复杂背景中一种特定运动目标检测与跟踪方法

doi:10.3969/j.issn.1000-3428.2015.05.040

计算机工程

复杂背景中一种特定运动目标检测与跟踪方法

马　超^1,2,沈　微¹,董景峰¹

(1. 东北林业大学工程技术学院,哈尔滨150040; 2. 哈尔滨工业大学计算机科学与技术学院,哈尔滨150001)

收稿日期:2014-04-28 出版日期:2015-05-15 发布日期:2015-05-15
作者简介:马　超(1979 - ),男,讲师、博士研究生,主研方向:数据可视化,物流信息技术;沈　微、董景峰,讲师、博士。
基金项目:
中央高校基本科研业务费专项基金资助项目“物联网中非结构化数据流的数据挖掘方法研究”(DL11BB21);黑龙江省教育厅科学技术研究基金资助项目“智能供应链中非结构化数据流的数据挖掘算法研究”(12513014)。

A Method of Specific Moving Objects Detection and Tracking in Complex Background

MA Chao ^1,2,SHEN Wei ¹,DONG Jingfeng ¹

(1. College of Engineering and Technology,Northeast Forestry University,Harbin 150040,China; 2. School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China)

Received:2014-04-28 Online:2015-05-15 Published:2015-05-15

摘要/Abstract

摘要： 针对复杂环境对运动目标检测与跟踪产生的不利影响,提出一种自适应运动能量阈值结合精简彩色SIFT 描述子的特定运动目标检测与跟踪方法。运用自适应运动能量阈值方法自动滤除复杂环境干扰以完成运动目标检测,由此形成目标匹配搜索域,并给出经主成份分析及精简后的彩色SIFT 描述子(PCA-CSIFT)进行目标匹配, 从而实现特定运动目标的连续跟踪。实验结果表明,在复杂环境下,运动目标检测方法对目标总量变化不敏感,错误率始终稳定在6. 5% ~34% 之间。PCA-CSIFT 算法在保持高可区分性的同时错误匹配率为25. 33% ~ 28% ,平均每帧处理时间不超过0. 26 s,具有较好的鲁棒性与实时性。

关键词: 运动目标检测, 运动目标跟踪, 自适应运动能量阈值, 复杂背景, 目标匹配

Abstract: Aiming at the disadvantageous affects caused by moving object detection and tracking in complex background of video scenes,a new method of detecting and tracking specific moving objects using adaptive moving energy threshold combined with compact colored SIFT descriptor is proposed. For detection of moving objects,disturbance of complex environment is filtered out automatically by adaptive moving energy threshold. Principal Components Analysis is applied to the Colored SIFT descriptor(PCA-CSIFT) for objects matching. Thereby the continuous tracking of specific moving objects is achieved. Extensive experiments on bench datasets show that,in complex background,the moving objects tracking method is not sensitive to the amount of objects and the ratio of error is stabilized at 6. 5% ~ 34% . The PCA-CSIFT holds high distinctiveness and robustness with ratio of mismatches 25. 33% ~28% . The average processing time of each frame is no more than 0. 26 s,so the method meets the need of real time.

Key words: moving objects detection, moving objects tracking, adaptive moving energy threshold, complex background, objects matching

中图分类号:

TP391

马超,沈微,董景峰. 复杂背景中一种特定运动目标检测与跟踪方法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.05.040.

MA Chao,SHEN Wei,DONG Jingfeng. A Method of Specific Moving Objects Detection and Tracking in Complex Background[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.05.040.

参考文献

参考文献 [ 1 ]　Yu Zhen,Chen Yunping. A Real-time Motion Detection Algorithm for Traffic Monitoring Systems Based on Consecutive Temporal Difference [C] / / Proceedings of ASCC’ 09. Hong Kong, China: IEEE Press, 2009: 121-129. [ 2 ]　Gangodkar D,Kumar P,Mittal A. Robust Segmentation of Moving Vehicles Under Complex Outdoor Condi-tions[J]. IEEE Transactions on Intelligent Transportation Systems, 2012,13(4):1738-1752. [ 3 ]　Cheung S C S, Kamath C. Robust Techniques for Background Subtraction in Urban Traffic Video [C] / / Proceedings of SPIE Image Video Communication Processing. New York, USA: ACM Press, 2004: 881-892. [ 4 ]　Atev S,Miller G,Papanikolopoulos N P. Clustering of Vehicle Trajectories [ J ]. IEEE Transactions on Intelligent Transportation Systems,2010,11 (3):647- 657. [ 5 ]　He Kaiming,Sun Jian,Tang Xiaoou. Single Image Haze Removal Using Dark Channel Prior [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353. [ 6 ]　Bossu J,Hautière N,Tarel J P. Rain or Snow Detection in Image Sequences Through use of a Histogram of Orientation of Streaks [ J ]. International Journal of Computer Vision,2011,93(3):348-367. [ 7 ]　Gao T,Li G,Lian S,et al. Tracking Video Objects with Featurepoints-based Particle Filtering [ J ]. Multimedia Tools Applications,2012,58(1):1-21. [ 8 ]　周陈龙,胡福乔. 基于Harris 和几何哈希法的目标匹配[J]. 计算机工程,2013,39(11):205-208. [ 9 ]　Abdel-Hakim A E,Farag A A. CSIFT:A SIFT Descriptor with Color Invariant Characteristics [C]/ / Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE Computer Society,2006:458-467. [10]　Verma A,Banerji S,Liu Chengjun. A New Color SIFT Descriptor and Methods for Image Category Classification[ C]/ / Proceedings of 2010 IRAST International Congress on Computer Applications and Computational Science. Singapore:IEEE Press,2010:256-265. [11]　Ancuti C, Bekaert P. SIFT-CCH: Increasing the SIFT Distinctness by Color Co-occurrence Histograms[C] / / Proceedings of the 5th International Symposium on Image and Signal Processing and Analysis. Istanbul, Turkey:IEEE Press,2007:326-331. 编辑　索书志

[1]	刘燕德, 曾体伟, 陈洞滨, 王观田. 基于区域相似信息的自适应运动目标检测算法[J]. 计算机工程, 2020, 46(3): 273-279.
[2]	李军,程健. 复杂背景图像下基于边缘点校验的圆检测方法 [J]. 计算机工程, 2018, 44(3): 259-263.
[3]	刘小静,薛峰. 基于边缘对比差分算法的运动目标检测[J]. 计算机工程, 2018, 44(10): 246-251.
[4]	段锁林,严翔,朱方,史兵. 基于改进混合高斯模型与六帧差分的目标检测算法[J]. 计算机工程, 2017, 43(7): 234-238.
[5]	王奎奎,玉振明. 基于DCT零系数与局部结构张量的局部模糊检测[J]. 计算机工程, 2017, 43(6): 207-211,218.
[6]	肖锋,冯飞,田鹏辉. 复杂场景下融合深度信息的显著区域匹配[J]. 计算机工程, 2017, 43(5): 248-254,260.
[7]	李娜,王洪元,王佳. 基于颜色空间分布的多摄像机行人匹配方法[J]. 计算机工程, 2016, 42(12): 217-221.
[8]	亚森·艾则孜,艾山·吾买尔. 运动目标检测中基于灰度特征模型的背景消除方法[J]. 计算机工程, 2015, 41(6): 240-246,257.
[9]	杨阳,唐慧明. 基于视频的行人车辆检测与分类[J]. 计算机工程, 2014, 40(11): 135-138.
[10]	喻旭勇，王直杰. 基于灰度触发的Mean Shift自动跟踪算法[J]. 计算机工程, 2014, 40(1): 228-231,235.
[11]	王金云, 周晖杰, 纪政. 复杂背景中的人脸识别技术研究[J]. 计算机工程, 2013, 39(8): 196-199,203.
[12]	王阿川, 曹琳, 曹军. 基于改进轮廓模型的单板缺陷图像快速识别[J]. 计算机工程, 2013, 39(4): 22-26,35.
[13]	张健, 沈春裕, 卢瑾. 基于分解的三维Otsu运动车辆检测方法[J]. 计算机工程, 2013, 39(2): 172-177.
[14]	支晨蛟，唐慧明. 基于视频角点特征匹配的车速检测方法[J]. 计算机工程, 2013, 39(12): 176-180.
[15]	周陈龙，胡福乔. 基于Harris和几何哈希法的目标匹配[J]. 计算机工程, 2013, 39(11): 205-208.

复杂背景中一种特定运动目标检测与跟踪方法

A Method of Specific Moving Objects Detection and Tracking in Complex Background

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10