An aircraft detection method based on improved mask R-CNN in remotely sensed imagery

Pengfei Zhao; Huayu Gao; Yun Zhang; Hongbo Li; Rui Yang

doi:10.1109/IGARSS.2019.8900528

An aircraft detection method based on improved mask R-CNN in remotely sensed imagery

Pengfei Zhao
, Huayu Gao
, Yun Zhang^*
, Hongbo Li
, Rui Yang

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology
Beijing Institute of Aerospace Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

Aircraft detection has become a research hotspot due to its important military and traffic status. It is very challenging since noisy background is easy to mix with the target, meanwhile, there are small and dense distributed targets in some images. This paper presents an end to end aircraft detection framework based on Mask R-CNN. First, a self-attention feature pyramid network (SA-FPN) is proposed to suppress the noise and highlight foreground. Then, in order to reduce the false alarm and increase the detection performance, we redesign the aspect ratios of the anchors. The experimental result shows that our detection method has a competitive performance.

Original language	English
Title of host publication	2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1370-1373
Number of pages	4
ISBN (Electronic)	9781538671504
DOIs	https://doi.org/10.1109/IGARSS.2019.8900528
State	Published - 2019
Externally published	Yes
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

Aircraft detection
Mask R-CNN
Remotely sensed imagery

Access to Document

10.1109/IGARSS.2019.8900528

Cite this

Zhao, P., Gao, H., Zhang, Y., Li, H., & Yang, R. (2019). An aircraft detection method based on improved mask R-CNN in remotely sensed imagery. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings (pp. 1370-1373). (International Geoscience and Remote Sensing Symposium (IGARSS) ). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2019.8900528

Zhao, Pengfei ; Gao, Huayu ; Zhang, Yun et al. / An aircraft detection method based on improved mask R-CNN in remotely sensed imagery. 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1370-1373 (International Geoscience and Remote Sensing Symposium (IGARSS) ).

@inproceedings{d631667c569c4c5cb55e457c24967302,

title = "An aircraft detection method based on improved mask R-CNN in remotely sensed imagery",

abstract = "Aircraft detection has become a research hotspot due to its important military and traffic status. It is very challenging since noisy background is easy to mix with the target, meanwhile, there are small and dense distributed targets in some images. This paper presents an end to end aircraft detection framework based on Mask R-CNN. First, a self-attention feature pyramid network (SA-FPN) is proposed to suppress the noise and highlight foreground. Then, in order to reduce the false alarm and increase the detection performance, we redesign the aspect ratios of the anchors. The experimental result shows that our detection method has a competitive performance.",

keywords = "Aircraft detection, Mask R-CNN, Remotely sensed imagery",

author = "Pengfei Zhao and Huayu Gao and Yun Zhang and Hongbo Li and Rui Yang",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

doi = "10.1109/IGARSS.2019.8900528",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS) ",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1370--1373",

booktitle = "2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings",

address = "美国",

}

Zhao, P, Gao, H, Zhang, Y , Li, H & Yang, R 2019, An aircraft detection method based on improved mask R-CNN in remotely sensed imagery. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS) , Institute of Electrical and Electronics Engineers Inc., pp. 1370-1373, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8900528

An aircraft detection method based on improved mask R-CNN in remotely sensed imagery. / Zhao, Pengfei; Gao, Huayu; Zhang, Yun et al.
2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1370-1373 (International Geoscience and Remote Sensing Symposium (IGARSS) ).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An aircraft detection method based on improved mask R-CNN in remotely sensed imagery

AU - Zhao, Pengfei

AU - Gao, Huayu

AU - Zhang, Yun

AU - Li, Hongbo

AU - Yang, Rui

PY - 2019

Y1 - 2019

N2 - Aircraft detection has become a research hotspot due to its important military and traffic status. It is very challenging since noisy background is easy to mix with the target, meanwhile, there are small and dense distributed targets in some images. This paper presents an end to end aircraft detection framework based on Mask R-CNN. First, a self-attention feature pyramid network (SA-FPN) is proposed to suppress the noise and highlight foreground. Then, in order to reduce the false alarm and increase the detection performance, we redesign the aspect ratios of the anchors. The experimental result shows that our detection method has a competitive performance.

AB - Aircraft detection has become a research hotspot due to its important military and traffic status. It is very challenging since noisy background is easy to mix with the target, meanwhile, there are small and dense distributed targets in some images. This paper presents an end to end aircraft detection framework based on Mask R-CNN. First, a self-attention feature pyramid network (SA-FPN) is proposed to suppress the noise and highlight foreground. Then, in order to reduce the false alarm and increase the detection performance, we redesign the aspect ratios of the anchors. The experimental result shows that our detection method has a competitive performance.

KW - Aircraft detection

KW - Mask R-CNN

KW - Remotely sensed imagery

UR - https://www.scopus.com/pages/publications/85092286583

U2 - 10.1109/IGARSS.2019.8900528

DO - 10.1109/IGARSS.2019.8900528

M3 - 会议稿件

AN - SCOPUS:85092286583

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1370

EP - 1373

BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Zhao P, Gao H, Zhang Y , Li H, Yang R. An aircraft detection method based on improved mask R-CNN in remotely sensed imagery. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1370-1373. (International Geoscience and Remote Sensing Symposium (IGARSS) ). doi: 10.1109/IGARSS.2019.8900528

An aircraft detection method based on improved mask R-CNN in remotely sensed imagery

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this