Synthetic CCTV Images of Aggressive Poses and Fights for Anomaly Detection

A sample of approximately 100 synthetic frames depicting aggressive behaviors and fighting poses from CCTV angles. The dataset is pre-labeled in YOLOv8 Pose Estimation format with bounding boxes and 17 keypoints per instance. It was created by Simuletic and last updated on November 26, 2025.

Use Cases

• Train models to detect violent incidents based on synthetic images of fighting poses.
• Develop systems for identifying aggressive behaviors and pre-fight cues in public spaces.
• Benchmark pose estimation models on a task-specific dataset of human keypoints in conflict scenarios.
• Augment real-world surveillance datasets with synthetic data for improved model generalization.

Strengths

• Data is pre-labeled in a standard format (YOLOv8 Pose Estimation) with bounding boxes and 17 keypoints.
• Images are described as high-quality and synthetic, which can offer controlled variation and privacy benefits.
• Dataset was last updated on November 26, 2025, indicating recent maintenance.

Limitations

• The dataset is a curated sample of only approximately 100 frames, which is a small scale for training complex models.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is synthetic, which may not fully capture the complexity and noise of real-world CCTV footage.

Provenance

Source

Simuletic

Collection Method

Synthetically generated images.

Time Range

null

Freshness

Last updated 2025-11-26 22:01:37; freshness should be verified.

Geography

null