TY - GEN
T1 - Low-Cost Image-Based Occupancy Sensor Using Deep Learning
AU - Sanjeev Kumar, T. M.
AU - Varghese, Susan G.
AU - Kurian, Ciji Pearl
AU - Chandra Mouli, Mouli
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - An occupancy sensor is going to be an integral part of smart buildings for energy efficiency as well as for providing human-centric lighting. This paper presents a low-cost image-based alternative for conventional occupancy sensors using deep learning. The developed system works as a standalone unit and can integrate with heating, ventilation and air conditioning (HVAC) and lighting control schemes. Here, a Raspberry Pi 3B + is utilized as the hub for occupancy detection. Single-shot multi-box detection (SSD) is used as the primary architecture and is compared with you only look once (YOLO), the test results are computed for several test rooms, and an evaluation of the practical requirements in terms of camera and images captured for accurate detections is measured based on positives obtained. Here, a low-cost system is designed which avoids the use of multiple sensors and is most suitable for offices and libraries, and classrooms.
AB - An occupancy sensor is going to be an integral part of smart buildings for energy efficiency as well as for providing human-centric lighting. This paper presents a low-cost image-based alternative for conventional occupancy sensors using deep learning. The developed system works as a standalone unit and can integrate with heating, ventilation and air conditioning (HVAC) and lighting control schemes. Here, a Raspberry Pi 3B + is utilized as the hub for occupancy detection. Single-shot multi-box detection (SSD) is used as the primary architecture and is compared with you only look once (YOLO), the test results are computed for several test rooms, and an evaluation of the practical requirements in terms of camera and images captured for accurate detections is measured based on positives obtained. Here, a low-cost system is designed which avoids the use of multiple sensors and is most suitable for offices and libraries, and classrooms.
UR - http://www.scopus.com/inward/record.url?scp=85115168027&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115168027&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-1642-6_22
DO - 10.1007/978-981-16-1642-6_22
M3 - Conference contribution
AN - SCOPUS:85115168027
SN - 9789811616419
T3 - Lecture Notes in Electrical Engineering
SP - 277
EP - 290
BT - Advances in Renewable Energy and Electric Vehicles - Select Proceedings of AREEV 2020
A2 - Padmanaban, Sanjeevikumar
A2 - Prabhu, Nagesh
A2 - K., Suryanarayana
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference on Advances in Renewable Energy and Electric Vehicles, AREEV 2020
Y2 - 22 December 2020 through 23 December 2020
ER -
