Convolutional Features for Correlation Filter Based Visual Tracking
2015 (English)In: Proceedings of the IEEE International Conference on Computer Vision, IEEE conference proceedings, 2015, 621-629 p.Conference paper (Refereed)
Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem. We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks. These activations have several advantages compared to the standard deep features (fully connected layers). Firstly, they mitigate the need of task specific fine-tuning. Secondly, they contain structural information crucial for the tracking problem. Lastly, these activations have low dimensionality. We perform comprehensive experiments on three benchmark datasets: OTB, ALOV300++ and the recently introduced VOT2015. Surprisingly, different to image classification, our results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers. Our results further show that the convolutional features provide improved results compared to standard handcrafted features. Finally, results comparable to state-of-theart trackers are obtained on all three benchmark datasets.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2015. 621-629 p.
, IEEE International Conference on Computer Vision. Proceedings, ISSN 1550-5499
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-128869DOI: 10.1109/ICCVW.2015.84ISI: 000380434700075ISBN: 978-146738390-5OAI: oai:DiVA.org:liu-128869DiVA: diva2:933006
15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015