With the continuous expansion of the power grid scale, the traditional overhead distribution line ledger management method has become difficult to meet the needs of modern power grid’s refined management. The introduction of unmanned aerial vehicle (UAV) technology has provided new opportunities for line inspection and ledger maintenance, but it also faces problems such as complex image naming, insufficient data association, and lagging information updates. This paper proposes a topological mapping technology for overhead distribution lines based on density clustering of UAV inspection images. By combining the GNSS positioning information and equipment recognition results in UAV images, the improved density clustering algorithm is used to achieve automatic classification of inspection images, construction of line topology, and topological correction. The technical route includes equipment and defect detection, image coordinate extraction, clustering analysis, equipment mapping, and topological correction modules. The YOLO algorithm is used for efficient recognition of key equipment and defects, and intelligent clustering and topological mapping of inspection data are achieved through matrix calculation and chain structure. Experiments show that this technology effectively improves the automation level and accuracy of ledger management, providing efficient and precise technical support for power grid operation and maintenance, while reducing the complexity of manual entry and maintenance.