Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Yu, Tsz-Ho; Kim, Taekyun; Cipolla, Roberto

doi:10.1109/cvpr.2013.467

Cited by 50 publications

(33 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our opinion, the Weizman dataset is already solved since many researchers report accuracies of 100%. However, in recent publications (Li et al, 2013;Tian et al, 2013;Yu et al, 2013) this dataset is still used to evaluate the corresponding methods. In order to allow a comparison to recent works and to show the benefit of our proposed method we evaluate Motion Binary Patterns on this dataset too.…”

Section: Resultsmentioning

confidence: 99%

Motion Binary Patterns for Action Recognition

Baumann

Lao²,

Ehlers

et al. 2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Abstract:In this paper, we propose a novel feature type to recognize human actions from video data. By combining the benefit of Volume Local Binary Patterns and Optical Flow, a simple and efficient descriptor is constructed. Motion Binary Patterns (MBP) are computed in spatio-temporal domain while static object appearances as well as motion information are gathered. Histograms are used to learn a Random Forest classifier which is applied to the task of human action recognition. The proposed framework is evaluated on the well-known, publicly available KTH dataset, Weizman dataset and on the IXMAS dataset for multi-view action recognition.The results demonstrate state-of-the-art accuracies in comparison to other methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Motion Binary Patterns for Action Recognition

Baumann

Lao²,

Ehlers

et al. 2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…In our opinion, the Weizman dataset is already solved since many researchers report accuracies of 100%. However, in recent publications [11,22,30] this dataset is still used to evaluate the corresponding methods. In order to allow a comparison to recent works and to show the benefit of our proposed method we evaluate VLBPs on this dataset too.…”

Section: Resultsmentioning

confidence: 99%

Computation strategies for volume local binary patterns applied to action recognition

Baumann

Ehlers

Rosenhahn

et al. 2014

2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Volume Local Binary Patterns are a well-known feature type to describe object characteristics in the spatiotemporal domain. Apart from the computation of a binary pattern further steps are required to create a discriminative feature. In this paper we propose different computation methods for Volume Local Binary Patterns. These methods are evaluated in detail and the best strategy is shown. A Random Forest is used to find discriminative patterns. The proposed methods are applied to the well-known and publicly available KTH dataset and Weizman dataset for singleview action recognition and to the IXMAS dataset for multiview action recognition. Furthermore, a comparison of the proposed framework to state-of-the-art methods is given.

show abstract

“…Whilst still an open problem, some have attempted to combine tracking and detection using both strong temporal and spatial priors [5,13,14,15,16,17], and very recently coupling action and pose estimation [18], [19]. However, directly combining the two often results in an untractable optimization problem where the global solution cannot be guaranteed [13].…”

Section: Introductionmentioning

confidence: 99%

Fixing the root node: Efficient tracking and detection of 3D human pose through local solutions

Daubney

Xie

Deng

et al. 2016

Image and Vision Computing

View full text Add to dashboard Cite

A B S T R A C T 3D human pose estimation is a very difficult task. In this paper we propose that this problem can be more easily solved by first finding the solutions to a set of easier sub-problems. These are to locally estimate pose conditioned on a fixed root node state, which defines the global position and orientation of the person. The global solution can then be found using information extracted during this procedure. This approach has two key benefits: The first is that each local solution can be found by modeling the articulated object as a kinematic chain, which has far less degrees of freedom than alternative models. The second is that by using this approach we can represent, or support, a much larger area of the posterior than is currently possible. This allows far more robust algorithms to be implemented since there is far less pressure to prune the search space to free up computational resources. We apply this approach to two problems: The first is single frame monocular 3D pose estimation, where we propose a method to directly extract 3D pose without first extracting any intermediate 2D representation or being dependent on strong spatial prior models. The second is multi-view 3D tracking where we show that using the above technique results in an approach that is far more robust than current approaches, without relying on strong temporal prior models. In both domains we demonstrate the strength and versatility of the proposed method.

show abstract

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Cited by 50 publications

References 31 publications

Motion Binary Patterns for Action Recognition

Motion Binary Patterns for Action Recognition

Computation strategies for volume local binary patterns applied to action recognition

Fixing the root node: Efficient tracking and detection of 3D human pose through local solutions

Contact Info

Product

Resources

About