Parametric distortion-adaptive neighborhood for omnidirectional camera
Authors:
- 6 August 2015
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 54 (23) , 6969-6978
Abstract
Catadioptric omnidirectional images exhibit serious nonlinear distortion due to the involved quadratic mirror. Conventional pinhole model-based methods perform poorly when directly applied to the deformed omnidirectional images. This study constructs a catadioptric geometry system to analyze the variation of the neighborhood of an object in terms of the elevation and azimuth directions in a spherical coordinate system. To accurately represent the distorted visual information, a parametric neighborhood mapping model is proposed based on the catadioptric geometry. Unlike the conventional catadioptric models, the prior information of the system is effectively integrated into the neighborhood formulation framework. Then the distortion-adaptive neighborhood can be directly calculated based on its measurable image radial distance. This method can significantly improve the computational efficiency of algorithm since statistical neighborhood sampling is not used. On the basis of the proposed neighborhood model, a distortion-invariant Haar wavelet transform is presented to perform the robust human detection and tracking in catadioptric omnidirectional vision. The experimental results verify the effectiveness of the proposed neighborhood mapping model and prove that the distorted neighborhood in the omnidirectional image follows a nonlinear pattern.Keywords
Funding Information
- National Natural Science Foundation of China (NSFC) (61273286, 61233010)
- Research Grants Council, University Grants Committee, Hong Kong (RGC, UGC) (CityU 118613)
This publication has 20 references indexed in Scilit:
- Super-resolution fusion of complementary panoramic images based on cross-selection kernel regression interpolationApplied Optics, 2014
- Landmark-Based Particle Localization Algorithm for Mobile Robots With a Fish-Eye Vision SystemIEEE/ASME Transactions on Mechatronics, 2013
- Optimal Design and Placement of Omni-Cameras in Binocular Vision Systems for Accurate 3-D Data MeasurementIEEE Transactions on Circuits and Systems for Video Technology, 2013
- Intelligent Video Systems and Analytics: A SurveyIEEE Transactions on Industrial Informatics, 2013
- Contour coding based rotating adaptive model for human detection and tracking in thermal catadioptric omnidirectional visionApplied Optics, 2012
- Depth space partitioning for omni-stereo object trackingIET Computer Vision, 2012
- A Catadioptric and Pan-Tilt-Zoom Camera Pair Object Tracking System for UAVsJournal of Intelligent & Robotic Systems, 2010
- Appearance-Guided Monocular Omnidirectional Visual Odometry for Outdoor Ground VehiclesIEEE Transactions on Robotics, 2008
- Omni-directional visual surveillanceImage and Vision Computing, 2004
- A Theory of Single-Viewpoint Catadioptric Image FormationInternational Journal of Computer Vision, 1999