DynPL-SVO: A Robust Stereo Visual Odometry for Dynamic Scenes

• Published in: IEEE transactions on instrumentation and measurement Vol. 73; p. 1
• Main Authors: Zhang, Baosheng, Ma, Xiaoguang, Ma, Hong-Jun, Luo, Chunbo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cameras; Cost function; dynamic scenes; Dynamics; Errors; Feature extraction; Heuristic algorithms; line features; Motion estimation; Motion simulation; Pedestrians; Robot dynamics; Robustness; Stereo visual odometry(SVO); Vehicle dynamics
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2023.3348882

Most feature-based stereo visual odometry (SVO) approaches estimate the motion of mobile robots by matching and tracking point features along a sequence of stereo images. However, in dynamic scenes mainly comprising moving pedestrians, vehicles, etc., there are insufficient robust static point features to enable accurate motion estimation, causing failures when reconstructing robotic motion. In this paper, we proposed DynPL-SVO, a complete dynamic SVO method that integrated united cost functions containing information between matched point features and re-projection errors perpendicular and parallel to the direction of the line features. Additionally, we introduced a dynamic grid algorithm to enhance its performance in dynamic scenes. The stereo camera motion was estimated through Levenberg-Marquard minimization of the re-projection errors of both point and line features. Comprehensive experimental results on KITTI and EuRoC MAV datasets showed that accuracy of the DynPL-SVO was improved by over 20% on average compared to other state-of-the-art SVO systems, especially in dynamic scenes.