Efficient Underground Object Detection for Ground Penetrating Radar Signals

  • Ibrahim Mesecan Epoka University
  • Ihsan Omur Bucak Meliksah University
Keywords: Ground penetrating radar, B-scan images, Image processing, Object detection, N-row average subtraction


Ground penetrating radar (GPR) is one of the common sensor system for underground inspection. GPR emits electromagnetic waves which can pass through objects. The reflecting waves are recorded and digitised, and then, the B-scan images are formed. According to the properties of scanning object, GPR creates higher or lower intensity values on the object regions. Thus, these changes in signal represent the properties of scanning object. This paper proposes a 3-step method to detect and discriminate landmines: n-row average-subtraction (NRAS); Min-max normalisation; and image scaling. Proposed method has been tested using 3 common algorithms from the literature. According to the results, it has increased object detection ratio and positive object discrimination (POD) significantly. For artificial neural networks (ANN), POD has increased from 77.4 per cent to 87.7 per cent. And, it has increased from 37.8 per cent to 80.2 per cent, for support vector machines (SVM).

Author Biographies

Ibrahim Mesecan, Epoka University
Mr Ibrahim Mesecan obtained his MSc (Software Engineering) in 1999. Currently pursuing his PhD at Mevlana university Konya, Turkey since 2012. Presently working as a Lecturer at Epoka University, Tirana, Albania. He has published three research articles and three books. His main interests are : Computer vision and pattern recognition.
Ihsan Omur Bucak, Meliksah University
Dr Ihsan Omur Bucak obtained his BS and MS, Istanbul Technical University, PhD, Oakland University, Rochester, Michigan, 2000. He is currently working as full-time Associate Professor at Meliksah University, Kayseri-Turkey. Research strength mainly lies on control systems, signal processing, artificial intelligence, and bioinformatics. His special interests are hybrid electric vehicles and power train controls.
How to Cite
Mesecan, I., & Bucak, I. (2016). Efficient Underground Object Detection for Ground Penetrating Radar Signals. Defence Science Journal, 67(1), 12-18. https://doi.org/10.14429/dsj.1.9063
Armaments & Explosives