Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Revista Facultad de Ingeniería
Print version ISSN 0121-1129On-line version ISSN 2357-5328
Abstract
VALENCIA-PAYAN M. SC, Cristian; MUNOZ-ORDONEZ M. SC, Julián and PENCUE-FIERRO, Leonairo. Driver-Assistant System Using Computer Vision and Machine Learning. Rev. Fac. ing. [online]. 2020, vol.29, n.54, e11760. Epub Dec 30, 2020. ISSN 0121-1129. https://doi.org/10.19053/01211129.v29.n54.2020.11760.
Safety has been one of the key points in vehicle design, in this case one of its main objectives is to implement warning systems to notify the driver about inappropriate or atypical process in their driving process, trying to avoid accidents that affect their vehicle passengers, as well as inflicting damage on third parties. Day by day, more systems are created to monitor the environment around the vehicle in order to ensure safe driving at all times. According to the World Health Organization, for 2016 there were 1.35 million deaths related to traffic accidents. This research presents the first driving assistance system developed for Colombia, the system detects and recognizes preventive and regulatory traffic signals and its precision is not affected by rotations and scale of the traffic signals present in an actual route, this is this way because the system is based on Haar classifiers. The system recognizes lane deviations, estimation of the curve direction and obstacle protruding along the way using computer vision algorithms, making it a low-cost computational system. Furthermore, this research provides the first resulting cascades for the detection of Colombian regulatory and preventive traffic signals. The system is tested in real environments on Colombian roads, obtaining an accuracy of over 90%. This research shows that computer vision-based methods are competitive against current proposals such as deep neural networks.
Keywords : computer vision; Haar classifier; machine learning; road safety; traffic sign.