Comprehensive Survey on Person Identification: Queries, Methods, and Datasets

Jingjing Wu, Yunkai Zhang, Xi Zhou, Shengeng Tang, Yanyan Wei

Abstract: Pedestrian recognition, which entails identifying and retrieving a specific pedestrian from an image gallery based on a query, is pivotal for applications such as urban surveillance and autonomous vehicle navigation. This survey provides a detailed overview of person identification, delineating two primary categories based on the query source: person identification with a prescriptive query, which utilizes actual captured images (e.g., RGB or infrared image), and person identification with a descriptive query, which employs non-visual descriptions such as text or sketches. Furthermore, we explore the datasets commonly employed in person re-identification research, which are critical for training and evaluating models under both single-modal and multi-modal scenarios. This comprehensive analysis aims to furnish a deeper understanding of the current state of visual-based person identification, thereby aiding in the advancement of research and development within this field.