Pedestrian Traffic Light Recognition for the Visually Impaired Using Deep Learning

This project is a part of a series of projects carried out in SIPL dedicated to creating an Android application that will assist the visually impaired people with pedestrian traffic lights. The current project consists of two parts: 1. Recognition of pedestrian traffic lights in a single image taken with a mobile phone from a pedestrian perspective. We use the Faster RCNN object detector with transfer learning on more than 900 pedestrian traffic light images, and achieve 98% accuracy. 2. Using the recognition module from part 1 along with object tracking to detect light switches from red to green or vice versa, for improved recognition robustness. For this aim, we use the KCF object tracker. We developed “light switch detection” algorithm, and tested it with 120 videos 3-10 seconds long. The algorithm we developed is very reliable, and we correctly identified all light switches in our dataset.

Pedestrian Traffic Light Recognition for the Visually Impaired Using Deep Learning
Pedestrian Traffic Light Recognition for the Visually Impaired Using Deep Learning