Research on Borehole Identification Under Tunnel Blasting Based on YOLOv5

In the context of tunnel blasting, a significant amount of manual labor is required for borehole explosive filling. Given the challenges posed by harsh blasting conditions, the high precision required for filling operations, and the vast number of fillings, a specialized explosive-filling robot has been designed. Utilizing the YOLOv5 object detection framework and integrating machine vision technology, an automated tunnel borehole identification method rooted in YOLOv5 has been proposed, aiming to enhance the efficiency and safety of tunnel blasting procedures. Through the collection and annotation of a vast number of tunnel blasting project images, a borehole dataset was established. With the deployment of the YOLOv5 deep learning object detection framework for training, coupled with machine vision and deep learning techniques, this methodology can autonomously identify and locate boreholes in intricate subterranean settings. Experimental findings indicate that this approach exhibits stellar performance even in complex tunnel situations, boasting an accuracy rate exceeding 80% in borehole detection. The system displays exceptional real-time performance, making it viable for practical applications in tunnel blasting operations, thus elevating the efficiency and safety of engineering tasks.