Depth Value Pre-Processing for Accurate Transfer Learning Based RGB-D Object Recognition

Andreas Aakerberg, Kamal Nasrollahi, Christoffer Bøgelund Rasmussen, Thomas B. Moeslund

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

12 Citationer (Scopus)
948 Downloads (Pure)

Abstract

Object recognition is one of the important tasks in computer vision which has found enormous applications.Depth modality is proven to provide supplementary information to the common RGB modality for objectrecognition. In this paper, we propose methods to improve the recognition performance of an existing deeplearning based RGB-D object recognition model, namely the FusionNet proposed by Eitel et al. First, we showthat encoding the depth values as colorized surface normals is beneficial, when the model is initialized withweights learned from training on ImageNet data. Additionally, we show that the RGB stream of the FusionNetmodel can benefit from using deeper network architectures, namely the 16-layered VGGNet, in exchange forthe 8-layered CaffeNet. In combination, these changes improves the recognition performance with 2.2% incomparison to the original FusionNet, when evaluating on the Washington RGB-D Object Dataset.
OriginalsprogEngelsk
TitelInternational Joint Conference on Computational Intelligence
ForlagSCITEPRESS Digital Library
Publikationsdato2017
Sider121-128
ISBN (Trykt)978-989-758-274-5
DOI
StatusUdgivet - 2017
BegivenhedInternational Joint Conference on Computational Intelligence - Funchal, Portugal
Varighed: 1 nov. 20173 nov. 2017
Konferencens nummer: 9
http://www.ijcci.org/

Konference

KonferenceInternational Joint Conference on Computational Intelligence
Nummer9
Land/OmrådePortugal
ByFunchal
Periode01/11/201703/11/2017
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Depth Value Pre-Processing for Accurate Transfer Learning Based RGB-D Object Recognition'. Sammen danner de et unikt fingeraftryk.

Citationsformater