What question did this study set out to answer?

This research aims to develop a framework for real-time detection of abnormal behaviors in video streams using Dynamic Graph Neural Networks.

Dynamic graph neural network video abnormal behavior detection method for real time streaming

View Full Paper

Ask AI

Bookmark

This research aims to develop a framework for real-time detection of abnormal behaviors in video streams using Dynamic Graph Neural Networks.
Utilizes Dynamic Graph Neural Networks for frame-wise graph updates.
Implements a lightweight spatio-temporal GCN optimized for live anomaly detection.
Evaluates the model's performance using accuracy, precision, recall, and F1-score metrics.
Achieved 99.65% accuracy with a precision and recall close to 1.
Demonstrated low false negative rate (0.35%) and false positive rate (0.03%).
Proved real-time processing capability with less than 200 milliseconds latency.

Authors

No takes yet. Share an insight, caveat, or question.

The proposed method demonstrates real-time detection of anomalous behavior in streaming video, suggesting a novel approach for public safety systems.

Sun et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

The proposed method demonstrates real-time detection of anomalous behavior in streaming video, suggesting a novel approach for public safety systems.