Monocular Human Action Recognition Utilizing Silhouette Feature Extraction and Skin Color Detection

2012 ◽  
Author(s):  
Junjie Zhang ◽  
Rentao Gu ◽  
Qing Ye ◽  
Yuefeng Ji
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Skin Color ◽  
Human Action Recognition ◽  
Human Action ◽  
Skin Color Detection ◽  
Color Detection

scholarly journals A Comprehensive Survey on Human Action Recognition

2020 ◽  
Vol 9 (2) ◽  
pp. 902-908
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Human Activity ◽  
Human Action Recognition ◽  
Present Situation ◽  
Human Action ◽  
Multiple Parameters ◽  
Multiple Feature ◽  
Comprehensive Survey ◽  
Complete Process

The present The present situation is having many challenges in security and surveillance of Human Action recognition (HAR). HAR has many fields and many techniques to provide modern and technical action implementation. We have studied multiple parameters and techniques used in HAR. We have come out with a list of outcomes and drawbacks of each technique present in different researches. This paper presents the survey on the complete process of recognition of human activity and provides survey on different Motion History Imaging (MHI) methods, model based, multiview and multiple feature extraction based recognition methods.

scholarly journals AR3D: Attention Residual 3D Network for Human Action Recognition

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1656
Author(s):  
Min Dong ◽  
Zhenglin Fang ◽  
Yongfa Li ◽  
Sheng Bi ◽  
Jiangcheng Chen
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Attention Mechanism ◽  
Global Features ◽  
Residual Structure ◽  
3D Network ◽  
Temporal And Spatial ◽  
3D Cnn

At present, in the field of video-based human action recognition, deep neural networks are mainly divided into two branches: the 2D convolutional neural network (CNN) and 3D CNN. However, 2D CNN’s temporal and spatial feature extraction processes are independent of each other, which means that it is easy to ignore the internal connection, affecting the performance of recognition. Although 3D CNN can extract the temporal and spatial features of the video sequence at the same time, the parameters of the 3D model increase exponentially, resulting in the model being difficult to train and transfer. To solve this problem, this article is based on 3D CNN combined with a residual structure and attention mechanism to improve the existing 3D CNN model, and we propose two types of human action recognition models (the Residual 3D Network (R3D) and Attention Residual 3D Network (AR3D)). Firstly, in this article, we propose a shallow feature extraction module and improve the ordinary 3D residual structure, which reduces the parameters and strengthens the extraction of temporal features. Secondly, we explore the application of the attention mechanism in human action recognition and design a 3D spatio-temporal attention mechanism module to strengthen the extraction of global features of human action. Finally, in order to make full use of the residual structure and attention mechanism, an Attention Residual 3D Network (AR3D) is proposed, and its two fusion strategies and corresponding model structure (AR3D_V1, AR3D_V2) are introduced in detail. Experiments show that the fused structure shows different degrees of performance improvement compared to a single structure.

scholarly journals Gymnastics Movement Signs Based on Network Communication and Body Contour Feature Extraction

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Haiyun Wang ◽  
Shujun Hu
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Rapid Development ◽  
Human Action Recognition ◽  
Recognition System ◽  
Human Action ◽  
Extraction Process ◽  
Network Communication ◽  
Body Contour ◽  
Contour Feature

With the rapid development of computer vision technology, human action recognition technology has occupied an important position in this field. The basic human action recognition system is mainly composed of three parts: moving target detection, feature extraction, and human action recognition. In order to understand the action signs of gymnastics, this article uses network communication and contour feature extraction to extract different morphological features during gymnastics. Then, the finite difference algorithm of edge curvature is used to classify different gymnastic actions and analyze and discuss the Gaussian background. A modular method, an improved hybrid Gaussian modeling method, is proposed, which adaptively selects the number of Gaussian distributions. The research results show that, compared with traditional contour extraction, the resolution of gymnastic motion features extracted through network communication and body contour features is clearer, and the increase rate is more than 30%. Moreover, the method proposed in this paper removes noise in the image extraction process, the effect is good, and the athlete’s action marks are very clear, which can achieve the research goal.

scholarly journals Composite Feature Vector Assisted Human Action Recognition through Supervised Learning

2020 ◽  
Vol 8 (6) ◽  
pp. 1556-1566
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Research Direction ◽  
Human Action ◽  
Support Vector ◽  
Complex Wavelet Transform ◽  
Simulation Experiments ◽  
Composite Feature ◽  
New Feature

Human Action Recognition is a key research direction and also a trending topic in several fields like machine learning, computer vision and other fields. The main objective of this research is to recognize the human action in image of video. However, the existing approaches have many limitations like low recognition accuracy and non-robustness. Hence, this paper focused to develop a novel and robust Human Action Recognition framework. In this framework, we proposed a new feature extraction technique based on the Gabor Transform and Dual Tree Complex Wavelet Transform. These two feature extraction techniques helps in the extraction of perfect discriminative features by which the actions present in the image or video are correctly recognized. Later, the proposed framework accomplished the Support Vector Machine algorithm as a classifier. Simulation experiments are conducted over two standard datasets such as KTH and Weizmann. Experimental results reveal that the proposed framework achieves better performance compared to state-of-art recognition methods.

Sign in / Sign up

Export Citation Format

Share Document