Abstract
Measured fractional vegetation cover (FVC) on the ground is very important for validation of the remote sensing products and algorithms. However, because of the influence of some factors such as the angle of illumination and vegetation density, the existence of vegetation shadows limits the accuracy of FVC estimation. This article proposes a deep learning method to reduce the FVC estimation error based on high dynamic range (HDR) images with vegetation shadows (HDR REC-DL method). The HDR REC-DL method can accurately extract FVC from HDR images with complex texture information on vegetation shadows. This method is based on the U-Net convolutional network structure for semantic segmentation of images containing vegetation shadows, and the segmentation results are less affected by vegetation types. Results from the HDR REC-DL method were highly similar to the vegetation segmentation results from visual interpretation. Values of the kappa coefficient, F1 score (F1), recall, and mean intersection over union of the HDR REC-DL method were 0.926, 0.942, 0.924, 0.916 for sunny weather and 0.903, 0.974, 0.983, and 0.895 for cloudy weather, respectively. Compared with the vegetation segmentation accuracy of the shadow-resistant algorithm, the HDR REC-DL method increases the kappa coefficient, F1, and mIOU by 21%, 16%, and 29% for sunny weather, and by 11.1%, 3.6%, and 10.3% for cloudy weather, respectively. The HDR REC-DL method provides a novel method for accurately estimating FVC from images containing vegetation shadows.
Highlights
VEGETATION is an important part of the terrestrial ecosystem and plays an important role in maintaining the balance of ecosystems, conserving water sources, and conserving water and soil [1,2,3,4]
A deep learning method based on normal exposure images (NOR) with vegetation shadows is proposed to reduce Fractional vegetation cover (FVC) estimation errors (NOR REC-DL method)
The NOR REC-DL method and high dynamic range (HDR) REC-DL method are deep learning methods based on normal exposure images and HDR images, respectively
Summary
VEGETATION is an important part of the terrestrial ecosystem and plays an important role in maintaining the balance of ecosystems, conserving water sources, and conserving water and soil [1,2,3,4]. The remote sensing estimation method uses satellite images to estimate FVC on a global or regional scale. There are many remote sensing inversion methods for FVC, and the commonly used methods include empirical model method, physical model method, mixed pixels decomposition method, and machine learning method[9,10,11,12,13,14]. Some researchers use empirical models, regression models and relationship models based on vegetation index to estimate FVC[9, 15]. Several studies estimate global FVC based on VIIRS surface reflectance data using machine learning methods such as back propagation neural networks (BPNNs) and general regression networks (GRNNs)[12].Some studies use deep learning regression models to estimate FVC in savanna ecosystems[11].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
