Authors
Mykhailo O Popov, Sergey A Stankevich, Sergey P Mosov, Ievgen Y Saprykin
Published in
Journal of emergency management (Weston, Mass.). Volume 24. Issue 7. Pages 109-116.
Abstract
Robotic landmine detection is considered to be a highly promising solution for safe and cost-effective humanitarian demining of large areas. A lot of research has been devoted to landmine detection with unmanned aerial vehicles (UAVs). The problem is the insufficient reliability of landmine detection using any of the known types of physical sensors mounted on UAVs. In this paper, a novel approach to landmine detection using an UAV is proposed. This approach is based on extracting information about the presence or absence of landmines using both optical images and signals obtained from nonimaging sensors installed on the UAV. Optical sensors include multi- or hyperspectral cameras and thermal infrared cameras. Nonimaging sensors can be onboard magnetometers and ground-penetrating radars. A smart combination of different types of physical sensors can significantly improve the reliability of landmine detection. We use Bayesian data fusion obtained under the unified probabilistic model for landmine detection by each of the UAV optical and signal sensors involved.
PMID:
43062228
Bibliographic data and abstract were imported from PubMed on 20 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 2
- Comments 0