Active Stereo Vision for 3D Profile Measurement

Abstract

Over the past decade, vision-based 3D sensing technology has been increasingly applied in manufacturing industries. The 3D shape of a part, which can be represented by using a point cloud, is usually required for two main purposes: reverse engineering or dimensional inspection. On the other hand, vision-based 3D sensing techniques can be divided into categories: passive stereo vision and active stereo vision. Stereo vision based on no additional devices besides the cameras is known as passive stereo vision, which works in a similar way as the human eyes. In this case, the passive stereo vision can be very compact and low-cost without any extra components. The extensive application of the passive vision benefits from the epipolar geometry, first introduced in (Longuet, 1981). Epipolar geometry, which provides the geometric constraints between 2D image points in the two cameras relative to the same 3D points with the assumption that the cameras can be presented by using the pinhole model, has been utilized in camera calibration. However, it still has some drawbacks for industrial inspection. The first difficulty is the correspondence problem. In other words, determining the pixels of different views in terms of the same physic point of the inspected part is not a trivial step, especially for a texture-less object, such as a piece of white paper. Another problem is the sparse resolution of the reconstruction, usually with a small number of points. Furthermore, the inappropriate ambient light condition would also lead to the failure of the passive stereo vision. In order to overcome the above drawbacks, active stereo vision, removing the ambiguity of the texture-less part with a special projection device, is commonly used when dense reconstructions are needed. For this technique, a special device (e.g. projector) is employed to emit special patterns onto the identified object, which will be detected by the camera. In a word, compared with the passive strategy, the active one is advantageous for robust and accurate 3D scene reconstruction. This chapter summarizes the coding strategy, 3D reconstruction, and sensor calibration for active stereo vision, as well as the specific application in manufacturing industry. Our contribution is to propose two pattern coding strategies and pixel-to-pixel calibration for accurate 3D reconstruction in industrial inspection. Active Stereo Vision for 3D Profile Measurement