loading
Papers
  • Login
  • Sign-Up

Research.Publish.Connect.

Paper

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

Topics: Applications: Image Processing and Artificial Vision, Pattern Recognition, Decision Making, Industrial and Real World applications, Financial Applications, Neural Prostheses and Medical Applications, Neural based Data Mining and Complex Information Processing, Neural Network Software and Applications, Applications of Deep Neural networks, Robotics and Control Applications; Deep Learning

Authors: Andreas Aakerberg ; Kamal Nasrollahi ; Christoffer B. Rasmussen and Thomas B. Moeslund

Affiliation: Aalborg University, Denmark

ISBN: 978-989-758-274-5

Keyword(s): Deep Learning, Computer Vision, Artificial Vision, RGB-D, Convolutional Neural Networks, Transfer Learning, Surface Normals.

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.

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user or Join INSTICC now for free.

Sign In SciTePress user: please login.

Sign In INSTICC Members: please login. If not a member yet, Join INSTICC now for free.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 23.20.245.192. INSTICC members have higher download limits (free membership now)

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Aakerberg A., Nasrollahi K., Rasmussen C. and Moeslund T. (2017). Depth Value Pre-Processing for Accurate Transfer Learning based RGB-D Object Recognition.In Proceedings of the 9th International Joint Conference on Computational IntelligenceISBN 978-989-758-274-5, pages 121-128. DOI: 10.5220/0006511501210128

@conference{ijcci17,
author={Andreas Aakerberg and Kamal Nasrollahi and Christoffer B. Rasmussen and Thomas B. Moeslund},
title={Depth Value Pre-Processing for Accurate Transfer Learning based RGB-D Object Recognition},
booktitle={Proceedings of the 9th International Joint Conference on Computational Intelligence},
year={2017},
pages={121-128},
doi={10.5220/0006511501210128},
isbn={978-989-758-274-5},
}

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence
TI - Depth Value Pre-Processing for Accurate Transfer Learning based RGB-D Object Recognition
SN - 978-989-758-274-5
AU - Aakerberg A.
AU - Nasrollahi K.
AU - Rasmussen C.
AU - Moeslund T.
PY - 2017
SP - 121
EP - 128
DO - 10.5220/0006511501210128

Sorted by: Show papers

Note: The preferred Subjects/Areas/Topics, listed below for each paper, are those that match the selected paper topics and their ontology superclasses.
More...

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.

Show authors

Note: The preferred Subjects/Areas/Topics, listed below for each author, are those that more frequently used in the author's papers.
More...