arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.11332cs.CV
收藏

基于深度学习的视频行人重识别:综述

Deep Learning for Video-based Person Re-Identification: A Survey

FloppyDISK AI Research(FloppyDISK人工智能研究院)

Khawar Islam

AI总结:

本文综述深度学习在视频行人重识别中的最新进展,梳理方法局限、技术里程碑与架构设计,并比较数据集性能、指出未来研究方向。

摘要:

基于视频的行人重识别(video re-ID)近来因其在监控、智慧城市和公共安全等多个领域的广泛实际应用而吸引了越来越多的关注。然而,由于视角、遮挡、姿态变化以及不确定的视频序列等诸多不确定挑战,video re-ID相当困难,并且仍处于持续发展阶段。在过去几年中,面向video re-ID的深度学习不断在公开数据集上取得令人惊讶的结果,研究人员也开发了多种方法来处理video re-ID中的不同问题。与基于图像的re-ID相比,video re-ID更具挑战性和复杂性。为了促进未来研究并应对挑战,本文作为首篇综合性论文,对用于video re-ID的深度学习方法的最新进展进行了综述。它广泛涵盖三个重要方面,包括简要的video re-ID方法及其局限性、具有技术挑战的主要里程碑,以及架构设计。本文还对各种可用数据集进行了性能比较分析,为改进video re-ID提供了具有价值的思路指导,并给出了令人期待的研究方向。

英文摘要:

Video-based person re-identification (video re-ID) has lately fascinated growing attention due to its broad practical applications in various areas, such as surveillance, smart city, and public safety. Nevertheless, video re-ID is quite difficult and is an ongoing stage due to numerous uncertain challenges such as viewpoint, occlusion, pose variation, and uncertain video sequence, etc. In the last couple of years, deep learning on video re-ID has continuously achieved surprising results on public datasets, with various approaches being developed to handle diverse problems in video re-ID. Compared to image-based re-ID, video re-ID is much more challenging and complex. To encourage future research and challenges, this first comprehensive paper introduces a review of up-to-date advancements in deep learning approaches for video re-ID. It broadly covers three important aspects, including brief video re-ID methods with their limitations, major milestones with technical challenges, and architectural design. It offers comparative performance analysis on various available datasets, guidance to improve video re-ID with valuable thoughts, and exciting research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑