Detection and classification of landmines using UWB antenna system and ANN analysis
Abstract
Background: The problem of detecting underground objects is found in many areas of human activity in the modern world, for example, a quick survey of the territory for the presence of underground utilities for earthworks, finding the location of grounding structures, cable breakage or short circuit, remote sensing for detecting and mapping of archaeological objects. The issue of humanitarian demining in Donetsk and Lugansk regions is also important in Ukraine. The latest ground surveying devices, such as ultrawideband subsurface radar, have already come to the aid for military sappers in developed countries to make the demining process safer.
Objectives: The goal of this work is to improve the recognition of subsurface objects by using an artificial neural network (ANN) for signal processing, to test the influence of interference in signals coming from ultrawideband antenna system on the reliability of determining the object in the observation area, its type and distance to subsurface radar.
Materials and methods: In this work, the ANN method is used to recognize the hidden objects by ultrawideband subsurface radar. The process of electromagnetic field propagation is simulated by finite time difference method (FDTD). Neural network testing is performed by adding Gaussian noise of different levels in the input signal. Simulation of the problem is performed 1000 times to exclude the randomness of recognition for different realizations of a noise.
Results: Histograms of objects recognition for two types of mines and six types of cans were obtained. A large set of false objects for neural network training gave good results in the detection of antipersonnel mines, which was reflected in the excellent stability of determining the position and type of object, even in the presence of interference with a high signal-to-noise ratio.
Conclusions: The problem of subsurface survey can be solved by using a fully connected neural network with five hidden layers of neurons. It has been determined that the use of artificial intelligence gives good results in the recognition of underground objects, if a high-quality learning data set for ANN will be prepared. Satisfactory stability of noisy signal operation is shown, which gives prospects for further testing of the developed method in application to a subsurface radar in the conditions of a real experiment.
Downloads
References
NATO supports humanitarian demining in Ukraine [Internet]. NATO News. 27 May 2016. Available from:https://www.nato.int/cps/en/natohq/news_131607.htm?selectedLocale=en
Maki KH. Development of robot and navigation techniques for humanitarian demining. 6th IEEE International Conference on Industrial Informatics; 2008 13-16 July Daejeon, South Korea; 2008. https://doi.org/10.1109/INDIN.2008.4618135
Earp SL, Hughes ES, Elkins TJ, Vickers R. Ultra-wideband ground-penetrating radar for the detection of buried metallic mines. Proceedings of the 1996 IEEE National Radar Conference; 1996 13-16 May; USA, Ann Arbor, MI,; 1996. https://doi.org/10.1109/NRC.1996.510648
Taylor JD. Ultrawideband radar: applications and design. Boca Raton, London, NewYork: CRC Press; 2012.
Millot P, Castanet L, Casadebaig L, Maaref N, Gaugue A, Ménard M, Khamlichi J, Louis G, Fortino N, Dauvignac J-Y, Clementi G, Schortgen M, Quellec L, Laroche V. An UWB Through-The-Wall radar with 3D imaging, detection and tracking capabilities. European Radar Conference (EuRAD); 2015 9-11 September; Paris, France; 2015. https://doi.org/10.1109/EuRAD.2015.7346281
Hai-zhong Y, Yu-feng O, Hong C. Application of ground penetrating radar to inspect the metro tunnel. 14th International Conference on Ground Penetrating Radar (GPR); 2012 4-8 June, Shanghai, China; 2012. https://doi.org/10.1109/ICGPR.2012.6254963
Hölbling Z, Mihaldinec H, Ambruš D, Džapo H, Bilas V, Vasić D. UWB localization for discrimination-enabled metal detectors in humanitarian demining. IEEE Sensors Applications Symposium (SAS); 2017 13-15 March; USA, Glassboro, NJ; 2017. https://doi.org/10.1109/SAS.2017.7894073
Morgenthaler A, Rappaport C. Fast GPR underground shape anomaly detection using the Semi-Analytic Mode Matching (SAMM) algorithm. IEEE International Geoscience and Remote Sensing Symposium – IGARSS; 201321-26 July; Australia, Melbourne, VIC; 2013. https://doi.org/10.1109/IGARSS.2013.6723051
Li W. Zhou H, Wan X. Generalized Hough Transform and ANN for subsurface cylindrical object location and parameters inversion from GPR data. 14th International Conference on Ground Penetrating Radar (GPR); 2012 4-8 June; China, Shanghai; 2012. https://doi.org/10.1109/ICGPR.2012.6254874
O Dumin, Plakhtii V, Pryshchenko O, Pochanin G. Comparison of ANN and Cross-Correlation Approaches for Ultra Short Pulse Subsurface Survey. 15th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET – 2020); 2020 February 25-29; Ukraine, Lviv-Slavske; 2020. https://doi.org/10.1109/TCSET49122.2020.235459
Sharma P, Kumar B, Singh D, Gaba SP. Metallic Pipe Detection using SF GPR: A New Approach using Neural Network. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS); 2016 10-15 July; China, Beijing; 2016. https://doi.org/10.1109/IGARSS.2016.7730726
Callan R. The essence of neural networks. New York: Prentice Hall Europe; 1999.
Dumin OM, Plakhtii VA, Pryshchenko OA, Shyrokorad DV. Recognition of objects under the earth's surface by ultra-wideband radio introscopy using artificial neural networks. Visnyk of V.N. Karazin Kharkiv National University, series “Radio Physics and Electronics”. 2018;28:24–29. [In Ukrainian].
Dumin OM, Plakhtii VA, Pryshchenko OA, Shyrokorad DV, Volvach YaS. The effect of reducing the noise of the input signal on the classification of the location of the object by an artificial neural network in ultra-wideband radio introscopy. Visnyk of V.N. Karazin Kharkiv National University, series “Radio Physics and Electronics”. 2019;31:27–35 [In Ukrainian]. https://doi.org/10.26565/2311-0872-2019-31-03
Dumin OM, Plakhtii VA, Pryshchenko OA, Shyrokorad DV. Discrete tomography method in data processing of ultra-wideband subsurface radar by artificial neural network. Visnyk of V.N. Karazin Kharkiv National University, series “Radio Physics and Electronics”. 2018;29:17–26. [In Ukrainian]. https://doi.org/10.26565/2311-0872-2018-29-03
Pochanin G, Capineri L, Bechtel T, Falorni P, Borgioli G, Ruban V, Orlenko O, Ogurtsova T, Pochanin O, Crawford F, Kholod P, Bossi L. Measurement of Coordinates for a Cylindrical Target Using Times of Flight from a 1-Transmitter and 4-Receiver UWB Antenna System. IEEE Transactions on Geoscience and Remote Sensing. 2020;58(2):1363-1372. https://doi.org/10.1109/TGRS.2019.2946064
Duque A, Perry W, Anderson-Cook C. Complex Microwave Permittivity of Secondary High Explosives. Propellants Explosives Pyrotechnics. 2013;39(2):275-283. https://doi.org/10.1002/prep.201300032
Vander Gaasta B, McFeeb J, Russella K, Fausta A. Design and validation of inert homemade explosive simulants for Ground Penetrating Radar. Proc. SPIE 9454, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX; 2015 20-24 April; USA, Baltimore, Maryland; 2015 21 May. 945412 https://doi.org/10.1117/12.2175586
Zafrir H, Bregman Y, Wolf D, Hershler S. Super-sensitive, real time and wide coverage, all terrain ground robotic and hand held systems for mine and UXO detection and mapping. 1998 Second International Conference on the Detection of Abandoned Land Mines; 1998 12-14 October; UK, Edinburgh; IEE Conf. Publ. No. 458; 1998. https://doi.org/10.1049/cp:19980721
Dumin O, Pryshchenko O, Plakhtii V, Pochanin G. Landmine detection and classification using UWB antenna system and ANN analysis. 2020 IEEE Ukrainian Microwave Week (UkrMW); 2020 September 21-25; Ukraine, Kharkiv; 2020. p. 1030–1035. https://doi.org/10.1109/UkrMW49653.2020.9252574
