Improveing depth estimation through fusion of stereo and TOF

In this paper, a novel method for depth estimation through fusion of stereo and TOF is proposed. Both the depth data and intensity gray images from TOF are taken into the calibration processing for getting the more accurate camera exterior parameters. Using the exterior parameters, the depth image captured by TOF is warped to the scope of the CCD camera pairs to form an initial depth image. Due to the problems of depth errors in the edges and the occlusion, the stereo rig is used to obtain the accurate depth of the edges of the objects, and eliminates the effect of occlusion simultaneously. Finally, by fusion method that takes advantage of the stereo vision, the depth data and the color image, the depth is optimized to obtain high resolution depth image. The experiment results show that higher spatial resolution and correct depth at edges´ position is obtained, compared with only using the TOF camera, and also the higher quality dense depth image.