基于改进ORB特征提取匹配与关键帧选择的VSLAM

VSLAM Based on Improved ORB Feature Extraction Matching and Keyframe Selection

针对传统ORB算法提取的特征点和弱光条件下特征点匹配点对的数量较少的问题,提出了采用自适应阈值提取ORB特征点结合暗通道先验去雾算法的方法,特征点数量均值提升比为251.35%,匹配特征点对提升比约为191.67%。为解决视觉SLAM跟踪时经典关键帧选择策略信息利用率较低的问题,设计了一个基于滑动窗口关键帧选择的跟踪模块。后端模块采用局部BA优化加全局位姿图优化的方式,建图模块通过PCL库产生稠密点云地图以提供更为丰富的纹理信息。利用开源的TUM GRB-D数据集对算法进行测试评估,实验结果表明,该系统得到的位姿均方根误差为0.0098,有着较好的准确性和有效性。

Aiming at the problem that the number of feature points extracted by traditional ORB algorithm and matching point pairs under low light condition is small,this paper proposes a method of extracting ORB feature points by adaptive threshold combined with dark channel prior dehazing algorithm.The mean lifting ratio of the number of feature points is 251.35%,and the matching feature point pair lifting ratio is about 191.67%.In order to solve the problem of low information utilization of classical keyframe selection strategy in visual SLAM tracking,this paper designs a tracking module based on sliding window key frame selection.The back-end module of this paper adopts the method of local BA optimization and global pose map optimization,and the map construction module generates dense point cloud map through PCL library to provide richer texture information.The open source TUM GRB-D dataset is used to test and evaluate the algorithm.