DocumentCode :
2273426
Title :
Implementation of 3D object recognition and tracking
Author :
Bongale, Pankaj ; Ranjan, Anurag ; Anand, Sahil
Author_Institution :
India Innovation Labs., Bangalore, India
fYear :
2012
fDate :
25-27 April 2012
Firstpage :
77
Lastpage :
79
Abstract :
In this paper, we discuss an object recognition and tracking system that utilizes the depth information from a low-cost depth sensor. Conventional object recognition methods that utilize RGB cameras are unable to accurately identify objects in the real world since they do not take into consideration the shape and three-dimensional characteristics of the object. Another major factor determining the accuracy of recognition is the lighting conditions and object pose at the time of recognition. We discuss an approach making use of the depth information and 3d properties of objects inorder to accurately identify them independent of lighting conditions.
Keywords :
image sensors; lighting; object recognition; object tracking; pose estimation; 3D object recognition; 3D object tracking; depth information; lighting conditions; low-cost depth sensor; object pose; three-dimensional object characteristics; Cameras; Histograms; Lighting; Object recognition; Shape; Three dimensional displays; Training; 3D object recognition; flann; point cloud; viewpoint feature histogram;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Recent Advances in Computing and Software Systems (RACSS), 2012 International Conference on
Conference_Location :
Chennai
Print_ISBN :
978-1-4673-0252-4
Type :
conf
DOI :
10.1109/RACSS.2012.6212701
Filename :
6212701
Link To Document :
بازگشت