Convolutional Features for Correlation Filter Based Visual Tracking

Citations Over TimeTop 1% of 2015 papers

Abstract

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 miti-gate 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 hand-crafted features. Finally, results comparable to state-of-the-art trackers are obtained on all three benchmark datasets.

Related Papers

• → Adaptive Feature Selection Siamese Networks for Visual Tracking(2020)9 cited
• → Densely Connected Discriminative Correlation Filters for Visual Tracking(2018)5 cited
• → Attention fusion and target-uncertain detection for discriminative tracking(2023)3 cited
• → Cascaded Generative and Discriminative Learning for Visual Tracking(2013)2 cited
• → Current progress in discriminative object tracking(2017)