Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

TLDR

Object segmentation of high‑resolution remote‑sensing images is widely used for road extraction, yet existing deep convolutional neural network approaches still yield limited accuracy. This study proposes an enhanced DCNN framework for road extraction that incorporates landscape metrics and conditional random fields. The framework employs an ELU activation function, integrates landscape metrics to reduce false road detections, applies a CRF for edge sharpening, and is evaluated on Massachusetts aerial and Thailand satellite imagery. The proposed method outperformed SegNet in precision, recall, and F1 across most remote‑sensing datasets.

Abstract

Object segmentation of remotely-sensed aerial (or very-high resolution, VHS) images and satellite (or high-resolution, HR) images, has been applied to many application domains, especially in road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts at applying the deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction of remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve the DCNN, a modern activation function called the exponential linear unit (ELU), is employed in our network, resulting in a higher number of, and yet more accurate, extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as the Thailand Earth Observation System (THEOS) satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, a state-of-the-art object segmentation technique, on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F 1 .