Pavement disease detection method based on deep learning

Abstract

The invention discloses a pavement disease detection method based on deep learning. A large number of normal road pictures are input, road disease image samples are not needed, a system result contains two neural networks, the structure of the first neural network is 'encoder-decoder-encoder', the first neural network is mainly responsible for encoding and decoding pictures, the encoding process is to convert the pictures into a group of vector data through the neural network, and finally, the decoded vector is compared with the decoded vector of the original picture. According to the pavementdisease detection method based on deep learning, which relates to the technical field of traffic pavement detection, a road disease sample does not need to be used for analysis, a large amount of manpower and material resources are saved, a plurality of neural networks are used, a large number of normal road pictures are analyzed for coding, decoding and re-coding training, the training quality is judged through a discrimination network, and finally, the difference between coded pictures and original picture codes is analyzed to detect whether a road has diseases or not.

Description

technical field [0001] The invention relates to the technical field of traffic road surface detection, in particular to a method for detecting road surface defects based on deep learning. Background technique [0002] In recent years, with the rapid development of society, the number of roads in our country has gradually increased, but there have also been some problems. Due to the large number of roads, it is difficult to find road surface diseases, which has buried safety hazards for driving safety accidents. Therefore, road surface diseases The detection technology is coming soon. In order to solve this problem, in the past, the road surface was detected by manual driving inspection. Passing it to the computer for analysis can not only realize automation, but also facilitate timely processing by relevant departments to ensure driving safety and minimize the loss of road surface diseases. At present, relevant computer image processing technology is mainly used to detect cr...

AI Technical Summary

Problems solved by technology

[0004] Although this patent also uses the method of deep learning to detect road surface diseases, this detection method is based on the information of edge detection for deep learning detection. At present, there is no good way to extract the edge of road surface detection. First, there may be branches, small Stones, water stains, shadow lighting, etc., if only edge detection is used, it is likely to be recognized as the edge of the road surface for identification, thereby making mistakes. In addition, the training data based on road surface edge detection will be unbalanced, because road surface diseases actually occur The situation is relatively low. For deep learning, the road data will not be able to guarantee the accuracy due to imbalance.

Images