Application of Dynamic Distributional Clauses for Multi-hypothesis Initialization in Model-based Object TrackingShow others and affiliations
2014 (English)In: Proceedings of the 9th International Conference on Computer Vision Theory and Applications - (Volume 1) / [ed] Sebastiano Battiato, SciTePress , 2014, Vol. 1, p. 256-261Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]
In this position paper we propose the use of the Distributional Clauses Particle Filter in conjunction with amodel-based 3D object tracking method in monocular camera sequences. We describe the model based objecttracking method that is based on contour and edge features for 3D pose relative estimation. We also describethe application of the Distributional Clauses Particle Filter that takes into account inputs from object tracking.We argue that objects’ dynamics can be modeled via probabilistic rules, which makes possible to predict andutilise a pose hypothesis space for fully occluded or ‘invisible’ (hidden-away) objects that may re-appear inthe camera field of view. Important issues, such as losing track of the object in a ‘total occlusion’ scenario, arediscussed.
Place, publisher, year, edition, pages
SciTePress , 2014. Vol. 1, p. 256-261
Series
VISIGRAPP, ISSN 2184-5921, E-ISSN 2184-4321
Keywords [en]
Object Tracking, Robot Vision, Particle Filters, Distributional Clauses
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:oru:diva-92171DOI: 10.5220/0004654002560261ISI: 000412737200029Scopus ID: 2-s2.0-84906906057ISBN: 9789897580048 (print)OAI: oai:DiVA.org:oru-92171DiVA, id: diva2:1561447
Conference
9th International Conference on Computer Vision Theory and Applications, (VISAPP 2014), Lisbon, Portugal, January 5-8, 2014
2021-06-072021-06-072021-06-07Bibliographically approved