Related Experiment Video
Updated: Aug 10, 2026
10:35
Bringing the Visible Universe into Focus with Robo-AO
Published on: February 12, 2013
19.4K
Intelligent Monitoring and Visualization System for High Building Nighttime Utilization Based on Image Processing
Yuanrong He1,2, Xianhui Yu1, Qihao Liang1
1Big Data Institute of Digital Natural Disaster Monitoring in Fujian, Xiamen University of Technology, Xiamen 361024, China.
Sensors (Basel, Switzerland)
|November 9, 2024
Summary
This study introduces a novel algorithm using light brightness for nighttime occupancy detection in university buildings, achieving 98.67% accuracy. This method enhances campus safety and energy efficiency without new sensors.
Area of Science:
- Building Management
- Computer Vision
- Geographic Information Systems (GIS)
Background:
- Complex high-rise buildings, particularly university laboratories, present challenges in nighttime supervision, increasing accident risks and impacting campus sustainability.
- Current occupancy detection methods like environmental sensors are costly and offer limited coverage, making them impractical for large campuses.
- Surveillance cameras, already part of campus infrastructure, offer a viable alternative for wide-area monitoring.
Purpose of the Study:
- To develop an efficient and cost-effective method for nighttime occupancy detection in complex buildings.
- To enhance campus building safety and energy efficiency through accurate occupancy monitoring.
- To integrate occupancy data with a 3D GIS model for improved spatiotemporal analysis and visualization.
Main Methods:
- A detection algorithm was designed to assess nighttime building use by analyzing light brightness captured by surveillance cameras.
- A comprehensive 3D GIS model was developed using a hierarchical "building-floor-room" structure, incorporating oblique photogrammetry and laser scanning.
- Occupancy detection results were combined with the 3D GIS data for visualization and analysis.
Main Results:
- The light brightness-based algorithm achieved an average accuracy of 98.67% for nighttime occupancy detection.
- The system enables large-scale occupancy detection without the need for additional sensor installation.
- The integrated 3D GIS model provides a refined spatiotemporal representation of complex buildings.
Conclusions:
- The developed algorithm offers a highly accurate and scalable solution for nighttime occupancy detection in campus buildings.
- Utilizing existing surveillance cameras reduces costs and improves the efficiency of building management.
- The 3D GIS integration provides a novel framework for visualizing and analyzing building occupancy, applicable to various environments.
