|
|
|
| Crack Detection in Construction Field Based on Improved Faster R-CNN Algorithm |
| LI Shuangyuan1, LIU Xiangyang2
|
| 1.Information Center，Jilin Institute of Chemical Technology，Jilin City 132022，China;2.School of Information and Control Engineering, Jilin Institute of Chemical Technology，Jilin City 132022,China |
|
|
|
|
Abstract Driven by artificial intelligence technology, the intelligentization of national building facilities is also developing rapidly, and the problem of wall crack detection is also receiving more and more attention. Aiming at the problem of low accuracy of traditional manual detection of building wall cracks, this paper proposes an improved Faster R-CNN algorithm for wall crack detection. Firstly, the experimental dataset is made and enhanced, then the ResNet50 residual network is used to replace the VGG16 network module for feature extraction, then the FPN feature pyramid module is added to improve the multi-scale detection ability of the model, and finally, the EIoU loss function is used to improve the accuracy of the model detection. The experiments show that the improved algorithm in this paper has greatly improved the detection ability, and the mAP value reaches 93.5%, which can meet the demand of high-precision detection.
|
|
Published: 25 May 2024
|
|
|
|
|
| [1] |
WANG Ying, SUN Kexin, LIU Zhengang, GAO Kangsheng, LIU Qi. Research on Bionic Robotic Fish Object Detection Algorithm based on Improved YOLOv5[J]. Journal of Jilin Institute of Chemical Technology, 2024, 41(5): 22-29. |
| [2] |
LIU Qi , SHENG Deqing , SUN Wanlong , WANG Ying.
Research on Fruit Target Detection based on Improved YOLOv5s
[J]. Journal of Jilin Institute of Chemical Technology, 2023, 40(7): 34-41. |
|
|
|
|
