DocumentCode :
155275
Title :
Place categorization through object classification
Author :
Charalampous, Konstantinos ; Kostavelis, Ioannis ; Chantzakou, Frantzeska-Eirini ; Volanis, Eleftherios-Stefanis ; Emmanouilidis, Christos ; Tsalides, Ph ; Gasteratos, A.
Author_Institution :
Dept. of Production & Manage. Eng., Democritus Univ. of Thrace, Xanthi, Greece
fYear :
2014
fDate :
14-17 Oct. 2014
Firstpage :
320
Lastpage :
324
Abstract :
This paper proposes a novel methodology for place categorization in mobile robots based on the presence of objects. In order to achieve such categorization, the robot is equipped with an RGB-D sensor. For a given time interval the sensor´s measurements are combined with robot´s localization data and reconstruct the 3D scene from the respective pointclouds. Afterwards, the method searches for dominant planes which are the most probable locations for finding objects. Given those planes, this work seeks and discriminates objects. The recognized objects, form a distribution which is given as input to a Naive Bayesian classifier in order to categorize the place.
Keywords :
image classification; image reconstruction; image sensors; mobile robots; object recognition; robot vision; 3D scene reconstruction; Naive Bayesian classifier; RGB-D sensor; mobile robots; object classification; object recognition; place categorization; pointclouds; robot localization data; Conferences; Mobile robots; Robot sensing systems; Support vector machines; Three-dimensional displays; Visualization; RGB-D data; object detection; object recognition; place categorization; robot navigation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Imaging Systems and Techniques (IST), 2014 IEEE International Conference on
Conference_Location :
Santorini
Type :
conf
DOI :
10.1109/IST.2014.6958497
Filename :
6958497
Link To Document :
بازگشت