A Two-stage digital damage diagnosis method for traffic marking based on deep learning

A Two-stage digital damage diagnosis method for traffic marking based on deep learning

연구 분야: Verification

학회: Signal, Image and Video Processing

Two-stage traffic marking digital diagnostics method based on deep learning is proposed, that is, traffic marking inpainting is performed first, and diagnosis is performed later, to ensure the data quality of digital diagnosis. Firstly, a arrow damaged traffic marking dataset is collected and created. In inpainting stage, Data-driven traffic marking inpainting model (TMIN-GAN) based on generative adversarial network is constructed. By inpainting, the damaged traffic marking and the corresponding repaired complete traffic marking composition data pairs are obtained. Subsequently, classification of the degree of impairment according to visual recognizability. And the data pairs are subjected to comparison using the Learned Perceptual Image Patch Similarity (LPIPS) indicator. For training of TMIN-GAN model, FE-Mask R-CNN is adopted to automatically label the dataset by relying on the mask generated by instance segmentation. The experimental results demonstrate that traffic marking inpainting by the TMIN-GAN, compared by hand, reduces inpainting time from 10 s to milliseconds. This provides an excellent foundation for damage diagnosis. In TMIN-GAN training, the difference between PSNR value of the mask based on FE-Mask R-CNN and that of the manual annotation is only 2.35%. This demonstrates the feasibility of automatic annotation based on FE-Mask R-CNN masks. Compared by PSNR and SSIM evaluation indicators, the rationality and superiority of using LPIPS for traffic marking damage diagnosis is demonstrated and get the range of divided damage levels.