Object detection from low-resolution embedded security camera lighting system

点击翻译按钮获取中文摘要

The video surveillance system of interest here is a smart light bulb with the embedded sound and security camera installed and wirelessly communicated. The collected video data can be used for smart home control and monitoring. The efficacy of such a system is highly dependent on our capabilities to automatically analyze and interpret the video data. Furthermore, a major concern in video surveillance systems is privacy. Therefore, the collected video needs to be blurred at the server side to prevent any identity recognition. The goal of this project is to develop advanced machine learning and video processing methods for automated object recognition from low-resolution blurred video surveillance data. A reliable solution to this problem will provide the partner company a unique tool in the field of smart video surveillance that ensures privacy while providing smart home management.