联合足迹识别与监控视频分析的智能刑侦系统

doi:10.13700/j.bh.1001-5965.2020.0062

北京航空航天大学学报 ›› 2020, Vol. 46 ›› Issue (9): 1730-1738.doi: 10.13700/j.bh.1001-5965.2020.0062

联合足迹识别与监控视频分析的智能刑侦系统

陶一宁¹, 苏峰¹, 袁培江¹, 王田苗¹, 钟涛², 郝静如²

1. 北京航空航天大学机械工程及自动化学院, 北京 100083;
2. 北京市公安局刑事侦查总队, 北京 100006

收稿日期:2020-03-02 发布日期:2020-09-22
通讯作者: 袁培江 E-mail:itr@buaa.edu.cn
作者简介:陶一宁男,硕士研究生。主要研究方向:计算机视觉、机器学习;袁培江男,博士,副教授,硕士生导师。主要研究方向:计算机视觉、机器人。
基金资助:
国家自然科学基金（61603015）

Intelligent criminal investigation system based on both footprint recognition and surveillance video analysis

TAO Yining¹, SU Feng¹, YUAN Peijiang¹, WANG Tianmiao¹, ZHONG Tao², HAO Jingru²

1. School of Mechanical Engineering and Automation, Beihang University, Beijing 100083, China;
2. Criminal Investigation Corps, Beijing Public Security Bureau, Beijing 100191, China

Received:2020-03-02 Published:2020-09-22
Supported by:
National Natural Science Foundation of China (61603015)

摘要/Abstract

摘要： 刑侦破案是打击违法犯罪和确保国家长治久安的基本要求。刑侦破案的一大关键是如何有效地利用采集到的信息。为了更好地配合刑侦工作，提出了联合足迹识别与监控视频分析的智能刑侦系统。该系统基于深度学习方法，首先根据足迹信息，包括鞋印长度、宽度、受力分布情况、步长、步幅等，利用卷积神经网络技术实现嫌疑人个人特征的预测；其次联合周边监控视频大数据进行智能分析比较，利用大数据技术快速处理信息，分析视频中行人的个人特点；最后运用虚拟现实仿真技术构建足部压力和鞋底受力分析有限元模型，利用模型获得各种复杂场景下的仿真足迹。三者相互印证，有机结合，快速筛选刑侦对象。实验结果表明，该系统可以高效准确地根据足迹特征实现身高预测，并且与视频监控大数据相结合，可以迅速缩小排查范围并锁定凶手。

关键词: 深度学习, 大数据, 刑侦破案, 监控视频分析, 足迹识别

Abstract: Criminal investigation is the basic requirement for cracking down on crimes and ensuring the long-term security of the country. One of the key points in criminal investigation is how to effectively use the collected information. In order to support criminal investigation better, an intelligent criminal investigation system based on both footprint recognition and surveillance video analysis is proposed. The system is powered by deep learning methods. First, using convolutional neural network technique, it predicts the characteristics of suspected individuals based on footprint information, including the footprint length, width, distribution of force, step length, stride, etc. Second, it uses the surrounding surveillance video big data for intelligent comparison to quickly screen criminal investigation objects and analyze the personal characteristics of pedestrians. Finally, the virtual reality simulation technology is used to construct a finite element model of foot pressure and sole stress analysis, and the model is used to obtain simulation footprints in various complex scenarios. The three confirmed each other and organically combined to quickly select criminal investigation targets. Experimental results show that the system can efficiently and accurately achieve people height prediction based on footprint characteristics. Combined with video surveillance big data, the proposed system can quickly narrow down the investigation range and find out the killer.

Key words: deep learning, big data, criminal investigations, surveillance video analysis, footprint recognition

中图分类号:

TP391.4

陶一宁, 苏峰, 袁培江, 王田苗, 钟涛, 郝静如. 联合足迹识别与监控视频分析的智能刑侦系统[J]. 北京航空航天大学学报, 2020, 46(9): 1730-1738.

TAO Yining, SU Feng, YUAN Peijiang, WANG Tianmiao, ZHONG Tao, HAO Jingru. Intelligent criminal investigation system based on both footprint recognition and surveillance video analysis[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(9): 1730-1738.

参考文献

[1] 孙传森.浅议犯罪现场足迹检验[J].经济研究导刊,2009(8):253-254.SUN C S.On the footprint inspection of crime scene[J].Economic Research Guide,2009(8):253-254(in Chinese).
[2] ISHAK N I,HEMY N,FRANKLIN D.Estimation of stature from hand and handprint dimensions in a Western Australian population[J].Forensic Science International,2012,216(1-3):199.e1-199.e7.
[3] ISHAK N I,HEMY N,FRANKLIN D.Estimation of sex from hand and handprint dimensions in a Western Australian population[J].Forensic Science International,2012,221(1-3):154.e1-154.e6.
[4] HEMY N,FLAVEL A,AISHAK N I,et al.Sex estimation using anthropometry of feet and footprints in a Western Australian population[J].Forensic Science International,2013,231(1-3):402.e1-402.e6.
[5] REEL S,ROUSE S,VERNON W,et al.Reliability of a two-dimensional footprint measurement approach[J].Science & Justice,2010,50(3):113-118.
[6] KRISHAN K.Individualizing characteristics of footprints in Gujjars of North India-Forensic aspects[J].Forensic Science International,2006,169(2):137-144.
[7] MOORTHY T N,MOSTAPA A,BOOMINATHAN R,et al.Stature estimation from footprint measurements in Indian Tamils by regression analysis[J].Egyptian Journal of Forensic Sciences,2014,4(1):7-16.
[8] 高毅.基于Footscan足底压力步态分析系统的足迹动力形态特征研究[J].中国人民公安大学学报(自然科学版),2011,17(2):9-13.GAO Y.Research on the dynamic morphology of footprints on the bases of gait analysis system of plantar pressure[J].Journal of Chinese People's Public Security University(Science and Technology),2011,17(2):9-13(in Chinese).
[9] 振强.马玉林学术研究会在内蒙古赤峰成立[J].刑事技术,1993(1):30.ZHEN Q.Ma Yulin academic research association was established in Chifeng,Inner Mongolia[J].Criminal Technology,1993(1):30(in Chinese).
[10] 吴大有.足迹检验的历史与现状[J].中国刑事警察,1995(2):48-49.WU D Y.History and current status of footprint inspection[J].Chinese Criminal Police,1995(2):48-49(in Chinese).
[11] 刘树权,叶剑平,温媛,等.足迹个体识别技术自动化——足迹计算机自动鉴定系统[J].刑事技术,1998(1):44-46.LIU S Q,YE J P,WEN Y,et al.Automation of individual footprint identification technology-Automatic footprint computer identification system[J].Criminal Technology,1998(1):44-46(in Chinese).
[12] 王清举,平西建,王永栋.立体足迹计算机自动识别系统的应用[J].刑事技术,2003(5):41-43.WANG Q J,PING X J,WANG Y D.Application of automatic stereo footprint computer recognition system[J].Criminal Technology,2003(5):41-43(in Chinese).
[13] 闫旭琴.自动鞋印分析与比对系统中的关键技术的研究与实现[D].青岛:山东科技大学,2007.YAN X Q.Research and implementation of key technologies in automatic shoe print analysis and comparison system[D].Qingdao:Shandong University of Science and Technology,2007(in Chinese).
[14] 王永栋,顾士清,党素琴,等.基于重压面形状分析的足迹识别系统的研究[C]//中国图象图形学学会.第十四届全国图象图形学学术会议论文集.北京:中国图象图形学学会,2008:794-797.WANG Y D,GU S Q,DANG S Q,et al.Research on footprint recognition system based on shape analysis of pressure surfaces[C]//Chinese Society of Image Graphics.Proceedings of the 14th National Conference on Image Graphics.Beijing:Chinese Society of Image Graphics,2008:794-797(in Chinese).
[15] 蒋晓玲.基于图像处理技术的足迹检验系统的设计与实现[D].南京:南京理工大学,2011.JIANG X L.Design and implementation of footprint inspection system based on image processing technology[D].Nanjing:Nanjing University of Science and Technology,2011(in Chinese).
[16] 董菲菲.基于三维鞋印的鞋底花纹分类及模块设计[D].南昌:南昌大学,2010.DONG F F.Sole pattern classification and module design based on three-dimensional shoe prints[D].Nanchang:Nanchang University,2010(in Chinese).
[17] 张彩霞,付焕利.未标定视频下的动态人体身高测量[J].计算机工程与应用,2017,53(21):162-166.ZHANG C X,FU H L.Dynamic human height measurement under uncalibrated video[J].Computer Engineering and Applications,2017,53(21):162-166(in Chinese).

联合足迹识别与监控视频分析的智能刑侦系统

Intelligent criminal investigation system based on both footprint recognition and surveillance video analysis

RichHTML

PDF (PC)

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

本文评价

[1]	陈猛夫. 基于迁移学习的暴恐图像自动识别[J]. 北京航空航天大学学报, 2020, 46(9): 1677-1681.
[2]	杜雨佳, 李海生, 姚春莲, 蔡强. 基于三元组网络的单图三维模型检索[J]. 北京航空航天大学学报, 2020, 46(9): 1691-1700.
[3]	张洁茹, 苏峰, 袁培江, 王田苗, 陶一宁, 丁东. 双光谱智能体温检测与健康大数据管理系统[J]. 北京航空航天大学学报, 2020, 46(9): 1739-1746.
[4]	张子昊, 周千里, 王蓉. 基于空间注意力机制的行人再识别方法[J]. 北京航空航天大学学报, 2020, 46(9): 1747-1755.
[5]	张子昊, 王蓉. 基于MobileFaceNet网络改进的人脸识别方法[J]. 北京航空航天大学学报, 2020, 46(9): 1756-1762.
[6]	邱博, 刘翔, 石蕴玉, 尚岩峰. 一种轻量化的多目标实时检测模型[J]. 北京航空航天大学学报, 2020, 46(9): 1778-1785.
[7]	陆展鸿, 单鲁斌, 苏立循, 焦雨欣, 王家骅, 王海霞. 基于U-Net的掌纹图像增强与ROI提取[J]. 北京航空航天大学学报, 2020, 46(9): 1807-1816.
[8]	李欣致, 董胜波, 崔向阳, 刘志哲, 郭广浩. 应用于智能芯片的可视化反馈系统研究[J]. 北京航空航天大学学报, 2020, 46(8): 1494-1502.
[9]	张阳, 牛之贤, 牛保宁, 常艳. 基于高分辨率网络的单声道歌声分离[J]. 北京航空航天大学学报, 2020, 46(8): 1555-1563.
[10]	李承昊, 茹乐, 何林远, 迟文升. 一种可变锚框候选区域网络的目标检测方法[J]. 北京航空航天大学学报, 2020, 46(8): 1610-1617.
[11]	吕娜, 周家欣, 陈卓, 刘鹏飞, 高维廷. 一种鲁棒性增强的机载网络流量分类方法[J]. 北京航空航天大学学报, 2020, 46(7): 1237-1246.
[12]	郑磊, 胡维多, 刘畅. 基于深度学习的大型陨石坑识别方法研究[J]. 北京航空航天大学学报, 2020, 46(5): 994-1004.
[13]	边亮, 罗霄阳, 李硕. 基于深度学习的图像拼接篡改检测[J]. 北京航空航天大学学报, 2020, 46(5): 1039-1044.
[14]	杨思晨, 王华锋, 王月海, 李锦涛, 王赟豪. 深度学习机制与小波融合的超分辨率重建算法[J]. 北京航空航天大学学报, 2020, 46(1): 189-197.
[15]	张克明, 蔡远文, 任元. 基于生成对抗网络的航天异常事件检测方法[J]. 北京航空航天大学学报, 2019, 45(7): 1329-1336.