학술논문

A Generic Method to Estimate Camera Extrinsic Parameters
Document Type
Conference
Source
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2022 - 2022 IEEE International Conference on. :1571-1575 May, 2022
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Computing and Processing
Signal Processing and Analysis
Closed-form solutions
Laser radar
Signal processing algorithms
Signal processing
Cameras
Particle measurements
Particle filters
Autonomous vehicles
Front-camera module
Multi-camera systems
Self-Calibration
Particle Filter
Language
ISSN
2379-190X
Abstract
In this paper, an approach to self-calibrate an outward-looking camera from camera images is presented. Ego lane boundaries are detected in the image frame. A straight line is fitted to each detected boundary. Vanishing point in image space is computed as the intersection of the fitted straight lines. A closed-form solution is obtained for camera pitch and yaw angles using vanishing points coordinates. A particle filter is initialized using pitch and yaw angles from closed-form solution and the rest of the camera extrinsic parameters (viz., roll, and translation parameters) obtained from approximate measurements.