You are currently viewing a new version of our website. To view the old version click .
Entropy
  • This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
  • Article
  • Open Access

16 December 2025

A Multi-Feature Fusion-Based Two-Stage Method for Airport Crater Extraction from Remote Sensing Images

,
and
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
*
Author to whom correspondence should be addressed.
This article belongs to the Special Issue Application of Information Theory to Computer Vision and Image Processing, 3rd Edition

Abstract

The accurate extraction of damage information around airport runways is crucial for the rapid development of subsequent damage effect assessment work and the timely formulation of the ensuing operational plan. However, the presence of dark interference areas such as trees and shadows in the background, as well as the increased irregularity at the edge of the crater due to the proximity to the crater, pose challenges to the accurate extraction of the crater area in high entropy images. In this paper, we present a multi-feature fusion-based two-stage method for airport crater extraction from remote sensing images. In stage I, we designed an edge arc segment grouping and matching strategy based on the shape characteristics of craters for preliminary detection. In stage II, we established a crater model based on the regional distribution characteristics of craters and used the marked point processing method for crater detection. In addition, during the step of calculating the magnitude of the edge gradient, we proposed a near-region search strategy, which enhanced the ability of the proposed method to accurately extract craters with irregular shapes. In the test images, the proposed method accurately extracts craters located around and within the runways. Among them, the average recall R and precision P of the proposed method for extracting all craters around the airport runways reached 89% and 87%, respectively, and the average recall R and precision P of the proposed method for extracting craters inside the runways reached 94% and 92%, respectively. Meanwhile, the results of comparative tests showed that our method outperformed other representative algorithms in terms of both crater extraction recall and extraction precision.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.