公开(公告)号：US20250022373A1

公开(公告)日：2025-01-16

申请号：US18635295

申请日：2024-04-15

Applicant: UNIVERSITY OF SOUTH CAROLINA

Inventor： SANJIB SUR ,  HEM K. REGMI

IPC: G08G1/16 ,  G01S13/931 ,  G06N3/0475

Abstract: The disclosed system and methodology enable coexistence of networking and sensing on next-generation millimeter-wave (mmWave) picocells for traffic monitoring and pedestrian safety at intersections in all weather conditions. Existing wireless signal-based object detection systems suffer from limited resolution, and their outputs may not provide sufficient discriminatory information in complex scenes, such as traffic intersections. The disclosed system uses 5G picocells, which operate at mmWave frequency bands and provide higher data rates and higher sensing resolution than traditional wireless technology. It is difficult to run sensing applications and data transfer simultaneously on mmWave devices due to potential interference. MmWave devices are vulnerable to weak reflectivity and specularity challenges which may result in loss of information about objects and pedestrians. To address such challenges, the disclosed design uses customized deep learning models that not only can recover missing information about the target scene but also enable coexistence of networking and sensing.

公开(公告)号：US20220373673A1

公开(公告)日：2022-11-24

申请号：US17726279

申请日：2022-04-21

Applicant: UNIVERSITY OF SOUTH CAROLINA

Inventor： SANJIB SUR ,  HEM K. REGMI

IPC: G01S13/88 ,  G01S13/90 ,  G06V10/774 ,  G06V10/764 ,  G06N3/04 ,  G06N3/08

Abstract: System and methodology are disclosed for approximating traditional SAR imaging on mobile mmWave devices. The presently disclosed technology enables human-perceptible and machine-readable shape generation and classification of hidden objects on mobile mmWave devices. The resulting system and corresponding methodology are capable of imaging through obstructions, like clothing, and under low visibility conditions. To this end, the presently disclosed technology incorporates 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. The technology is disclosed in particular for security applications, but the broader model disclosed is adaptable to different applications, even with limited training samples.