ZHOUQian-qian,SITUZu-xiang,LIUHan-lin,et al.Sewer Defects Recognition Based on Generative Adversarial Networks and Transfer Learning[J].China Water & Wastewater,2022,38(17):27-33.
Sewer Defects Recognition Based on Generative Adversarial Networks and Transfer Learning
China Water & Wastewater[ISSN:1000-4062/CN:12-1073/TU]
volume:
第38卷
Number:
第17期
Page:
27-33
Column:
Date of publication:
2022-09-01
- Keywords:
- deep learning; generative adversarial networks; transfer learning; sewer defects; intelligent recognition
- Abstract:
- The service reliability of urban drainage facilities is becoming an increasingly important engineering issue. Highly efficient, automated and large-scale intelligent detection of sewer defects is an urgent need and an important development trend for the construction and management of urban drainage facilities. Deep learning technology has developed rapidly in recent years, providing new methods for sewer defects detection. However, insufficient amount of data and unbalanced samples are common problems of deep learning models, which affects the generalization ability and recognition robustness of the models. Based on the current state-of-the-art generative adversarial network (StyleGAN), a high-quality sewer defects image synthesis method is proposed to solve the training sample problem. Further, a convolutional neural network algorithm is used to implement the sewer defects recognition with the help of transfer learning and pretrained model (SqueezeNet network), and the effect of the synthesized images is verified. Results showed that StyleGAN could efficiently synthesize high-quality sewer defects images with mean average precision of 90.0% for the recognition model (99.7%, 92.3%, 87.7% and 81.7% for the specific precisions of tree root, disjoint, residential wall and obstacle, respectively). Data augmentation with the help of generative adversarial networks provides a promising approach for deep learning model training with important applications.
Last Update:
2022-09-01