UHP-SOT: An Unsupervised High-Performance Single Object Tracker
This work addresses the problem of unsupervised object tracking for computer vision applications, offering a novel method that competes with supervised approaches.
The paper tackles unsupervised single object tracking by proposing UHP-SOT, which uses foreground and background correlations to address issues like tracking loss and box adaptation, achieving state-of-the-art performance on benchmarks TB-50 and TB-100 with speeds of 22.7-32.0 FPS on a CPU.
An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object Tracker) in this work. UHP-SOT consists of three modules: 1) appearance model update, 2) background motion modeling, and 3) trajectory-based box prediction. A state-of-the-art discriminative correlation filters (DCF) based tracker is adopted by UHP-SOT as the first module. We point out shortcomings of using the first module alone such as failure in recovering from tracking loss and inflexibility in object box adaptation and then propose the second and third modules to overcome them. Both are novel in single object tracking (SOT). We test UHP-SOT on two popular object tracking benchmarks, TB-50 and TB-100, and show that it outperforms all previous unsupervised SOT methods, achieves a performance comparable with the best supervised deep-learning-based SOT methods, and operates at a fast speed (i.e. 22.7-32.0 FPS on a CPU).