Year: 2024
Type: conference-paper
Abstract: This paper presents Mission, the first-of-this-kind cross-modal reidentification (ReID) design for mmWave Radar and RGB cameras. Given a person of interest detected by Radar in camera-restricted scenarios, Mission can identify the image of the person from cameras that are ubiquitously deployed in camera-allowed areas. We envision that cross Vison-RF ReID can significantly enrich mmWave human sensing with a wide spectrum of applications in security surveillance, tracking, and personalized services. Technically, we introduce a novel method for cross-modal similarity estimation that exploits inherent synergies between fine-grained 2D images and coarse-grained 3D Radar point clouds to effectively overcome their modal discrepancy. Through extensive experiments, we demonstrated that our proposed system can achieve 85% top-1 accuracy and 90% top-5 accuracy among 58 volunteers.
Authors: Ruofeng Liu, Tianshun Yao, Ruili Shi, Luoyu Mei, Shuai Wang, Zhimeng Yin, Wenchao Jiang, Shuai Wang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4404034643