A Study on Abnormal Sign Detection Based on Normal Behavior Pattern Changes in Indoor CCTV Environments

View at Publisher

Ask AI

Bookmark

Share

Key Points

The aim is to develop a generalized method for detecting anomalies based on changes in normal behavior patterns.
Utilized YOLOv5s for detecting human objects in CCTV footage.
Accumulated movement information based on centroid coordinates over time windows to extract behavioral characteristics.
Compared patterns formed during normal behavior intervals to identify periods of significant change as anomalies.
Stability in feature values during normal intervals was observed, while increased variability was noted during behavioral change periods.
An F1-score improvement from 0.835 to 0.908 was achieved, indicating an approximately 7% performance enhancement against frame-based methods.
Reduction in false detection caused by temporary noise was also confirmed.

Demonstrates improved anomaly detection in indoor CCTV environments, suggesting enhanced security measures.

No abstract yet. The journal hasn't published one we can show.

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

Park et al. (2026) studied this question.

View at Publisher

Ask AI

Bookmark

Share