Multi-level Feature Selection for Oriented Object Detection

Chen Jiang, Yefan Jiang, Zhangxing Bian, Fan Yang, Siyu Xia

Abstract

Horizontal object detection has made significant progress, but the representation of horizontal bounding box still has application limitations for oriented objects. In this paper, we propose an end-to-end rotation detector to localize and classify oriented targets precisely. Firstly, we introduce the path aggregation module, to shorten the path of feature propagation. To distribute region proposals to the most suitable feature map, we propose the feature selection module instead of using selection mechanism based on the size of region proposals. What’s more, for rotation detection, we adopt eight-parameter representation method to parametrize the oriented bounding box and we add a novel loss to handle the boundary problems resulting from the representation way. Our experiments are evaluated on DOTA and HRSC2016 datasets.

Download


Paper Citation


in Harvard Style

Jiang C., Jiang Y., Bian Z., Yang F. and Xia S. (2021). Multi-level Feature Selection for Oriented Object Detection.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 36-43. DOI: 10.5220/0010213000360043


in Bibtex Style

@conference{icpram21,
author={Chen Jiang and Yefan Jiang and Zhangxing Bian and Fan Yang and Siyu Xia},
title={Multi-level Feature Selection for Oriented Object Detection},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={36-43},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010213000360043},
isbn={978-989-758-486-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Multi-level Feature Selection for Oriented Object Detection
SN - 978-989-758-486-2
AU - Jiang C.
AU - Jiang Y.
AU - Bian Z.
AU - Yang F.
AU - Xia S.
PY - 2021
SP - 36
EP - 43
DO - 10.5220/0010213000360043