Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (9): 2479-2492.DOI: 10.11772/j.issn.1001-9081.2020010038

Special Issue: 综述

• Artificial intelligence •     Next Articles

Survey of person re-identification technology based on deep learning

WEI Wenyu1, YANG Wenzhong1, MA Guoxiang2, HUANG Mei1   

  1. 1. College of Information Science and Engineering, Xinjiang University, Urumqi Xinjiang 830046, China;
    2. School of Software, Xinjiang University, Urumqi Xinjiang 830046, China
  • Received:2020-01-15 Revised:2020-04-02 Online:2020-04-04 Published:2020-09-10
  • Supported by:
    This work is partially supported by the Key Project of National Natural Science Foundation of China (U1435215), the National Natural Science Foundation of China (U1603115), the National Key Research and Development Program of China (2017YFC0820702-3), the Natural Science Foundation of Xinjiang Uygur Autonomous Region (2017D01C042).

基于深度学习的行人再识别技术研究综述

魏文钰1, 杨文忠1, 马国祥2, 黄梅1   

  1. 1. 新疆大学 信息科学与工程学院, 乌鲁木齐 830046;
    2. 新疆大学 软件学院, 乌鲁木齐 830046
  • 通讯作者: 杨文忠
  • 作者简介:魏文钰(1995-),女,新疆哈密人,硕士研究生,主要研究方向:计算机视觉、行人再识别、信息安全;杨文忠(1971-),男,河南南阳人,副教授,博士,CCF会员,主要研究方向:网络舆情、情报分析、信息安全、无线传感器网络;马国祥(1993-),男,新疆伊宁人,硕士研究生,主要研究方向:计算机视觉、机器学习、信息安全;黄梅(1996-),女,新疆和硕人,硕士研究生,主要研究方向:计算机视觉、遥感图像处理。
  • 基金资助:
    国家自然科学基金重点项目(U1435215);国家自然科学基金资助项目(U1603115);国家重点研发计划项目(2017YFC0820702-3);新疆维吾尔自治区自然科学基金资助项目(2017D01C042)。

Abstract: As one of intelligent video surveillance technologies, person Re-identification (Re-id) has great research significance for maintaining social order and stability, and it aims to retrieve the specific person in different camera views. For traditional hand-crafted feature methods are difficult to address the complex camera environment problem in person Re-id task, a large number of deep learning-based person Re-id methods were proposed, so as to promote the development of person Re-id technology greatly. In order to deeply understand the person Re-id technology based on deep learning, a large number of related literature were collated and analyzed. First, a comprehensive introduction was given from three aspects: image, video and cross-modality. The image-based person Re-id technology was divided into two categories: supervised and unsupervised, and the two categories were generalized respectively. Then, some related datasets were listed, and the performance of some algorithms in recent years on image and video datasets were compared and analyzed. At last, the development difficulties of person Re-id technology were summarized, and the possible future research directions of this technology were discussed.

Key words: person Re-identification (Re-id), deep learning, feature learning, metric learning, Convolutional Neural Network (CNN)

摘要: 行人再识别(Re-id)作为智能视频监控技术之一,其目的是在不同的摄像机视图中检索出指定身份的行人,因此该项技术对维护社会治安稳定具有重大研究意义。针对传统的手工特征方法难以应对行人Re-id任务中复杂的摄像机环境的问题,大量基于深度学习的行人Re-id方法被提出,极大地推动了行人Re-id技术的发展。为了深入了解基于深度学习的行人Re-id技术,整理和分析了大量相关文献,首先从图像、视频、跨模态这3个方面展开综述性介绍,将图像行人Re-id技术分为有监督和无监督两大类并分别进行概括;然后列举了部分相关数据集,并对近年来在图像和视频数据集上的一些算法进行性能的比较与分析;最后总结了行人Re-id技术的发展难点,并深入讨论了该技术未来可能的研究方向。

关键词: 行人再识别, 深度学习, 特征学习, 度量学习, 卷积神经网络

CLC Number: