A Review of Research on Road Feature Extraction Through Remote Sensing Images Based on Deep Learning Algorithms

Road feature extraction from remote sensing images is one of the most challenging research which is mainly performed in the spatial system. The road feature extraction may be utilized for intelligent transportation, smart cities, autonomous driving, urban planning, and emergency management. Many researchers have studied road feature extraction by applying machine learning algorithms. However, no literature indicates a comprehensive survey pertaining to the higher accuracy of the road feature extraction in the last many years. This paper is focused on comprehensive survey of the road feature extraction that uses algorithms of deep learning for higher accuracy in the road feature extraction. This paper first indicates a tree structure that extends into four subtasks such as road centerline detection, road surface segmentation, road edge detection and a combination thereof. Subsequently, methodological level classification is analyzed in respect of all said four categories present in various kinds of literature published in recent years. Further, this paper also indicates the datasets and metrics which are used commonly.