Benchmarking Visual Feature Representations for LiDAR-Inertial-Visual Odometry Under Challenging Conditions
在恶劣条件下对激光雷达-惯性-视觉里程计的视觉特征表示进行基准测试
机构 * Department of Covergence IT Engineering, Pohang University of Science and Technology(POSTECH)(convergence IT工程系,POSTECH大学) ; School of Mechanical Engineering, Kunsan National University(机械工程学院,库山国立大学) ; Department of Artificial Intelligence and Robotics, Sejong University(人工智能与机器人系,世宗大学) ; Disaster Scientific Investigation Division Disaster Investigation Technology Team, National Disaster Management Research Institute, Ministry of the Interior and Safety(灾害科学调查 division 灾害调查技术团队,国家灾害管理研究所,内政与安全部) ; Department of Electrical Engineering, POSTECH(电气工程系,POSTECH大学)
专题命中 激光雷达 :LiDAR(title,abstract);autonomous driving(abstract);分类 cs.RO
AI总结 本文提出一种混合方法,结合直接光度法和基于描述符的特征匹配,提升在恶劣条件下的视觉里程计性能。
Comments 14 pages, Publised IEEE Access2026
Journal ref E. Choi et al., "Benchmarking Visual Feature Representations for LiDAR-Inertial-Visual Odometry Under Challenging Conditions," in IEEE Access, vol. 14, pp. 30186-30199, 2026