Spectral Filter Tracking
TLDR
This paper proposes a simple but efficient spectral filter tracking method from the viewpoint of a graph, where each candidate’s image region is modeled as a pixelwise grid graph, and achieves the state-of-the-art performance on OTB-2015 and VOT2016 under the same feature extraction strategy.Abstract:
Visual object tracking is a challenging computer vision task with numerous real-world applications. In this paper, we propose a simple but efficient spectral filter tracking (SFT) method from the viewpoint of a graph, where each candidate’s image region is modeled as a pixelwise grid graph. Instead of the conventional graph matching, we formulate the tracking as a plain least square regression problem of learning spectral filters on graphs to predict an optimal vertex, which indicates the center of the target. To bypass computationally expensive eigenvalue decomposition on graph Laplacian $ \mathcal {L}$ , we parameterize spectral graph filters as a polynomial of $ \mathcal {L}$ to aggregate local graph features according to spectral graph theory, in which $ \mathcal {L}^{k}$ exactly encodes a k-hop local neighborhood of each vertex. Thus, different from the holistic regression in those correlation filter-based methods, SFT can operate on localized regions around a pixel (i.e., a vertex), which can effectively reduce the influence of local variations and cluttered backgrounds. Furthermore, we observe that the correlation filter tracking may be viewed as a specific case of our proposed spectral filtering method. The implementation of SFT can simply boil down to only a few line codes, but surprisingly it beats the correlation filter-based model with the same feature input and achieves the state-of-the-art performance on OTB-2015 and VOT2016 under the same feature extraction strategy.read more
Citations
More filters
Proceedings ArticleDOI
Graph Convolutional Tracking
TL;DR: The GCT jointly incorporates two types of Graph Convolutional Networks into a siamese framework for target appearance modeling and adopts a spatial-temporal GCN to model the structured representation of historical target exemplars.
Proceedings ArticleDOI
Feature-Attentioned Object Detection in Remote Sensing Imagery
TL;DR: A novel feature-attentioned object detection framework is introduced to boost its performance in remote sensing imagery, which can focus on learning these intrinsic representations from different aspects in an end-to-end framework.
Proceedings ArticleDOI
Cross-Modal Pattern-Propagation for RGB-T Tracking
TL;DR: This paper proposes a cross-modal pattern-propagation (CMPP) tracking framework to diffuse instance patterns across RGB-T data on spatial domain as well as temporal domain, and adopts the spirit of pattern propagation to dynamic temporal domain.
Journal ArticleDOI
Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment
TL;DR: This paper solves the cross-camera tracklet matching problem by TRACklet-to-Target Assignment (TRACTA), and proposes the Restricted Non-negative Matrix Factorization (RNMF) algorithm to compute the optimal assignment solution that meets a set of constraints, which should be in force in practice.
Journal ArticleDOI
Visual object tracking: A survey
TL;DR: A comprehensive overview of state-of-the-art tracking frameworks including both deep and non-deep trackers is provided in this article , where the authors present both quantitative and qualitative tracking results of various trackers on five benchmark datasets.
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Journal ArticleDOI
Object Detection with Discriminatively Trained Part-Based Models
TL;DR: An object detection system based on mixtures of multiscale deformable part models that is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges is described.
Journal ArticleDOI
High-Speed Tracking with Kernelized Correlation Filters
TL;DR: 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.
Journal ArticleDOI
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
TL;DR: The field of signal processing on graphs merges algebraic and spectral graph theoretic concepts with computational harmonic analysis to process high-dimensional data on graphs as discussed by the authors, which are the analogs to the classical frequency domain and highlight the importance of incorporating the irregular structures of graph data domains when processing signals on graphs.
Journal ArticleDOI
Incremental Learning for Robust Visual Tracking
TL;DR: A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.