, a video tracking method based on object multi-feature fusion is proposed. Firstly, the foreground of a moving target was detected using the method of background modeling, and the image of the moving target was separated from the video frame. Then the target that had been detected currently was set to match the target that appeared previously through the location information of the sequential frames of the object. Furthermore, considering the failure of the location matching, the SIFT(scale invariant feature transform ) and color histogram feature of the target image were extracted to match the different targets. The experimental results showed excellent performance of the real-time video tracking of multi-objects moving slowly in the general surveillance system.
- 参考文献/References:
-
[1] 李锴. 基于粒子滤波与半监督多分类器的视频跟踪[D]. 上海:复旦大学, 2012:6-8.LI Kai. Video tracking based on particle filter and semi-supervised multiple classifiers[D]. Shanghai:Fudan University, 2012:6-8.
[2] 杨戈, 刘宏.视觉跟踪算法综述[J].智能系统学报, 2010, 5(2):95-105.YANG Ge, LIU Hong. Survey of visual tracking algorithms[J]. CAAI Transactions on Intelligent Systems, 2010, 5(2):95-105.
[3] FAZLI S, POUR H M, BOUZARI H. Particle filter based object tracking with SIFT and color feature[C]//Second International Conference on Machine Vision. Dubai, UAE, 2009:89-93.
[4] ZHOU H, YUAN Y, SHI C. Object tracking using SIFT features and mean shift[J]. Computer Vision and Image Understanding, 2009, 113(3):345-352.
[5] BEYAN C, TEMIZEL A. Adaptive mean-shift for automated multi object tracking[J]. Computer Vision, 2012, 6(1):1-12.
[6] JIANG M, LI M, WANG H. A robust combined algorithm of object tracking based on moving object detection[C]//Intelligent Control and Information Processing. Dalian, China, 2010:619-622.
[7] RAHMAN M S, SAHA A, KHANUM S. Multi-object tracking in video sequences based on background subtraction and SIFT feature matching[C]//Fourth International Conference of Computer Sciences and Convergence Information Technology. Seoul, Korea, 2009:457-462.
[8] WREN C R, AZARBAYEJANI A, DARRELL T. Real-time tracking of the human body[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):780-785.
[9] PAKORN K, BOWDEN R. An improved adaptive background mixture model for real-time tracking with shadow detection[M]. New Youk:Springer, 2002:135-144.
[10] ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Proceedings of the 17th International Conference of Pattern Recognition. Cambridge, UK, 2004, 2:28-31.
[11] KIM K, CHALIDABHONGSE T H. Real-time foreground-background segmentation using codebook model[J]. Real-time Imaging, 2005, 11(3):172-185.
[12] SIGARI M H, FATHY M. Real-time background modeling/subtraction using two-layer codebook model[C]//Proceedings of the International Multi-Conference of Engineers and Computer Scientists. Hong Kong, China, 2008:19-21.
[13] ZHU Y, LIANG Y, ZHU Y. The improved Gaussian mixture model based on motion estimation[C]//Proceedings of Third International Conference on Multimedia Information Networking and Security. Shanghai, China, 2011:46-50.
[14] 邹煜. 基于轮廓提取和颜色直方图的图像检索[D].重庆:西南大学, 2011:28-29.ZOU Yu. Image retrieval method based on color histogram and contour extraction[D]. Chongqing:Southwest University, 2011:28-29.
[15] LINDEBERG T. Scale-space theory:a basic tool for analyzing structures at different scales[J]. Journal of Applied Statistics, 1994, 21(1/2):225-270.
[16] LOWE D G.Object recognition from local scale-invariant features[C]//The Proceedings of the Seventh IEEE International Conference of Computer Vision.Kerkyra, Greece, 1999, 2:1150-1157.
[17] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[18] 赵雷, 陈万忠, 韩双双. 一种改进的运动目标跟踪与轨迹记录算法[J]. 智能系统学报, 2008, 3(2):145-149.ZHAO Lei, CHEN Wanzhong, HAN Shuangshuang. An improved algorithm for tracking and recording moving targets[J]. CAAI Transactions on Intelligent Systems, 2008, 3(2):145-149.
- 相似文献/References:
-
[1]许国梁,周航,袁良友.利用混合高斯和拓扑结构的人体“鬼影”抑制算法[J].智能系统学报,2021,16(2):294.[doi:10.11992/tis.201912030]
XU Guoliang,ZHOU Hang,YUAN Liangyou.Human “ghost” suppression algorithm using Gaussian mixture model and topology[J].CAAI Transactions on Intelligent Systems,2021,16():294.[doi:10.11992/tis.201912030]
备注/Memo
收稿日期:2013-09-30。
基金项目:国家自然科学基金重大研究计划资助项目(90920013)
作者简介:柳培忠,男,1976年生,讲师,博士,美国杜克大学高级访问学者,主要研究方向为仿生图像处理技术、仿生模式识别理论与方法、网络视觉媒体检索技术、微波成像分析等;阮晓虎,男,1986年生,硕士研究生,主要研究方向为视频、图像处理、模式识别、深度学习相关算法。参与国家自然科学基金重大研究计划项目1项。
通讯作者:田震,男,1988年生,硕士研究生,主要研究方向为图像处理、智能监控系统、模式识别等,E-mail:tianzhen@semi.ac.cn。
更新日期/Last Update:
1900-01-01