Heat Mapping Drones: An Autonomous Computer-Vision-Based Procedure for Building Envelope Inspection Using Unmanned Aerial Systems (UAS)

Tarek Rakha, Amanda Liberty, Alice Gorodetsky, Burak Kakillioglu, Senem Velipasalar

Research output: Contribution to journalArticlepeer-review

52 Scopus citations

Abstract

Comprehensive and accurate energy audits are essential to maximize energy savings and improvements in buildings realized from the design and implementation of deep retrofits for building envelopes. This paper presents a methodology for employing drones to conduct rapid building envelope performance diagnostics and perform aerial mapping of energy flows. The presented framework is tested on the Syracuse University campus to showcase: (1) visually identifying areas of thermal anomalies using an Unmanned Aerial System (UAS) equipped with thermal cameras and (2) detailed inspection applied to areas of high interest to quantify envelope heat flow using computer-vision techniques. Overall precision and recall rates of 76% and 74% were achieved, respectively. A discussion of the findings suggests refining procedure accuracy as a step toward automated envelope inspection.

Original languageEnglish (US)
Pages (from-to)30-44
Number of pages15
JournalTechnology Architecture and Design
Volume2
Issue number1
DOIs
StatePublished - 2018

ASJC Scopus subject areas

  • Architecture
  • Visual Arts and Performing Arts
  • Urban Studies

Fingerprint

Dive into the research topics of 'Heat Mapping Drones: An Autonomous Computer-Vision-Based Procedure for Building Envelope Inspection Using Unmanned Aerial Systems (UAS)'. Together they form a unique fingerprint.

Cite this