A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images
Although unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/5/1533 |
| _version_ | 1797999988481982464 |
|---|---|
| author | Sirui Tian Yiyu Lin Wenyun Gao Hong Zhang Chao Wang |
| author_facet | Sirui Tian Yiyu Lin Wenyun Gao Hong Zhang Chao Wang |
| author_sort | Sirui Tian |
| collection | DOAJ |
| description | Although unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to performance degradation. In this paper, an unsupervised multi-scale convolution auto-encoder (MSCAE) was proposed which can simultaneously obtain the global features and local characteristics of targets with its U-shaped architecture and pyramid pooling modules (PPMs). The compact depth-wise separable convolution and the deconvolution counterpart were devised to decrease the trainable parameters. The PPM and the multi-scale feature learning scheme were designed to learn multi-scale features. Prior knowledge of SAR speckle was also embedded in the model. The reconstruction loss of the MSCAE was measured by the structural similarity index metric (SSIM) of the reconstructed data and the images filtered by the improved Lee sigma filter. A speckle suppression restriction was also added in the objective function to guarantee that the speckle suppression procedure would take place in the feature learning stage. Experimental results with the MSTAR dataset under the standard operating condition and several extended operating conditions demonstrated the effectiveness of the proposed model in SAR object classification tasks. |
| first_indexed | 2024-04-11T11:13:06Z |
| format | Article |
| id | doaj.art-af44b33caa164420b3b0ec22aaea27f9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:13:06Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-af44b33caa164420b3b0ec22aaea27f92022-12-22T04:27:24ZengMDPI AGSensors1424-82202020-03-01205153310.3390/s20051533s20051533A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar ImagesSirui Tian0Yiyu Lin1Wenyun Gao2Hong Zhang3Chao Wang4Department of Electronic Engineering, School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaDepartment of Electrical and Computer Engineering, University of California, Riverside, Riversidem, CA 92521, USACollege of Computer and Information, Hohai University, Nanjing 211100, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, ChinaAlthough unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to performance degradation. In this paper, an unsupervised multi-scale convolution auto-encoder (MSCAE) was proposed which can simultaneously obtain the global features and local characteristics of targets with its U-shaped architecture and pyramid pooling modules (PPMs). The compact depth-wise separable convolution and the deconvolution counterpart were devised to decrease the trainable parameters. The PPM and the multi-scale feature learning scheme were designed to learn multi-scale features. Prior knowledge of SAR speckle was also embedded in the model. The reconstruction loss of the MSCAE was measured by the structural similarity index metric (SSIM) of the reconstructed data and the images filtered by the improved Lee sigma filter. A speckle suppression restriction was also added in the objective function to guarantee that the speckle suppression procedure would take place in the feature learning stage. Experimental results with the MSTAR dataset under the standard operating condition and several extended operating conditions demonstrated the effectiveness of the proposed model in SAR object classification tasks.https://www.mdpi.com/1424-8220/20/5/1533multi-scale representation learning (msrl)pyramid pooling module (ppm)compact depth-wise separable convolution (cseconv)convolution auto-encoder (cae)object classificationsynthetic aperture radar (sar) |
| spellingShingle | Sirui Tian Yiyu Lin Wenyun Gao Hong Zhang Chao Wang A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images Sensors multi-scale representation learning (msrl) pyramid pooling module (ppm) compact depth-wise separable convolution (cseconv) convolution auto-encoder (cae) object classification synthetic aperture radar (sar) |
| title | A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images |
| title_full | A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images |
| title_fullStr | A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images |
| title_full_unstemmed | A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images |
| title_short | A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images |
| title_sort | multi scale u shaped convolution auto encoder based on pyramid pooling module for object recognition in synthetic aperture radar images |
| topic | multi-scale representation learning (msrl) pyramid pooling module (ppm) compact depth-wise separable convolution (cseconv) convolution auto-encoder (cae) object classification synthetic aperture radar (sar) |
| url | https://www.mdpi.com/1424-8220/20/5/1533 |
| work_keys_str_mv | AT siruitian amultiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT yiyulin amultiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT wenyungao amultiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT hongzhang amultiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT chaowang amultiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT siruitian multiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT yiyulin multiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT wenyungao multiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT hongzhang multiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages AT chaowang multiscaleushapedconvolutionautoencoderbasedonpyramidpoolingmoduleforobjectrecognitioninsyntheticapertureradarimages |