KIT | KIT-Bibliothek | Impressum | Datenschutz

Residual Shuffling Convolutional Neural Networks for Deep Semantic Image Segmentation Using Multi-Modal Data

Chen, Kaiqiang; Weinmann, Michael; Gao, X.; Yan, M.; Hinz, S. 1; Jutzi, Boris ORCID iD icon 1
1 Institut für Photogrammetrie und Fernerkundung (IPF), Karlsruher Institut für Technologie (KIT)

Abstract:

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000083949
Originalveröffentlichung
DOI: 10.5194/isprs-annals-IV-2-65-2018
Scopus
Zitationen: 16
Dimensions
Zitationen: 12
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2018
Sprache Englisch
Identifikator ISSN: 2194-9042
urn:nbn:de:swb:90-839496
KITopen-ID: 1000083949
Erschienen in 2018 ISPRS TC II Mid-term Symposium "Towards Photogrammetry 2020"; Riva del Garda; Italy, June 4-7, 2018. Ed.: T. Fuse
Verlag Copernicus Publications
Seiten 65-72
Serie ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; 4
Schlagwörter Semantic Segmentation, Aerial Imagery, Multi-Modal Data, Deep Learning, CNN, Residual Network
Nachgewiesen in Scopus
Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page