scholarly journals FCAU-Net for the Semantic Segmentation of Fine-Resolution Remotely Sensed Images

2022 ◽  
Vol 14 (1) ◽  
pp. 215
Author(s):  
Xuerui Niu ◽  
Qiaolin Zeng ◽  
Xiaobo Luo ◽  
Liangfu Chen
Keyword(s):  
Spatial Information ◽  
Satellite Image ◽  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Feature Representation ◽  
Position Information ◽  
Feature Information ◽  
Remotely Sensed Images ◽  
Public Datasets ◽  
Fine Resolution

The semantic segmentation of fine-resolution remotely sensed images is an urgent issue in satellite image processing. Solving this problem can help overcome various obstacles in urban planning, land cover classification, and environmental protection, paving the way for scene-level landscape pattern analysis and decision making. Encoder-decoder structures based on attention mechanisms have been frequently used for fine-resolution image segmentation. In this paper, we incorporate a coordinate attention (CA) mechanism, adopt an asymmetric convolution block (ACB), and design a refinement fusion block (RFB), forming a network named the fusion coordinate and asymmetry-based U-Net (FCAU-Net). Furthermore, we propose novel convolutional neural network (CNN) architecture to fully capture long-term dependencies and fine-grained details in fine-resolution remotely sensed imagery. This approach has the following advantages: (1) the CA mechanism embeds position information into a channel attention mechanism to enhance the feature representations produced by the network while effectively capturing position information and channel relationships; (2) the ACB enhances the feature representation ability of the standard convolution layer and captures and refines the feature information in each layer of the encoder; and (3) the RFB effectively integrates low-level spatial information and high-level abstract features to eliminate background noise when extracting feature information, reduces the fitting residuals of the fused features, and improves the ability of the network to capture information flows. Extensive experiments conducted on two public datasets (ZY-3 and DeepGlobe) demonstrate the effectiveness of the FCAU-Net. The proposed FCAU-Net transcends U-Net, Attention U-Net, the pyramid scene parsing network (PSPNet), DeepLab v3+, the multistage attention residual U-Net (MAResU-Net), MACU-Net, and the Transformer U-Net (TransUNet). Specifically, the FCAU-Net achieves a 97.97% (95.05%) pixel accuracy (PA), a 98.53% (91.27%) mean PA (mPA), a 95.17% (85.54%) mean intersection over union (mIoU), and a 96.07% (90.74%) frequency-weighted IoU (FWIoU) on the ZY-3 (DeepGlobe) dataset.

scholarly journals MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

2021 ◽  
pp. 1-5
Author(s):  
Rui Li ◽  
Chenxi Duan ◽  
Shunyi Zheng ◽  
Ce Zhang ◽  
Peter M. Atkinson
Keyword(s):  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Remotely Sensed Images ◽  
Fine Resolution

scholarly journals Unsupervised classification of saturated areas using a time series of remotely sensed images

2007 ◽  
Vol 4 (3) ◽  
pp. 1663-1696 ◽  
Author(s):  
D. A. DeAlwis ◽  
Z. M. Easton ◽  
H. E. Dahlke ◽  
W. D. Philpot ◽  
T. S. Steenhuis
Keyword(s):  
Water Content ◽  
Management Practices ◽  
Spatial Information ◽  
New York State ◽  
Soil Surface ◽  
Resource Planning ◽  
Remotely Sensed ◽  
Leaf Water Content ◽  
Remotely Sensed Data ◽  
Remotely Sensed Images

Abstract. The spatial distribution of saturated areas is an important consideration in numerous applications, such as water resource planning or sighting of management practices. However, in humid well vegetated climates where runoff is produced by saturation excess processes on hydrologically active areas (HAA) the delineation of these areas can be difficult and time consuming. Much of the non-point source pollution in these watersheds originates from these HAAs. Thus, a technique that can simply and reliably predict these areas would be a powerful tool for scientists and watershed managers tasked with implementing practices to improve water quality. Remotely sensed data is a source of spatial information and could be used to identify HAAs, should a proper technique be developed. The objective of this study is to develop a methodology to determine the spatial variability of saturated areas using a temporal sequence of remotely sensed images. The Normalized Difference Water Index (NDWI) was derived from medium resolution LANDSAT 7 ETM+ imagery collected over seven months in the Town Brook watershed in the Catskill Mountains of New York State and used to characterize the areas that were susceptible to saturation. We found that within a single landcover type, saturated areas were characterized by the soil surface water content when the vegetation was dormant and leaf water content of vegetation during the growing season. The resulting HAA map agreed well with both observed and spatially distributed computer simulated saturated areas. This methodology appears promising for delineating saturated areas in the landscape.

scholarly journals Semantic Segmentation on Remotely-Sensed Images Using Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning

2018 ◽  
Author(s):  
Teerapong Panboonyuen ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern ◽  
Peerapon Vateekul
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Convolutional Network ◽  
Domain Specific ◽  
Medium Resolution ◽  
Remotely Sensed Images ◽  
Very High ◽  
Resolution Data

In remote sensing domain, it is crucial to automatically annotate semantics, e.g., river, building, forest, etc, on the raster images. Deep Convolutional Encoder Decoder (DCED) network is the state-of-the-art semantic segmentation for remotely-sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN network for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose to apply a recent CNN network call ''Global Convolutional Network (GCN)'', since it can capture different resolutions by extracting multi-scale features from different stages of the network. Also, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, ''Channel Attention'' is presented into our network in order to select most discriminative filters (features). Third, ''Domain Specific Transfer Learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given data sets: ($i$) medium resolution data collected from Landsat-8 satellite and ($ii$) very high resolution data called ''ISPRS Vaihingen Challenge Data Set''. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

scholarly journals Semantic Segmentation on Remotely-Sensed Images Using Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning

2018 ◽  
Author(s):  
Teerapong Panboonyuen ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern ◽  
Peerapon Vateekul
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Convolutional Network ◽  
Domain Specific ◽  
Medium Resolution ◽  
Remotely Sensed Images ◽  
Very High ◽  
Resolution Data

In remote sensing domain, it is crucial to annotate semantics, e.g., river, building, forest, etc, on the raster images. Deep Convolutional Encoder Decoder (DCED) network is the state-of-the-art semantic segmentation for remotely-sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose to apply a recent CNN call ``Global Convolutional Network (GCN)'', since it can capture different resolutions by extracting multi-scale features from different stages of the network. Also, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, ``Channel Attention'' is presented into our network in order to select most discriminative filters (features). Third, ``Domain Specific Transfer Learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given data sets: ($i$) medium resolution data collected from Landsat-8 satellite and ($ii$) very high resolution data called ``ISPRS Vaihingen Challenge Data Set''. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

scholarly journals Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

2019 ◽  
Vol 11 (18) ◽  
pp. 2142 ◽  
Author(s):  
Lianfa Li
Keyword(s):  
Land Use ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Residual Learning ◽  
Fully Convolutional Networks ◽  
Remotely Sensed Images ◽  
Real World Datasets

Semantic segmentation is a fundamental means of extracting information from remotely sensed images at the pixel level. Deep learning has enabled considerable improvements in efficiency and accuracy of semantic segmentation of general images. Typical models range from benchmarks such as fully convolutional networks, U-Net, Micro-Net, and dilated residual networks to the more recently developed DeepLab 3+. However, many of these models were originally developed for segmentation of general or medical images and videos, and are not directly relevant to remotely sensed images. The studies of deep learning for semantic segmentation of remotely sensed images are limited. This paper presents a novel flexible autoencoder-based architecture of deep learning that makes extensive use of residual learning and multiscaling for robust semantic segmentation of remotely sensed land-use images. In this architecture, a deep residual autoencoder is generalized to a fully convolutional network in which residual connections are implemented within and between all encoding and decoding layers. Compared with the concatenated shortcuts in U-Net, these residual connections reduce the number of trainable parameters and improve the learning efficiency by enabling extensive backpropagation of errors. In addition, resizing or atrous spatial pyramid pooling (ASPP) can be leveraged to capture multiscale information from the input images to enhance the robustness to scale variations. The residual learning and multiscaling strategies improve the trained model’s generalizability, as demonstrated in the semantic segmentation of land-use types in two real-world datasets of remotely sensed images. Compared with U-Net, the proposed method improves the Jaccard index (JI) or the mean intersection over union (MIoU) by 4-11% in the training phase and by 3-9% in the validation and testing phases. With its flexible deep learning architecture, the proposed approach can be easily applied for and transferred to semantic segmentation of land-use variables and other surface variables of remotely sensed images.

scholarly journals Application of spatial classification rules for remotely sensed images

2014 ◽  
Vol 55 ◽  
Author(s):  
Giedrius Stabingis ◽  
Lijana Stabingienė
Keyword(s):  
Classification Accuracy ◽  
Supervised Classification ◽  
Spatial Information ◽  
Gaussian Random Field ◽  
Remotely Sensed ◽  
Classification Rule ◽  
Classification Rules ◽  
Classification Methods ◽  
Remotely Sensed Images ◽  
Supervised Classification Methods

In this paper the remote sensed image classification example using spacial classification rule with distance (SCRD) is examined. This supervised classification method was first presented in paper [11]. This method is improved version of earlier method PBDF [4, 10, 9], during the classification it incorporates more spatial information. The advantage of this method is its ability to classify data which is corrupted by Gaussian random field and it is typical to remotely sensed images classified in this letter which are corrupted by clouds. Classification accuracy is compared with earlier method and with other commonly used supervised classification methods.

Remote Sensing and Spatial Statistics as Tools in Crime Analysis

2005 ◽  
pp. 270-292 ◽  
Author(s):  
Dongmei Chen ◽  
John R. Weeks ◽  
John V. Kaiser Jr.
Keyword(s):  
Remote Sensing ◽  
Spatial Statistics ◽  
Analytical Approach ◽  
Spatial Information ◽  
Criminal Activity ◽  
Emergency Situation ◽  
Remotely Sensed ◽  
Remotely Sensed Images ◽  
Basic Approaches ◽  
New Variables

This chapter explores the feasibility and utility of using aerial photography or remotely sensed satellite imagery to identify geographic or “place” features that may be associated with criminal activity. It assesses whether or not variables derived from satellite images can provide surrogate relationships between land use and crime. A review of the remote sensing literature suggests two basic approaches to the use of remotely sensed images in law enforcement: (1) tactical; and (2) analytical. The tactical approach uses the imagery as a background to the maps and other spatial information that an officer on the beat might have as he or she is investigating a crime or emergency situation. The analytical approach uses the remotely sensed images to create new variables that may serve as proxies for the risk of crime in particular locations. In this study we employ the analytical approach to the use of remotely sensed images, classifying images according to the presence or absence of vegetation within a pixel, as well as the classification of specific urban attributes, such as parking lots. We also employ spatial statistics to quantify the relationship between features of the images and crime events on the ground, and these analyses may be particularly useful as input to policy decisions about policing within the community.

scholarly journals Duplex Restricted Network with Guided Upsampling for the Semantic Segmentation of Remotely Sensed Images

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Xiaoyu Wang ◽  
Longxue Liang ◽  
Haowen Yan ◽  
Xiaosuo Wu ◽  
Wanzhen Lu ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Remotely Sensed ◽  
Remotely Sensed Images
Sign in / Sign up

Export Citation Format

Share Document