loading
Documents

Research.Publish.Connect.

Paper

Authors: Sanjukta Ghosh 1 ; Peter Amon 2 ; Andreas Hutter 2 and André Kaup 3

Affiliations: 1 Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Siemens Corporate Technology, Germany ; 2 Siemens Corporate Technology, Germany ; 3 Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Germany

ISBN: 978-989-758-226-4

Keyword(s): Pedestrian Counting, Deep Learning, Convolutional Neural Networks, Synthetic Images, Transfer Learning, Cross Entropy Cost Function, Squared Error Cost Function.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Motion, Tracking and Stereo Vision ; Video Surveillance and Event Detection

Abstract: Counting pedestrians in surveillance applications is a common scenario. However, it is often challenging to obtain sufficient annotated training data, especially so for creating models using deep learning which require a large amount of training data. To address this problem, this paper explores the possibility of training a deep convolutional neural network (CNN) entirely from synthetically generated images for the purpose of counting pedestrians. Nuances of transfer learning are exploited to train models from a base model trained for image classification. A direct approach and a hierarchical approach are used during training to enhance the capability of the model for counting higher number of pedestrians. The trained models are then tested on natural images of completely different scenes captured by different acquisition systems not experienced by the model during training. Furthermore, the effectiveness of the cross entropy cost function and the squared error cost function are eval uated and analyzed for the scenario where a model is trained entirely using synthetic images. The performance of the trained model for the test images from the target site can be improved by fine-tuning using the image of the background of the target site. (More)

PDF ImageFull Text

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

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.146.98.143

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:
Ghosh, S.; Amon, P.; Hutter, A. and Kaup, A. (2017). Pedestrian Counting using Deep Models Trained on Synthetically Generated Images.In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 86-97. DOI: 10.5220/0006132600860097

@conference{visapp17,
author={Sanjukta Ghosh. and Peter Amon. and Andreas Hutter. and André Kaup.},
title={Pedestrian Counting using Deep Models Trained on Synthetically Generated Images},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={86-97},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006132600860097},
isbn={978-989-758-226-4},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Pedestrian Counting using Deep Models Trained on Synthetically Generated Images
SN - 978-989-758-226-4
AU - Ghosh, S.
AU - Amon, P.
AU - Hutter, A.
AU - Kaup, A.
PY - 2017
SP - 86
EP - 97
DO - 10.5220/0006132600860097

Login or register to post comments.

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