A deep learning approach for urban land cover classification from high-spatial resolution imagery and geomorphometric variables

I. Lizarazo, S. Ramirez

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

This paper describes a deep learning approach for urban land cover classification in the context of the ISPRS 2D semantic labelling benchmark. A high spatial resolution digital swface model (DSM) and a true ortho-image over the city Potsdam (Germany) was used as input dataset for obtaining six target classes. The proposed approach focuses on augmenting the original input dataset with a combined set of geo-morphometric variables extracted from DSM -including slope/aspect transformation, second derivate of elevation, compound topographic index and hierarchical slope position-. Furthermore, it uses advanced deep learning architecture provided by H2O framework which follows the model of multi-layer, feedforward neural networks for predictive modelling. Automatic hyper­parameter tuning with random search was conducted for model selection. The method comprises five steps: (i) spectral segmentation of ortho-irnages; (ii) extraction of relevant geo-morphometric variables from DSM; (iii) multivariate land cover classification; and (iv) accuracy assessment. The proposed approach was used for classifying a selected ISPRS benchmark tile where a reference map is available. Thematic accuracy of the proposed approach was assessed using the traditional error matrix and compared with thematic accuracy of a deep learning classification based only on the original data set (i.e. DSM and multispectral imagery). In addition, the deep learning classification approach was compared with a random forest (RF) classification using both original and augmented input dataset. It is shown that: (i) thematic accuracy improves only slightly when geomorphological variables are used to enhance the input dataset; and (ii) deep neural nets provide a similar predictive power than random forests for urban remote sensing applications.
Original languageEnglish
Title of host publicationProceedings of GEOBIA 2016
Subtitle of host publicationSolutions and synergies, 14-16 September 2016, Enschede, Netherlands
EditorsN. Kerle, M. Gerke, S. Lefevre
Place of PublicationEnschede
PublisherUniversity of Twente, Faculty of Geo-Information Science and Earth Observation (ITC)
Number of pages6
ISBN (Print)978-90-365-4201-2
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016: Solutions & Synergies - University of Twente Faculty of Geo-Information and Earth Observation (ITC), Enschede, Netherlands
Duration: 14 Sep 201616 Sep 2016
Conference number: 6
https://www.geobia2016.com/

Conference

Conference6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016
Abbreviated titleGEOBIA
CountryNetherlands
CityEnschede
Period14/09/1616/09/16
Internet address

Fingerprint

Dive into the research topics of 'A deep learning approach for urban land cover classification from high-spatial resolution imagery and geomorphometric variables'. Together they form a unique fingerprint.

Cite this