Multi-region Segmentation Pavement Crack Detection Method Based on Deep Learning

With the development of convolutional neural network and deep learning, pavement crack detection has also attracted some attention. The cracks on the pavement have the characteristics of different sizes and shapes. At present, there are still many problems in the practical application of the detection algorithm. On the one hand, many detection methods use quadrilateral contour frame as the detection frame, which is not very high for the cracks with narrow shape in the image. On the other hand, the detection frame obtained by some methods cannot accurately capture the uneven crack texture, resulting in false detection. To solve these two problems, a pavement crack detection method based on multi-region segmentation based on deep learning is proposed in this paper. In this method, the pavement crack instances in the image scene are mapped into the overall area, core area, and frame area space respectively to obtain the segmentation map of the pavement crack instances in the above three areas. Then the whole region segmentation map and border region segmentation map are used to guide the generation of core region segmentation map. To obtain more accurate detection results, the proposed method uses the detected crack frame region to supervise and learn the core region. Finally, the detection image of the core area is generated into crack lines with higher coincidence, and the detection results are obtained. The experimental results show that the accuracy of the proposed method on CrackForest data set can reach more than 83%. Compared with the existing detection algorithms, its F value is improved by more than 1%, and the algorithm has good detection results in different data sets.