Road Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review

Abstract

Road extraction from high-resolution remote sensing images (HRSI) is a challenging but hot research topic in the past decades. A large number of methods are invented to deal with this problem. This article provides a comprehensive review of these existing approaches. We classified the methods into heuristic and data-driven. The heuristic methods are the mainstream in the early years, and the data-driven methods based on deep learning have been quickly developed recently. With regard to the heuristic methods, the road feature model is firstly introduced, then, the classic extraction methods are reviewed in two sub-categories: semi-automatic and automatic. The principles, inspirations, advantages and disadvantages of these methods are described. In terms of the data-driven methods, the road extraction methods based on deep neural network, particularly those based on patched convolutional neural network, fully convolutional network and generative adversarial network are reviewed. We perform subjective comparisons between the methods inner each type. Furthermore, the quantity performances achieved on the same dataset are compared between the heuristic and data-driven methods to show the strengthening of the data-driven methods. Finally, the conclusion and prospects are summarized.

Roads in the Southwestern Amazon, State of Acre, between 2007 and 2019

“…With a total area of 164,422 km 2 , twice the size of Ireland, the State is divided into 22 municipalities (Figure 1). Approximately 63% (101,645 km 2 ) of its territory is covered by protected areas, consisting of Conservation Units (Federal, State, and Municipal) with 48% (77,744 km 2 ) and Indigenous Lands with 15% (23,901 km 2 ) [14]. Additionally, almost 10% (15,039 km 2 ) of the State was deforested by 2019, the sixth-highest among Brazilian Amazon states [21].…”

“…The dynamics of opening or building unofficial roads can occur through narrow paths and forest areas that make detection difficult, requiring high-resolution images and improved image processing techniques [16,17]. Some recent studies have shown that Deep Learning techniques can automatically extract roads from high spatial resolution satellite images with high accuracy [14,25]. However, few studies have applied these techniques in the Amazon.…”

“…The road extraction from remote sensing images is still a challenge, which depends on the spectral and/or spatial resolution of the images and the road's infrastruture (diverse road material and complex backgrounds-urban or rural), which affect the mapping method [14]. Automatic or semi-automatic mapping methods are based on high spatial resolution images, which have a high cost and low temporal availability [15][16][17].…”

Road Extraction in Mountainous Regions from High-Resolution Images Based on DSDNet and Terrain Optimization

“…With the recent development in artificial intelligence, especially deep learning technology, new ideas have been provided for road extraction [3]. Deep learning was developed Remote Sens.…”

“…2021, 13, 90 2 of 18 from research of neural networks and has made significant advancements in computer vision [4,5] and other fields. It has shown great advantages in image scene classification [6,7], target detection [8,9] and semantic segmentation [10][11][12]; the latter is a useful tool for road extraction [3] so we use it here as the basis for our method. However, from the perspective of practical applications, there are many special issues that need to be studied.…”