1
|
Husni E, Prayoga GA, Tamba JD, Retnowati Y, Fauzandi FI, Yusuf R, Yahya BN. Microclimate Investigation of Vehicular Traffic on The Urban Heat Island Through IoT-Based Device. Heliyon 2022; 8:e11739. [DOI: 10.1016/j.heliyon.2022.e11739] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2022] [Revised: 04/10/2022] [Accepted: 11/10/2022] [Indexed: 11/18/2022] Open
|
2
|
Wang W. Research on Athlete Detection Method Based on Visual Image and Artificial Intelligence System. Comput Intell Neurosci 2022; 2022:2418367. [PMID: 36210969 PMCID: PMC9536965 DOI: 10.1155/2022/2418367] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/21/2022] [Accepted: 08/22/2022] [Indexed: 11/30/2022]
Abstract
Pedestrian detection and tracking based on computer vision has gradually become an international pattern recognition, which is one of the most active research topics in the field of computer vision and artificial intelligence. Using the theoretical results in the field of pattern recognition and computer vision technology, we are committed to detect and track pedestrians from video sequences. In addition to computer vision-based passer-by detection and tracking technology as the key, in the advanced computer vision action and analysis, it has a direct impact on the accuracy and robustness of its understanding. We analyzed various targets, such as subsequent recognition motion and pedestrian motion, and described them as high-level application processing, such as action understanding. In addition, because of the unique texture of human clothes compared with the surrounding natural landscape, they are highly "prominent" from the perspective of human visual system, and they are particularly prominent in the peripheral part of human contact with the background. In this paper, a binary function based on importance is proposed. As the space representation of image itself is not sensitive to noise and local signal, space representation is used. In addition, as an observation model, it can reduce the adverse effects of background noise and local noise on the tracking algorithm. Through the function block tracking, the pedestrian's body can be tracked in detail. At the same time, the color band learning method is used to update the target template online to deal with the changes of target appearance caused by sunshine, pedestrian posture, and other factors. According to the experimental results, even if the appearance and posture of pedestrians change greatly, it has a stable tracking effect.
Collapse
Affiliation(s)
- Weiyi Wang
- Baotou Medical College, Baotou, Neimenggu, China
| |
Collapse
|
3
|
Ma Y, Zhi Z, Che H. Extraction and Analysis of Foot Bone Shape Features Based on Deep Learning. Computational and Mathematical Methods in Medicine 2022; 2022:1-11. [PMID: 35991148 PMCID: PMC9385372 DOI: 10.1155/2022/2372160] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Revised: 07/14/2022] [Accepted: 07/21/2022] [Indexed: 11/17/2022]
Abstract
With the rapid development of artificial intelligence, more and more researchers and research institutions begin to pay attention to the bone feature recognition field. Human bone movement is very complex, and human bone shape recognition technology can be widely used in medical treatment, sports, and other fields. At present, there are mainly two kinds of methods for extracting the shape features of human foot bone based on optical image acquisition technology and sensor information perception technology. However, due to the interference factors such as target posture change, camera shake, and individual behavior differences, it is still a very challenging task to design a robust algorithm for extraction and analysis of foot bone shape features. In recent years, convolutional neural network- (CNN-) based foot contour feature recognition methods emerge one after another and have made breakthrough progress. How to use and how to fully explore the potential relationship of various characteristics contained in the foot bone data and how to enhance the robustness of view changes and other aspects need to be further studied. In this context, this paper proposed an improved CNN model, which not only has the capability of deep feature extraction of the CNN model but also can obtain the optimal model parameters with the combination of particle swarm optimization algorithm. The effectiveness of the proposed method in the extraction and analysis of foot bone shape features is verified in the simulation experiment.
Collapse
|
4
|
Zhang L. Improved Graph Convolutional Neural Network for Dance Tracking and Pose Estimation. Comput Intell Neurosci 2022; 2022:7133491. [PMID: 35795760 DOI: 10.1155/2022/7133491] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/30/2022] [Accepted: 05/31/2022] [Indexed: 12/03/2022]
Abstract
Movement recognition technology is widely used in various practical application scenarios, but there are few researches on dance movement recognition at present. Aiming at the problem of low accuracy of dance movement recognition due to complex pose changes in dance movements, this paper designed an improved graph convolutional neural network algorithm for dance tracking and pose estimation. In this method, the spatial and temporal characteristics of motion are extracted from the skeleton joint diagram of human body. Then, GCN (graph convolutional neural) is used to extract potential spatial information between skeleton nodes. Finally, LSTM (long short-term memory) extracts the time series features before and after human actions as a supplement and performs late fusion of the prediction outputs of the two networks, respectively, to improve the problem of insufficient generalization ability of single network. The experimental results show that this method can effectively improve the accuracy of dance movement recognition in general movement recognition data set and dance pose data set. It has certain application value in dance self-help teaching, professional dancer movement correction, and other application scenarios.
Collapse
|
5
|
Hua X, Han L, Jiang Y. Human Behavior Recognition in Outdoor Sports Based on the Local Error Model and Convolutional Neural Network. Comput Intell Neurosci 2022; 2022:6988525. [PMID: 35800705 PMCID: PMC9256384 DOI: 10.1155/2022/6988525] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/11/2022] [Revised: 05/27/2022] [Accepted: 06/15/2022] [Indexed: 01/04/2023]
Abstract
With the rapid development of the Internet, various electronic products based on computer vision play an increasingly important role in people's daily lives. As one of the important topics of computer vision, human action recognition has become the main research hotspot in this field in recent years. The human motion recognition algorithm based on the convolutional neural network can realize the automatic extraction and learning of human motion features and achieve good classification performance. However, deep convolutional neural networks usually have a large number of layers, a large number of parameters, and a large memory footprint, while embedded wearable devices have limited memory space. Based on the traditional cross-entropy error-based training mode, the parameters of all hidden layers must be kept in memory and cannot be released until the end of forward and reverse error propagation. As a result, the memory used to store the parameters of the hidden layer cannot be released and reused, and the memory utilization efficiency is low, which leads to the backhaul locking problem, limiting the deployment and execution of deep convolutional neural networks on wearable sensor devices. Based on this, this topic designs a local error convolutional neural network model for human motion recognition tasks. Compared with the traditional global error, the local error constructed in this paper can train the convolutional neural network layer by layer, and the parameters of each layer can be trained independently according to the local error and does not depend on the gradient propagation of adjacent upper and lower layers. As a result, the memory used to store all hidden layer parameters can be released in advance without waiting for the end of forward and backward propagation, avoiding the problem of backhaul locking, and improving the memory utilization of convolutional neural networks deployed on embedded wearable devices.
Collapse
Affiliation(s)
- Xia Hua
- Department of Physical Education, China University of Petroleum (East China), Qingdao, Shandong 266580, China
| | - Lei Han
- Department of Physical Education, China University of Petroleum (East China), Qingdao, Shandong 266580, China
| | - Yang Jiang
- ZUGO Intelligence Technology (Shen Zhen) Co. Ltd., ZUGO Digital Energy Building Keji First Road High-Tech Zone, Zhuhai, Guandong 519080, China
| |
Collapse
|
6
|
Abstract
In order to analyse the sports psychology of athletes and to identify the psychology of athletes in their movements, a human action recognition (HAR) algorithm has been designed in this study. First, a HAR model is established based on the convolutional neural network (CNN) to classify the current action state by analysing the action information of a task in the collected videos. Secondly, the psychology of basketball players displaying fake actions during the offensive and defensive process is investigated by combining with related sports psychological theories. Then, the psychology of athletes is also analysed through the collected videos, so as to predict the next response action of the athletes. Experimental results show that the combination of grayscale and red-green-blue (RGB) images can reduce the image loss and effectively improve the recognition accuracy of the model. The optimised convolutional three-dimensional network (C3D) HAR model designed in this study has a recognition accuracy of 80% with an image loss of 5.6. Besides, the time complexity is reduced by 33%. Therefore, the proposed optimised C3D can recognise effectively human actions, and the results of this study can provide a reference for the investigation of the image recognition of human action in sports.
Collapse
Affiliation(s)
- Jiatian Liu
- College of Strength and Conditioning, Beijing Sport University, Beijing, China
| |
Collapse
|
7
|
Abstract
In the decision-making system of sports assistant teaching and training, the performance of such system is not robust to different situations with a low accuracy. To solve the problems in the decision-making system, we proposed a decision-making method combining association rules and support vector machine (SVM) in this paper. First of all, we give a computer-aided decision support system for sports assistant learning and teaching training, which is fully elaborated from three aspects: virtual reality (VR) technology, VR based sports assistant learning and teaching and situational cognition, and VR based sports assistant learning and teaching mode. After that, the paper gives the feature extraction of sports auxiliary teaching training through association rules and the decision-making of the extracted association rules by SVM. We have done two different experiments for both association rules mining and SVM on both experiment group and control group of databases. Experimental results have shown that the training characteristics of sports auxiliary teaching very well. In the decision support of association rules, compared with the existing BP neural network, linear discriminant analysis and naive Bayes and other methods, the SVM method has better effect of action recognition in decision support system of sports assistant teaching and training. The robustness is the best for the application of SVM. We provide a new perspective for the decision support of sports auxiliary teaching training by using association rules and SVM. Through the method of this paper, we can obtain better decision-making effect and more robust process of sports auxiliary teaching and training.
Collapse
Affiliation(s)
- Tong-Zhigang
- P.E. School of Shihezi University, Shihezi Xinjiangs, China
| |
Collapse
|
8
|
Ren Y, Chen B, Li A. Intelligent system for sports movement quantitative analysis. IFS 2021. [DOI: 10.3233/jifs-189345] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Action is the key to sports and the core factor of standardization, quantification, and comprehensive evaluation. However, in the actual competition training, the occurrence of sports activities is often fleeting, and it is difficult for human eyes to identify quickly and accurately. There are many existing quantitative analysis methods of sports movements, but because there are many complex factors in the actual scene, the effect is not ideal. How to improve the accuracy of the model is the key to current research, but also the core problem to be solved. To solve this problem, this paper puts forward an intelligent system of sports movement quantitative analysis based on deep learning method. The method in this paper is firstly to construct the fuzzy theory human body feature method, through which the influencing factors in the quantitative analysis of movement can be distinguished, and the effective classification can be carried out to eliminate irrelevantly and simplify the core elements. Through the method of human body characteristics based on fuzzy theory, an intelligent system of deep learning quantitative analysis is established, which optimizes the algorithm and combines many modern technologies including DBN architecture. Finally, the accuracy of the method is improved by sports action detection, figure contour extraction, DBN architecture setting, and normalized sports action recognition and quantification. To verify the effect of this model, this paper established a performance comparison experiment based on the traditional method and this method. The experimental results show that compared with the traditional three methods, the accuracy of the in-depth learning sports movement quantitative analysis method in this paper has greatly improved and its performance is better.
Collapse
Affiliation(s)
- Yanhong Ren
- Department of Physical Education, Jiaozuo Teachers College, Jiaozuo, Henan, China
| | - Bo Chen
- Sports Department, Henan University of Economics and Law, Zhengzhou, Henan, China
| | - Aizeng Li
- Department of Physical Education, Henan Polytechnic University, Jiaozuo, Henan, China
| |
Collapse
|
9
|
Chen L, Liang H, Lu F, Papangelis K, Man KL, Yue Y. Collaborative behavior, performance and engagement with visual analytics tasks using mobile devices. Hum Cent Comput Inf Sci 2020; 10. [DOI: 10.1186/s13673-020-00253-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
Abstract
Interactive visualizations are external tools that can support users’ exploratory activities. Collaboration can bring benefits to the exploration of visual representations or visualizations. This research investigates the use of co-located collaborative visualizations in mobile devices, how users working with two different modes of interaction and view (Shared or Non-Shared) and how being placed at various position arrangements (Corner-to-Corner, Face-to-Face, and Side-by-Side) affect their knowledge acquisition, engagement level, and learning efficiency. A user study is conducted with 60 participants divided into 6 groups (2 modes
$$\times$$
×
3 positions) using a tool that we developed to support the exploration of 3D visual structures in a collaborative manner. Our results show that the shared control and view version in the Side-by-Side position is the most favorable and can improve task efficiency. In this paper, we present the results and a set of recommendations that are derived from them.
Collapse
|
10
|
Cao D, Chen Z, Gao L. An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks. Hum Cent Comput Inf Sci 2020. [DOI: 10.1186/s13673-020-00219-9] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/29/2023]
Abstract
Abstract
Object detection methods aim to identify all target objects in the target image and determine the categories and position information in order to achieve machine vision understanding. Numerous approaches have been proposed to solve this problem, mainly inspired by methods of computer vision and deep learning. However, existing approaches always perform poorly for the detection of small, dense objects, and even fail to detect objects with random geometric transformations. In this study, we compare and analyse mainstream object detection algorithms and propose a multi-scaled deformable convolutional object detection network to deal with the challenges faced by current methods. Our analysis demonstrates a strong performance on par, or even better, than state of the art methods. We use deep convolutional networks to obtain multi-scaled features, and add deformable convolutional structures to overcome geometric transformations. We then fuse the multi-scaled features by up sampling, in order to implement the final object recognition and region regress. Experiments prove that our suggested framework improves the accuracy of detecting small target objects with geometric deformation, showing significant improvements in the trade-off between accuracy and speed.
Collapse
|
11
|
Kwak J, Sung Y. Automatic 3D Landmark Extraction System Based on an Encoder–Decoder Using Fusion of Vision and LiDAR. Remote Sensing 2020; 12:1142. [DOI: 10.3390/rs12071142] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
To provide a realistic environment for remote sensing applications, point clouds are used to realize a three-dimensional (3D) digital world for the user. Motion recognition of objects, e.g., humans, is required to provide realistic experiences in the 3D digital world. To recognize a user’s motions, 3D landmarks are provided by analyzing a 3D point cloud collected through a light detection and ranging (LiDAR) system or a red green blue (RGB) image collected visually. However, manual supervision is required to extract 3D landmarks as to whether they originate from the RGB image or the 3D point cloud. Thus, there is a need for a method for extracting 3D landmarks without manual supervision. Herein, an RGB image and a 3D point cloud are used to extract 3D landmarks. The 3D point cloud is utilized as the relative distance between a LiDAR and a user. Because it cannot contain all information the user’s entire body due to disparities, it cannot generate a dense depth image that provides the boundary of user’s body. Therefore, up-sampling is performed to increase the density of the depth image generated based on the 3D point cloud; the density depends on the 3D point cloud. This paper proposes a system for extracting 3D landmarks using 3D point clouds and RGB images without manual supervision. A depth image provides the boundary of a user’s motion and is generated by using 3D point cloud and RGB image collected by a LiDAR and an RGB camera, respectively. To extract 3D landmarks automatically, an encoder–decoder model is trained with the generated depth images, and the RGB images and 3D landmarks are extracted from these images with the trained encoder model. The method of extracting 3D landmarks using RGB depth (RGBD) images was verified experimentally, and 3D landmarks were extracted to evaluate the user’s motions with RGBD images. In this manner, landmarks could be extracted according to the user’s motions, rather than by extracting them using the RGB images. The depth images generated by the proposed method were 1.832 times denser than the up-sampling-based depth images generated with bilateral filtering.
Collapse
|
12
|
Huh J, Hwa J, Seo Y. Hierarchical System Decomposition Using Genetic Algorithm for Future Sustainable Computing. Sustainability 2020; 12:2177. [DOI: 10.3390/su12062177] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
A Hierarchical Subsystem Decomposition (HSD) is of great help in understanding large-scale software systems from the software architecture level. However, due to the lack of software architecture management, HSD documentations are often outdated, or they disappear in the course of repeated changes of a software system. Thus, in this paper, we propose a new approach for recovering HSD according to the intended design criteria based on a genetic algorithm to find an optimal solution. Experiments are performed to evaluate the proposed approach using two open source software systems with the 14 fitness functions of the genetic algorithm (GA). The HSDs recovered by our approach have different structural characteristics according to objectives. In the analysis on our GA operators, crossover contributes to a relatively large improvement in the early phase of a search. Mutation renders small-scale improvement in the whole search. Our GA is compared with a Hill-Climbing algorithm (HC) implemented by our GA operators. Although it is still in the primitive stage, our GA leads to higher-quality HSDs than HC. The experimental results indicate that the proposed approach delivers better performance than the existing approach.
Collapse
|