Human action recognition based on estimated weak poses

Gong, Wenjuan; Gonzàlez, Jordi; Roca, Francesc

doi:10.1186/1687-6180-2012-162

Cited by 8 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, in Relevance Vector Machines (RVMs), which are a Bayesian kernel method, the most decisive training examples are picked as relevance vectors [32,123,124,125]. Non-linear mapping models are also utilized, for example, Gaussian Processes [26]. …”

Section: Methodologiesmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Methodologiesmentioning

confidence: 99%

“…Although algorithms and techniques used in human action recognition are different from those used in human pose estimation, recognition results of these two are sometimes combined within a framework to boost the performance of a single task [23,24,25,26]. Surveys on action recognition include [27,28,29,30].…”

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

show abstract

“…For learning and extracting key poses, different methods including K-means and local maximal or minimal energy are often used, such as the works reported in [9], [10], [11]. Those methods can extract common poses shared by various action types and thus cause confusion for the classification phase.…”

Section: Related Workmentioning

confidence: 99%

Discriminative Key Pose Extraction Using Extended LC-KSVD for Action Recognition

Zhou

Zhang

et al. 2014

2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

This paper presents a method for extracting discriminative key poses for skeleton-based action recognition. Poses are represented by normalized joint locations, velocities and accelerations of skeleton joints. An extended label consistent K-SVD (ELC-KSVD) algorithm is proposed for learning the common and action-specific dictionaries. Discriminative key poses are represented by the atoms of the action-specific dictionaries. With the specific dictionaries, sparse codes are obtained for representing action instances through max pooling and temporal pyramid. A SVM classifier is trained for action recognition. The proposed method was evaluated on the MSRC-12 gesture and MSR-Action 3D datasets. Experimental results have shown that the proposed method is effective in extracting discriminative key poses.

show abstract

“…An image scan in [32] provides a contour signature as a matrix involving the contour polar coordinates. An equivalent descriptor called shape context descriptor is presented in [33] as a compact human pose representation. The processed image is divided into different ranges of radial and angle coordinates.…”

Section: Characterization Of the Hand: A Further Investigation On A Smentioning

confidence: 99%

Hand posture recognition using jointly optical flow and dimensionality reduction

Boughnim

Marot

Fossati

et al. 2013

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Hand posture recognition is generally addressed by using either YC b C r (luminance and chrominance components) or HSV (hue, saturation, value) mappings which assume that a hand can be distinguished from the background from some colorfulness and luminance properties. This can hardly be used when a dark hand, or a hand of any color, is under study. In addition, existing recognition processes rely on descriptors or geometric shapes which can be reliable; this comes at the expense of an increased computational complexity. To cope with these drawbacks, this paper proposes a four-step method recognition technique consisting of (i) a pyramidal optical flow for the detection of large movements and hence determine the region of interest containing the expected hand, (ii) a preprocessing step to compute the hand contour while ensuring geometric and illumination invariance, (iii) an image scanning method providing a signature which characterizes non-star-shaped contours with a one-pixel precision, and (iv) a posture classification method where a sphericity criterion preselects a set of candidate postures, principal component analysis reduces the dimensionality of the data, and Mahalanobis distance is used as a criterion to identify the hand posture in any test image. The proposed technique has been assessed in terms of its performances including the computational complexity using both visual and statistical results.

show abstract

Human action recognition based on estimated weak poses

Cited by 8 publications

References 39 publications

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Discriminative Key Pose Extraction Using Extended LC-KSVD for Action Recognition

Hand posture recognition using jointly optical flow and dimensionality reduction

Contact Info

Product

Resources

About