IN-TERRESTRIAL AQUACULTURE FIELDS MAPPING FROM HIGH RESOLUTION REMOTE SENSING IMAGES

Convolution neural networks are widely used for image processing in remote sensing. Aquacultures have an important role in food security and hence should be monitored. In this paper, a novel light-weight neural network for in-terrestrial aquaculture field retrieval from high-resolution remote sensing images is proposed. The structure of this pond segmentation network is based on the UNet architec-ture, providing higher training speed. Experiments are performed on Gaofen satellite datasets in Shang-hai, China. The proposed network detects the in-land aquaculture ponds in a shorter time than state-of-the-art neural network-based models and reaches an overall accuracy of about 90 %. © 2023, LLC Editorial of Journal Light Technik. All rights reserved.