R-FCN Object Detection Ensemble based on Object Resolution and Image Quality

Christoffer Bøgelund Rasmussen, Kamal Nasrollahi, Thomas B. Moeslund

Abstract

Object detection can be difficult due to challenges such as variations in objects both inter- and intra-class. Additionally, variations can also be present between images. Based on this, research was conducted into creating an ensemble of Region-based Fully Convolutional Networks (R-FCN) object detectors. Ensemble strategies explored were firstly data sampling and selection and secondly combination strategies. Data sampling and selection aimed to create different subsets of data with respect to object size and image quality such that expert R-FCN ensemble members could be trained. Two combination strategies were explored for combining the individual member detections into an ensemble result, namely average and a weighted average. R-FCNs were trained and tested on the PASCAL VOC benchmark object detection dataset. Results proved positive with an increase in Average Precision (AP), compared to state-of-the-art similar systems, when ensemble members were combined appropriately.

Download


Paper Citation


in Harvard Style

Rasmussen C., Nasrollahi K. and Moeslund T. (2017). R-FCN Object Detection Ensemble based on Object Resolution and Image Quality.In Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI, ISBN 978-989-758-274-5, pages 110-120. DOI: 10.5220/0006511301100120


in Bibtex Style

@conference{ijcci17,
author={Christoffer Bøgelund Rasmussen and Kamal Nasrollahi and Thomas B. Moeslund},
title={R-FCN Object Detection Ensemble based on Object Resolution and Image Quality},
booktitle={Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,},
year={2017},
pages={110-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006511301100120},
isbn={978-989-758-274-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,
TI - R-FCN Object Detection Ensemble based on Object Resolution and Image Quality
SN - 978-989-758-274-5
AU - Rasmussen C.
AU - Nasrollahi K.
AU - Moeslund T.
PY - 2017
SP - 110
EP - 120
DO - 10.5220/0006511301100120