Abstract
This paper proposed an effective recognition algorithm for night traffic lights. The algorithm first carries out the pre-processing of collected night traffic light images, and then makes the RGB color space of images transfer into the HSI, further removing noise through morphological operations to extract candidate regions, and last realizes night traffic light identification based on template matching and regional pixel information. The experimental results show that this algorithm has a higher identification accuracy than other ones.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
