Simultaneous Object Segmentation and Recognition by Merging CNN Outputs from Uniformly Distributed Multiple Viewpoints

Yoshikatsu NAKAJIMA  Hideo SAITO  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.5   pp.1308-1316
Publication Date: 2018/05/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017MVP0024
Type of Manuscript: Special Section PAPER (Special Section on Machine Vision and its Applications)
Category: Machine Vision and its Applications
object recognition,  convolutional neural network,  SLAM,  segmentation,  

Full Text: PDF(7.3MB)
>>Buy this Article

We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.