Video Tracking Using Learned Hierarchical Features

Abstract

In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to the specific target object. The adaptation is conducted in both layers of the deep feature learning module so as to include appearance information of the specific target object. As a result, the learned hierarchical features can be robust to both complicated motion transformations and appearance changes of target objects. We integrate our feature learning algorithm into three tracking methods. Experimental results demonstrate that significant improvement can be achieved using our learned hierarchical features, especially on video sequences with complicated motion transformations.

12 pages, 7 figures

References in corpus (1)

• Video Tracking Using Learned Hierarchical Features

Cited by in corpus (16)

• Video Tracking Using Learned Hierarchical Features
• Dual Deep Network for Visual Tracking
• Distractor-aware Siamese Networks for Visual Object Tracking
• Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Survey
• Transformers in Single Object Tracking: An Experimental Survey
• A Comparison Study of Credit Card Fraud Detection: Supervised versus Unsupervised
• Robust Visual Tracking via Convolutional Networks
• Robust Visual Tracking via Hierarchical Convolutional Features
• Scene Parsing with Integration of Parametric and Non-parametric Models
• Deep Learning for Image Denoising: A Survey
• Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
• Hierarchical Spatial Sum-Product Networks for Action Recognition in Still Images
• Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks
• Correlated Logistic Model With Elastic Net Regularization for Multilabel Image Classification
• Robust Structured Group Local Sparse Tracker Using Deep Features
• Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking