The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS
Transactions ID Number: 29-788
Full Name: Aldo Cumani
Position: Research Director
Age: ON
Sex: Male
Address: str. delle Cacce, 91
Country: ITALY
Tel:
Tel prefix:
Fax:
E-mail address: a.cumani@inrim.it
Other E-mails: aldocumani@alumni.com
Title of the Paper: Selecting Feature Detectors for Accurate Visual Odometry
Authors as they appear in the Paper: Aldo Cumani Antonio Guiducci
Email addresses of all the authors: a.cumani@inrim.it,a.guiducci@inrim.it
Number of paper pages: 10
Abstract: This work analyzes the performances of different feature detectors/descriptors in the context of incremental path estimation from passive stereo vision (Visual Odometry). Several state-of-the-art approaches have been tested, including a fast Hessian-based feature detector/descriptor developed at INRIM. Tests on both synthetic image sequences and real data show that in this particular application our approach yields results of accuracy comparable to the others, while being substantially faster and much more reliable.
Keywords: Robot localisation, Stereo vision, Visual odometry, Feature descriptors, Feature detectors
EXTENSION of the file: .pdf
Special (Invited) Session: Comparison of Feature Detectors for Rover Navigation
Organizer of the Session: 619-149
How Did you learn about congress:
IP ADDRESS: 193.204.114.65
