Show simple item record

dc.contributor.authorSmulders, Dehan
dc.contributor.authorUren, Kenneth
dc.contributor.authorVan Schoor, George
dc.contributor.authorVan Daalen, Corné
dc.contributor.authorEngelbrecht, Japie
dc.date.accessioned2019-06-07T07:11:22Z
dc.date.available2019-06-07T07:11:22Z
dc.date.issued2019
dc.identifier.citationSmulders, D. et al. 2019. CREAK descriptor evaluation for visual odometry. Proceedings, 2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA), Bloemfontein, South Africa, 28-30 Jan. Article no 8704807:188-193. [https://doi.org/10.1109/RoboMech.2019.8704807]en_US
dc.identifier.isbn978-1-7281-0369-3 (Online)
dc.identifier.urihttp://hdl.handle.net/10394/32604
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8704807
dc.identifier.urihttps://doi.org/10.1109/RoboMech.2019.8704807
dc.description.abstractEach year, latest state of the art technologies and algorithms arise that claim and prove to-shine their predecessors. One such algorithm is the Colour-based Retina Key-point (CREAK) descriptor, which is based on the FAST Retina Key-point (FREAK) descriptor with the included functionality of considering colour information in its Key-point description. This paper explores the implementation of CREAK in a “real-time” visual odometry application by means of a comparative study of the more well-known FREAK algorithm. Although FREAK achieved more accurate odometry when key-points were abundant, this proved to be too computationally expensive. CREAK on the other hand outperformed FREAK when key-points are scarce due to its lack of false-positive matchesen_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectFREAKen_US
dc.subjectCREAKen_US
dc.subjectVisual odometryen_US
dc.subjectFeature descriptoren_US
dc.subjectEvaluationen_US
dc.titleCREAK descriptor evaluation for visual odometryen_US
dc.typePresentationen_US
dc.contributor.researchID12064203 - Uren, Kenneth Richard
dc.contributor.researchID12134457 - Van Schoor, George
dc.contributor.researchID24058319 - Smulders, Dehan N.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record