Recently, Correlation Filter CF-based methods have demonstrated excellent performance for visual object tracking. However, CF-based models often face one model degradation problem: With low learning rate, the tracking model cannot be updated as fast as the large-scale variation or deformation of fast motion targets; As for high learning rate, the tracking model is not robust enough against disturbance, such as occlusion. To enable the tracking model adapt with such variation effectively, a progressive updating mechanism is necessary. In order to exploit spatial and temporal information in original data for tracking model adaptation, we employ an implicit interpolation model. With motion-estimated interpolation using adjacent tracking frames, the obtained intermediate response map can fit the learning rate well, which will effectively alleviate the learning-related model degradation. The evaluations on the benchmark datasets KITTI and VOT2017 demonstrate that the proposed tracker outperforms the existing CF-based models, with advantages regarding the tracking accuracy.
CITATION STYLE
Kong, X., Zhao, M., Zhang, C., Zhou, Q., & Lai, Y. (2020). Alleviating tracking model degradation using interpolation-based progressive updating. In Domain Adaptation for Visual Understanding (pp. 129–142). Springer International Publishing. https://doi.org/10.1007/978-3-030-30671-7_9
Mendeley helps you to discover research relevant for your work.