Robust Human Detection under Visual Degradation via Thermal and mmWave Radar Fusion

Kaiwen Cai, Qiyue Xia, Peize Li, John Stankovic, Chris Xiaoxuan Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

The majority of human detection methods rely on the sensor using visible lights (e.g., RGB cameras) but such sensors are limited in scenarios with degraded vision conditions. In this paper, we present a multimodal human detection system that combines portable thermal cameras and single-chip mmWave radars. To mitigate the noisy detection features caused by the low contrast of thermal cameras and the multipath noise of radar point clouds, we propose a Bayesian feature extractor and a novel uncertainty-guided fusion method that surpasses a variety of competing methods, either single modal or multi-modal. We evaluate the proposed method on real-world data collection and demonstrate that our approach outperforms the state-of-the-art methods by a large margin.
Original languageEnglish
Title of host publicationEWSN '23: Proceedings of the 2023 INTERNATIONAL CONFERENCE ON EMBEDDED WIRELESS SYSTEMS AND NETWORKS
Number of pages12
Publication statusAccepted/In press - 12 Jul 2023
EventInternational Conference on Embedded Wireless Systems and Networks 2023 - Rende, Italy
Duration: 25 Sept 202327 Sept 2023
Conference number: 20
https://events.dimes.unical.it/ewsn2023/

Conference

ConferenceInternational Conference on Embedded Wireless Systems and Networks 2023
Abbreviated titleEWSN 2023
Country/TerritoryItaly
CityRende
Period25/09/2327/09/23
Internet address

Fingerprint

Dive into the research topics of 'Robust Human Detection under Visual Degradation via Thermal and mmWave Radar Fusion'. Together they form a unique fingerprint.

Cite this