Towards global flood mapping onboard low cost satellites with machine learning

in Scientific Reports (2021), 11(7249 (2021)),

Spaceborne Earth observation is a key technology for flood response, offering valuable information to decision makers on the ground. Very large constellations of small, nano satellites— ’CubeSats’ are a ... [more ▼]

Spaceborne Earth observation is a key technology for flood response, offering valuable information to decision makers on the ground. Very large constellations of small, nano satellites— ’CubeSats’ are a promising solution to reduce revisit time in disaster areas from days to hours. However, data transmission to ground receivers is limited by constraints on power and bandwidth of CubeSats. Onboard processing offers a solution to decrease the amount of data to transmit by reducing large sensor images to smaller data products. The ESA’s recent PhiSat-1 mission aims to facilitate the demonstration of this concept, providing the hardware capability to perform onboard processing by including a power-constrained machine learning accelerator and the software to run custom applications. This work demonstrates a flood segmentation algorithm that produces flood masks to be transmitted instead of the raw images, while running efficiently on the accelerator aboard the PhiSat-1. Our models are trained on WorldFloods: a newly compiled dataset of 119 globally verified flooding events from disaster response organizations, which we make available in a common format. We test the system on independent locations, demonstrating that it produces fast and accurate segmentation masks on the hardware accelerator, acting as a proof of concept for this approach. [less ▲]

Towards multiscale data fusion of high-resolution space borne and terrestrial datasets over Tristan da Cunha

Poster (2018, April 10)

Ever improving low cost, lightweight and easy to use sensing technologies are enabling the capture of rich 3D Datasets to support an unprecedented range of applications in Geosciences. Especially low-cost ... [more ▼]

Ever improving low cost, lightweight and easy to use sensing technologies are enabling the capture of rich 3D Datasets to support an unprecedented range of applications in Geosciences. Especially low-cost LiDAR systems as well as optical sensors, which can be deployed from terrestrial or low altitude aerial platforms, allow the collection of large datasets without detailed expert knowledge or training. Dense pointcloud derived from these technologies provide an invaluable source to fill the gap between highly precise and accurate terrestrial topographic surveys and large area Digital Surface Models (DSMs) derived from airborne and spaceborne sensors. However, the collection of reliable 3D pointclouds in remote and hazardous locations remains to be very difficult and costly. Establishing a reliable georeference, ensuring accuracy and data quality as well as merging such rich datasets with existing or space borne mapping provide additional challenges. The presented case study investigates the data quality and integration of a heterogeneous dataset collected over the remote island of Tristan da Cunha. High-resolution 3D pointclouds derived by TLS and drone Photogrammetry are merged with space borne imagery while preserving the accurate georeference provided by Ground Control derived from geodetic observations. The volcanic island of Tristan da Cunha located in the centre of the Southern Atlantic Ocean is one of the most remote and difficult to access locations on the planet. Its remote location, rough climatic conditions and consistent cloud coverage provides exceptional challenges for terrestrial, aerial as well as space borne data acquisition. Amongst many other scientific installations, the island also hosts a continuous GNSS station observation and monitoring facilities operated by the University of Luxembourg, which provided the opportunity to conduct a local terrestrial data acquisition campaign consistent with a terrestrial ground survey, Laserscanning and an image acquisition from a low-cost drone. The highly accurate Ground Control network, observed by GNSS and total station, provides a reliable georeference. Pointclouds were acquired around the area of the harbour using a Leica P20 terrestrial Laserscanner, as well as drone Photogrammetry based on images collected by a low-cost DJI Phantom3 drone. To produce a map of the complete island a comprehensive dataset of high-resolution space borne imagery based on the Digital Globe WorldView constellation was acquired which provided high resolution mapping information. The case study presents a cross-validation of terrestrial, low altitude airborne as well as spaceborne datasets in terms coregistration, absolute georeference, scale, resolution and overall data quality. Following the evaluation a practical approach to fuse this heterogeneous dataset is applied which aims to preserve overall data quality, local resolution and accurate georeference and avoid edge artefacts. The conclusions drawn from our preliminary results provide some good practice advice for similar projects. The final topographic dataset enables mapping and monitoring of local geohazards as, e.g. coastal erosion and recent landslides thus also supporting the local population. [less ▲]

Towards Optimised Deployment of Electric Bus Systems with On-Route Charging using Cooperative ITS

Scientific Conference (2018, July)

Towards Optimized Deployment of Electric Bus Systems Using Cooperative ITS

Poster (2019, January)

In this paper we analyze the impact of using cooperative intelligent transportation systems (C-ITS) to manage electrical bus systems. A simulation-based study is presented where three control strategies ... [more ▼]

In this paper we analyze the impact of using cooperative intelligent transportation systems (C-ITS) to manage electrical bus systems. A simulation-based study is presented where three control strategies are used to regulate the operations of a line, namely bus holding, Green Light Optimal Dwell Time Adaptation (GLODTA) and Transit Signal Priority (TSP). The results show, using a realistic scenario of a major line in Luxembourg City, that buses are efficiently operated without necessarily providing additional priority to public transport, hence without negatively affecting the capacity of the private vehicles system. Benefits in terms of headway regulations, energy consumption and travel time variance reductions are quantified. [less ▲]

Tradeoffs in networks with positive and negative feedback

Scientific Conference (2005)

Traffic control which maximises network throughput: Some simple examples

in Transportation Research. Part C, Emerging Technologies (2019), 107

A transformation of the position based visual servoing problem into a convex optimization problem

in Proceedings of the 51th IEEE Conference on Decision and Control (2012)

Here we address the problem of moving a camera from an initial pose to a final pose. The trajectory between the two poses is subject to constraints on the camera motion and the visibility, where we have ... [more ▼]

Here we address the problem of moving a camera from an initial pose to a final pose. The trajectory between the two poses is subject to constraints on the camera motion and the visibility, where we have bounds on the allowed velocities and accelerations of the camera and require that a set of point features are visible for the camera. We assume that the pose is possible to retrieve from the observations of the point features, i.e., we have a Position Based Visual Servoing Problem with constraints. We introduce a two step method that transforms the problem into a convex optimization problem with linear constraints. In the first step the rotational motion is restricted to be of a certain type. This restriction allows us to retrieve an explicit solution of the rotational motion that is optimal in terms of minimizing geodesic distance. Furthermore, this restriction guarantees that the rotational motion satisfies the constraints. Using the explicit solution, we can formulate a convex optimization problem for the translational motion, where we include constraints on workspace and visibility. [less ▲]

Translating Collections: An Insight on Curating a Historical Multilayered Digital Exhibition on the Great War

Presentation (2018, December 07)

Travel-sharing in multimodal systems: a behavioural modelling approach

Scientific Conference (2013)

trend Analysis and interpretation of Luxembourg’s consumption Footprint NFA 2010 edition, data years 2000 – 2007

Report (2012)

The Ecological Footprint methodology by Global Footprint Network measures human consumption of products and services from different ecosystems in terms of the amount of bioproductive land and sea area ... [more ▼]

The Ecological Footprint methodology by Global Footprint Network measures human consumption of products and services from different ecosystems in terms of the amount of bioproductive land and sea area needed to supply these products and services. In other words, the Ecological Footprint calculates the land area needed to produce food, provide resources, produce energy, and absorb the CO2 emissions generated by the supply chains within one year at country level. For the calculations of Luxembourg’s Ecological Footprint, international statistical databases are used to identify the quantities of produced, imported and exported goods and services. Then, Global Footprint Network applies different factors to the quantities to assess the area needed to supply these products and services. Finally, the Consumption Footprint of a nation is divided by the number of inhabitants and compared to other countries at a per capita level (global hectares per capita). This means that the Ecological Footprint can be used as an indicator for the sustainability of a national consumption by assessing human land uses. In the following paragraph, Luxembourg’s Ecological Footprint is discussed in the framework of the environmental indicators of Luxembourg’s competitiveness scoreboard (see Table 9) [MECE, 2010]. Luxembourg’s ranking is rather low for all of the scoreboard indicators: number of ISO 9001 certifications per billion of inhabitants (21 out of 27); number of ISO 14001 certifications per billion of inhabitants (15 out of 27); total greenhouse gas emissions (15 out of 27); renewable energy ration (23 out of 27); quantity of municipal waste per capita per year (24 out of 27); energetic intensity (8 out of 27); transport by car (17 out of 27); Ecological Footprint in gha per capita per year (27 out of 27). Based on the environmental competiveness scoreboard indicators, it can be concluded that in general, Luxembourg’s environmental performance is low compared to the other countries of the European Union. With respect to Luxembourg’s Ecological Footprint, it can be said that Luxembourg’s consumption is not sustainable. The number of planets that would be needed if the world's population lived like the population of Luxembourg in 2007 is about six. However, per year, the biocapacity (bioproductive land) of the planet can only regenerate once. [less ▲]