Roadside Traffic Monitoring Using Video Processing on the Edge

Roadside traffic monitoring is increasingly performed by deploying roadside high-resolution video cameras and then running computer vision (CV) models on the video data. Since computer vision models are compute-intensive as they utilize deep neural networks (DNNs), the data is usually sent to one or more edge servers located adjacent to mobile base stations, thereby keeping the in-situ (on camera) processing load as less as possible. Recent techniques propose running CV models on tiles of videos separately to detect and track small objects. Several CV models exist, each with different requirements of compute and memory. Since more compute and memory-intensive CV models provide higher accuracy, a key challenge of such techniques is to determine which vision model should be used on which tile. This becomes even more challenging if multiple videos are processed by the same edge server. In this paper, we first formulate this problem of model selection and tile allocation as an Integer Linear Programming (ILP) instance, and then propose an approximation algorithm based on linear relaxation followed by randomized rounding to solve it. We present experimental results of our methods on an open source dataset based on trace-driven simulation to show that it gives result fast enough while also reducing execution time in a variety of scenarios.