A self-attention capsule feature pyramid network for water body extraction from remote sensing imagery

Yu, Yongtao; Yao, Yuting; Guan, Haiyan; Li, Dilong; Liu, Zuojun; Wang, Lan-fang; Yu, Chunshui; Xiao, Shaozhang; Wang, Wenhao; Lv, Chang

doi:10.1080/01431161.2020.1842544

Cited by 22 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [23] proposed an end-to-end trainable model named the multi-scale lake water extraction network (MSLWENet) to extract lake water from Google remote sensing images. Yu et al [24] developed a novel self-attention capsule feature pyramid network (SA-CapsFPN) to extract water bodies from remote sensing images. Li et al [25] built a deep learning model for water extraction based on the EfficientNet-B5 (Perdriel, Argentina).…”

Section: Related Work 21 Water Extraction Methodsmentioning

confidence: 99%

Fine-Grained Tidal Flat Waterbody Extraction Method (FYOLOv3) for High-Resolution Remote Sensing Images

et al. 2021

View full text Add to dashboard Cite

The tidal flat is long and narrow area along rivers and coasts with high sediment content, so there is little feature difference between the waterbody and the background, and the boundary of the waterbody is blurry. The existing waterbody extraction methods are mostly used for the extraction of large water bodies like rivers and lakes, whereas less attention has been paid to tidal flat waterbody extraction. Extracting tidal flat waterbody accurately from high-resolution remote sensing imagery is a great challenge. In order to solve the low accuracy problem of tidal flat waterbody extraction, we propose a fine-grained tidal flat waterbody extraction method, named FYOLOv3, which can extract tidal flat water with high accuracy. The FYOLOv3 mainly includes three parts: an improved object detection network based on YOLOv3 (Seattle, WA, USA), a fully convolutional network (FCN) without pooling layers, and a similarity algorithm for water extraction. The improved object detection network uses 13 convolutional layers instead of Darknet-53 as the model backbone network, which guarantees the water detection accuracy while reducing the time cost and alleviating the overfitting phenomenon; secondly, the FCN without pooling layers is proposed to obtain the accurate pixel value of the tidal flat waterbody by learning the semantic information; finally, a similarity algorithm for water extraction is proposed to distinguish the waterbody from non-water pixel by pixel to improve the extraction accuracy of tidal flat water bodies. Compared to the other convolutional neural network (CNN) models, the experiments show that our method has higher accuracy on the waterbody extraction of tidal flats from remote sensing images, and the IoU of our method is 2.43% higher than YOLOv3 and 3.7% higher than U-Net (Freiburg, Germany).

show abstract

Section: Related Work 21 Water Extraction Methodsmentioning

confidence: 99%

Fine-Grained Tidal Flat Waterbody Extraction Method (FYOLOv3) for High-Resolution Remote Sensing Images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A water body extraction NN, named WBE-NN, was proposed in [ 45 ] to extract water bodies from multispectral imagery at multiple resolutions while distinguishing water from shadows, and performed much better than NDWI, an SVM, and several CNN architectures. A self-attention capsule feature pyramid network (SA-CapsFPN) was proposed in [ 49 ] to extract water bodies from satellite imagery of different resolutions. SA-CapsFPN is able to recognize bodies of water across scales and different shapes and colors, as well as in varying surface and environmental conditions, although it is still entirely dependent on optical imagery as input to the CNN.…”

Section: The State Of the Art: Advances In Intelligent Waterbody Info...mentioning

confidence: 99%

“…A self-attention capsule feature pyramid network (SA-CapsFPN) was proposed in [ 49 ] to extract water bodies from satellite imagery. SA-CapsFPN is able to recognize bodies of water across scales and different shapes and colors, as well as utilizing different information channels.…”

Section: The State Of the Art: Advances In Intelligent Waterbody Info...mentioning

confidence: 99%

“…To our knowledge, no RS datasets for water body detection and water quality monitoring are downloaded from GEE and then annotated, let alone interfaces for directly annotating RS imagery on GEE. Obtaining RS imagery from Google Earth (GE) manually or with the help of code scripts, then annotating accordingly (see [ 34 , 42 , 49 ] for examples). For instance, the following two datasets generated and used in [ 34 , 49 ] are both from GE, but are not shared publicly.…”

Section: Challenges and Opportunitiesmentioning

confidence: 99%

“… Obtaining RS imagery from Google Earth (GE) manually or with the help of code scripts, then annotating accordingly (see [ 34 , 42 , 49 ] for examples). For instance, the following two datasets generated and used in [ 34 , 49 ] are both from GE, but are not shared publicly. “The first dataset was collected from the Google Earth service using the BIGEMAP software ( , accessed on 15 December 2021).…”

Section: Challenges and Opportunitiesmentioning

confidence: 99%

See 2 more Smart Citations

Towards Synoptic Water Monitoring Systems: A Review of AI Methods for Automating Water Body Detection and Water Quality Monitoring Using Remote Sensing

Yang

Driscol

Sarigai

et al. 2022

Sensors

View full text Add to dashboard Cite

Water features (e.g., water quantity and water quality) are one of the most important environmental factors essential to improving climate-change resilience. Remote sensing (RS) technologies empowered by artificial intelligence (AI) have become one of the most demanded strategies to automating water information extraction and thus intelligent monitoring. In this article, we provide a systematic review of the literature that incorporates artificial intelligence and computer vision methods in the water resources sector with a focus on intelligent water body extraction and water quality detection and monitoring through remote sensing. Based on this review, the main challenges of leveraging AI and RS for intelligent water information extraction are discussed, and research priorities are identified. An interactive web application designed to allow readers to intuitively and dynamically review the relevant literature was also developed.

show abstract

Effects of extreme flooding on aquatic vegetation cover in Shengjin Lake, China

Guo

Zhou

Chen

et al. 2022

Hydrological Processes

View full text Add to dashboard Cite

Aquatic plants are the main primary producers and an important part of the aquatic ecosystem. Seasonal flooding broke out in July 2020 in the middle and lower reaches of the Yangtze River, resulting in continued high water levels in lakes connected to the Yangtze River. To study the impact of extreme flooding on aquatic vegetation cover, we utilized two methods (surveying and remote sensing image data) to determine the changes in the aquatic vegetation cover of Shengjin Lake, one of the lakes connected to the Yangtze River, during the wet season from 2018 to 2020. The results showed that the dominant aquatic plant species before the flood in July 2020 were the emergent plant Zizania caduciflora, the floating plant Trapa incisa, the submerged plant Ceratophyllum demersum and Vallisineria natans. The area covered by aquatic vegetation in 2018–2019 showed a slight upward trend, increasing from 24.94 to 25.94 km2. In April 2020, the aquatic vegetation cover was 25.53 km2, and after the flooding in July 2020, the aquatic vegetation cover decreased sharply to 1.36 km2, which was mainly composed of emergent plant Z. caduciflora in the nearshore. No recovery of the dominant aquatic plant species, the floating plant T. incisa and other submerged plants, was seen during the monitoring of water level decline from September to December 2020. Winter wetland plants were not significantly affected by flooding. The results of the study provide a theoretical basis for the maintenance mechanism of aquatic vegetation and lake management in Shengjin Lake.

show abstract

A self-attention capsule feature pyramid network for water body extraction from remote sensing imagery

Cited by 22 publications

References 36 publications

Fine-Grained Tidal Flat Waterbody Extraction Method (FYOLOv3) for High-Resolution Remote Sensing Images

Fine-Grained Tidal Flat Waterbody Extraction Method (FYOLOv3) for High-Resolution Remote Sensing Images

Towards Synoptic Water Monitoring Systems: A Review of AI Methods for Automating Water Body Detection and Water Quality Monitoring Using Remote Sensing

Effects of extreme flooding on aquatic vegetation cover in Shengjin Lake, China

Contact Info

Product

Resources

About