Querying Zero-streaming Cameras.

Low-cost cameras grow rapidly, producing colossal videos that enable powerful analytics but also stress network and compute resources. An unexploited opportunity is that most of the videos remain "cold" without ever being queried. For resource efficiency, we advocate for these cameras to be zero-streaming: they capture videos directly to their cheap local storage and only communicate with the cloud when analytics is requested. To this end, we present a system that spans the cloud and cameras. Our key ideas are twofold. When capturing video frames, a camera learns accurate knowledge on a sparse sample of frames, rather than learning inaccurate knowledge on all frames; in executing one query, a camera processes frames in multiple passes with multiple operators trained and picked by the cloud during the query, rather than one pass processing with operator(s) decided ahead of the query. On diverse queries over 15 videos and with typical wireless network bandwidth and low-cost camera hardware, our system prototype runs at more than 100x video realtime. It outperforms competitive alternative designs by at least 4x and up to two orders of magnitude.