一种基于线性序列差异分析降维的人体行为识别方法
|
摘要
在视频数据处理过程中容易出现维数灾难的问题。为此,提出一种线性序列差异分析方法,对视频数据降维来进行人体行为识别。运用ViBe算法对视频帧进行背景减除操作获取行为区域,在该区域内提取稠密轨迹特征从而去除背景数据的干扰。使用Fisher Vector对特征编码后进行线性序列差异分析,采用动态线性规整算法计算序列类别间相似度,得到最小化类内残差和最大化类间残差的线性变换,将特征从高维空间投影至低维空间,降低特征维数。利用降维后的特征训练支持向量机,实现人体行为识别。在KTH数据集和UCF101数据集上进行数据仿真,结果表明,与主成分分析算法、线性判别分析法等相比,该方法可有效提高识别准确率。
Aiming at the problem that dimensionality disaster easily occurs in the processing of dealing with video data,a dimension reduction method called Linear Sequence Discriminant Analysis(LSDA) is proposed for human action recognition.ViBe algorithm is used to subtract the backgrounds of video frames to get action areas,and dense trajectories are extracted in these areas to suppress the noise caused by camera movements.Fisher Vector is used to encode the features and linear sequence discriminant analysis is conducted on them,the sequence class separability is measured by dynamic time warping distance.In order to reduce the data dimension,a linear discriminative projection of the feature vectors in sequences is mapped to a lower-dimensional subspace by maximizing the between-class separability and minimizing the within-class separability.Support Vector Machine(SVM) is learned from the reduced dimension features,and then get the results of human action recognition.Simulation results on KTH datasets and UCF101 datasets show that compared with Principal Component Analysis(PCA),Linear Discriminant Analysis(LDA) and other dimension reduction methods,the proposed method can effectively improve the recognition accuracy.
Aiming at the problem that dimensionality disaster easily occurs in the processing of dealing with video data,a dimension reduction method called Linear Sequence Discriminant Analysis(LSDA) is proposed for human action recognition.ViBe algorithm is used to subtract the backgrounds of video frames to get action areas,and dense trajectories are extracted in these areas to suppress the noise caused by camera movements.Fisher Vector is used to encode the features and linear sequence discriminant analysis is conducted on them,the sequence class separability is measured by dynamic time warping distance.In order to reduce the data dimension,a linear discriminative projection of the feature vectors in sequences is mapped to a lower-dimensional subspace by maximizing the between-class separability and minimizing the within-class separability.Support Vector Machine(SVM) is learned from the reduced dimension features,and then get the results of human action recognition.Simulation results on KTH datasets and UCF101 datasets show that compared with Principal Component Analysis(PCA),Linear Discriminant Analysis(LDA) and other dimension reduction methods,the proposed method can effectively improve the recognition accuracy.
引文
[1] 黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,20(6):1093-1118.
[2] 单言虎,张彰,黄凯奇.人的视觉行为识别研究回顾、现状及展望[J].计算机研究与发展,2016,53(1):93-112.
[3] 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.
[4] TURK M,PENTLAND A.Eigenfaces for recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86.
[5] BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Eigenfaces vs.fisherfaces:recognition using class specific linear projection[C]//Proceedings of the 4th European Conference on Computer Vision.Berlin,Germany:Springer,1996:45-58.
[6] HUANG S,YE J,WANG T,et al.Extracting refined low-rank features of robust pca for human action recognition[J].Arabian Journal for Science and Engineering,2015,40(5):1427-1441.
[7] 王淼,孙季丰,余家林.基于特征层融合和随机投影的行为识别算法[J].科学技术与工程,2017,17(13):210-215.
[8] HE X,NIYOGI P.Locality preserving projections[J].Advances in Neural Information Processing Systems,2002,16(1):186-197.
[9] 王鑫,沃波海,管秋,等.基于流形学习的人体动作识别[J].中国图象图形学报,2014,19(6):914-923.
[10] WRIGHT J,MA Y,MAIRAL J,et al.Sparse representation for computer vision and pattern recognition [J].Proceedings of the IEEE,2010,98(6):1031-1044.
[11] 张瑞杰,魏福山.结合Fisher判别分析和稀疏编码的图像场景分类[J].计算机辅助设计与图形学学报,2015,27(5):808-814.
[12] 肖玉玲.结合HOG/HOF级联特征和多层分类器的人体行为识别[J].计算机工程与设计,2017,38(9):2567-2572.
[13] KEOGH E,RATANAMAHATANA C A.Exact indexing of dynamic time warping[J].Knowledge and Information Systems,2005,7(3):358-386.
[14] SU B,DING X,WANG H,et al.Discriminative dimensionality reduction for multi-dimensional sequences[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(1):77-91.
[15] WANG H,SCHMID C.Action recognition with improved trajectories[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2014:3551-3558.
[16] SCHULDT C,LAPTEV I,CAPUTO B.Recognizing human actions:a local SVM approach[C]//Proceedings of International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:32-36.
[17] SOOMRO K,ZAMIR A R,SHAH M.UCF101:a dataset of 101 human actions classes from videos in the wild[EB/OL].[2017-12-25].https://arxiv.org/pdf/1212.0402.pdf.
[2] 单言虎,张彰,黄凯奇.人的视觉行为识别研究回顾、现状及展望[J].计算机研究与发展,2016,53(1):93-112.
[3] 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.
[4] TURK M,PENTLAND A.Eigenfaces for recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86.
[5] BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Eigenfaces vs.fisherfaces:recognition using class specific linear projection[C]//Proceedings of the 4th European Conference on Computer Vision.Berlin,Germany:Springer,1996:45-58.
[6] HUANG S,YE J,WANG T,et al.Extracting refined low-rank features of robust pca for human action recognition[J].Arabian Journal for Science and Engineering,2015,40(5):1427-1441.
[7] 王淼,孙季丰,余家林.基于特征层融合和随机投影的行为识别算法[J].科学技术与工程,2017,17(13):210-215.
[8] HE X,NIYOGI P.Locality preserving projections[J].Advances in Neural Information Processing Systems,2002,16(1):186-197.
[9] 王鑫,沃波海,管秋,等.基于流形学习的人体动作识别[J].中国图象图形学报,2014,19(6):914-923.
[10] WRIGHT J,MA Y,MAIRAL J,et al.Sparse representation for computer vision and pattern recognition [J].Proceedings of the IEEE,2010,98(6):1031-1044.
[11] 张瑞杰,魏福山.结合Fisher判别分析和稀疏编码的图像场景分类[J].计算机辅助设计与图形学学报,2015,27(5):808-814.
[12] 肖玉玲.结合HOG/HOF级联特征和多层分类器的人体行为识别[J].计算机工程与设计,2017,38(9):2567-2572.
[13] KEOGH E,RATANAMAHATANA C A.Exact indexing of dynamic time warping[J].Knowledge and Information Systems,2005,7(3):358-386.
[14] SU B,DING X,WANG H,et al.Discriminative dimensionality reduction for multi-dimensional sequences[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(1):77-91.
[15] WANG H,SCHMID C.Action recognition with improved trajectories[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2014:3551-3558.
[16] SCHULDT C,LAPTEV I,CAPUTO B.Recognizing human actions:a local SVM approach[C]//Proceedings of International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:32-36.
[17] SOOMRO K,ZAMIR A R,SHAH M.UCF101:a dataset of 101 human actions classes from videos in the wild[EB/OL].[2017-12-25].https://arxiv.org/pdf/1212.0402.pdf.