Co-occurrence Background Model with Hypothesis on Degradation Modification for Robust Object Detection

Wenjun Zhou, Shun’ichi Kaneko, Manabu Hashimoto, Yutaka Satoh, Dong Liang

2018

Abstract

This paper presents a prospective background model for robust object detection in severe scenes. This background model using a novel algorithm, Co-occurrence Pixel-block Pairs (CPB), that extracts the spatiotemporal information of pixels from background and identifies the state of pixels at current frame. First, CPB realizes a robust background model for each pixel with spatiotemporal information based on a “pixel to block” structure. And then, CPB employs an efficient evaluation strategy to detect foreground sensitively, which is named as correlation dependent decision function. On the basis of this, a Hypothesis on Degradation Modification (HoD) for CPB is introduced to adapt dynamic changes in scenes and reinforce robustness of CPB to against “noise” in real conditions. This proposed model is robust to extract foreground against changes, such as illumination changes and background motion. Experimental results in different challenging datasets prove that our model has good effect for object detection.

Paper Citation

in Harvard Style

Zhou W., Kaneko S., Hashimoto M., Satoh Y. and Liang D. (2018). Co-occurrence Background Model with Hypothesis on Degradation Modification for Robust Object Detection. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 266-273. DOI: 10.5220/0006613202660273

in Bibtex Style

@conference{visapp18,
author={Wenjun Zhou and Shun’ichi Kaneko and Manabu Hashimoto and Yutaka Satoh and Dong Liang},
title={Co-occurrence Background Model with Hypothesis on Degradation Modification for Robust Object Detection},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={266-273},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006613202660273},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Co-occurrence Background Model with Hypothesis on Degradation Modification for Robust Object Detection
SN - 978-989-758-290-5
AU - Zhou W.
AU - Kaneko S.
AU - Hashimoto M.
AU - Satoh Y.
AU - Liang D.
PY - 2018
SP - 266
EP - 273
DO - 10.5220/0006613202660273
PB - SciTePress