Performance Improvement in Vslam Using Stabilized Feature Points

Mathematical and Computational Applications

Şahin, Caner¹ 

关键词: vSLAM;    Video stabilization;    Feature extraction;    Extended Kalman Filter;   

DOI  :  10.3390/mca18030361

学科分类：计算数学

来源: mdpi

【 摘 要 】

Simultaneous localization and mapping (SLAM) is the main prerequisite for the autonomy of a mobile robot. In this paper, we present a novel method that enhances the consistency of the map using stabilized corner features. The proposed method integrates template matching based video stabilization and Harris corner detector. Extracting Harris corner features from stabilized video consistently increases the accuracy of the localization. Data coming from a video camera and odometry are fused in an Extended Kalman Filter (EKF) to determine the pose of the robot and build the map of the environment. Simulation results validate the performance improvement obtained by the proposed technique.

【 授权许可】

CC BY