Automated road extraction using reinforced road indices for Sentinel-2 data

Accurate Road feature extraction from multispectral images tends to be difficult due to the technical challenges posed by the data. The field of study has extreme importance with respect to urban planning, asset mapping, transport planning, and feasibility studies. In this paper, we utilize the road index (RI) to formulate our methodology for feature extraction. For further processing of the RI output image, we opted for Bot-Hat morphological operator to highlight the road features and suppress the surrounding features. We then classified the image using a Pixel-Based Unsupervised Classification to break the features into different classes. Subsequently, Contrast-Split segmentation algorithm was applied to segment the road network for network extraction. The experiment results showed an F1 score of 76.10% and 83.81% for the Lahore and Richmond datasets respectively