Road Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks

Henry, Corentin; Azimi, Seyed Majid; Merkle, Nina

doi:10.1109/lgrs.2018.2864342

Cited by 177 publications

(107 citation statements)

References 15 publications

(21 reference statements)

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…Due to the attention modules, the proposed method, i.e., mask (m), successfully separates the top right regions. When comparing mask (e), (k), and (n), mask (k) [13] 0.7607 0.6014 0.4933 0.5853 U-net [14] 0.7524 0.6004 0.4814 0.6057 Deeplabv2 [17] 0.7348 0.6004 0.4746 0.5915 RefineNet [19] 0.7641 0.5961 0.4817 0.6134 PSPNet [18] 0.7292 0.6338 0.4934 0.5933 Deeplabv3+ [10] 0.7550 0.6009 0.4828 0.6079 DAN [28] 0.7376 0.6043 0.4786 0.5948 Deepunet [15] 0 connects the middle regions to some big regions, however, the proposed method, that is, mask (n), smoothly separates the middle regions to the correct shapes. The same results can be obtained in masks (l) and (o).…”

Section: Resultsmentioning

confidence: 99%

“…Yao et al . used pretrained FCNs on SAR images to classify buildings, land use, bodies of water and other natural areas, but unsatisfactory results are obtained for buildings. Chu et al .…”

Section: Related Workmentioning

confidence: 99%

“…FCN has established a new advanced technology in the semantic segmentation of aeronautical optical images [9] and successfully applied to satellite SAR images. Yao et al [10] used pretrained FCNs on SAR images to classify buildings, land use, bodies of water and other natural areas, but unsatisfactory results are obtained for buildings. Chu et al [11] integrated deep spatial patterns learned automatically by FCN with sparse and lowrank subspace features.…”

Section: Spatial Information Deep Cnns (Dcnns) Havementioning

confidence: 99%

See 2 more Smart Citations

A segmentation network with multiattention and its application to SAR image analysis

Long

Mabu

2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Image segmentation plays an important role in image understanding and region‐based applications. Many image segmentation algorithms have been proposed, but in this paper, we enhance the segmentation performance of deep learning using attention models that extract important features from the target images. The structure of the segmentation network is an encoder–decoder model that can combine position features and channel features, where the attention mechanisms refine both position and channel features. In the experiments, the proposed method is applied to satellite image analysis, where synthetic aperture radar images are analyzed to detect landslide areas after heavy rain occurred. The experimental results show that the proposed method obtains higher segmentation accuracy comparing with some conventional methods. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Yao et al . used pretrained FCNs on SAR images to classify buildings, land use, bodies of water and other natural areas, but unsatisfactory results are obtained for buildings. Chu et al .…”

Section: Related Workmentioning

confidence: 99%

Section: Spatial Information Deep Cnns (Dcnns) Havementioning

confidence: 99%

See 1 more Smart Citation

A segmentation network with multiattention and its application to SAR image analysis

Long

Mabu

2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…The aquaculture net contains a large amount of seawater information, which is actually a kind of noise, which will seriously affect the task of extracting and identifying the aquaculture net. The emergence of semantic segmentation methods has fully solved this problem, such as FCN (fully convolutional neural networks) [18][19][20][21], U-Net [22], Segnet [23], Deeplab series [24,25], and other semantic segmentation algorithms, which learn in end-to-end form, provide pixel semantic information to complete the pixel-level classification of images, and take into account the spectral, spatial, and contextual information, and have high classification accuracy. Among them, the FCN network is the forerunner of semantic segmentation, whose main characteristics are encoding-decoding structure and skip connection.…”

mentioning

confidence: 99%

A New Method for Extracting Laver Culture Carriers Based on Inaccurate Supervised Classification with FCN-CRF

Pan

Jiang

Zhang

et al. 2020

JMSE

View full text Add to dashboard Cite

Timely monitoring of marine aquaculture has considerable significance for marine ecological protection and maritime safety and security. Considering that supervised learning needs to rely on a large number of training samples and the characteristics of intensive and regular distribution of the laver aquaculture zone, in this paper, an inaccurate supervised classification model based on fully convolutional neural network and conditional random filed (FCN-CRF) is designed for the study of a laver aquaculture zone in Lianyungang, Jiangsu Province. The proposed model can extract the aquaculture zone and calculate the area and quantity of laver aquaculture net simultaneously. The FCN is used to extract the laver aquaculture zone by roughly making the training label. Then, the CRF is used to extract the isolated laver aquaculture net with high precision. The results show that the k a p p a coefficient of the proposed model is 0.984, the F 1 is 0.99, and the recognition effect is outstanding. For label production, the fault tolerance rate is high and does not affect the final classification accuracy, thereby saving more label production time. The findings provide a data basis for future aquaculture yield estimation and offshore resource planning as well as technical support for marine ecological supervision and marine traffic management.

show abstract

“…With regard to local line detection, many edge detectors based on SAR image characteristics are presented, such as ratio of averages (ROA) operator [3], ratio of exponentially weighted averages (ROEWA) operator [4], multiplicative Duda operator [5], D1D2 operators [6,7], and so on. Recently, the method of deep fully convolutional neural networks was also introduced to detect road candidates [8]. As for the global optimization process, a commonly used framework is Markov random fields (MRFs) [2,6,9,10] which construct a graph model on road segments.…”

mentioning

confidence: 99%

A Method for Road Network Extraction from High-Resolution SAR Imagery Using Direction Grouping and Curve Fitting

2019

View full text Add to dashboard Cite

Roads are an important recognition target in synthetic aperture radar (SAR) image interpretation. Although a considerable number of high-quality SAR images are now available, the method of road extraction is lagging. To extract the road network with low missed and false rates, this paper proposed a road network extraction approach which includes line detection, road segmentation, road network extraction and optimization. First, the linear feature response and direction map are obtained from the SAR intensity image using the multiplicative Duda operation. Then, the backscattering coefficient and coefficient of variation are combined using a support vector machine to eliminate the linear structures of non-roads, and the binary image of road candidates is subsequently achieved by morphological profiles of path openings. Next, with the obtained direction map, a novel thinning method based on binary image decomposition and curve fitting is presented to obtain line segments of the road network. Finally, a series of measures which involve overlap, continuity, and junction optimization are proposed to construct the road network. In the experiments, the proposed method was applied to Radarsat-2 and TerraSAR-X high-resolution images. The experimental results showed that the proposed method had an excellent performance in terms of both completeness and correctness. one for local linear feature detection aiming to achieve road candidates, and one for global optimization processing, which generates regular road lines and connects the gaps to form a road network. With regard to local line detection, many edge detectors based on SAR image characteristics are presented, such as ratio of averages (ROA) operator [3], ratio of exponentially weighted averages (ROEWA) operator [4], multiplicative Duda operator [5], D1D2 operators [6,7], and so on. Recently, the method of deep fully convolutional neural networks was also introduced to detect road candidates [8]. As for the global optimization process, a commonly used framework is Markov random fields (MRFs) [2,6,9,10] which construct a graph model on road segments. In [11], a Bayesian framework which constructed a conditional random field (CRF) model was utilized to achieve road network optimization. Besides, the work by Lu et al. [12] proposed a method based on region-growing to extract the road network which extended road region step-by-step with automatically selected seeds. Similarly, Cheng et al. [13] presented an approach using a parallel particle filter to track road centerlines. Other methods are based on the genetic algorithm [14] and the snakes model [15] can also be found in the literature.In this article, we develop a road network extraction approach also based on the aforementioned two steps. On the subject of local line detection, the method of multiplicative Duda operators [5] is applied, which utilizes a group of sliding windows with different widths and directions to obtain linear feature responses. Compared with other line detectors, the multiplicative Duda operator ...

show abstract

Road Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks

Cited by 177 publications

References 15 publications

A segmentation network with multiattention and its application to SAR image analysis

A segmentation network with multiattention and its application to SAR image analysis

A New Method for Extracting Laver Culture Carriers Based on Inaccurate Supervised Classification with FCN-CRF

A Method for Road Network Extraction from High-Resolution SAR Imagery Using Direction Grouping and Curve Fitting

Contact Info

Product

Resources

About