Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles

Abstract: 

Autonomous vehicle framework relies on localization algorithms to position itself and navigates to the destination. In this paper, we explore a light-weight visual localization method to realize the vehicle position and attitude estimation based on images rather than the dominant LIDAR data. We apply SLAM and an offline map correction method to generate a high precision map, which composes 3D points and feature descriptors. For each image, we extract the features and match against the map to explore correspondences. In the correspondences search process, we rely on the previous camera pose estimation result to determine the search scope, where significantly improves the localization accuracy. The searching process is embedded in the pose estimation stage, which we adjust the PnP procedure to better fit the autonomous driving task. Simply based on a single CPU thread support, experiments on the benchmark KITTI dataset demonstrate the superior results of our method.

up
0 users have voted:

Comments

Presentation slide for ICIP paper "From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles"

Paper Details

Authors:
Xue-Iuan Wong, James McBride
Submitted On:
22 September 2019 - 12:32am
Short Link:
Type:
Presentation Slides
Event:
Document Year:
2019
Cite

Document Files

icip3500.pdf

(19)

Subscribe

[1] Xue-Iuan Wong, James McBride, "From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4812. Accessed: Feb. 18, 2020.
@article{4812-19,
url = {http://sigport.org/4812},
author = {Xue-Iuan Wong; James McBride },
publisher = {IEEE SigPort},
title = {From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles},
year = {2019} }
TY - EJOUR
T1 - From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles
AU - Xue-Iuan Wong; James McBride
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4812
ER -
Xue-Iuan Wong, James McBride. (2019). From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles. IEEE SigPort. http://sigport.org/4812
Xue-Iuan Wong, James McBride, 2019. From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles. Available at: http://sigport.org/4812.
Xue-Iuan Wong, James McBride. (2019). "From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles." Web.
1. Xue-Iuan Wong, James McBride. From Mapping to Localization: A Complete Framework to Visually Estimate Position and Attitude for Autonomous Vehicles [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4812