ACQUAL
Operational land cover mapping in Africa using machine learning and multi-source datasets

The overall goal of this MSc thesis is to develop a scalable machine learning solution for mapping land cover classes in Africa. For this purpose, we will use the LandCoverNet training samples shared on the Radiant Earth Foundation ML...

Look at Topic
ACQUAL
2D outlining of buildings using airborne point cloud data and deep learning

Literature review on 2D outlining of buildings, and delineating techniques using deep learning. Implement suitable deep learning network, generate training data and 2D outlines on dense point clouds of buildings. Analyze 2D outlines,...

Look at Topic
ACQUAL
Analysis and processing of mobile mapping data (LIDAR, RGB) in railroad environment

Machine/deep learning approaches for sensor fusion, object detection, object classification, and object localization methods applied on RGB images and 3D point clouds. Reporting to both the university (MSc research) and the company...

Look at Topic
ACQUAL
Area-to-point geographically weighted regression kriging for downscaling MODIS images

To gain both spectral and spatial advantage, this study develops a framework of area-to-point geographically weighted regression kriging to downscale MODIS images. The methodology combines deterministic and stochastic modelling. The...

Look at Topic
FORAGES, ACQUAL
Assessing and reconstructing historical forest structural characteristics using various Remote sensing sources in old growth forests in the Rhodopi mountains, Bulgaria

The key objective of the project in Bulgaria with which this topic is associated, is to translate the output of scenarios of future forest management and climate change into decision support information to improve habitat suitability for...

Look at Topic
ACQUAL
Automatic extraction of agricultural field polygons with a deep learning framework

For this MSc research topic, the student will resort to deep learning methods based on convolutional neural networks to investigate agricultural fields' delineation [1], [2]. These methods allow us to effectively learn the...

Look at Topic
ACQUAL, PLUS
COVID-19, Water, Sanitation and Hygiene (WASH), and Disaster Risk Reduction. Where are the links?

To analyze the links between (1) COVID-19 and WASH; (2) WASH and natural disasters/vulnerability to disasters/disaster risk reduction; and (3) Natural disasters/vulnerability to disasters/disaster risk reduction and COVID-19. To evaluate...

Look at Topic
ACQUAL
COVID19 - who is really affected when and where and what are the impacts?

Review the literature. Examine spatial and temporal trends of covid19. Characterize these trends and assess the short-term and long term affects for different regions. To do so will require the integration of different geographies and...

Look at Topic
ACQUAL
Changing COVID-19-related risk perceptions and hygiene behaviours across space and time

To understand individuals’ changing COVID-19-related risk perceptions across space and time. To identify major determinants for changes in risk perceptions and hygiene behaviours. To assess the implications of risk perceptions on...

Look at Topic
ACQUAL
Comparing Water, Sanitation and Hygiene (WASH) in Ancient and Modern Rome. What have we learnt in more than 2000 years?

To analyze the WASH and (ill)health situation in (1) ancient and (2) modern Rome. To compare the ancient and modern scenarios against each other, considering population growth and density, settlement structure, and other factors. To...

Look at Topic
ACQUAL
Deep Learning based fusion of SAR and optical data to synthesize cloud-free and enhanced quality imagery

The student will initially revise the literature on deep generative networks, on image synthesis, and on deep learning based image fusion. The main focus will be on methods that are able to compose an efficient end-to-end trained system....

Look at Topic
ACQUAL
Deep Learning based multisource data fusion for biomass estimation

The student will initially revise the literature on biomass estimation and on multimodal deep learning models. The main focus will be on developing an end-to-end trainable multimodal/multi-path deep neural network composed of multiple...

Look at Topic
ACQUAL
Deep Learning based multisource data fusion for detecting deforestation

The overall goal of this research is to develop deep learning based methods to compose a multimodal classifier for detecting changes on Land Use and Land Cover, especially those changes caused by the suppression of the vegetation...

Look at Topic
ACQUAL
Deep Learning for Dense Image Matching

The student will initially revise the existing literature on image matching algorithms using CNN as backbone. The use of already existing code and available datasets to train these algorithms will be the starting point of the work. As...

Look at Topic
ACQUAL
Deep learning algorithms for building opening detection from UAV images

The student will initially revise the existing literature on single stage and two-stage detectors. The proposed network will predict the bounding boxes of openings in UAV images. Some datasets of understanding façade such as CMP-base...

Look at Topic
ACQUAL
Deep learning algorithms for single image depth estimation from UAV images

The student will initially revise the existing literature on the SIDE algorithms. The use of already existing code and available datasets to train these algorithms will be the starting point of the work. The UAV datasets will be...

Look at Topic
ACQUAL
Deep learning for glacier area mapping and facies classification

There is a long list of glacier surface characteristics which can be mapped from optical and SAR remote sensing. In this research thesis, the student will investigate deep learning techniques for automatically extracting the glacier...

Look at Topic
ACQUAL
Deep learning for the classification of water and bridges in Airborne Laser Scanner data

Key challenge in this research is to find out different strategies to improve the classification of water and bridges.

Look at Topic
ACQUAL
Detection and classification of objects with machine/deep learning for asset management in buildings

Machine/deep learning approaches for object detection, object classification, and object localization methods applied mainly on RGB images (and optionally on 3D point clouds)

Look at Topic
ACQUAL
Detection of gradual changes in seasonal phenomena using time series analysis

Methods using seasonal time series to classify crops exist, for example dynamic time warping (DTW). Methods to find sudden changes in time series with or without added seasonal patterns exist as well, for example B-FAST. Using these...

Look at Topic
ACQUAL
Development of a spatially explicit active learning method for crop areas mapping from satellite image time series

The overall goal of this MSc research is to develop spatially explicit active learning methods for crop areas mapping from satellite images time series. Different spatial information, e.g. geographic distance between samples or pattern,...

Look at Topic
ACQUAL
Development of a spatially explicit active learning method for crop areas mapping from satellite image time series and auxiliary datasets

The overall goal of this MSc research is to develop spatially explicit active learning methods for crop areas mapping from satellite images time series and auxiliary data. Different spatial information, e.g. geographic distance between...

Look at Topic
ACQUAL
Development of unsupervised or weakly supervised Deep Learning methods for cloud detection

The student will initially revise the literature on unsupervised and weekly supervised deep networks, and on cloud detection methods. The main focus will be on methods that are able to compose an efficient end-to-end trained system, and...

Look at Topic
ACQUAL, PLUS
Digital twins /3D city modelling. (the topic has several possible directions)

This research will focus on applying innovative methods (in some cases machine learning), integration of different 3D data for creation and applications of Digital Twins/3D city models. There are several possible...

Look at Topic
ACQUAL
Feasibility of RGB-D Visual SLAM for accurate indoor point cloud creation

Intel® RealSense™ depth camera D435i, i.e., the combination of an IMU, RGB stereo camera, and a depth camera, is connected onto a laptop and utilized by the student to scan an indoor environment. ROS libs, ORB-SLAM2, or other suitable...

Look at Topic
ACQUAL
Forest height estimation using radar remote sensing images

The objective of this study is to reveal to what extend noise reduction can improve the accuracy of estimated forest parameters using RVOG model. Several efficient algorithms exist in the literature to suppress the speckle noise in SAR...

Look at Topic
ACQUAL
Generalization of image classification methods across different urban environments

This study will make use of labelled UAV / satellite imagery across different urban environments. A supervised machine learning method (e.g. Fully Convolutional Networks) will be trained on one study area, and the generalization of that...

Look at Topic
ACQUAL
Hierarchical Bayesian space-time small area mapping of COVID-19 risk: The case of Netherlands

The objective of this topic is to develop space-time risk maps that takes into account population variabilities, demographic, environmental and socioeconomic factors, spatial, temporal, and space-time variations. This will require the...

Look at Topic
ACQUAL
Hybrid adjustment of UAS-based LiDAR and image data

The objective of this research is to find an efficient and applicable registration method to co-register LiDAR data (trajectories and point clouds) and image data (camera poses and point clouds) simultaneously acquired with a hybrid UAS...

Look at Topic
ACQUAL
InSAR phase time series analysis using machine learning approaches

This study attempts to explore existing and advanced machine approaches such as a recurrent neural network for time series analysis. The input data – InSAR phase time series can be downloaded from https://bodemdalingskaart.nl, along...

Look at Topic
ACQUAL
Indoor scene segmentation and depth estimation using deep learning

The student will initially revise the existing literature on scene segmentation and depth estimation with deep learning. Student will focus on the technologies can be used to train an efficient end-to-end network. The network only takes...

Look at Topic
ACQUAL
Kenya pre- and post-landslide analysis with Sentinel-1 satellite SAR imagery

This study will make use of labelled UAV / satellite imagery across different urban environments. A supervised machine learning method (e.g. Fully Convolutional Networks) will be trained on one study area, and the generalization of that...

Look at Topic
ACQUAL, PLUS
MAPPING SOCIO-ECONOMIC INEQUALITIES INSIDE AND ACROSS CITIES USING MACHINE LEARNING AND EARTH OBSERVATION

The focus of this research topic will be on employing state-of-the-art remote sensing algorithms (including machine learning, BIG data and cloud computation) for the mapping of deprivation and/or socio-economic conditions within cities,...

Look at Topic
ACQUAL
Machine learning for disaster risk management - how can we ensure everyone is included and protect societal/human values?

A study will be conducted of the real-world use case to identify possible risks to human/societal values such as biases, personally identifiable information (PII), or demographically identifiable information (DII). The study will look at...

Look at Topic
ACQUAL, PLUS
Mapping socio-economic inequalities inside and across cities using machine learning and earth observation (topic has several sub-topics)

The focus of this research topic will be on employing state-of-the-art remote sensing algorithms for the mapping of deprivation and/or socio-economic conditions within cities, this will be combined with local data (either existing data,...

Look at Topic
ACQUAL
Multi temporal Land use classification using synthetic aperture radar images

The objective of this study is time-series or multi-temporal classification of Enschede. Seasonal polarimetric spaceborne RadarSAT-2 images over the city will be considered. From each data set several efficient polarimetric features will...

Look at Topic
ACQUAL
Object based change detection on multi epoch airborne laser scanner data using Siamese networks

Literature review on change detection using multi epoch point clouds, Siamese networks. Implement suitable deep learning network, generate training data and change detection on multi epoch dense point clouds. Analyze object changes,...

Look at Topic
ACQUAL
Real time optimization of hybrid UAV’s flight path for road infrastructure monitoring

The student should first conduct a literature review on general flight planning, giving particular attention the the vast literature on next-best-view. The student will then implement an algorithm that allows the flight path to be...

Look at Topic
ACQUAL
Scattering characterization and temporal change detection using co-polarimetric SAR imagery

This study will utilize and compare several polarimetric decomposition methods to generate a reliable classification map, and identify the temporal evolution of all radar scatterers using classification dynamic map. The main objective is...

Look at Topic
ACQUAL
Semantic Labeling of Urban Areas in Aerial Imagery

Deep learning has transformed the field of computer vision, and now rivals human-level performance in tasks such as image recognition and object detection. Once trained, these models serve as generic feature extractors, and can be...

Look at Topic
ACQUAL
Sensing our environment for assessing health risks

Review the literature. Explore how different sensors, including humans, are being used to monitor our environment and how these are applicable to health risks. One aspect of this research will examine the role humans and citizen science...

Look at Topic
ACQUAL
Sensor fusion of mobile mapping data for road management using machine/deep learning

Machine/deep learning approaches for sensor fusion, object detection, object classification, and object localization methods applied on RGB images and 3D point clouds

Look at Topic
ACQUAL
Smart Monitoring of the Work Progress in a Building Construction Site Using Low-Cost Indoor Mapping System

The main objective of this research is the smart use of indoor mapping systems output either LiDAR-based or image-based to monitor the progress of the work in building construction and the quality checks between the as-built and...

Look at Topic
ACQUAL
Space-time geostatistical modelling, mapping and simulation of COVID 19: A case study of the Netherlands

The main objective of this study is to develop a geostatistical model for filtering the observed risk, granular mapping, and generation of realizations through simulations. The structure of the method depends on the data structure of the...

Look at Topic
ACQUAL
Stability analysis of skyscrapers in the Netherlands using coherent stacking interferometry

In 2D SAR images the backscattering from ground, façade, roof are superimposed in to a single pixel due to layover issue. This work attempts to implement a new interferometric technique that is able to resolve the layover issue and...

Look at Topic
ACQUAL
Statistical downscaling of ambient air PM concentrations using AOD from TROPOMI data

The objective is to develop a space-time statistical downscaling method for predicting PM concentrations from AOD retrieved from TROPOMI at the European scale. Data required include PM observations from European monitoring stations and...

Look at Topic
ACQUAL
Street furniture detection and identification in multi temporal equirectangular images of mobile mapping systems

Research aims for the identification of street furniture features like light poles and traffic signs out of the 360˚ panoramic images acquired by a mobile mapping system. Few research is published in this focus but we are aiming to...

Look at Topic
ACQUAL
The automated detection and recovery of gaps in 3D image based point clouds

In this MSc project, the objective is to apply an automated and efficient detection of gaps in the 3D reconstructed object parts and replan the imaging network to have finally a fully coved object with the required level of details and...

Look at Topic
ACQUAL, PLUS
Towards building information modelling (BIM) based on 3D automated maps for informal settlements.

With this research topic, we aim in investigation of automated 2D and 3D maps as initial step towards BIM modelling. The topic can include work related to classification of UAV (or other RS data), visualization, methods and tools for...

Look at Topic
ACQUAL
Ultra-precise road marking vertices extraction using UAV imagery and deep learning algorithms.

The student should start with a literature review, investigating the state-of-the-art methodologies for infrastructure inventory generation. The student will then develop an algorithm for road marking extraction from images. In...

Look at Topic
ACQUAL
Virtual Reality for Education - learning while in my back yard

Review mobile apps that may be useful for use in the classroom to conduct local fieldwork. Test and assess mobile phone apps and provide recommendations on what apps are appropriate.

Look at Topic