scholarly journals Accurate Recognition Method of Human Body Movement Blurred Image Gait Features Using Graph Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yang Yu
Keyword(s):  
Neural Network ◽  
Human Body ◽  
Feature Recognition ◽  
Body Movement ◽  
Human Movement ◽  
Recognition Method ◽  
Gait Features ◽  
Gait Feature ◽  
Blurred Image ◽  
Blurred Images

In view of the problems of low precision, poor quality, and long time of gait feature recognition due to the influence of human body movement environment on the recognition process of the current gait feature recognition method of human body movement blurred image, a new method of gait feature recognition based on graph neural network (GNN) method is proposed. The gait features of human movement blurred images were extracted, and the fusion clustering recognition of the GNN algorithm was used to locate the gait features of human movement blurred images. The gait features of human body movement blurred images were located by the GNN method. According to the contour feature point info of the human body movement blurred image, the standard deviation of gait feature location of the human body movement blurred image was calculated, the gait feature of the blurred image of human body movement was reconstructed, and the gait recognition of the human body movement blurred image was achieved. The results show that the extraction of human movement is good, with high positioning confidence, good recognition quality, average recognition accuracy of 92%, and greatly shortened recognition time.

scholarly journals Human Body Mixed Motion Pattern Recognition Method Based on Multi-Source Feature Parameter Fusion

Sensors ◽  
2020 ◽  
Vol 20 (2) ◽  
pp. 537 ◽  
Author(s):  
Jiyuan Song ◽  
Aibin Zhu ◽  
Yao Tu ◽  
Yingxu Wang ◽  
Muhammad Affan Arif ◽  
...  
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Lower Extremity ◽  
Human Body ◽  
Recognition Accuracy ◽  
Screening Method ◽  
Motion Pattern ◽  
Recognition Method ◽  
Motion State ◽  
Motion Mode

Aiming at the requirement of rapid recognition of the wearer’s gait stage in the process of intelligent hybrid control of an exoskeleton, this paper studies the human body mixed motion pattern recognition technology based on multi-source feature parameters. We obtain information on human lower extremity acceleration and plantar analyze the relationship between these parameters and gait cycle studying the motion state recognition method based on feature evaluation and neural network. Based on the actual requirements of exoskeleton per use, 15 common gait patterns were determined. Using this, the studies were carried out on the time domain, frequency domain, and energy feature extraction of multi-source lower extremity motion information. The distance-based feature screening method was used to extract the optimal features. Finally, based on the multi-layer BP (back propagation) neural network, a nonlinear mapping model between feature quantity and motion state was established. The experimental results showed that the recognition accuracy in single motion mode can reach up to 98.28%, while the recognition accuracy of the two groups of experiments in mixed motion mode was found to be 92.7% and 97.4%, respectively. The feasibility and effectiveness of the model were verified.

Continuous Monitoring of Overt Human Body Movement by Radio Telemetry: A Brief Review

1967 ◽  
Vol 24 (3_suppl) ◽  
pp. 1303-1308 ◽  
Author(s):  
R. E. Herron ◽  
R. W. Ramsden
Keyword(s):  
Human Body ◽  
Systematic Study ◽  
Continuous Monitoring ◽  
Radio Telemetry ◽  
Body Movement ◽  
Human Movement ◽  
Major Obstacle ◽  
Analog Signals

Although radio transmission of analog signals has been known for over 100 yr., very few investigators have exploited this approach to the systematic study of overt human movement. The small number of known previous applications are critically reviewed and suggestions made regarding future possibilities. Now that micro-electronic transmitters are commonplace, the only major obstacle to future use of this technique seems to rest with the design of unobtrusive motion transducers which are parsimonious in the acquisition of relevant data.

scholarly journals Deep Large Margin Nearest Neighbor for Gait Recognition

2021 ◽  
Vol 30 (1) ◽  
pp. 604-619
Author(s):  
Wanjiang Xu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Video Surveillance ◽  
Computational Efficiency ◽  
Nearest Neighbor ◽  
Gait Recognition ◽  
Large Margin ◽  
Extensive Evaluation ◽  
Gait Features ◽  
Gait Feature

Abstract Gait recognition in video surveillance is still challenging because the employed gait features are usually affected by many variations. To overcome this difficulty, this paper presents a novel Deep Large Margin Nearest Neighbor (DLMNN) method for gait recognition. The proposed DLMNN trains a convolutional neural network to project gait feature onto a metric subspace, under which intra-class gait samples are pulled together as small as possible while inter-class samples are pushed apart by a large margin. We provide an extensive evaluation in terms of various scenarios, namely, normal, carrying, clothing, and cross-view condition on two widely used gait datasets. Experimental results demonstrate that the proposed DLMNN achieves competitive gait recognition performances and promising computational efficiency.

scholarly journals Image Deblurring using Wiener Filtering and Siamese Neural Network

2021 ◽  
Vol 9 (3) ◽  
pp. 96
Author(s):  
Vaibhav Setia ◽  
Shreya Kumar
Keyword(s):  
Neural Network ◽  
Image Matching ◽  
Signal To Noise Ratio ◽  
Wiener Filter ◽  
Function Estimation ◽  
Point Spread ◽  
Spread Function ◽  
Blurred Image ◽  
Blurred Images ◽  
Local Image

Blurred images are difficult to avoid in situations when minor Atmospheric turbulence or camera movement results in low-quality images. We propose a system that takes a blurred image as input and produces a deblurred image by utilizing various filtering techniques. Additionally, we utilize the Siamese Network to match local image segments. A Siamese Neural Network model is used that is trained to account for image matching in the spatial domain. The best-matched image returned by the model is then further used for Signal-to-Noise ratio and Point Spread Function estimation. The Wiener filter is then used to deblur the image. Finally, the results of the deblurring techniques with existing algorithms are compared and it is shown that the error in deblurring an image using the techniques presented in this paper is considerably lesser than other techniques.

scholarly journals Intelligent Recognition Method of Athlete Wrong Movement Based on Image Vision

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Wang Lu ◽  
JiangYuan Hou
Keyword(s):  
Human Body ◽  
Body Movement ◽  
Three Dimensional ◽  
Image Data ◽  
Recognition Method ◽  
Canny Operator ◽  
Cloud Data ◽  
Movement Recognition ◽  
Cmos Sensor ◽  
Intelligent Recognition

Current methods of human body movement recognition neglect the depth denoising and edge restoration of movement image, which leads to great error in athletes’ wrong movement recognition and poor application intelligence. Therefore, an intelligent recognition method based on image vision for sports athletes’ wrong actions is proposed. The basic principle, structure, and 3D application of computer image vision technology are defined. Capturing the human body image and point cloud data, the three-dimensional dynamic model of sports athletes action is constructed. The color camera including CCD sensor and CMOS sensor is selected to collect the wrong movement image of athlete and provide image data for the recognition of wrong movement. Wavelet transform coefficient and quantization matrix threshold are introduced to denoise the wrong motion images of athletes. Based on this, the feature of sports athlete’s motion contour image is extracted in spatial frequency domain, and the edge of the image is further recovered by Canny operator. Experimental results show that the proposed method can accurately identify the wrong movements of athletes, and there is no redundancy in the recognition results. Image denoising effect is good and less time-consuming and can provide a reliable basis for related fields.

ANN-Based Feature Recognition to Integrate CAD and CAM

2011 ◽  
Vol 55-57 ◽  
pp. 1269-1274
Author(s):  
Yong Tao Hao ◽  
Yong Min Chi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Bp Neural Network ◽  
Feature Recognition ◽  
Intelligent Manufacturing ◽  
Recognition Method ◽  
Feature Extraction Method ◽  
The Subject ◽  
Artificial Neural ◽  
Manufacturing Feature

This paper presents an intelligent manufacturing feature extraction method employing artificial neural network techniques. It discuss the subject about how to represent the features as the input expression of the ANN(Artificial Neural Network), how to determine the structure of ANN and the ANN-based feature recognition method. This method is mainly used pre-trained BP neural network to identify the B-rep model representation of the product. Through a lot testing, the validity of the system was verified.

The Visual Simulation Analysis of Human Body Movement Model

2014 ◽  
Vol 556-562 ◽  
pp. 3913-3916
Author(s):  
Jun Jie Wang
Keyword(s):  
Human Body ◽  
Simulation Analysis ◽  
Body Movement ◽  
Linear Optimization ◽  
Human Movement ◽  
The Body ◽  
Body Parts ◽  
Optimization Strategy ◽  
Matching Accuracy ◽  
Movement Model

This paper proposes the re-built human body movement model with multiple cameras. In the tracking frame of the non-linear optimization strategy, the paper builds the body dynamic model to dynamically simulate the human movement which effectively solves the issues of the body parts overlap and tracking errors accumulate. Compared with traditional methods, the required equipment is very economic and the matching accuracy of the algorithm is quite high. The paper applies the athletes as the experimental examples which illustrate the proposed algorithm can effectively increase the 3D image tracking matching accuracy in dynamic videos as the analysis basis.

Deadlift Recognition and Application based on Multiple Modalities using Recurrent Neural Network

2020 ◽  
Vol 2020 (17) ◽  
pp. 2-1-2-6
Author(s):  
Shih-Wei Sun ◽  
Ting-Chen Mou ◽  
Pao-Chi Chang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Network Structure ◽  
Inertial Sensors ◽  
Body Movement ◽  
The Body ◽  
Body Parts ◽  
Multimodal Sensing ◽  
Multiple Devices ◽  
Neural Network Structure

To improve the workout efficiency and to provide the body movement suggestions to users in a “smart gym” environment, we propose to use a depth camera for capturing a user’s body parts and mount multiple inertial sensors on the body parts of a user to generate deadlift behavior models generated by a recurrent neural network structure. The contribution of this paper is trifold: 1) The multimodal sensing signals obtained from multiple devices are fused for generating the deadlift behavior classifiers, 2) the recurrent neural network structure can analyze the information from the synchronized skeletal and inertial sensing data, and 3) a Vaplab dataset is generated for evaluating the deadlift behaviors recognizing capability in the proposed method.

Sign in / Sign up

Export Citation Format

Share Document