Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches

By Yang Li, Jianke Zhu, Steven C. H. Hoi. Computer Vision and Pattern Recognition, 2015

347 citations recorded by the source corpus.

Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization. In this paper, we propose a new tracking method, Reliable Patch Trackers (RPT), which attempts to identify and exploit the reliable patches that can be tracked effectively through the whole tracking process. Specifically, we present a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework. As the reliable patches distributed over the image, we exploit the motion trajectories to distinguish them from the background. Therefore, the visual object can be defined as the clustering of homo-trajectory patches, where a Hough voting-like scheme is employed to estimate the target state. Encouraging experimental results on a large set of sequences showed that the proposed approach is very effective and in comparison to the state-of-the-art trackers. The full source code of our implementation will be publicly available.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a9448de3265ed9ecdc11c79273aee92daa31f79a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Object Detection from Video Tubelets with Convolutional Neural Networks (2016, background): “Object tracking has been studied for decades [26, 20, 12].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, neutral): “We first evaluate the quality of our spatio-temporal box proposals against tracking algorithms on the Visual Tracker SCM [59] Struck [20] TLD [26] ASLA [25] CXT [12] VTD [30] VTS [31] TGPR [17] RPT [34] [52] [35] We compare our unsupervised video object box proposals to state-of-the-art supervised t”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, positive): “…and run on the workstation with Intel Core CPU i5-7500 (3.40GHz) and Where N represents the number of pixels, i represents the index of pixels, M represents the number of categories, c represents the index of categories, y ic is the label of pixel i , when the category of pixel i is c , y ic…”
CoTracker: It is Better to Track Together (2023, background): “However, this approximation is crude as points are often strongly correlated ( e.g ., when they belong to the same object).”
Video Object Detection with an Aligned Spatial-Temporal Memory (2017, background): “, [30,33]), which requires accurate localization, is also closely-related.”
Large Margin Object Tracking with Circulant Feature Maps (2017, methodology): “aluation on LMCF We evaluate LMCF with 9 state-of-the-art trackers designed with conventional hand-crafted features including Struck [13], MEEM [31], TGPR [10], DLSSVM [22], Staple [2], KCF [14], RPT [20], DSST [5] and SAMF [19]. Among them, Struck and DLSSVM are structured SVM based methods, Staple”
CREST: Convolutional Residual Learning for Visual Tracking (2017, methodology): “We compare our CREST tracker with 29 trackers from the OTB-2013 benchmark [45] and other 21 state-of-the-art trackers including KCF [17], MEEM [48], TGPR [13], DSST [7], RPT [27], MUSTer [20], LCT [31], HCFT [30], FCNT [42], SRDCF [9], CNN-SVM [19], DeepSRDCF [8], DAT [35], Staple [2], SRDCFdecon [1”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “Correlation filters have recently been introduced into visual tracking and shown to achieve high speed as well as robust performance [4, 9, 16, 15, 18, 26, 24, 21, 25, 29].”
T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos (2016, background): “Object tracking has been studied for decades [27], [28], [29].”
Kernel Cross-Correlator (2017, background): “The reliable patch tracker (RPT) presents a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework (Li, Zhu, and Hoi 2015).”
VITAL: VIsual Tracking via Adversarial Learning (2018, methodology): “We compare VITAL with 29 trackers from the OTB-2013 benchmark [59] and other 28 stateof-the-art trackers including DSST [10], KCF [22], TGPR [16], MEEM [63], RPT [34], LCT [37], MUSTer [25], HCFT [36], FCNT [57], SRDCF [12], CNN-SVM [24], DeepSRDCF [11], DAT [41], Staple [3], SRDCFdecon [13], CCOT [”