Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones
The pervasive threat of landmines across conflict-affected regions necessitates advancements in detection technologies to enhance safety and efficiency in demining efforts. Furthermore, the development of a solution that can be effectively utilized in both resource-rich and resource-poor environment...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11008598/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471978620059648 |
|---|---|
| author | Daniel Heuschmid Oliver Wacker Yannick Zimmermann Pascal Penava Ricardo Buettner |
| author_facet | Daniel Heuschmid Oliver Wacker Yannick Zimmermann Pascal Penava Ricardo Buettner |
| author_sort | Daniel Heuschmid |
| collection | DOAJ |
| description | The pervasive threat of landmines across conflict-affected regions necessitates advancements in detection technologies to enhance safety and efficiency in demining efforts. Furthermore, the development of a solution that can be effectively utilized in both resource-rich and resource-poor environments is essential, as many conflict-affected regions lack the financial means or technical infrastructure to deploy expensive and complex detection technologies. This paper introduces a deep learning-based approach utilizing uncrewed aerial vehicles equipped with thermal imaging cameras for landmine detection. Leveraging the MobileNetV3-Large architecture and building upon it, we propose a lightweight, yet powerful, machine learning model that can be seen as a safe, cost-efficient and fast landmine detection method. We evaluated our approach using a unique dataset comprising 2,700 thermographic images captured by a DJI Matrice 100 drone with a Zenmuse XT infrared camera. Through meticulous data pre-processing and augmentation strategies, we enhance the model’s ability to generalize across different terrains and mine types, addressing one of the primary challenges in landmine detection. The evaluation of our model on a rigorously curated test set demonstrates promising results, achieving a training accuracy of 96.97 %, a validation accuracy of 97.19 %, and a test accuracy of 96.14 %. These metrics not only demonstrate the model’s effectiveness in identifying landmines from thermal images but also highlight its potential to outperform other thermal approaches in real-world demining operations. This supports the application of uncrewed aerial vehicles and deep learning technologies in humanitarian and environmental challenges. |
| format | Article |
| id | doaj-art-6e32f4ab559342babb9cddf8348143d0 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6e32f4ab559342babb9cddf8348143d02025-08-20T03:24:39ZengIEEEIEEE Access2169-35362025-01-0113917779179410.1109/ACCESS.2025.357219611008598Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal DronesDaniel Heuschmid0https://orcid.org/0009-0003-9678-1082Oliver Wacker1https://orcid.org/0009-0005-5814-671XYannick Zimmermann2Pascal Penava3https://orcid.org/0009-0004-9870-8193Ricardo Buettner4https://orcid.org/0000-0003-2263-6408Chair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, GermanyChair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, GermanyChair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, GermanyChair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, GermanyChair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, GermanyThe pervasive threat of landmines across conflict-affected regions necessitates advancements in detection technologies to enhance safety and efficiency in demining efforts. Furthermore, the development of a solution that can be effectively utilized in both resource-rich and resource-poor environments is essential, as many conflict-affected regions lack the financial means or technical infrastructure to deploy expensive and complex detection technologies. This paper introduces a deep learning-based approach utilizing uncrewed aerial vehicles equipped with thermal imaging cameras for landmine detection. Leveraging the MobileNetV3-Large architecture and building upon it, we propose a lightweight, yet powerful, machine learning model that can be seen as a safe, cost-efficient and fast landmine detection method. We evaluated our approach using a unique dataset comprising 2,700 thermographic images captured by a DJI Matrice 100 drone with a Zenmuse XT infrared camera. Through meticulous data pre-processing and augmentation strategies, we enhance the model’s ability to generalize across different terrains and mine types, addressing one of the primary challenges in landmine detection. The evaluation of our model on a rigorously curated test set demonstrates promising results, achieving a training accuracy of 96.97 %, a validation accuracy of 97.19 %, and a test accuracy of 96.14 %. These metrics not only demonstrate the model’s effectiveness in identifying landmines from thermal images but also highlight its potential to outperform other thermal approaches in real-world demining operations. This supports the application of uncrewed aerial vehicles and deep learning technologies in humanitarian and environmental challenges.https://ieeexplore.ieee.org/document/11008598/Convolutional neural networkdeep learninglandmine detectionMobileNetV3thermal imaginguncrewed aerial vehicles |
| spellingShingle | Daniel Heuschmid Oliver Wacker Yannick Zimmermann Pascal Penava Ricardo Buettner Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones IEEE Access Convolutional neural network deep learning landmine detection MobileNetV3 thermal imaging uncrewed aerial vehicles |
| title | Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones |
| title_full | Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones |
| title_fullStr | Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones |
| title_full_unstemmed | Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones |
| title_short | Advancements in Landmine Detection: Deep Learning-Based Analysis With Thermal Drones |
| title_sort | advancements in landmine detection deep learning based analysis with thermal drones |
| topic | Convolutional neural network deep learning landmine detection MobileNetV3 thermal imaging uncrewed aerial vehicles |
| url | https://ieeexplore.ieee.org/document/11008598/ |
| work_keys_str_mv | AT danielheuschmid advancementsinlandminedetectiondeeplearningbasedanalysiswiththermaldrones AT oliverwacker advancementsinlandminedetectiondeeplearningbasedanalysiswiththermaldrones AT yannickzimmermann advancementsinlandminedetectiondeeplearningbasedanalysiswiththermaldrones AT pascalpenava advancementsinlandminedetectiondeeplearningbasedanalysiswiththermaldrones AT ricardobuettner advancementsinlandminedetectiondeeplearningbasedanalysiswiththermaldrones |