基于纹理特征改进的GFL运动目标提取方法
|
摘要
基于广义融合套索(GFL)前景模型,融合视频的纹理特征,提出一种基于纹理特征的运动目标提取方法。方法通过GFL前景模型提取前景运动目标和背景,再利用LBP算法提取前景与背景在多个方向上的纹理特征,比较两者纹理特征的相似度,去除前景中的投射阴影,解决由于运动目标遮挡产生的阴影问题,同时还引入误判率去描述模型的准确度。通过对广场、办公室以及体育馆等实际场景进行测试,实验表明提出的算法能够有效去除运动目标产生的阴影。
Based on Generalized Fused Lasso(GFL) foreground model and the texture information of video,this paper proposes a moving target extraction method based on texture features.This method uses GFL foreground model to extract foreground moving object and background.Then it extracts the texture features of foreground and background in many directions by LBP algorithm,compares the similarity of two texture features,and removes the misjudged shadow regions in the foreground,which can reduce the cast shadows due to occlusion of moving targets.The paper also introduces the misjudgment rate to describe the accuracy of model.By testing real scenes that contain cast shadows,such as squares,offices,and gymnasiums,the proposed algorithm can effectively monitor the areas where shadows are cast.
Based on Generalized Fused Lasso(GFL) foreground model and the texture information of video,this paper proposes a moving target extraction method based on texture features.This method uses GFL foreground model to extract foreground moving object and background.Then it extracts the texture features of foreground and background in many directions by LBP algorithm,compares the similarity of two texture features,and removes the misjudged shadow regions in the foreground,which can reduce the cast shadows due to occlusion of moving targets.The paper also introduces the misjudgment rate to describe the accuracy of model.By testing real scenes that contain cast shadows,such as squares,offices,and gymnasiums,the proposed algorithm can effectively monitor the areas where shadows are cast.
引文
[1]李瑞峰,王亮亮,王珂.人体动作行为识别研究综述[J].模式识别与人工智能,2014,27(1):35-48.
[2]OLIVER N M,ROSARIO B,PENTLAND A P.A Bayesian computer vision system for modeling human interactions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):255-272.
[3]蔡念,周杨,刘根,等.鲁棒主成分分析的运动目标检测综述[J].中国图象图形学报,2016,21(10):1265-1275.
[4]XIN B,TIAN Y,WANG Y Z,et al.Background subtraction via generalized fused lasso foreground modeling[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2015:4676-4684.
[5]WRIGHT J,GANESH A,RAO S,et al.Robust Principal Component Analysis:Exact Recovery of Corrupted Lowrank Matrices by Convex Optimization[R].Coordinated Science Laboratory Report,2009.
[6]张泽宏,徐贵力,许扬,等.一种鲁棒的运动目标阴影去除及修复算法[J].计算机与现代化,2018(7):98-102.
[7]XIN B,KAWAHARA Y,WANG Y Z,et al.Efficient generalized fused lasso and its application to the diagnosis of Alzheimer's disease[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.2014:2163-2169.
[8]CANDS E J,LI X,MA Y,et al.Robust principal component analysis?[J].Journal of the ACM(JACM),2011,58(3):11.
[9]OJALA T,PIETIKINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[10]周书仁,殷建平.基于Haar特性的LBP纹理特征[J].软件学报,2013,24(8):1909-1926.
[11]武明虎,宋冉冉,刘敏.结合HSV与纹理特征的视频阴影消除算法[J].中国图象图形学报,2017,22(10):1373-1380.
[12]毛秉毅.基于自适应LBP算法的纹理分析[J].计算机工程与应用,2007,43(2):89-90.
[13]练秋生,刘春亮.基于Gabor滤波器和LBP的分级掌纹识别[J].计算机工程与应用,2007,43(6):212-215.
[14]王玮,黄非非,李见为.使用多尺度LBP特征描述与识别人脸[J].光学精密工程,2008,16(4):696-705.
[15]梁鹏,何俊诗,黎绍发.基于多尺度LBP金字塔特征的分类算法[J].计算机工程,2011,37(8):166-168.
[16]杨剑哲,孙巧榆,王君,等.基于改进增广拉格朗日乘子法的鲁棒性主成分分析[J].哈尔滨工业大学学报,2015,47(11):27-33.
[17]LIN Z C,CHEN M M,MA Y.The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Lowrank Matrices[R].UIUC Technical Report,2009.
[18]CAI J F,CANDS E J,SHEN Z W.A singular value thresholding algorithm for matrix completion[J].SIAMJournal on Optimization,2010,20(4):1956-1982.
[19]FRIEDMAN J,HASTIE T,HFLING H,et al.Pathwise coordinate optimization[J].The Annals of Applied Statistics,2007,1(2):302-332.
[20]付蓉,石美红,陈惠娟.自适应局部二值模式算法及其在织物疵点检测中的应用[J].纺织高校基础科学学报,2010,23(1):99-104.
[21]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009(4):622-635.
[22]曹健,陈红倩,张凯,等.结合区域颜色和纹理的运动阴影检测方法[J].机器人,2011,33(5):628-633.
[23]邓亚丽,毋立芳,李云腾.一种有效的图像阴影自动去除算法[J].信号处理,2011,27(11):1724-1728.
[24]李鹏飞,陈朝武,李晓峰.智能视频算法评估综述[J].计算机辅助设计与图形学学报,2010,22(2):352-360.
[2]OLIVER N M,ROSARIO B,PENTLAND A P.A Bayesian computer vision system for modeling human interactions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):255-272.
[3]蔡念,周杨,刘根,等.鲁棒主成分分析的运动目标检测综述[J].中国图象图形学报,2016,21(10):1265-1275.
[4]XIN B,TIAN Y,WANG Y Z,et al.Background subtraction via generalized fused lasso foreground modeling[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2015:4676-4684.
[5]WRIGHT J,GANESH A,RAO S,et al.Robust Principal Component Analysis:Exact Recovery of Corrupted Lowrank Matrices by Convex Optimization[R].Coordinated Science Laboratory Report,2009.
[6]张泽宏,徐贵力,许扬,等.一种鲁棒的运动目标阴影去除及修复算法[J].计算机与现代化,2018(7):98-102.
[7]XIN B,KAWAHARA Y,WANG Y Z,et al.Efficient generalized fused lasso and its application to the diagnosis of Alzheimer's disease[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.2014:2163-2169.
[8]CANDS E J,LI X,MA Y,et al.Robust principal component analysis?[J].Journal of the ACM(JACM),2011,58(3):11.
[9]OJALA T,PIETIKINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[10]周书仁,殷建平.基于Haar特性的LBP纹理特征[J].软件学报,2013,24(8):1909-1926.
[11]武明虎,宋冉冉,刘敏.结合HSV与纹理特征的视频阴影消除算法[J].中国图象图形学报,2017,22(10):1373-1380.
[12]毛秉毅.基于自适应LBP算法的纹理分析[J].计算机工程与应用,2007,43(2):89-90.
[13]练秋生,刘春亮.基于Gabor滤波器和LBP的分级掌纹识别[J].计算机工程与应用,2007,43(6):212-215.
[14]王玮,黄非非,李见为.使用多尺度LBP特征描述与识别人脸[J].光学精密工程,2008,16(4):696-705.
[15]梁鹏,何俊诗,黎绍发.基于多尺度LBP金字塔特征的分类算法[J].计算机工程,2011,37(8):166-168.
[16]杨剑哲,孙巧榆,王君,等.基于改进增广拉格朗日乘子法的鲁棒性主成分分析[J].哈尔滨工业大学学报,2015,47(11):27-33.
[17]LIN Z C,CHEN M M,MA Y.The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Lowrank Matrices[R].UIUC Technical Report,2009.
[18]CAI J F,CANDS E J,SHEN Z W.A singular value thresholding algorithm for matrix completion[J].SIAMJournal on Optimization,2010,20(4):1956-1982.
[19]FRIEDMAN J,HASTIE T,HFLING H,et al.Pathwise coordinate optimization[J].The Annals of Applied Statistics,2007,1(2):302-332.
[20]付蓉,石美红,陈惠娟.自适应局部二值模式算法及其在织物疵点检测中的应用[J].纺织高校基础科学学报,2010,23(1):99-104.
[21]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009(4):622-635.
[22]曹健,陈红倩,张凯,等.结合区域颜色和纹理的运动阴影检测方法[J].机器人,2011,33(5):628-633.
[23]邓亚丽,毋立芳,李云腾.一种有效的图像阴影自动去除算法[J].信号处理,2011,27(11):1724-1728.
[24]李鹏飞,陈朝武,李晓峰.智能视频算法评估综述[J].计算机辅助设计与图形学学报,2010,22(2):352-360.