Cloud-based computer vision for consumer video monitoring application

点击翻译按钮获取中文摘要

Availability of inexpensive video cameras, easy accessibility of internet, advancement in automated video processing/computer vision and emergence of cloud computing have contributed to the opportunity to create this research proposal. This research proposes cost efficient ways for automated consumer video monitoring. The proposed monitoring system would consist of webcams or IP cameras for home or small business monitoring. Motion events will be automatically detected and classified into different categories. Categorized motion events will be stored on a cloud platform. The user will have the capability to browse through these events, much like browsing recorded TV programs on a PVR. The uniqueness of this research provides flexibility to the user to define motion events or event categories. Real-time and accurate computer vision and automated image and video analysis algorithms will run on the cloud platform to achieve this feat.