Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model
Amid the era of intelligent construction and inspection, traditional object detection models like YOLOv8 struggle in bridge defect detection due to high computational complexity and limited speed. To address this, the lightweight SATH–YOLO model was proposed in this paper. First, the Star Block from...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/5/1449 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850050693425004544 |
|---|---|
| author | Lanlin Zou Ao Liu |
| author_facet | Lanlin Zou Ao Liu |
| author_sort | Lanlin Zou |
| collection | DOAJ |
| description | Amid the era of intelligent construction and inspection, traditional object detection models like YOLOv8 struggle in bridge defect detection due to high computational complexity and limited speed. To address this, the lightweight SATH–YOLO model was proposed in this paper. First, the Star Block from StarNet was used to build the STNC2f module, enriching semantic information and improving multi-scale feature fusion while reducing parameters and computation. Second, the SPPF module was replaced with an AIFI module to capture finer-grained local features, improving feature-fusion precision and adaptability in complex scenarios. Lastly, a lightweight TDMDH detection head with shared convolution and dynamic feature selection further reduced computational costs. With the SATH–YOLO model, parameter count, computation, and model size were reduced significantly by 39.9%, 8.6%, and 36.2%, respectively. Meanwhile, the average detection precision was not impacted but improved by 1%, which meets the demands of edge devices and resource-constrained environments. |
| format | Article |
| id | doaj-art-39aa26f85ec343ae95d3e15ed030d297 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-39aa26f85ec343ae95d3e15ed030d2972025-08-20T02:53:22ZengMDPI AGSensors1424-82202025-02-01255144910.3390/s25051449Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO ModelLanlin Zou0Ao Liu1College of Automotive and Transportation Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaCollege of Automotive and Transportation Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaAmid the era of intelligent construction and inspection, traditional object detection models like YOLOv8 struggle in bridge defect detection due to high computational complexity and limited speed. To address this, the lightweight SATH–YOLO model was proposed in this paper. First, the Star Block from StarNet was used to build the STNC2f module, enriching semantic information and improving multi-scale feature fusion while reducing parameters and computation. Second, the SPPF module was replaced with an AIFI module to capture finer-grained local features, improving feature-fusion precision and adaptability in complex scenarios. Lastly, a lightweight TDMDH detection head with shared convolution and dynamic feature selection further reduced computational costs. With the SATH–YOLO model, parameter count, computation, and model size were reduced significantly by 39.9%, 8.6%, and 36.2%, respectively. Meanwhile, the average detection precision was not impacted but improved by 1%, which meets the demands of edge devices and resource-constrained environments.https://www.mdpi.com/1424-8220/25/5/1449bridge defect detectionlightweight architectureStarNetAdaptive Intra-Feature Interactiontask-dynamic detectionfeature fusion |
| spellingShingle | Lanlin Zou Ao Liu Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model Sensors bridge defect detection lightweight architecture StarNet Adaptive Intra-Feature Interaction task-dynamic detection feature fusion |
| title | Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model |
| title_full | Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model |
| title_fullStr | Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model |
| title_full_unstemmed | Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model |
| title_short | Intelligent Detection Algorithm for Concrete Bridge Defects Based on SATH–YOLO Model |
| title_sort | intelligent detection algorithm for concrete bridge defects based on sath yolo model |
| topic | bridge defect detection lightweight architecture StarNet Adaptive Intra-Feature Interaction task-dynamic detection feature fusion |
| url | https://www.mdpi.com/1424-8220/25/5/1449 |
| work_keys_str_mv | AT lanlinzou intelligentdetectionalgorithmforconcretebridgedefectsbasedonsathyolomodel AT aoliu intelligentdetectionalgorithmforconcretebridgedefectsbasedonsathyolomodel |