What it does
KeiVideo intercepts the raw sensor stream and runs the inference work — detection, classification, scene understanding — before frames ever leave the camera module. The host application sees a clean structured output instead of paying the cost of decoding and processing full-resolution frames.
Why on-sensor
Bandwidth, latency, and power all favour pushing inference as close to the sensor as possible. The result is a camera that ships features, not pixels.
cross-references