Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

Abstract

Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments. Code and supplementary material are available at http://www.cvl.isy.liu.se/research/objrec/visualtracking/conttrack/index.html.

Accepted at ECCV 2016

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• High-Speed Tracking with Kernelized Correlation Filters
• Learning Spatially Regularized Correlation Filters for Visual Tracking

Cited by in corpus (18)

• SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
• Deeper and Wider Siamese Networks for Real-Time Visual Tracking
• Unsupervised Deep Tracking
• Target-Aware Deep Tracking
• SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
• Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking
• Prediction-Tracking-Segmentation
• MAVOT: Memory-Augmented Video Object Tracking
• Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
• Online Multi-Object Tracking with Dual Matching Attention Networks
• Hallucinated Adversarial Learning for Robust Visual Tracking
• DCCO: Towards Deformable Continuous Convolution Operators
• Learning Rotation Adaptive Correlation Filters in Robust Visual Object Tracking
• Real-time tracker with fast recovery from target loss
• End-to-end feature fusion siamese network for adaptive visual tracking
• Multi-Adapter RGBT Tracking
• A Strong Feature Representation for Siamese Network Tracker
• Generic Multiview Visual Tracking