A novel depth estimation method for uncalibrated stereo images

In this paper, a depth map estimation algorithm that performs stereo matching without explicit image rectification has been proposed. In the proposed method, the fundamental matrix is estimated by using Random Sample Consensus and the 8-point algorithm. Then, the epilolar line equation obtained by the projective mapping is derived and the search for point correspondence is performed along the epilolar line. Simulation results show that the proposed method produces accurate depth maps for uncalibrated stereo images with reduced computational complexity.