Group Member: Kai Zhang, Tande Chen @ Stevens Institute of Technology
Supervisor: Dr. Kevin Lu @ Stevens Institute of Technology
"I pledge my honor that I have abided by the Stevens Graduate Student Code of Academic Integrity"
Keywords: IoT; Computer Vision; Deep Learning; TensorFlow; Part Affinity Fields (PAFs); Smart Security & Surveillance.
The security and surveillance industry is changing, and solutions have moved far past basic alarm monitoring. Live video surveillance and other remote security features have increased visibility for organizations that want to safeguard their people, assets, and buildings. The Internet of Things (IoT) is helping create safer cities, homes, and businesses by enabling both private and public organizations to securely and remotely monitor facilities and public spaces in real-time with smart security and surveillance solutions.
The greatest benefit of using IoT solutions for security system is the ability to prevent the loss of critical assets. IoT security solutions allow organizations to:
Security is a big factor in the emergence of smart home systems. With a sophisticated enough system, home security becomes a powerful tool that gives piece of mind and power to the user. Security systems are also a large deterrent for crime. The mere presence of a camera will put doubt in any criminals mind about committing a crime. There are already many security systems on the market available and in use today, however integrating the security system into the smart home gives the user a one stop access to everything in their home. If the smart home system integrates the smart phone into the system then this means that the user will always know the status of the security of their home.
The other issue concerns the supervision of empty-nesters, especially when children or caregivers are temporarily unavailable. Falls are serious and costly for elderly people. The Centers for Disease Control and Prevention of the US reports that millions of older people, 65 and older, fall each year at least once. Therefore, we hope to introduce a reasoning module, which formulates a number of measures to reason whether a person is fallen, into our Intelligent Surveillance System.
The principles of our system design are high reliability, low power consumption, small volume and low price. There are 4 main tasks in this system: