Post-Processing for Shadow Detection in Drone-Acquired Images Using U-NET

Citation

Zali, Siti Aisyah and Mat Desa, Shahbe and Che Embi, Zarina and Mohd Isa, Wan Noorshahida (2022) Post-Processing for Shadow Detection in Drone-Acquired Images Using U-NET. Future Internet, 14 (8). p. 231. ISSN 1999-5903

[img] Text
futureinternet-14-00231-v2.pdf - Published Version
Restricted to Repository staff only

Download (2MB)

Abstract

Shadows in drone images commonly appear in various shapes, sizes, and brightness levels, as the images capture a wide view of scenery under many conditions, such as varied flying height and weather. This property of drone images leads to a major problem when it comes to detecting shadow and causes the presence of noise in the predicted shadow mask. The purpose of this study is to improve shadow detection results by implementing post-processing methods related to automatic thresholding and binary mask refinement. The aim is to discuss how the selected automatic thresholding and two methods of binary mask refinement perform to increase the efficiency and accuracy of shadow detection. The selected automatic thresholding method is Otsu’s thresholding, and methods for binary mask refinement are morphological operation and dense CRF. The study shows that the proposed methods achieve an acceptable accuracy of 96.43%.

Item Type: Article
Uncontrolled Keywords: Shadow detection, deep learning, U-Net, aerial images, automatic thresholding, binary mask refinement, post-processing
Subjects: Q Science > QC Physics > QC350-467 Optics. Light
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 07 Oct 2022 02:49
Last Modified: 07 Oct 2022 02:49
URII: http://shdl.mmu.edu.my/id/eprint/10508

Downloads

Downloads per month over past year

View ItemEdit (login required)