Description:
Reference #: 01537
The University of South Carolina is offering licensing opportunities for Human-Perceptible and Machine-Readable Shape Generation and Classification of Hidden Objects
Background:
Millimeter-wave (mmWave) systems enable through-obstruction imaging and are widely used for screening in state of-the-art airports and security portals. They can detect hidden contrabands, such as weapons, explosives, and liquids, by penetrating wireless mmWave signals through clothes, bags, and non-metallic obstructions. Besides, mmWave imaging systems could enable applications to track beyond line-of-sight, see through walls, recognize humans through obstructions, and analyze materials without contaminating them.
Invention Description:
We propose our invention, a system that approximates traditional SAR imaging on mobile millimeter-wave devices. It enables human perceptible and machine-readable shape generation and classification of hidden objects on mobile millimeter wave devices. The system is capable of imaging through obstructions, like clothing, and under low visibility conditions.
Potential Applications:
Hidden shape perception by humans or classification by machines under hand-held settings will enable multiple applications, such as in-situ security check without pat-down search, baggage discrimination without opening the baggage, packaged inventory item counting without intrusions, discovery of faults in water pipes or gas lines without tearing up walls, etc.
Advantages and Benefits:
Since under traditional SAR, mmWave imaging suffers from poor resolution, specularity, and weak reflectivity from objects, the reconstructed shapes could often be imperceptible by humans. To this end, our invention designs a machine learning model to recover the high spatial frequencies in the object to reconstruct an accurate 2D shape and predict its 3D features and category.