LaeNet: A Novel Lightweight Multitask CNN for Automatically Extracting Lake Area and Shoreline from Remote Sensing Images

Liu, Wei1,2; Chen, Xingyu1; Ran, Jiangjun1,3; Liu, Lin4; Wang, Qiang5; Xin, Linyang1; Li, Gang6,7

2021

10.3390/rs13010056

REMOTE SENSING   影响因子和分区

2072-4292

Variations of lake area and shoreline can indicate hydrological and climatic changes effectively. Accordingly, how to automatically and simultaneously extract lake area and shoreline from remote sensing images attracts our attention. In this paper, we formulate lake area and shoreline extraction as a multitask learning problem. Different from existing models that take the deep and complex network architecture as the backbone to extract feature maps, we present LaeNet-a novel end-to-end lightweight multitask fully CNN with no-downsampling to automatically extract lake area and shoreline from remote sensing images. Landsat-8 images over Selenco and the vicinity in the Tibetan Plateau are utilized to train and evaluate our model. Experimental results over the testing image patches achieve an Accuracy of 0.9962, Precision of 0.9912, Recall of 0.9982, F1-score of 0.9941, and mIoU of 0.9879, which align with the mainstream semantic segmentation models (UNet, DeepLabV3+, etc.) or even better. Especially, the running time of each epoch and the size of our model are only 6 s and 0.047 megabytes, which achieve a significant reduction compared to the other models. Finally, we conducted fieldwork to collect the in-situ shoreline position for one typical part of lake Selenco, in order to further evaluate the performance of our model. The validation indicates high accuracy in our results (DRMSE: 30.84 m, DMAE: 22.49 m, DSTD: 21.11 m), only about one pixel deviation for Landsat-8 images. LaeNet can be expanded potentially to the tasks of area segmentation and edge extraction in other application fields.

lightweight CNN lake area segmentation lake shoreline extraction spatial gradient map

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China[41974094,41874004]

Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology

Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology

WOS:000606656500001

MDPI

20210209743451

Complex networks ; Extraction ; Image segmentation ; Lakes ; Network architecture ; Semantics

Computer Systems and Equipment:722 ; Chemical Operations:802.3

Web of Science

1.Southern Univ Sci & Technol, Dept Earth & Space Sci, Shenzhen 518055, Peoples R China
2.Nanyang Inst Technol, Sch Comp & Software, Nanyang 473004, Peoples R China
3.Southern Univ Sci & Technol, Shenzhen Key Lab Deep Offshore Oil & Gas Explorat, Shenzhen 518055, Peoples R China
4.Chinese Univ Hong Kong, Fac Sci, Earth Syst Sci Programme, Hong Kong, Peoples R China
5.Vultus AB, Lilla Fiskaregatan 19, S-22222 Lund, Sweden
6.Guangzhou Marine Geol Survey, Guangzhou 510075, Peoples R China
7.Southern Marine Sci & Engn Guangdong Lab, Guangzhou 511458, Peoples R China

Liu, Wei,Chen, Xingyu,Ran, Jiangjun,et al. LaeNet: A Novel Lightweight Multitask CNN for Automatically Extracting Lake Area and Shoreline from Remote Sensing Images[J]. REMOTE SENSING,2021,13(1):1-21.

Liu, Wei.,Chen, Xingyu.,Ran, Jiangjun.,Liu, Lin.,Wang, Qiang.,...&Li, Gang.(2021).LaeNet: A Novel Lightweight Multitask CNN for Automatically Extracting Lake Area and Shoreline from Remote Sensing Images.REMOTE SENSING,13(1),1-21.

Liu, Wei,et al."LaeNet: A Novel Lightweight Multitask CNN for Automatically Extracting Lake Area and Shoreline from Remote Sensing Images".REMOTE SENSING 13.1(2021):1-21.