Self-matching of stereoscopic images without camera calibration

To use an uncalibrated stereoscopic head in computer vision applications where the calibration object is not available and the taken images are noisy, we propose an algorithm for the self-matching of stereoscopic images of indoor scenes. We present also a theoretical adaptation to noisy data of the mathematical approach. The stereo matching algorithm has been tested on both synthetic and real images, and the number of lines matched demonstrates the robustness of the geometric method.