Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters
Top Cited Papers
Open Access
- 4 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in International Journal of Computer Vision
- Vol. 129 (5), 1359-1375
- https://doi.org/10.1007/s11263-021-01435-1
Abstract
Discriminative Correlation Filters (DCF) have been shown to achieve impressive performance in visual object tracking. However, existing DCF-based trackers rely heavily on learning regularised appearance models from invariant image feature representations. To further improve the performance of DCF in accuracy and provide a parsimonious model from the attribute perspective, we propose to gauge the relevance of multi-channel features for the purpose of channel selection. This is achieved by assessing the information conveyed by the features of each channel as a group, using an adaptive group elastic net inducing independent sparsity and temporal smoothness on the DCF solution. The robustness and stability of the learned appearance model are significantly enhanced by the proposed method as the process of channel selection performs implicit spatial regularisation. We use the augmented Lagrangian method to optimise the discriminative filters efficiently. The experimental results obtained on a number of well-known benchmarking datasets demonstrate the effectiveness and stability of the proposed method. A superior performance over the state-of-the-art trackers is achieved using less than $$10\%$$ deep feature channels.
Funding Information
- Engineering and Physical Sciences Research Council (EP/N007743/1, EP/R018456/1)
- National Natural Science Foundation of China (61672265, U1836218)
This publication has 63 references indexed in Scilit:
- Robust Visual Tracking via Structured Multi-Task Sparse LearningInternational Journal of Computer Vision, 2012
- Low-Rank Sparse Learning for Robust Visual TrackingLecture Notes in Computer Science, 2012
- Exploiting the Circulant Structure of Tracking-by-Detection with KernelsLecture Notes in Computer Science, 2012
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of MultipliersFoundations and Trends® in Machine Learning, 2010
- Speeded-Up Robust Features (SURF)Computer Vision and Image Understanding, 2008
- Model Selection and Estimation in Regression with Grouped VariablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- Toeplitz and Circulant Matrices: A ReviewFoundations and Trends® in Communications and Information Theory, 2005
- Support vector trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002