基于改进的Faster R-CNN算法建筑领域裂缝检测研究

Crack Detection in Construction Field based on Improved Faster R-CNN Algorithm

在人工智能技术的驱动下,国家建筑设施智能化也在迅猛发展,墙体裂缝的检测问题也受到人们越来越多的关注。针对传统人工对建筑墙体裂缝检测精度低的问题,提出一种改进的Faster R-CNN算法进行墙面裂缝检测。首先,自制实验数据集并进行数据增强,之后使用ResNet50残差网络来替代VGG16网络模块进行特征提取,接着加入FPN特征金字塔模块,提高模型多尺度检测能力,最后使用EIoU损失函数提高模型检测精度。通过实验表明,改进后的算法检测能力大大提升,mAP值达到93.5%,能够满足高精度检测的需求。

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 was made and enhanced,then the ResNet50 residual network was used to replace the VGG16 network module for feature extraction,then the FPN feature pyramid module was added to improve the multi-scale detection ability of the model,and finally,the EIoU loss function was used to improve the accuracy of the model detection.The experiments showed 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.