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

TL;DR

DynPL-SVO is a novel stereo visual odometry method designed for dynamic scenes, integrating point and line feature information and a dynamic grid algorithm to improve motion estimation accuracy in environments with moving objects.

Contribution

The paper introduces DynPL-SVO, a robust dynamic stereo visual odometry approach that combines unified cost functions and a dynamic grid algorithm for better performance in dynamic scenes.

Findings

Achieved over 20% accuracy improvement on KITTI and EuRoC datasets.

Enhanced robustness in scenes with moving pedestrians and vehicles.

Outperformed existing state-of-the-art SVO systems in dynamic environments.

Abstract

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 \textit{dynamic} \textit{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.