Deep learning concrete crack identification method combined with texture features
The structural cracks of concrete have a significant influence on the structural safety,so it is necessary to detect and monitor concrete crack.Aiming at masses of training samples are needed for deep learning methods,deep learning model also need large time to train model,a deep learning target detection framework combining texture features with concrete crack data is proposed.Texture features and pre-processed concrete data are merged to increase the number of feature channels in order to reduce the demand of training samples for the model and improve training speed.Concrete crack detection can be realized under the condition of limited number of samples.Through self-made steel fiber reinforced concrete crack data set to experiment and comparison.The experimental results show that the number of parameters that need to be fitted in the model training and training time can be correspondingly reduced and the detection accu-racy has also been improved.
万方数据
维普
