e1171e8ff8
Motion detection now optionally runs MobileNet V2 SSD (COCO, quantized) on frames that trigger motion, identifying objects like people, cats, and cars. Events without detected objects are suppressed by default. Snapshots include bounding box annotations. New MCP tool vision_get_detections() enables label-based queries. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
18 lines
313 B
Plaintext
18 lines
313 B
Plaintext
# vixy-vision Server Requirements
|
|
|
|
# Web framework
|
|
fastapi>=0.100.0
|
|
uvicorn[standard]>=0.22.0
|
|
|
|
# Camera / CV
|
|
opencv-python-headless>=4.8.0
|
|
|
|
# Config
|
|
python-dotenv>=1.0.0
|
|
|
|
# HTTP client (for posting events to collector)
|
|
httpx>=0.24.0
|
|
|
|
# Object detection (installed separately by setup.sh)
|
|
# tflite-runtime>=2.14.0
|