结合时空拓扑特征和稀疏表达的人体行为识别算法

doi:10.3724/SP.J.1087.2013.01701

计算机应用 ›› 2013, Vol. 33 ›› Issue (06): 1701-1710.DOI: 10.3724/SP.J.1087.2013.01701

结合时空拓扑特征和稀疏表达的人体行为识别算法

黄文丽¹,范勇²

1. 蒲城清洁能源化工有限责任公司, 陕西渭南 715506
2. 西南科技大学计算机科学与技术学院，四川绵阳 621010

收稿日期:2012-12-14 修回日期:2013-02-22 出版日期:2013-06-01 发布日期:2013-06-05
通讯作者: 黄文丽
作者简介:黄文丽（1986-），女，四川眉山人，硕士，主要研究方向：计算机视觉、行为识别；范勇（1972-），男，重庆人,教授，博士，主要研究方向：机器视觉、图像处理。
基金资助:
国家自然科学基金资助项目（10676029）;国家自然科学基金资助项目（10776028）

Human behavior recognition algorithm with space-time topological feature and sparse expression

HUANG Wenli¹,FAN Yong²

1. Pucheng Clean Energy Chemical Company Limited, Weinan Shaanxi 715506, China
2. College of Computer Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China

Received:2012-12-14 Revised:2013-02-22 Online:2013-06-05 Published:2013-06-01
Contact: HUANG Wenli

摘要/Abstract

摘要： 基于视觉的行为分析是图像处理、模式识别等领域重要研究内容之一，在公共安全和军事上有广泛前景。在固定单摄像机下，针对单特征描述力欠缺、运动遮挡、空洞和阴影等问题，提出一种结合时空拓扑特征和稀疏表达的行为识别算法。该算法利用随机投影融合拓扑结构、几何不变特征和时空Poisson信息构造强内聚高区分低维的时空拓扑特征，结合模拟人脑解决问题的加噪稀疏机制，识别近景人体行为。实验结果表明时空拓扑特征比单特征的识别率高12.79%，在噪声情况下识别率仅降低6.15%，多行为识别率达到87.78%；该算法具有较强的时空特征描述力、噪声鲁棒性和识别高效性。

关键词: 时空拓扑特征, 稀疏表达, 行为识别

Abstract: Behavior analysis based on vision is one of the important research topics in image processing, pattern recognition,etc, and it has wide application prospects on public security and military field. For the problems of a fixed camera such as lack of the single feature description, motion occlusions, holes and shadows, the paper proposed a behavior recognition algorithm which combines space-time topological feature with sparse expression. It used random projection to get a space-time topological feature of strong cohesion, high distinction and low dimension, which fused topology structure, geometric invariant and space-time Poisson information. The noise-adding sparse mechanism resolving problems by simulating human was combined to identify behaviors of human body in a close-range monitor scene. The experimental results show that the recognition rate of space-time topological feature is 12.79% higher than that of single one. The recognition rate of this proposed algorithm is only 6.15% down in a noisy scene, and that for multi-behavior reaches 87.78%. This algorithm has the properties of strong description for space-time feature, higher robustness against noise and high efficiency for behavior recognition.

Key words: space-time topological feature, sparse expression, behavior recognition

中图分类号:

TP391.4

黄文丽范勇. 结合时空拓扑特征和稀疏表达的人体行为识别算法[J]. 计算机应用, 2013, 33(06): 1701-1710.

HUANG Wenli FAN Yong. Human behavior recognition algorithm with space-time topological feature and sparse expression[J]. Journal of Computer Applications, 2013, 33(06): 1701-1710.

参考文献

[1] JAIMES A, GATICA-PEREZ D, SEBE N, et al. Human-centered computing: toward a human revolution［J］. Computer,2007, 40(5): 30-34.
[2] 王亮，胡卫明，谭铁牛. 人运动的视觉分析综述［J］. 计算机学报,2002, 25(3): 225-237.

[3] 徐光祐，曹媛媛. 动作识别与行为理解综述［J］. 中国图象图形学报, 2009, 14(2): 189-195.

[4] 凌志刚，赵春晖，梁彦，等. 基于视觉的人行为理解综述［J］. 计算机应用研究, 2008, 25(9): 2570-2578.

[5] GORELICK L, BLANK M, SHECHTMAN E, et al. Actions as space-time shapes［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2247-2253.

[6] GAVRILA D M, DAVIS L S. 3-D model-based tracking of humans in action: a multi-view approach［C］// 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 1996:73-80.

[7] DAVIS J, BOBICK A. The representation and recognition of action using temporal templates［C］// 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 1997:928-934.

[8] BREGLER C. Learning and recognizing human dynamics in video sequences［C］// 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 1997:568-574.

[9] VINJE W E, GALLANT J L. Sparse coding and decorrelation in primary visual cortex during natural vision［J］. Science, 2000, 287(5456): 1273-1276.

[10]WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.

[11] 张春梅，尹忠科，肖明霞. 基于冗余字典的信号超完备表示与稀疏分解［J］. 科学通报, 2006, 51(6): 628-633.

[12] AGGARWAL J K, CAI Q. Human motion analysis: a review［J］. Computer Vision and Image Understanding, 1999, 73(3): 428-440.

[13] DUDA R O, HART P E, STORK D G. Pattern classification and scene analysis［M］. 2nd ed. New York:Wiley-Interscience, 1995.

[14] JOHNSON W B, LINDENSTRAUSS J, SCHECHTMAN G. Extensions of Lipschitz maps into Banach spaces［J］. Israel Journal of Mathematics, 1986, 54(2): 129-138.

[15] WANG Y, HUANG K, TAN T. Human activity recognition based on R transform［C］// IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2007:1-8.

[16] BORGEFORS G. Distance transformations in digital images［J］. Computer Vision, Graphics, and Image Processing,1986, 34(3): 344-371.

[17] 许秋燕. 二维泊松方程和扩散方程的一类显式并行算法［D］. 济南: 山东大学, 2010.

[18] WEIZMANN[EB/OL].[2012-08-20].http://www.wisdom.weizmann.ac.il/~vision/SpaceTime Actions.html.

结合时空拓扑特征和稀疏表达的人体行为识别算法

Human behavior recognition algorithm with space-time topological feature and sparse expression

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
[2]	刘世泽, 秦艳君, 王晨星, 高存远, 罗海勇, 赵方, 王宝会. 基于多尺度特征提取的交通模式识别算法[J]. 计算机应用, 2021, 41(6): 1573-1580.
[3]	田志强, 邓春华, 张俊雯. 基于骨骼时序散度特征的人体行为识别算法[J]. 计算机应用, 2021, 41(5): 1450-1457.
[4]	蒋丽, 黄仕建, 严文娟. 基于低秩行为信息和多尺度卷积神经网络的人体行为识别方法[J]. 计算机应用, 2021, 41(3): 721-726.
[5]	戎炜, 蒋哲远, 谢昭, 吴克伟. 基于聚类关联网络的群组行为识别[J]. 计算机应用, 2020, 40(9): 2507-2513.
[6]	周云, 陈淑荣. 基于双流非局部残差网络的行为识别方法[J]. 计算机应用, 2020, 40(8): 2236-2240.
[7]	杨文璐, 于孟孟, 谢宏. 基于关键姿势的双人交互行为识别[J]. 计算机应用, 2020, 40(8): 2231-2235.
[8]	陈皓, 肖利雪, 李广, 潘跃凯, 夏雨. 基于人体关节点数据的攻击性行为识别[J]. 计算机应用, 2019, 39(8): 2235-2241.
[9]	王萍, 庞文浩. 基于视频分段的空时双通道卷积神经网络的行为识别[J]. 计算机应用, 2019, 39(7): 2081-2086.
[10]	郭明祥, 宋全军, 徐湛楠, 董俊, 谢成军. 基于三维残差稠密网络的人体行为识别算法[J]. 计算机应用, 2019, 39(12): 3482-3489.
[11]	王立林, 刘俊. 基于多尺度卷积的船舶行为识别方法[J]. 计算机应用, 2019, 39(12): 3691-3696.
[12]	姬晓飞, 秦琳琳, 王扬扬. 基于RGB和关节点数据融合模型的双人交互行为识别[J]. 计算机应用, 2019, 39(11): 3349-3354.
[13]	吴亮, 何毅, 梅雪, 刘欢. 基于时空兴趣点和概率潜动态条件随机场模型的在线行为识别方法[J]. 计算机应用, 2018, 38(6): 1760-1764.
[14]	黄凤, 王晓明. 增强的单幅图像自学习超分辨方法[J]. 计算机应用, 2017, 37(9): 2636-2642.
[15]	王智文, 蒋联源, 王宇航, 王日凤, 张灿龙, 黄镇谨, 王鹏涛. 基于尺度自适应局部时空特征的足球比赛视频中的多运动员行为表示[J]. 计算机应用, 2016, 36(8): 2134-2138.