Facade labelling using neural networks

Facade labelling using neural networks

Kolenbrander, Thomas (TU Delft Electrical Engineering, Mathematics and Computer Science)
van Oort, Bart (TU Delft Electrical Engineering, Mathematics and Computer Science)
de Ruiter, Frank (TU Delft Electrical Engineering, Mathematics and Computer Science)
Yue, Tim (TU Delft Electrical Engineering, Mathematics and Computer Science)

van Gemert, J.C. (mentor)
Khademi, S. (mentor)
Visser, O.W. (graduation committee)
Wang, H. (graduation committee)

Delft University of Technology

Computer Science

2017-06-28

This report describes the process of the Bachelorproject(TI3806) done for ‘De Energiebespaarders’, a startup in Amsterdam striving to make homes more energy efficient through accessible advice and installation of insulation or solar panels. The goal of the project was to apply machine learning to improve their system for identifying house features; windows, doors, and walls, and calculate their surface areas to improve the advice they can give to customers. The old system could produce good results, but was time-consuming to use and sensitive in regard to user input. We chose to implement a new system that makes the process automatic. In the report, our design process and our chosen implementation is described. Our new system makes use of a convolutional neural network to give pixels a label of wall(blue), window(red), door(purple), or nothing(black), without the need for the user to click the individual features beforehand. The results are promising and can save a lot of time, but the results are still inconsistent at times. Therefore, the report also contains recommendations for improvement of this new system, as De Energiebespaarders have shown interest in further developing our system.

Machine Learning
Semantic Segmentation
neural networks
Load Balancing
De Energiebespaarders
Facade Labelling

http://resolver.tudelft.nl/uuid:8b7a82e1-9188-4b68-b582-2b5632e14501

Student theses

bachelor thesis

© 2017 Thomas Kolenbrander, Bart van Oort, Frank de Ruiter, Tim Yue