Exploring Training Pair-Generation Strategies for Deep Metric Learning for Floor Plan Retrieval

Existing content-based image retrieval models work well for natural photos, but not for images of architectural floor plans. <br/>Previous work on floor plan retrieval has focused on graph-based methods, rather than image-based floor plans.<br/>Training a CNN-based representation learning framework on segmented floor plan images with standard...

IAmHOME: Transforming an existing house into a smart house to provide for the well-being of its residents

This thesis investigates the transition of traditional houses into Smart Homes, emphasizing the improvement of residents’ well-being, particularly for those aged 50 to 60. It is set against the rapid growth of Smart Home Devices enabled by the Internet of Things, facilitating easy control and monitoring of home features. There has been a...

Object Detection in Illustrated Imagery

In contrast to the prevalent focus on real photos in computer vision research, we present a contribution by making the Ot &amp; Sien dataset machine learning-ready for object detection tasks in illustrations. We refer to the new dataset as Ot &amp; Sien++ that is composed of scanned images of children’s book illustrations, thereby venturing into...

Digital Ornaments: The Crossover of Digital Technology & Contemporary Ornamentation

The use of artificial intelligence (AI), digital tools and fabrication technologies in architecture has followed a paradigm shift, enhancing its design and construction processes and performances. While it has enhanced the performability and efficiency aspects of architecture, it has removed the aesthetics and symbolism of ornamentation and...

Learning to Reconstruct Compact Building Models from Point Clouds

Three-dimensional building models play a pivotal role in shaping the digital twin of our world. With the advance of sensing technologies, unprecedented data acquisition capabilities on capturing the built environment have surfaced, with photogrammetry and light detection and ranging being the two important sources, both of which can acquire...

Unsupervised Cross Domain Image Matching with Outlier Detection

This work proposes a method for matching images from different domains in an unsupervised manner, and detecting outlier samples in the target domain at the same time. This matching problem is made difficult by i) the different domain images that are related but under different conditions (e.g. photos of the same location captured in different...

Facade labelling using neural networks

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...

Heart Rate Monitoring using Adaptive Noise Cancellation: 2015-2016 Q4

Heart Rate Monitoring Using PPG Signals

Monitoring the heart rate using PPG signals that is worn on the wrist has the downside that it is susceptible to motion. The device on the wrist moves along with the motions of the arm, consequently creating artifacts in the measurement. There are many signal processing techniques that can remove these artifacts. This thesis discusses one of the...

Heart rate monitoring using PPG signals

This bachelor’s thesis discusses the idea and implementation of real-time heart rate monitoring using photo- plethysmography (PPG) signals. PPG signals measured from the wrist are often subjected to distortion and noise. Signal processing techniques that tackle these issues were investigated and implemented. The algo- rithm of choice was JOSS....

Sound Reflections in an audio-based game for visually impaired children

In this thesis a model for sound reflections designed which is to be used in an audio-based game for visually impaired people is described. This project is a part of a three-group bachelor graduation project of six peoplein total. The three groups combined create a working game for visually impaired children, meant to be used to train the user’s...

Sound localization in audio-based games for visually impaired children

This thesis describes the design of a sound localization algorithm in audio-based games for visually impaired children. An algorithm was developed to allow real-time audio playback and manipulation, using overlapping audio blocks multiplied by a window function. The audio signal was played through headphones. Multiple sound localization cues are...

Audio-based game for visually impaired children

This thesis was made for the Bachelor Graduation Project (Electrical Engineering). The purpose of the project was to design an audio-based game for visually impaired children. In this thesis the gameplay and the graph- ical user interface are designed. We choose to make a simplified dungeon crawler in the programming language Python. We designed...