Abstract: The charging operation of roadway excavation by drilling and blasting is an important process link of tunnel excavation. The traditional charging process has a low degree of mechanization and relies on manual operation, which is time-consuming, labor-intensive and unsafe. In order to solve the problems of charging by drilling and blasting in tunnel excavation, an intelligent improvement scheme, intelligent blasthole detection and path planning system, is innovatively proposed based on deep learning and intelligent algorithm technology. The system can improve the charging accuracy and construction efficiency, and provide technical support for intelligent charging of drilling and blasting. The system architecture consists of data access layer, business logic layer and presentation layer, including modules such as image acquisition, data processing, blasthole detection, path planning and visualization interface. Firstly, the blasthole image data on the excavation working face is obtained by high-precision image sensors; secondly, the intelligent data processing and analysis of the blasthole intelligent detection model based on deep learning is adopted to realize accurate detection and identification of blasthole data; finally, the improved greedy algorithm is combined with the 2−opt local search algorithm to design a charging path planning algorithm, which realizes efficient planning and optimization of charging sequence. The system integrates visualization functions and provides intuitive blasthole data management, intelligent blasthole identification, blasthole data archiving, and charging path planning, which facilitates construction personnel to perform real-time monitoring and dynamic adjustment. The research results show that the accuracy of the system in blasthole detection can reach 96.24%, and the average calculation time of the path planning algorithm is about 100 milliseconds. The system can improve the efficiency, safety and intelligence level of charging during the drilling and blasting construction process, and serve the blasthole detection and path planning in the intelligent charging process of the drilling and blasting tunnel excavation.