Computer Vision Methods for Automotive Applications

• Autores: Díaz, Aldo André, Kurka, Paulo R. G.
• Formato: artículo
• Fecha de Publicación: 2020
• Institución: Universidad Nacional de Ingeniería
• Repositorio: Revistas - Universidad Nacional de Ingeniería
• Lenguaje: español
• OAI Identifier: oai:oai:revistas.uni.edu.pe:article/801
• Enlace del recurso: https://revistas.uni.edu.pe/index.php/tecnia/article/view/801
• Nivel de acceso: acceso abierto
• Materia: visión computacional; detección de aros; ángulos de calibración de vehículos; odometría estéreo; computer vision; wheel rim detection; vehicle calibration angles; stereo odometry

Recent advances in computer vision have favored technological developments in the automotive industry. In this work, we present methods relevant to the use of cameras as measurement devices in computer vision and their applications in the automotive industry. The methods are edge and ellipse detection, camera calibration, 3-D reconstruction and stereo vision. The applications include methods for detecting rims in automotive wheels, estimation of the calibration angles of vehicles and the reconstruction of a vehicle's trajectory using stereo vision. The results showed the potential of computer vision methods to solve complex problems in the automotive industry. In conclusion, a set of techniques and applications of computer vision in the automotive industry are presented in order to motivate future developments in this and other related areas.