[1]MAO Yingchi,TANG Jianghong,WANG Jing,et al.Multi-task enhanced dam crack image detection based on Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2021,16(2):286-293.[doi:10.11992/tis.201910004]
Copy
Multi-task enhanced dam crack image detection based on Faster R-CNN
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
16
Number of periods:
2021 2
Page number:
286-293
Column:
学术论文—机器感知与模式识别
Public date:
2021-03-05
- Title:
- Multi-task enhanced dam crack image detection based on Faster R-CNN
- Keywords:
- crack image detection; Faster R-CNN; Multi-task detection; small targets detection; transfer learning; dam safety; RPN; small sample
- CLC:
- TP391
- DOI:
- 10.11992/tis.201910004
- Abstract:
- To improve the accuracy of the detection of multiple small targets using the faster R-CNN model, we propose 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 enhanced 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 adaptive balance TrAdaBoost method. Our experimental results show that the proposed ME Faster R-CNN with the K-MABtrA 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 increased by 1.06% and 1.56%, respectively.
- References:
-
[1] 苏南. 我国200米级高坝密集, 安全风险不可轻视[EB/OL]. (2017-11-09).https://www.thepaper.cn/newsDetail_forward_1858088.
[2] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, USA, 2015:91-99.
[3] HABER E, RUTHOTTO L, HOLTHAM E, et al. Learning across scales-a multiscale method for convolution neural networks[C]//Proceedings of the 23nd AAAI Conference on Artificial Intelligence. 2017.
[4] GERBER D, MEIER S, KELLERMANN W. Efficient target activity detection based on recurrent neural networks[C]//Proceedings of 2017 Hands-free Speech Communications and Microphone Arrays. San Francisco, USA, 2017:46-50.
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, USA, 2014:580-587.
[6] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:1440-1448.
[7] LIU WEI, ANGUELOV D, ERHAN D, et al. SSD:single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands, 2016:21-37.
[8] REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:6517-6525.
[9] KANG H H, LEE S W, YOU S H, et al. Novel vehicle detection system based on stacked DoG kernel and AdaBoost[J]. PLoS one, 2018, 13(3):e0193733.
[10] DAI Wenyuan, YANG Qiang, XUE Guirong, et al. Boosting for transfer learning[C]//Proceedings of the 24th International Conference on Machine Learning. New York, USA, 2007:193-200.
[11] AL-STOUHI S, REDDY C K. Adaptive boosting for transfer learning using dynamic updates[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany, 2011:60-75.
[12] 郭勇. 基于单源及多源的迁移学习方法研究[D]. 西安:西安电子科技大学, 2013.
GUO Yong. Research of transfer learning based on single-source and multi-source[D]. Xi’an:Xidian University, 2013.
[13] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016:770-778.
[14] WICAKSONO Y A, RIZALDY A, FAHRIAH S, et al. Improve image segmentation based on closed form matting using K-means clustering[C]//Proceedings of 2017 International Seminar on Application for Technology of Information and Communication. Semarang, Indonesia, 2018:26-30.
[15] AKCAY S, KUNDEGORSKI M E, WILLCOCKS C G, et al. Using deep convolutional neural network architectures for object classification and detection within X-ray baggage security imagery[J]. IEEE transactions on information forensics and security, 2018, 13(9):2203-2215.
[16] RAHMAN M A, WANG Yang. Optimizing intersection-over-union in deep neural networks for image segmentation[C]//Proceedings of 12th International Symposium on Advances in Visual Computing. Las Vegas, USA, 2016:234-244.
[17] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Proceedings of 13th European Conference on Computer Vision. Zurich, Switzerland, 2014:818-833.
[18] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of 3rd International Conference on Learning Representations. San Diego, USA, 2015.
- Similar References:
Memo
-
Last Update:
2021-04-25