Accurately locating the boundary points of complex-shaped tunnel contour changes and extracting the contours of each segment can provide strong support for tunnel deformation monitoring, point cloud orthophoto generation, and reconstruction of existing tunnel models. Based on high-precision tunnel point cloud data collected by mobile laser scanning, the original cross-section point cloud is first extracted and preprocessed, and then contour changes are identified by using the neighborhood density features of contour feature points. Finally, the mileage positioning method and boundary extraction algorithm are combined to complete the tunnel segmentation and contour extraction. Experiments using measured data from a subway tunnel and a highway tunnel verify the feasibility of this method. Compared with existing research, this method breaks away from the high dependence on the tunnel′s central axis, can independently and accurately identify contour changes, and effectively improves processing efficiency. It provides an efficient and innovative solution for engineering applications related to complex-shaped tunnel segmentation and contour extraction, and has a certain reference value for the application optimization of high-performance laser scanning technology.