In underwater computer vision systems, the camera is usually housed in a watertight case with a glass interface between water and air, which causes the light rays to refract, affecting image formation geometrically. In this paper, we propose an approach to calibrate the housing parameters of a flat-port underwater camera for a reasonable underwater refractive camera model. Our approach is specifically designed to deal with the refraction effect caused by the light traveling in different mediums. In this camera model, the calibrated housing parameters include the distance between the camera and glass interface and the normal of the glass interface in the camera coordinate system. We employ an underwater binocular vision system to calibrate the housing parameters in two steps. First, the distance to the glass interface is estimated by capturing a checkerboard image and computing the distance from the camera center to a known flat plane. Then, the normal of the glass interface is calculated by a multiobjective optimization method using geometric constraints in the underwater binocular stereo system. Extensive experiments have been conducted on our underwater dataset and the results verify the effectiveness of the proposed scheme for underwater camera calibration and three-dimensional measurements.