Abstract: Aiming at the characteristics of long-distance tunnel, long maintenance intervals, limited repairing time and small changes in the deformation data, this paper presents a detection method of tunnel deformation based on active omni-directional vision tunnel section deformation. Firstly, the active panoramic vision sensor (ASODVS) is installed at the tunnel and detecting device scans the cross section of tunnel to acquire tunnel section panoramic images. Secondly, the sub-pixel center of the panoramic image is extracted by the improved Gauss curve fitting method, and the smooth processing is performed by using the Bezier curves. Thirdly, the system analyzes the geometry information of the tunnel cross-section of the inner wall through calibration results of omnidirectional vision sensor. The tunnel cross section 3D point cloud data are used for 3D reconstruction. Finally, the precision of the tunnel reconstruction model is analyzed. The experimental results show the method has the advantages of high speed acquisition, real-time, comprehensive data and good visualization. It can meet the needs of the rapid qualitative and quantitative analyses.