Methods of Using Self-organising Maps for Terrain Classification, Using an Example of Developing a Military Passability Map

Pokonieczny, Krzysztof

doi:10.1007/978-3-319-61297-3_26

Cited by 15 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study presented an example of the use of Kohonen artificial neural networks to integrate satellite images with LIDAR (Light Detection and Ranging) data in order to identify the elements of land cover [17]. The use of this kind of neural network has been used to develop CCM maps [18]. An interesting implementation of artificial neural networks in a popular spatial information system [19] was used to develop a toolkit for the ArcGIS software, which enables the teaching and deploying of ANN to perform Digital Terrain Model (DTM) generation tasks.…”

Section: Introductionmentioning

confidence: 99%

“…During the conversion of the data to this model, a large part of the spatial information (both geometric and descriptive, Figure 4) was lost. However, it was assumed that this method of organizing the data was sufficient for the statistical analyses and entering of the land cover parameters into the neural network, as presented elsewhere [18,25]. (both geometric and descriptive, Figure 4) was lost.…”

mentioning

confidence: 99%

“…(both geometric and descriptive, Figure 4) was lost. However, it was assumed that this method of organizing the data was sufficient for the statistical analyses and entering of the land cover parameters into the neural network, as presented elsewhere [18,25]. Due to the fact that the generated land cover parameters were presented using various units (e.g., surface area in square meters, length in meters, etc.)…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Pokonieczny

2018

IJGI

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

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

Pokonieczny

2018

IJGI

Self Cite

View full text Add to dashboard Cite

show abstract

“…A detailed description of the method presented above is provided in [6,7]. In order to apply the methodology described above, it was necessary to assign a terrain resistance coefficient to each class of objects contained in the used database (DMU 25).…”

Section: Processing Datamentioning

confidence: 99%

“…There are several Cross-Country Movement (CCM) models, which are developed for the navigation of military vehicles -e.g. see [4][5][6][7] [21]. The outputs of these models can be in the form of a map or digital Global Positioning System (GPS) navigation implemented in an off-road vehicle.…”

Section: Introductionmentioning

confidence: 99%

Method of developing the maps of passability for unmanned ground vehicles

Pokonieczny

Rybanský

2018

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Abstract. The paper presents the methodology for developing passability maps that may be used for planning the movement of unmanned ground vehicles (UGVs). They were based on a standardised spatial data base in the scale of 1:25 000, created and used by the military forces and a high resolution digital terrain model. Maps were generated for square shaped primary fields. 5 sizes of such fields were used (side length 25, 50, 100, 200 and 500 m). Basing on the ground cover and terrain formation, for each primary field the index of passability (IOP) is calculated, being the terrain resistance coefficient. The obtained maps were compared to each other. As the presented methodology is completely automated, an analysis of the passability maps generation time depending on the size of the primary field was conducted. The obtained results demonstrated that maps that are most useful for planning UGV routes are those generated with use of the smallest primary fields (25 m), as they visualise the most terrain obstacles. The generated maps may be recorded in the UGV memory. As far as completely autonomous structures are concerned, this will enable the algorithms implemented in the vehicle, with the support of other sensors, to determine the optimal route of the UGV.

show abstract

Determination the ability of military vehicles to override vegetation

Rybanský

2020

Journal of Terramechanics

View full text Add to dashboard Cite

Methods of Using Self-organising Maps for Terrain Classification, Using an Example of Developing a Military Passability Map

Cited by 15 publications

References 15 publications

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

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

Method of developing the maps of passability for unmanned ground vehicles

Determination the ability of military vehicles to override vegetation

Contact Info

Product

Resources

About