Abstract

While spatial structured light based free space optical communication provides high-bandwidth communication with broad application prospect, severe signal distortion caused by optical scattering from ambient microparticles in the atmosphere can lead to data degradation. A deep-learning-based adaptive demodulator has been demonstrated to resolve the information encoded in the severely distorted channel, but the high generalization ability for different scattering always requires prohibitive costs on data preparation and reiterative training. Here, we demonstrate a meta-learning-based auto-encoder demodulator, which learns from prior theoretical knowledge, and then training with only three realistic samples per class can rectify and recognize transmission distortion. By employing such a demodulator to hybrid vector beams, high fidelity communication can be established, and data costs are reduced when faced with different scattering channels. In a proof-of-principle experiment, an image with 256 gray values is transmitted under severe scattering with an error ratio of less than 0.05%. Our work opens the door to high-fidelity optical communication in random media environments.

© 2022 Optica Publishing Group

65,536-ary orbital angular momentum–shift keying free-space optical communication based on few-shot learning

Wenhui Chen, Qian Lin, Weicheng Chen, Zhishen Zhang, Zikuan Zhuang, Zhikun Su, and Li Zhang
Opt. Lett. 48(7) 1886-1889 (2023)

Data transmission under high scattering based on OAM-basis transmission matrix

Zeqi Liu, Hengkang Zhang, Kaige Liu, Bin Zhang, Xing Fu, and Qiang Liu
Opt. Lett. 47(17) 4580-4583 (2022)

High-base vector beam encoding/decoding for visible-light communications

Yifan Zhao and Jian Wang
Opt. Lett. 40(21) 4843-4846 (2015)

Experimental performance of deep learning channel estimation for an X-ray communication-based OFDM-PWM system

Wenxuan Chen, Yunpeng Liu, Junxu Mu, Zhaopeng Feng, and Xiaobin Tang
Opt. Lett. 47(3) 461-464 (2022)

Blind light field image quality assessment based on deep meta-learning

Jian Ma, Xiaoyin Zhang, and Junbo Wang
Opt. Lett. 48(23) 6184-6187 (2023)