Theta- disparity: An efficient representation of the 3D scene structure
2015 (English)In: 13th International Conference on Intelligent Autonomous Systems, IAS 2014, Springer, 2015, Vol. 302, 795-806 p.Conference paper (Refereed)Text
We propose a new representation of 3D scene structure, named thetadisparity. The proposed representation is a 2D angular depth histogram that is calculated using a disparity map. It models the structure of the prominent objects in the scene and reveals their radial distribution relative to a point of interest. The proposed representation is analyzed and used as a basic attention mechanism to autonomously resolve two different robotic scenarios. The method is efficient due to the low computational complexity. We show that the method can be successfully used for the planning of different tasks in the industrial and service robotics domains, e.g., object grasping, manipulation, plane extraction, path detection, and obstacle avoidance.
Place, publisher, year, edition, pages
Springer, 2015. Vol. 302, 795-806 p.
, Advances in Intelligent Systems and Computing, ISSN 2194-5357 ; 302
3D scene understanding, Autonomous robotics, Industrial and service robots, Object detection, Object recognition, Robotics, Three dimensional computer graphics, 3D scenes, Attention mechanisms, Low computational complexity, Point of interest, Prominent objects, Radial distributions, Service robots, Robot programming
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-181498DOI: 10.1007/978-3-319-08338-4_57ISI: 000377956900057ScopusID: 2-s2.0-84945932099ISBN: 978-331908337-7OAI: oai:DiVA.org:kth-181498DiVA: diva2:912385
13th International Conference on Intelligent Autonomous Systems, IAS 2014, Padova, Italy, 15 July 2014 through 18 July 2014
QC 201603162016-03-162016-02-022016-07-18Bibliographically approved