• Citer

Group counting using micro-doppler signatures from a 77GHz FMCW radar: a CNN approach

par Cakoni, Dejvi ;Storrer, Laurent ;De Doncker, Philippe ;Horlin, François
Référence (11-12 May, 2023: Brussels, Belgium), Proc. of the 43rd Symposium on Information Theory and Signal Processing in the Benelux (SITB)
Publication Publié, 2023-05-11

Publication dans des actes

• Accès en ligne
• Détails
• Contenu
• Statistiques

Résumé :

People counting and detection technologies haveshown great versatility in various scnearios and have become animportant tool for event organizers and city planners to optimizetheir operations. This paper presents a novel approach for people counting using Micro-Doppler Signatures (MDS) extractedfrom a Frequency-Modulated Continuous-Wave (FMCW) radaroperating at 77GHz. The system utilizes the unique gait modelof each individual, which results in a distinct MDS, to classifygroups of different sizes using a Convolutional Neural Network(CNN). The proposed system overcomes the limitations of existingpeople counting techniques such as the need for a clear line ofsight and being affected by lighting conditions.