Based on the previously trained network model, a visual SLAM system is constructed. Tested on the KITTI dataset and compared with the latest ORB-SLAM3 system. The experimental results show that the methods in this paper are better than ORB-SLAM3 in sequences 00,03,04,06 and 10. Then the test is carried out in the real scene, and the results show that the drawing effect is better and the robustness is strong.
正在翻译中..