High Performance Visual Object Tracking with Unified Convolutional Networks

Abstract

Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in different tasks and individual components in tracking systems are learned separately, thus the achieved tracking performance may be suboptimal. Besides, most of these trackers are not designed towards real-time applications because of their time-consuming feature extraction and complex optimization details. In this paper, we propose an end-to-end framework to learn the convolutional features and perform the tracking process simultaneously, namely, a unified convolutional tracker (UCT). Specifically, the UCT treats feature extractor and tracking process both as convolution operation and trains them jointly, which enables learned CNN features are tightly coupled with tracking process. During online tracking, an efficient model updating method is proposed by introducing peak-versus-noise ratio (PNR) criterion, and scale changes are handled efficiently by incorporating a scale branch into network. Experiments are performed on four challenging tracking datasets: OTB2013, OTB2015, VOT2015 and VOT2016. Our method achieves leading performance on these benchmarks while maintaining beyond real-time speed.

arXiv commentExtended version of [arXiv:1711.04661] our UCT tracker in ICCV VOT2017

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• High-Speed Tracking with Kernelized Correlation Filters
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• Transferring Rich Feature Hierarchies for Robust Visual Tracking
• DCFNet: Discriminant Correlation Filters Network for Visual Tracking
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• Action Machine: Rethinking Action Recognition in Trimmed Videos
• Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes
• Multi-hierarchical Independent Correlation Filters for Visual Tracking
• Exploiting Offset-guided Network for Pose Estimation and Tracking
• Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
• Optical Flow Based Online Moving Foreground Analysis