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
: A camera detects moving pixels and alerts Blue Iris.
: CodeProject.AI analyzes the image using computer vision models (like YOLOv5 or YOLOv8). If the object matches your specific confirmation criteria (e.g., person or car ), Blue Iris flags the clip as Verified , saves it to the database, fires a high-resolution alert, and pushes notifications. codeproject blue iris verified
In a standard network video recorder (NVR) setup, video analytics rely on basic pixel-change detection. If a cloud of bugs flies across a lens or a tree branch sways, the software logs a trigger.
: Blue Iris extracts high-resolution keyframes and passes them to CodeProject.AI Server via a local API. If the object matches your specific confirmation criteria (e
: The system is highly adaptive, allowing users to process AI locally using a standard CPU, a dedicated NVIDIA GPU for faster speeds, or even a Google Coral AI chip to offload processing tasks. Strategic Deployment
Before diving into Blue Iris, it's crucial to understand the AI engine that powers it. CodeProject.AI Server is a standalone, self-hosted, and artificial intelligence microserver . Think of it as a dedicated, local AI brain that runs on your Windows, Linux, or macOS machine, or even in a Docker container. It analyzes images and video feeds from your cameras to identify objects like people, cars, animals, and packages. : Blue Iris extracts high-resolution keyframes and passes
If the AI returns nothing, Blue Iris cancels the alert, preventing an unnecessary push notification or external smart-home automation rule from firing. Step-by-Step Configuration for Verified Alerts