Discriminative Correlation Filter with Channel and Spatial Reliability

Abstract

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to the part of the object suitable for tracking. This both allows to enlarge the search region and improves tracking of non-rectangular objects. Reliability scores reflect channel-wise quality of the learned filters and are used as feature weighting coefficients in localization. Experimentally, with only two simple standard features, HoGs and Colornames, the novel CSR-DCF method -- DCF with Channel and Spatial Reliability -- achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB100. The CSR-DCF runs in real-time on a CPU.

Accepted to: International Journal of Computer Vision: https://link.springer.com/article/10.1007/s11263-017-1061-3

References in corpus (6)

• High-Speed Tracking with Kernelized Correlation Filters
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Learning Spatially Regularized Correlation Filters for Visual Tracking
• A Novel Performance Evaluation Methodology for Single-Target Trackers
• Transferring Rich Feature Hierarchies for Robust Visual Tracking
• Visual object tracking performance measures revisited

Cited by in corpus (10)

• Deep Learning for Visual Tracking: A Comprehensive Survey
• Synthetic data generation for end-to-end thermal infrared tracking
• Video-rate multispectral imaging in laparoscopic surgery: First-in-human application
• Global Instance Tracking: Locating Target More Like Humans
• Tracking-by-Trackers with a Distilled and Reinforced Model
• Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
• Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
• Physics-informed laboratory estimation of Sargassum windage
• An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers
• Deciphering circulating tumor cells binding in a microfluidic system thanks to a parameterized mathematical model