Synthetic CCTV Images for Knife Detection in Public Spaces

An open-source synthetic dataset for computer vision object detection, focused on people holding knives in public and semi-public environments, viewed from CCTV and surveillance camera perspectives. It was created by Simuletic and last updated on November 18, 2025. The dataset is designed to help train and evaluate YOLO, YOLOv8, YOLOWorld, Detectron, and other object detection models.

Use Cases

• Train object detection models for threat recognition based on the described focus on knives in public spaces.
• Evaluate model performance for security analytics based on the synthetic CCTV and surveillance camera perspectives.
• Benchmark YOLO, YOLOv8, and Detectron models for abnormal behavior detection based on the dataset's stated purpose.

Strengths

• Annotations are provided in YOLO format with bounding boxes.
• Dataset is explicitly designed for training and evaluating multiple modern object detection frameworks like YOLO and Detectron.
• Last updated on November 18, 2025, indicating recent maintenance.

Limitations

• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is synthetic, which may not fully capture the complexity and variability of real-world CCTV footage.

Provenance

Source

Simuletic via Hugging Face

Collection Method

Synthetically generated for computer vision tasks.

Time Range

null

Freshness

Last updated 2025-11-18 17:18:50

Geography

null