Segmentation of High Spatial Resolution Remote Sensing Image based On U-Net Convolutional Networks

Zheng, Xiaoxiong; Chen, Tao

doi:10.1109/igarss39084.2020.9324600

Cited by 15 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the effectiveness of method, PSPNet, 15 DUC_HDC, 30 Deeplabv3+, 14 U-Net, 9 and other classical neural networks are compared with the P-Net using the pretrained ImageNet backbone network for feature extraction. The overall segmentation evaluation results of each model on GID validation set are shown in Table 6.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…The existing semantic segmentation network mainly solves the above problems in two ways: one is to design the encoding and decoding structure to gradually restore the feature map size; the other is to expand the receptive field by dilation convolution (or cavity convolution). 8 Typical codec networks include U-Net 9 and SegNet. 10 Based on FCN, the U-Net model introduces skip connection to jointly learn the primary and secondary features to extract the details of the image.…”

Section: Introductionmentioning

confidence: 99%

“…Typical codec networks include U-Net 9 and SegNet 10 . Based on FCN, the U-Net model introduces skip connection to jointly learn the primary and secondary features to extract the details of the image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Remote sensing image semantic segmentation method based on small target and edge feature enhancement

Wang,

Qiao,

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

.Semantic segmentation of high-resolution remote sensing images based on deep learning has become a hot research topic and has been widely applied. At present, based on the structure of the convolutional neural network, when extracting target features through multiple layer convolutional layers, it is easy to cause the loss of small target features and fuzzy boundary of ground object classification. Therefore, we propose a remote sensing image semantic segmentation method P-Net to detect small target and enhance edge feature. The proposed network was based on an Encoder-Decoder structure. The decoder included the following components: a progressive small target feature enhancement network (IFEN), a boundary thinning module (BRM), and a feature aggregation module (FIAM). Firstly, the dense side output features of the encoder network were utilized to learn and acquired small target feature information and target edge features. Secondly, the pyramid segmentation attention module was introduced to effectively extract fine-grained and multi-scale spatial information. This module enhanced the feature expression of small targets and obtained high-level semantic feature information. The boundary refinement module was designed to refine the low-level spatial feature information extracted by the encoder. Finally, in order to improve the accuracy of remote sensing image object segmentation boundaries, skip connections were used to fuse high-level semantic information and low-level spatial information acrossed layers. These skip connections had the same spatial resolution but different semantic information. In this paper, six evaluation indices including mean intersection over union, frequency weighted intersection over union, pixel accuracy, F1, recall, and precision were used to verify on two public datasets of high-resolution remote sensing images, Gaofen image dataset (GID) and wuhan dense labeling dataset (WHDLD). In the GID dataset, each index reached 78.90%, 78.87%, 87.76%, 87.74%, 87.51%, and 88.04%, respectively; in the WHDLD dataset, each index reached 63.21%, 75.20%, 84.67%, 75.79%, 76.56%, and 75.45%, respectively. The results show that the performance of proposed method is better than that of DeepLabv3+, U-NET, PSPNet, and DUC_HDC methods. More precisely, the recognition performance of small target features is better, and the boundary obtained between object categories is clearer.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remote sensing image semantic segmentation method based on small target and edge feature enhancement

Wang,

Qiao,

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…The advent of deep learning has effectively addressed this issue. The use of deep learning for the analysis of remote sensing images is becoming increasingly widespread across various research fields, such as perimeter mapping, ecosystem services [6,7], delineation of agricultural fields [8], large-scale mapping of tree crops [9], extensive road extraction [10], and detection of burned areas [11] Deep learning has also demonstrated high performance in classifying and extracting the necessary information from remote sensing images, as evidenced by achievements with network models like U-Net [12], Residual Networks (ResNet) [13], Deep Residual U-Net (ResU-Net) [14], convolutional network-based semantic segmentation [15], and Pyramid Scene Parsing Network (MP-Net) [16].…”

Section: Introductionmentioning

confidence: 99%

MMDL-Net: Multi-Band Multi-Label Remote Sensing Image Classification Model

Cheng,

Li,

Deng

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

High-resolution remote sensing imagery comprises spatial structure features of multispectral bands varying in scale, color, and shape. These heterogeneous geographical features introduce grave challenges to the fine segmentation required for classification applications in remote sensing imagery, where direct application of traditional image classification models fails to deliver optimal results. To overcome these challenges, a multispectral, multi-label model, MMDL-Net, has been developed. This model is integrated with the multi-label BigEarthNet dataset, primarily employed for land cover classification research in remote sensing imagery, with each image composed of 13 spectral bands and spatial resolutions of 10 m, 20 m, and 60 m. To effectively utilize the information across these bands, a multispectral stacking module has been introduced to concatenate this spectral information. To proficiently process three distinct large-scale remote sensing image datasets, a multi-label classification module has been incorporated for training and inference. To better learn and represent the intricate features within the images, a twin-number residual structure has been proposed. The results demonstrate that the MMDL-Net model achieves a top accuracy of 83.52% and an F1 score of 77.97%, surpassing other deep learning models and conventional methods, thereby exhibiting exceptional performance in the task of multispectral multi-label classification of remote sensing imagery.

show abstract

“…Based on this, a large number of improved semantic segmentation networks have emerged, such as SegNet [11], U-Net [12], PSPNet [13], and DeepLab [14]. Some scholars have applied these improved networks to the task of VHR remote-sensing image land-cover classification, and these networks have shown excellent performance compared with traditional algorithms [15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Convolution Self-Attention Network for Land-Cover Classification in VHR Remote-Sensing Images

et al. 2022

View full text Add to dashboard Cite

The current deep convolutional neural networks for very-high-resolution (VHR) remote-sensing image land-cover classification often suffer from two challenges. First, the feature maps extracted by network encoders based on vanilla convolution usually contain a lot of redundant information, which easily causes misclassification of land cover. Moreover, these encoders usually require a large number of parameters and high computational costs. Second, as remote-sensing images are complex and contain many objects with large-scale variances, it is difficult to use the popular feature fusion modules to improve the representation ability of networks. To address the above issues, we propose a dynamic convolution self-attention network (DCSA-Net) for VHR remote-sensing image land-cover classification. The proposed network has two advantages. On one hand, we designed a lightweight dynamic convolution module (LDCM) by using dynamic convolution and a self-attention mechanism. This module can extract more useful image features than vanilla convolution, avoiding the negative effect of useless feature maps on land-cover classification. On the other hand, we designed a context information aggregation module (CIAM) with a ladder structure to enlarge the receptive field. This module can aggregate multi-scale contexture information from feature maps with different resolutions using a dense connection. Experiment results show that the proposed DCSA-Net is superior to state-of-the-art networks due to higher accuracy of land-cover classification, fewer parameters, and lower computational cost. The source code is made public available.

show abstract

Segmentation of High Spatial Resolution Remote Sensing Image based On U-Net Convolutional Networks

Cited by 15 publications

References 5 publications

Remote sensing image semantic segmentation method based on small target and edge feature enhancement

Remote sensing image semantic segmentation method based on small target and edge feature enhancement

MMDL-Net: Multi-Band Multi-Label Remote Sensing Image Classification Model

Dynamic Convolution Self-Attention Network for Land-Cover Classification in VHR Remote-Sensing Images

Contact Info

Product

Resources

About