SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
This work addresses occlusion and similarity issues in MOT for applications like surveillance and autonomous driving, representing an incremental advance with specific performance gains.
The paper tackles challenges in Multiple Object Tracking (MOT) like occlusions and similar objects by introducing SMILEtrack, which integrates an object detector with a Siamese network-based Similarity Learning Module and a Similarity Matching Cascade, achieving improvements of 0.4-0.8 MOTA and 2.1-2.2 HOTA over BYTETrack on MOT17 and MOT20 datasets.
Despite recent progress in Multiple Object Tracking (MOT), several obstacles such as occlusions, similar objects, and complex scenes remain an open challenge. Meanwhile, a systematic study of the cost-performance tradeoff for the popular tracking-by-detection paradigm is still lacking. This paper introduces SMILEtrack, an innovative object tracker that effectively addresses these challenges by integrating an efficient object detector with a Siamese network-based Similarity Learning Module (SLM). The technical contributions of SMILETrack are twofold. First, we propose an SLM that calculates the appearance similarity between two objects, overcoming the limitations of feature descriptors in Separate Detection and Embedding (SDE) models. The SLM incorporates a Patch Self-Attention (PSA) block inspired by the vision Transformer, which generates reliable features for accurate similarity matching. Second, we develop a Similarity Matching Cascade (SMC) module with a novel GATE function for robust object matching across consecutive video frames, further enhancing MOT performance. Together, these innovations help SMILETrack achieve an improved trade-off between the cost ({\em e.g.}, running speed) and performance (e.g., tracking accuracy) over several existing state-of-the-art benchmarks, including the popular BYTETrack method. SMILETrack outperforms BYTETrack by 0.4-0.8 MOTA and 2.1-2.2 HOTA points on MOT17 and MOT20 datasets. Code is available at https://github.com/pingyang1117/SMILEtrack_Official