{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T19:00:03Z","timestamp":1774292403849,"version":"3.50.1"},"reference-count":31,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"publisher","award":["Contract P2-0041"],"award-info":[{"award-number":["Contract P2-0041"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>A few promising solutions for thermal imaging Unexploded Ordnance (UXO) detection were proposed after the start of the military conflict in Ukraine in 2014. At the same time, most of the landmine clearance protocols and practices are based on old, 20th-century technologies. More than 60 countries worldwide are still affected by explosive remnants of war, and new areas are contaminated almost every day. To date, no automated solutions exist for surface UXO detection by using thermal imaging. One of the reasons is also that there are no publicly available data. This research bridges both gaps by introducing an automated UXO detection method, and by publishing thermal imaging data. During a project in Bosnia and Herzegovina in 2019, an organisation, Norwegian People\u2019s Aid, collected data about unexploded ordnances and made them available for this research. Thermal images with a size of 720 \u00d7 480 pixels were collected by using an Unmanned Aerial Vehicle at a height of 3 m, thus achieving a very small Ground Sampling Distance (GSD). One of the goals of our research was also to verify if the explosive war remnants\u2019 detection accuracy could be improved further by using Convolutional Neural Networks (CNN). We have experimented with various existing modern CNN architectures for object identification, whereat the YOLOv5 model was selected as the most promising for retraining. An eleven-class object detection problem was solved primarily in this study. Our data were annotated semi-manually. Five versions of the YOLOv5 model, fine-tuned with a grid-search, were trained end-to-end on randomly selected 640 training and 80 validation images from our dataset. The trained models were verified on the remaining 88 images from our dataset. Objects from each of the eleven classes were identified with more than 90% probability, whereat the Mean Average Precision (mAP) at a 0.5 threshold was 99.5%, and the mAP at thresholds from 0.5 to 0.95 was 87.0% up to 90.5%, depending on the model\u2019s complexity. Our results are comparable to the state-of-the-art, whereat these object detection methods have been tested on other similar small datasets with thermal images. Our study is one of the few in the field of Automated UXO detection by using thermal images, and the first that solves the problem of identifying more than one class of objects. On the other hand, publicly available thermal images with a relatively small GSD will enable and stimulate the development of new detection algorithms, where our method and results can serve as a baseline. Only really accurate automatic UXO detection solutions will help to solve one of the least explored worldwide life-threatening problems.<\/jats:p>","DOI":"10.3390\/rs15040967","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T05:51:06Z","timestamp":1676008266000},"page":"967","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["UAV Thermal Imaging for Unexploded Ordnance Detection by Using Deep Learning"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8207-9805","authenticated-orcid":false,"suffix":"Jr.","given":"Milan","family":"Baji\u0107","sequence":"first","affiliation":[{"name":"Department of IT and Computer Sciences, Zagreb University of Applied Sciences, 10000 Zagreb, Croatia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5140-3358","authenticated-orcid":false,"given":"Bo\u017eidar","family":"Poto\u010dnik","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Faculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, Slovenia"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Manickavasagan, A., and Jayasuriya, H. (2014). Imaging with Electromagnetic Spectrum, Springer.","DOI":"10.1007\/978-3-642-54888-8"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Messina, G., and Modica, G. (2020). Applications of UAV Thermal Imagery in Precision Agriculture: State of the Art and Future Research Outlook. Remote Sens., 12.","DOI":"10.3390\/rs12091491"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1080\/03071847709428741","article-title":"Thermal Imaging and its Military Applications","volume":"122","author":"Harrison","year":"1977","journal-title":"RUSI J."},{"key":"ref_4","unstructured":"Kuenzer, C., and Dech, S. (2013). Remote Sensing and Digital Image Processing, Springer."},{"key":"ref_5","unstructured":"Roberts, S., and Williams, J. (1995). After the Guns Fall Silent: The Enduring Legacy of Landmines, Oxfam."},{"key":"ref_6","unstructured":"GICHD (2022, December 15). Explosive Ordnance Guide for Ukraine\u2014Second Edition. Available online: https:\/\/www.gichd.org\/fileadmin\/GICHD-resources\/rec-documents\/GICHD_Ukraine_Guide_2022_Second_Edition_web.pdf."},{"key":"ref_7","unstructured":"(2022, December 15). Types of Explosive Ordances. Available online: https:\/\/www.gichd.org\/en\/explosive-ordnance\/."},{"key":"ref_8","unstructured":"Bajic, M. (2020). Testing of Remotely Piloted Aircraft Systems with a Thermal Infrared Camera to Detect Explosive Devices at Con-Taminated Areas and Validation of Developed Standard Operational Procedures, Norwegian Peoples Aid."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1002\/rob.21985","article-title":"Object detection, recognition, and tracking from UAVs using a thermal camera","volume":"38","author":"Leira","year":"2021","journal-title":"J. Field Robot."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.1007\/s10489-020-01882-2","article-title":"TIRNet: Object detection in thermal infrared images for autonomous driving","volume":"51","author":"Dai","year":"2020","journal-title":"Appl. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Banuls, A., Mandow, A., Vazquez-Martin, R., Morales, J., and Garcia-Cerezo, A. (2020, January 4). Object Detection from Thermal Infrared and Visible Light Cameras in Search and Rescue Scenes. Proceedings of the 2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/SSRR50563.2020.9292593"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nikulin, A., De Smet, T.S., Baur, J., Frazer, W.D., and Abramowitz, J.C. (2018). Detection and Identification of Remnant PFM-1 \u2018Butterfly Mines\u2019 with a UAV-Based Thermal-Imaging Protocol. Remote Sens., 10.","DOI":"10.3390\/rs10111672"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Krause, P., Salahat, E., and Franklin, E. (2018, January 21-23). Diurnal Thermal Dormant Landmine Detection Using Unmanned Aerial Vehicles. Proceedings of the IECON 2018\u201444th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA.","DOI":"10.1109\/IECON.2018.8591378"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yao, Y., Wen, M., and Wang, Y. (2019, January 5\u20137). Multi-Temporal IR Thermography For Mine Detection. Proceedings of the 2019 10th Interna-tional Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), Shanghai, China.","DOI":"10.1109\/Multi-Temp.2019.8866906"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Baur, J., Steinberg, G., Nikulin, A., Chiu, K., and de Smet, T.S. (2020). Applying Deep Learning to Automate UAV-Based Detection of Scatterable Landmines. Remote Sens., 12.","DOI":"10.3390\/rs12050859"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"125459","DOI":"10.1109\/ACCESS.2020.3007481","article-title":"Thermal Object Detection in Difficult Weather Conditions Using YOLO","volume":"8","author":"Kristo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"55546","DOI":"10.1109\/ACCESS.2022.3177628","article-title":"YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection","volume":"10","author":"Kong","year":"2022","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"141861","DOI":"10.1109\/ACCESS.2021.3120870","article-title":"YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection","volume":"9","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"116793","DOI":"10.1016\/j.eswa.2022.116793","article-title":"Remote sensing image super-resolution and object detection: Benchmark and state of the art","volume":"197","author":"Wang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_21","unstructured":"Baji\u0107, M., and Poto\u010dnik, B. (2022, December 15). UXOTi_NPA 11 class UXO thermal images dataset. Available online: https:\/\/github.com\/MilanBajicjr\/UXOTi_NPA."},{"key":"ref_22","unstructured":"(2022, December 15). Zenmuse XT. Available online: https:\/\/www.dji.com\/hr\/Zenmuse-Xt."},{"key":"ref_23","unstructured":"(2022, December 15). CVAT. Available online: https:\/\/www.Cvat.Ai."},{"key":"ref_24","first-page":"1","article-title":"A Lightweight Framework for Obstacle Detection in the Railway Image Based on Fast Region Proposal and Improved YOLO-Tiny Network","volume":"71","author":"Guan","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","unstructured":"(2022, December 15). Ultralytics. Available online: https:\/\/Ultralytics.com."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft Coco: Common Objects in Context. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_27","unstructured":"(2022, December 15). YOLOv5 Models. Available online: https:\/\/Github.com\/Ultralytics\/Yolov5."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Mark Liao, H.-Y., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H. (2020, January 14\u201319). CSPNet: A New Backbone That Can Enhance Learning Capability of CNN. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref_29","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18\u201323). Path Aggregation Network for Instance Segmentation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Xu, R., Lin, H., Lu, K., Cao, L., and Liu, Y. (2021). A Forest Fire Detection System Based on Ensemble Learning. Forests, 12.","DOI":"10.3390\/f12020217"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/967\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:29:24Z","timestamp":1760120964000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["rs15040967"],"URL":"https:\/\/doi.org\/10.3390\/rs15040967","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]}}}