Along with Dr. Yoones Rezaei, CS faculty Dr. Stephen Lee and Dr. Daniel Mosse received a Best Paper Runner Up award from BuildSys 2021 for their paper "Deep Reinforcement Learning for Energy-efficient Parking Video Analytics Platform." Read the abstract for the paper here:
Advances in deep vision techniques and ubiquity of smart cameras will drive the next generation of video analytics. However, video analytics applications consume vast amounts of energy as both deep learning techniques, and cameras are power-hungry. In this paper, we focus on a parking video analytics platform and propose RL-CamSleep, a deep reinforcement learning-based technique, to actuate the cameras to reduce the energy footprint while retaining the system’s utility. Our key insight is that many video-analytics applications do not always need to be operational, and we can design policies to activate video analytics only when necessary. Moreover, our work is complementary to existing work that focuses on improving hardware and software efficiency. We evaluate our approach on a city-scale parking dataset having 76 streets spread across the city. Our analysis demonstrates how streets have various parking patterns, highlighting the importance of an adaptive policy. Our results show that our approach can learn such an adaptive policy that can reduce energy by 87.89% and achieve high accuracy of 98.65% in performing video analytics.