scholarly journals Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7397
Author(s):  
Yanjun Wang ◽  
Shaochun Li ◽  
Yunhao Lin ◽  
Mengjie Wang
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
High Resolution ◽  
Water Resource ◽  
Spatial Resolution ◽  
Water Body ◽  
Water Bodies ◽  
Image Texture ◽  
Support Vector ◽  
Remote Sensing Images

Rapid and accurate extraction of water bodies from high-spatial-resolution remote sensing images is of great value for water resource management, water quality monitoring and natural disaster emergency response. For traditional water body extraction methods, it is difficult to select image texture and features, the shadows of buildings and other ground objects are in the same spectrum as water bodies, the existing deep convolutional neural network is difficult to train, the consumption of computing resources is large, and the methods cannot meet real-time requirements. In this paper, a water body extraction method based on lightweight MobileNetV2 is proposed and applied to multisensor high-resolution remote sensing images, such as GF-2, WorldView-2 and UAV orthoimages. This method was validated in two typical complex geographical scenes: water bodies for farmland irrigation, which have a broken shape and long and narrow area and are surrounded by many buildings in towns and villages; and water bodies in mountainous areas, which have undulating topography, vegetation coverage and mountain shadows all over. The results were compared with those of the support vector machine, random forest and U-Net models and also verified by generalization tests and the influence of spatial resolution changes. First, the results show that the F1-score and Kappa coefficients of the MobileNetV2 model extracting water bodies from three different high-resolution images were 0.75 and 0.72 for GF-2, 0.86 and 0.85 for Worldview-2 and 0.98 and 0.98 for UAV, respectively, which are higher than those of traditional machine learning models and U-Net. Second, the training time, number of parameters and calculation amount of the MobileNetV2 model were much lower than those of the U-Net model, which greatly improves the water body extraction efficiency. Third, in other more complex surface areas, the MobileNetV2 model still maintained relatively high accuracy of water body extraction. Finally, we tested the effects of multisensor models and found that training with lower and higher spatial resolution images combined can be beneficial, but that using just lower resolution imagery is ineffective. This study provides a reference for the efficient automation of water body classification and extraction under complex geographical environment conditions and can be extended to water resource investigation, management and planning.

scholarly journals A Multi-Scale Water Extraction Convolutional Neural Network (MWEN) Method for GaoFen-1 Remote Sensing Images

2020 ◽  
Vol 9 (4) ◽  
pp. 189 ◽  
Author(s):  
Hongxiang Guo ◽  
Guojin He ◽  
Wei Jiang ◽  
Ranyu Yin ◽  
Lei Yan ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Water Body ◽  
Semantic Segmentation ◽  
Water Bodies ◽  
Water Extraction ◽  
Remote Sensing Images ◽  
Multi Scale

Automatic water body extraction method is important for monitoring floods, droughts, and water resources. In this study, a new semantic segmentation convolutional neural network named the multi-scale water extraction convolutional neural network (MWEN) is proposed to automatically extract water bodies from GaoFen-1 (GF-1) remote sensing images. Three convolutional neural networks for semantic segmentation (fully convolutional network (FCN), Unet, and Deeplab V3+) are employed to compare with the water bodies extraction performance of MWEN. Visual comparison and five evaluation metrics are used to evaluate the performance of these convolutional neural networks (CNNs). The results show the following. (1) The results of water body extraction in multiple scenes using the MWEN are better than those of the other comparison methods based on the indicators. (2) The MWEN method has the capability to accurately extract various types of water bodies, such as urban water bodies, open ponds, and plateau lakes. (3) By fusing features extracted at different scales, the MWEN has the capability to extract water bodies with different sizes and suppress noise, such as building shadows and highways. Therefore, MWEN is a robust water extraction algorithm for GaoFen-1 satellite images and has the potential to conduct water body mapping with multisource high-resolution satellite remote sensing data.

Multi-Spectral Image Fusion Using Intensity Modulation and Non-Separable Wavelet Frame

2005 ◽  
Author(s):  
Xuhong Yang ◽  
Zhongliang Jing ◽  
Jian-Xun Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Spatial Resolution ◽  
Intensity Modulation ◽  
Spectral Information ◽  
Wavelet Frame ◽  
Remote Sensing Images ◽  
Spectral Image ◽  
Panchromatic Image ◽  
Fusion Approach

A fusion approach is proposed to refine the resolution of multi-spectral images using the corresponding high-resolution panchromatic images. The technique is based on intensity modulation and non-separable wavelet frame. The high-resolution panchromatic image is decomposed by the non-separable wavelet frame. Then the wavelet coefficients are used as the factor of modulating to modulate the multi-spectral image. Experimental results indicate that, comparing with the traditional methods, the proposed method can efficiently preserve the spectral information while improving the spatial resolution of remote sensing images.

Study on Remote Sensing Images of De-Blurring Based on Dictionary Learning

2015 ◽  
Vol 738-739 ◽  
pp. 217-222
Author(s):  
Yan Jia ◽  
Zhen Tao Qin ◽  
Bang Xin Yang
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Spatial Resolution ◽  
Dictionary Learning ◽  
High Spatial Resolution ◽  
Learning Algorithm ◽  
Research Field ◽  
Projection Algorithm ◽  
Remote Sensing Images ◽  
Novel Algorithm

De-blurring the high resolution remote sensing images is an important issue in the relative research field of remote sensing. In this paper a novel algorithm of de-blurring the high resolution remote sensing images is proposed based on sparse representation. The high spatial resolution remote sensing images can be de-blurred by gradient projection algorithm, and keep the useful information of the image. The experimental results of the remote sensing images obtained by “the first satellite of high resolution” show that the algorithm can de-blur the image more effectively and improve the PSNR, this method has better performance than other dictionary learning algorithm.

scholarly journals Comparative Analysis of Machine Learning Algorithms in Automatic Identification and Extraction of Water Boundaries

2021 ◽  
Vol 11 (21) ◽  
pp. 10062
Author(s):  
Aimin Li ◽  
Meng Fan ◽  
Guangduo Qin ◽  
Youcheng Xu ◽  
Hailong Wang
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Decision Tree ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Water Bodies ◽  
Support Vector ◽  
Landsat 8 ◽  
Transfer Performance ◽  
Remote Sensing Images

Monitoring open water bodies accurately is important for assessing the role of ecosystem services in the context of human survival and climate change. There are many methods available for water body extraction based on remote sensing images, such as the normalized difference water index (NDWI), modified NDWI (MNDWI), and machine learning algorithms. Based on Landsat-8 remote sensing images, this study focuses on the effects of six machine learning algorithms and three threshold methods used to extract water bodies, evaluates the transfer performance of models applied to remote sensing images in different periods, and compares the differences among these models. The results are as follows. (1) Various algorithms require different numbers of samples to reach their optimal consequence. The logistic regression algorithm requires a minimum of 110 samples. As the number of samples increases, the order of the optimal model is support vector machine, neural network, random forest, decision tree, and XGBoost. (2) The accuracy evaluation performance of each machine learning on the test set cannot represent the local area performance. (3) When these models are directly applied to remote sensing images in different periods, the AUC indicators of each machine learning algorithm for three regions all show a significant decline, with a decrease range of 0.33–66.52%, and the differences among the different algorithm performances in the three areas are obvious. Generally, the decision tree algorithm has good transfer performance among the machine learning algorithms with area under curve (AUC) indexes of 0.790, 0.518, and 0.697 in the three areas, respectively, and the average value is 0.668. The Otsu threshold algorithm is the optimal among threshold methods, with AUC indexes of 0.970, 0.617, and 0.908 in the three regions respectively and an average AUC of 0.832.

scholarly journals A Neural Network-Based Distributed Compressed Sensing Algorithm to Derive Continuous Hyperspectral Images in Wireless Sensor Networks

2022 ◽  
Author(s):  
Md. Sarkar Hasanuzzaman
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
High Resolution ◽  
Super Resolution ◽  
Hyperspectral Images ◽  
Wireless Sensor ◽  
Remote Sensing Images

Abstract Hyperspectral imaging is a versatile and powerful technology for gathering geo-data. Planes and satellites equipped with hyperspectral cameras are currently the leading contenders for large-scale imaging projects. Aiming at the shortcomings of traditional methods for detecting sparse representation of multi-spectral images, this paper proposes wireless sensor networks (WSNs) based single-hyperspectral image super-resolution method based on deep residual convolutional neural networks. We propose a different strategy that involves merging cheaper multispectral sensors to achieve hyperspectral-like spectral resolution while maintaining the WSN's spatial resolution. This method studies and mines the nonlinear relationship between low-resolution remote sensing images and high-resolution remote sensing images, constructs a deep residual convolutional neural network, connects multiple residual blocks in series, and removes some unnecessary modules. For this purpose, a decision support system is used that provides the outcome to the next layer. Finally, this paper, fully explores the similarities between natural images and hyperspectral images, use natural image samples to train convolutional neural networks, and further use migration learning to introduce the trained network model to the super-resolution problem of high-resolution remote sensing images, and solve the lack of training samples problem. A comparison between different algorithms for processing data on datasets collected in situ and via remote sensing is used to evaluate the proposed approach. The experimental results show that the method has good performance and can obtain better super-resolution effects.

scholarly journals An Efficient Building Extraction Method from High Spatial Resolution Remote Sensing Images Based on Improved Mask R-CNN

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1465 ◽  
Author(s):  
Lili Zhang ◽  
Jisen Wu ◽  
Yu Fan ◽  
Hongmin Gao ◽  
Yehong Shao
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Extraction Methods ◽  
Detection Algorithm ◽  
Building Extraction ◽  
Remote Sensing Images ◽  
Edge Detection Algorithm ◽  
Average Value

In this paper, we consider building extraction from high spatial resolution remote sensing images. At present, most building extraction methods are based on artificial features. However, the diversity and complexity of buildings mean that building extraction methods still face great challenges, so methods based on deep learning have recently been proposed. In this paper, a building extraction framework based on a convolution neural network and edge detection algorithm is proposed. The method is called Mask R-CNN Fusion Sobel. Because of the outstanding achievement of Mask R-CNN in the field of image segmentation, this paper improves it and then applies it in remote sensing image building extraction. Our method consists of three parts. First, the convolutional neural network is used for rough location and pixel level classification, and the problem of false and missed extraction is solved by automatically discovering semantic features. Second, Sobel edge detection algorithm is used to segment building edges accurately so as to solve the problem of edge extraction and the integrity of the object of deep convolutional neural networks in semantic segmentation. Third, buildings are extracted by the fusion algorithm. We utilize the proposed framework to extract the building in high-resolution remote sensing images from Chinese satellite GF-2, and the experiments show that the average value of IOU (intersection over union) of the proposed method was 88.7% and the average value of Kappa was 87.8%, respectively. Therefore, our method can be applied to the recognition and segmentation of complex buildings and is superior to the classical method in accuracy.

Based on High Resolution of Remote Sensing Data Mining Houses Information Extraction Methods Research

2012 ◽  
Vol 170-173 ◽  
pp. 2803-2807
Author(s):  
Yan Hua Sun ◽  
Ping Wang
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Information Extraction ◽  
Spatial Resolution ◽  
Mining Area ◽  
Extraction Methods ◽  
Accuracy Evaluation ◽  
Remote Sensing Images ◽  
Extraction Technology ◽  
Solar Altitude

High resolution remote sensing images generally refer to image to the spatial resolution within 10m aerospace、aviation remote sensing images. The emergence of high-resolution images strengthened the ability to recognize the large scale features, especially for the extraction of houses information in mining area. High spatial resolution image has rich delicate texture feature, it is urgent to solution the problem of how to extract the features. The technology is very useful for statistic houses information、village relocation assessment and research of pressure coal status, providing important data basis for village relocation, statistics, assessment. Taking henan as a mining area for example, houses information extraction methods are discussed. This paper mainly research contents as followings: It is combined with the space texture information of high resolution imaging rich, using different methods to extract building information, including followings: First, ordinary image segmentation technology; this method is simple and feasible, but extracted housing information is not accurate. Second, the object-oriented method of feature extraction technology, visualization degree and extracting accuracy of this method is higher; Third, it has conducted the preliminary height extraction of the houses; according to the solar altitude angles and the shadow of the houses to calculate the height of the houses. And considering the influence of undulating terrain, using the terrain DEM data to analyze study area, finally determined the shadow length, and then used solar altitude angles to calculate houses height. Based on the verification, accuracy evaluation results show that houses contour information extraction accuracy is: accuracy of the number and area is over 80%, the total rate of wrong classifications is lower. Houses highly information extraction accuracy is within the 85%. The research methods are effective.

Sign in / Sign up

Export Citation Format

Share Document