scholarly journals A Comprehensive Survey of Vision-Based Human Action Recognition Methods

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1005 ◽  
Author(s):  
Hong-Bo Zhang ◽  
Yi-Xiang Zhang ◽  
Bineng Zhong ◽  
Qing Lei ◽  
Lijie Yang ◽  
...  
Keyword(s):  
Action Recognition ◽  
Image Data ◽  
Human Action Recognition ◽  
Human Action ◽  
Feature Representation ◽  
Detection Methods ◽  
Comprehensive Overview ◽  
Survey Paper ◽  
Depth Data ◽  
Comprehensive Survey

Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human–object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.

A Set of New Hermite Kernel Functions in Kernel Extreme Learning Machine and Application in Human Action Recognition

2019 ◽  
Vol 33 (12) ◽  
pp. 1955014 ◽  
Author(s):  
Xueping Liu ◽  
Xingzuo Yue
Keyword(s):  
Extreme Learning Machine ◽  
Action Recognition ◽  
Structural Information ◽  
Image Data ◽  
Human Action Recognition ◽  
Human Action ◽  
Kernel Functions ◽  
Support Vector ◽  
Learning Speed ◽  
Learning Machine

The kernel function has been successfully utilized in the extreme learning machine (ELM) that provides a stabilized and generalized performance and greatly reduces the computational complexity. However, the selection and optimization of the parameters constituting the most common kernel functions are tedious and time-consuming. In this study, a set of new Hermit kernel functions derived from the generalized Hermit polynomials has been proposed. The significant contributions of the proposed kernel include only one parameter selected from a small set of natural numbers; thus, the parameter optimization is greatly facilitated and excessive structural information of the sample data is retained. Consequently, the new kernel functions can be used as optimal alternatives to other common kernel functions for ELM at a rapid learning speed. The experimental results showed that the proposed kernel ELM method tends to have similar or better robustness and generalized performance at a faster learning speed than the other common kernel ELM and support vector machine methods. Consequently, when applied to human action recognition by depth video sequence, the method also achieves excellent performance, demonstrating its time-based advantage on the video image data.

Feature Extraction and Representation for Distributed Multi-View Human Action Recognition

2013 ◽  
Vol 3 (2) ◽  
pp. 145-154 ◽  
Author(s):  
Jiajia Luo ◽  
Wei Wang ◽  
Hairong Qi
Keyword(s):  
Action Recognition ◽  
Approximation Error ◽  
Human Action Recognition ◽  
Human Action ◽  
Base Station ◽  
Feature Representation ◽  
Superior Performance ◽  
Feature Descriptor ◽  
Testing Stage ◽  
New Feature

Multi-view human action recognition has gained a lot of attention in recent years for its superior performance as compared to single view recognition. In this paper, we propose a new framework for the real-time realization of human action recognition in distributed camera networks (DCNs). We first present a new feature descriptor (Mltp-hist) that is tolerant to illumination change, robust in homogeneous region and computationally efficient. Taking advantage of the proposed Mltp-hist, the noninformative 3-D patches generated from the background can be further removed automatically that effectively highlights the foreground patches. Next, a new feature representation method based on sparse coding is presented to generate the histogram representation of local videos to be transmitted to the base station for classification. Due to the sparse representation of extracted features, the approximation error is reduced. Finally, at the base station, a probability model is produced to fuse the information from various views and a class label is assigned accordingly. Compared to the existing algorithms, the proposed framework has three advantages while having less requirements on memory and bandwidth consumption: 1) no preprocessing is required; 2) communication among cameras is unnecessary; and 3) positions and orientations of cameras do not need to be fixed. We further evaluate the proposed framework on the most popular multi-view action dataset IXMAS. Experimental results indicate that our proposed framework repeatedly achieves state-of-the-art results when various numbers of views are tested. In addition, our approach is tolerant to the various combination of views and benefit from introducing more views at the testing stage. Especially, our results are still satisfactory even when large misalignment exists between the training and testing samples.

Human Action Recognition Based on Normalized Interest Points and Super-Interest Points

2014 ◽  
Vol 11 (01) ◽  
pp. 1450005
Author(s):  
Yangyang Wang ◽  
Yibo Li ◽  
Xiaofei Ji
Keyword(s):  
Action Recognition ◽  
Clustering Algorithm ◽  
Three Dimensional ◽  
Temporal Correlation ◽  
Human Action Recognition ◽  
Human Action ◽  
Feature Representation ◽  
Interest Point ◽  
Interest Points ◽  
Active Research

Visual-based human action recognition is currently one of the most active research topics in computer vision. The feature representation directly has a crucial impact on the performance of the recognition. Feature representation based on bag-of-words is popular in current research, but the spatial and temporal relationship among these features is usually discarded. In order to solve this issue, a novel feature representation based on normalized interest points is proposed and utilized to recognize the human actions. The novel representation is called super-interest point. The novelty of the proposed feature is that the spatial-temporal correlation between the interest points and human body can be directly added to the representation without considering scale and location variance of the points by introducing normalized points clustering. The novelty concerns three tasks. First, to solve the diversity of human location and scale, interest points are normalized based on the normalization of the human region. Second, to obtain the spatial-temporal correlation among the interest points, the normalized points with similar spatial and temporal distance are constructed to a super-interest point by using three-dimensional clustering algorithm. Finally, by describing the appearance characteristic of the super-interest points and location relationship among the super-interest points, a new feature representation is gained. The proposed representation formation sets up the relationship among local features and human figure. Experiments on Weizmann, KTH, and UCF sports dataset demonstrate that the proposed feature is effective for human action recognition.

scholarly journals Challenges and Limitations in Human Action Recognition on Unmanned Aerial Vehicles: A Comprehensive Survey

2021 ◽  
Vol 38 (5) ◽  
pp. 1403-1411
Author(s):  
Nashwan Adnan Othman ◽  
Ilhan Aydin
Keyword(s):  
Action Recognition ◽  
Smart Cities ◽  
Large Angle ◽  
Human Action Recognition ◽  
Human Action ◽  
Human Detection ◽  
Long Distance ◽  
Benchmark Datasets ◽  
Comprehensive Survey ◽  
Aerial Vehicle

An Unmanned Aerial Vehicle (UAV), commonly called a drone, is an aircraft without a human pilot aboard. Making UAVs that can accurately discover individuals on the ground is very important for various applications, such as people searches, and surveillance. UAV integration in smart cities is challenging, however, because of problems and concerns such as privacy, safety, and ethical/legal use. Human action recognition-based UAVs can utilize modern technologies. Thus, it is essential for future development of the aforementioned applications. UAV-based human activity recognition is the procedure of classifying photo sequences with action labels. This paper offers a comprehensive study of UAV-based human action recognition techniques. Furthermore, we conduct empirical research studies to assess several factors that might influence the efficiency of human detection and action recognition techniques in UAVs. Benchmark datasets commonly utilized for UAV-based human action recognition are briefly explained. Our findings reveal that the existing human action recognition innovations can identify human actions on UAVs with some limitations in range, altitudes, long-distance, and a large angle of depression.

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 Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review

Micromachines ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 72
Author(s):  
Dengshan Li ◽  
Rujing Wang ◽  
Peng Chen ◽  
Chengjun Xie ◽  
Qiong Zhou ◽  
...  
Keyword(s):  
Object Detection ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Detection Methods ◽  
Video Object ◽  
Action Detection ◽  
Video Frames ◽  
Video Detection ◽  
Human Action Detection

Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames.

scholarly journals Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-20 ◽  
Author(s):  
Yang Liu ◽  
Zhaoyang Lu ◽  
Jing Li ◽  
Chao Yao ◽  
Yanzi Deng
Keyword(s):  
Visible Light ◽  
Transfer Learning ◽  
Action Recognition ◽  
Domain Adaptation ◽  
Human Action Recognition ◽  
Human Action ◽  
Feature Representation ◽  
Support Vector ◽  
Auxiliary Data ◽  
Infrared Data

Recently, infrared human action recognition has attracted increasing attention for it has many advantages over visible light, that is, being robust to illumination change and shadows. However, the infrared action data is limited until now, which degrades the performance of infrared action recognition. Motivated by the idea of transfer learning, an infrared human action recognition framework using auxiliary data from visible light is proposed to solve the problem of limited infrared action data. In the proposed framework, we first construct a novel Cross-Dataset Feature Alignment and Generalization (CDFAG) framework to map the infrared data and visible light data into a common feature space, where Kernel Manifold Alignment (KEMA) and a dual aligned-to-generalized encoders (AGE) model are employed to represent the feature. Then, a support vector machine (SVM) is trained, using both the infrared data and visible light data, and can classify the features derived from infrared data. The proposed method is evaluated on InfAR, which is a publicly available infrared human action dataset. To build up auxiliary data, we set up a novel visible light action dataset XD145. Experimental results show that the proposed method can achieve state-of-the-art performance compared with several transfer learning and domain adaptation methods.

A Co-Training Based Semi-Supervised Human Action Recognition Algorithm

2011 ◽  
Vol 267 ◽  
pp. 1065-1070 ◽  
Author(s):  
He Jin Yuan ◽  
Cui Ru Wang ◽  
Jun Liu
Keyword(s):  
Action Recognition ◽  
Learning Algorithm ◽  
Correlation Coefficients ◽  
Human Action Recognition ◽  
Human Action ◽  
Recognition Algorithm ◽  
Feature Representation ◽  
Motion Energy ◽  
Energy History ◽  
Training Examples

A novel semi-supervised algorithm based on co-training is proposed in this paper. In the method, the motion energy history image are used as the different feature representation of human action; then the co-training based semi-supervised learning algorithm is utilized to predict the category of unlabeled training examples. And the average motion energy and history images are calculated as the recognition model for each category action. When recognition, the observed action is firstly classified through its correlation coefficients to the prior established templates respectively; then its final category is determined according to the consistency between the classification results of motion energy and motion history images. The experiments on Weizmann dataset demonstrate that our method is effective for human action recognition.

Sign in / Sign up

Export Citation Format

Share Document