This study proposes a creative method of semantic graph matching and semantic scan context descriptors of candidate frames to address the long-term localization issues in unmanned vehicle based on simultaneous localization and mapping maps. The relocalization of point cloud scenes is achieved through a two-step process, involving coarse and fine localization. First, semantic and geometric features are extracted from the point cloud, eliminating mobile and movable objects. Thus, a semantic graph is constructed by fusing semantic information and topological relationships, and rapid relocalization coarse matching is realized through graph similarity calculation. Then, the relative yaw and horizontal movement between point clouds are computed through global semantic iterative closest point, providing a well-initialized alignment. Finally, the global semantic descriptor is generated through semantic scan context, and accurate relocalization is obtained by comparing descriptors to distinguish point cloud similarity. Experimental results demonstrate that the proposed method achieves a 20.10%, 20.90%, and 20.47% improvement in accuracy in place recognition, occluded scenes, and perspective change scenes, respectively, compared to the semantic graph-based place recognition method.