Building detection and segmentation using a CNN with automatically generated training data

Xiangyu Zhuo, Friedrich Fraundorfer, Franz Kurz, Peter Reinartz

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Abstract

Significantly outperforming traditional machine learning methods, deep convolutional neural networks have gained increasing popularity in the application of image classification and segmentation. Nevertheless, deep learning-based methods usually require a large amount of training data, which is quite labor-intensive and time-demanding. To deal with the problem in generating training data, we propose in this paper a novel approach to generate image annotations by transferring labels from aerial images to UAV images and refine the annotations using a densely connected CRF model with an embedded naive Bayes classifier. The generated annotations not only present correct semantic labels, but also preserve accurate class boundaries. To validate the utility of these automatic annotations, we deploy them as training data for pixel-wise image segmentation and compare the results with the segmentation using manual annotations. Experiment results demonstrate that the automatic annotations can achieve comparable segmentation accuracy as the manual annotations.

Originalspracheenglisch
Titel2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers
Seiten3461-3464
Seitenumfang4
ISBN (elektronisch)9781538671504
DOIs
PublikationsstatusVeröffentlicht - 31 Okt 2018
Veranstaltung38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Valencia, Spanien
Dauer: 22 Jul 201827 Jul 2018

Publikationsreihe

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Band2018-July

Konferenz

Konferenz38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
LandSpanien
OrtValencia
Zeitraum22/07/1827/07/18

    Fingerprint

Schlagwörter

    ASJC Scopus subject areas

    • !!Computer Science Applications
    • !!Earth and Planetary Sciences(all)

    Dieses zitieren

    Zhuo, X., Fraundorfer, F., Kurz, F., & Reinartz, P. (2018). Building detection and segmentation using a CNN with automatically generated training data. in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings (S. 3461-3464). [8518521] (International Geoscience and Remote Sensing Symposium (IGARSS); Band 2018-July). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS.2018.8518521