Format

Send to

Choose Destination
Nat Commun. 2019 Mar 6;10(1):1082. doi: 10.1038/s41467-019-09103-2.

Machine-learning reprogrammable metasurface imager.

Author information

1
State Key Laboratory of Advanced Optical Communication Systems and Networks, Department of Electronics, Peking University, 100871, Beijing, China. lianlin.li@pku.edu.cn.
2
State Key Laboratory of Advanced Optical Communication Systems and Networks, Department of Electronics, Peking University, 100871, Beijing, China.
3
State Key Laboratory of Millimeter Waves, Southeast University, 210096, Nanjing, China.
4
Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583, Singapore.
5
Photonics Initiative, Advanced Science Research Center, City University of New York, 85 St. Nicholas Terrace, New York, NY, 10031, USA. aalu@gc.cuny.edu.
6
Physics Program, The Graduate Center, City University of New York, 365 Fifth Avenue, New York, NY, 10016, USA. aalu@gc.cuny.edu.
7
Department of Electrical Engineering, City College of New York, New York, NY, 10031, USA. aalu@gc.cuny.edu.
8
Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583, Singapore. chengwei.qiu@nus.edu.sg.
9
State Key Laboratory of Millimeter Waves, Southeast University, 210096, Nanjing, China. tjcui@seu.edu.cn.

Abstract

Conventional microwave imagers usually require either time-consuming data acquisition, or complicated reconstruction algorithms for data post-processing, making them largely ineffective for complex in-situ sensing and monitoring. Here, we experimentally report a real-time digital-metasurface imager that can be trained in-situ to generate the radiation patterns required by machine-learning optimized measurement modes. This imager is electronically reprogrammed in real time to access the optimized solution for an entire data set, realizing storage and transfer of full-resolution raw data in dynamically varying scenes. High-accuracy image coding and recognition are demonstrated in situ for various image sets, including hand-written digits and through-wall body gestures, using a single physical hardware imager, reprogrammed in real time. Our electronically controlled metasurface imager opens new venues for intelligent surveillance, fast data acquisition and processing, imaging at various frequencies, and beyond.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center