Automatic Crime Detector
Real-time video anomaly detection with automated evidence alerts
- Type
- AI / ML
- Final recorded accuracy on the trained detection scope
- 95.1%Final recorded accuracy on the trained detection scopeRecorded before delivery
- Video analysis with trained YOLO models
- Frame by frameVideo analysis with trained YOLO modelsTechon Pixel delivery
- Email alerts with timestamps and captured evidence
- AutomatedEmail alerts with timestamps and captured evidenceTechon Pixel delivery
Overview
A Django web application that analyses webcam and uploaded video frame by frame with trained YOLO models, captures anomalies with timestamps and sends automated email alerts, with remote web access.
An applied computer-vision product for monitoring video sources and flagging anomalous events for human review. Detection scope is limited to the classes the model was trained on; this is anomaly detection, not a certified law-enforcement system.
The challenge
- Keeping frame-by-frame inference responsive on commodity hardware
- Reducing false positives to a level operators can trust
What we built
- Webcam and uploaded-video input paths
- Frame-by-frame analysis with trained Ultralytics YOLO models
- Anomaly capture with detection timestamps
- Automated email notification with captured evidence
- Remote web access to review detections
Our role
Machine-learning and web-application engineering
- Model training and evaluation
- Detection pipeline and alerts
- Web application
Platform and stack
- Python
- Django
- OpenCV
- Ultralytics YOLO
- Email notification integration
Build a system with similar complexity
Book a free 30-minute consultation, or write to us, you will always talk directly to the person who builds your product.
Techon Pixel · info@techonpixel.com