LED recognition method based on deep learning in UAV optical camera communication

Xu Sun; YinHui Yu; Qing Cheng

doi:10.1364/AO.469622

Applied Optics
Vol. 61,
Issue 29,
pp. 8688-8694
(2022)
•https://doi.org/10.1364/AO.469622

LED recognition method based on deep learning in UAV optical camera communication

Xu Sun, YinHui Yu, and Qing Cheng

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Xu Sun, YinHui Yu, and Qing Cheng, "LED recognition method based on deep learning in UAV optical camera communication," Appl. Opt. 61, 8688-8694 (2022)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article
Editors' Pick

Check for updates

Related Topics
Table of Contents Category
- Imaging Systems, Image Processing, and Displays
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: July 6, 2022
- Revised Manuscript: August 16, 2022
- Manuscript Accepted: August 31, 2022
- Published: October 3, 2022

Abstract

Optical camera communication (OCC) is a potential technology in unmanned aerial vehicle (UAV) communication scenes, which can be used as a complementary scheme for radio frequency (RF) technology to effectively mitigate electromagnetic interference. The UAV OCC system still has the problems of low reliability, poor robustness, and long latency. In this paper, we propose the $n$-ary image that contains binary image information with different thresholds for the LED area. In addition, the multi-spectrum fast recognition (MFR) algorithm based on deep learning is designed. The MFR algorithm combines the frequency channel attention (FCA) and the involution convolution operator, which take the $n$-ary image as input to accurately identify the LED state. The experiment results show that the proposed method can reduce the bit error rate (BER) and latency of the UAV OCC system.

Full Article | PDF Article

More Like This

Effective interference mitigation scheme for multi-LED-based mobile optical camera communication

Yiting Yang, Jing He, and Biao Zhou
Appl. Opt. 60(35) 10928-10934 (2021)

Unmanned-aerial-vehicle based optical camera communication system using light-diffusing fiber and rolling-shutter image-sensor

Yun-Han Chang, Shang-Yen Tsai, Chi-Wai Chow, Chih-Chun Wang, Deng-Cheng Tsai, Yang Liu, and Chien-Hung Yeh
Opt. Express 31(11) 18670-18679 (2023)

Object recognition in optical camera communication enabled by image restoration

Meitong Guo, Pinpin Zhang, Yimao Sun, Weihua Zhang, Yingjie Zhou, and Yanbing Yang
Opt. Express 30(20) 37026-37037 (2022)

Previous Article Next Article

Data availability

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (10)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (6)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (4)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Experiment Parameters	Value
LED array	$4 \times 4$
LED wavelength	808 nm
LED diameter	2 mm
LED interval	3 cm
Ambient light	684 lux
Center wavelength of optical filter	$808 n m \pm 2 n m$
Image sensor type	CCD
Image sensor size	1/3^′′
Camera resolution	$640 \times 480$ pixels
Lens focal length	6 mm

Input Images	$M A$	BER
Original image	0.7814	$1.747 \times 10^{- 2}$
Cropped original image	0.9516	$3.914 \times 10^{- 3}$
Pseudo 3-ary image	0.9059	$7.626 \times 10^{- 3}$
3-ary	0.9802	$1 .465 \times 1 0^{- 3}$
4-ary	0.9802	$1.477 \times 10^{- 3}$
5-ary	0.9796	$1.528 \times 10^{- 3}$
6-ary	0.9784	$1.629 \times 10^{- 3}$

Input Forms	Inference Time (ms)	$M A$	BER	Epoch
Fixed size	6.003	0.978	$1.540 \times 10^{- 3}$	24^b
Preselected ${s i z e}^{2 +}$	5.776^b	0.980^b	$1 .465 \times 1 0^{- 3}$ ^b	49
Preselected ${s i z e}^{4 +}$	5.854	0.979	$1.477 \times 10^{- 3}$	36
Preselected ${s i z e}^{6 +}$	5.983	0.979	$1.503 \times 10^{- 3}$	28

Methods	Model Size (kb)	Inference Time (ms)	$M A$	BER
CNN model	131	5.799	0.973	$2.298 \times 10^{- 3}$
Involution convolution model	75.8	6.093	0.969	$2.677 \times 10^{- 3}$
FCA model	87.6	5.910	0.974	$1.970 \times 10^{- 3}$
MFR algorithm	43	5.776	0.980	$1 .465 \times 1 0^{- 3}$

LED Recognition Methods	Model Size	Inference Time	$MA$	BER
Liu et al. [26]	11.1 kb	4.029 ms	0.407	$1.756 \times 10^{- 1}$
Huynh et al. [27]	12.4 kb	11.022 ms	0.254	$2.164 \times 10^{- 1}$
Kim et al. [28]	14.5 kb	7.614 ms	0.324	$1.937 \times 10^{- 1}$
Sun et al. [21]	208 MB	359.376 ms	0.974	$2.968 \times 10^{- 3}$
Ours	43 kb	5.776 ms	0.980	$1 .465 \times 1 0^{- 3}$

Abstract

Data availability

Cited By

Figures (10)

Tables (6)

Equations (4)

Applied Optics