Joint Angles Similarities and HOG2 for Action Recognition

Ohn-Bar, Eshed; Trivedi, Mohan M.

doi:10.1109/cvprw.2013.76

Cited by 263 publications

(172 citation statements)

References 13 publications

Supporting

Mentioning

160

Contrasting

Unclassified

Order By: Relevance

“…• cross-subject evaluation: the sequences performed by 20 actors are used as training and the others as testing data. The subjects that have to be used as training are: Table 1.…”

Section: Resultsmentioning

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

“…• cross-subject evaluation: the sequences performed by 20 actors are used as training and the others as testing data. The subjects that have to be used as training are: Table 1.…”

Section: Resultsmentioning

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

show abstract

“…This approach extracts low-level features from skeletal data, such as pairwise joint displacements, and uses Principal Component Analysis (PCA) to perform dimension reduction. Many other existing human representations are also based on low-level skeleton-based features [211,128,148,143,132,126,149,150,164,167,168,127,172] without modeling the hierarchy of the data. Several multi-layer techniques were also implemented to create skeleton-based human representations from low-level features.…”

Section: Representations Based On Low-level Featuresmentioning

confidence: 99%

Space-time representation of people based on 3D skeletal data: A review

Han

Reily

Hoff

et al. 2017

Computer Vision and Image Understanding

274

192

View full text Add to dashboard Cite

Spatiotemporal human representation based on 3D visual perception data is a rapidly growing research area. Representations can be broadly categorized into two groups, depending on whether they use RGB-D information or 3D skeleton data. Recently, skeletonbased human representations have been intensively studied and kept attracting an increasing attention, due to their robustness to variations of viewpoint, human body scale and motion speed as well as the realtime, online performance. This paper presents a comprehensive survey of existing space-time representations of people based on 3D skeletal data, and provides an informative categorization and analysis of these methods from the perspectives, including information modality, representation encoding, structure and transition, and feature engineering. We also provide a brief overview of skeleton acquisition devices and construction methods, enlist a number of benchmark datasets with skeleton data, and discuss potential future research directions.

show abstract

“…Our approach differs from local feature-based approaches [25,44] and skeleton-based approaches [43,45]. We learn hierarchical kernel descriptors, which are essentially nonlinear feature mappings.…”

Section: Related Workmentioning

confidence: 99%

“…Our approach is capable of fusing RGB and depth data for classification while methods in [25,44] can only be applied to depth data. Compared with skeleton data-based approaches [43,45], we propose an elegant framework that is capable of fusing RGB and depth data while it is not clear how the evolutionary algorithm [43] can fuse various modality data. We achieve comparable results with [44,45] and outperform [43] on MSR-Action3D dataset as RGB videos are not provided in this dataset.…”

Section: Related Workmentioning

confidence: 99%

Learning hierarchical 3D kernel descriptors for RGB-D action recognition

Kong

Satarboroujeni

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

a b s t r a c tHuman action recognition is an important and challenging task due to intra-class variation and complexity of actions which is caused by diverse style and duration in performed action. Previous works mostly concentrate on either depth or RGB data to build an understanding about the shape and movement cues in videos but fail to simultaneously utilize rich information in both channels. In this paper we study the problem of RGB-D action recognition from both RGB and depth sequences using kernel descriptors. Kernel descriptors provide an unified and elegant framework to turn pixel-level attributes into descriptive information about the performed actions in video. We show how using simple kernel descriptors over pixel attributes in video sequences achieves a great success compared to the state-of-the-art complex methods. Following the success of kernel descriptors (Bo, et al., 2010) on object recognition task, we put forward the claim that using 3D kernel descriptors could be an effective way to project the low-level features on 3D patches into a powerful structure which can effectively describe the scene. We build our system upon the 3D Gradient kernel descriptor and construct a hierarchical framework by employing efficient match kernel (EMK) (Bo, and Sminchisescu, 2009) and hierarchical kernel descriptors (HKD) as higher levels to abstract the mid-level features for classification. Through extensive experiments we demonstrate the proposed approach achieves superior performance on four standard RGB-D sequences benchmarks.

show abstract

Joint Angles Similarities and HOG2 for Action Recognition

Cited by 263 publications

References 13 publications

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

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

Space-time representation of people based on 3D skeletal data: A review

Learning hierarchical 3D kernel descriptors for RGB-D action recognition

Contact Info

Product

Resources

About