Image-Based Floor Segmentation in Visual Inertial Navigation
2013 (English)In: 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), New York: IEEE , 2013, , 6 p.1402-1407 p.Conference paper (Refereed)
This paper presents a floor segmentation algorithmfor indoor sequences that works with single grey-scale images.The portion of the floor closest to the camera is segmentedby judiciously joining a set of horizontal and vertical lines,previously detected. Since the proposed method is not based oncomputing the vanishing point, the system can deal with anykind of indoor scenes and adapts quickly to camera movements.A second contribution is the detection of moving features forpoints within the segmented floor area. Based on the estimatedcamera ego-motion, the ground plane homography is derived.Then, the expected optical flow for the ground points is calculatedand used for rejecting features that belong to moving obstacles.A key point of the designed method is that no restrictions on thecamera motion are imposed for the homography derivation.
Place, publisher, year, edition, pages
New York: IEEE , 2013. , 6 p.1402-1407 p.
, IEEE Instrumentation and Measurement Technology Conference. Proceedings, ISSN 1091-5281
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-122238DOI: 10.1109/I2MTC.2013.6555644ISI: 000326900400255ScopusID: 2-s2.0-84882251471ISBN: 978-1-4673-4621-4OAI: oai:DiVA.org:kth-122238DiVA: diva2:621452
2013 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Life, I2MTC 2013; Minneapolis, MN; United States; 6 May 2013 through 9 May 2013
QC 201306102013-05-142013-05-142014-01-07Bibliographically approved