Building Robust Industrial Applicable Object Detection Models using Transfer Learning and Single Pass Deep Learning Architectures

Steven Puttemans, Timothy Callemein, Toon Goedemé

2018

Abstract

The uprising trend of deep learning in computer vision and artificial intelligence can simply not be ignored. On the most diverse tasks, from recognition and detection to segmentation, deep learning is able to obtain state-of-the-art results, reaching top notch performance. In this paper we explore how deep convolutional neural networks dedicated to the task of object detection can improve our industrial-oriented object detection pipelines, using state-of-the-art open source deep learning frameworks, like Darknet. By using a deep learning architecture that integrates region proposals, classification and probability estimation in a single run, we aim at obtaining real-time performance. We focus on reducing the needed amount of training data drastically by exploring transfer learning, while still maintaining a high average precision. Furthermore we apply these algorithms to two industrially relevant applications, one being the detection of promotion boards in eye tracking data and the other detecting and recognizing packages of warehouse products for augmented advertisements.

Paper Citation

in Harvard Style

Puttemans S., Callemein T. and Goedemé T. (2018). Building Robust Industrial Applicable Object Detection Models using Transfer Learning and Single Pass Deep Learning Architectures. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 209-217. DOI: 10.5220/0006562002090217

in Bibtex Style

@conference{visapp18,
author={Steven Puttemans and Timothy Callemein and Toon Goedemé},
title={Building Robust Industrial Applicable Object Detection Models using Transfer Learning and Single Pass Deep Learning Architectures},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={209-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006562002090217},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Building Robust Industrial Applicable Object Detection Models using Transfer Learning and Single Pass Deep Learning Architectures
SN - 978-989-758-290-5
AU - Puttemans S.
AU - Callemein T.
AU - Goedemé T.
PY - 2018
SP - 209
EP - 217
DO - 10.5220/0006562002090217
PB - SciTePress