WAVE: Edge-Device Cooperated Real-Time Object Detection for Open-Air Applications

Abstract

CNN based real-time object detection can facilitate various AI applications that need to understand the surroundings via camera, such as autonomous package delivery robots, augmented reality, and intelligent drone applications. Currently, due to the high computation cost of CNN, accurate real-time object detection is only possible when mobile devices can upload video frames to powerful edge servers through high-speed wireless networks like WiFi. However, for many open-air AI applications, the network conditions (such as cellular networks) are usually unfavorable, far from satisfying the network demands of state-of-the-art systems. In this paper, we focus on the challenges incurred by mobile communication networks and propose WAVE containing three novel techniques, which are Deep RoI Encoding, Prioritized Parallel Offloading and Fine-grained Offloading Strategy, to realize real-time, robust and low-cost object detection for open-air AI applications. The experimental results show that under LTE networks, WAVE can improve the detection accuracy of the object detection tasks and the face recognition tasks by 19.35%-33.61%, keep the offloading latency under 33ms, and save up to 90% data traffic.