ABSTRACT
Systems able to assist drivers in the safe driving of vehicles
provide several advantages, such as the reduction of traffic
accidents, mostly with fatalities, normally caused by human
failures, whether for distractions or even problems related to
lighting or climate change. Based on this, this research aims to
present a computational model capable of detect stop signs and
speed limit signs, so that it contributes to the development of
progressively intelligent vehicles. The system was implemented
in Phyton programming language, with the support of OpenCV
library, and it was divided into two steps: firstly it was
performed the training and classification of the objects through
Haar Cascade classification method, and in the second step, in
order to improve the results, colors relevant to the object were
identified using the HSV color space. During the experiments,
the proposed algorithm presented satisfactory results, with a hit
rate of 91% for speed limit signs and 93% for stop signs. In order
to refine the proposed solution, it is intended for the next steps
to include traffic sign information recognition, to either describe
the specified speed on the detected objects and further reduce
false positives.