Road scene classification based on street-level images and spatial data
Roman Prykhodchenko, Paweł Skruch
Abstract
Understanding the context of the scene is one of the most important aspects for new generation of autonomous vehicles. It is a very trivial task for a human to recognize the scene context by only a single look at the picture, however, for a computer, it is still a challenging task. This problem can be solved by automatic data labeling using deep-learning models for scene classification. Relying on scene type labels we can select relevant scenes to prepare a balanced dataset to train more advanced instance detection models using data from a specific road condition. This study presents a novel framework based on a deep convolutional neural network (CNN) for the automatic road scene classification of street-level automotive images. For the evaluation of our approach, we use a well-known autonomous benchmark dataset, from which we extract geo-position data and combine them with predictions from the scene classification model to get ground truth labels to train and evaluate a ResNet-50 model for scene classification. The results and comparison with state-of-the-art methods are presented.