Abstract
This paper presents a monocular visual odometry algorithm that incorporates a wheeled vehicle model for ground vehicles. The main innovation of this algorithm is to use the single-track bicycle model to interpret the relationship between the yaw rate and side slip angle, which are the two most important parameters that describe the motion of a wheeled vehicle. Additionally, the pitch angle is also considered since the planar-motion hypothesis often fails due to the dynamic characteristics of wheel suspensions and tires in real-world environments. Linearization is used to calculate a closed-form solution of the motion parameters that works as a hypothesis generator in a RAndom SAmple Consensus (RANSAC) scheme to reduce the complexity in solving equations involving trigonometric. All inliers found are used to refine the winner solution through minimizing the reprojection error. Finally, the algorithm is applied to real-time on-board visual localization applications. Its performance is evaluated by comparing against the state-of-the-art monocular visual odometry methods using both synthetic data and publicly available datasets over several kilometers in dynamic outdoor environments.
Highlights
Self-localization is arguably one of the most challenging problems in intelligent vehicle research.Traditionally, wheel speed encoder is used for auto-localization of wheeled autonomous vehicles.the accuracy of localization using photoelectric encoder is oblivious to external environment due to its dependency on proprioceptive sensors
In order to reduce the degree of freedom in vision based motion estimation problem, a few researchers have introduced motion models of wheeled vehicle into the pose estimation process
As a hypothesis generator in relative pose estimation based on hypothesis-test-validation framework, minimal set solving algorithms are not able to provide accurate solution because error exists in the coordinates of point correspondences
Summary
Self-localization is arguably one of the most challenging problems in intelligent vehicle research. Scaramuzza et al [12,13] showed that, due to the existence of the Instantaneous Center of Rotation, motion can be locally described as planar and circular, and the motion model can be simplified to 1 DoF (Degree of Freedom) This simplification leads to a 1-point minimal solver. If we treat the camera and the vehicle as a spring-mass system, when acceleration, deceleration, or sharp turns occurs, the planar-motion hypothesis will fail due to the dynamic characteristics of wheel suspensions and tires. For these reasons, in their latest work [15], the authors relaxed the locally.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
