Research on Target Recognition Method of Tunnel Lining Image Based on Deep Learning

Aiming at the complexity and diversity of ground-penetrating radar-based tunnel disease target imaging, as well as the relatively complex disease image identification process, low recognition rate, and the inability to achieve end-to-end identification, this paper proposes an improved Faster-R-CNN method for tunnel lining image target identification. The method can quickly and accurately determine the location of the disease images and classify them. The effectiveness of this method is verified by taking the common disease images such as steel arch and uncompactness in tunnel lining structure as the real measurement recognition objects, which provides a new method for automatic ground-penetrating radar image interpretation.