Redirigiendo al acceso original de articulo en 17 segundos...
ARTÍCULO
TITULO

Article Users Activity Gesture Recognition on Kinect Sensor Using Convolutional Neural Networks and FastDTW for Controlling Movements of a Mobile Robot

Miguel Pfitscher    
Daniel Welfer    
Evaristo José do Nascimento    
Marco Antonio de Souza Leite Cuadros    
Daniel Fernando Tello Gamarra    

Resumen

In this paper, we use data from the Microsoft Kinect sensor that processes the captured imageof a person using and extracting the joints information on every frame. Then, we propose the creation ofan image derived from all the sequential frames of a gesture the movement, which facilitates training in aconvolutional neural network. We trained a CNN using two strategies: combined training and individualtraining. The strategies were experimented in the convolutional neural network (CNN) using theMSRC-12 dataset, obtaining an accuracy rate of 86.67% in combined training and 90.78% of accuracyrate in the individual training.. Then, the trained neural network was used to classify data obtained fromKinect with a person, obtaining an accuracy rate of 72.08% in combined training and 81.25% inindividualized training. Finally, we use the system to send commands to a mobile robot in order to controlit.

 Artículos similares

       
 
Jing Liu and Yong Zhong    
As a structural indicator of dense subgraphs, k-core has been widely used in community search due to its concise and efficient calculation. Many community search algorithms have been expanded on the basis of k-core. However, relevant algorithms often set... ver más
Revista: Applied Sciences

 
Pietro Dell?Oglio, Alessandro Bondielli and Francesco Marcelloni    
Today, most newspapers utilize social media to disseminate news. On the one hand, this results in an overload of related articles for social media users. On the other hand, since social media tends to form echo chambers around their users, different opin... ver más
Revista: Algorithms

 
Robert E. Przekop, Ewa Gabriel, Daria Pakula and Bogna Sztorch    
The L-FDM technique enables the direct introduction of chemicals, dyes, radioactive substances, pesticides, antibiotics, nanoparticles, trace elements, fertilizers, phosphors, monomers for polymerization, proteins, peptides, and active ingredients in the... ver más
Revista: Applied Sciences

 
Algirdas Dobrovolskis, Egidijus Kazanavicius and Laura Ki?auskiene    
The technological maturity of AI solutions has been consistently increasing over the years, expanding its application scope and domains. Smart home systems have evolved to act as proactive assistants for their residents, autonomously detecting behavioral... ver más
Revista: Applied Sciences

 
Margherita Pazzini, Leonardo Cameli, Claudio Lantieri, Valeria Vignali, Daniele Mingozzi and Giuseppe Crescenzo    
BIM (building information modelling) has led to substantial improvements in all design steps. Applied mainly as an information management system in the digital design of structures and buildings, only in recent years has the use of BIM also extended to t... ver más
Revista: Infrastructures