Stereo Matching Optimization with Multi-baseline Trinocular Camera Model
Jie Wang, Chenglei Peng, Ming Li, Xu‐Dong Chen, Sidan Du, Yang Li · 2020
In this paper, we focused on accelerating the stereo matching by using multi-baseline trinocular camera model. To optimize matching cost calculation and cost aggregation steps, we designed a special scheme called the trinocular dynamic disparity range (T-DDR) by narrowing disparity searching range. Based on that, we proposed the T-DDR-SGM for trinocular stereo matching. Evaluation results showed that T-DDR-SGM could significantly reduce the computational complexity with slightly improving the accuracy. We proved that the proposed optimization methods for the trinocular stereo matching are effective and the trinocular stereo matching is useful for reducing computational complexity.