Transi-TEC: Extracción de señales tridimensionales en señales de tránsito

Road safety is fundamental in modern transport infrastructure. Inadequate demarcation or theft of traffic signs can lead to accidents resulting in loss of life and logistical problems on highways, highlighting the need for efficient systems to monitor and maintain road signage. This project proposes the development of an innovative computer vision-based system for automated detection, localization, and tracking of traffic signs.
The proposed system uses a standard resolution camera to capture images of the road environment. Through image processing and machine learning algorithms, it can spatially extract traffic signs and automatically establish their precise location. The implementation is distinguished by its low cost, requiring only common hardware, which facilitates its widespread adoption.
The main objective is to create a georeferenced and updated database of traffic signs. This database will serve as a dynamic record to compare the location and condition of signs over time, facilitating the identification of areas that require new signs or the replacement of damaged or stolen ones.

Examinar los métodos o algoritmos para extracción espacial de señales de tránsito en tiempo real usando procesamiento de vídeo e imágenes que se ajusten a la realidad costarricense

Computing algorithms, AI and software design.