基于帧差法和混合高斯的海上运动目标检测
|
摘要
海上运动目标检测是视频信息处理的重要研究内容之一。由于海上场景的复杂性,传统的高斯混合背景模型存在一定的不足。因此论文提出了一种三帧差分法和改进的混合高斯背景模型相结合的运动目标检测算法。首先,用三帧差分法检测出变化的区域;然后,根据相邻像素间的相关性,把每帧图像划分为背景区域、干扰区域和目标区域,对不同的区域采取不同的更新策略,从而实现模型的自适应学习。实验表明,该方法可以有效地抑制海上波纹对运动目标检测的影响,并具有较好的灵敏度、自适应性和良好的检测效果。
The detection of marine moving target is one of the important research contents of video information processing. Due to the complexity of the sea scene,the traditional Gaussian mixed background model has some shortcomings. Therefore,this paper presents a three-frame difference method and an improved hybrid Gaussian background model combined with the moving target detection algorithm. Firstly,the change of the region is detected by the three-frame difference method. Then,according to the correlation between adjacent pixels,each frame image is divided into background region,interference region and target area,and different updating strategies are adopted for different regions,so as to realize the adaptive learning of the model. Experiments show that the method can effectively suppress the influence of sea ripple on the detection of moving objects,and has good sensitivity,self-adaptability and good detection results.
The detection of marine moving target is one of the important research contents of video information processing. Due to the complexity of the sea scene,the traditional Gaussian mixed background model has some shortcomings. Therefore,this paper presents a three-frame difference method and an improved hybrid Gaussian background model combined with the moving target detection algorithm. Firstly,the change of the region is detected by the three-frame difference method. Then,according to the correlation between adjacent pixels,each frame image is divided into background region,interference region and target area,and different updating strategies are adopted for different regions,so as to realize the adaptive learning of the model. Experiments show that the method can effectively suppress the influence of sea ripple on the detection of moving objects,and has good sensitivity,self-adaptability and good detection results.
引文
[1]Zhang Jie-yu,Barron J L.Optical flow at occluion[C]//The Ninth Conference on Computer and Robot Vision,Toronto,Canada,2012:198-205.
[2]Tsai D M,Lai S C.Independent component analysis-based background subtraction for indoor surveillance[J].IEEE Transactions on Image Processing,2009,18(1):158-160.
[3]Piccardi M.Background subtraction techniques:a review[C]//IEEE International Conference on Systems,Man and Cybernetics,Sydney,Australia,2004:3099-3104.
[4]孙挺,齐迎春,耿国华.基于帧间差分和背景差分的运动目标检测算法[J].吉林大学学报(工学版),2016,46(4):1326-1329.SUN Ting,QI Yingchun,GENG Guohua.Motion target detection algorithm based on interframe difference and background difference[J].Journal of Jilin University(Engineering Science),2016,46(4):1326-1329.
[5]王明芬,李翠华,余强力.基于融合邻域信息的海面运动目标检测[J].厦门大学学报(自然科学版),2007,46(5):641-645.WANG Mingfen,LI Cuihua,YU Qiangli.Study on sea surface moving target detection based on fusion neighborhood information[J].Journal of Xiamen University(Natural Science Edition),2007,46(5):641-645.
[6]WC Hu,CY Yang,DY Huang.Robust real-time ship detection and tracking for visual surveillance of cage aquaculture[J].Visual Communication&Image Representation,2011,3(9):543-556.
[7]吴琦颖,李翠华.一种新颖的海上运动目标实时检测方法[J].计算机工程与应用,2007,43(14):213-216.WU Qiying,LI Cuihua.A novel real-time detection method for maritime moving targets[J].Computer Engineering and Applications,2007,43(14):213-216.
[8]谢小竹,洪景新,肖思兴.有效的海上运动目标检测方法[J].计算机工程与应用,2009,45(4):225.XIE Xiaozhu,HONG Jingxin,XIAO Sixing.Effective method for detecting sea moving targets[J].Computer Engineering and Applications,2009,45(4):225.
[9]Stauffer C,Grimsen W.Adaptive background mixture models for real-time tracking[C]//In:Proceedings of IEEEConference on Computer Vision and Pattern Recognition,Fort Collins,Colorado,USA,1999:246-252.
[10]吕国亮,赵曙光,赵俊.基于三帧差分和连通性检验的图像运动目标检测新方法[J].液晶与显示,2007(1):87-92.LV Guoliang,ZHAO Shuguang,ZHAO Jun.A New Method for Image Moving Target Detection Based on Three-frame Difference and Connectivity Test[J].LCDand Display,2007(1):87-92.
[11]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图象图形学报,2008,13(4):729-734.LIU Xin,LIU Hui,QIANG Zhenping,et al.Hybrid background model of mixed Gaussian model and interframe difference fusion[J].Chinese Journal of Image and Graphics,2008,13(4):729-734.
[12]刘静,王玲.混合高斯模型背景法的一种改进算法[J].计算机工程与应用,2010,46(13):168-170.LIU Jing,WANG Ling.Improved algorithm of Gaussian mixture model for background subtraction[J].Computer Engineering and Applications,2010,46(13):168-170.
[13]Sheikh Y,Shah M.Bayesian modeling of dynamic scenes for object detection[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(11):1778-1792.
[14]Zivkovic Z.Improved adaptive Gaussian mixture model for background subtraction[C]//In:Proceedings of the17th International Conference on Pattern Recognition,Cambridge,UnitedKingdom,2004,2:28-31.
[15]Hayman E,Eklundh J.Statistical background subtraction for a mobile observer[C]//In:Proceedings of the 9th International Conference on Computer Vision,Nice,France,2003:67-74.
[16]刘亚,艾海舟,徐光祐.一种基于背景模型的运动目标检测与跟踪算法[J].信息与控制,2002,31(4):315-319.LIU Ya,AI Haizhou,XU Guangyou.Moving object detection and tracking based on background subtraction[J].Information and Control,2002,31(4):315-319.
[2]Tsai D M,Lai S C.Independent component analysis-based background subtraction for indoor surveillance[J].IEEE Transactions on Image Processing,2009,18(1):158-160.
[3]Piccardi M.Background subtraction techniques:a review[C]//IEEE International Conference on Systems,Man and Cybernetics,Sydney,Australia,2004:3099-3104.
[4]孙挺,齐迎春,耿国华.基于帧间差分和背景差分的运动目标检测算法[J].吉林大学学报(工学版),2016,46(4):1326-1329.SUN Ting,QI Yingchun,GENG Guohua.Motion target detection algorithm based on interframe difference and background difference[J].Journal of Jilin University(Engineering Science),2016,46(4):1326-1329.
[5]王明芬,李翠华,余强力.基于融合邻域信息的海面运动目标检测[J].厦门大学学报(自然科学版),2007,46(5):641-645.WANG Mingfen,LI Cuihua,YU Qiangli.Study on sea surface moving target detection based on fusion neighborhood information[J].Journal of Xiamen University(Natural Science Edition),2007,46(5):641-645.
[6]WC Hu,CY Yang,DY Huang.Robust real-time ship detection and tracking for visual surveillance of cage aquaculture[J].Visual Communication&Image Representation,2011,3(9):543-556.
[7]吴琦颖,李翠华.一种新颖的海上运动目标实时检测方法[J].计算机工程与应用,2007,43(14):213-216.WU Qiying,LI Cuihua.A novel real-time detection method for maritime moving targets[J].Computer Engineering and Applications,2007,43(14):213-216.
[8]谢小竹,洪景新,肖思兴.有效的海上运动目标检测方法[J].计算机工程与应用,2009,45(4):225.XIE Xiaozhu,HONG Jingxin,XIAO Sixing.Effective method for detecting sea moving targets[J].Computer Engineering and Applications,2009,45(4):225.
[9]Stauffer C,Grimsen W.Adaptive background mixture models for real-time tracking[C]//In:Proceedings of IEEEConference on Computer Vision and Pattern Recognition,Fort Collins,Colorado,USA,1999:246-252.
[10]吕国亮,赵曙光,赵俊.基于三帧差分和连通性检验的图像运动目标检测新方法[J].液晶与显示,2007(1):87-92.LV Guoliang,ZHAO Shuguang,ZHAO Jun.A New Method for Image Moving Target Detection Based on Three-frame Difference and Connectivity Test[J].LCDand Display,2007(1):87-92.
[11]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图象图形学报,2008,13(4):729-734.LIU Xin,LIU Hui,QIANG Zhenping,et al.Hybrid background model of mixed Gaussian model and interframe difference fusion[J].Chinese Journal of Image and Graphics,2008,13(4):729-734.
[12]刘静,王玲.混合高斯模型背景法的一种改进算法[J].计算机工程与应用,2010,46(13):168-170.LIU Jing,WANG Ling.Improved algorithm of Gaussian mixture model for background subtraction[J].Computer Engineering and Applications,2010,46(13):168-170.
[13]Sheikh Y,Shah M.Bayesian modeling of dynamic scenes for object detection[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(11):1778-1792.
[14]Zivkovic Z.Improved adaptive Gaussian mixture model for background subtraction[C]//In:Proceedings of the17th International Conference on Pattern Recognition,Cambridge,UnitedKingdom,2004,2:28-31.
[15]Hayman E,Eklundh J.Statistical background subtraction for a mobile observer[C]//In:Proceedings of the 9th International Conference on Computer Vision,Nice,France,2003:67-74.
[16]刘亚,艾海舟,徐光祐.一种基于背景模型的运动目标检测与跟踪算法[J].信息与控制,2002,31(4):315-319.LIU Ya,AI Haizhou,XU Guangyou.Moving object detection and tracking based on background subtraction[J].Information and Control,2002,31(4):315-319.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |