Skip to search formSkip to main contentSkip to account menu
DOI:10.3390/s22197624 - Corpus ID: 252834659
@article{Sariturk2022ARU, title={A Residual-Inception U-Net (RIU-Net) Approach and Comparisons with U-Shaped CNN and Transformer Models for Building Segmentation from High-Resolution Satellite Images}, author={Batuhan Sariturk and Dursun Zafer Seker}, journal={Sensors (Basel, Switzerland)}, year={2022}, volume={22}, url={https://api.semanticscholar.org/CorpusID:252834659}}
- Batuhan Sariturk, D. Seker
- Published in Italian National Conference… 1 October 2022
- Computer Science, Engineering, Environmental Science
The results showed that RIU-Net was significantly successful on Inria dataset and on Massachusetts datasets, Residual U-Net, Attention ResidUAL U- Net, and Trans U- net provided successful results.
9 Citations
3
2
Figures and Tables from this paper
- figure 1
- table 1
- figure 2
- table 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
- figure 8
- figure 9
- figure 10
- figure 11
- figure 12
Topics
RIU-Net (opens in a new tab)Test Accuracy (opens in a new tab)U-Net (opens in a new tab)Convolutional Neural Network (opens in a new tab)Massachusetts Building Dataset (opens in a new tab)IOU Scores (opens in a new tab)MobileNets (opens in a new tab)Transformer (opens in a new tab)Inria Aerial Image Labeling Dataset (opens in a new tab)Xception (opens in a new tab)
9 Citations
- Zhao XuZhiyang JiaJiahang SunWenpei DongZhang Li
- 2023
Computer Science, Medicine
ICCVIT
DO-UNet is introduced, which strengthens the structure of U-Net and outperforms other models in terms of dice coefficients and accuracy, and visualization results confirm DO-UNet's superiority in accurately segmenting spinal structures.
- Ozan OzturkMustafa Serkan IsikM. KadaD. Seker
- 2023
Environmental Science, Engineering
Applied Sciences
The combination of optical images and LiDAR point cloud in the deep learning model has increased the prediction performance and provided the integrity of road geometry in woodland and shadowed areas.
- 2
- PDF
- Zixiong WangShaodan LiZimeng Zhu
- 2023
Environmental Science, Computer Science
Sustainability
According to the compared experiments on the satellite images and public building datasets, the results show that the proposed method has a better performance, compared with other methods based on the same unified hierarchical models, in terms of quantitative and qualitative evaluation.
- 1
- PDF
- Tariq Al ShouraHo-fung LeungB. Balaji
- 2023
Computer Science, Environmental Science
Sensors
An adaptive convolutional kernels layer (AKL) is proposed as an architecture that adjusts dynamically to images’ sizes in order to extract comparable spectral information from images of different sizes, improving the features’ spatial resolution without sacrificing the local receptive field for various image applications.
- Long ShaoJianqiao Sun
- 2023
Engineering, History
Heritage Science
Improved U-Net models, traditional U- net models, FCN models, and EfficientNet models that incorporate channel attention mechanisms are used to identify historic building genes, obtaining the optimal intelligent recognition for historical architectural genes based on deep learning.
- 2
- PDF
- Zihan DengNan XiangJunjun Pan
- 2023
Medicine, Engineering
Bioengineering
It is found that the design of interaction and the choice of immersive technology in virtual surgery development should be closely related to the corresponding interactive operations in the real surgical speciality, which facilitates targeted technological adaptations in the direction of greater applicability and fidelity of simulation.
- Tsz-Kin LauPei-Chi TsaiHsin-yu OuTzu-Ping Lin
- 2023
Environmental Science, Engineering
Sustainable Cities and Society
- 1
- Kai LiYupeng Deng Junxian Ma
- 2023
Engineering, Computer Science
A novel Offset-Building Model (OBM) is proposed, and a prompt-based evaluation method is introduced, where the model reduces offset errors by 16.6% and improves roof Intersection over Union (IoU) by 10.8% compared to other models.
- E. SellamiHassan Rhinane
- 2024
Environmental Science, Engineering
E3S Web of Conferences
Year after year, floods become more and more a frequent and destructive force of nature, causing significant infrastructure losses and loss of life. An accurate and rapid assessment is required to…
62 References
- Haiying WangF. Miao
- 2022
Computer Science, Environmental Science
European Journal of Remote Sensing
An efficient model called residual U-Net (RU-Net) is proposed to extract buildings by combining the advantages of U- net, residual learning, atrous spatial pyramid pooling, and focal loss to reduce the parameters and degradation of the network.
- 39
- Highly Influential
- PDF
- Jun ChenYuxuan JiangLinbo LuoYue GuKangle Wu
- 2021
Computer Science, Environmental Science
2021 IEEE International Conference on Image…
A deepened space module is introduced, which can ignore the channels with weak target features and emphasize the effective features, and is embedded in each splicing layer in the upsampling process of U-net to achieve the effect of feature selection.
- 1
- Batuhan SariturkD. SekerOzan OzturkB. Bayram
- 2022
Computer Science, Engineering
Earth Science Informatics
The successful results of Deeper 1 and Deeper 2 architectures show that deeper architectures can provide better results even if there is not too much data, and Shallower 1 architecture appears to have a performance not far behind deep architectures, with less computational cost, and this shows usefulness for geographic applications.
- 5
- Yaohui LiuJie Zhou Zhiqiang Li
- 2020
Environmental Science, Engineering
IEEE Access
Compared to available deep learning models, the proposed ARC-Net demonstrates better segmentation performance with less computational costs and is both effective and efficient in automatic building extraction from high-resolution aerial images.
- 45
- PDF
- Ziang ZhangChengdong WuS. ColemanD. Kerr
- 2020
Computer Science, Medicine
Comput. Methods Programs Biomed.
- 169
- PDF
- C. QiuHe Li Michael Schmitt
- 2022
Computer Science, Environmental Science
IEEE Journal of Selected Topics in Applied Earth…
A baseline for model cross-area generalization ability is established and a proposal to fine-tune pretrained models from one area on a small subset of an unseen area, the effectiveness of which depends on the model choice and the data size for tuning is investigated.
- 19
- PDF
- Wenjing DengQ. ShiJun Li
- 2021
Computer Science, Engineering
IEEE Journal of Selected Topics in Applied Earth…
The stable encoder– decoder architecture is used, combined with a grid-based attention gate and atrous spatial pyramid pooling module, to capture and restore features progressively and effectively and validate the effectiveness of deep learning in practical scenarios.
- 58
- PDF
- Hu CaoYueyue Wang Manning Wang
- 2022
Computer Science, Medicine
ECCV Workshops
Under the direct down-sampling and up-sampled of the inputs and outputs by 4x, experiments demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full Convolution or the combination of transformer and convolution.
- 1,475 [PDF]
- Libo WangShenghui FangRui LiXiaoliang Meng
- 2022
Computer Science, Engineering
IEEE Transactions on Geoscience and Remote…
A novel Vision Transformer (BuildFormer), with a dual-path structure, designed to encode rich spatial details and a global context path to capture global dependencies, and a window-based linear multi-head self-attention, which strengthens the global context extraction by using large windows and greatly improves the potential of the Vision Trans transformer in processing large-sized remote sensing images.
- 87 [PDF]
- Qingyu LiYilei ShiXiao Xiang Zhu
- 2022
Computer Science, Engineering
IEEE Transactions on Geoscience and Remote…
This work proposes an instruction to assign the perturbation to the intermediate feature representations within the encoder, which considers the spatial resolution of input remote sensing imagery and the mean size of individual buildings in the study area.
- 17 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers