camera.ui

Apple's on-device foundation model as an assistant model for camera.ui. Runs through the fm command line tool of macOS 27, no key and no cloud.

Shared ML inference framework for camera.ui detection plugins (onnx, openvino, coreml, ncnn)

Imports Home Assistant sensors into camera.ui: motion, occupancy, contacts, doorbells, smoke, leak and more become assignable camera.ui sensors that can trigger camera detection.

ONNX Runtime detection backend for camera.ui. Runs object detection, face detection and recognition, license plate recognition with OCR, and CLIP semantic embeddings.

Apple CoreML detection backend for camera.ui. Runs object detection, face detection and recognition, license plate recognition with OCR, and CLIP semantic embeddings on Apple hardware.

NCNN detection backend for camera.ui. Runs object detection, face detection and recognition, and license plate recognition with OCR.

OpenVINO detection backend for camera.ui with the older 2024.6 runtime. For Intel GPUs up to 10th gen Core on Windows, whose drivers cannot build the GPU code of newer OpenVINO releases. On Linux the camera.ui Docker image covers these GPUs with legacy co

ONNX Runtime detection backend for camera.ui with the older CUDA 12 runtime. For NVIDIA GPUs before GTX 1650 (Maxwell, Pascal, Volta) and for systems that stay on CUDA 12. Use the regular ONNX plugin on newer hardware.

Audio event detection for camera.ui. Classifies sounds from camera audio streams using the YAMNet model.