Initial investigations into using an ensemble of deep neural networks for building façade image semantic segmentation

Menglin Dai; Gregory Meyers; Danielle Densley Tingley; Martin Mayfield

doi:10.1117/12.2532828

2 October 2019 Initial investigations into using an ensemble of deep neural networks for building façade image semantic segmentation

Menglin Dai, Gregory Meyers, Danielle Densley Tingley, Martin Mayfield

Author Affiliations +

Proceedings Volume 11157, Remote Sensing Technologies and Applications in Urban Environments IV; 1115708 (2019) https://doi.org/10.1117/12.2532828
Event: SPIE Remote Sensing, 2019, Strasbourg, France

Abstract

Due to now outdated construction technology, houses which have not been retrofitted since construction typically fail to meet modern energy performance levels. However, identifying at a city scale which houses could benefit the most from retrofit solutions is currently a labour intensive process. In this paper, a system that uses a vehicle mounted camera to capture pictures of residential buildings and then performs semantic segmentation to differentiate components of captured buildings is presented. An ensemble of U-Net semantic segmentation models are trained to identify walls, roofs, chimneys, windows and doors from building façade images and differentiate between window and door instances which are partially visible or obscured. Results show that the ensemble of U-Net models achieved high accuracy in identifying walls, roofs and chimneys, moderate accuracy in identifying windows and low accuracy in identifying doors and instances of windows and doors which were partially visible or obscured. When U-Net models were retrained to identify doors or windows, irrespective of partially visible and obscured instances, a significant rise in door and window identification accuracy was observed. It is believed that a larger training dataset would produce significantly improved results across all classes. The results presented here prove the operational feasibility in the first part of a process to combine this model with high-resolution thermography and GPS for automating building retrofitting evaluations.

Conference Presentation

Citation Download Citation

Menglin Dai, Gregory Meyers, Danielle Densley Tingley, and Martin Mayfield "Initial investigations into using an ensemble of deep neural networks for building façade image semantic segmentation", Proc. SPIE 11157, Remote Sensing Technologies and Applications in Urban Environments IV, 1115708 (2 October 2019); https://doi.org/10.1117/12.2532828

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available