2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images

Recently, intelligence-based hotspot detection has been widely used in solar photovoltaic (PV) image applications. However, the semantic segmentation approach has limitations in terms of accuracy, particularly for hotspot thermal images. This study introduces a novel method based on Two-tier Semanti...

Full description

Bibliographic Details
Main Authors: Nurul Huda, Ishak, Iza Sazanita, Isa, Muhammad Khusairi, Osman, Mohd Shawal, Jadin, Kamarulazhar, Daud, Mohd Zulhamdy, Ab Hamid
Format: Article
Language:English
Published: IEEE 2025
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/45020/
http://umpir.ump.edu.my/id/eprint/45020/1/2TSS-%20Two-tier%20semantic%20segmentation%20framework%20with%20enhancement.pdf
_version_ 1848827237809258496
author Nurul Huda, Ishak
Iza Sazanita, Isa
Muhammad Khusairi, Osman
Mohd Shawal, Jadin
Kamarulazhar, Daud
Mohd Zulhamdy, Ab Hamid
author_facet Nurul Huda, Ishak
Iza Sazanita, Isa
Muhammad Khusairi, Osman
Mohd Shawal, Jadin
Kamarulazhar, Daud
Mohd Zulhamdy, Ab Hamid
author_sort Nurul Huda, Ishak
building UMP Institutional Repository
collection Online Access
description Recently, intelligence-based hotspot detection has been widely used in solar photovoltaic (PV) image applications. However, the semantic segmentation approach has limitations in terms of accuracy, particularly for hotspot thermal images. This study introduces a novel method based on Two-tier Semantic Segmentation (2TSS) framework explicitly aimed at enhancing hotspot detection in thermal images of PV modules. The proposed method is designed with two subsequent stages of segmentation models, including image pre-processing at the initial of the framework. The first tier of segmentation distinguishes between solar PV modules and the background, whilst the second tier enhances the hotspot localization region. This research enhances comprehension of multi-tier segmentation architectures in deep learning, focusing on optimizing performance for solar energy systems through comparative analysis of semantic models. Three different segmentation models, namely U-Net, ResNet 18 and ResNet 50 were tested. The ResNet 50 model demonstrated superior segmentation performance across both tiers with 98% and 85% accuracy respectively. In summary, the proposed method demonstrates that applying a combined enhancement algorithm prior to training for hotspot segmentation promotes superior performance with an accuracy improvement of 2.26% over the non-enhancement approach.
first_indexed 2025-11-15T03:57:32Z
format Article
id ump-45020
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:57:32Z
publishDate 2025
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling ump-450202025-07-07T01:05:25Z http://umpir.ump.edu.my/id/eprint/45020/ 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images Nurul Huda, Ishak Iza Sazanita, Isa Muhammad Khusairi, Osman Mohd Shawal, Jadin Kamarulazhar, Daud Mohd Zulhamdy, Ab Hamid QA75 Electronic computers. Computer science TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering Recently, intelligence-based hotspot detection has been widely used in solar photovoltaic (PV) image applications. However, the semantic segmentation approach has limitations in terms of accuracy, particularly for hotspot thermal images. This study introduces a novel method based on Two-tier Semantic Segmentation (2TSS) framework explicitly aimed at enhancing hotspot detection in thermal images of PV modules. The proposed method is designed with two subsequent stages of segmentation models, including image pre-processing at the initial of the framework. The first tier of segmentation distinguishes between solar PV modules and the background, whilst the second tier enhances the hotspot localization region. This research enhances comprehension of multi-tier segmentation architectures in deep learning, focusing on optimizing performance for solar energy systems through comparative analysis of semantic models. Three different segmentation models, namely U-Net, ResNet 18 and ResNet 50 were tested. The ResNet 50 model demonstrated superior segmentation performance across both tiers with 98% and 85% accuracy respectively. In summary, the proposed method demonstrates that applying a combined enhancement algorithm prior to training for hotspot segmentation promotes superior performance with an accuracy improvement of 2.26% over the non-enhancement approach. IEEE 2025 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/45020/1/2TSS-%20Two-tier%20semantic%20segmentation%20framework%20with%20enhancement.pdf Nurul Huda, Ishak and Iza Sazanita, Isa and Muhammad Khusairi, Osman and Mohd Shawal, Jadin and Kamarulazhar, Daud and Mohd Zulhamdy, Ab Hamid (2025) 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images. IEEE Access, 13. pp. 88888-88904. ISSN 2169-3536. (Published) https://doi.org/10.1109/ACCESS.2025.3570974 https://doi.org/10.1109/ACCESS.2025.3570974
spellingShingle QA75 Electronic computers. Computer science
TA Engineering (General). Civil engineering (General)
TK Electrical engineering. Electronics Nuclear engineering
Nurul Huda, Ishak
Iza Sazanita, Isa
Muhammad Khusairi, Osman
Mohd Shawal, Jadin
Kamarulazhar, Daud
Mohd Zulhamdy, Ab Hamid
2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title_full 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title_fullStr 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title_full_unstemmed 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title_short 2TSS: Two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
title_sort 2tss: two-tier semantic segmentation framework with enhancement for hotspot detection of solar photovoltaic thermal images
topic QA75 Electronic computers. Computer science
TA Engineering (General). Civil engineering (General)
TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/45020/
http://umpir.ump.edu.my/id/eprint/45020/
http://umpir.ump.edu.my/id/eprint/45020/
http://umpir.ump.edu.my/id/eprint/45020/1/2TSS-%20Two-tier%20semantic%20segmentation%20framework%20with%20enhancement.pdf