Style transfer-based domain adaptation for vegetation segmentation with optical imagery

Abstract

Style transfer methods are an important task for domain adaptation of optical imagery to improve the performance of deep learning models when using different sensor systems. For the transformation between datasets, cycle-consistent adversarial networks achieve good results. However, during the style transfer process, characteristic spectral information that is essential for the analysis of vegetation could get lost. This issue is especially important since optical airborne- and spaceborne-based sensors are frequently used to investigate vegetation ground coverage and its condition. In this paper, we present a cycle-consistent adversarial domain adaptation method with four input channels for the segmentation of vegetation areas using index-based metrics. We show that our method preserves the specific ratio between the near-IR and RGB bands and improves the segmentation network performance for the target domain.

Enhancing Very High-Resolution Satellite Images At 15 cm: A Novel Pipeline With Synthetic Data and Single Image Superresolution

“…Previous works such as [61]-[63] have shown potential for satellite ⇌ maps. Schenkel et al [64] proposed a cycleconsistent adversarial domain adaptation method to transfer style for aerial ⇌ satellite, aerial ⇌ aerial images in the near-IR and RGB bands at low spatial resolutions. I2I have also been used for converting between optical and synthetic aperture radar (SAR) images.…”

Style Transfer of Chinese Art Works Based on Dual Channel Deep Learning Model

“…This method greatly speeds up the operation speed. Reference [ 7 ] proposed a periodic consistency antagonistic domain adaptive method with four input channels for vegetation region segmentation based on an index. This method preserves the specific ratio between near infrared and RGB bands and improves the segmentation network performance of the target domain.…”