Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
arXiv:1608.07242
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)
Cited by in corpus (38)
- Deep Learning for Visual Tracking: A Comprehensive Survey
- Good Features to Correlate for Visual Tracking
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking
- Siamese Attentional Keypoint Network for High Performance Visual Tracking
- A Twofold Siamese Network for Real-Time Object Tracking
- SiamVGG: Visual Tracking using Deeper Siamese Networks
- NoScope: Optimizing Neural Network Queries over Video at Scale
- Parallel Tracking and Verifying
- Deformable Object Tracking with Gated Fusion
- TDIOT: Target-driven Inference for Deep Video Object Tracking
- Lucid Data Dreaming for Video Object Segmentation
- Multi-hierarchical Independent Correlation Filters for Visual Tracking
- SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
- Benchmarking Deep Trackers on Aerial Videos
- Tracking by Instance Detection: A Meta-Learning Approach
- Recurrent Filter Learning for Visual Tracking
- Correlation Tracking via Joint Discrimination and Reliability Learning
- 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
- Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking
- Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning
- Robust Tracking Using Region Proposal Networks
- Visual Tracking via Dynamic Memory Networks
- Efficient Diverse Ensemble for Discriminative Co-Tracking
- DCCO: Towards Deformable Continuous Convolution Operators
- Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
- Fast Dynamic Convolutional Neural Networks for Visual Tracking
- Feature Selection Convolutional Neural Networks for Visual Tracking
- SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
- FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
- Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
- A Strong Feature Representation for Siamese Network Tracker
- Multi-Branch Siamese Networks with Online Selection for Object Tracking
- Saliency based Semi-supervised Learning for Orbiting Satellite Tracking
- Infrared target tracking based on proximal robust principal component analysis method
- Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
- Pixel-wise object tracking