Improved Person Detection on Omnidirectional Images with Non-maxima Supression

Roman Seidel, André Apitzsch, Gangolf Hirtz

2019

Abstract

We propose a person detector on omnidirectional images, an accurate method to generate minimal enclosing rectangles of persons. The basic idea is to adapt the qualitative detection performance of a convolutional neural network based method, namely YOLOv2 to fish-eye images. The design of our approach picks up the idea of a state-of-the-art object detector and highly overlapping areas of images with their regions of interests. This overlap reduces the number of false negatives. Based on the raw bounding boxes of the detector we fine-tuned overlapping bounding boxes by three approaches: the non-maximum suppression, the soft non-maximum suppression and the soft non-maximum suppression with Gaussian smoothing. The evaluation was done on the PIROPO database and an own annotated Flat dataset, supplemented with bounding boxes on omnidirectional images. We achieve an average precision of 64.4 % with YOLOv2 for the class person on PIROPO and 77.6 % on Flat. For this purpose we fine-tuned the soft non-maximum suppression with Gaussian smoothing.

Download


Paper Citation


in Harvard Style

Seidel R., Apitzsch A. and Hirtz G. (2019). Improved Person Detection on Omnidirectional Images with Non-maxima Supression. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 474-481. DOI: 10.5220/0007388404740481


in Bibtex Style

@conference{visapp19,
author={Roman Seidel and André Apitzsch and Gangolf Hirtz},
title={Improved Person Detection on Omnidirectional Images with Non-maxima Supression},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={474-481},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007388404740481},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Improved Person Detection on Omnidirectional Images with Non-maxima Supression
SN - 978-989-758-354-4
AU - Seidel R.
AU - Apitzsch A.
AU - Hirtz G.
PY - 2019
SP - 474
EP - 481
DO - 10.5220/0007388404740481
PB - SciTePress