An occupancy distribution estimation method using the surveillance cameras in buildings

Occupancy distribution can not only help improve the energy efficiency of the buildings but also generate better evacuation plan under emergency. There are many techniques such as CO2 sensor network, radio frequency identification (RFID), ultra wideband (UWB), passive infrared (PIR) etc. that can be used to estimate the occupancy distribution. However, these methods require the extra installation of devices, which are expensive and impractical for large-scale deployment. In this paper, we propose an occupancy distribution estimation method using the surveillance cameras in buildings, requiring no further deployment of sensors. By processing the camera videos, the number of passing occupants at the entrance of a region will be recorded so that the occupancy distribution can be estimated. We tested our method in a real functioning building and the validity of our method is shown in the experiments.

[1]  Youtian Du,et al.  Measuring indoor occupancy in intelligent buildings using the fusion of vision sensors , 2013 .

[2]  Ali Yeon Md Shakaff,et al.  A robust multimedia surveillance system for people counting , 2017, Multimedia Tools and Applications.

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Zeyad Q. H. Al-Zaydi,et al.  An adaptive people counting system with dynamic features selection and occlusion handling , 2016, J. Vis. Commun. Image Represent..

[5]  Lei Huang,et al.  Robust people counting in video surveillance: Dataset and system , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[6]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[7]  Wei Yuan,et al.  SVM based people counting method in the corridor scene using a single-layer laser scanner , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[8]  Rui Zhang,et al.  An information technology enabled sustainability test-bed (ITEST) for occupancy detection through an environmental sensing network , 2010 .

[9]  Dileeka Dias,et al.  Smart building — Towards the insight remotely , 2016, 2016 International Conference on Internet of Things and Applications (IOTA).

[10]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Lun Jiang,et al.  SCOPES: Smart Cameras Object Position Estimation System , 2009, EWSN.

[12]  Sean P. Meyn,et al.  A sensor-utility-network method for estimation of occupancy in buildings , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[13]  Qing-Shan Jia,et al.  A Decentralized Stay-Time Based Occupant Distribution Estimation Method for Buildings , 2015, IEEE Transactions on Automation Science and Engineering.

[14]  Qing-Shan Jia,et al.  A review of occupant behavior models in residential building: Sensing, modeling, and prediction , 2016, 2016 Chinese Control and Decision Conference (CCDC).

[15]  Qing-Shan Jia,et al.  Estimation of occupant distribution by detecting the entrance and leaving events of zones in building , 2012, 2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[16]  Qing-Shan Jia,et al.  A three-level human movement model in the whole building scale , 2016, 2016 12th IEEE International Conference on Control and Automation (ICCA).

[17]  Xiaolan Xie,et al.  A dual-infrared sensing system for occupant distribution estimation in buildings , 2014, 2014 IEEE International Conference on Automation Science and Engineering (CASE).

[18]  Han Zou,et al.  An RFID indoor positioning system by using weighted path loss and extreme learning machine , 2013, 2013 IEEE 1st International Conference on Cyber-Physical Systems, Networks, and Applications (CPSNA).