Traffic Light Detection System for Low Vision or Visually Impaired Person Through Voice

This work focus is to give a better and much more efficient solution for visually impaired person. The work is helpful for blind person to crossing the traffic signal without any other help. Blind person will have camera on his head, which will capture the image and video of traffic signal. The input of the system is a continues traffic video sequence or image of traffic light. which first will be video converted into individual frames for further processing. By using canny edge detection and circular hough transformation, identified the shape of traffic light and further identified the light present on traffic signal(red, green). Found the color on traffic light then calculate the time presented on the traffic signal. Identified the color and time on signal send notification to the blind person through voice.