Detection and Identification of Remnant PFM-1 ‘Butterfly Mines’ with a UAV-Based Thermal-Imaging Protocol

Nikulin, Alex; Smet, Timothy S. de; Baur, Jasper; Frazer, W. D.; Abramowitz, Jacob

doi:10.3390/rs10111672

Cited by 23 publications

(20 citation statements)

References 45 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Can Faster R-CNN be used to automate the detection and map the coordinates of these mines? Previous research has demonstrated the efficacy of thermal imaging to detect the PFM-1 in static and active field trials [10][11][12]. This study expands upon those results by demonstrating the ability of a low-cost plug-and-play multispectral sensor to detect scatterable surface-laid antipersonnel landmines in the visible light, green, red, red-edge, and near-infrared bands of the electromagnetic spectrum.…”

Section: Discussionsupporting

confidence: 66%

“…Following the stationary proof-of-concept phase, we deployed an unmanned aerial vehicle (UAV) with a mounted infrared camera to remotely collect automated time-lapse thermal surveys over simulated minefields seeded with inert PFM-1 mines and aluminum elements of the KSF-1 casing. Dynamic UAV datasets confirmed that PFM-1 mines yielded statistically significant (and remotely detectable) temperature differences between the polyethylene bodies of the landmines and their host environments, both in direct thermal comparisons and in time-lapse DATI datasets [11].…”

Section: Landmine Overviewmentioning

confidence: 62%

“…The FLIR Vue Pro 13 mm has a resolution of 640 × 512 pixels, collects thermal infrared spectral data and is exported as a 14 bit raw TIF file from ThermoViewer export. A previous study on the PFM-1 showed that long wave infrared (LWIR) imagery had an average detection sensitivity rate of 77.88% [11], as well as additional studies [41][42][43][44] demonstrating the effectiveness of thermal infrared sensing for landmine detection. The Parrot Sequoia is equipped with an RGB camera which has a 4.88 mm focal length, a resolution of 4608 × 3456 pixels and is exported as a JPG file.…”

Section: Instrumentationmentioning

confidence: 98%

See 2 more Smart Citations

Applying Deep Learning to Automate UAV-Based Detection of Scatterable Landmines

et al. 2020

Self Cite

View full text Add to dashboard Cite

Recent advances in unmanned-aerial-vehicle-(UAV-) based remote sensing utilizing lightweight multispectral and thermal infrared sensors allow for rapid wide-area landmine contamination detection and mapping surveys. We present results of a study focused on developing and testing an automated technique of remote landmine detection and identification of scatterable antipersonnel landmines in wide-area surveys. Our methodology is calibrated for the detection of scatterable plastic landmines which utilize a liquid explosive encapsulated in a polyethylene or plastic body in their design. We base our findings on analysis of multispectral and thermal datasets collected by an automated UAV-survey system featuring scattered PFM-1-type landmines as test objects and present results of an effort to automate landmine detection, relying on supervised learning algorithms using a Faster Regional-Convolutional Neural Network (Faster R-CNN). The RGB visible light Faster R-CNN demo yielded a 99.3% testing accuracy for a partially withheld testing set and 71.5% testing accuracy for a completely withheld testing set. Across multiple test environments, using centimeter scale accurate georeferenced datasets paired with Faster R-CNN, allowed for accurate automated detection of test PFM-1 landmines. This method can be calibrated to other types of scatterable antipersonnel mines in future trials to aid humanitarian demining initiatives. With millions of remnant PFM-1 and similar scatterable plastic mines across post-conflict regions and considerable stockpiles of these landmines posing long-term humanitarian and economic threats to impacted communities, our methodology could considerably aid in efforts to demine impacted regions.

show abstract

Section: Discussionsupporting

confidence: 66%

Section: Landmine Overviewmentioning

confidence: 62%

Section: Instrumentationmentioning

confidence: 98%

See 1 more Smart Citation

Applying Deep Learning to Automate UAV-Based Detection of Scatterable Landmines

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Remotely piloted aircraft systems (RPAS) provide special advantages over other platforms, in particular high GSD, and more economical preparations for performing and collecting data in smaller areas. Examples of RPAS use in landmine detection can be found in [37][38][39], and indicators of mine presence detection in [40,41].…”

Section: Introductionmentioning

confidence: 99%

The AIDSS Module for Data Acquisition in Crisis Situations and Environmental Protection

Krtalić

Bajić²,

Ivelja

et al. 2020

Sensors

View full text Add to dashboard Cite

The Toolbox implementation for removal of antipersonnel mines, submunitions and unexploded ordnance (TIRAMISU) Advanced Intelligence Decision Support System is an operational system proposed to Mine Action Centres worldwide for conducting non-technical surveys in humanitarian demining. The system consists of three modules, one of which is the module for data acquisition introduced and described in this study. The module has been designed, produced, improved, used and operationally tested and validated on several platforms (helicopters, remotely piloted aircraft systems (RPAS) and a blimp), with various sensors and acquisition units (Global Positioning System (GPS) and inertial measurement unit) in a variety of combinations for additional data acquisition from deep inside a suspected hazardous area. For the purposes of aerial data acquisition over a suspected hazardous area, the use of multiple sensors such as visible digital cameras and multi-spectral visible, near infrared (VNIR), hyperspectral VNIR and thermal infrared sensors are of benefit, because they display the scene in different ways. Off-the-shelf equipment and software were mostly used, but some specific equipment, such as sensor pods, was developed and also some software solutions for data acquisition and pre-processing (transforming hyperspectral line scanner data into hyperspectral images, and producing hyperspectral cubes). The technical stability and robustness of the module were confirmed by operationally testing and evaluating the systems on the aforementioned platforms and missions in several actual suspected hazardous areas in Croatia and Bosnia and Herzegovina, between 2001 and 2015.

show abstract

“…The authors thank the Urs Endress foundation for supporting this work. https://www.ue-stiftung.org as "butterfly mine" [2] which has been used extensively in Afghanistan. This mine exhibits an elongated aluminium cylinder in the center surrounded by an explosive filled plastic cover in the form of a butterfly wing.…”

Section: Introductionmentioning

confidence: 99%

Uav-Based Polarimetric Synthetic Aperture Radar for Mine Detection

Burr

Schartel

Mayer

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

In this contribution a polarimetric side-looking synthetic aperture radar (SAR) mounted on a unmanned aerial vehicle (UAV) is presented and discussed with respect to the detection and localization of landmines. As an example for an anti-personal mine a PFM-1 which contains an elongated aluminium rod was considered. Such anisotropic geometries exibit a polarization dependend radar cross section (RCS). Through a special configuration of three antennas, polarimetric SAR measurements involving a back projection algorithm could be implemented. This concept allows for the detection and furthermore the classification of such anisotropic objects. First field tests using a tachymeter for localization of the UAV over a snow covered meadow successfully demonstrated the performance by the detection of small metal rods depending on their orientation with respect to the flight path of the UAV. These experimental results were supported by simulations expressing the necessity of polarimetric measurements in combination with a distinct flight trajectory for a robust detection of certain landmines.

show abstract

Detection and Identification of Remnant PFM-1 ‘Butterfly Mines’ with a UAV-Based Thermal-Imaging Protocol

Cited by 23 publications

References 45 publications

Applying Deep Learning to Automate UAV-Based Detection of Scatterable Landmines

Applying Deep Learning to Automate UAV-Based Detection of Scatterable Landmines

The AIDSS Module for Data Acquisition in Crisis Situations and Environmental Protection

Uav-Based Polarimetric Synthetic Aperture Radar for Mine Detection

Contact Info

Product

Resources

About