Control of adaptive running platform based on machine vision technologies and neural networks

Obukhov, Artem; Krasnyanskiy, Mikhail; Dedov, Denis; Vostrikova, V; Teselkin, Daniil; Surkova, Ekaterina

doi:10.1007/s00521-022-07166-9

“… recording a person's movement on a video camera with subsequent capture of key points of the body; the person's speed is determined by setting a fixed speed value on the treadmill [5] and using manual start/stop to record changes in walking;  simulation of the movement of a digital human model in a virtual environment, saving the animation in the form of a video sequence, and then capturing the position of all the necessary points and the current speed of the model's movement. This allows for varying the speed of movement by changing the animation speed [6]. The two methods are combined after obtaining information from two sources and normalizing the initial data on the position of the human body.…”

Section: Methodsmentioning

confidence: 99%

“…The number of key points is determined by body recognition algorithms. Previous research shows that 18 points are enough to completely reconstruct a human body model [6]. To capture points of the body, it is possible to use various machine learning models (MediaPipe, MoveNet) and modern TokenPose models and their modifications [7].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Neural network algorithm for predicting human speed based on computer vision and machine learning

Obukhov,

Teselkin,

Surkova

et al. 2024

ITM Web Conf.

0

View full text Add to dashboard Cite

The problem of increasing the accuracy of predicting human actions is an urgent task for various human-machine systems. The study examines the solution to the problem of predicting human speed using neural network algorithms, computer vision technologies, and machine learning. The formalization and software implementation of a neural network speed prediction algorithm are presented. To solve the problems of determining the current speed and predicting the upcoming positions of the human body depending on the dynamics of its movement, a comparison of various machine learning models was carried out. The RandomForestRegressor algorithm showed the best position prediction accuracy. The best determination of the current speed was demonstrated by dense multilayer neural networks. The experiment revealed that when predicting a person's position at an interval of 0.6 seconds, his speed is determined with an accuracy of more than 90%. The results obtained can be used to implement neural network algorithms for controlling human-machine systems.

show abstract

Development of a stress-free algorithm for controlling active running platforms

Obukhov,

Karpushkin,

Siukhin

et al. 2024

ITM Web Conf.

0

View full text Add to dashboard Cite

The problem of increasing the accuracy of predicting human actions is an urgent task for various human-machine systems. The study examines the solution to the problem of predicting human speed using neural network algorithms, computer vision technologies, and machine learning. The formalization and software implementation of a neural network speed prediction algorithm are presented. To solve the problems of determining the current speed and predicting the upcoming positions of the human body depending on the dynamics of its movement, a comparison of various machine learning models was carried out. The RandomForestRegressor algorithm showed the best position prediction accuracy. The best determination of the current speed was demonstrated by dense multilayer neural networks. The experiment revealed that when predicting a person's position at an interval of 0.6 seconds, his speed is determined with an accuracy of more than 90%. The results obtained can be used to implement neural network algorithms for controlling human-machine systems.

show abstract

Development of a Stress-Free Algorithm for Control of Running Platforms Based on Neural Network Technologies

Obukhov,

Dedov,

Teselkin

et al. 2024

IA

0

View full text Add to dashboard Cite

The article discusses the task of predicting human speed using neural network technologies and computer vision to minimize lags in treadmill control systems, which pose a health risk to the user. To solve this problem, a stress-free algorithm has been developed, including: predicting the position and speed of the user on the treadmill; calculating the treadmill speed based on the analysis of the user's position and movement characteristics; data collection and processing schemes for training neural network methods; and determining the necessary number of predicted frames to eliminate lags. The scientific novelty of the research lies in the development of a treadmill control algorithm that combines: computer vision technologies for recognizing the user's body model on the platform; neural networks; and machine learning methods to determine the final human speed based on combining data on the person's position in the frame and the current and predicted speed of the person. The proposed algorithm is implemented using Python libraries, and its validation was conducted during experimental studies analyzing the preceding 10 and 15 frames to predict the next 10 and 15 frames. Comparing machine learning algorithms (linear regression, decision tree, random forest, multilayer, convolutional, and recurrent neural networks) at different lengths of analyzed and predicted frames, the RandomForestRegressor algorithm showed the best accuracy in predicting position, while dense multilayer neural networks performed best in determining current speed. Experimental research has been conducted on applying the developed algorithm and models to determine human speed (achieving accuracy when forecasting in the range of 10-15 frames) as well as integrating them into treadmill control systems. Trials have shown the effectiveness of the proposed approach and the correctness of system operation under real conditions. The developed algorithm allows for not using noise-sensitive sensors that require attachment to the user's body but rather forecasting user actions through analyzing all points of the person's body to reduce lags in various human-machine systems.

show abstract

Control of adaptive running platform based on machine vision technologies and neural networks

Cited by 4 publications

References 63 publications

Neural network algorithm for predicting human speed based on computer vision and machine learning

Neural network algorithm for predicting human speed based on computer vision and machine learning

Development of a stress-free algorithm for controlling active running platforms

Development of a Stress-Free Algorithm for Control of Running Platforms Based on Neural Network Technologies

Contact Info

Product

Resources

About