Back to Datasets

    CCTV Aggressive Pose Detection Dataset

    CCTV Aggressive Pose Detection Dataset sample 1

    This dataset enables AI systems to detect aggressive body language and fighting behaviors from CCTV perspectives before incidents escalate. Each image contains 17-keypoint skeleton annotations (COCO standard) capturing aggressive stances, punching motions, shoving, and confrontational postures. Scenarios include bars, public squares, parking areas, and transit hubs. The dataset differentiates between normal pedestrian behavior and threatening poses, enabling proactive security alerts. All imagery is 100% synthetic—no real individuals are depicted. The open-source sample contains 104 annotated images; the full package includes 1,000 images with evaluation videos.

    1,000 images

    Full Package

    104

    Open Source Samples

    COCO Keypoints

    Annotation Format

    100%

    Privacy Compliant

    Dataset Features

    17-keypoint skeleton annotations (COCO standard)
    Aggressive vs normal pose classification
    Diverse public space scenarios
    Proactive threat detection focus
    100% privacy-compliant synthetic data
    104 open-source sample images

    Intended Use Cases

    Nightlife venue securityPublic transport monitoringSchool safety systemsSmart city threat detection

    Free Sample vs. Commercial Package

    Free Open-Source Sample

    • 104 annotated images
    • Format: COCO Keypoints
    • Hosted on Kaggle
    • Licence: See the hosting platform's terms of use

    Commercial Package

    The Creative Commons licence above applies only to the free sample, not to the full commercial package.

    Limitations & Recommended Validation

    This dataset is 100% synthetic. While it is designed to closely match real-world sensor and camera conditions, synthetic imagery can still differ from live footage in ways that affect model accuracy (a "domain gap"). Validate a trained model against real-world footage from your specific deployment environment before production use.

    Not intended as a sole basis for biometric identification, legal evidence, or safety-critical decisions without independent human review and real-world testing.