In large-scale and sparse scenes, such as farmland, orchards, mines, and substations, 3D simultaneous localization and mapping are challenging matters that need to address issues such as maintaining reliable data association for scarce environmental information and reducing the computational complexity of global optimization for large-scale scenes. To solve these problems, a real-time incremental simultaneous localization and mapping algorithm called MIM_SLAM is proposed in this paper. This algorithm is applied in mobile robots to build a map on a non-flat road with a 3D LiDAR sensor. MIM_SLAM's main contribution is that multi-level ICP (Iterative Closest Point) matching is used to solve the data association problem, a Fisher information matrix is used to describe the uncertainty of the estimated pose, and these poses are optimized by the incremental optimization method, which can greatly reduce the computational cost. Then, a map with a high consistency will be established. The proposed algorithm has been evaluated in the real indoor and outdoor scenes as well as two substations and benchmarking dataset from KITTI with the characteristics of sparse and large-scale. Results show that the proposed algorithm has a high mapping accuracy and meets the real-time requirements.