: On each camera, enable "Confirm with AI" and list the objects you want to verify (e.g., person, car ).
CodeProject.AI Server integration with Blue Iris enables fast, private, and local object detection, marking alerts as "Verified" when the AI confirms objects like people or cars. This setup utilizes high-resolution snapshot analysis via models like YOLOv5, allowing users to configure confidence thresholds and specific labels for real-time alert verification. For more details, visit CodeProject. AI responses may include mistakes. Learn more
: Within the camera's "Alerts" tab, the AI settings must point to the local CodeProject.AI server IP and port. The Role of Community and Verification codeproject blue iris verified
The "verified" status of this integration is rooted in its technical design. CodeProject.AI Server was built to be API-compatible with the older DeepStack service, making it a seamless, drop-in replacement for Blue Iris. Blue Iris is configured to send HTTP calls to the CodeProject.AI Server with image data, and the server replies with a list of identified objects and their confidence scores.
: Use specialized modules within CodeProject.AI to read and log license plates locally without needing expensive cloud subscriptions. : On each camera, enable "Confirm with AI"
For users on low-power PCs (like an Intel Celeron running Blue Iris), a Google Coral USB accelerator is a game-changer. CodeProject.AI now supports Coral. If "Verified" means "instantaneous" to you, switch the inference engine to Coral in the AI settings.
To make the AI efficient, you must configure how individual cameras trigger the AI analysis. Right-click a camera feed and select . Go to the Trigger tab and click Artificial Intelligence . For more details, visit CodeProject
By passing initial pixel-motion triggers through an integrated AI verification layer, users can experience a drop in false positives caused by wind, rain, insects, or passing headlights. The Power of CodeProject.AI Verification