Feature Extraction Method of Urban Road Network Structure Based on Fractal Algorithm

Authors

  • Wen Wen School of Modern Service, Harbin Vocational and Technical College, Harbin 150081, China
  • Hongxing Deng School of Traffic and Transportation, Northeast Forestry University, Harbin 150040, China

Abstract

The structure of an urban road network affects the smoothness of traffic flow. There are several problems with the existing feature extraction methods applied to the urban road network structure, such as the time it takes to extract features and the great number of feature extraction errors. In this paper, a method for extracting urban road network features is designed based on a fractal algorithm. The proposed method involves: analyzing the urban road network structure and road network density, and determining the hierarchical relationship of urban road network structure. The polarized light intensity is reduced by means of the Stokes vector to obtain an image of the urban road network structure. The different gray values of this image
are transformed by the three-component method using the average gray value to obtain the image. The average filtering method is used to complete image preprocessing. The core algorithm of the fractal algorithm is analyzed, the dimension of the urban network structure is divided with the Koch curve, the terrain slope and surface fluctuation of the urban road network structure are determined, and the feature extraction is achieved by means of the fractal algorithm. The experimental results show that the proposed method can effectively improve the accuracy of the feature extraction and
reduce the number of extraction errors. Furthermore, the proposed extraction process is relatively simple, cost-effective, and feasible.

Keywords: Fractal algorithm: urban road network; structural features; extraction method; three-component method; Koch curve

Cite As

W. Wen, H. Deng, "Feature Extraction Method of Urban Road Network Structure Based on Fractal Algorithm", Engineering Intelligent Systems, vol. 31 no. 2, pp. 93-103, 2023.






Downloads

Published

2023-03-01

Issue

Vol. 31 No. 2 (2023): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.