Please wait a minute...
文章检索
复杂系统与复杂性科学  2025, Vol. 22 Issue (2): 73-81    DOI: 10.13306/j.1672-3813.2025.02.009
  特邀专栏 本期目录 | 过刊浏览 | 高级检索 |
多信息融合的步态侦查技术研究
冯磊1,2, 赵兴春2, 周扬钧3
1.中国人民公安大学侦查学院,北京 100038;
2.公安部鉴定中心,北京 100038;
3.长沙市公安局刑事侦查支队,长沙 410001
Research on Gait Investigation Technology Based on Multi-information Fusion
FENG Lei1,2, ZHAO Xingchun2, ZHOU Yangjun3
1. School of Criminal Investigation, People′s Public Security University of China, Beijing 100038, China;
2. Institute of Forensic Science, Ministry of Public Security, Beijing 100038, China;
3. Changsha Public Security Bureau Criminal Investigation Detachment, Changsha 410001, China
全文: PDF(3732 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 当前复杂刑事案件呈现出多要素耦合、动态演化的系统性特征,其侦查过程面临非线性信息整合的挑战。犯罪嫌疑人通过换装换鞋、面部遮挡、姿态伪装等反侦查手段,并结合复杂环境干扰,导致视频结构化、人脸识别等单一视频技术手段的实战效能显著降低。为解决这一问题,聚焦嫌疑人识别与追踪的实际需求,突破单一模态的识别瓶颈,融合视频结构化、人脸识别、步态识别等多源信息,提出以步态识别为核心的多信息融合视频侦查体系,实现嫌疑人行为模式与身份特征的双重刻画,为提升身份识别能力与复杂案件侦破效率提供了新的技术路径。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
冯磊
赵兴春
周扬钧
关键词 复杂案件多源信息步态识别融合应用    
Abstract:Complex criminal cases today present systematic characteristics of multi-factor coupling and dynamic evolution, and their investigation process faces the challenge of nonlinear information integration. Criminal suspects use anti-detection methods such as changing clothes and shoes, facial obstruction, and posture camouflage, combined with complex environmental interference, which significantly reduces the practical effectiveness of single technical means such as face recognition and video structuring. In order to resolve this problem, this article focuses on the actual needs of suspect identification and tracking, breaks through the recognition bottleneck of a single modality, systematically integrates multi-information such as video structuring, face recognition, and gait recognition, and proposes a multi-information fusion video investigation system with gait recognition as the core, which realizes the dual characterization of suspect behavior patterns and identity characteristics, and provides a new technical path for improving identity recognition capabilities and the efficiency of solving complex cases.
Key wordscomplex cases    multi-source information    gait recognition    fusion application
收稿日期: 2025-04-06      出版日期: 2025-06-03
ZTFLH:  D918.2  
基金资助:公安部科技强警基础工作专项(2023JC18);中央级公益性科研院所基本科研业务费专项(2023JB012)
通讯作者: 赵兴春(1974),男,湖南常德人,博士,研究员,主要研究方向为法医学、证据法学、医事法学。   
作者简介: 冯磊(1993),男,山东潍坊人,博士研究生,中级警务技术任职资格,主要研究方向为刑事侦查、现场勘验、痕迹检验。
引用本文:   
冯磊, 赵兴春, 周扬钧. 多信息融合的步态侦查技术研究[J]. 复杂系统与复杂性科学, 2025, 22(2): 73-81.
FENG Lei,ZHAO Xingchun,ZHOU Yangjun. Research on Gait Investigation Technology Based on Multi-information Fusion[J]. Complex Systems and Complexity Science, 2025, 22(2): 73-81.
链接本文:  
https://fzkx.qdu.edu.cn/CN/10.13306/j.1672-3813.2025.02.009      或      https://fzkx.qdu.edu.cn/CN/Y2025/V22/I2/73
[1] TABAR M R R, NIKAKHTAR F, PARKAVOUSI L, et al. Revealing higher-order interactions in high-dimensional complex systems: a data-driven approach[J]. Physical Review X, 2024, 14(1): 011050.
[2] 高子林,王银河.一类不确定混沌系统的自适应模糊同步控制[J]. 复杂系统与复杂性科学,2017,14(4): 7988.
GAO Z L, WANG Y H. Adaptive fuzzy synchronization control of a class of uncertain chaotic systems[J]. Complex Systems and Complexity Science, 2017, 14(4): 7988.
[3] NORRIS C, MC CAHILL M.CCTV:Beyond penal modernism?[J]. British Journal of Criminology,2006,46(1): 97118.
[4] WANG L, LI Z, TAN S, et al. Automatic detection of vertex noise in low-light-level image intensifier based on Gaussian differential filtering and a search strategy for the multifilament structure[J]. Signal, Image and Video Processing, 2025, 19(6): 113.
[5] 吴志雄,崔勇.视频中台体系架构研究与设计[J]. 计算机工程与应用,2024,60(23): 286302.
WU Z X, CUI Y. Research and design of video middle platform architecture[J]. Computer Engineering and Applications, 2024, 60(23): 286302.
[6] 屠云峰,王天昊.基于视频结构化分析技术的跨镜自动追踪系统在轨道交通中的应用[J]. 中国安防,2023(8): 7882.
TU Y F, WANG T H. Application of cross-camera automatic tracking system based on video structured analysis technology in rail transit[J]. China Security & Protection, 2023(8): 7882.
[7] 张尧尧.基于视频结构化的侦查应用[J]. 法制与社会,2020(19): 7576.
ZHANG Y Y. Investigation application based on video structuring [J]. Legal System and Society, 2020(19): 7576.
[8] GRABOWSKI D, SAEED K. Comparison of the effectiveness of face recognition algorithms in terms of photo distortion level[C]//International Symposium on Applied Computing for Software and Smart Systems. Singapore: Springer Nature Singapore, 2024: 115128.
[9] GRIESMAYER M. Explainable AI: a comparison on explainability methods in the field of facial recognition[D]. Wien:Technische Universität Wien, 2024.
[10] ALI W, TIAN W, DIN S U, et al. Classical and modern face recognition approaches: a complete review[J]. Multimedia Tools and Applications, 2021, 80: 48254880.
[11] GUO Y, WANG H, WANG L, et al. 3D face recognition: two decades of progress and prospects[J]. ACM Computing Surveys, 2023, 56(3): 139.
[12] 罗常伟,於俊,于灵云,等.三维人脸识别研究进展综述[J]. 清华大学学报(自然科学版),2021,61(1): 7788.
LUO C W, YU J, YU L Y, et al. A review of the research progress of three-dimensional face recognition [J]. Journal of Tsinghua University(Science and Technology), 2021, 61(1): 7788.
[13] 宋平, 黄玲, 王云龙, 等. 基于计算光场成像的虹膜活体检测方法[J]. 自动化学报, 2019, 45(9): 17011712.
SONG P, HUANG L, WANG Y L, et al. Iris liveness detection method based on computational light field imaging [J]. Acta Automatica Sinica, 2019, 45(9): 17011712.
[14] MALGHEET J R, MANSHOR N B, AFFENDEY L S. Iris recognition development techniques: a comprehensive review[J]. Complexity, 2021(1): 6641247.
[15] KUMAR G, GULATI A, VERMA A, et al. Iris recognition system in the context of authentication[C]//International Conference on Recent Trends in Image Processing and Pattern Recognition. Cham: Springer Nature Switzerland, 2023: 349360.
[16] NGUYEN K, PROENÇA H, ALONSO-FERNANDEZ F. Deep learning for iris recognition: a survey[J]. ACM Computing Surveys, 2024, 56(9): 135.
[17] NGUYEN K, PROEN?A H, ALONSO-FERNANDEZ F. Deep learning for iris recognition: a survey[J]. ACM Computing Surveys, 2024, 56(9): 135.
[18] YIN Y, HE S, ZHANG R, et al. Deep learning for iris recognition: a review[DB/OL].[20250215]. https://arxiv.org/pdf/2303.08514.
[19] LI M, ZHU X, GONG S. Unsupervised tracklet person re-identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(7): 17701782.
[20] YU S, LI S, CHEN D, et al. Cocas: a large-scale clothes changing person dataset for re-identification[DB/OL].[20250215]. https://arxiv.org/pdf/2005.07862.
[21] NING E, WANG C, ZHANG H, et al. Occluded person re-identification with deep learning: a survey and perspectives[J]. Expert Systems With Applications, 2024, 239: 122419.
[22] SARKER P K, ZHAO Q, UDDIN M K. Transformer-based person re-identification: a comprehensive review[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(7): 52225239.
[23] 颜志国,徐峥,梅林,等.下一代公共安全视频监控系统的大数据分析[J]. 上海大学学报(自然科学版),2016,22(1): 8187.
YAN Z G, XU Z, MEI L, et al. Big data analysis of the next generation public security video surveillance system [J]. Journal of Shanghai University(Natural Science Edition), 2016, 22(1): 8187.
[24] 杜向阳,李伟勋,陈增强,等.非线性耦合多智能体系统组编队跟踪控制[J]. 复杂系统与复杂性科学,2022,19(4): 7279.
DU X Y, LI W X, CHEN Z Q, et al. Formation tracking control of nonlinear coupled multi-agent system [J]. Complex Systems and Complexity Sciences, 2022, 19(4): 7279.
[25] 吴大有,陈建蒙,郭志田.利用现场单足迹的步态特征认定犯罪[J]. 刑事技术,1984(3): 2628.
WU D Y, CHEN J M, GUO Z T. Using on-site single footprint gait characteristics in crime identification[J]. Forensic Science and Technology, 1984(3): 2628.
[26] 韩均良.起脚特征和落脚特征的识别[J]. 刑事技术,1991(2): 1314.
HAN J L. Identification of toe-off and heel-strike characteristics[J]. Forensic Science and Technology, 1991(2): 1314.
[27] 韩均良.常见步态特征的观察与识别[J]. 河南公安学刊,1993(1): 2628.
HAN J L. Observation and identification of common gait characteristics[J]. Henan Police Journal, 1993(1): 2628.
[28] AUNG S T Y, KUSAKUNNIRAN W. A comprehensive review of gait analysis using deep learning approaches in criminal investigation[J]. PeerJ Computer Science, 2024, 10: e2456.
[29] MUNUSAMY V, SENTHILKUMAR S. Emerging trends in gait recognition based on deep learning: a survey[J]. Peer J Computer Science, 2024, 10: e2158.
[30] 邬明汉,黄永祯,郭柏冬,等.基于步态识别的视频侦查技术与应用[J]. 中国人民公安大学学报(自然科学版),2021,27(3): 2228.
WU M H, HUANG Y Z, GUO B D, et al. Video investigation technology and application based on gait recognition[J]. Journal of People′s Public Security University of China(Natural Science Edition), 2021, 27(3): 2228.
[31] MAGRIS M, IOSIFIDIS A. Bayesian learning for neural networks: an algorithmic survey[J]. Artificial Intelligence Review, 2023, 56(10): 1177311823.
[32] 杨剑,陈刚.“犯罪过程中的信息转移原理”的反思与完善——信息本体论视角[J]. 中国人民公安大学学报(社会科学版),2020,36(5): 8189.
YANG J, CHEN G. Reflection and improvement on "the principle of information transfer in criminal processes": an information ontology perspective[J]. Journal of People′s Public Security University of China(Social Sciences Edition), 2020, 36(5): 8189.
[33] 何家弘. 从相似到同一: 犯罪侦查研究[M]. 北京:中国法制出版社, 2008.
[34] HURMUZLU Y, BASDOGAN C. On the measurement of dynamic stability of human locomotion[J]. J Biomech Eng, 1994,116(1): 3036.
[35] LIU P, YU N, YANG Y, et al. Quantitative assessment of gait characteristics in patients with Parkinson′s disease using 2D video[J]. Parkinsonism & Related Disorders, 2022, 101: 4956.
[36] 狄增如, 陈晓松. 复杂系统科学研究进展[J]. 北京师范大学学报(自然科学版), 2022, 58(3): 371381.
DI Z R, CHEN X S. Research progress in complex systems science[J]. Journal of Beijing Normal University(Natural Science Edition), 2022, 58(3): 371381.
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed