Human Action Recognition Utilizing Variations in Skeleton Dimensions

Moussa, Mona M.; Hemayed, Elsayed E.; Nemr, Heba A. El; Fayek, Magda B.

doi:10.1007/s13369-017-2694-9

Cited by 12 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is the unit orthogonal vector generated in the linear subspace, which corresponds to the twodimensional hyperplane at the same time, and the definite feature frame in the video sequence is denoted as a i1 , a i2 ⋯ , a ir . The more inconsistent the recognition result is with the original action, the more dimensions are required [19].…”

Section: Action Segmentation Modelmentioning

confidence: 99%

Footprint Extraction and Sports Dance Action Recognition Method Based on Artificial Intelligence Distributed Edge Computing

Hu¹,

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Distributed edge computing technology for artificial intelligence refers to an emerging technology that integrates network core processing functions, computing functions, storage functions, etc. into one end source closer to objects or data on the basis of an open platform to optimize service quality. In this paper, distributed edge computing technology is applied to footprint extraction and sports dance action recognition, aimed at improving the recognition efficiency and recognition quality. Firstly, the overview of edge computing theory is introduced; these include edge computing concepts, edge computing characteristics, and edge computing platforms; and then, the classification of action recognition technology is described. Finally, the edge computing recognition technology and traditional recognition technology are compared and tested. The experimental results show that the average accuracy of edge computing technology for footprint extraction can reach 98.98, and the average recognition rate of sports dance movements can reach 80.21%, which verifies its practicability.

show abstract

Section: Action Segmentation Modelmentioning

confidence: 99%

Footprint Extraction and Sports Dance Action Recognition Method Based on Artificial Intelligence Distributed Edge Computing

Hu¹,

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Because the scene of criminal investigation is easy to destroy and due to other reasons, only one part of the identity feature is often collected. At this time, multimodal identification can provide more professional retrieval [24]. (2) Finance: as the financial field involves a lot of property privacy, it is particularly important to ensure identity authentication [25].…”

Section: Behavior Detectionmentioning

confidence: 99%

Human Motion Recognition Based on Multimodal Characteristics of Learning Quality in Football Scene

Gao

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The task of human motion recognition based on video is widely concerned, and its research results have been widely used in intelligent human-computer interaction, virtual reality, intelligent monitoring, security, multimedia content analysis, etc. The purpose of this study is to explore the human action recognition in the football scene combined with learning quality related multimodal features. The method used in this study is to select BN-Inception as the underlying feature extraction network and use uncontrolled environment and real world to capture datasets UCFl01 and HMDB51, and pretraining is carried out on the ImageNet dataset. The spatial depth convolution network takes image frame as input, and the temporal depth convolution network takes stacked optical flow as input to carry out human action multimodal identification. In the results of multimodal feature fusion, the accuracy of UCFl01 dataset is generally high, all of which are over 80%, and the highest is 95.2%, while the accuracy of HMDB51 dataset is about 70%, and the lowest is only 56.3%. It can be concluded that the method of this study has higher accuracy and better effect in multimodal feature acquisition, and the accuracy of single-mode feature recognition is significantly lower than that of multimodal feature recognition. It provides an effective method for the multimodal feature of human motion recognition in the scene of football or sports.

show abstract

“…An abundance of research has been done on human action recognition based on conventional machine learning techniques, such as K Nearest Neighbor (KNN) classifiers [34,35], Support Vector Machine (SVM) [18,[35][36][37][38][39][40], Hidden Markov Models (HMM) [41,42], clustering strategies [42][43][44], and Bayesian learning [45,46]. Most of these techniques first extract hand-crafted features [34,36,38,39,46,47] and then apply a learning algorithm in order to classify the action. Wu et al,in [34], propose action descriptors with a sliding temporal window of size 5, which includes joint position, angular velocity, and angular acceleration.…”

Section: Conventional Learning-based Approachesmentioning

confidence: 99%

“…Linear Discriminant Analysis (LDA) is employed to reduce feature dimensionality, the k-means clustering algorithm is utilized to generate codewords, and Hidden Markov Models are deployed for action recognition on the basis of the codewords. Moussa et al [38] propose a methodology that depends on high-level features that carry information about changes in human body dimensions during the performance of the action. Their proposed system comprises four stages: the extraction of skeleton details, parameter calculation, parameter encoding, and, finally, a classification module, in which a multi-class linear SVM classifier is employed.…”

Section: Conventional Learning-based Approachesmentioning

confidence: 99%

Keys for Action: An Efficient Keyframe-Based Approach for 3D Action Recognition Using a Deep Neural Network

Yasin

Hussain

Weber

2020

Sensors

View full text Add to dashboard Cite

In this paper, we propose a novel and efficient framework for 3D action recognition using a deep learning architecture. First, we develop a 3D normalized pose space that consists of only 3D normalized poses, which are generated by discarding translation and orientation information. From these poses, we extract joint features and employ them further in a Deep Neural Network (DNN) in order to learn the action model. The architecture of our DNN consists of two hidden layers with the sigmoid activation function and an output layer with the softmax function. Furthermore, we propose a keyframe extraction methodology through which, from a motion sequence of 3D frames, we efficiently extract the keyframes that contribute substantially to the performance of the action. In this way, we eliminate redundant frames and reduce the length of the motion. More precisely, we ultimately summarize the motion sequence, while preserving the original motion semantics. We only consider the remaining essential informative frames in the process of action recognition, and the proposed pipeline is sufficiently fast and robust as a result. Finally, we evaluate our proposed framework intensively on publicly available benchmark Motion Capture (MoCap) datasets, namely HDM05 and CMU. From our experiments, we reveal that our proposed scheme significantly outperforms other state-of-the-art approaches.2 of 24 inertial sensor-and accelerometer-based systems [7,8]; and hybrid systems [9]. As another domain, 3D motions are reconstructed from different sources, e.g., reconstruction from video or image data [10][11][12][13][14] and reconstruction from accelerometer data [15,16]. In short, motions captured or generated by different sources of means are abundant and contain a lot of hidden knowledge and information that may be exploited further in different types of applications, such as those mentioned above.There exists a variety of action classification methods that are based on different input data; the input may be in the form of simple RGB videos or spatiotemporal joint trajectories acquired by means of a sensor system (e.g., mechanical, magnetic, optic, inertial, non-optic wearable sensors and RGB-D sensors, such as Kinect) or an estimated 3D skeleton from image data or a hybrid system. Although a lot of research has been done in the domain of action recognition, there still exist numerous challenges, such as viewpoint variations, different human body sizes and appearances, and illumination factors that may influence the efficiency and performance of existing algorithms [17]. Moreover, each performing actor has his or her own way and style of executing the same action. The actions may also have many variations in terms of speed and length. In addition to these inter-class variations, extensive intra-class variations make the task more difficult. For example, it is not an easy task to differentiate between jogging and running, walkForward and walkBackward, sitDownChair and sitDownFloor, standUpSitChair and standUpSitFloor, rotateArmBackward and rota...

show abstract

Human Action Recognition Utilizing Variations in Skeleton Dimensions

Cited by 12 publications

References 21 publications

Footprint Extraction and Sports Dance Action Recognition Method Based on Artificial Intelligence Distributed Edge Computing

Footprint Extraction and Sports Dance Action Recognition Method Based on Artificial Intelligence Distributed Edge Computing

Human Motion Recognition Based on Multimodal Characteristics of Learning Quality in Football Scene

Keys for Action: An Efficient Keyframe-Based Approach for 3D Action Recognition Using a Deep Neural Network

Contact Info

Product

Resources

About