Revisiting Robust Visual Tracking Using Pixel-Wise Posteriors

Schubert, Falk; Casaburo, Daniele; Dickmanns, Dirk; Belagiannis, Vasileios

doi:10.1007/978-3-319-20904-3_26

Cited by 5 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, they propose to exploit semantics to localise object accurately via an energy-minimization-based segmentation. In [82] [82] M Graph-based framework Graph-cut Deep matching Box, Mask Wang [174] S CNN CNN CNN Box, Mask Yao [199] S Graph-based framework CNN Correlation lter Box Zhang [207] S CNN CNN CNN Box, Mask Yeo [203] S Probabilistic framework Markov Chain Markov Chain Box, Mask Liu [109] M Probabilistic framework CRF CRF Mask Tjaden [158] M Probabilistic framework Pixel-wise posterior Pixel-wise posterior Mask Schubert [142] S Probabilistic framework Pixel-wise posterior Pixel-wise posterior Box, Mask Milan [117] M Probabilistic framework SVM CRF Box, Mask Wen [184] S [156] M Probabilistic framework MCMC MCMC Box Bugeau [21] M Graph-based framework Graph-cuts Mean-shift Box, Mask Bibby [14] S Probabilistic framework Pixel-wise posterior Pixel-wise posterior Box, Mask Paragios [123] M Graph-based framework Active contours Interframe di erence Mask clustering of bounding boxes. The random walker algorithm [122] is also formulated on a weighted graph.…”

Section: 521mentioning

confidence: 99%

“…There are many probabilistic framework for jointly solving video object segmentation and tracking, such as Bayesian methods [3,156,186,203], pixel-wise posterior based methods [14,142,158], and CRF based methods [105,109,117]. In [3], Aeschliman et al present a probabilistic framework for jointly solving tracking and ne, pixel-level segmentation.…”

Section: Probabilistic Frameworkmentioning

confidence: 99%

“…In [14,142,158], a probability generative model is built a segmentation-based tracking method using pixel-wise posteriors. These methods construct the appearance-model using a probabilistic formulation, carry out the level-set segmentation using this model, and then perform the contour propagation.…”

Section: Probabilistic Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Video Object Segmentation and Tracking: A Survey

Yao,

Lin,

Xia

et al. 2019

Preprint

View full text Add to dashboard Cite

Object segmentation and object tracking are fundamental research area in the computer vision community. These two topics are di cult to handle some common challenges, such as occlusion, deformation, motion blur, and scale variation. The former contains heterogeneous object, interacting object, edge ambiguity, and shape complexity. And the latter su ers from di culties in handling fast motion, out-of-view, and real-time processing. Combining the two problems of video object segmentation and tracking (VOST) can overcome their respective di culties and improve their performance. VOST can be widely applied to many practical applications such as video summarization, high de nition video compression, human computer interaction, and autonomous vehicles. This article aims to provide a comprehensive review of the state-of-theart tracking methods, and classify these methods into di erent categories, and identify new trends. First, we provide a hierarchical categorization existing approaches, including unsupervised VOS, semi-supervised VOS, interactive VOS, weakly supervised VOS, and segmentation-based tracking methods. Second, we provide a detailed discussion and overview of the technical characteristics of the di erent methods. Third, we summarize the characteristics of the related video dataset, and provide a variety of evaluation metrics. Finally, we point out a set of interesting future works and draw our own conclusions.

show abstract

Section: 521mentioning

confidence: 99%

Section: Probabilistic Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Video Object Segmentation and Tracking: A Survey

Yao,

Lin,

Xia

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The pixel‐wise posterior‐based visual tracker proposed in [5 ] presents a bag‐of‐pixels representation, in which rigid motion and shape deformation can be dealt with. In [6 ], the estimation of pixel‐wise posteriors was boosted using only a subset of the pixels. In contrast to these methods, our method provides a theoretical basis for the efficient estimation of pixel‐wise posteriors using minibatches.…”

Section: Introductionmentioning

confidence: 99%

Zero‐variance minibatch Monte Carlo for pixel‐wise visual tracking

Park

Kwon

2020

Electron. lett.

View full text Add to dashboard Cite

In this study, the authors present a novel visual tracking method using the pixel‐wise posterior estimation and minibatch Monte Carlo sampling. To avoid background pixels in the noisy bounding box representation, they estimate the posteriors in a pixel‐wise manner. To boost the pixel‐wise posterior estimation, they adopt minibatch Monte Carlo sampling, where only a small portion of pixels are used for inference. Experimental results demonstrate that the proposed visual tracker produces accurate tracking results using a small portion of pixels for the posterior estimation and is comparable to state‐of‐the‐art methods.

show abstract