Journals
Advanced Photonics
Photonics Insights
Advanced Photonics Nexus
Photonics Research
Advanced Imaging
View All Journals
Chinese Optics Letters
High Power Laser Science and Engineering
Articles
Optics
Physics
Geography
View All Subjects
Conferences
CIOP
HPLSE
AP
View All Events
News
About CLP
Search by keywords or author
Login
Registration
Login in
Registration
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
metasurface
laser
nir
optical coherence tomography
Lithium niobate
OAM
Journals >
Acta Optica Sinica >
Volume 38 >
Issue 6 >
Page 0615004 > Article
Acta Optica Sinica
Vol. 38, Issue 6, 0615004 (2018)
Aerial Target Detection Based on Improved Faster R-CNN
Xiaoyu Feng
*
, Wei Mei, and Dashuai Hu
Author Affiliations
Department of Electronics and Optics Engineering, Army Engineering University, Shijiazhuang, Hebei 050003, China
show less
DOI:
10.3788/AOS201838.0615004
Cite this Article
Set citation alerts
Xiaoyu Feng, Wei Mei, Dashuai Hu. Aerial Target Detection Based on Improved Faster R-CNN[J]. Acta Optica Sinica, 2018, 38(6): 0615004
Copy Citation Text
EndNote(RIS)
BibTex
Plain Text
show less
Fig. 1.
Frame of Faster R-CNN
Download full size
Fig. 2.
Accumulation of dilation
Download full size
Fig. 3.
Pooling of feature map
Download full size
Fig. 4.
Regional amplification
Download full size
Fig. 5.
Influences of scale and occlusion on confidences
Download full size
Fig. 6.
False positive with high confidence
Download full size
Fig. 7.
Frame of improved Faster R-CNN
Download full size
Fig. 8.
Examples of detection results
Download full size
Fig. 9.
Examples of detection results of M4
Download full size
Content
Fighter
Helicopter
Aerobus
Bird
Others
Video
11 sequences
(about 7000 frames)
7 sequences
(about 6000 frames)
10 sequences
(about 9000 frames)
4 sequences
(about 1000 frames)
6 sequences
(about 4000 frames)
Image
300
300
300
300
300
Table 1.
Dataset of aerial targets
Model
Fighter
Helicopter
Aerobus
Bird
Others
mAP
M0
90.76
91.04
92.35
63.71
72.76
82.12
M2
93.42
96.67
94.22
75.81
95.76
91.18
M3
91.53
92.64
93.19
69.37
78.07
84.96
M4
98.72
99.37
97.42
98.61
99.76
98.78
Table 2.
Result on test set1 %
Model
Fighter
Helicopter
Aerobus
Bird
Others
mAP
M0
0
0
0
0
0
0
M1
54.05
68.66
62.26
39.61
85.36
61.99
Table 3.
Result on test set2%
Detector
Faster R-CNN
[
9
]
SSD299
[
10
]
SSD443
[
10
]
YOLO
[
11
]
YOLOv2 544
[
11
]
M4
AP /%
84.9
71.2
78.6
77.0
86.3
90.7%
Speed /(frame·s
-1
)
8.3
46
19
45
40
25
Table 4.
Detection performances on class aero of VOC
Abstract
Get PDF(in Chinese)
Figures&Tables (13)
Equations (0)
References (23)
Cited By (33)
Get Citation
Copy Citation Text
Xiaoyu Feng, Wei Mei, Dashuai Hu. Aerial Target Detection Based on Improved Faster R-CNN[J]. Acta Optica Sinica, 2018, 38(6): 0615004
Download Citation
EndNote(RIS)
BibTex
Plain Text
Set citation alerts for the article
Tools
Share
Set citation alerts for the article
Save the article for my favorites
Paper Information
Category: Machine Vision
Received: Dec. 6, 2017
Accepted: --
Published Online: Jun. 7, 2018
The Author Email: Feng Xiaoyu (826782445@qq.com)
DOI:
10.3788/AOS201838.0615004
Recommended Topics
laser devices and laser physics
Lasers and Laser Optics
Laser physics
laser manufacturing
Instrumentation, Measurement and Metrology
Set citation alerts for the article
Please enter your email address
Cancel
Confirm