Real-Time Intelligent Surveillance for Public Safety

A national R&D program (≈ US$24 million over 5 years) developing context-aware video anomaly detection for real-time public-safety surveillance. The system analyzes up to ~1,000 cameras streamed from regional CCTV control centers operated by cities, district offices, and police stations, and flags crime-related anomalies in everyday civic activity — fighting, shooting, burglary, arson, explosion, road accidents, riots, shoplifting, and assault.

Roles & partners: core/source technology developed at KIST under the Ministry of Science and ICT (MSIT); an applied track under the Ministry of Trade, Industry and Energy (MOTIE) in collaboration with Yonsei University and the Korean National Police Agency (KNPA).
Real-world deployment: field-validated with local governments in Anyang City, Korea, where the system contributed to resolving a real missing-person case.

Related publications: (Ahn et al., 2025; Ahn et al., 2026)

References

2026

BMVC

BUSTER: Adaptive Sampling for VLM-Guided Unsupervised Video Anomaly Detection

Deokhyun Ahn, Yonghun Choi, Jae-Ho Han, Ig-Jae Kim, and Haksub Kim

In Proceedings of the British Machine Vision Conference (BMVC), 2026

Under Review

2025

TIP

Where and What: Contextual Dynamics-Aware Anomaly Detection in Surveillance Videos

Deokhyun Ahn, Yongjin Jo, DongBum Kim, Gi Pyo Nam, Jae-Ho Han, and Haksub Kim

IEEE Transactions on Image Processing, 2025

IF 13.7 · top 2.2% in Electrical & Electronic Engineering

Bib HTML

@article{ahn2025where,
  title = {Where and What: Contextual Dynamics-Aware Anomaly Detection in Surveillance Videos},
  author = {Ahn, Deokhyun and Jo, Yongjin and Kim, DongBum and Nam, Gi Pyo and Han, Jae-Ho and Kim, Haksub},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  note = {IF 13.7 · top 2.2\% in Electrical \& Electronic Engineering},
}