EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning for Real-Time Surveillance and Anomaly Detection

Dr. Jingwei Zhao

American Journal of Machine Learning · 31.12.2024 · 5 (6) · 11-21

DOI: 10.71465/ajml3061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Machine Learning, online erschienen am 31.12.2024. Verfasst von Dr. Jingwei Zhao. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time surveillance and anomaly detection have become critical for ensuring safety and security in various applications, such as public spaces, critical infrastructure, and healthcare facilities. Traditional systems, relying on manual intervention and rule-based algorithms, often struggle with the dynamic and vast nature of video data. Recent advancements in deep learning have paved the way for more efficient, automated, and accurate detection systems. This paper explores the application of deep learning techniques, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), in real-time surveillance and anomaly detection. The paper highlights the potential of these models to not only enhance detection accuracy but also offer scalable and robust solutions. The challenges, methods, and future directions of deep learning in this field are also discussed.

Zitieren

APA

Zhao, D. J. (2024). Deep Learning for Real-Time Surveillance and Anomaly Detection. American Journal of Machine Learning, 5(6), 11-21. https://doi.org/10.71465/ajml3061

Vancouver

Zhao DJ. Deep Learning for Real-Time Surveillance and Anomaly Detection. American Journal of Machine Learning. 2024;5(6):11-21. doi:10.71465/ajml3061

BibTeX
@article{Zhao2024,
  author = {Zhao, Dr. Jingwei},
  title = {Deep Learning for Real-Time Surveillance and Anomaly Detection},
  journal = {American Journal of Machine Learning},
  year = {2024},
  volume = {5},
  number = {6},
  pages = {11--21},
  doi = {10.71465/ajml3061}
}
Kostenlos starten →