Water Identification from High-Resolution Remote Sensing Images Based on Multidimensional Densely Connected Convolutional Neural Networks

Wang, Guojie; Wu, Mengjuan; Wei, Xikun; Song, Hwangjun

doi:10.3390/rs12050795

Cited by 73 publications

(29 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a fully convolutional network (FCN) can classify images at the pixel level [19][20][21][22][23][24], and its multi-scale feature fusion structure improves the accuracy of image segmentation. Compared with the FCN structure, a SegNet structure uses the pooled index calculated in the maximum pooling step of the corresponding encoder in the decoder structure to perform a nonlinear upsampling step, which can save more memory space and there is no need to update parameters in the upsampling stage, and many improved deep-learning models are based on the SegNet structure [25][26][27][28][29][30]. In order to improve the use of feature information in images, the long connection structure of UNet is also widely used in image segmentation, and this structure achieves the fusion of multi-scale image information to improve segmentation performance.…”

Section: Introductionmentioning

confidence: 99%

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Lin

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Automatic road extraction from very-high-resolution remote sensing images has become a popular topic in a wide range of fields. Convolutional neural networks are often used for this purpose. However, many network models do not achieve satisfactory extraction results because of the elongated nature and varying sizes of roads in images. To improve the accuracy of road extraction, this paper proposes a deep learning model based on the structure of Deeplab v3. It incorporates squeeze-and-excitation (SE) module to apply weights to different feature channels, and performs multi-scale upsampling to preserve and fuse shallow and deep information. To solve the problems associated with unbalanced road samples in images, different loss functions and backbone network modules are tested in the model’s training process. Compared with cross entropy, dice loss can improve the performance of the model during training and prediction. The SE module is superior to ResNext and ResNet in improving the integrity of the extracted roads. Experimental results obtained using the Massachusetts Roads Dataset show that the proposed model (Nested SE-Deeplab) improves F1-Score by 2.4% and Intersection over Union by 2.0% compared with FC-DenseNet. The proposed model also achieves better segmentation accuracy in road extraction compared with other mainstream deep-learning models including Deeplab v3, SegNet, and UNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Lin

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These two methods used to calculate the water index, distinguish between water and building, the optimal threshold to extract water is highly subjective, and also varies with region and time. But in that the every water index has its main problem is the NDWI was poor at distinguishing between water and buildings, mountain shadows [12]. Statistical methods of unsupervised classifications are used for identifying the water bodies.…”

Section: Water Bodies and Settlement Density Using Image Classification Methodmentioning

confidence: 99%

Identification of vulnerable zone of surface water epidemiology using Remote Sensing and GIS techniques

Karuppaiah

2021

Proceedings of the 3rd International Electronic Conference on Environmental Research and Public Health —Public Health Issues In

View full text Add to dashboard Cite

：The maintaining of drinking water quality, access to clean urban surface water are the most challenge resulting in water-borne diseases. Although, the developing countries, the Geographical Information System (GIS) technology has not been yet systematically utilized. Therefore, the present study aimed to establish the parameters for assessing surface water quality and how they would cause health issues in the study area. This study reveals the surface water quality variations by using principal component analysis (PCA) techniques with the help of Landsat 8 Operational Land Imager (OLI) satellite imagery. Regular monitoring of environmental quality database produced by (GIS) could manage information from various sources such as, domestic, industrial, recreational activities, point and non-points sources etc. This monitoring activity could make spatial correlations with epidemiology data about time and space distribution of water-borne diseases. The spatial correlation of water contamination tank and it's surroundings of land use / land cover (LULC) activities were calculated by the technique of buffer analysis. Using Medical GIS, could easily detect the circulation and spread of disease across the geographic regions which could be used for planning, policy making, water resource protection and avoid contamination. The study area also included the industrial and residential areas of Madurai urban region, Tamil Nadu, India, to validate ground truth verification. The study would help to reveal the disease monitoring, surveillance systems, improving the distribution of health resources by predicting available health care accessibility, the source of pollution and it impacts on public health. Especially in Madurai need more attention to epidemiology. Because, the 11,132 epidemic disease affected cases were recorded in 2019 [1]. In every year government of India spends more money for this type of epidemiological spread; especially in Tamil Nadu spend 8868 lakhs of money. WHO also revealed that the developing countries are highly affected by the epidemic diseases.

show abstract

“…Application of machine learning techniques, such as artificial neural networks, that are well-trained to identify feature patterns or mimic complex feature interactions is an attractive alternative that could furnish more accurate results through more consistently applied workflows over time and space. Recent work with machine learning has revealed promising results for extraction of hydrography [18][19][20][21][22][23] and other associated features [24][25][26] from lidar point cloud and other remotely sensed data. Research presented in this paper aims to test and develop machine learning workflows to extract hydrographic features from 3DEP and other data to enhance the collection and validation of hydrography data.…”

Section: Introductionmentioning

confidence: 99%

Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling

et al. 2021

View full text Add to dashboard Cite

Accurate maps of regional surface water features are integral for advancing ecologic, atmospheric and land development studies. The only comprehensive surface water feature map of Alaska is the National Hydrography Dataset (NHD). NHD features are often digitized representations of historic topographic map blue lines and may be outdated. Here we test deep learning methods to automatically extract surface water features from airborne interferometric synthetic aperture radar (IfSAR) data to update and validate Alaska hydrographic databases. U-net artificial neural networks (ANN) and high-performance computing (HPC) are used for supervised hydrographic feature extraction within a study area comprised of 50 contiguous watersheds in Alaska. Surface water features derived from elevation through automated flow-routing and manual editing are used as training data. Model extensibility is tested with a series of 16 U-net models trained with increasing percentages of the study area, from about 3 to 35 percent. Hydrography is predicted by each of the models for all watersheds not used in training. Input raster layers are derived from digital terrain models, digital surface models, and intensity images from the IfSAR data. Results indicate about 15 percent of the study area is required to optimally train the ANN to extract hydrography when F1-scores for tested watersheds average between 66 and 68. Little benefit is gained by training beyond 15 percent of the study area. Fully connected hydrographic networks are generated for the U-net predictions using a novel approach that constrains a D-8 flow-routing approach to follow U-net predictions. This work demonstrates the ability of deep learning to derive surface water feature maps from complex terrain over a broad area.

show abstract

Water Identification from High-Resolution Remote Sensing Images Based on Multidimensional Densely Connected Convolutional Neural Networks

Cited by 73 publications

References 56 publications

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Identification of vulnerable zone of surface water epidemiology using Remote Sensing and GIS techniques

Extensibility of U-Net Neural Network Model for Hydrographic Feature Extraction and Implications for Hydrologic Modeling

Contact Info

Product

Resources

About