Cargando…

A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature

Aircraft detection in remote sensing images (RSIs) has drawn widespread attention in recent years, which has been widely used in the military and civilian fields. While the complex background, variations of aircraft pose and size bring great difficulties to the effective detection. In this paper, we...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Xin, Liu, Jinghong, Xu, Fang, Xie, Zhihua, Zuo, Yujia, Cao, Lihua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749598/
https://www.ncbi.nlm.nih.gov/pubmed/35009861
http://dx.doi.org/10.3390/s22010319
_version_ 1784631268528357376
author Chen, Xin
Liu, Jinghong
Xu, Fang
Xie, Zhihua
Zuo, Yujia
Cao, Lihua
author_facet Chen, Xin
Liu, Jinghong
Xu, Fang
Xie, Zhihua
Zuo, Yujia
Cao, Lihua
author_sort Chen, Xin
collection PubMed
description Aircraft detection in remote sensing images (RSIs) has drawn widespread attention in recent years, which has been widely used in the military and civilian fields. While the complex background, variations of aircraft pose and size bring great difficulties to the effective detection. In this paper, we propose a novel aircraft target detection scheme based on small training samples. The scheme is coarse-to-fine, which consists of two main stages: region proposal and target identification. First, in the region proposal stage, a circular intensity filter, which is designed based on the characteristics of the aircraft target, can quickly locate the centers of multi-scale suspicious aircraft targets in the RSIs pyramid. Then the target regions can be extracted by adding bounding boxes. This step can get high-quality but few candidate regions. Second, in the stage of target identification, we proposed a novel rotation-invariant feature, which combines rotation-invariant histogram of oriented gradient and vector of locally aggregated descriptors (VLAD). The feature can characterize the aircraft target well by avoiding the impact of its rotation and can be effectively used to remove false alarms. Experiments are conducted on Remote Sensing Object Detection (RSOD) dataset to compare the proposed method with other advanced methods. The results show that the proposed method can quickly and accurately detect aircraft targets in RSIs and achieve a better performance.
format Online
Article
Text
id pubmed-8749598
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87495982022-01-12 A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature Chen, Xin Liu, Jinghong Xu, Fang Xie, Zhihua Zuo, Yujia Cao, Lihua Sensors (Basel) Article Aircraft detection in remote sensing images (RSIs) has drawn widespread attention in recent years, which has been widely used in the military and civilian fields. While the complex background, variations of aircraft pose and size bring great difficulties to the effective detection. In this paper, we propose a novel aircraft target detection scheme based on small training samples. The scheme is coarse-to-fine, which consists of two main stages: region proposal and target identification. First, in the region proposal stage, a circular intensity filter, which is designed based on the characteristics of the aircraft target, can quickly locate the centers of multi-scale suspicious aircraft targets in the RSIs pyramid. Then the target regions can be extracted by adding bounding boxes. This step can get high-quality but few candidate regions. Second, in the stage of target identification, we proposed a novel rotation-invariant feature, which combines rotation-invariant histogram of oriented gradient and vector of locally aggregated descriptors (VLAD). The feature can characterize the aircraft target well by avoiding the impact of its rotation and can be effectively used to remove false alarms. Experiments are conducted on Remote Sensing Object Detection (RSOD) dataset to compare the proposed method with other advanced methods. The results show that the proposed method can quickly and accurately detect aircraft targets in RSIs and achieve a better performance. MDPI 2022-01-01 /pmc/articles/PMC8749598/ /pubmed/35009861 http://dx.doi.org/10.3390/s22010319 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Xin
Liu, Jinghong
Xu, Fang
Xie, Zhihua
Zuo, Yujia
Cao, Lihua
A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title_full A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title_fullStr A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title_full_unstemmed A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title_short A Novel Method of Aircraft Detection under Complex Background Based on Circular Intensity Filter and Rotation Invariant Feature
title_sort novel method of aircraft detection under complex background based on circular intensity filter and rotation invariant feature
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749598/
https://www.ncbi.nlm.nih.gov/pubmed/35009861
http://dx.doi.org/10.3390/s22010319
work_keys_str_mv AT chenxin anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT liujinghong anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT xufang anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT xiezhihua anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT zuoyujia anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT caolihua anovelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT chenxin novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT liujinghong novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT xufang novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT xiezhihua novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT zuoyujia novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature
AT caolihua novelmethodofaircraftdetectionundercomplexbackgroundbasedoncircularintensityfilterandrotationinvariantfeature