Silhouette-based human action recognition using sequences of key poses

Chaaraoui, Alexandros André; Climent-Pérez, Pau; Flórez-Revuelta, Francisco

doi:10.1016/j.patrec.2013.01.021

Cited by 160 publications

(115 citation statements)

References 35 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…As has been shown in [5,6], this learning method handles multiple views successfully. In the present work, the skeleton and the silhouette could be considered as different views.…”

Section: Classification Methods Based On Bag Of Key Posesmentioning

confidence: 74%

See 1 more Smart Citation

Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices

Chaaraoui

Padilla-López

Flórez-Revuelta

2013

2013 IEEE International Conference on Computer Vision Workshops

Self Cite

View full text Add to dashboard Cite

“…As has been shown in [5,6], this learning method handles multiple views successfully. In the present work, the skeleton and the silhouette could be considered as different views.…”

Section: Classification Methods Based On Bag Of Key Posesmentioning

confidence: 74%

“…As learning algorithm we employ a method based on bag of key poses [5,6]. Similar to the bag-of-words-model, first, a codebook -called bag of key poses -is obtained using the -means clustering algorithm.…”

Section: Classification Methods Based On Bag Of Key Posesmentioning

confidence: 99%

Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices

Chaaraoui

Padilla-López

Flórez-Revuelta

2013

2013 IEEE International Conference on Computer Vision Workshops

Self Cite

View full text Add to dashboard Cite

“…Values within the interval [4,8,16,32, 64] have been investigated, and the obtained results for cross-subject and cross-view evaluations are shown in Table 1. Cross-subject evaluation is more challenging than the cross-view one, and the best results are represented by a large number of clusters.…”

Section: Resultsmentioning

confidence: 99%

“…The most informative postures, i.e. keyposes, are learned through unsupervised clustering generating a bag of key poses model [16]. An action is modeled as histograms of key poses, with the adoption of a temporal pyramid to keep the distribution of the key-poses within the action.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of a skeleton-based method for human activity recognition on a large-scale RGB-D dataset

Cippitelli¹,

Gambi²,

Spinsante³

et al. 2016

2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)

View full text Add to dashboard Cite

Low cost RGB-D sensors have been used extensively in the field of Human Action Recognition. The availability of skeleton joints simplifies the process of feature extraction from depth or RGB frames, and this feature fostered the development of activity recognition algorithms using skeletons as input data. This work evaluates the performance of a skeleton-based algorithm for Human Action Recognition on a large-scale dataset. The algorithm exploits the bag of key poses method, where a sequence of skeleton features is represented as a set of key poses. A temporal pyramid is adopted to model the temporal structure of the key poses, represented using histograms. Finally, a multi-class SVM performs the classification task, obtaining promising results on the large-scale NTU RGB+D dataset.

show abstract

“…Based on the method published in [16], the most representative feature representations involved in each action class (the so-called key poses) are obtained based on a clustering algorithm, and a bag-of-key-poses model is generated. In order to complement this spatial information related to the human posture, temporal cues are considered by means of modelling the evolution of the human silhouettes along the action sequences.…”

Section: Human Action Recognition Methodsmentioning

confidence: 99%

Continuous Human Action Recognition in Ambient Assisted Living Scenarios

Chaaraoui

Flórez-Revuelta²

2015

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Self Cite

View full text Add to dashboard Cite

Abstract. Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.

show abstract

Silhouette-based human action recognition using sequences of key poses

Cited by 160 publications

References 35 publications

Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices

Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices

Evaluation of a skeleton-based method for human activity recognition on a large-scale RGB-D dataset

Continuous Human Action Recognition in Ambient Assisted Living Scenarios

Contact Info

Product

Resources

About