Learning Background-Aware Correlation Filters for Visual Tracking

@article{Galoogahi2017LearningBC,
  title={Learning Background-Aware Correlation Filters for Visual Tracking},
  author={Hamed Kiani Galoogahi and Ashton Fagg and Simon Lucey},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1144-1152}
}
Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn - on the fly - how the object is changing over time. A fundamental drawback to CFs, however, is that the background of the target is not modeled over time which can result in suboptimal performance. Recent tracking algorithms have suggested to resolve this… 

Figures and Tables from this paper

Learning target-aware correlation filters for visual tracking
Hard negative mining for correlation filters in visual tracking
TLDR
A robust tracking method in which a hard negative mining scheme is employed in each frame, and a target verification strategy is developed by introducing a peak signal-to-noise ratio (PSNR) criterion.
Efficient Multi-level Correlating for Visual Tracking
TLDR
This paper proposes a multi-level CF-based tracking approach named MLCFT which further explores the potential capacity of CF with two-stage detection: primal detection and oriented re-detection and demonstrates that this approach outperforms the most state-of-the-art trackers while tracking at speed of exceeded 16 frames per second on challenging benchmarks.
Multi-Channel Feature Dimension Adaption for Correlation Tracking
TLDR
Adimension adaption correlation filters (DACF) is proposed, which adopts the multi-channel deep CNN features to obtain a discriminative sample appearance model, resisting the background clutters, and tackles the issue of over-fitting.
Correlation Filter-Based Visual Tracking with Multi-featured Adaptive Online Learning
TLDR
Improved background-aware correlation filter (BACF) is proposed that utilize colour features as a complement of Histogram of Oriented Gradient (HOG) to improve the representation of the target, and implementing adaptive feature fusion in the response layer using Peak to Sidelobe Ratio (PSR) as a reference metric.
Complementary Discriminative Correlation Filters Based on Collaborative Representation for Visual Object Tracking
TLDR
This work proposes the use of a collaborative representation between successive frames to extract the dynamic appearance information from a target with rapid appearance changes, which results in suppressing the undesirable impact of the background.
Adaptive multi-branch correlation filters for robust visual tracking
TLDR
This paper proposes an adaptive multi-branch correlation filter tracking method that is introduced to tolerate temporal changes of the object, which can serve different circumstances and incorporates both foreground and background information to learn background suppression.
...
...

References

SHOWING 1-10 OF 46 REFERENCES
Convolutional Features for Correlation Filter Based Visual Tracking
TLDR
The results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers, and show that the convolutional features provide improved results compared to standard hand-crafted features.
Learning Spatially Regularized Correlation Filters for Visual Tracking
TLDR
The proposed SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples, and an optimization strategy is proposed, based on the iterative Gauss-Seidel method, for efficient online learning.
Staple: Complementary Learners for Real-Time Tracking
TLDR
It is shown that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.
Fully-Convolutional Siamese Networks for Object Tracking
TLDR
A basic tracking algorithm is equipped with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video and achieves state-of-the-art performance in multiple benchmarks.
Visual object tracking using adaptive correlation filters
TLDR
A new type of correlation filter is presented, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame, which enables the tracker to pause and resume where it left off when the object reappears.
Encoding color information for visual tracking: Algorithms and benchmark
TLDR
This paper comprehensively encode 10 chromatic models into 16 carefully selected state-of-the-art visual trackers and performs detailed analysis on several issues, including the behavior of various combinations between color model and visual tracker, the degree of difficulty of each sequence for tracking, and how different challenge factors affect the tracking performance.
High-Speed Tracking with Kernelized Correlation Filters
TLDR
A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.
Siamese Instance Search for Tracking
TLDR
It turns out that the learned matching function is so powerful that a simple tracker built upon it, coined Siamese INstance search Tracker, SINT, suffices to reach state-of-the-art performance.
Hierarchical Convolutional Features for Visual Tracking
TLDR
This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets.
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration
TLDR
This paper presents a very appealing tracker based on the correlation filter framework and suggests an effective scale adaptive scheme to tackle the problem of the fixed template size in kernel correlation filter tracker.
...
...