Fast Stereo Matching Algorithm Using Adaptive Window

Due to fixed window area-based stereo algorithms having given rise to relatively large matching errors around depth discontinuities, a adaptive window for stereo matching algorithm using integral image was proposed in this paper. A new similarity function and Four-direction line mask were employed in initial parallax gain aspect, not only to reduce noise effects but also to improve matching accuracy. Meanwhile, the window cost function that consists of average errors, variance of error and bias to larger windows was used to determine the size of matching and improve the matching accuracy. Simultaneously this algorithm using the integer image to enhance the efficiency conveniently, and the computation load having nothing to do without the window size, may reduce the timing operand is a constant. At last, the experiment result shows advantages of this algorithm, and it can be used in real-time system.