Strategic Way to Count the Number
of People in a Room Using Multiple
Kinect Cameras
Yuchen Liu, Sourav Chakraborty, Ashutosh Kumar, Rakesh Seal
and Sohang Sengupta
Abstract This paper proposes a system in which we use multiple Kinect cameras
placed in very strategic positions to accurately detect the presence of the number of
human beings present in a room and also keep a count of the number entering and
leaving the room. Banking physical security and enterprise data centre security are
some of the areas where such technologies can effectively make a difference in terms
of physical security practices and attendance.
Keywords Kinect camera · Face detection · OpenCV · Overhead camera · Deep
learning · Facenet · Computer vision · Convolutional neural network (CNN)
Y. Liu
Department of Electrical and Computer Engineering, Boston University, Boston, USA
e-mail: lyc@bu.edu
S. Chakraborty
Imperial College London Business School, London, UK
e-mail: sourav.chakraborty18@imperial.ac.uk
A. Kumar
Department of Information Technology, Institute of Engineering and Management, Kolkata, India
e-mail: iashu12966@gmail.com
R. Seal (B )
Department of Electronics and Communication Engineering, Institute of Engineering and
Management, Kolkata, India
e-mail: rakeshseal0@gmail.com
S. Sengupta
Department of Computer Science and Engineering, Institute of Engineering and Management,
Kolkata, India
e-mail: mailsohang@gmail.com
© Springer Nature Singapore Pte Ltd. 2020
M. Chakraborty et al. (eds.), Proceedings of International
Ethical Hacking Conference 2019, Advances in Intelligent
Systems and Computing 1065, https://doi.org/10.1007/978-981-15-0361-0_3
39