An Improved Multi-Object Tracking Algorithm Designed for Complex Environments

Multi-object tracking (MOT) algorithms are a key research direction in the field of computer vision. Among them, the joint detection and embedding (JDE) method, with its excellent speed and accuracy performance, has become the current mainstream solution. However, in complex scenes with dense targets or occlusions, the tracking performance of existing algorithms is often limited, especially in terms of unstable identity assignment and insufficient tracking accuracy. To address these challenges, this paper proposes a new multi-object tracking model-the Reparameterized and Global Context Track (RGTrack). This model is based on the Correlation-Sensitive Track (CSTrack) framework and innovatively introduces multi-branch training and attention mechanisms, combined with reparameterized convolutional networks and global attention modules, significantly enhancing the network's feature extraction ability in complex scenes, especially in ignoring irrelevant information and focusing on key areas. It adopted a multiple association strategy to better establish the association relationship between targets in consecutive frames. Through this improvement, the Reparameterized and Global Context Track can better handle scenes with dense targets and severe occlusions, providing more accurate target identity matching and continuous tracking. Experimental results show that compared with the Correlation-Sensitive Track, the Reparameterized and Global Context Track has significant improvements in multiple key indicators: multi-object tracking accuracy (MOTA) increased by 1.15%, Identity F1 Score (IDF1) increased by 1.73%, and Mostly Tracked (MT) increased by 6.86%, while ID-switched (ID Sw) decreased by 47.49%. These results indicate that the Reparameterized and Global Context Track not only can stably track targets in more complex scenes but also significantly improves the continuity of target identities. Moreover, the Reparameterized and Global Context Track increased the frames per second (FPS) by 51.48% and reduced the model size by 3.08%, demonstrating its significant advantages in real-time performance and computational efficiency. Therefore, the Reparameterized and Global Context Track model maintains high accuracy while having stronger real-time processing capabilities, making it especially suitable for embedded devices and resource-constrained application environments.