A Review: Recent Advancements in Online Private Mode Multi-Object Tracking

Multi-object tracking (MOT) aims to establish connections between target objects throughout consecutive video frames to capture the complete trajectories of these moving objects. Due to the progress made in deep neural networks (DNN) and the growing need for intelligent video analysis, MOT has garnered considerable attention in “computer vision”. MOT exhibits scholarly and economic promise in various domains, including urban public security, military applications, self-driving technology, etc. Despite the diverse range of approaches researchers propose to address this challenge, it doesn’t remain easy due to changing objects’ appearances, significant occlusion, and non-linear motion patterns. Our review process provides fundamental insights into multi-object tracking. It covers essential aspects such as the basic workflow, different approaches to conducting the MOT task, challenges encountered, dataset requirements, evaluation metrics, and procedure for result submission to MOT and CodaLab servers. This study analyses the benefits and constraints of current strategies, techniques, and methods through a systematic review of the latest advancements in object detection and online private detection-based MOT algorithms published. Additionally, we present a quantitative comparison and analysis of experimental evidence of the top-performing MOT algorithms across various metrics. Finally, we propose future research directions by analyzing the commonalities among several methods demonstrating excellent performance.