Good Features to Correlate for Visual Tracking

Creative Commons License

Gundogdu E., Alatan A. A.

IEEE TRANSACTIONS ON IMAGE PROCESSING, vol.27, pp.2526-2540, 2018 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 27
  • Publication Date: 2018
  • Doi Number: 10.1109/tip.2018.2806280
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.2526-2540
  • Keywords: Visual tracking, correlation filters, deep feature learning, OBJECT TRACKING, ROBUST
  • Middle East Technical University Affiliated: Yes


During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in this family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize the robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks, which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.