PDL Abstract

Efficient Multi-Tenant Inference on Video using Microclassifiers

SysML’18, February 15–16, 2018, Stanford, CA.

Giulio Zhou, Thomas Kim, Christopher Canel, Conglong Li, Hyeontaek Lim, David G. Andersen, Michael Kaminsky†, Subramanya R. Dulloor†

Carnegie Mellon University
† Intel Labs


This paper addresses a growing challenge in processing video: The scaling challenge presented by the combination of an increasing number of video sources (cameras) and an increasing number of heavy-weight DNN-based applications (which we term “queries”) to be run on each source. As a running example, we draw from an environmental and traffic monitoring deployment at CMU, one feed from which is depicted at right. This feed supports applications such as car and pedestrian counting, open parking spot detection, train detection (in support of an environmental monitoring research project attempting to determine locomotive emissions), and observing if building lights are left on. These cameras are deployed using a mix of the high-speed campus network, and a lower-speed/highercost cable modem deployment on power poles in the area.