ABSTRACT
With the rapid development of deep learning, remote sensing image interpretation using semantic segmentation has been widely used in various fields. Deep convolutional Neural network (DCNN) is an important tool for semantic segmentation. However, increasing the complexity of the network and deepening the neural network not only can improve the accuracy of the network, but also lead to the overfitting problem. Based on this point, this paper used the squeeze-and-excitation (SE) modules to optimize the network. SE modules are superimposed after each layer of the ResNet-101 network. This method not only improves network performance but does not lose small target information too much. In this experiment, RGB and nDSM multi-channels of high resolution remote sensing (RS) images with multi-semantic information are used. Experimental results show that the accuracy of the proposed method in the training set and verification set can reach 98.11% and 98.45%, and the model is in continuous convergence. OA, Precision, Recall, F1 and MIOU can reach 85.73%, 84.64%, 85.76%, 85.67%, and 75.47% respectively.
- Liu J H. 2011. Research on adaptive segmentation method of high spatial resolution remote sensing image. Fuzhou University.Google Scholar
- Zheng C, Zhang Y, Wang L. 2017. Semantic segmentation of remote sensing imagery using an object-based Markov random field model with auxiliary label fields. IEEE T Geosci Remote, 55, 5, (May 2017), 3015-3028. https://doi.org/10.1109/TGRS.2017.2658731.Google ScholarCross Ref
- Camps-Valls G, Bruzzone L. 2009. Kernel Methods for Remote Sensing Data Analysis Idex.Google Scholar
- Tang YQ. 2013. Object-oriented multi-feature change detection for high resolution image cities. Wuhan University.Google Scholar
- Zheng C, Chen Y, Shao J, 2022. An MRF-based multigranularity edge-preservation optimization for semantic segmentation of remote sensing images. IEEE Geosci Remote S, 19, 1-5. https://doi.org/10.1109/LGRS.2021.3058939.Google ScholarCross Ref
- Zheng C, Zhang Y, Wang L. 2021. Multigranularity Multiclass-Layer Markov Random Field Model for Semantic Segmentation of Remote Sensing Images. IEEE T Geosci Remote, 59, 12, (December 2021), 10555-10574. https://doi.org/10.1109/TGRS.2020.3033293.Google ScholarCross Ref
- Paul A, Mukherjee D P, Das P, 2018. Improved Random Forest for Classification. IEEE T Image Process, 27, 8, (August 2018), 4012-4024. https://doi.org/10.1109/TIP.2018.2834830.Google ScholarCross Ref
- Bovolo F, Bruzzone L, Marconcini M, 2007. A Novel Context-Sensitive SVM for Classification of Remote Sensing Images. In 2006 IEEE International Symposium on Geoscience and Remote Sensing, Denver, CO, USA, 2006, 2498-2501. https://doi.org/10.1109/IGARSS.2006.646.Google ScholarCross Ref
- Yuan XH, Shi JF, Gu LC. 2021. A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst Appl, 169, 6214, (May 2021), 114417. https://doi.org/10.1016/j.eswa.2020.114417.Google ScholarCross Ref
- Simonyan K, Zisserman A. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556.Google Scholar
- Chen HY, Sun ZL, Kong W. 2020. Semantic Image Segmentation Based on Fusion of Deep Neural Networks and Atrous Convolution. Journal of Chinese Computer systems. 41(01):166-170.Google Scholar
- Yang R, Zheng C, Wang L, Zhao Y. 2023. MAE-BG: dual-stream boundary optimization for remote sensing image semantic segmentation, Geocarto Int, 38, 1, (April 2023), 2190622. https://doi.org/10.1080/10106049.2023.2190622Google ScholarCross Ref
- Long J, Shelhamer E, Darrell T. 2015. Fully Convolutional Networks for Semantic Segmentation. Ieee T Pattern Anal, 39, 4, (April 2017), 640-651. https://doi.org/10.1109/TPAMI.2016.2572683.Google ScholarDigital Library
- He KM, Zhang X, Ren S, 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 770-778. https://doi.org/10.1109/CVPR.2016.90.Google ScholarCross Ref
- Jha D, Smedsrud P H, Riegler M A, 2019. ResUNet++: An Advanced Architecture for Medical Image Segmentation. In 2019 IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA, 225-2255. https://doi.org/10.1109/ISM46123.2019.00049.Google ScholarCross Ref
- Fid A, Fw B, Pc A, 2020. ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS J Photogramm, 162, (April 2020), 94-114. https://doi.org/10.1016/j.isprsjprs.2020.01.013.Google ScholarCross Ref
- Li R, Zheng SY, Zhang C, 2021. A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images. arXiv:2102.07997.Google Scholar
- Hu J, Shen L, Sun G. 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, UT, USA, 7132-7141. https://doi.org/10.1109/CVPR.2018.00745.Google ScholarCross Ref
Index Terms
- Boundary Detector Network with Squeeze-and-Excitation Network for Semantic Segmentation of Remote Sensing Images
Recommendations
DDCAttNet: Road Segmentation Network for Remote Sensing Images
Wireless Algorithms, Systems, and ApplicationsAbstractSemantic segmentation of remote sensing images based on deep convolutional neural networks has proven its effectiveness. However, due to the complexity of remote sensing images, deep convolutional neural networks have difficulties in segmenting ...
Semantic Segmentation of Remote Sensing Image Based on GAN and FCN Network Model
Accurate remote sensing image segmentation can guide human activities well, but current image semantic segmentation methods cannot meet the high-precision semantic recognition requirements of complex images. In order to further improve the accuracy of ...
Segmentation of remote-sensing images by incremental neural network
In this study, a novel incremental neural network (INeN) is proposed for the segmentation of remote-sensing images. The data set consists of seven images acquired by the Landsat-5 TM sensor. Two feature extraction methods are comparatively examined for ...
Comments