RAVIP: Real-Time AI Vision Platform for Heterogeneous Multi-Channel Video Stream

Object detection techniques based on deep learning such as YOLO have high detection performance andprecision in a single channel video stream. In order to expand to multiple channel object detection in real-time,however, high-performance hardware is required. In this paper, we propose a novel back-end server framework,a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel tosimultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assemblesappropriate component modules from the RODEM (real-time object detection module) Base to create perchannelinstances for each channel, enabling efficient parallelization of object detection instances on limitedhardware resources through continuous monitoring with respect to resource utilization. Through practicalexperiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performingobject detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provideobject detection services with 25 FPS for all 16 channels at the same time. KCI Citation Count: 0