Implementing Real-Time Traffic Light Detection and Classification

Object detection is widely used in the world of Neural Network based classifiers are used together with other object detection techniques. The aim of this study was to explore the modern open source based solutions for object detection on detecting traffic signals on road. Tensor Flow Object Detection API, an open source framework for object detection related tasks, was used for training and testing an SSD (Single-Shot Multi box Detector) with Mobilenet- model. The model was tested as pre-trained and with fine-tuning with a dataset consisting of images extracted from video footage of traffic signal. Following hypotheses were examined: 1) Pre-trained model will not work on the data without fine-tuning. 2) Fine-tuned model will work reasonably well on the given data. 3) Fine-tuned model will have problems with occlusion and picture against roadside. 4) Using more variable training data will improve results on new images.