{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/landmine-detection-using-autoencoders-on","title":"Landmine Detection Using Autoencoders on Multi-polarization GPR Volumetric Data","arxiv_id":"1810.01316","date":"2018-10-02","proceeding":null,"authors":["Paolo Bestagini","Federico Lombardi","Maurizio Lualdi","Francesco Picetti","Stefano Tubaro"],"abstract":"Buried landmines and unexploded remnants of war are a constant threat for the\npopulation of many countries that have been hit by wars in the past years. The\nhuge amount of human lives lost due to this phenomenon has been a strong\nmotivation for the research community toward the development of safe and robust\ntechniques designed for landmine clearance. Nonetheless, being able to detect\nand localize buried landmines with high precision in an automatic fashion is\nstill considered a challenging task due to the many different boundary\nconditions that characterize this problem (e.g., several kinds of objects to\ndetect, different soils and meteorological conditions, etc.). In this paper, we\npropose a novel technique for buried object detection tailored to unexploded\nlandmine discovery. The proposed solution exploits a specific kind of\nconvolutional neural network (CNN) known as autoencoder to analyze volumetric\ndata acquired with ground penetrating radar (GPR) using different\npolarizations. This method works in an anomaly detection framework, indeed we\nonly train the autoencoder on GPR data acquired on landmine-free areas. The\nsystem then recognizes landmines as objects that are dissimilar to the soil\nused during the training step. Experiments conducted on real data show that the\nproposed technique requires little training and no ad-hoc data pre-processing\nto achieve accuracy higher than 93% on challenging datasets.","url_abs":"http://arxiv.org/abs/1810.01316v1","url_pdf":"http://arxiv.org/pdf/1810.01316v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"landmine-detection-using-autoencoders-on","repo_url":"https://github.com/polimi-ispl/landmine_detection_autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"gpr","task_name":"GPR"},{"task_slug":"landmine","task_name":"Landmine"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}