Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Generation of BIM data based on the automatic detection, identification and localization of lamps in buildings

Francisco Troncoso-Pastoriza, Pablo Eguía-Oller, Rebeca P. Díaz-Redondo, Enrique Granada-Álvarez

TL;DR

The paper tackles automatic detection, identification, and localization of building lamps to populate BIM-based energy models for improved lighting energy management. It proposes a fast, edge-driven pipeline consisting of model registration, pose candidate extraction (blob detection, shape estimation, pose estimation, filtering), and pose/model selection with Fast Directional Chamfer Matching, followed by refinement via Direct Directional Chamfer Optimization and robust 3D pose processing. The system demonstrates high accuracy (96.9% correct lamp identifications within 10 m) and substantial computational savings (ROI-focused processing reducing the most costly step to a fraction of its original time), enabling near-real-time operation and seamless BIM integration through gbXML. Practically, the approach supports automatic lighting inventory and state integration into BIM, facilitating energy-efficient building management and faster BIM-based simulations; future work includes more lamp models and extending to thermal imaging for broader coverage.

Abstract

In this paper we introduce a method that supports the detection, identification and localization of lamps in a building, with the main goal of automatically feeding its energy model by means of Building Information Modeling (BIM) methods. The proposed method, thus, provides useful information to apply energy-saving strategies to reduce energy consumption in the building sector through the correct management of the lighting infrastructure. Based on the unique geometry and brightness of lamps and the use of only greyscale images, our methodology is able to obtain accurate results despite its low computational needs, resulting in near-real-time processing. The main novelty is that the focus of the candidate search is not over the entire image but instead only on a limited region that summarizes the specific characteristics of the lamp. The information obtained from our approach was used on the Green Building XML Schema to illustrate the automatic generation of BIM data from the results of the algorithm.

Generation of BIM data based on the automatic detection, identification and localization of lamps in buildings

TL;DR

The paper tackles automatic detection, identification, and localization of building lamps to populate BIM-based energy models for improved lighting energy management. It proposes a fast, edge-driven pipeline consisting of model registration, pose candidate extraction (blob detection, shape estimation, pose estimation, filtering), and pose/model selection with Fast Directional Chamfer Matching, followed by refinement via Direct Directional Chamfer Optimization and robust 3D pose processing. The system demonstrates high accuracy (96.9% correct lamp identifications within 10 m) and substantial computational savings (ROI-focused processing reducing the most costly step to a fraction of its original time), enabling near-real-time operation and seamless BIM integration through gbXML. Practically, the approach supports automatic lighting inventory and state integration into BIM, facilitating energy-efficient building management and faster BIM-based simulations; future work includes more lamp models and extending to thermal imaging for broader coverage.

Abstract

In this paper we introduce a method that supports the detection, identification and localization of lamps in a building, with the main goal of automatically feeding its energy model by means of Building Information Modeling (BIM) methods. The proposed method, thus, provides useful information to apply energy-saving strategies to reduce energy consumption in the building sector through the correct management of the lighting infrastructure. Based on the unique geometry and brightness of lamps and the use of only greyscale images, our methodology is able to obtain accurate results despite its low computational needs, resulting in near-real-time processing. The main novelty is that the focus of the candidate search is not over the entire image but instead only on a limited region that summarizes the specific characteristics of the lamp. The information obtained from our approach was used on the Green Building XML Schema to illustrate the automatic generation of BIM data from the results of the algorithm.
Paper Structure (18 sections, 11 equations, 20 figures, 4 tables, 1 algorithm)

This paper contains 18 sections, 11 equations, 20 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Model registration
  5. Extraction of pose candidates
  6. Blob detection
  7. Shape estimation
  8. Pose estimation and filtering
  9. Pose and model selection
  10. Pose refinement and scoring
  11. 3D pose processing
  12. Automatic inclusion of lighting information in BIM
  13. Results
  14. Individual images
  15. Computational cost
  16. ...and 3 more sections

Figures (20)

  • Figure 1: Outline of the detection and location method.
  • Figure 2: Blob detection process.
  • Figure 3: Normalized and smoothed histogram and threshold values for multiple images with different contents.
  • Figure 4: Binary images resulting from the threshold operation with different values.
  • Figure 5: Outline of the pose filters used to discard false positives based on the supposed camera orientation and distance range.
  • ...and 15 more figures