Back to Search
Start Over
EXPLORING SEMANTIC RELATIONSHIPS FOR HIERARCHICAL LAND USE CLASSIFICATION BASED ON CONVOLUTIONAL NEURAL NETWORKS
- Source :
- ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol V-2-2020, Pp 599-607 (2020), XXIV ISPRS Congress, Commission II : edition 2020, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; 5,2
- Publication Year :
- 2020
-
Abstract
- 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. residential or agricultural) 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.
- Subjects :
- Dewey Decimal Classification::500 | Naturwissenschaften::550 | Geowissenschaften
lcsh:Applied optics. Photonics
Geospatial analysis
010504 meteorology & atmospheric sciences
Computer science
010501 environmental sciences
computer.software_genre
01 natural sciences
Convolutional neural network
lcsh:Technology
aerial imagery
ddc:550
semantic relationships
Segmentation
hierarchical land use classification
Konferenzschrift
0105 earth and related environmental sciences
Hierarchy (mathematics)
business.industry
lcsh:T
Spatial database
lcsh:TA1501-1820
Pattern recognition
Object (computer science)
Class (biology)
lcsh:TA1-2040
geospatial database
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
computer
Class hierarchy
CNN
Subjects
Details
- Language :
- English
- ISSN :
- 21949050
- Database :
- OpenAIRE
- Journal :
- ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol V-2-2020, Pp 599-607 (2020), XXIV ISPRS Congress, Commission II : edition 2020, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; 5,2
- Accession number :
- edsair.doi.dedup.....ec6069c92fe8e9537a9e64afe00e843f