Translator Disclaimer
27 August 2020 Wetland Type Information Extraction Using Deep Convolutional Neural Network
Author Affiliations +
Abstract

Liu, X.L.; Wu, D.Y.; Wang, H.Z., and Liu, J.X., 2020. Wetland type information extraction using deep convolutional neural network. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 526-529. Coconut Creek (Florida), ISSN 0749-0208.

Image classification is an extremely important component in the field of remote sensing. With the development of modern satellite remote sensing technology, image classification now forms the basis of various remote sensing applications. In recent years, deep learning methods are established as the optimal methods in the field of image recognition, and have become a research hotspot in the field of artificial intelligence. In this work, we propose a method for extracting information regarding the type of wetland under consideration using deep convolutional neural network. We apply preprocessing to images in order to achieve the required format before feeding the images to the neural network. We present the classification accuracy and computational efficiency of the proposed method. We also provide a comparison of the proposed method with other methods presented in literature. The results and analysis reveal that proposed technique is able to capture the details of wetland imagery. We show that multi-scale segmentation of remote sensing images and using deep convolutional neural network to automatically identify and extract image information results in higher classification accuracy and efficiency.

©Coastal Education and Research Foundation, Inc. 2020
Xiaolan Liu, Dayong Wu, Hongzhi Wang, and Jianxiao Liu "Wetland Type Information Extraction Using Deep Convolutional Neural Network," Journal of Coastal Research 115(sp1), 526-529, (27 August 2020). https://doi.org/10.2112/JCR-SI115-144.1
Received: 25 January 2020; Accepted: 28 May 2020; Published: 27 August 2020
JOURNAL ARTICLE
4 PAGES


SHARE
ARTICLE IMPACT
RIGHTS & PERMISSIONS
Get copyright permission
Back to Top