EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Road Network Index: A Novel Spectral Index for Urban Road Network Extraction from Landsat Imagery

Yashwant Soni, Uma Meena, Vikash Mishra

Journal of Applied Science and Technology Trends · 19.04.2026 · 7 (1) · 223-231

DOI: 10.38094/jastt71788 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Science and Technology Trends, online erschienen am 19.04.2026. Verfasst von Yashwant Soni und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban road information extraction from low- to medium-resolution remote sensing imagery remains challenging due to the limited spectral separability between road surfaces and surrounding urban features. This work proposes a road network index (RNI), a novel spectral index for urban road network extraction, to delineate the urban road network from Landsat satellite imagery. In the first step, the Landsat data is pre-processed to handle the atmospheric correction followed by the selection of the spectral bands used to develop RNI by performing spectral analysis. The proposed RNI is used for the identification of road information from Landsat imagery, and the road and non-road information is separated using thresholding. Furthermore, the non-road components are eliminated by using geometric feature analysis. By applying RNI to Landsat multispectral imagery, we can extract urban road networks accurately and efficiently. Results reveal that RNI is automated, convenient in asphalt road extraction from medium-resolution satellite imagery. Experimental results demonstrate that the proposed approach achieves an overall accuracy of 91.67%, a Kappa coefficient of 0.8334, and an F1-score of 91.64%, indicating strong agreement and balance between precision and recall. These findings confirm that RNI provides an automated and reliable solution for asphalt road extraction from medium-resolution satellite imagery, particularly in complex urban environments.

Zitieren

APA

Soni, Y., Meena, U., & Mishra, V. (2026). Road Network Index: A Novel Spectral Index for Urban Road Network Extraction from Landsat Imagery. Journal of Applied Science and Technology Trends, 7(1), 223-231. https://doi.org/10.38094/jastt71788

Vancouver

Soni Y, Meena U, Mishra V. Road Network Index: A Novel Spectral Index for Urban Road Network Extraction from Landsat Imagery. Journal of Applied Science and Technology Trends. 2026;7(1):223-231. doi:10.38094/jastt71788

BibTeX
@article{Soni2026,
  author = {Soni, Yashwant and Meena, Uma and Mishra, Vikash},
  title = {Road Network Index: A Novel Spectral Index for Urban Road Network Extraction from Landsat Imagery},
  journal = {Journal of Applied Science and Technology Trends},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {223--231},
  doi = {10.38094/jastt71788}
}
Kostenlos starten →