Nothing Special   »   [go: up one dir, main page]

loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

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

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

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 datase ts 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)

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 65.254.225.175

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 (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2; ISSN 2184-4321, SciTePress, 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 (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={250-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008902402500259},
isbn={978-989-758-402-2},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - SSD-ML: Hierarchical Object Classification for Traffic Surveillance
SN - 978-989-758-402-2
IS - 2184-4321
AU - Zwemer, M.
AU - Wijnhoven, R.
AU - de With, P.
PY - 2020
SP - 250
EP - 259
DO - 10.5220/0008902402500259
PB - SciTePress

<style> #socialicons>a span { top: 0px; left: -100%; -webkit-transition: all 0.3s ease; -moz-transition: all 0.3s ease-in-out; -o-transition: all 0.3s ease-in-out; -ms-transition: all 0.3s ease-in-out; transition: all 0.3s ease-in-out;} #socialicons>ahover div{left: 0px;} </style>