Coupled hidden conditional random fields for RGB-D human action recognition

Liu, An-An; Nie, Weizhi; Su, Yuting; Ma, Li; Hao, Tong; Yang, Zhaoxuan

doi:10.1016/j.sigpro.2014.08.038

Cited by 77 publications

(34 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this article, the proposed method is compared with the method of Xia et al [44] which has received considerable attention in literature [2], [13], [9], [46] and has been used for comparison in very recent methods [43], [3], [38], [18], [23]. Note that all the above methods has experimented with datasets created using an older version of Kinect sensor and not containing involuntary actions.…”

Section: Action Recognition and Comparisonmentioning

confidence: 99%

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

2018

View full text Add to dashboard Cite

Abstract-Human action recognition has been one of the most active fields of research in computer vision over the last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of data. Development of depth sensors has made it feasible to track positions of human body joints over time. This paper proposes a novel method for action recognition which uses temporal 3D skeletal Kinect data. This method introduces the definition of body states and then every action is modeled as a sequence of these states. The learning stage uses Fisher Linear Discriminant Analysis (LDA) to construct discriminant feature space for discriminating the body states. Moreover, this paper suggests the use of the Mahalonobis distance as an appropriate distance metric for the classification of the states of involuntary actions. Hidden Markov Model (HMM) is then used to model the temporal transition between the body states in each action. According to the results, this method significantly outperforms other popular methods, with recognition (recall) rate of 88.64% for eight different actions and up to 96.18% for classifying the class of all fall actions versus normal actions.Index Terms-Human action recognition, involuntary action recognition, Fisher, linear discriminant analysis (LDA), kinect, 3D skeleton data, hidden markov model (HMM).

show abstract

Section: Action Recognition and Comparisonmentioning

confidence: 99%

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

2018

View full text Add to dashboard Cite

show abstract

“…space : In this paper [4] recognized that the multi-level modality and perspective to representation of the joints and the 3D action recognition. In certain the RGB sequences and the depth images, construct the best differences motion history image and after recognize many perspective calculation for getting motion processes, then these histograms extract the gradient from the each calculation to explain the target motion, finally multiperspective and the multi projections joint represent, the recognition and discriminant model proposed challenges for human activity recognition.…”

Section: B Activity Recognition Model With Joint Representation In 3dmentioning

confidence: 99%

“…Visual surveillance technique is used for identifying packages of human actions [2]. Researchers used different techniques to recognize human actions such as hierarchical probabilistic approach [3], multi-modality representation of joints [4], HDP-HMM which is multi-level [5], Eigen-joint based method [8] using NBNN classifier. All the mentioned work is not reliable for real world application.…”

mentioning

confidence: 99%

Human Activity Recognition in Real-Times Environments using Skeleton Joints

Kumar¹,

Kumar²,

Singh³

et al. 2016

IJIMAI

View full text Add to dashboard Cite

-In this research work, we proposed a most effective noble approach for Human activity recognition in real-time environments. We recognize several distinct dynamic human activity actions using kinect. A 3D skeleton data is processed from real-time video gesture to sequence of frames and getter skeleton joints (Energy Joints, orientation, rotations of joint angles) from selected setof frames. We are using joint angle and orientations, rotations information from Kinect therefore less computation required. However, after extracting the set of frames we implemented several classification techniques Principal Component Analysis (PCA) with several distance based classifiers and Artificial Neural Network (ANN) respectively with some variants for classify our all different gesture models. However, we conclude that use very less number of frame (10-15%) for train our system efficiently from the entire set of gesture frames. Moreover, after successfully completion of our classification methods we clinch an excellent overall accuracy 94%, 96% and 98% respectively. We finally observe that our proposed system is more useful than comparing to other existing system, therefore our model is best suitable for real-time application such as in video games for player action/gesture recognition.

show abstract

“…Some leading representations include learned geometrical models of the human body parts [13], space-time pattern templates [6,14], shape or form features [15][16][17], sequential model [18][19][20][21][22], interest point based representations [23,5], and motion/optical flow patterns [24].…”

Section: Related Workmentioning

confidence: 99%

Human Action Recognition Bases on Local Action Attributes

Zhang¹,

Lin²,

Nie³

et al. 2015

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-Human action recognition received many interest in the computer vision community.Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

show abstract

Coupled hidden conditional random fields for RGB-D human action recognition

Cited by 77 publications

References 52 publications

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

Human Activity Recognition in Real-Times Environments using Skeleton Joints

Human Action Recognition Bases on Local Action Attributes

Contact Info

Product

Resources

About