华中科技大学学报（自然科学版）2024，Vol.52Issue(6)：156-163,8.DOI:10.13245/j.hust.240658
基于深度学习图像特征的动态环境视觉SLAM方法
Visual SLAM method for dynamic environment based on deep learning image features
摘要
Abstract
Aiming at the problem that traditional visual simultaneous localization and mapping(SLAM)algorithms rely on hand-crafted features,which are not stable enough for dynamic objects and change of illumination conditions and are prone to lose tracking,a stable and real-time method of image feature extraction and matching was presented based on deep learning.The neural network model with attention mechanism was trained through multi-task distillation training to realize feature extraction and matching for scenes with dramatic changes in illumination conditions.Based on the global and local features,a relocalization method based on hierarchical features was proposed to improve the overall accuracy and stability of the system,and it was real-time.Feature extraction and matching tests were performed on images with different illumination and angles in the same scene compared with Superpoint,and localization accuracy tests were performed on TUM datasets compared with ORB SLAM2 and GCN SLAM.Results show that the proposed method can extract sufficient stable features when illumination conditions change dramatically,and it performs better on fr3/sitting_static and fr3/walking_static than the other two methods.The root mean square error of tracks were 6.131 mm and 124.493 mm.Finally,sparse mapping was carried out in real indoor environments,and the effectiveness of the improved relocalization method was verified.关键词
视觉同时定位与地图构建(SLAM)/深度学习/注意力/多任务蒸馏/特征提取Key words
visual SLAM/deep learning/attention/multi-task distillation/feature extraction分类
信息技术与安全科学引用本文复制引用
刘冬,于涛,丛明,杜宇..基于深度学习图像特征的动态环境视觉SLAM方法[J].华中科技大学学报（自然科学版）,2024,52(6):156-163,8.基金项目
装备预研教育部联合基金资助项目(8091B022119) （8091B022119）
国家自然科学基金资助项目(62173064) （62173064）
中央高校基本科研业务费专项资金资助项目(DUT22JC13). （DUT22JC13）
