Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework
Ground penetrating radar (GPR), as a non-invasive instrument, has been widely used in the civil field. The interpretation of GPR data plays a vital role in underground infrastructures to transfer raw data to the interested information, such as diameter. However, the diameter identification of object...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/11/1804 |
| _version_ | 1797549199400632320 |
|---|---|
| author | Wentai Lei Jiabin Luo Feifei Hou Long Xu Ruiqing Wang Xinyue Jiang |
| author_facet | Wentai Lei Jiabin Luo Feifei Hou Long Xu Ruiqing Wang Xinyue Jiang |
| author_sort | Wentai Lei |
| collection | DOAJ |
| description | Ground penetrating radar (GPR), as a non-invasive instrument, has been widely used in the civil field. The interpretation of GPR data plays a vital role in underground infrastructures to transfer raw data to the interested information, such as diameter. However, the diameter identification of objects in GPR B-scans is a tedious and labor-intensive task, which limits the further application in the field environment. The paper proposes a deep learning-based scheme to solve the issue. First, an adaptive target region detection (ATRD) algorithm is proposed to extract the regions from B-scans that contain hyperbolic signatures. Then, a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) framework is developed that integrates Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network to extract hyperbola region features. It transfers the task of diameter identification into a task of hyperbola region classification. Experimental results conducted on both simulated and field datasets demonstrate that the proposed scheme has a promising performance for diameter identification. The CNN-LSTM framework achieves an accuracy of 99.5% on simulated datasets and 92.5% on field datasets. |
| first_indexed | 2024-03-10T15:11:19Z |
| format | Article |
| id | doaj.art-cd7abf4136894353ba9d4819706db420 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T15:11:19Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-cd7abf4136894353ba9d4819706db4202023-11-20T19:19:55ZengMDPI AGElectronics2079-92922020-10-01911180410.3390/electronics9111804Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM FrameworkWentai Lei0Jiabin Luo1Feifei Hou2Long Xu3Ruiqing Wang4Xinyue Jiang5School of Computer Science and Engineering, Central South University, Changsha 410075, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410075, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410075, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410075, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410075, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410075, ChinaGround penetrating radar (GPR), as a non-invasive instrument, has been widely used in the civil field. The interpretation of GPR data plays a vital role in underground infrastructures to transfer raw data to the interested information, such as diameter. However, the diameter identification of objects in GPR B-scans is a tedious and labor-intensive task, which limits the further application in the field environment. The paper proposes a deep learning-based scheme to solve the issue. First, an adaptive target region detection (ATRD) algorithm is proposed to extract the regions from B-scans that contain hyperbolic signatures. Then, a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) framework is developed that integrates Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network to extract hyperbola region features. It transfers the task of diameter identification into a task of hyperbola region classification. Experimental results conducted on both simulated and field datasets demonstrate that the proposed scheme has a promising performance for diameter identification. The CNN-LSTM framework achieves an accuracy of 99.5% on simulated datasets and 92.5% on field datasets.https://www.mdpi.com/2079-9292/9/11/1804ground penetrating radar (GPR)hyperbola region detectionConvolutional Neural Network (CNN)Long Short-Term Memory (LSTM)hyperbola classificationdiameter identification |
| spellingShingle | Wentai Lei Jiabin Luo Feifei Hou Long Xu Ruiqing Wang Xinyue Jiang Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework Electronics ground penetrating radar (GPR) hyperbola region detection Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) hyperbola classification diameter identification |
| title | Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework |
| title_full | Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework |
| title_fullStr | Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework |
| title_full_unstemmed | Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework |
| title_short | Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework |
| title_sort | underground cylindrical objects detection and diameter identification in gpr b scans via the cnn lstm framework |
| topic | ground penetrating radar (GPR) hyperbola region detection Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) hyperbola classification diameter identification |
| url | https://www.mdpi.com/2079-9292/9/11/1804 |
| work_keys_str_mv | AT wentailei undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework AT jiabinluo undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework AT feifeihou undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework AT longxu undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework AT ruiqingwang undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework AT xinyuejiang undergroundcylindricalobjectsdetectionanddiameteridentificationingprbscansviathecnnlstmframework |