Use of a Multilayer Perceptron to Automate Terrain Assessment for the Needs of the Armed Forces

Abstract

The classification of terrain in terms of passability plays a significant role in the process of military terrain assessment. It involves classifying selected terrain to specific classes (GO, SLOW-GO, NO-GO). In this article, the problem of terrain classification to the respective category of passability was solved by applying artificial neural networks (multilayer perceptron) to generate a continuous Index of Passability (IOP). The neural networks defined this factor for primary fields in two sizes (1000 × 1000 m and 100 × 100 m) based on the land cover elements obtained from Vector Smart Map (VMap) Level 2 and Shuttle Radar Topography Mission (SRTM). The work used a feedforward neural network consisting of three layers. The paper presents a comprehensive analysis of the reliability of the neural network parameters, taking into account the number of neurons, learning algorithm, activation functions and input data configuration. The studies and tests carried out have shown that a well-trained neural network can automate the process of terrain classification in terms of passability conditions.

Analysis of the Possibilities of Using Different Resolution Digital Elevation Models in the Study of Microrelief on the Example of Terrain Passability

“…An informatic system that automates the passability map development process is presented in [26]. An article [27] discusses the method of generating the passability index with the use of artificial neural networks. The crucial element of the discussed analyzes is the influence of individual parts of the geographic environment on the passability conditions.…”

Methodology of Using Terrain Passability Maps for Planning the Movement of Troops and Navigation of Unmanned Ground Vehicles

“…The conducted research deals with their application with the use of various sources of spatial data [ 23 ], discussed the problems of accuracy [ 24 , 25 ] and the methods of cartographic visualisation of the resulting maps [ 26 ]. Apart from that, the authors proposed methodologies, conducted tests and analyses on the application of artificial neural networks (multi-layer perceptron [ 27 ] and Kohonen Self Organizing Map [ 28 ]) to generate maps. Besides the analyses of passability on the operational level, which brought results in the form of generalised maps in a small scale, the authors also proposed methods to develop high-resolution (detailed) passability models, which allow users to plan the movement of individual vehicles [ 29 , 30 ] of a specific type.…”

“…The research presented here complements the studies listed in the previous section. The main research question which the authors were confronted with was the presentation of the methodology to convert the passability model that was developed and presented by the authors in numerous publications (including [ 22 , 24 , 27 , 29 , 30 ]) as the basis for the automated generation of the optimal path. This will doubtlessly lead to improved functionality and usability of the developed model.…”