Modeling and Propagating CNNs in a Tree Structure for Visual Tracking

Abstract

We present an online visual tracking algorithm by managing multiple target appearance models in a tree structure. The proposed algorithm employs Convolutional Neural Networks (CNNs) to represent target appearances, where multiple CNNs collaborate to estimate target states and determine the desirable paths for online model updates in the tree. By maintaining multiple CNNs in diverse branches of tree structure, it is convenient to deal with multi-modality in target appearances and preserve model reliability through smooth updates along tree paths. Since multiple CNNs share all parameters in convolutional layers, it takes advantage of multiple models with little extra cost by saving memory space and avoiding redundant network evaluations. The final target state is estimated by sampling target candidates around the state in the previous frame and identifying the best sample in terms of a weighted average score from a set of active CNNs. Our algorithm illustrates outstanding performance compared to the state-of-the-art techniques in challenging datasets such as online tracking benchmark and visual object tracking challenge.

10 pages, Hyeonseob Nam and Mooyeol Baek have equal contribution

References in corpus (2)

• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Learning Deconvolution Network for Semantic Segmentation

Cited by in corpus (12)

• Deeper and Wider Siamese Networks for Real-Time Visual Tracking
• SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
• Benchmarking Deep Trackers on Aerial Videos
• Recurrent Filter Learning for Visual Tracking
• MAVOT: Memory-Augmented Video Object Tracking
• Multi-Task Driven Feature Models for Thermal Infrared Tracking
• A Review of Visual Trackers and Analysis of its Application to Mobile Robot
• Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning
• Robust Tracking Using Region Proposal Networks
• DCCO: Towards Deformable Continuous Convolution Operators
• Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
• A Strong Feature Representation for Siamese Network Tracker