A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism
With the rapid development of computer vision and machine vision, methods based on deep learning have achieved good results in the field of object detection, identification, and tracking. However, for the detection and identification of rebars in smart construction sites, it is very difficult to per...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/14/8233 |
| _version_ | 1797590431515541504 |
|---|---|
| author | Yanmei Zheng Guanghui Zhou Bibo Lu |
| author_facet | Yanmei Zheng Guanghui Zhou Bibo Lu |
| author_sort | Yanmei Zheng |
| collection | DOAJ |
| description | With the rapid development of computer vision and machine vision, methods based on deep learning have achieved good results in the field of object detection, identification, and tracking. However, for the detection and identification of rebars in smart construction sites, it is very difficult to perform accurate real-time detection of rebars by using object detection technology on the equipment in the field because of the problems of the dense cross-section between bundled bars, the mutual adhesion of cross-section boundaries, and mutual occlusion between cross-sections. To address the above problems, we propose a multi-scale rebar detection network RebarNet with an embedded attention mechanism based on YOLOv5, combining the K-means++ algorithm, attention mechanism, a newly designed SD_IoU Loss, and multi-scale feature fusion, aiming to solve the problems of missed and false detection in dense small object detection. Due to the problems of scarce rebar cross-section datasets, no publicly available large datasets, and weak rebar cross-sectional features, we constructed a new rebar cross-sectional dataset, used a semi-automatic annotation method to annotate part of the dataset, and then used the data enhancement algorithm to expand the rebar dataset. The experimental results show that the average accuracy (mAP) of our proposed RebarNet network is 97.9%, which is comparable to mainstream target detection algorithms such as Faster R-CNN, SSD, RetinaNet, CenterNet, CornerNet, YOLOv3, YOLOv4, and YOLOv5s. mAP0.5 is improved by 8.1%, 13%, 26.4%, 25.8%, 26.2%, 11.7%, 7.6%, and 9%, respectively. In addition, the frames per second (FPS) transmission reaches 89 frames per second, the model weight is only 17.0 MB. In summary, the proposed RebarNet can effectively reduce missed and false detections in the rebar counting detection task based on real-time detection. |
| first_indexed | 2024-03-11T01:20:22Z |
| format | Article |
| id | doaj.art-25a5a8fa0e0a4a1f81f8606972b5c74c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T01:20:22Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-25a5a8fa0e0a4a1f81f8606972b5c74c2023-11-18T18:10:10ZengMDPI AGApplied Sciences2076-34172023-07-011314823310.3390/app13148233A Multi-Scale Rebar Detection Network with an Embedded Attention MechanismYanmei Zheng0Guanghui Zhou1Bibo Lu2College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003, ChinaCollege of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003, ChinaCollege of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003, ChinaWith the rapid development of computer vision and machine vision, methods based on deep learning have achieved good results in the field of object detection, identification, and tracking. However, for the detection and identification of rebars in smart construction sites, it is very difficult to perform accurate real-time detection of rebars by using object detection technology on the equipment in the field because of the problems of the dense cross-section between bundled bars, the mutual adhesion of cross-section boundaries, and mutual occlusion between cross-sections. To address the above problems, we propose a multi-scale rebar detection network RebarNet with an embedded attention mechanism based on YOLOv5, combining the K-means++ algorithm, attention mechanism, a newly designed SD_IoU Loss, and multi-scale feature fusion, aiming to solve the problems of missed and false detection in dense small object detection. Due to the problems of scarce rebar cross-section datasets, no publicly available large datasets, and weak rebar cross-sectional features, we constructed a new rebar cross-sectional dataset, used a semi-automatic annotation method to annotate part of the dataset, and then used the data enhancement algorithm to expand the rebar dataset. The experimental results show that the average accuracy (mAP) of our proposed RebarNet network is 97.9%, which is comparable to mainstream target detection algorithms such as Faster R-CNN, SSD, RetinaNet, CenterNet, CornerNet, YOLOv3, YOLOv4, and YOLOv5s. mAP0.5 is improved by 8.1%, 13%, 26.4%, 25.8%, 26.2%, 11.7%, 7.6%, and 9%, respectively. In addition, the frames per second (FPS) transmission reaches 89 frames per second, the model weight is only 17.0 MB. In summary, the proposed RebarNet can effectively reduce missed and false detections in the rebar counting detection task based on real-time detection.https://www.mdpi.com/2076-3417/13/14/8233rebar detectionYOLOv5K-means++attention mechanismSD_IoU lossmulti-scale detection |
| spellingShingle | Yanmei Zheng Guanghui Zhou Bibo Lu A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism Applied Sciences rebar detection YOLOv5 K-means++ attention mechanism SD_IoU loss multi-scale detection |
| title | A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism |
| title_full | A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism |
| title_fullStr | A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism |
| title_full_unstemmed | A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism |
| title_short | A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism |
| title_sort | multi scale rebar detection network with an embedded attention mechanism |
| topic | rebar detection YOLOv5 K-means++ attention mechanism SD_IoU loss multi-scale detection |
| url | https://www.mdpi.com/2076-3417/13/14/8233 |
| work_keys_str_mv | AT yanmeizheng amultiscalerebardetectionnetworkwithanembeddedattentionmechanism AT guanghuizhou amultiscalerebardetectionnetworkwithanembeddedattentionmechanism AT bibolu amultiscalerebardetectionnetworkwithanembeddedattentionmechanism AT yanmeizheng multiscalerebardetectionnetworkwithanembeddedattentionmechanism AT guanghuizhou multiscalerebardetectionnetworkwithanembeddedattentionmechanism AT bibolu multiscalerebardetectionnetworkwithanembeddedattentionmechanism |