The depth information of two-dimensional (2D) images cannot be captured via monocular-vision measurement technology, consequently, the three-dimensional (3D) coordinates in the 2D image cannot be measured rapidly and directly. Hence, this paper proposes a 3D crack-change detection method based on monocular vision. Using an equivalent crack-change model, a special target was designed, feature points were used to solve the Epnp (efficient perspective-n-point), the relative pose of the camera during repeated photograph capturing was obtained, the depth information was restored using the least-squares method, and the actual 3D displacement change was obtained using the iterative closest point algorithm for coordinate-system conversion. The absolute-error accuracy was within 0.5 mm, which satisfies the requirements of cracks specified in engineering.