基于3D结构光传感器的老龄人异常行为检测方法

罗坚; 唐琎; 赵鹏; 毛芳; 汪鹏

光学技术, 2016, 42 (2): 146, 网络出版: 2016-04-01

基于3D结构光传感器的老龄人异常行为检测方法

AAbnormal behavior detection for elderly based on 3D structure light sensor

论文大纲

罗坚 ^1,2,*唐琎 ¹赵鹏 ¹毛芳 ¹汪鹏 ¹

作者单位

¹ 中南大学信息科学与工程学院, 湖南长沙 410000

² 湖南信息职业技术学院信息工程系, 湖南长沙 410000

3D建模异常行为检测多线性子空间分析彩色动作能量图 3D modeling abnormal behavior detection multi-linear subspace learning color motion energy image

摘要

针对多视角下老龄人异常行为检测问题, 利用3D人体数据和多线性子空间分析方法, 从时间、视角和空间动作特征对其进行了研究。首先通过三维结构光传感器获取人体扫描点云数据, 并进行点云精简和人体表面重建。然后提取人体点云数据的表面曲率特征, 并将其映射到二维彩色图像中, 构成彩色动作特征图。通过提取特定时长内所有动作的彩色特征图, 生成基于曲率的彩色动作能量图模型, 并使用2D-PCA对彩色动作能量特征图进行降维。最后运用基于张量分析的多线性子空间分析方法, 对多视角下降维后的数据进行视角无关的特征提取, 并完成异常行为的分类和识别。实验结果表明, 该方法切实可行, 可将其应用于助老机器人和老龄人监护等相关领域。

Abstract

For the problems of multi-view elderly abnormal behavior detection, it is studied in real-time space, multi-view conditions and action features variations by 3D human body data and Multi-linear Subspace Analysis method. First, point cloud data reduction and 3D surface model reconstruction of the human body are achieved using 3D body scanning point cloud data captured by 3D structure light sensor. Then, the surface curvature features of human point cloud data are extracted and projected onto a 2D space to generate curvature based color motion feature images (CCMIs). By averaging the CCMIs of a motion cycle, a 2D curvature based color motion energy image (CCMEI) model is obtained. 2D principal component is used to reduce the dimensionality of CCMEI. Multi-linear Subspace Analysis method based on tensor decomposition is then introduced to extract view-invariant features from multi-view data after dimension reduction and conduct abnormal behavior classification and recognition. Experimental results demonstrate that the proposed method is feasible, and it can be applied to the service robots for the elderly, the aged care and related fields.

参考文献

[1] ADAM A, et al．Robust real-time unusual event detection using multiple fixed-location monitors［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(3):555-560.

[2] XIANG Tao, et al. Incremental and adaptive abnormal behaviour detection［J］. Computer Vision and Image Understanding, 2008,111(1):59-73.

[3] MA Xuyan, et al. Abnormal behavior detection based on global motion orientation［J］. Advanced Materials Research, 2013, 765: 2264-2267.

[4] LI X, et al. A position-based approach of extracting elderly daily behavior habits for service robot［C］∥Proceedings of the 3rd IEEE Conference on Industrial Electronics and Applications. USA:IEEE, 2008: 102-106．

[5] BASHIR F I, et al．Object trajectory based activity classification and recognition using Hidden Markov models［J］．IEEE Transactions on Image Processing, 2007, 16(7): 1912-1919.

[6] 崔永艳,等. 基于多示例学习的异常行为检测方法［J］.模式识别与人工智能, 2011,24(6):862-868. CUI Yongyan, et al. Abnormal event detection based on the multi-instance learning［J］. PR and AI,2011,24(6):862-868.

[7] LI Ce, et al. Visual abnormal behavior detection based on trajectory sparse reconstruction analysis［J］.Neurocomputing, 2013, 119: 94-100.

[8] LEE S C, et al. Hierarchical abnormal event detection by real time and semi-real time multi-tasking video surveillance system ［J］. Machine Vision and Applications, 2014, 25(1): 133-143.

[9] BOBICK A F, et al.The recognition of human move merit using temporal templates［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(3):257-267．

[10] 李海涛,等. 基于位置-动作特征的助老机器人服务对象异常行为检测［J］.计算机工程与科学,2010,32(6):122-128.LI Haitao,et al. The old people's unusual behavior detection by service robots based on the position-action features［J］. Computer Engineering & Science,2010,32(6):122-128.

[11] 吴艳平,等. 基于运动图像序列的异常行为检测［J］.计算机应用研究,2010,27(7):2741-2744.WU Yanping,et al. Abnomaly detection based on motion image sequence［J］. Application Research of Computers ,2010,27(7):2741-2744.

[12] ZHANG Dongping, et al. Crowd abnormal behavior detection based on machine learning［J］. Information Technology Journal. 2013, 12(6):1199-1205.

[13] SMISEK J, et al.3D with Kinect［C］// Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops. Barcelona, Spain:IEEE,2011:1154-1160.

[14] 朱煜,等. 一种改进的点云数据精简方法［J］. 计算机应用,2012,32(2):521-523.ZHU Yu,et al. Improved algorithm for point cloud data simplification［J］. Journal of Computer Application,2012,32(2):521-523.

[15] HAN J, et al. Individual recognition using gait energy image［J］. IEEE Transactions on Pattern Analysis Machine Intelligence, 2006,28(2):316-322.

[16] INAN T, et al. 3D face recognition with local shape descriptors［J］. IEEE Transactions on Information Forensics and Security,2012, 7(2):577-587.

[17] MASHHOORI A, et al. Block-wise two-directional 2DPCA with ensemble learning for face recognition［J］. Neurocomputing, 2013,108:111-17.

[18] VASILESCU M A O, et al. Multilinear (tensor) image synthesis ,analysis, and recognition［J］. IEEE Signal Processing Magazine,2007,24:118-123.

罗坚, 唐琎, 赵鹏, 毛芳, 汪鹏. 基于3D结构光传感器的老龄人异常行为检测方法[J]. 光学技术, 2016, 42(2): 146. LUO Jian, TANG Jin, ZHAO Peng, MAO Fang, WANG Peng. AAbnormal behavior detection for elderly based on 3D structure light sensor[J]. Optical Technique, 2016, 42(2): 146.

基于3D结构光传感器的老龄人异常行为检测方法

关于本站 Cookie 的使用提示

全站搜索

基于3D结构光传感器的老龄人异常行为检测方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索