Next Article in Journal
Role of Maximum Entropy and Citizen Science to Study Habitat Suitability of Jacobin Cuckoo in Different Climate Change Scenarios
Previous Article in Journal
Assessing Earthquake Impacts and Monitoring Resilience of Historic Areas: Methods for GIS Tools
Previous Article in Special Issue
Implicit, Formal, and Powerful Semantics in Geoinformation
Article

Cloud and Snow Segmentation in Satellite Images Using an Encoder–Decoder Deep Convolutional Neural Networks

1
Institute of Surveying and Mapping, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China
2
Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy
*
Author to whom correspondence should be addressed.
Academic Editors: Gloria Bordogna and Cristiano Fugazza
ISPRS Int. J. Geo-Inf. 2021, 10(7), 462; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10070462
Received: 21 May 2021 / Revised: 23 June 2021 / Accepted: 1 July 2021 / Published: 6 July 2021
(This article belongs to the Special Issue Artificial Intelligence for Multisource Geospatial Information)
The segmentation of cloud and snow in satellite images is a key step for subsequent image analysis, interpretation, and other applications. In this paper, a cloud and snow segmentation method based on a deep convolutional neural network (DCNN) with enhanced encoder–decoder architecture—ED-CNN—is proposed. In this method, the atrous spatial pyramid pooling (ASPP) module is used to enhance the encoder, while the decoder is enhanced with the fusion of features from different stages of the encoder, which improves the segmentation accuracy. Comparative experiments show that the proposed method is superior to DeepLabV3+ with Xception and ResNet50. Additionally, a rough-labeled dataset containing 23,520 images and fine-labeled data consisting of 310 images from the TH-1 satellite are created, where we studied the relationship between the quality and quantity of labels and the performance of cloud and snow segmentation. Through experiments on the same network with different datasets, we found that the cloud and snow segmentation performance is related more closely to the quantity of labels rather than their quality. Namely, under the same labeling consumption, using rough-labeled images only performs better than rough-labeled images plus 10% fine-labeled images. View Full-Text
Keywords: satellite image; semantic segmentation; encoder–decoder; CNN; TH-1; cloud and snow detection; label quality satellite image; semantic segmentation; encoder–decoder; CNN; TH-1; cloud and snow detection; label quality
Show Figures

Figure 1

MDPI and ACS Style

Zheng, K.; Li, J.; Ding, L.; Yang, J.; Zhang, X.; Zhang, X. Cloud and Snow Segmentation in Satellite Images Using an Encoder–Decoder Deep Convolutional Neural Networks. ISPRS Int. J. Geo-Inf. 2021, 10, 462. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10070462

AMA Style

Zheng K, Li J, Ding L, Yang J, Zhang X, Zhang X. Cloud and Snow Segmentation in Satellite Images Using an Encoder–Decoder Deep Convolutional Neural Networks. ISPRS International Journal of Geo-Information. 2021; 10(7):462. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10070462

Chicago/Turabian Style

Zheng, Kai, Jiansheng Li, Lei Ding, Jianfeng Yang, Xucheng Zhang, and Xun Zhang. 2021. "Cloud and Snow Segmentation in Satellite Images Using an Encoder–Decoder Deep Convolutional Neural Networks" ISPRS International Journal of Geo-Information 10, no. 7: 462. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10070462

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop