Hierarchical 3D kernel descriptors for action recognition using depth sequences

Kong, Yu; Satarboroujeni, Behnam; Fu, Yun

doi:10.1109/fg.2015.7163084

Cited by 13 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 13 illustrates the confusion matrix of this setup. [23] 86.5 DMM-HOG [18] 88.7 HON4D [35] 88.9 DSTIP [19] 89.3 Moving Pose [43] 91.7 Actionlet Ensemble [46] 88.2 Skeletons Lie group [47] 89.5 Skeletal Quads [44] 89.9 Super Normal Vector [12] 93.1 2D-CNN [51] 91.2 3D-CNN [51] 86.1 HOG3D+LLC [37] 90.9 Hierarchical 3D Kernel [38] 92.7 DMM-LBP-DF [26] 91.9 DMM-LBP-DF [26] 93.0 HP-DMM-CNN [66] 92.3 BoA [66] 86.9 Our Method (GMHI + GSHI) 94.5…”

Section: Second Experimental Setup and Resultsmentioning

confidence: 99%

3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images

Bulbul¹,

Islam

Ali

2019

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, we present an approach for identification of actions within depth action videos. First, we process the video to get motion history images (MHIs) and static history images (SHIs) corresponding to an action video based on the use of 3D Motion Trail Model (3DMTM). We then characterize the action video by extracting the Gradient Local Auto-Correlations (GLAC) features from the SHIs and the MHIs. The two sets of features i.e., GLAC features from MHIs and GLAC features from SHIs are concatenated to obtain a representation vector for action. Finally, we perform the classification on all the action samples by using the l2-regularized Collaborative Representation Classifier (l2-CRC) to recognize different human actions in an effective way. We perform evaluation of the proposed method on three action datasets, MSR-Action3D, DHA and UTD-MHAD. Through experimental results, we observe that the proposed method performs superior to other approaches.

show abstract

Section: Second Experimental Setup and Resultsmentioning

confidence: 99%

3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images

Bulbul¹,

Islam

Ali

2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Gestures can also be modelled as rigid 3D patterns (Ke et al, 2005), from which features can be extracted using 3D extensions of rectangle filters (Viola and Jones, 2001). The work of (Kong et al, 2015) uses pixel-level attributes in a hierarchical architecture of 3D kernel descriptors, and efficient match kernel is used to recognize gestures from depth data.…”

Section: From Body Part Detection To Holistic Pattern Detectionmentioning

confidence: 99%

Challenges in Multi-modal Gesture Recognition

Escalera

Athitsos

Guyon

2017

The Springer Series on Challenges in Machine Learning

View full text Add to dashboard Cite

This paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition 2011-2015. We began right at the start of the Kinect T M revolution when inexpensive infrared cameras providing image depth recordings became available. We published papers using this technology and other more conventional methods, including regular video cameras, to record data, thus providing a good overview of uses of machine learning and computer vision using multimodal data in this area of application. Notably, we organized a series of challenges and made available several datasets we recorded for that purpose, including tens of thousands of videos, which are available to conduct further research. We also overview recent state of the art works on gesture recognition based on a proposed taxonomy for gesture recognition, discussing challenges and future lines of research.

show abstract

“…This work is an extension of our previous paper [1]. The extensions are: (a) Type of data, here we use both RGB and depth data while in [1] we just focus on depth data.…”

Section: E-mail Address: Yukong@eceneuedu (Y Kong)mentioning

confidence: 99%

“…The extensions are: (a) Type of data, here we use both RGB and depth data while in [1] we just focus on depth data. (b) Method used in middle layer of framework.…”

Section: E-mail Address: Yukong@eceneuedu (Y Kong)mentioning

confidence: 99%

See 1 more Smart Citation

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

Kong

Satarboroujeni

2016

Computer Vision and Image Understanding

Self Cite

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

Hierarchical 3D kernel descriptors for action recognition using depth sequences

Cited by 13 publications

References 12 publications

3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images

3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images

Challenges in Multi-modal Gesture Recognition

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

Contact Info

Product

Resources

About