SciELO - Scientific Electronic Library Online

 
vol.31 número3Protocolos de encaminamiento de datos para uso en microrredes rurales aisladasAcción psicofarmacológica y analgésica del antidepresivo inhibidor selectivo de la recaptación de serotonina fluoxetina en ratón hembra índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google

Compartilhar


Información tecnológica

versão On-line ISSN 0718-0764

Resumo

SANTOS, Daniel; DALLOS, Leonardo  e  GAONA-GARCIA, Paulo A.. Motion tracking algorithms using AI and machine learning techniques. Inf. tecnol. [online]. 2020, vol.31, n.3, pp.23-38. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642020000300023.

The main objective of this article is to implement a tracking algorithm analysis based on computer vision techniques and machine learning to identify, track, and classify different elements and patterns present on a video. There are variations associated with the precision in which these types of techniques are applied to carry out the tracking of moving objects, which can significantly affect capture quality and performance processing used by physical devices. The most used algorithms (SIFT, SURF and ORB) for this type of tracing were analyzed. ORB was the most efficient. It was possible to conclude that the analyses of the models developed showed good results under controlled conditions. However, there were errors and the accuracy dropped considerably under uncontrolled conditions.

Palavras-chave : artificial vision; artificial intelligence; computer vision; image processing; object tracking.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )