Camera pose estimation using particle filters

In this paper we propose a pose estimation algorithm based on Particle filtering which uses LED sightings gathered from wireless sensor nodes (WSN) to estimate the pose of the camera. The LEDs act as (visual) markers for our pose estimation algorithm. We also compare the performance of our pose esti...

Full description

Saved in:
Bibliographic Details
Main Authors: Herranz, F., Muthukrishnan, K., Langendoen, K.
Format: Conference Proceeding
Language:English
Subjects:
Atmospheric measurements
Cameras
Estimation
Light emitting diodes
Particle measurements
Vectors
Wireless sensor networks
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we propose a pose estimation algorithm based on Particle filtering which uses LED sightings gathered from wireless sensor nodes (WSN) to estimate the pose of the camera. The LEDs act as (visual) markers for our pose estimation algorithm. We also compare the performance of our pose estimation algorithm against two reference algorithms - (i) Extended Kalman filtering (EKF) and (ii) Discrete Linear Transform (DLT) based approaches. The performance of all the three algorithms are evaluated for different camera frame rates, varying level of measurement noise and for different marker distribution. Our results (small-scale experimental and room-level simulation studies) show that the particle filtering algorithm gives an accuracy of a few millimetres in position and a few degrees in orientation.
DOI:10.1109/IPIN.2011.6071919