一种基于局部拓扑与l1/2范数的解析字典分类的人群事件检测

doi:10.11959/j.issn.1000-0801.2018254

电信科学 ›› 2018, Vol. 34 ›› Issue (10): 65-71.doi: 10.11959/j.issn.1000-0801.2018254

一种基于局部拓扑与l_1/2范数的解析字典分类的人群事件检测

禹青,陈恳,李萌,李斐

宁波大学信息科学与工程学院，浙江宁波 315211

修回日期:2018-09-05 出版日期:2018-10-01 发布日期:2018-11-08
作者简介:禹青（1994-），女，宁波大学信息科学与工程学院硕士生，主要研究方向为监控视频中的人群异常分析与检测、多媒体通信技术。|陈恳（1962-），男，宁波大学信息科学与工程学院副教授、硕士生导师，主要研究方向为图像及视频信息处理、多媒体通信、智能控制。|李萌（1992-），女，宁波大学信息科学与工程学院硕士生，主要研究方向为监控视频中的人群异常分析与检测、多媒体通信技术。|李斐（1992-），女，宁波大学信息科学与工程学院硕士生，主要研究方向为视频图像处理、监控视频中的人群异常分析与检测、多媒体通信技术。
基金资助:
国家自然科学基金资助项目(60972063);宁波市自然科学基金资助项目(2014A610065);宁波大学科研基金（理）/学科资助项目(XKXL1308)

Abnormal event detection based on local topology and l_1/2norm regularize

Qing YU,Ken CHEN,Meng LI,Fei LI

Institute of Communication Technology,Ningbo University,Ningbo 315211,China

Revised:2018-09-05 Online:2018-10-01 Published:2018-11-08
Supported by:
The National Natural Science Foundation of China(60972063);The Natural Science Foundation of Ningbo of China(2014A610065);Scientific Research Foundation of Ningbo University(XKXL1308)

摘要/Abstract

摘要：

所提方案在传统解析字典算法基础上，加入局部拓扑项用以描述数据之间的结构信息，同时用l_1/2范数代替 l₁范数作为稀疏约束，从而提高表示系数的稀疏度。在特征提取上，融合了包含丰富运动信息的相互作用力直方图与包含纹理信息的梯度方向直方图，然后用改进的字典对特征数据进行训练，最后通过计算测试样本在该字典下的重构误差来判断测试样本是否为异常样本。在标准行为库UMN（University of Minnesota）数据库上进行的实验证实了算法具有较高的性能。与传统的算法相比，提出的改进的解析字典分类算法在针对人群异常事件中取得了更为有效的检测。

关键词: 解析字典, 局部拓扑项, 相互作用力直方图, 梯度方向直方图

Abstract:

A new dictionary learning method was proposed by introducing a local topology term to describe structural information of video events and using the l_1/2norm as the sparsity constraint to the representation coefficients based on the traditional analysis dictionary learning method.In feature extraction,a histogram of interaction force(HOIF) containing rich motion information and a histogram of oriented gradient(HOG) containing texture information were merged.Then,the improved dictionary was used to train the feature data.Finally,the reconstruction error of the testing sample under the dictionary was used to determine whether the testing sample was an abnormal sample.Experiments on UMN show the high performance of the algorithm.Compared with the state-of-the-art algorithms,the analysis dictionary classification algorithm based on local topology and l_1/2norm has made more effective detection on the abnormal events in the crowd.

Key words: analysis dictionary, local topology term, histogram of interaction force, histogram of oriented gradient

中图分类号:

TP391

禹青,陈恳,李萌,李斐. 一种基于局部拓扑与l_1/2范数的解析字典分类的人群事件检测[J]. 电信科学, 2018, 34(10): 65-71.

Qing YU,Ken CHEN,Meng LI,Fei LI. Abnormal event detection based on local topology and l_1/2norm regularize[J]. Telecommunications Science, 2018, 34(10): 65-71.

图/表 7

图1

图2

图3

图4

图5

图6

表1

参考文献 19

[1]	ZHANG Y , LU H C , ZHANG L H ,et al. Combining motion and appearance cues for anomaly detection[J]. Pattern Recognition, 2016,51(C): 443-452.
[2]	吴新宇, 郭会文, 李楠楠 ,等. 基于视频的人群异常事件检测综述[J]. 电子测量与仪器学报, 2014,28(6): 575-584.
	WU X Y , GUO H W , LI N N ,et al. Survey on the video-based abnormal event dete-ction in crowd scenes[J]. Journal of Electronic Measurement and Instrumentation, 2014,28(6): 575-584.
[3]	ZHAO B , LI F F , XING E P . Online detection of unusual eventsin videos via dynamic-sparse coding[J]. Computer Vision and Pattern Recognition, 2011,32(4): 3313-3320.
[4]	MEHRAN R , OYAMA A , SHAH M . Abnormal crowd behavior detection using social force model[C]// IEEE Conference on Computer Vision and Pattern Recognition,June 20-25,2009,Miami,FL,USA. Piscataway:IEEE Press, 2009: 935-942.
[5]	WU S , MOORE B E , SHAH M . Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes[C]// IEEE Conference on Computer Vision and Pattern Recognition,June 13-18,2010,San Francisco,CA,USA. Piscataway:IEEE Press, 2010: 2054-2060.
[6]	CONG Y , YUAN J , LIU J . Abnormal event detection in crowded scenes using sparse representation[J]. Pattern Recognition, 2013(46): 1851-1864.
[7]	ZHU X , LIU J , WANG J ,et al. Sparse representation for robust abnormality detection in crowded scenes[J]. Pattern Recognition, 2014,47(5): 1791-1799.
[8]	ZHANG Z , MEI X , XIAO B . Abnormal event detection via compact low-rank sparse learning[J]. Pattern Recognition, 2016,31(2): 29-36.
[9]	GUO J , GUO Y Q , KONG X W ,et al. Discriminative analysis dictionary learning[C]// Thirtieth AAAI Conference on Artificial Intelligence(AAAI-16),February 12-17,2016,Phoenix,Arizona,USA. Palo Alto:AAAI Press, 2016: 1617-1623.
[10]	YUAN Y , FENG Y , LU X . Structured dictionary learning for abnormal event detection in crowded scenes[J]. Pattern Recognition, 2018(73): 99-110.
[11]	练秋生, 石保顺, 陈书贞 . 字典学习模型、算法及其应用研究进展[J]. 自动化学报, 2015,41(2): 240-260.
	LIAN Q S , SHI B S , CHEN S Z . Research advances on dictionary learning models,algorithms and applications[J]. Acta Automatica Sinica, 2015,41(2): 240-260.
[12]	NAM S , DAVIES M E , ELAD M ,et al. The cosparse analysis model and algorithm-MS[J]. Applied ＆ Computational Harmonic Analysis, 2013,34(1): 30-56.
[13]	LUO D , DING C , NIE F ,et al. Cauchy graph embedding[C]// International Conference on International Conference on Machine Learning,June 28-July 2,2011,Bellevue,Washington,USA. New York:ACM Press, 2011: 553-560.
[14]	LI Z , HAYASHI T , DING S ,et al. Constrained analysis dictionary learning with the ?1/2-norm regularizer[C]// International Conference on Signal Processing,January 9-11,2017,Da Nang,Vietnam. Piscataway:IEEE Press, 2017: 890-894.
[15]	HE R , ZHENG W S , TAN T ,et al. Half-quadratic-based iterative minimization for robust sparse representation[J]. IEEE Transactions on Pattern Analysis＆Machine Intelligence, 2014,36(2): 261-275.
[16]	李萌, 陈恳, 郭春梅 ,等. 融合显著性信息和社会力模型的人群异常检测[J]. 光电工程, 2016,43(12): 193-199.
	LI M , CHEN K , GUO C M ,et al. Abnormal crowed event detection by fusing saliency information and social force mode[J]. Opto-Electronic Engineering, 2016,43(12): 193-199.
[17]	UIJLINGS J R R , DUTA I C , ROSTAMZADEH N ,et al. Realtime video classification using dense HOF/HOG[C]// International Conference on Multimedia Retrieval,Apr 1-4,2014,Glasgow,UK. New York:ACM Press, 2014: 145-152.
[18]	YI Y G , LI X H , ZHAO R . A constrained sparse representation approach for video anomaly detection[C]// Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC),October 3-5,2017,Xi’an,China.[S.l.:s.n]. 2017: 45-49.
[19]	LI A , MIAO Z J , CEN Y G ,et al. Abnormal event detection based on sparse reconstruction in crowded scenes[C]// 2016 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP),March 20-25,2016,Shanghai,China. Piscataway:IEEE Press, 2016: 1786-1790.

方法	草坪场景	室内场景	广场场景
参考文献[7]方法	0.977 6	0.963 1	0.965 5
参考文献[6]方法	0.989 1	0.964 2	0.966 0
参考文献[18]方法	0.997 4	0.967 1	0.988 7
参考文献[19]方法	0.997 6	0.957 0	0.986 9
本文方法	0.998 8	0.995 8	0.996 4

一种基于局部拓扑与l_1/2范数的解析字典分类的人群事件检测

Abnormal event detection based on local topology and l_1/2norm regularize

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 19

相关文章 15

Metrics

推荐阅读 0

[1]	金宏辉, 简志华, 杨曼, 吴超. 采用圆周局部三值模式纹理特征的合成语音检测方法[J]. 电信科学, 2023, 39(6): 85-95.
[2]	马辉, 王瑞琴, 杨帅. 一种渐进式增长条件生成对抗网络模型[J]. 电信科学, 2023, 39(6): 105-113.
[3]	卢敏, 胡娟, 张先超, 丁伟健, 乐光学. 基于用户多特征融合的个性化推荐模型[J]. 电信科学, 2023, 39(5): 101-115.
[4]	张永, 刘纪奎, 柯文龙. 基于并行可分离卷积和标签平滑正则化的脑电情感识别[J]. 电信科学, 2023, 39(5): 116-128.
[5]	邓琨, 蒋庆丰, 刘星妍. 融合节点分析与边分析的复杂网络社区识别算法[J]. 电信科学, 2023, 39(4): 87-100.
[6]	冶莉娟, 王亦婷, 朱励程. 基于细胞自动机模型电力网络攻击预测技术[J]. 电信科学, 2023, 39(4): 173-179.
[7]	韩一士, 徐雨欣, 卢甜甜. 一种基于耦合网络的RD-IHSAT网络谣言传播模型[J]. 电信科学, 2023, 39(2): 118-131.
[8]	徐嘉, 简志华, 金宏辉, 吴超, 游林, 吴迎笑. 基于中心对称局部二值模式的合成伪装语音检测方法[J]. 电信科学, 2023, 39(1): 72-78.
[9]	任华健, 郝秀兰, 徐稳静. 融合递增词汇选择的深度学习中文输入法[J]. 电信科学, 2022, 38(12): 56-64.
[10]	周薇娜, 刘露. 复杂场景下多尺度船舶实时检测方法[J]. 电信科学, 2022, 38(10): 67-78.
[11]	金楠, 王瑞琴, 陆悦聪. 基于艾宾浩斯遗忘曲线和注意力机制的推荐算法[J]. 电信科学, 2022, 38(10): 89-97.
[12]	杨帅, 王瑞琴, 马辉. 基于多通道的边学习图卷积网络[J]. 电信科学, 2022, 38(9): 95-104.
[13]	赵东明. 电信运营商知识图谱技术体系研究及应用实践[J]. 电信科学, 2022, 38(8): 151-162.
[14]	于佳祺, 简志华, 徐嘉, 游林, 汪云路, 吴超. 基于联合特征与随机森林的伪装语音检测[J]. 电信科学, 2022, 38(6): 91-99.
[15]	申情, 郭文宾, 楼俊钢, 余强国. 考虑多层次潜在特征的个性化推荐模型[J]. 电信科学, 2022, 38(2): 71-83.

一种基于局部拓扑与l1/2范数的解析字典分类的人群事件检测

Abnormal event detection based on local topology and l1/2norm regularize

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 19

相关文章 15

Metrics

推荐阅读 0

一种基于局部拓扑与l_1/2范数的解析字典分类的人群事件检测

Abnormal event detection based on local topology and l_1/2norm regularize