Göm meny

Image could not be displayed.

ECO: Efficient Convolution Operators for Tracking

In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving \emph{both} speed and performance.

We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model; (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples; (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and TempleColor. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method C-COT in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.


Martin Danelljan, Goutam Bhat, Fahad Khan, Michael Felsberg.
ECO: Efficient Convolution Operators for Tracking.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.



Matlab code on GitHub

Raw Results

Raw result files for the OTB, UAV123, Temple-Color and VOT2016 datasets.