Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN
Rebar constitutes a crucial element within tunnel lining structures, where its precise arrangement plays a pivotal role in determining both structural stability and load-bearing capacity. Due to the rebar’s high dielectric constant approaching infinity, radar signal reflections are intensified, mani...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/367 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549382437044224 |
|---|---|
| author | Chuan Li Nianbiao Cai Tong Pu Xi Yang Hao Liu Lulu Wang |
| author_facet | Chuan Li Nianbiao Cai Tong Pu Xi Yang Hao Liu Lulu Wang |
| author_sort | Chuan Li |
| collection | DOAJ |
| description | Rebar constitutes a crucial element within tunnel lining structures, where its precise arrangement plays a pivotal role in determining both structural stability and load-bearing capacity. Due to the rebar’s high dielectric constant approaching infinity, radar signal reflections are intensified, manifesting as distinct hyperbolic patterns within radar imagery. By performing convolutional operations, these hyperbolic features of rebar can be effectively extracted from radar images. Building upon the feature extraction capabilities of the ResNet50 model, this study introduces a Deformable Attention to Capture Salient Information (DAS) mechanism, employing deformable and separable convolutions to enhance rebar localization and concentrate on hyperbolic features resulting from multiple reflections. Before the Region Proposal Network (RPN) and region of interest (ROI) pooling stages in Faster R-CNN, this study integrates a hyperbolic attention (HAT) module. Through refined distance metrics, the hyperbolic attention mechanism enhances the network’s Precision in identifying rebar hyperbolic features within feature maps. To ensure robustness across diverse conditions, this study utilizes a simulated public dataset for tunnel linings, alongside real data from the Husa Tunnel, to create a comprehensive ground-penetrating radar image dataset for tunnel linings. Experimental results indicate that the proposed model achieved an Average Precision of 94.93%, reflecting a 3.14% increase compared to the baseline model. Lastly, in a random selection of 50 radar images for testing, the model achieved a rebar detection accuracy of 93.46%, representing an enhancement of 0.94% over the baseline model. |
| format | Article |
| id | doaj-art-d57b8c9ce3f245e5b74a124be1b5c22a |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-d57b8c9ce3f245e5b74a124be1b5c22a2025-01-10T13:15:19ZengMDPI AGApplied Sciences2076-34172025-01-0115136710.3390/app15010367Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNNChuan Li0Nianbiao Cai1Tong Pu2Xi Yang3Hao Liu4Lulu Wang5Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaYunnan Aerospace Engineering Geophysical Detecting Co., Ltd., Kunming 650200, ChinaYunnan Aerospace Engineering Geophysical Detecting Co., Ltd., Kunming 650200, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaRebar constitutes a crucial element within tunnel lining structures, where its precise arrangement plays a pivotal role in determining both structural stability and load-bearing capacity. Due to the rebar’s high dielectric constant approaching infinity, radar signal reflections are intensified, manifesting as distinct hyperbolic patterns within radar imagery. By performing convolutional operations, these hyperbolic features of rebar can be effectively extracted from radar images. Building upon the feature extraction capabilities of the ResNet50 model, this study introduces a Deformable Attention to Capture Salient Information (DAS) mechanism, employing deformable and separable convolutions to enhance rebar localization and concentrate on hyperbolic features resulting from multiple reflections. Before the Region Proposal Network (RPN) and region of interest (ROI) pooling stages in Faster R-CNN, this study integrates a hyperbolic attention (HAT) module. Through refined distance metrics, the hyperbolic attention mechanism enhances the network’s Precision in identifying rebar hyperbolic features within feature maps. To ensure robustness across diverse conditions, this study utilizes a simulated public dataset for tunnel linings, alongside real data from the Husa Tunnel, to create a comprehensive ground-penetrating radar image dataset for tunnel linings. Experimental results indicate that the proposed model achieved an Average Precision of 94.93%, reflecting a 3.14% increase compared to the baseline model. Lastly, in a random selection of 50 radar images for testing, the model achieved a rebar detection accuracy of 93.46%, representing an enhancement of 0.94% over the baseline model.https://www.mdpi.com/2076-3417/15/1/367faster R-CNNtunnel liningground-penetrating radar (GPR)hyperbolic featuresrebar recognition |
| spellingShingle | Chuan Li Nianbiao Cai Tong Pu Xi Yang Hao Liu Lulu Wang Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN Applied Sciences faster R-CNN tunnel lining ground-penetrating radar (GPR) hyperbolic features rebar recognition |
| title | Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN |
| title_full | Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN |
| title_fullStr | Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN |
| title_full_unstemmed | Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN |
| title_short | Rebar Recognition Using Multi-Hyperbolic Attention in Faster R-CNN |
| title_sort | rebar recognition using multi hyperbolic attention in faster r cnn |
| topic | faster R-CNN tunnel lining ground-penetrating radar (GPR) hyperbolic features rebar recognition |
| url | https://www.mdpi.com/2076-3417/15/1/367 |
| work_keys_str_mv | AT chuanli rebarrecognitionusingmultihyperbolicattentioninfasterrcnn AT nianbiaocai rebarrecognitionusingmultihyperbolicattentioninfasterrcnn AT tongpu rebarrecognitionusingmultihyperbolicattentioninfasterrcnn AT xiyang rebarrecognitionusingmultihyperbolicattentioninfasterrcnn AT haoliu rebarrecognitionusingmultihyperbolicattentioninfasterrcnn AT luluwang rebarrecognitionusingmultihyperbolicattentioninfasterrcnn |