基于Faster R-CNN的多任务增强裂缝图像检测方法

Multi-task enhanced dam crack image detection based on Faster R-CNN

针对Faster R-CNN算法对多目标、小目标检测精度不高的问题,本文提出一种基于Faster R-CNN的多任务增强裂缝图像检测(Multitask Enhanced Dam Crack Image Detection Based on Faster R-CNN,ME-Faster RCNN)方法。同时提出一种基于K-means的多源自适应平衡TrAdaBoost的迁移学习方法(multi-source adaptive balance TrAdaBoost based on K-means,K-MABtrA)辅助网络训练,解决样本不足问题。ME-Faster R-CNN将图片输入ResNet-50网络提取特征;然后将所得特征图输入多任务增强RPN模型,同时改善RPN模型的锚盒尺寸和大小以提高检测识别精度,生成候选区域;最后将特征图和候选区域发送到检测处理网络。K-MABtrA方法利用K-means聚类删除与目标源差别较大的图像,再在多元自适应平衡TrAdaBoost迁移学习方法下训练模型。实验结果表明:将ME-Faster R-CNN在K-MABtrA迁移学习的条件下应用于小数据集大坝裂缝图像集的平均IoU为82.52%,平均精度mAP值为80.02%,与相同参数设置下的Faster R-CNN检测算法相比,平均IoU和mAP值分别提高了1.06%和1.56%。

To improve the accuracy of the detection of multiple small targets using the faster R-CNN model,we pro-pose a multi-task enhanced dam-crack image detection method based on faster R-CNN(ME-Faster R-CNN).In addition,to solve the problem of insufficient dam-crack samples,we propose a transfer learning method,multi-source adaptive balance TrAdaBoost based on K-means(K-MABtrA),to assist with network training.In the ME-Faster R-CNN,the ResNet-50 network is adopted to extract features from original images,obtain the feature map,and input a multi-task en-hanced region-proposal-network module to generate candidate regions by adopting the appropriate size and dimensions of the anchor box.Lastly,the features map and candidate regions are processed to detect dam cracks.The K-MABtrA method first uses K-means clustering to delete unsuitable images.Then,models are trained using the multi-source adapt-ive balance TrAdaBoost method.Our experimental results show that the proposed ME Faster R-CNN with the K-MAB-trA method can obtain an 82.52%average intersection over union(IoU)and 80.02%mean average precision(mAP).Compared with Faster R-CNN detection method using the same parameters,the average IoU and mAP values was in-creased by 1.06%and 1.56%,respectively.