A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition
Ground penetrating radar (GPR) is an effective and efficient nondestructive testing technology for subsurface investigations. Deep learning-based methods have been successfully used in automatic underground target recognition. However, these methods are mostly based on supervised learning, requiring...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/10/3138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850256567253860352 |
|---|---|
| author | Li Liu Dajiang Yu Xiping Zhang Hang Xu Jingxia Li Lijun Zhou Bingjie Wang |
| author_facet | Li Liu Dajiang Yu Xiping Zhang Hang Xu Jingxia Li Lijun Zhou Bingjie Wang |
| author_sort | Li Liu |
| collection | DOAJ |
| description | Ground penetrating radar (GPR) is an effective and efficient nondestructive testing technology for subsurface investigations. Deep learning-based methods have been successfully used in automatic underground target recognition. However, these methods are mostly based on supervised learning, requiring large amounts of labeled training data to guarantee high accuracy and generalization ability, which is a challenge in GPR fields due to time-consuming and labor-intensive data annotation work. To alleviate the demand for abundant labeled data, a semi-supervised deep learning method named attention–temporal ensembling (Attention-TE) is proposed for underground target recognition using GPR B-scan images. This method integrates a semi-supervised temporal ensembling architecture with a triplet attention module to enhance the classification performance. Experimental results of laboratory and field data demonstrate that the proposed method can automatically recognize underground targets with an average accuracy of above 90% using less than 30% of labeled data in the training dataset. Ablation experimental results verify the efficiency of the triplet attention module. Moreover, comparative experimental results validate that the proposed Attention-TE algorithm outperforms the supervised method based on transfer learning and four semi-supervised state-of-the-art methods. |
| format | Article |
| id | doaj-art-584dc4a840824d419d5ff18dc6125362 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-584dc4a840824d419d5ff18dc61253622025-08-20T01:56:38ZengMDPI AGSensors1424-82202025-05-012510313810.3390/s25103138A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target RecognitionLi Liu0Dajiang Yu1Xiping Zhang2Hang Xu3Jingxia Li4Lijun Zhou5Bingjie Wang6Key Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaShanxi Intelligent Transportation Institute Co., Ltd., Taiyuan 030024, ChinaKey Laboratory of Advanced Transducers & Intelligent Control System, Ministry of Education, College of Physics & Optoelectronics, Taiyuan University of Technology, Taiyuan 030024, ChinaGround penetrating radar (GPR) is an effective and efficient nondestructive testing technology for subsurface investigations. Deep learning-based methods have been successfully used in automatic underground target recognition. However, these methods are mostly based on supervised learning, requiring large amounts of labeled training data to guarantee high accuracy and generalization ability, which is a challenge in GPR fields due to time-consuming and labor-intensive data annotation work. To alleviate the demand for abundant labeled data, a semi-supervised deep learning method named attention–temporal ensembling (Attention-TE) is proposed for underground target recognition using GPR B-scan images. This method integrates a semi-supervised temporal ensembling architecture with a triplet attention module to enhance the classification performance. Experimental results of laboratory and field data demonstrate that the proposed method can automatically recognize underground targets with an average accuracy of above 90% using less than 30% of labeled data in the training dataset. Ablation experimental results verify the efficiency of the triplet attention module. Moreover, comparative experimental results validate that the proposed Attention-TE algorithm outperforms the supervised method based on transfer learning and four semi-supervised state-of-the-art methods.https://www.mdpi.com/1424-8220/25/10/3138ground penetrating radarunderground target recognitiondeep learningsemi-supervised learningtemporal ensemblingtriplet attention |
| spellingShingle | Li Liu Dajiang Yu Xiping Zhang Hang Xu Jingxia Li Lijun Zhou Bingjie Wang A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition Sensors ground penetrating radar underground target recognition deep learning semi-supervised learning temporal ensembling triplet attention |
| title | A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition |
| title_full | A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition |
| title_fullStr | A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition |
| title_full_unstemmed | A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition |
| title_short | A Semi-Supervised Attention-Temporal Ensembling Method for Ground Penetrating Radar Target Recognition |
| title_sort | semi supervised attention temporal ensembling method for ground penetrating radar target recognition |
| topic | ground penetrating radar underground target recognition deep learning semi-supervised learning temporal ensembling triplet attention |
| url | https://www.mdpi.com/1424-8220/25/10/3138 |
| work_keys_str_mv | AT liliu asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT dajiangyu asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT xipingzhang asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT hangxu asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT jingxiali asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT lijunzhou asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT bingjiewang asemisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT liliu semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT dajiangyu semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT xipingzhang semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT hangxu semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT jingxiali semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT lijunzhou semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition AT bingjiewang semisupervisedattentiontemporalensemblingmethodforgroundpenetratingradartargetrecognition |