Analysis of modern methods of search and classification of explosive objects

Abstract

The article is devoted to the analysis of existing methods of searching for explosive objects on the surface of the earth and under it, and to the development of new effective approaches to solving the problem. We focus on developing solutions based on AI technologies and methods that use publicly available hardware, structural methods, and machine learning methods The problems and their solutions mentioned in the article are quite specific and, despite the relevance of the topic of searching for explosive objects, poorly developed. The main reason for this situation is either the lack of information in the public domain, when developments are carried out by military departments or private companies, or the relatively low development of countries that suffer from the problem of demining territories where military operations have been or are being conducted. From 2014 to 2022, on the territory of Ukraine, the area affected by explosive objects was approximately equal to the area of Croatia, which took 20 years to clear the territories after the war in the Balkans (1991–1995). After 2022, the territory affected by explosive objects increased several times. The intensity of shelling can currently be compared to the First and Second World Wars, so it is safe to say that the problem of finding explosive objects has reached a higher level. Therefore, considering the volume of data and the scale of the affected territories, we decided to study the main directions and modern methods of searching and classifying explosive objects in order to use them to create a system or a framework for solving the given task. The results of this article are planned to be used to create a single algorithmic environment for solving the problems of finding explosive objects, which, if necessary, will be able to process data from different sources of information, with different degrees of detail and depth.