Searched for:
(1 - 20 of 56)

Pages

document
Li, Xin (author)
Visual context plays a key role in many computer vision tasks, and performance of eye/gaze-tracking methods also benefit from it. However, the size of contextual information (e.g. full face image) is very large w.r.t the primary input i.e. cropped image of the eye. This adds large computational costs to the algorithm and makes it inefficient,...
master thesis 2019
document
Graur, Dan (author)
Given the increasing popularity of Machine Learning, and the ever increasing need to solve larger and more complex learning challenges, it is unsurprising that numerous distributed learning strategies have been brought forward in recent years, along with many large scale Machine Learning frameworks. It is however unclear how well these...
master thesis 2019
document
Wang, Yizhou (author)
In the past few years, convolutional neural networks (CNNs) have been widely utilized and shown state-of-the-art performances on computer vision tasks. However, CNN based approaches usually require a large amount of storage, run-time memory, as well as computation power in both training and inference time, which are usually used on GPU based...
master thesis 2019
document
Elghlan, Faris (author)
This M.Sc. thesis report investigates the application of one-class classification techniques to complex high-dimensional data. The aim of a one-class classifier is to separate target data from non-target data, but only a dataset containing target data is available for training. The issue with high-dimensional data is that it is difficult to...
master thesis 2019
document
Friđriksdóttir, Esther (author)
Physical activity and mobility are important indicators of the recovery process of patients in the general ward of the hospital. Currently, monitoring mobility of hospitalized patients relies largely on direct observation from the caregivers. Accelerometers have the potential to quantify physical activity of patients objectively and without...
master thesis 2019
document
Batheja, Dhruv (author)
This work tackles the problem of repetition counting in videos using modern deep learning techniques. For this task, the intention is to build an end-to-end trainable model that could estimate the number of repetitions without having to manually intervene with the feature selection process. The models that exist currently perform well on videos...
master thesis 2019
document
Klip, Roy (author)
The amount of personal imagery kept on (mobile) devices is increasing by the day. Analysis and organization of these large collections of data are becoming increasingly important in the field of digital forensics, as they can aid in the search for legal evidence. The grouping of faces based on their identity is an important aspect as it provides...
master thesis 2019
document
Ai, Zhiwei (author)
Deep learning methods have been demonstrated to be promising in semantic segmentation of point clouds. Existing works focus on extracting informative local features based on individual points and their local neighborhood. They lack consideration of the general structures and latent contextual relations of underlying shapes among points. To this...
master thesis 2019
document
Sun, Wei (author)
This work applies keypoint detection method to solve gate recognition problem. Unlike regular object detection task, gate recognition problem is made difficult by the fact that gate is empty wireframe which means that the object surrounded by gate-edge is not relevant and should not be taken into consideration when detecting. However, regular...
master thesis 2019
document
El Doori, Isa (author)
The ability to locate specific objects within images is an essential step in various computer vision based engineering applications. Image segmentation is the task of dividing an image into "segments" that are uniform as well as homogeneous with respect to some characteristics, for example grey tone or texture as in Haralick et al. This thesis...
master thesis 2019
document
Arnaoutis, Vasos (author)
Deep Learning performance dependents on the application and methodology. Neural Networks with convolutional layers have been a great success in multiple tasks trained under Supervised Learning algorithms. For higher dimensional problems, the selection of a deep network architecture can significantly improve the accuracy of the network, however...
master thesis 2019
document
YANG, MINGHAO (author)
One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an overparameterized network. However, there are two issues associated with most one-shot NAS methods. First, dependencies...
master thesis 2019
document
van der Meer, Remco (author)
Recent works have shown that neural networks can be employed to solve partial differential equations, bringing rise to the framework of physics informed neural networks.The aim of this project is to gain a deeper understanding of these novel methods, and to use these insights to further improve them. We show that solving a partial differential...
master thesis 2019
document
Mulder, Boris (author)
Very complex flows can be expensive to compute using current CFD techniques. In this thesis, models based on deep learning were used to replace certain parts of the flow domain, with the objective of replacing well-known regions with simplified models to increase efficiency. To keep the error produced by the deep learning model bounded, a...
master thesis 2019
document
Priadi Teguh Wibowo, Priadi (author)
Visualizing runners trajectory from video data is not straightforward because the video data does not contain the explicit information of which runners appear in the video. Only the visual information related to the runner, such as runner’s unique ID (called bib number), is available. To this end, we propose two automatic runner detection...
master thesis 2019
document
Hendrix, Ward (author)
In common Dutch cardiac care, patients only have few follow-up meetings with their cardiologists after they have been treated at the hospital. Sometimes, they have to wait several months for their next visit. Therefore, patients often turn to online platforms where they can ask questions to other patients or healthcare professionals, namely...
master thesis 2019
document
Boehmer, Daniël (author)
Wind energy plays a major role in the ongoing energy transition. To accelerate the adoption of wind energy and thereby the energy transition, the Levelized Cost of Energy (LCOE) has to be minimized. Apart from increasing turbine performance, reducing turbine down-time can contribute to lowering the LCOE.Down-time is defined as time during which...
master thesis 2019
document
Sankararaman, Shyam Prasadh (author)
Hyperspectral imaging (HSI) is a promising imaging modality in medical applications, especially for non-invasive and non-contact disease diagnosis and image-guided surgery. Encoding both spatial and spectral information, it can detect subtle changes in the biochemical and morphological properties of a tissue, revealing the early progression of a...
master thesis 2019
document
Deichler, Anna (author)
Recently, the AlphaGo algorithm has managed to defeat the top level human player in the game of Go. Achieving professional level performance in the game of Go has long been considered as an AI milestone. The challenging properties of high state-space complexity, long reward horizon and high action branching factor in the game of Go are also...
master thesis 2019
document
Jargot, Dominik (author)
Nowadays, autonomous driving is a trending topic in the automotive field. One of the most crucial challenges of autonomous driving research is environment perception. Currently, many techniques achieve satisfactory performance in 2D object detection using camera images. Nevertheless, such 2D object detection might be not sufficient for autonomous...
master thesis 2019
Searched for:
(1 - 20 of 56)

Pages