{"title":"Lightweight omnidirectional visual-inertial odometry for MAVs based on improved keyframe tracking and marginalization","authors":"Bo Gao, Baowang Lian, Chengkai Tang","doi":"10.1007/s11235-024-01208-4","DOIUrl":null,"url":null,"abstract":"<p>Due to the limited onboard resources on Micro Aerial Vehicles (MAVs), the poor real-time performance has always been an urgent problem to be solved in the practical applications of visual inertial odometry (VIO). Therefore, a lightweight omnidirectional visual-inertial odometry (LOVIO) for MAVs based on improved keyframe tracking and marginalization was proposed. In the front-end processing of LOVIO, wide field-of-view (FOV) images are captured by an omnidirectional camera, frames are tracked by semi-direct method combining of direct method with rapidity and feature-based method with accuracy. In the back-end optimization, the Hessian matrix corresponding to the error optimization equation is stepwise marginalized, so the high-dimensional matrix is decomposed and the operating efficiency is improved. Experimental results on the dataset TUM-VI show that LOVIO can significantly reduce running time consumption without loss of precision and robustness, that means LOVIO has better real-time and practicability for MAVs.</p>","PeriodicalId":51194,"journal":{"name":"Telecommunication Systems","volume":"7 1","pages":""},"PeriodicalIF":1.7000,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Telecommunication Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11235-024-01208-4","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Due to the limited onboard resources on Micro Aerial Vehicles (MAVs), the poor real-time performance has always been an urgent problem to be solved in the practical applications of visual inertial odometry (VIO). Therefore, a lightweight omnidirectional visual-inertial odometry (LOVIO) for MAVs based on improved keyframe tracking and marginalization was proposed. In the front-end processing of LOVIO, wide field-of-view (FOV) images are captured by an omnidirectional camera, frames are tracked by semi-direct method combining of direct method with rapidity and feature-based method with accuracy. In the back-end optimization, the Hessian matrix corresponding to the error optimization equation is stepwise marginalized, so the high-dimensional matrix is decomposed and the operating efficiency is improved. Experimental results on the dataset TUM-VI show that LOVIO can significantly reduce running time consumption without loss of precision and robustness, that means LOVIO has better real-time and practicability for MAVs.
期刊介绍:
Telecommunication Systems is a journal covering all aspects of modeling, analysis, design and management of telecommunication systems. The journal publishes high quality articles dealing with the use of analytic and quantitative tools for the modeling, analysis, design and management of telecommunication systems covering:
Performance Evaluation of Wide Area and Local Networks;
Network Interconnection;
Wire, wireless, Adhoc, mobile networks;
Impact of New Services (economic and organizational impact);
Fiberoptics and photonic switching;
DSL, ADSL, cable TV and their impact;
Design and Analysis Issues in Metropolitan Area Networks;
Networking Protocols;
Dynamics and Capacity Expansion of Telecommunication Systems;
Multimedia Based Systems, Their Design Configuration and Impact;
Configuration of Distributed Systems;
Pricing for Networking and Telecommunication Services;
Performance Analysis of Local Area Networks;
Distributed Group Decision Support Systems;
Configuring Telecommunication Systems with Reliability and Availability;
Cost Benefit Analysis and Economic Impact of Telecommunication Systems;
Standardization and Regulatory Issues;
Security, Privacy and Encryption in Telecommunication Systems;
Cellular, Mobile and Satellite Based Systems.