Extended Kalman Filter-Based Visual Odometry in Dynamic Environments Using Modified 1-Point RANSAC

TL;DR

This paper introduces a new visual odometry method that improves accuracy in dynamic environments by tracking both static and moving objects.

Contribution

A modified 1-point RANSAC framework is proposed to estimate ego-motion and object-motion simultaneously in dynamic scenes.

Findings

The modified 1-point RANSAC detects dynamic objects and uses them for pose estimation.

Combining static and dynamic landmarks improves robustness in complex environments.

The method is inspired by adaptive strategies in biological vision systems.

Abstract

Visual odometry in dynamic environments is particularly challenging, as moving objects often cause incorrect data associations and large pose estimation errors. Traditional EKF-based VO methods rely on 1-point RANSAC to reject outliers under the assumption of a static world, thereby discarding dynamic landmarks as noise. However, in practice, outliers may arise not only from measurement errors but also from the motion of objects. To address this issue, we propose a modified 1-point RANSAC framework that detects dynamic objects and leverages both static and dynamic landmarks for ego-motion estimation. Inspired by adaptive strategies observed in biological vision systems, our approach integrates EKF-based state estimation with dynamic object tracking to achieve simultaneous ego-motion and object-motion estimation, improving robustness in complex and dynamic scenes.

Figures