Related Experiment Video
Updated: Jun 18, 2025
10:28
Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization
Published on: July 5, 2016
10.3K
Towards large-scale single-shot millimeter-wave imaging for low-cost security inspection
Liheng Bian1,2, Daoyu Li3, Shuoguang Wang4,5
1State Key Laboratory of CNS/ATM & MIIT Key Laboratory of Complex-field Intelligent Sensing, Beijing Institute of Technology, 100081, Beijing, China. bian@bit.edu.cn.
Nature Communications
|July 31, 2024
Summary
This study introduces a cost-effective millimeter-wave (MMW) imaging system for security. It uses an optimized sparse sampling strategy and AI to detect concealed objects with reduced hardware costs.
Area of Science:
- Physics
- Electrical Engineering
- Computer Science
Background:
- Millimeter-wave (MMW) imaging offers contactless security inspection capabilities.
- High costs associated with large antenna arrays limit the widespread adoption of MMW imaging in high-throughput security screening.
Purpose of the Study:
- To develop a low-cost, high-fidelity, large-scale single-shot MMW imaging framework for security applications.
- To enable robust MMW image reconstruction and object detection using significantly reduced hardware.
Main Methods:
- Statistical analysis of MMW echoes to determine optimal sparse sampling strategies for antenna arrays.
- Development of an untrained, interpretable learning scheme for reconstructing MMW images from sparse data.
- Implementation of a neural network for automatic object detection in MMW images.
Main Results:
- Achieved an order-of-magnitude reduction in antenna array cost through an optimized sparse sampling strategy.
- Demonstrated accurate and robust MMW image reconstruction from sparsely sampled data.
- Successfully detected centimeter-sized concealed targets using a 10% sparse array, outperforming contemporary methods at low sampling ratios.
Conclusions:
- The developed MMW imaging framework offers a practical solution for low-cost, high-fidelity security inspection.
- The combination of sparse sampling and advanced reconstruction algorithms significantly reduces hardware costs while maintaining performance.
- This technique shows promise for large-scale, single-shot MMW imaging applications in security and other fields.
