A Decision Forest Based Feature Selection Framework for Action Recognition from RGB-Depth Cameras

Negin, Farhood; Özdemir, Firat; Yüksel, Kamer Ali; Akgül, Ceyhun Burak; Erçil, Aytül

doi:10.1007/978-3-642-39094-4_74

Cited by 35 publications

(34 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, it is hard to distinguish actions "Googles and "Had enough which have particular reference objects. The result based on WorkoutSu-10 dataset outperforms the discriminative model RDF [12] even though the number of instances in [12] was 300 fewer than in our experiment.…”

Section: Trained Action Classificationcontrasting

confidence: 53%

“…4: A lexicon based WorkoutSu-10 dataset. Methods MSRC-12 WorkoutSu-10 Cov3DJ [26] 91.70% -RDF [12] 94.03% 98% ELC-KSVD [27] 90.22% -LDA [14] 74.81% 92.27% HGM [18] 66.25% 82.37% Ours 85.86% 98.71% models and results are shown in Table 1; the proposed method can be catgorised as a generative model. In particular, we compare it with classical latent Dirichlet allocation (LDA) model [14] and a hierarchical generative model (HGM) [18] which is a two-layer LDA.…”

Section: Trained Action Classificationmentioning

confidence: 99%

“…The proposed method for learning pose lexicon and action classification is developed and formulated in Section 3. In Section 4, experiments are presented to demonstrate the effectiveness of the proposed method in recognition tasks using MSRC-12 Kinect gesture [11], WorkoutSU-10 exercise [12] datasets and novel actions extracted from the two datasets. Finally, the paper is concluded with remarks in Section 5.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning a pose lexicon for semantic action recognition

Zhou¹,

Li²,

Ogunbona³

2016

2016 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input streams, semantic poses and visual pose candidates, and statistically learns a mapping between them to construct the lexicon. With the learned lexicon, action recognition can be cast as the problem of finding the maximum translation probability of a sequence of semantic poses given a stream of visual pose candidates. Experiments evaluating pre-trained and zero-shot action recognition conducted on MSRC-12 gesture and WorkoutSu-10 exercise datasets were used to verify the efficacy of the proposed method.

show abstract

Section: Trained Action Classificationcontrasting

confidence: 53%

Section: Trained Action Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning a pose lexicon for semantic action recognition

Zhou¹,

Li²,

Ogunbona³

2016

2016 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

show abstract

“…3) Results on MSRC-12 Dataset: Table VII gives the classification rates on MSRC-12 dataset using different [42]) by 0.68%. Due to the loss of temporal information, the recognition rate by RRV-VRB+BoW (92.34%) is slightly inferior to RRV-VRB+LCS+DTW.…”

Section: B Experiments Resultsmentioning

confidence: 99%

RRV: A Spatiotemporal Descriptor for Rigid Body Motion Recognition

Guo

Shao

2018

IEEE Trans. Cybern.

View full text Add to dashboard Cite

The motion behaviors of a rigid body can be characterized by a six degrees of freedom motion trajectory, which contains the 3-D position vectors of a reference point on the rigid body and 3-D rotations of this rigid body over time. This paper devises a rotation and relative velocity (RRV) descriptor by exploring the local translational and rotational invariants of rigid body motion trajectories, which is insensitive to noise, invariant to rigid transformation and scale. The RRV descriptor is then applied to characterize motions of a human body skeleton modeled as articulated interconnections of multiple rigid bodies. To show the descriptive ability of our RRV descriptor, we explore its potentials and applications in different rigid body motion recognition tasks. The experimental results on benchmark datasets demonstrate that our RRV descriptor learning discriminative motion patterns can achieve superior results for various recognition tasks.

show abstract

“…A realistic 3D hand model with 21 different parts was used to create synthetic depth images for decision forest training. In another example, Negin et al used decision forests on kinematic time series for determining the best set of features to use from a depth camera [Negin et al 2013]. These features are then fed into a SVM for gesture recognition.…”

Section: Decision Trees and Forestsmentioning

confidence: 99%

An introduction to 3D gestural interfaces

LaViola

2014

ACM SIGGRAPH 2014 Courses

View full text Add to dashboard Cite

A Decision Forest Based Feature Selection Framework for Action Recognition from RGB-Depth Cameras

Cited by 35 publications

References 7 publications

Learning a pose lexicon for semantic action recognition

Learning a pose lexicon for semantic action recognition

RRV: A Spatiotemporal Descriptor for Rigid Body Motion Recognition

An introduction to 3D gestural interfaces

Contact Info

Product

Resources

About