Smart Sensing for HVAC Control: Collaborative Intelligence in Optical and IR Cameras

被引:40
作者
Cao, Ningyuan [1 ]
Ting, Justin [1 ]
Sen, Shreyas [2 ]
Raychowdhury, Arijit [1 ]
机构
[1] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
[2] Purdue Univ, Sch Elect & Comp Engn, W Lafayette, IN 47907 USA
关键词
Data fusion; energy savings; heating; ventilation; and cooling (HVAC) control; occupancy detection; SYSTEM; VIDEO;
D O I
10.1109/TIE.2018.2818665
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Energy management of heating, ventilation, and cooling (HVAC) has become a primary concern for residential and commercial buildings. In order to save energy without compromising the comfort of occupants, various techniques have been explored to sense the real-time occupancy/vacancy of HVAC zones. Among all these approaches, wireless-camera-based sensing stands out for its potential application in surveillance and security in addition to energy management. However, limited lifetime and detection accuracy have prevented pervasiveness of wireless-camera-based occupancy detection. This paper presents a novel wireless device platform and prototype development that incorporates an infrared (IR) camera with an optical (OP) camera to provide collaborative intelligence at low power and enhanced accuracy. Compared to the single sensor baseline design, the proposed fusion-based OP/IR design demonstrates 5x miss rate improvement, 5x reduction in false positive rate, and 3 x lifetime extension for battery usage with respect to a single-sensor-based design. Compared to a programmed thermostat and schedule based HVAC control, the design saves a maximum of 26% of HVAC energy.
引用
收藏
页码:9785 / 9794
页数:10
相关论文
共 27 条
[1]  
Agarwal Y., 2010, P 2 ACM WORKSH EMB S, P1, DOI DOI 10.1145/1878431.1878433
[2]  
[Anonymous], 2010, SENSYS 2010 PROC 8 A, DOI DOI 10.1145/1869983.1870005
[3]  
[Anonymous], 2014, BUILDINGS OVERVIEW C
[4]  
Cao N., 2017, 2017 IEEE SENSORS, P1, DOI DOI 10.1109/ICSENS.2017.8234091
[5]   Self-Optimizing IoT Wireless Video Sensor Node With In-Situ Data Analytics and Context-Driven Energy-Aware Real-Time Adaptation [J].
Cao, Ningyuan ;
Bin Nasir, Saad ;
Sen, Shreyas ;
Raychowdhury, Arijit .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2017, 64 (09) :2470-2480
[6]  
Chowdary MK, 2013, 2013 INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND SIGNAL PROCESSING (ICCSP), P1032, DOI 10.1109/iccsp.2013.6577213
[7]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[8]   Logistic regression and artificial neural network classification models: a methodology review [J].
Dreiseitl, S ;
Ohno-Machado, L .
JOURNAL OF BIOMEDICAL INFORMATICS, 2002, 35 (5-6) :352-359
[9]  
Erickson V. L., 2011, Proceedings 2011 10th International Conference on Information Processing in Sensor Networks (IPSN 2010), P258
[10]  
Hall DL, 1997, P IEEE, V85, P6, DOI 10.1109/ISCAS.1998.705329