Smart surveillance is getting increasingly popular as technologies become easier to use and cheaper. Traditional surveillance records video footage to a storage device continuously. However, this generates enormous amount of data and reduces the life of the hard drive. Newer devices with Internet connection save footage to the Cloud. This feature comes with bandwidth requirements and extra Cloud costs. In this paper, we propose a deep learning based, distributed, and scalable surveillance architecture using Edge and Cloud computing. Our design reduces both the bandwidth and as well as the Cloud costs significantly by processing footage prior sending to the Cloud.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL