应用勒贝格积分和卡尔曼滤波的移动目标检测跟踪算法Moving target detection and tracking algorithm based on Lebesgue integral and Kalman filtering
李毅,李珊珊
摘要(Abstract)：
为了更好地完成移动目标的检测跟踪,提出应用勒贝格积分和卡尔曼滤波的移动目标检测跟踪算法。该算法将动态视频中某点的灰度值变化看作离散随机信号,利用其在不同时段有不同性质的特点,按照勒贝格积分的思路对变化平缓的背景时段信号进行积分,完成背景提取。以提取的背景为参考值,经过差分计算检出移动目标,之后用卡尔曼滤波预测目标可能的运动范围,通过奇异值分解系数进行特征匹配,确定目标最终位置,根据偏差修正卡尔曼滤波参数,实现目标的实时跟踪。实验结果表明,该算法可以完成复杂运动环境中对移动目标的检测跟踪。
关键词(KeyWords)： 移动目标检测;实时跟踪;差分计算;特征匹配;奇异值分解;背景提取
基金项目(Foundation): 全国高校实验室工作研究会学术研究计划(SY2015Z059)~~
作者(Author): 李毅,李珊珊
DOI: 10.16652/j.issn.1004-373x.2018.23.014
参考文献(References)：
- [1]KOHLLEPPEL R.Ground moving target tracking of PAMIR detections with a Gaussian mixture-PHD filter[C]//Proceedings of 2011 International Radar Symposium.Leipzig:IEEE,2011:193-198.
- [2]LIPTON A,KANADE T,FUJIYOSHI H.A system for video surveillance and monitoring[M].Pittsburg:Carnegie Mellon University Press,2000:11-18.
- [3]夏永泉,李卫丽,甘勇,等.智能视频监控中的运动目标检测技术研究[J].通信技术,2009(6):185-187.XIA Yongquan,LI Weili,GAN Yong,et al.Studies on moving objects detection technology in intelligent video surveillance[J].Communications technology,2009(6):185-187.
- [4]DUNCAN J H,CHOU T C.On the detection of motion and the computation of optical flow[J].IEEE transactions on pattern analysis and machine intelligence,1992,14(3):346-352.
- [5]KUMAR P,RANGANATH S,SENGUPTA K,et al.Cooperative multi-target tracking with efficient split and merge handling[J].IEEE transactions on circuits and system for video technology,2006,16(12):1477-1490.
- [6]ZHOU S K,CHELLAPPA A,MOGHADDA B.Visual tracking and recognition using appearance-adaptive models in particle filters[J].IEEE transactions on image processing,2004,13(11):1491-1506.
- [7]WANG Qin,WANG Yaonan.Multiple moving objects tracking under complex scenes[C]//Proceedings of the 8th World Congress on Intelligent Control and Automation.Dalian,China:IEEE,2006:9871-9875.
- [8]YILMAZ A,LI X,SHAH M.Contour based object tracking with occlusion handling in video acquired using mobile cameras[J].IEEE transactions on pattern analysis and machine intelligence,2004,26(11):1531-1536.
- [9]JONES Frank.欧氏空间上的勒贝格积分[M].北京:世界图书出版公司,2010:15-24.JONES Frank.Lebesgue integration on Euclidean space[M].Beijing:World Publishing Corporation,2010:15-24.
- [10]VIEREN C,CABESTAING F,POSTAIRE J.Catching moving objects with snakes for motion tracking[J].Pattern recognition letters,1995,18(7):679-685.
- [11]ROSS S M.概率论基础教程[M].北京:机械工业出版社,2014:89-95.ROSS S M.A first course in probability[M].Beijing:China Machine Press,2014:89-95.
- [12]SEKI M,FUJIWARA H,SUMI K.A robust background subtraction method for changing background[C]//Proceedings of the Fifth IEEE Workshop on Applications of Computer Vision.Palm Springs:IEEE,2000:207-213.
- [13]NERI A,COLONNESE S,RUSSO G.Automatic moving object and background separation[J].Signal processing,1998,66(2):219-232.71
- [14]FARMER M E,HSU R L,JAIN A K.Interacting multiple model(IMM)Kalman filters for robust high speed human motion tracking[C]//Proceedings of the 16th International Conference on Pattern Recognition.Quebec City:IEEE,2002:20-23.
- [15]卢健,王晖.SVD和DCT提取特征向量的方法在人脸识别中的比较[J].武汉大学学报(信息科学版),2005,30(2):118-121.LU Jian,WANG Hui.Comparison between SVD and DCT feature extraction methods in face recognition[J].Journal of Wuhan University(geomatics and information science),2005,30(2):118-121.