Generative Adversarial Approach to Urban Areas’ NDVI Estimation: A Case Study of Łódź, Poland

Quaestiones Geographicae

article

Maciej Adamiak¹  Krzysztof Będkowski²  Adam Bielecki² 

[1] ReasonField Lab;University of Lodz, Faculty of Geographical Sciences, Institute of Urban Geography

关键词: generative adversarial networks;    NDVI;    green areas;    orthophoto;    artificial datasets;   

DOI  :  10.14746/quageo-2023-0007

学科分类：医学（综合）

来源: Walter de Gruyter GmbH

【 摘 要 】

Generative adversarial networks (GAN) opened new possibilities for image processing and analysis. Inpainting, dataset augmentation using artificial samples, or increasing spatial resolution of aerial imagery are only a few notable examples of utilising GANs in remote sensing (RS). The normalised difference vegetation index (NDVI) ground-truth labels were prepared by combining RGB and NIR orthophotos. The dataset was then utilised as input for a conditional generative adversarial network (cGAN) to perform an image-to-image translation. The main goal of the neural network was to generate an artificial NDVI image for each processed 256 px × 256 px patch using only information available in the panchromatic input. The network achieved a structural similarity index measure (SSIM) of 0.7569 ± 0.1083, a peak signal-to-noise ratio (PSNR) of 26.6459 ± 3.6577 and a root-mean-square error (RSME) of 0.0504 ± 0.0193 on the test set, which should be considered high. The perceptual evaluation was performed to verify the method's usability when working with a real-life scenario. The research confirms that the structure and texture of the panchromatic aerial RS image contain sufficient information for NDVI estimation for various objects of urban space.

【 授权许可】

CC BY