Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting
IEEE Transactions on Mobile Computing · 2024-12 · 23 (12) · 14233-14247
DOI: 10.1109/tmc.2024.3444469 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-12. Verfasst von Lifei Hao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Inner Mongolia A.R. of China, Science & Technology Plan Project of Inner Mongolia A. R. of China.
Abstract (Originalsprache)
Crowd counting aims to estimate the number of individuals in targeted areas. However, mainstream vision-based methods suffer from limited coverage and difficulty in multi-camera collaboration, which limits their scalability, whereas emerging WiFi-based methods can only obtain coarse results due to signal randomness. To overcome the inherent limitations of unimodal approaches and effectively exploit the advantage of multi-modal approaches, this paper presents an innovative WiFi and video-fused multi-modal paradigm by leveraging a heterogeneous dual-attentional network, which jointly models the intra- and inter-modality relationships of global WiFi measurements and local videos to achieve accurate and stable large-scale crowd counting. First, a flexible hybrid sensing network is constructed to capture synchronized multi-modal measurements characterizing the same crowd at different scales and perspectives; second, differential preprocessing, heterogeneous feature extractors, and self-attention mechanisms are sequentially utilized to extract and optimize modality-independent and crowd-related features; third, the cross-attention mechanism is employed to deeply fuse and generalize the matching relationships of two modalities. Extensive real-world experiments demonstrate that our method can significantly reduce the error by 26.2%, improve the stability by 48.43%, and achieve the accuracy of about 88% in large-scale crowd counting when including the videos from two cameras, compared to the best WiFi unimodal baseline.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Inner Mongolia A.R. of China
- Science & Technology Plan Project of Inner Mongolia A. R. of China
- Ordos Science & Technology Plan
- University Youth Science and Technology Talent Development Project of Inner Mongolia A. R. of China
- First-class Discipline Special Research Project of Inner Mongolia A. R. of China
Zitieren
APA
Hao, L., Huang, B., Jia, B., & Mao, G. (2024). Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting. IEEE Transactions on Mobile Computing, 23(12), 14233-14247. https://doi.org/10.1109/tmc.2024.3444469
Vancouver
Hao L, Huang B, Jia B, Mao G. Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting. IEEE Transactions on Mobile Computing. 2024;23(12):14233-14247. doi:10.1109/tmc.2024.3444469
BibTeX
@article{Hao2024,
author = {Hao, Lifei and Huang, Baoqi and Jia, Bing and Mao, Guoqiang},
title = {Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {12},
pages = {14233--14247},
doi = {10.1109/tmc.2024.3444469}
}
EUVIMED