[Paper] Urban Road Extraction Based-on Morphological Operations and Radon Transform on DSM Data

This thesis addresses the topic of semi-automated extraction of urban road networks from high-resolution satellite imagery. Research on this topic is mainly motivated by the use geographic information systems in transportation (GIS-T), and the need for reliable data acquisition methods and to update GIS-T databases. To this end, 1-m spatial resolution IKONOS imagery provides a new data source to collect the spatial models of citywide road networks. In this thesis, a novel methodology of a semi-automated road extraction using high-resolution satellite imagery over urban areas is developed. The main objective of this research is to extract urban road networks from a single IKONOS image. To detect the road features from a highly complex scene, a multiscale analysis of the optimal image was performed. To extract roads and their networks, the knowledge of road geometry is exploited in an interactive environment. The key advantage of the developed method is the full employment of a human and a computer's abilities for fast and precise road extraction from high-resolution satellite imagery. The results show that the presented method enables reliable road extraction over urban areas. The potential applications exemplified in case studies indicate that the high-resolution satellite imagery offers an efficient and precise source for geographic and transportation databases. Based on this research, the limitations and future work for the prototype system are discussed.

Download Full-text

A Method for Road Extraction from High-Resolution Remote Sensing Images Based on Multi-Kernel Learning

Information ◽

10.3390/info10120385 ◽

2019 ◽

Vol 10 (12) ◽

pp. 385

Author(s):

Rui Xu ◽

Yanfang Zeng

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Kernel Learning ◽

Morphological Operations ◽

Road Extraction ◽

The Road ◽

Topological Features ◽

Important Research Topic ◽

Wide Range ◽

Quantitative Results

Extracting road from high resolution remote sensing (HRRS) images is an economic and effective way to acquire road information, which has become an important research topic and has a wide range of applications. In this paper, we present a novel method for road extraction from HRRS images. Multi-kernel learning is first utilized to integrate the spectral, texture, and linear features of images to classify the images into road and non-road groups. A precise extraction method for road elements is then designed by building road shaped indexes to automatically filter out the interference of non-road noises. A series of morphological operations are also carried out to smooth and repair the structure and shape of the road element. Finally, based on the prior knowledge and topological features of the road, a set of penalty factors and a penalty function are constructed to connect road elements to form a complete road network. Experiments are carried out with different sensors, different resolutions, and different scenes to verify the theoretical analysis. Quantitative results prove that the proposed method can optimize the weights of different features, eliminate non-road noises, effectively group road elements, and greatly improve the accuracy of road recognition.

Download Full-text