Low-Cost Image-Based Occupancy Sensor Using Deep Learning

T. M. Sanjeev Kumar, Susan G. Varghese, Ciji Pearl Kurian, Mouli Chandra Mouli

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.

Original languageEnglish
Title of host publicationAdvances in Renewable Energy and Electric Vehicles - Select Proceedings of AREEV 2020
EditorsSanjeevikumar Padmanaban, Nagesh Prabhu, Suryanarayana K.
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages14
ISBN (Print)9789811616419
Publication statusPublished - 2022
EventInternational Conference on Advances in Renewable Energy and Electric Vehicles, AREEV 2020 - Nitte, India
Duration: 22-12-202023-12-2020

Publication series

NameLecture Notes in Electrical Engineering
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119


ConferenceInternational Conference on Advances in Renewable Energy and Electric Vehicles, AREEV 2020

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering


Dive into the research topics of 'Low-Cost Image-Based Occupancy Sensor Using Deep Learning'. Together they form a unique fingerprint.

Cite this