Semi-automatic Learning Framework Combining Object Detection and Background Subtraction

Sugino Nicolas Alejandro, Tsubasa Minematsu, Atsushi Shimada, Takashi Shibata, Rin-ichiro Taniguchi, Eiji Kaneko, Hiroyoshi Miyano

2020

Abstract

Public datasets used to train modern object detection models do not contain all the object classes appearing in real-world surveillance scenes. Even if they appear, they might be vastly different. Therefore, object detectors implemented in the real world must accommodate unknown objects and adapt to the scene. We implemented a framework that combines background subtraction and unknown object detection to improve the pretrained detector’s performance and apply human intervention to review the detected objects to minimize the latent risk of introducing wrongly labeled samples to the training. The proposed system enhanced the original YOLOv3 object detector performance in almost all the metrics analyzed, and managed to incorporate new classes without losing previous training information

Paper Citation

in Harvard Style

Alejandro S., Minematsu T., Shimada A., Shibata T., Taniguchi R., Kaneko E. and Miyano H. (2020). Semi-automatic Learning Framework Combining Object Detection and Background Subtraction. 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, SciTePress, pages 96-106. DOI: 10.5220/0008941200960106

in Bibtex Style

@conference{visapp20,
author={Sugino Nicolas Alejandro and Tsubasa Minematsu and Atsushi Shimada and Takashi Shibata and Rin-ichiro Taniguchi and Eiji Kaneko and Hiroyoshi Miyano},
title={Semi-automatic Learning Framework Combining Object Detection and Background Subtraction},
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={96-106},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008941200960106},
isbn={978-989-758-402-2},
}

in EndNote Style

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 - Semi-automatic Learning Framework Combining Object Detection and Background Subtraction
SN - 978-989-758-402-2
AU - Alejandro S.
AU - Minematsu T.
AU - Shimada A.
AU - Shibata T.
AU - Taniguchi R.
AU - Kaneko E.
AU - Miyano H.
PY - 2020
SP - 96
EP - 106
DO - 10.5220/0008941200960106
PB - SciTePress