The correlation filter is suitable for tracking on account of its low computational complexity and promising performance. However, the number of available training samples is limited to the filter size, and the lack of samples leads to poor generalization. Moreover, spectral leakage degrades the filter quality. In this paper, we, therefore, propose a sampling operator for learning a scalable correlation filter in an enlarged window, whose size is larger than the object size. The scalable filter encodes the sparse frequency representation to reconstruct a larger filter with zeros outside of the object in the spatial domain. The sampling operator, which is composed of windowing and sampling operations, enables learning the scalable filter from a large window, and it suppresses spectral leakage. Our method was evaluated on the OTB-100, TC-128, and UAV-123 datasets and achieved the promising results in terms of precision and success rates.
Bibliographical noteFunding Information:
This work was partly supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (2016-0-00197, Development of the high-precision natural 3D view generation technology using smart-car multi sensors and deep learning) and Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (2016-0-00562, Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly).
All Science Journal Classification (ASJC) codes
- Computer Science(all)
- Materials Science(all)