IRUS Total

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

File Description SizeFormat 
cvpr_2016_ed_johns.pdfAccepted version968.03 kBUnknownView/Open
Title: Pairwise Decomposition of Image Sequences for Active Multi-View Recognition
Authors: Johns, E
Leutenegger, S
Davison, AJ
Item Type: Conference Paper
Abstract: A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classi- fier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.
Issue Date: 12-Dec-2016
Date of Acceptance: 11-Apr-2016
URI: http://hdl.handle.net/10044/1/31448
DOI: https://dx.doi.org/10.1109/CVPR.2016.414
ISSN: 1063-6919
Publisher: Computer Vision Foundation (CVF)
Journal / Book Title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Dyson Technology Limited
Funder's Grant Number: PO 4500378543
Conference Name: Computer Vision and Pattern Recognition
Keywords: Science & Technology
Computer Science, Artificial Intelligence
Computer Science
Publication Status: Published
Start Date: 2016-06-26
Finish Date: 2016-07-01
Conference Place: Las Vegas, Nevada USA
Appears in Collections:Computing
Faculty of Engineering