loading
Documents

Research.Publish.Connect.

Paper

Authors: M. H. Zwemer 1 ; R. G. J. Wijnhoven 2 and P. H. N. de With 3

Affiliations: 1 Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands, ViNotion B.V., Eindhoven, The Netherlands ; 2 ViNotion B.V., Eindhoven, The Netherlands ; 3 Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

ISBN: 978-989-758-402-2

ISSN: 2184-4321

Keyword(s): Surveillance Application, SSD Detector, Hierarchical Classification.

Abstract: We propose a novel CNN detection system with hierarchical classification for traffic object surveillance. The detector is based on the Single-Shot multibox Detector (SSD) and inspired by the hierarchical classification used in the YOLO9000 detector. We separate localization and classification during training, by introducing a novel loss term that handles hierarchical classification. This allows combining multiple datasets at different levels of detail with respect to the label definitions and improves localization performance with non-overlapping labels. We experiment with this novel traffic object detector and combine the public UADETRAC, MIO-TCD datasets and our newly introduced surveillance dataset with non-overlapping class definitions. The proposed SSD-ML detector obtains 96.4% mAP in localization performance, outperforming default SSD with 5.9%. For this improvement, we additionally introduce a specific hard-negative mining method. The effect of incrementally adding more dataset s reveals that the best performance is obtained when training with all datasets combined (we use a separate test set). By adding hierarchical classification, the average classification performance increases with 1.4% to 78.6% mAP. This positive result is based on combining all datasets, although label inconsistencies occur in the additional training data. In addition, the final system can recognize the novel ‘van’ class that is not present in the original training data. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

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 34.238.190.122

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:
Zwemer, M.; Wijnhoven, R. and de With, P. (2020). SSD-ML: Hierarchical Object Classification for Traffic Surveillance.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, ISSN 2184-4321, pages 250-259. DOI: 10.5220/0008902402500259

@conference{visapp20,
author={M. H. Zwemer. and R. G. J. Wijnhoven. and P. H. N. de With.},
title={SSD-ML: Hierarchical Object Classification for Traffic Surveillance},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={250-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008902402500259},
isbn={978-989-758-402-2},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - SSD-ML: Hierarchical Object Classification for Traffic Surveillance
SN - 978-989-758-402-2
AU - Zwemer, M.
AU - Wijnhoven, R.
AU - de With, P.
PY - 2020
SP - 250
EP - 259
DO - 10.5220/0008902402500259

Login or register to post comments.

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