Road detection in spaceborne SAR images using a genetic algorithm

Abstract

Abstract-This paper presents a technique for the detection of roads in a spaceborne synthetic aperture radar (SAR) image using a genetic algorithm (GA). Roads in a spaceborne SAR image can be modeled as curvilinear structures that possess width. Curve segments, which represent the candidate positions for roads, are extracted from the image using a curvilinear structure detector, and the roads are accurately detected by grouping those curve segments. For this purpose, we designed a grouping method based on a GA, which is a global optimization method. We combined perceptual grouping factors with it and tried to reduce its overall computational cost by introducing a concept of region growing. In this process, a selected initial seed is grown into a finally grouped segment by the iterated GA process, which considers segments only in a search region. To detect roads more accurately, postprocessing, including noisy curve segment removal, is performed after grouping. We applied our method to ERS-1 SAR and SIR-C/X-SAR images that have a resolution of about 30 m. The experimental results show that our method can accurately detect road networks as well as single-track roads and is much faster than a globally applied GA approach.Index Terms-Genetic algorithm (GA), perceptual grouping, road detection, synthetic aperture radar (SAR).

Line-Detection Based on the Sum of Gradient Angle Differences

“…Steger [18] and Lindeberg [17] proposed line-detection approaches that identify line pixels based on large second directional derivatives in a direction determined by the eigenvector corresponding to the maximum absolute eigenvalue of the Hessian matrix. In similar studies, Laptev et al [21] and Jeon et al [22] employed Steger¡s method to detect roads in aerial images and synthetic-aperture radar images, respectively. However, as will be demonstrated in the following sections, the SD-based line-detection methods used in the abovementioned studies suffer from problems such as non-unique responses to a single line signal and dis-localization because of a relatively large line width.…”

SAR image road network extraction with scene context priming

“…Some works using topological characteristics have been proposed on network reconstruction after road segments extraction in SAR imagery. Relevant literature lists Markov random fields (MRFs) [11][1] [3][7] , genetic algorithms [12] , perceptual grouping [13] or hough transformation [14], but research work is still ongoing.…”

Road recognition in high resolution SAR image based on genetic algorithm

“…Many researchers have proposed various methods for road recognition [1][2][3][4]. Tupin [1] uses Markov Random Field to link line segments which are detected locally to form fully roads.…”

“…Paper [4] applies Snakes Model to detecting roads. The algorithm for grouping curve lines based on Genetic Algorithm (GA) to detecting roads by Jeon [2,3] is one of the most excellent algorithms. Only basis on accuracy of extracting curve lines, Jeon's algorithm can detect roads exactly.…”