Road identification in aerial images on fractional differential and one-pass ridge edge detection

Xiuzhi Yang,Weixing Wang

doi:10.1117/1.jrs.8.083597

Abstract

A method for detecting and identifying thin and vague roads in aerial images is proposed. The method first smooths an image by using a Gaussian filter, then uses a fractional differential operator to enhance the image for sharpening roads, then applies a one-pass ridge edge detection algorithm to roughly detect the roads, and finally utilizes a number of post functions to accurately identify roads. For each detected point in an aerial road image, the new ridge detection algorithm detects if it is a candidate for the ridge edge points by searching through four different directions. After that, the extracted segments of lines/curves are smoothed and their gaps are linked according to preset thresholds of lengths and directions, and the noisy lines are removed based on the rules of the curve length and shape information. If roads are thick, the image can be shrunk to a road with a width less than six pixels, then the detection result for the course resolution image is mapped into the original image to accurately re-identify the road. In experiments, by comparison to traditional methods, the studied method can have better detection results for thin and vague roads, which are difficult to detect with traditional algorithms.

Highlights

With the development of highway and rural roads, road networks have recently become more and more complex, and many new roads are constructed every day
This paper suggests a method for resolving the problem of the difficulty in extracting thin and vague road lines or curves from aerial images
Compared to some traditional algorithms, the main features of the new operator are: (1) Enhance images through a fractional differential template to highlight road details,; compared with the conventional Laplacian and high-pass filter operators, the new operator can enhance road information without adding too much noise; (2) get road lines or curves by using the new ridge edge detection algorithm based on ridge characteristics proposed in this study

Summary

Introduction

With the development of highway and rural roads, road networks have recently become more and more complex, and many new roads are constructed every day. There are many methods to process complex and vague images, and one of them is presented by Eitan He studied an algorithm by using hierarchy and an adaptive idea in segmenting visual scenes. A slender road image is often mixed in with a variety of natural features and man-made facilities; sometimes, it is even difficult to identify these with human vision In this case, a complex road network is hard to identify through the approach that is based on gray scale similarity.[15] It is difficult to detect ridge-like roads by using a conventional edge detection method and even when applying an improved smart Canny edge detection algorithm,[16] some thin and small lines or curves cannot be completely detected in most cases. For the whole method of detecting thin or vague roads, ridge detecting is a significant step, more post functions are needed for the final road identification

Ridge Edge Detection Algorithm for Thin and Vague Roads

Conclusions