Sampling Operator to Learn the Scalable Correlation Filter for Visual Tracking
Open Access
- 16 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 11554-11564
Abstract
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 OTB- 100, TC-128, and UAV-123 datasets and achieved promising results in terms of precision and success rates.Keywords
Funding Information
- Institute for Information and Communications Technology Promotion
- Ministry of Science, ICT and Future Planning
- Korea government (MSIP)
This publication has 44 references indexed in Scilit:
- Encoding Color Information for Visual Tracking: Algorithms and BenchmarkIEEE Transactions on Image Processing, 2015
- Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches2015
- Correlation filters with limited boundaries2015
- Real-time part-based visual tracking via adaptive correlation filters2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Accurate Scale Estimation for Robust Visual Tracking2014
- Multi-channel Correlation Filters2013
- Exploiting the Circulant Structure of Tracking-by-Detection with Kernels2012
- Struck: Structured output tracking with kernels2011