无人机视频图像运动目标检测算法综述
|
摘要
运动目标检测是实现目标跟踪、交通监控、行为分析等任务的基础。但在无人机获取的视频图像中,无人机运动、旋翼震动或外界风力等客观因素使图像出现较为明显的背景、光照等变化,会对运动目标的检测产生影响。因此,如何降低干扰、提高检测精度,让无人机在运动目标检测领域发挥作用在信息时代具有相当重要的意义。无人机视频图像的运动目标检测相比传统运动目标检测,检测思路基本一致,但干扰因素众多。本文以此为切入点,分类综述了适用于无人机视频图像运动目标检测的算法及其改进,主要包括运动估计算法、帧间差法、背景建模法、光流法等传统算法和近年出现的新型算法;通过对无人机运动状态的划分探讨比较了上述方法的优缺点及适用场景。帧间差法更适合处理无人机悬停状态的数据,背景建模法、光流法及新型算法对无人机悬停及巡航状态的数据均可处理;上述算法均不能很好解决光照变化造成误检、漏检现象。所以处理无人机视频数据时,要根据其运动信息及数据特点选择合适的算法,才能获得好的检测结果。
Moving target detection is the basis for tasks such as target tracking,traffic monitoring and behavior analysis.However,in the video images captured by UAV,objective factors such as drone movement,propeller rotation or wind will affect the detection of moving targets,these uncertainties may cause failure during the detection.It is very important to reduce the interference,improve the detection accuracy,and make the UAV play an important role in the field of motion detection in the information age.Compared with thetraditional moving target detection,the detection method of UAV video image is basically consistent with many interference factors.In this paper,the algorithm and its improvement for UAV video image moving target detection are summarized,including traditional algorithms such as motion estimation algorithm,frame difference method,background modeling method,optical flow method,and new algorithms appearing in recent years.The advantages,disadvantages and application scenarios of the above methods have been compared through the division of UAV movement status.The frame difference method is more suitable for the data of UAV hover state,the background modeling method,the optical flow method and the new algorithm can be used to deal with the UAV hover and cruise state data.None of them can solve the problem of false detection and missed inspection caused by illumination change.For processing UAV video data,it is necessary to select an appropriate algorithm according to its motion information and data characteristics to obtain good detection results.
Moving target detection is the basis for tasks such as target tracking,traffic monitoring and behavior analysis.However,in the video images captured by UAV,objective factors such as drone movement,propeller rotation or wind will affect the detection of moving targets,these uncertainties may cause failure during the detection.It is very important to reduce the interference,improve the detection accuracy,and make the UAV play an important role in the field of motion detection in the information age.Compared with thetraditional moving target detection,the detection method of UAV video image is basically consistent with many interference factors.In this paper,the algorithm and its improvement for UAV video image moving target detection are summarized,including traditional algorithms such as motion estimation algorithm,frame difference method,background modeling method,optical flow method,and new algorithms appearing in recent years.The advantages,disadvantages and application scenarios of the above methods have been compared through the division of UAV movement status.The frame difference method is more suitable for the data of UAV hover state,the background modeling method,the optical flow method and the new algorithm can be used to deal with the UAV hover and cruise state data.None of them can solve the problem of false detection and missed inspection caused by illumination change.For processing UAV video data,it is necessary to select an appropriate algorithm according to its motion information and data characteristics to obtain good detection results.
引文
[1]李德仁,李明.无人机遥感系统的研究进展与应用前景[J].武汉大学学报(信息科学版),2014,39(5):505-513.LI D R,LI M.Research advance and application prospect of unmanned aerial vehicle remote sensingsystem[J].Geomatics and Information Science of Wuhan University,2014,39(5):505-513.(in Chinese)
[2]王欢.运动目标检测与跟踪技术研究[D].南京:南京理工大学,2009.WANG H.Research on moving object detection and trackingtechniques[D].Nanjing:Nanjing University of Science&Technology,2009.(in Chinese)
[3]POLLARD T,ANTONE M.Detecting and tracking all moving objects in wide-area aerial video[C]//Proceedings of 2012 Computer Vision and Pattern Recognition Workshops.Providence,Rhode Island,USA:IEEE,2012:15-22.
[4]REINARTZ P,LACHAISE M,SCHMEER E,et al.Traffic monitoring with serial images from airborne cameras[J].ISPRS Journal of Photogrammetry and Remote Sensing,2006,61(3-4):149-158.
[5]CAO X,LAN J,YAN P,et al.Vehicle detection and tracking in airborne videos by multi-motion layer analysis[J].Machine Vision and Applications,2012,23(5):921-935.
[6]COLLINS,LIPTON,KANADE,et al.A system for video surveillance and monitoring:VSAM final report[R].Carnegie:Carnegie Mellon University,2000.
[7]ALI S,SHAH M.COCOA:tracking in aerial imagery[J].SPIE,2006,6209(1):105-114.
[8]SHASTRY A C,SCHOWENGERDT R A.Airborne video registration and traffic-flow parameter estimation[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(4):391-405.
[9]ABDELWAHAB M A,ABDELWAHAB M M.A novel algorithm for vehicle detection and tracking in airborne videos[C]//Proceedings of 2015 IEEE International Symposium on Multimedia.Miami,Florida,USA:IEEE,2015:65-68.
[10]董晶,傅丹,杨夏.无人机视频运动目标实时检测及跟踪[J].应用光学,2013,34(2):255-259.DONG J,FU D,YANG X.Real-time moving object detection and tracking by using UAV videos[J].Journal of Applied Optics,2013,34(2):255-259.(in Chinese)
[11]彭博,蔡晓禹,张有节,等.基于对称帧差和分块背景建模的无人机视频车辆自动检测[J].东南大学学报(自然科学版),2017,47(4):685-690.PENG B,CAI X Y,ZHANG Y J,et al.Automatic vehicle detection from UAV videos based on symmetrical frame difference and background block modeling[J].Journal of Southeast University(Natural Science Edition),2017,47(4):685-690.(in Chinese)
[12]蔡晓禹,张有节,彭博,等.基于无人机视频的车辆检测与评价指标研究[J].计算机仿真,2017,34(8):157-161.CAI X Y,ZHANG Y J,PENG B,et al.Research on vehicle detection Based on UAV video and its evaluation Indexes[J].Computer Simulation,2017,34(8):157-161.(in Chinese)
[13]刘亚伟,李小民.无人机航拍视频中目标检测和跟踪方法综述[J].飞航导弹,2016(9):53-56,70.LIU YY,LI X M.Review of target detection and tracking methods in UAV aerial video[J].Winged Missiles Journal,2016(9):53-56,70.(in Chinese)
[14]李文辉.航拍视频中运动目标的检测与跟踪算法研究[D].西安:西安电子科技大学,2014.LI W H.Research on detection and tracking algorithms of moving target in aerialvideo[D].Xian:Xidian University,2014.(in Chinese).
[15]王大伟,严俊,王彬,等.视频序列的运动估计技术综述[J].电视技术,2012,36(3):20-23.WANG D W,YAN J,WANG B,et al.Survey of motion estimation used in video sequence[J].Video Engineering,2012,36(3):20-23.(in Chinese)
[16]黄新生,杨庆伟,王亦平,等.图像序列运动估计技术综述[J].计算机仿真,2008,25(5):180-184.HUANG X S,YANG Q W,WANG Y P,et al.Review of motion estimation technique for image sequence[J].Computer Simulation,2008,25(5):180-184.(in Chinese)
[17]钟平,于前洋,金光.基于特征点匹配技术的运动估计及补偿方法[J].光电子·激光,2004,15(1):73-77.ZHONG P,YU Q Y,JIN G.Motion estimation and motion compensation based on matching technology of feature point[J].Journal of Optoelectronics·Laser,2004,15(1):73-77.(in Chinese)
[18]武艳美,肖阳辉.基于特征点匹配的全局运动估计[J].计算机工程,2011,37(22):148-150.WU Y X,XIAO Y H.Global motion estimation based on feature points matching[J].Computer Engineering,2011,37(22):148-150.(in Chinese)
[19]宋宇,李嵩,游海龙,等.航拍视频中基于特征匹配的全局运动估计[J].长春工业大学学报,2015,36(2):214-217.SONG Y,LI S,YOU H L,et al.Feature matching based global motion estimation for aerial video data[J].Journal of Changchun University of Technology,2015,36(2):214-217.(in Chinese)
[20]万缨,韩毅,卢汉清.运动目标检测算法的探讨[J].计算机仿真,2006,23(10):221-226.WAN Y,HAN Y,LU H Q.The methods for moving object detection[J].Computer Simulation,2006,23(10):221-226.(in Chinese)
[21]尹宏鹏,陈波,柴毅,等.基于视觉的目标检测与跟踪综述[J].自动化学报,2016,42(10):1466-1489.YIN H P,CHEN B,CHAI Y,et al.Vision-based object detection and tracking:a review[J].Acta Automatica Sinica,2016,42(10):1466-1489.(in Chinese)
[22]程爱灵,黄昶,李小雨.运动目标检测算法研究综述[J].信息通信,2017(1):12-14.CHENG AI L,HUANG X,LI X Y.Review on the algorithm of moving target detection[J].Information&Communications,2017(1):12-14.(in Chinese)
[23]LIU G,NING S,YOU Y,et al.An improved moving objects detection algorithm[C]//Proceedings of2013 International Conference on Wavelet Analysis and Pattern Recognition.Tianjin,China:IEEE,2013,29(5):96-102.
[24]谢红,原博,解武.一种基于改进三帧差分和ViBe算法的运动目标检测算法[J].应用科技,2016,43(6):46-52.XIE H,YUAN B,XIE W.Moving target detection algorithm based on the improved three-frame differences and ViBe algorithm[J].Applied Science and Technology,2016,43(6):46-52.(in Chinese)
[25]陈宝远,霍智超,陈光毅,等.一种改进的三帧差分运动目标检测算法[J].应用科技,2016(2):10-13.CHEN B Y,HUO Z C,CHEN G Y,et al.An improved three-frame difference algorithm for moving object detection[J].Applied Science and Technology,2016(2):10-13.(in Chinese)
[26]苏杭.动态背景多目标检测与跟踪技术研究[D].成都:电子科技大学,2016.SU H.Multi-object detection and tracking technology research in the dynamic background[D].Chengdu:University of Electronic Science and Technology of China,2016.(in Chinese).
[27]STAUFFER C,GRIMSON W E L.Adaptive background mixture models for real-time Tracking[C]//Proceedings of1999 Computer Vision and Pattern Recognition.Ft.Collins,CO,USA:IEEE,1999,2:252Vol.2.
[28]BARNICH O,DROOGENBROECK M V.ViBE:A powerful random technique to estimate the background in video sequences[C]//Proceedings of 2009 IEEE International Conference on Acoustics,Speech and Signal Processing.Taipei,Taiwan,China:IEEE,2009:945-948.
[29]BARNICH O,VAN DROOGENBROECK M.ViBe:A universal background subtraction algorithm for video sequences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[30]张磊,傅志中,周岳平.基于HSV颜色空间和Vibe算法的运动目标检测[J].计算机工程与应用,2014(04):181-185.ZHANG L,FU Z Z,ZHOU Y P.Moving objects detection based on HSV colorspace and Vibe algorithm[J].Computer Engineering and Applications,2014(04):181-185.(in Chinese)
[31]HORN B K P,SCHUNCK B G.Determining optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[32]余启明.基于背景减法和帧差法的运动目标检测算法研究[D].赣州:江西理工大学,2013.YU Q M.Research on moving object detection algorithm based on subtraction background method and frame difference method[D].Ganzhou:Jiangxi University of Science and Technology,2013.(in Chinese)
[33]张苑欣.动态背景下运动目标的检测与跟踪[D].西安:西安电子科技大学,2015.ZHANG Y X.Research on the moving targets detection and tracking methods under the dynamic scenes[D].Xidian:Xidian University,2015.(in Chinese)
[34]LUCAS B D,KANADE T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of th 7th International Joint Conference on Artificial Intelligence.Vancouver,British Columbia,Canada:IJCAI,1981,2(3):674-679.
[35]BAARIR Z E,CHARIF F.Fast modified Horn&Schunck method for the estimation of optical flow fields[C]//Proceedings of2011 Signal Processing Systems.BEIrut,lEBanon:IEEE,2011:283-288.
[36]刘洪彬,常发亮.权重系数自适应光流法运动目标检测[J].光学精密工程,2016,24(2):460-468.LIU H B,CHANG F L.Moving object detection by optical flow method based on adaptive weight coefficient[J].Optics and Precision Engineering,2016,24(2):460-468.(in Chinese)
[37]慈文彦.运动目标检测方法综述[J].信息技术,2016(12):93-100.CI W Y.A review on moving target detection in video sequences[J].Information Technology,2016(12):93-100.(in Chinese)
[38]李俊韬,张海,范跃祖,等.复杂场景条件下的运动目标检测算法[J].光电工程,2004,31(S1):36-39.LI J T,ZHANG H,FAN Y Z,et al.A detection algorithm for moving targets in complex scenes[J].Opto-Electronic Engineering,2004,35(S1):36-39.(in Chinese)
[39]李响,谭南林,王天雷,等.复杂场景下基于局部运动补偿的目标检测[J].仪器仪表学报,2014,31(07):1555-1563.LI X,TAN N L,WANG T L,et al.Object detection based on local motion compensation in complex scenes[J].Chinese Journal of Scientific Instrument,2014,35(7):1555-1563.(in Chinese)
[40]张旭光,韩广良,孙巍,等.复杂背景下运动目标的提取[J].光电工程,2006,33(4):10-13.ZHANG X G,HAN L,SUN W,et al.Extraction of moving objects in clutter background[J].Opto-Electronic Engineering,2006,33(4):10-13.(in Chinese)
[41]DONG X,WANG K,JIA G.Moving Object and Shadow Detection Based on RGB Color Space and Edge Ratio[C]//Proceedings of 2009 International Congress on Image and Signal Processing.Tianjin,China:IEEE,2009:1-5.
[42]LIAO S,ZHAO G,KELLOKUMPU V,et al.Modeling pixel process with scale invariant local patterns for background subtraction in complex scene[C]//Proceedings of 2010 Computer Vision and Pattern Recognition.San Francisco,CA,USA:IEEE,2010:1301-1306.
[43]CHOI J M,CHANG H J,YOO Y J,et al.Robust moving object detection against fast illumination change[J].Computer Vision and Image Understanding,2012,116(2):179-193.
[44]MINAEIAN S,LIU J,SON Y J.Effective and efficient detection of moving targets from a UAV’s camera[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(2):497-506.
[45]TEUTSCH M,KRGER W,BEYERER J.Moving object detection in top-view aerial videos improved by image stacking[J].Optical Engineering,2017,56(8):1083102.
[46]KALANTAR B,MANSOR S B,ABDUL HALIN A,et al.Multiple moving object detection from UAV videos using trajectories of matched regional adjacency graphs[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(9):5198-5213.
[47]王妍.基于无人机视频的运动车辆检测研究[D].北京:北京交通大学,2017.WANG Y.Research on moving vehicle detection based on UAV videos[D].Beijing:Beijing Jiaotong University,2017.(in Chinese)
[48]冯艳.动态背景下基于SIFT特征匹配的目标检测算法[D].西安:西安电子科技大学,2014.FENG Y.A target detection algorithm in dynamic background based on SIFT feature matching[D].Xian:XIDI-AN UNIVERSITY,2014.(in Chinese)
[49]张森悦,李一波.复杂条件下的运动目标检测方法研究综述[J].沈阳航空工业学院学报,2008,25(3):59-63.ZHANG S Y,LI Y B.Study survey on moving objects detection in complicated condition[J].Journal of Shenyang Institute of Aeronautical Engineering,2008,25(3):59-63.(in Chinese)
[50]于渊博,张涛,郭立红,等.卫星视频运动目标检测算法[J].液晶与显示,2017,(32):138-143.YU Y B,ZHANG T,GUO L H,et al.Moving objects detection on satellite video[J].Chinese Journal of Liquid Crystals and Displays,2017,32(2):138-143.(in Chinese)
[2]王欢.运动目标检测与跟踪技术研究[D].南京:南京理工大学,2009.WANG H.Research on moving object detection and trackingtechniques[D].Nanjing:Nanjing University of Science&Technology,2009.(in Chinese)
[3]POLLARD T,ANTONE M.Detecting and tracking all moving objects in wide-area aerial video[C]//Proceedings of 2012 Computer Vision and Pattern Recognition Workshops.Providence,Rhode Island,USA:IEEE,2012:15-22.
[4]REINARTZ P,LACHAISE M,SCHMEER E,et al.Traffic monitoring with serial images from airborne cameras[J].ISPRS Journal of Photogrammetry and Remote Sensing,2006,61(3-4):149-158.
[5]CAO X,LAN J,YAN P,et al.Vehicle detection and tracking in airborne videos by multi-motion layer analysis[J].Machine Vision and Applications,2012,23(5):921-935.
[6]COLLINS,LIPTON,KANADE,et al.A system for video surveillance and monitoring:VSAM final report[R].Carnegie:Carnegie Mellon University,2000.
[7]ALI S,SHAH M.COCOA:tracking in aerial imagery[J].SPIE,2006,6209(1):105-114.
[8]SHASTRY A C,SCHOWENGERDT R A.Airborne video registration and traffic-flow parameter estimation[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(4):391-405.
[9]ABDELWAHAB M A,ABDELWAHAB M M.A novel algorithm for vehicle detection and tracking in airborne videos[C]//Proceedings of 2015 IEEE International Symposium on Multimedia.Miami,Florida,USA:IEEE,2015:65-68.
[10]董晶,傅丹,杨夏.无人机视频运动目标实时检测及跟踪[J].应用光学,2013,34(2):255-259.DONG J,FU D,YANG X.Real-time moving object detection and tracking by using UAV videos[J].Journal of Applied Optics,2013,34(2):255-259.(in Chinese)
[11]彭博,蔡晓禹,张有节,等.基于对称帧差和分块背景建模的无人机视频车辆自动检测[J].东南大学学报(自然科学版),2017,47(4):685-690.PENG B,CAI X Y,ZHANG Y J,et al.Automatic vehicle detection from UAV videos based on symmetrical frame difference and background block modeling[J].Journal of Southeast University(Natural Science Edition),2017,47(4):685-690.(in Chinese)
[12]蔡晓禹,张有节,彭博,等.基于无人机视频的车辆检测与评价指标研究[J].计算机仿真,2017,34(8):157-161.CAI X Y,ZHANG Y J,PENG B,et al.Research on vehicle detection Based on UAV video and its evaluation Indexes[J].Computer Simulation,2017,34(8):157-161.(in Chinese)
[13]刘亚伟,李小民.无人机航拍视频中目标检测和跟踪方法综述[J].飞航导弹,2016(9):53-56,70.LIU YY,LI X M.Review of target detection and tracking methods in UAV aerial video[J].Winged Missiles Journal,2016(9):53-56,70.(in Chinese)
[14]李文辉.航拍视频中运动目标的检测与跟踪算法研究[D].西安:西安电子科技大学,2014.LI W H.Research on detection and tracking algorithms of moving target in aerialvideo[D].Xian:Xidian University,2014.(in Chinese).
[15]王大伟,严俊,王彬,等.视频序列的运动估计技术综述[J].电视技术,2012,36(3):20-23.WANG D W,YAN J,WANG B,et al.Survey of motion estimation used in video sequence[J].Video Engineering,2012,36(3):20-23.(in Chinese)
[16]黄新生,杨庆伟,王亦平,等.图像序列运动估计技术综述[J].计算机仿真,2008,25(5):180-184.HUANG X S,YANG Q W,WANG Y P,et al.Review of motion estimation technique for image sequence[J].Computer Simulation,2008,25(5):180-184.(in Chinese)
[17]钟平,于前洋,金光.基于特征点匹配技术的运动估计及补偿方法[J].光电子·激光,2004,15(1):73-77.ZHONG P,YU Q Y,JIN G.Motion estimation and motion compensation based on matching technology of feature point[J].Journal of Optoelectronics·Laser,2004,15(1):73-77.(in Chinese)
[18]武艳美,肖阳辉.基于特征点匹配的全局运动估计[J].计算机工程,2011,37(22):148-150.WU Y X,XIAO Y H.Global motion estimation based on feature points matching[J].Computer Engineering,2011,37(22):148-150.(in Chinese)
[19]宋宇,李嵩,游海龙,等.航拍视频中基于特征匹配的全局运动估计[J].长春工业大学学报,2015,36(2):214-217.SONG Y,LI S,YOU H L,et al.Feature matching based global motion estimation for aerial video data[J].Journal of Changchun University of Technology,2015,36(2):214-217.(in Chinese)
[20]万缨,韩毅,卢汉清.运动目标检测算法的探讨[J].计算机仿真,2006,23(10):221-226.WAN Y,HAN Y,LU H Q.The methods for moving object detection[J].Computer Simulation,2006,23(10):221-226.(in Chinese)
[21]尹宏鹏,陈波,柴毅,等.基于视觉的目标检测与跟踪综述[J].自动化学报,2016,42(10):1466-1489.YIN H P,CHEN B,CHAI Y,et al.Vision-based object detection and tracking:a review[J].Acta Automatica Sinica,2016,42(10):1466-1489.(in Chinese)
[22]程爱灵,黄昶,李小雨.运动目标检测算法研究综述[J].信息通信,2017(1):12-14.CHENG AI L,HUANG X,LI X Y.Review on the algorithm of moving target detection[J].Information&Communications,2017(1):12-14.(in Chinese)
[23]LIU G,NING S,YOU Y,et al.An improved moving objects detection algorithm[C]//Proceedings of2013 International Conference on Wavelet Analysis and Pattern Recognition.Tianjin,China:IEEE,2013,29(5):96-102.
[24]谢红,原博,解武.一种基于改进三帧差分和ViBe算法的运动目标检测算法[J].应用科技,2016,43(6):46-52.XIE H,YUAN B,XIE W.Moving target detection algorithm based on the improved three-frame differences and ViBe algorithm[J].Applied Science and Technology,2016,43(6):46-52.(in Chinese)
[25]陈宝远,霍智超,陈光毅,等.一种改进的三帧差分运动目标检测算法[J].应用科技,2016(2):10-13.CHEN B Y,HUO Z C,CHEN G Y,et al.An improved three-frame difference algorithm for moving object detection[J].Applied Science and Technology,2016(2):10-13.(in Chinese)
[26]苏杭.动态背景多目标检测与跟踪技术研究[D].成都:电子科技大学,2016.SU H.Multi-object detection and tracking technology research in the dynamic background[D].Chengdu:University of Electronic Science and Technology of China,2016.(in Chinese).
[27]STAUFFER C,GRIMSON W E L.Adaptive background mixture models for real-time Tracking[C]//Proceedings of1999 Computer Vision and Pattern Recognition.Ft.Collins,CO,USA:IEEE,1999,2:252Vol.2.
[28]BARNICH O,DROOGENBROECK M V.ViBE:A powerful random technique to estimate the background in video sequences[C]//Proceedings of 2009 IEEE International Conference on Acoustics,Speech and Signal Processing.Taipei,Taiwan,China:IEEE,2009:945-948.
[29]BARNICH O,VAN DROOGENBROECK M.ViBe:A universal background subtraction algorithm for video sequences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[30]张磊,傅志中,周岳平.基于HSV颜色空间和Vibe算法的运动目标检测[J].计算机工程与应用,2014(04):181-185.ZHANG L,FU Z Z,ZHOU Y P.Moving objects detection based on HSV colorspace and Vibe algorithm[J].Computer Engineering and Applications,2014(04):181-185.(in Chinese)
[31]HORN B K P,SCHUNCK B G.Determining optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[32]余启明.基于背景减法和帧差法的运动目标检测算法研究[D].赣州:江西理工大学,2013.YU Q M.Research on moving object detection algorithm based on subtraction background method and frame difference method[D].Ganzhou:Jiangxi University of Science and Technology,2013.(in Chinese)
[33]张苑欣.动态背景下运动目标的检测与跟踪[D].西安:西安电子科技大学,2015.ZHANG Y X.Research on the moving targets detection and tracking methods under the dynamic scenes[D].Xidian:Xidian University,2015.(in Chinese)
[34]LUCAS B D,KANADE T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of th 7th International Joint Conference on Artificial Intelligence.Vancouver,British Columbia,Canada:IJCAI,1981,2(3):674-679.
[35]BAARIR Z E,CHARIF F.Fast modified Horn&Schunck method for the estimation of optical flow fields[C]//Proceedings of2011 Signal Processing Systems.BEIrut,lEBanon:IEEE,2011:283-288.
[36]刘洪彬,常发亮.权重系数自适应光流法运动目标检测[J].光学精密工程,2016,24(2):460-468.LIU H B,CHANG F L.Moving object detection by optical flow method based on adaptive weight coefficient[J].Optics and Precision Engineering,2016,24(2):460-468.(in Chinese)
[37]慈文彦.运动目标检测方法综述[J].信息技术,2016(12):93-100.CI W Y.A review on moving target detection in video sequences[J].Information Technology,2016(12):93-100.(in Chinese)
[38]李俊韬,张海,范跃祖,等.复杂场景条件下的运动目标检测算法[J].光电工程,2004,31(S1):36-39.LI J T,ZHANG H,FAN Y Z,et al.A detection algorithm for moving targets in complex scenes[J].Opto-Electronic Engineering,2004,35(S1):36-39.(in Chinese)
[39]李响,谭南林,王天雷,等.复杂场景下基于局部运动补偿的目标检测[J].仪器仪表学报,2014,31(07):1555-1563.LI X,TAN N L,WANG T L,et al.Object detection based on local motion compensation in complex scenes[J].Chinese Journal of Scientific Instrument,2014,35(7):1555-1563.(in Chinese)
[40]张旭光,韩广良,孙巍,等.复杂背景下运动目标的提取[J].光电工程,2006,33(4):10-13.ZHANG X G,HAN L,SUN W,et al.Extraction of moving objects in clutter background[J].Opto-Electronic Engineering,2006,33(4):10-13.(in Chinese)
[41]DONG X,WANG K,JIA G.Moving Object and Shadow Detection Based on RGB Color Space and Edge Ratio[C]//Proceedings of 2009 International Congress on Image and Signal Processing.Tianjin,China:IEEE,2009:1-5.
[42]LIAO S,ZHAO G,KELLOKUMPU V,et al.Modeling pixel process with scale invariant local patterns for background subtraction in complex scene[C]//Proceedings of 2010 Computer Vision and Pattern Recognition.San Francisco,CA,USA:IEEE,2010:1301-1306.
[43]CHOI J M,CHANG H J,YOO Y J,et al.Robust moving object detection against fast illumination change[J].Computer Vision and Image Understanding,2012,116(2):179-193.
[44]MINAEIAN S,LIU J,SON Y J.Effective and efficient detection of moving targets from a UAV’s camera[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(2):497-506.
[45]TEUTSCH M,KRGER W,BEYERER J.Moving object detection in top-view aerial videos improved by image stacking[J].Optical Engineering,2017,56(8):1083102.
[46]KALANTAR B,MANSOR S B,ABDUL HALIN A,et al.Multiple moving object detection from UAV videos using trajectories of matched regional adjacency graphs[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(9):5198-5213.
[47]王妍.基于无人机视频的运动车辆检测研究[D].北京:北京交通大学,2017.WANG Y.Research on moving vehicle detection based on UAV videos[D].Beijing:Beijing Jiaotong University,2017.(in Chinese)
[48]冯艳.动态背景下基于SIFT特征匹配的目标检测算法[D].西安:西安电子科技大学,2014.FENG Y.A target detection algorithm in dynamic background based on SIFT feature matching[D].Xian:XIDI-AN UNIVERSITY,2014.(in Chinese)
[49]张森悦,李一波.复杂条件下的运动目标检测方法研究综述[J].沈阳航空工业学院学报,2008,25(3):59-63.ZHANG S Y,LI Y B.Study survey on moving objects detection in complicated condition[J].Journal of Shenyang Institute of Aeronautical Engineering,2008,25(3):59-63.(in Chinese)
[50]于渊博,张涛,郭立红,等.卫星视频运动目标检测算法[J].液晶与显示,2017,(32):138-143.YU Y B,ZHANG T,GUO L H,et al.Moving objects detection on satellite video[J].Chinese Journal of Liquid Crystals and Displays,2017,32(2):138-143.(in Chinese)