Abstract
This paper introduces an innovative computer vision-based method to improve demand-side management for reducing building energy consumption. Unlike traditional approaches, it accurately detects occupancy status using existing CCTV infrastructure. Advanced deep learning and computer vision techniques track and count people, informing a controlling strategy integrated with building systems. This method achieves a significant reduction of approximately 4% in energy consumption.
| Original language | English |
|---|---|
| Title of host publication | 2025 IEEE 34th International Symposium on Industrial Electronics, ISIE 2025 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798350374797 |
| DOIs | |
| State | Published - 2025 |
| Event | 34th IEEE International Symposium on Industrial Electronics, ISIE 2025 - Toronto, Canada Duration: 20 Jun 2025 → 23 Jun 2025 |
Publication series
| Name | IEEE International Symposium on Industrial Electronics |
|---|---|
| ISSN (Print) | 2163-5137 |
| ISSN (Electronic) | 2163-5145 |
Conference
| Conference | 34th IEEE International Symposium on Industrial Electronics, ISIE 2025 |
|---|---|
| Country/Territory | Canada |
| City | Toronto |
| Period | 20/06/25 → 23/06/25 |
Bibliographical note
Publisher Copyright:© 2025 IEEE.
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 7 Affordable and Clean Energy
Keywords
- Computer Vision
- Convolutional Neural Network
- Deep Learning
- Demand Response
- Demand Side Management
- Single Shot Detector
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
Fingerprint
Dive into the research topics of 'Computer Vision-Based Approach for Energy Efficiency in Commercial Buildings'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver