In order to achieve high-precision positioning of unmanned vehicles in low-light environments, based on the system framework of the VINS-Fusion algorithm, a fusion positioning algorithm LL- VI G for unmanned vehicles under low-light conditions is proposed. Aiming at the problems of low contrast, noise, and difficulty in feature extraction under low-light conditions, A multi-layer fusion image enhancement algorithm is proposed to improve the number of corner points extracted under low light conditions. For the problems of cumulative error in VI-SLAM and GNSS signals being easily interfered, a graph optimization method is used to integrate the GNSS global image. The fusion of positioning information and VI-SLAM positioning results reduces the cumulative error of VI-SLAM to a certain extent, and at the same time provides high-precision positioning in the absence of GNSS signals, improving the positioning accuracy and robustness of unmanned vehicles. The multi-layer fusion image enhancement algorithm proposed in this paper is experimentally verified based on the New Tsukuba Stereo dataset. The results show that the image enhanced by this algorithm can effectively increase the number of corner extractions. The LL-VIG algorithm proposed in this paper is experimentally verified based on the KITTI public data set and real vehicle scenarios. The results show that the positioning accuracy of LL- VI G is significantly higher than that of the comparison algorithm VINS-Fusion.