Unsupervised Person and Vehicle Re-identification via Relative Hard Samples in Industrial Surveillance System

Person and Vehicle Re-Identification (Re-ID) is a critical task in the realm of intelligent industrial surveillance systems. It aims to identify the same person or vehicle across different camera views or scenes, facilitating individual tracking across multiple cameras within industrial environments. Re-Id in an industrial environment can be more challenging than in a general environment due to its unique setting and limited annotated dataset. Hence, this paper focuses on addressing the fully unsupervised re-ID problem, aiming to develop a re-ID solution that can learn without the need for any human-annotated labeled data. Furthermore, recent studies have demonstrated the effectiveness of self-supervised Momentum Contrastive learning (MoCo) as an unsupervised object re-ID method. However, MoCo neglects the hard sample learning. Here, we introduced Relative Hard Samples (RHS) learning to ensure selection in an adaptive and stable way by considering the characteristics of each sample. Experimental results confirm the effectiveness of our proposed hard sample learning strategy RHS selection and RHS learning. Comprehensive experiments have been conducted on one vehicle re-ID dataset and two person re-ID datasets.