DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
This work addresses the problem of tracking objects in crowded scenes with occlusions for computer vision applications, representing an incremental advancement in method design.
The paper tackles the challenge of multiple object tracking under severe occlusions by proposing DNMOT, a DeNoising Transformer that simulates occlusions during training to learn robust denoising, achieving state-of-the-art performance on MOT17, MOT20, and DanceTrack datasets with clear improvements over previous methods.
Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur. In this paper, we analyze the limitations of traditional Convolutional Neural Network-based methods and Transformer-based methods in handling occlusions and propose DNMOT, an end-to-end trainable DeNoising Transformer for MOT. To address the challenge of occlusions, we explicitly simulate the scenarios when occlusions occur. Specifically, we augment the trajectory with noises during training and make our model learn the denoising process in an encoder-decoder architecture, so that our model can exhibit strong robustness and perform well under crowded scenes. Additionally, we propose a Cascaded Mask strategy to better coordinate the interaction between different types of queries in the decoder to prevent the mutual suppression between neighboring trajectories under crowded scenes. Notably, the proposed method requires no additional modules like matching strategy and motion state estimation in inference. We conduct extensive experiments on the MOT17, MOT20, and DanceTrack datasets, and the experimental results show that our method outperforms previous state-of-the-art methods by a clear margin.