Parachute: Dynamic Resource-Aware Privacy-Preserving Video Analytics on Edge

Video analytics (VA) has become essential in applications, yet it poses significant challenges related to privacy preservation, network bandwidth, and computational resources. With the increasing deployment of high-definition cameras, privacy concerns and resource constraints are becoming critical barriers to the widespread adoption of VA systems. Existing privacy-preserving techniques are often static, inefficient, and fail to adapt to dynamic, real-time scenarios. In this article, we propose Parachute, a dynamic, resource-aware, and privacy-preserving VA system that adaptively switches between a local mode and a collaborative mode in response to traffic conditions. The system uses local reinforcement learning (RL) to enable each individual camera to operate independently, and switches to multiagent RL (MARL) for coordinated optimization when local resources become limited. Experiments on real-world datasets demonstrate that Parachute effectively balances detection accuracy and privacy protection, outperforming baseline methods under bandwidth constraints.