title: Extraction of routing relevant geodata using telemetry sensor data of agricultural vehicles
creator: Lauer, Johannes
subject: 004
subject: 004 Data processing Computer science
subject: 550
subject: 550 Earth sciences
description: The mechanization of processes in agriculture is growing within the last hundred years. Within the last decades, the information technology in this sector constantly grew and data is one of the key factors for process optimization. For planning and execution of logistic processes and harvest campaigns, road maps and field geometries are essential to guide the large vehicles to their work places and to optimize harvest chains. Through nowadays available telemetry data of these vehicles, a new data source generates new opportunities. Mining geographic data from these movement data, that can improve agricultural work processes is one of the main objectives of this thesis. As a first step, data cleaning processes, and further preprocessing steps are shown. With classification algorithms, the continuous movement data will be separated into different work processes. Based on this data, algorithms to generate geographic geographic features, such as field boundaries have been analyzed and improved. As quality metric to compare the results, the Jaccard-Distance has been established. With the classified road representing measurements, the rural road networks were created and the results of different algorithmic approaches have been compared. The usability of volunteered geographic information to route the heterogeneous set of agricultural vehicles is shown in a third step. Due to the fact, that routes for e.g. harvesters are not ending at the field boundary, solutions for infield route graph generation have been given. The presented components provide the content and the services within a framework structure. The concluding prototype, a web based routing system demonstrates the interaction of all components and provides a consecutive routing from farm to field and within the field.
date: 2018
type: Dissertation
type: info:eu-repo/semantics/doctoralThesis
type: NonPeerReviewed
format: application/pdf
identifier: https://archiv.ub.uni-heidelberg.de/volltextserverhttps://archiv.ub.uni-heidelberg.de/volltextserver/23966/7/diss_jlauer_150dpi.pdf
identifier: DOI:10.11588/heidok.00023966
identifier: urn:nbn:de:bsz:16-heidok-239665
identifier:   Lauer, Johannes  (2018) Extraction of routing relevant geodata using telemetry sensor data of agricultural vehicles.  [Dissertation]     
relation: https://archiv.ub.uni-heidelberg.de/volltextserver/23966/
rights: info:eu-repo/semantics/openAccess
rights: http://archiv.ub.uni-heidelberg.de/volltextserver/help/license_urhg.html
language: eng