Open Access

ARTICLE

Enhancing Building Facade Image Segmentation via Object-Wise Processing and Cascade U-Net

Haemin Jung¹, Heesung Park², Hae Sun Jung³, Kwangyon Lee^4,*

1 Department of Industrial & Management Engineering, Korea National University of Transportation, Chungju, 27469, Republic of Korea
2 Department of Industrial Engineering, Yonsei University, Seoul, 03722, Republic of Korea
3 Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, 03063, Republic of Korea
4 School of Electronic Engineering, Soongsil University, Seoul, 06978, Republic of Korea

* Corresponding Author: Kwangyon Lee. Email:

Computers, Materials & Continua 2024, 81(2), 2261-2279. https://doi.org/10.32604/cmc.2024.057118

Received 08 August 2024; Accepted 07 October 2024; Issue published 18 November 2024

Abstract

The growing demand for energy-efficient solutions has led to increased interest in analyzing building facades, as buildings contribute significantly to energy consumption in urban environments. However, conventional image segmentation methods often struggle to capture fine details such as edges and contours, limiting their effectiveness in identifying areas prone to energy loss. To address this challenge, we propose a novel segmentation methodology that combines object-wise processing with a two-stage deep learning model, Cascade U-Net. Object-wise processing isolates components of the facade, such as walls and windows, for independent analysis, while Cascade U-Net incorporates contour information to enhance segmentation accuracy. The methodology involves four steps: object isolation, which crops and adjusts the image based on bounding boxes; contour extraction, which derives contours; image segmentation, which modifies and reuses contours as guide data in Cascade U-Net to segment areas; and segmentation synthesis, which integrates the results obtained for each object to produce the final segmentation map. Applied to a dataset of Korean building images, the proposed method significantly outperformed traditional models, demonstrating improved accuracy and the ability to preserve critical structural details. Furthermore, we applied this approach to classify window thermal loss in real-world scenarios using infrared images, showing its potential to identify windows vulnerable to energy loss. Notably, our Cascade U-Net, which builds upon the relatively lightweight U-Net architecture, also exhibited strong performance, reinforcing the practical value of this method. Our approach offers a practical solution for enhancing energy efficiency in buildings by providing more precise segmentation results.

---

Keywords

---