Deep-Learning-Based Edge Detection for Improving Building Footprint Extraction from Satellite Images

Ahmadian, Nima; Sedaghat, Amin; Mohammadi, Nazila; Aghdami-Nia, Mohammad

doi:10.3390/ecrs2023-16615

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the computer vision applications to the industry realm, Ahmadian et al [2] developed a deep-learning-based edge detection to improve building footprint extraction from satellite images. A common issue in these target applications is that the resulting edge maps are sensitive to noise; thus, this study focused on reducing noise in the edges computed from images of buildings that may affect boundary resolution.…”

Section: Introductionmentioning

confidence: 99%

A New Class of Edge Filter Based on a Cross-correlation-like Equation Derived from Fractional Calculus Principles

Gonzalez-Lee,

Vazquez-Leal,

Garcia-Martinez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this paper, we propose a new sliding window edge-oriented filter that computes the output pixels using a cross-correlation-like equation derived from the principles of fractional calculus (FC); thus, we call it the “fractional cross-correlation filter” (FCCF). We assessed the performance of this filter utilizing exclusively edge-preservation-oriented metrics such as the gradient conduction mean square error (GCMSE), the edge-based structural similarity (EBSSIM), and the multi-scale structural similarity (MS-SSIM); we conducted a statistical assessment of the performance of the filter based on those metrics by using the Berkeley segmentation dataset benchmark as a test corpus. Experimental data reveal that our approach achieves higher performance compared to conventional edge filters for all the metrics considered in this study. This is supported by the statistical analysis we carried out; specifically, the FCCF demonstrates a consistent enhancement in edge detection. We also conducted additional experiments for determining the main filter parameters, which we found to be optimal for a broad spectrum of images. The results underscore the FCCF’s potential to make significant contributions to the advancement of image processing techniques since many practical applications such as medical imaging, image enhancement, and computer vision rely heavily on edge detection filters.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Class of Edge Filter Based on a Cross-correlation-like Equation Derived from Fractional Calculus Principles

Gonzalez-Lee,

Vazquez-Leal,

Garcia-Martinez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Deep-Learning-Based Edge Detection for Improving Building Footprint Extraction from Satellite Images

Abstract: This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

Cited by 1 publication

References 15 publications

A New Class of Edge Filter Based on a Cross-correlation-like Equation Derived from Fractional Calculus Principles

A New Class of Edge Filter Based on a Cross-correlation-like Equation Derived from Fractional Calculus Principles

Contact Info

Product

Resources

About