MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

Zhang, Xinyu; Li, Jinjiang; Hua, Zhen

doi:10.1109/jstars.2022.3185245

Cited by 32 publications

(11 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xia et al [41] take advantage of an U-shaped segmentation network (U-Net) to allow skip connections between different resolution levels. Zhang et al [42] adopt an squeeze-and-excitation technique for the re-calibration of feature channels when segmenting water. Nonetheless, these segmentation models have the disadvantage of requiring full-scene annotated data in contrast to pixel-based water classification which become more suitable to relieve the data scarcity problem in developing countries like Nepal.…”

Section: B Deep Learning-based Methodsmentioning

confidence: 99%

Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

Parajuli

Fernández-Beltrán

Kang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Monitoring water bodies from remote sensing data is certainly an essential task to supervise the actual conditions of the available water resources for environment conservation, sustainable development and many other applications. Being Sentinel-2 images some of the most attractive data, existing traditional index-based and deep learning-based water extraction methods still have important limitations to effectively deal with large heterogeneous areas since many types of water bodies with different spatial-spectral complexities are logically expected. Note that, in this scenario, optimal feature abstraction and neighbourhood information may certainly vary from water to water pixel, however existing methods are generally constrained by a fix abstraction level and amount of land cover context. To address these issues, this paper presents a new attentional dense convolutional neural network (AD-CNN) specially designed for water body extraction from Sentinel-2 imagery. On the one hand, AD-CNN exploits dense connections to allow uncovering deeper features while simultaneously characterizing multiple data complexities. On the other hand, the proposed model also implements a new residual attention module to dynamically put the focus on the most relevant spatial-spectral features for classifying water pixels. To test the performance of AD-CNN, a new water database of Nepal (WaterPAL) is also built. The conducted experiments reveal the competitive performance of the proposed architecture with respect to several traditional indexbased and state-of-the-art deep learning-based water extraction models. The codes and data related to this paper will be accessible on https://github.com/rufernan/ADCNN.

show abstract

Section: B Deep Learning-based Methodsmentioning

confidence: 99%

Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

Parajuli

Fernández-Beltrán

Kang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, when used independently, Ki-Net solely captures edges, limiting overall accuracy. To address this, Ki-Net has been integrated with U-Net to form KiU-Net, leveraging the low-altitude fine edge-taking features of Ki-Net and the elevated shape-apprehending features of U-Net, resulting in improved accuracy [39].…”

Section: Related Workmentioning

confidence: 99%

KiAtt Fusion: Remote Sensing-Based Water Bodies Segmentation for Environmental Monitoring

Sikander,

Rehman,

Perwaiz

et al. 2024

Preprint

View full text Add to dashboard Cite

Monitoring the environment and managing water bodies are crucial for preserving ecosystems and ensuring sustainable resource utilization. This study aims to propose a robust approach for segmenting water bodies by combining various complementary attributes extracted from deep learning techniques. By leveraging deep contextual features learned from attention regions and enhanced edge detection, our method significantly improves the accuracy of detecting water bodies in low-resolution satellite imagery. Utilizing S1 and S2 Sentinel imagery data and exploring multi-band features, we enhance key attributes through advanced UNet architectures—specifically, Ki-UNet and Attention UNet—and integrate complementary features for downstream tasks. Additionally, we assembled a local dataset from the Khyber Pakhtunkhwa (KPK) region of Pakistan, facilitating precise water body segmentation from satellite or aerial views. Our ensemble model achieved remarkable accuracy and Intersection over Union (IoU) scores, reaching up to 99.01% and 96.2%, respectively, surpassing state-of-the-art models. This research provides automated, accurate segmentation techniques essential for environmental management and resource assessment, offering a promising solution for delineating water bodies. github link : (https://github.com/SaadBaloch96/Dataset/blob/main/README.md)

show abstract

“…As a channel attention module, the squeeze-andexcitation (SE) module 31 is widely applied to semantic segmentation tasks. 32 and semantic segmentation. 35 In this study, in order to improve the quality of feature extraction, ECA channel attention module is introduced into FPN network.…”

Section: Improved Yolov4-tinymentioning

confidence: 99%

“…In recent years, attention mechanism has been widely used in convolutional neural networks to improve the quality of feature extraction. As a channel attention module, the squeeze-and-excitation (SE) module 31 is widely applied to semantic segmentation tasks 32 . ECA channel attention module improves on SE module.…”

Section: Double-stream Structure Of Flame Detection Modelmentioning

confidence: 99%

Lightweight anti-interference flame detection method based on context information

Xue

Wang

et al. 2022

J. Electron. Imag.

View full text Add to dashboard Cite

As an important part of fire prevention and control, there are high standards for realtime, anti-interference, and accuracy about flame detection. At present, flame target detection methods lack comprehensive research on the above three indicators. To solve this problem, we propose a lightweight anti-interference flame detection method based on improved YOLOv4tiny. On the ground of dynamic characteristics of flame changing with time, a double-stream structure of flame detection model is designed. First, deeply separable convolution is applied to YOLOv4-tiny, resulting in a lighter backbone network. Second, in the feature extraction stage, the learning ability of the network to shallow features is improved by further integrating multiscale features, and the efficient channel attention module is introduced into the feature pyramid network to further improve the accuracy. Finally, intersection over union (IOU) postprocessing algorithm is used to shield the interference of fire-like targets effectively. Experimental results show that the parameter quantity of our methods are 3.95 and 4.22 MB, respectively, and accordingly their precisions reach 94.10% and 94.27%. Detection times are 35 and 46 ms, separately. In addition, after using IOU postprocessing algorithm, mAP and F1 composite index both increased to varying degrees, the consumption time is only 0.23 ms.

show abstract

MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

Cited by 32 publications

References 79 publications

Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 Images

KiAtt Fusion: Remote Sensing-Based Water Bodies Segmentation for Environmental Monitoring

Lightweight anti-interference flame detection method based on context information

Contact Info

Product

Resources

About