Yang, C.; Rottensteiner, F.; Heipke, C.: Exploring semantic relationships for hierarchical land use classification based on convolutional neural networks. In: Paparoditis, N. et.al. (Eds.): XXIV ISPRS Congress, Commission II : edition 2020. Katlenburg-Lindau : Copernicus Publications, 2020 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; 5,2), S. 599-607. DOI: https://doi.org/10.5194/isprs-annals-V-2-2020-599-2020
Zusammenfassung: | |
Land use (LU) is an important information source commonly stored in geospatial databases. Most current work on automatic LU classification for updating topographic databases considers only one category level (e.g. <i>residential</i> or <i>agricultural</i>) consisting of a small number of classes. However, LU databases frequently contain very detailed information, using a hierarchical object catalogue where the number of categories differs depending on the hierarchy level. This paper presents a method for the classification of LU on the basis of aerial images that differentiates a fine-grained class structure, exploiting the hierarchical relationship between categories at different levels of the class catalogue. Starting from a convolutional neural network (CNN) for classifying the categories of all levels, we propose a strategy to simultaneously learn the semantic dependencies between different category levels explicitly. The input to the CNN consists of aerial images and derived data as well as land cover information derived from semantic segmentation. Its output is the class scores at three different semantic levels, based on which predictions that are consistent with the class hierarchy are made. We evaluate our method using two test sites and show how the classification accuracy depends on the semantic category level. While at the coarsest level, an overall accuracy in the order of 90% can be achieved, at the finest level, this accuracy is reduced to around 65%. Our experiments also show which classes are particularly hard to differentiate. © 2020 Copernicus GmbH. All rights reserved. | |
Lizenzbestimmungen: | CC BY 4.0 Unported |
Publikationstyp: | BookPart |
Publikationsstatus: | publishedVersion |
Erstveröffentlichung: | 2020 |
Die Publikation erscheint in Sammlung(en): | Fakultät für Bauingenieurwesen und Geodäsie |
Pos. | Land | Downloads | ||
---|---|---|---|---|
Anzahl | Proz. | |||
1 | United States | 25 | 27,78% | |
2 | Germany | 23 | 25,56% | |
3 | China | 17 | 18,89% | |
4 | Austria | 4 | 4,44% | |
5 | Korea, Republic of | 3 | 3,33% | |
6 | India | 3 | 3,33% | |
7 | Brazil | 3 | 3,33% | |
8 | Indonesia | 2 | 2,22% | |
9 | Hong Kong | 2 | 2,22% | |
10 | Taiwan | 1 | 1,11% | |
andere | 7 | 7,78% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.