Multi-spectral and Topographic Fusion for Automated Road Extraction

Abstract

Road geometry is pertinent information in various GIS studies. Reliable and updated road information thus calls for conventional on-site survey being replaced by more accurate and efficient remote sensing technology. Generally, this approach involves image enhancement and extraction of relevant features, such as elongate gradient and intersecting corners. Thus far, its implication is often impeded by wrongly extraction of other urban peripherals with similar pixel characteristics. This paper therefore proposes the fusion of THEOS satellite image and topographic derivatives, obtained from underlying Digital Surface Models (DSM). Multi-spectral indices in thematic layers and surface properties of designated roads were both fed into state-of-the-art machine learning algorithms. The results were later fused, taken into account consistently leveled road surface. The proposed technique was thus able to eliminate irrelevant urban structures such as buildings and other constructions, otherwise left by conventional index based extraction. The numerical assessment indicates recall of 84.64%, precision of 97.40% and overall accuracy of 97.78%, with 0.89 Kappa statistics. Visual inspection reported herewith also confirms consistency with ground truth reference.

Land Use and Land Cover Change Detection for Water Yield Estimation using Remote Sensing Data in Batu Pahat, Johor

“…However, with the advancement of Geographic Information System (GIS) and Remote Sensing (RS), the data obtained from the Earth Observation Satellite were used for digital image processing using machine learning regardless of human labor. As a result, the LULC data are acquired quickly [8], [9] and used as the input to analyze water yield estimation in couple with other spatial data to determine the relationship between the water yield and the urban growth, as well as the change of LULC for monitoring and preparation. Further, such data might be useful for urban planning.…”

“…Further, such data might be useful for urban planning. From the literature review and relevant research, most of them studied the LULC classification using satellite images and the LULC change detection using satellite images by utilizing the machine learning algorithms widely [8], [9]. Nevertheless, the study on the application of LULC and the spatial data to analyze the relationship between the water yield and urban growth and the use of each type of land is very rare.…”