Share Email Print
cover

Proceedings Paper • new

Evaluation of CNNs for land cover classification in high-resolution airborne images
Author(s): Gisela Häufel; Lukas Lucks; Melanie Pohl; Dimitri Bulatov; Hendrik Schilling
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Semantic land cover classification of satellite images or airborne images is becoming increasingly important for applications like urban planning, road net analysis or environmental monitoring. Sensor orientations or varying illumination make classification challenging. Depending on image source and classification task, it is not always easy to name the most discriminative features for a successful performance. To avoid feature selection, we transfer aspects of a feature-based classification approach to Convolutional Neural Networks (CNNs) which internally generate specific features. As land covering classes, we focus on buildings, roads, low (grass) and high vegetation (trees). Two different approaches will be analyzed: The first approach, using InceptionResNetV2, stems from networks used for image recognition. The second approach constitutes a fully convolutional neural network (DeepLabV3+) and is typically used for semantic image segmentation. Before processing, the image needs to be subdivided into tiles. This is necessary to make the data processible for the CNN, as well as for computational reasons. The tiles working with InceptionResNetV2 are derived from a superpixel segmentation. The tiles for working with DeepLabV3+ are overlapping tiles of a certain size. The advantages of this CNN is that its architecture enables to up-sample the classification result automatically and to produce a pixelwise labeling of the image content. As evaluation data for both approaches, we used the ISPRS benchmark of the city Vaihingen, Germany, containing true orthophotos and ground truth labeled for classification.

Paper Details

Date Published: 9 October 2018
PDF: 11 pages
Proc. SPIE 10790, Earth Resources and Environmental Remote Sensing/GIS Applications IX, 1079003 (9 October 2018); doi: 10.1117/12.2325604
Show Author Affiliations
Gisela Häufel, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB (Germany)
Lukas Lucks, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB (Germany)
Melanie Pohl, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB (Germany)
Dimitri Bulatov, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB (Germany)
Hendrik Schilling, Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB (Germany)


Published in SPIE Proceedings Vol. 10790:
Earth Resources and Environmental Remote Sensing/GIS Applications IX
Ulrich Michel; Karsten Schulz, Editor(s)

© SPIE. Terms of Use
Back to Top