A Survey on Model Based Approaches for 2D and 3D Visual Human Pose Recovery

Perez-Sala, Xavier; Escalera, Sérgio; Ángulo, Cecilio; Gonzàlez, Jordi

doi:10.3390/s140304189

Cited by 57 publications

(39 citation statements)

References 82 publications

(157 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to show the suitability of QRkit for these problems, we have implemented a simple 2D optimization that fits an ellipse to a set of 2D points. It can be considered a simplification of surface fitting tasks such as human body tracking [33] or hand tracking [37,38], which have recently received a great deal of interest. The structure of the Jacobian is depicted in Figure 5(a).…”

Section: Methodsmentioning

confidence: 99%

QRkit: Sparse, Composable QR Decompositions for Efficient and Stable Solutions to Problems in Computer Vision

Svoboda

Cashman

Fitzgibbon

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Embedded computer vision applications increasingly require the speed and power benefits of single-precision (32 bit) floating point. However, applications which make use of Levenberg-like optimization can lose significant accuracy when reducing to single precision, sometimes unrecoverably so. This accuracy can be regained using solvers based on QR rather than Cholesky decomposition, but the absence of sparse QR solvers for common sparsity patterns found in computer vision means that many applications cannot benefit. We introduce an open-source suite of solvers for Eigen, which efficiently compute the QR decomposition for matrices with some common sparsity patterns (block diagonal, horizontal and vertical concatenation, and banded). For problems with very particular sparsity structures, these elements can be composed together in 'kit' form, hence the name QRkit. We apply our methods to several computer vision problems, showing competitive performance and suitability especially in single precision arithmetic.

show abstract

Section: Methodsmentioning

confidence: 99%

QRkit: Sparse, Composable QR Decompositions for Efficient and Stable Solutions to Problems in Computer Vision

Svoboda

Cashman

Fitzgibbon

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Other recent surveys were carried out on specific methodologies.For example, the survey from Lepetit et al [19] and the survey from Perez-Sala et al [20] both study model-based approaches, which employ human body knowledge such as the human body’s appearance and structure for the enhancement of human pose estimation. There are also surveys dedicated to human motion analysis where motion information is prerequisite [15,16,21,22].…”

Section: Introductionmentioning

confidence: 99%

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Gong

Zhang

Gonzàlez

et al. 2016

Sensors

Self Cite

130

View full text Add to dashboard Cite

Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approaches or human motion analysis, etc. As far as we know, an overall review of this problem domain has yet to be provided. Furthermore, recent advancements based on deep learning have brought novel algorithms for this problem. In this paper, a comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements. Based on one standard pipeline for the solution of computer vision problems, this survey splits the problem into several modules: feature extraction and description, human body models, and modeling methods. Problem modeling methods are approached based on two means of categorization in this survey. One way to categorize includes top-down and bottom-up methods, and another way includes generative and discriminative methods. Considering the fact that one direct application of human pose estimation is to provide initialization for automatic video surveillance, there are additional sections for motion-related methods in all modules: motion features, motion models, and motion-based methods. Finally, the paper also collects 26 publicly available data sets for validation and provides error measurement methods that are frequently used.

show abstract

“…Perez-Sala et al [52] reviewed the state-of-the-art for visionbased motion capture. It provided an overview of the methods that describe appearance, resolve viewpoints, spatial models, temporal models, and human behaviour.…”

Section: Previous Surveysmentioning

confidence: 99%

Wearable Sensing for Solid Biomechanics

Wong

Zhang

et al. 2015

IEEE Sensors J.

View full text Add to dashboard Cite

Abstract-Understanding the solid biomechanics of the human body is important to the study of structure and function of the body, which can have a range of applications in healthcare, sport, wellbeing, and workflow analysis. Conventional laboratorybased biomechanical analysis systems and observation-based tests are only designed to capture brief snapshots of the mechanics of movement. With recent developments in wearable sensing technologies, biomechanical analysis can be conducted in less constrained environments, thus allowing continuous monitoring and analysis beyond laboratory settings. In this paper, we review the current research in wearable sensing technologies for biomechanical analysis, focusing upon sensing and analytics that enable continuous, long-term monitoring of kinematics and kinetics in a free-living environment. The main technical challenges, including measurement drift, external interferences, nonlinear sensor properties, sensor placement, and muscle variations that can affect the accuracy and robustness of existing methods, and different methods for reducing the impact of these sources of errors are described in this review. Recent developments in motion estimation in kinematics, mobile force sensing in kinematics, sensor reduction for electromyography, as well as the future direction of sensing for biomechanics are also discussed.

show abstract

A Survey on Model Based Approaches for 2D and 3D Visual Human Pose Recovery

Cited by 57 publications

References 82 publications

QRkit: Sparse, Composable QR Decompositions for Efficient and Stable Solutions to Problems in Computer Vision

QRkit: Sparse, Composable QR Decompositions for Efficient and Stable Solutions to Problems in Computer Vision

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Wearable Sensing for Solid Biomechanics

Contact Info

Product

Resources

About