Multi-hierarchical Independent Correlation Filters for Visual Tracking

Abstract

For visual tracking, most of the traditional correlation filters (CF) based methods suffer from the bottleneck of feature redundancy and lack of motion information. In this paper, we design a novel tracking framework, called multi-hierarchical independent correlation filters (MHIT). The framework consists of motion estimation module, hierarchical features selection, independent CF online learning, and adaptive multi-branch CF fusion. Specifically, the motion estimation module is introduced to capture motion information, which effectively alleviates the object partial occlusion in the temporal video. The multi-hierarchical deep features of CNN representing different semantic information can be fully excavated to track multi-scale objects. To better overcome the deep feature redundancy, each hierarchical features are independently fed into a single branch to implement the online learning of parameters. Finally, an adaptive weight scheme is integrated into the framework to fuse these independent multi-branch CFs for the better and more robust visual object tracking. Extensive experiments on OTB and VOT datasets show that the proposed MHIT tracker can significantly improve the tracking performance. Especially, it obtains a 20.1% relative performance gain compared to the top trackers on the VOT2017 challenge, and also achieves new state-of-the-art performance on the VOT2018 challenge.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Feature Pyramid Networks for Object Detection
• Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking
• Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
• DCFNet: Discriminant Correlation Filters Network for Visual Tracking
• Good Features to Correlate for Visual Tracking
• Distractor-aware Siamese Networks for Visual Object Tracking
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video

Cited by in corpus (6)

• Benchmarking Deep Trackers on Aerial Videos
• Exploiting Offset-guided Network for Pose Estimation and Tracking
• State-aware Re-identification Feature for Multi-target Multi-camera Tracking
• Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
• Motion Control on Bionic Eyes: A Comprehensive Review
• High Performance Visual Object Tracking with Unified Convolutional Networks