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 ▲]

RIVER MORPHOLOGY MONITORING OF A SMALL-SCALE ALPINE RIVERBED USING DRONE PHOTOGRAMMETRY AND LIDAR

in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2020, August 12), XLIII-B2-2020 Article Metrics Related articles(1017), 1024

An efficient alternative to labour-intensive terrestrial and costly airborne surveys is the use of small, inexpensive Unmanned Aerial Vehicles (UAVs) or Remotely Piloted Aerial Systems (RPAS). These low ... [more ▼]

An efficient alternative to labour-intensive terrestrial and costly airborne surveys is the use of small, inexpensive Unmanned Aerial Vehicles (UAVs) or Remotely Piloted Aerial Systems (RPAS). These low-altitude remote sensing platforms, commonly known as drones, can carry lightweight optical and LiDAR sensors. Even though UAV systems still have limited endurance, they can provide a flexible and relatively inexpensive monitoring solution for a limited area of interest. This study investigated the applicability of monitoring the morphology of a frequently changing glacial stream using high-resolution topographic surface models derived from low-altitude UAV-based photogrammetry and LiDAR. An understanding of river-channel morphology and its response to anthropogenic and natural disturbances is imperative for effective watershed management and conservation. We focus on the data acquisition, processing workflow and highlight identified challenges and shortcomings. Additionally, we demonstrate how LiDAR data acquisition simulations can help decide which laser scanning approach to use and help optimise data collection to ensure full coverage with desired level of detail. Lastly, we showcase a case study of 3D surface change analysis in an alpine stream environment with UAV-based photogrammetry. The datasets used in this study were collected as part of the ISPRS Summer School of Alpine Research, which will continue to add new data layers on a biyearly basis. This growing data repository is freely available for research. [less ▲]

Conventional EO Satellites vs. CubeSats; FDL - AI flood detection onboard a Nano Satellite

Scientific Conference (2019, December 11)

A comparison between conventional Earth Observation Satellites and CubeSats; Requirements, Capabilities and Data Quality

Scientific Conference (2019, September 11)

From its early beginning as an educational tool in 1999, cubesats have evolved into a popular platform for technology demonstrations and scientific instruments. Ideas and innovations sparked from an ... [more ▼]

From its early beginning as an educational tool in 1999, cubesats have evolved into a popular platform for technology demonstrations and scientific instruments. Ideas and innovations sparked from an enthusiastic community led to the development of new Earth Observation (EO) technology concepts based on large constellations of satellites with high-resolution optical imagers previously considered as infeasible. Probably the most significant constellation today is deployed by Planet who are currently operating a fleet larger than 120 3U Dove satellites, which provide an imaging service with up to 3m Ground Sample Distance (GSD). The number of low-cost EO Cubesat systems is constantly increasing. However, for a number of reasons there still seems to be a reluctance to use such data for many EO applications. A better understanding of the capabilities of the current generation of small Cubesats compared to the traditional well-established bigger operational missions of high and medium resolution EO satellites is required. What are the critical capabilities and quality indicators? Due to the limited size and weight of Cubesats, critical system components, e.g. for navigation and communication, always compete with operational payloads such as optical camera/sensor systems. A functional EO system requires balanced payload, which provides adequate navigational capabilities, that match the requirements of the optical imagers (camera) deployed with the system. This study reviews the current performance and capabilities of Cubesats for optical EO and compares them to the capabilities of conventional, dedicated high and medium resolution EO systems. We summarise key performance parameters and quality indicators to evaluate the difference between the systems. An empirical study compares recent very high-resolution (VHR) imagery from big EO satellite missions with available images from Cubesats for the use case in disaster monitoring. Small and agile Nanosatellites or Cubesats already show remarkable performance. Although it is not expected that their performance and capability will match those of current bigger EO satellite missions, they are expected to provide a valuable tool for EO and remote sensing, in particular for downstream industry applications. [less ▲]

Towards a high-resolution drone-based 3D mapping dataset to optimise flood hazard modelling

in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2019, June), XLII-2/W13

The occurrence of urban flooding following strong rainfall events may increase as a result of climate change. Urban expansion, ageing infrastructure and an increasing number of impervious surfaces are ... [more ▼]

The occurrence of urban flooding following strong rainfall events may increase as a result of climate change. Urban expansion, ageing infrastructure and an increasing number of impervious surfaces are further exacerbating flooding. To increase resilience and support flood mitigation, bespoke accurate flood modelling and reliable prediction is required. However, flooding in urban areas is most challenging. State-of-the-art flood inundation modelling is still often based on relatively low-resolution 2.5 D bare earth models with 2-5m GSD. Current systems suffer from a lack of precise input data and numerical instabilities and lack of other important data, such as drainage networks. Especially, the quality and resolution of the topographic input data represents a major source of uncertainty in urban flood modelling. A benchmark study is needed that defines the accuracy requirements for highly detailed urban flood modelling and to improve our understanding of important threshold processes and limitations of current methods and 3D mapping data alike. This paper presents the first steps in establishing a new, innovative multiscale data set suitable to benchmark urban flood modelling. The final data set will consist of high-resolution 3D mapping data acquired from different airborne platforms, focusing on the use of drones (optical and LiDAR). The case study includes residential as well as rural areas in Dudelange/Luxembourg, which have been prone to localized flash flooding following strong rainfall events in recent years. The project also represents a cross-disciplinary collaboration between the geospatial and flood modelling community. In this paper, we introduce the first steps to build up a new benchmark data set together with some initial flood modelling results. More detailed investigations will follow in the next phases of this project. [less ▲]

Merging DEMs from VHR Optical Imagery with Drone Data - A High-resolution DEM for Tristan da Cunha

Scientific Conference (2018, December 12)

The extraction of high-resolution, Digital Elevation Models (DEM) from very high-resolution (VHR) optical satellite imagery, as well as low altitude drone images by Photogrammetric methods or modern ... [more ▼]

The extraction of high-resolution, Digital Elevation Models (DEM) from very high-resolution (VHR) optical satellite imagery, as well as low altitude drone images by Photogrammetric methods or modern Structure from Motion (SFM) engines, has rapidly matured. Today both data sources are representing cost-effective alternatives to dedicated airborne sensors, especially for remote and difficult to access regions. Ever-growing archives of high-resolution Satellite imagery, are providing a rich data source which covers even the most remote locations with high-resolution imagery up to 0.30m ground sample distance multiple times enabling the generation of high-resolution DEMS. Furthermore, low-cost, low weight and easy to use drones can easily be deployed in remote regions and capture limited areas with very high resolution. Dense point clouds derived from this method provide an invaluable data source to fill the gap between globally available low-resolution DEMs and highly accurate terrestrial surveys. The presented case study investigates the use of VHR archive imagery as well as low-cost drone imagery to generate high-quality DEMs using photogrammetric tools over a remote region which is difficult to access by manned airborne platforms. We highlight the potential and limitations of both data sources to provide high resolution, accurate elevation data. [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 ▲]

An evaluation of low-cost consumer-grade UAS systems for 3D reality capture

Poster (2016, September 22)

During the last years, small lightweight and low cost remotely piloted aerial systems (RPAS) commonly referred as Drones have rapidly developed into capable low-cost Unmanned Aerial Systems (UAS). Fuelled ... [more ▼]

During the last years, small lightweight and low cost remotely piloted aerial systems (RPAS) commonly referred as Drones have rapidly developed into capable low-cost Unmanned Aerial Systems (UAS). Fuelled by a vibrant community of scientists, professionals and hobby enthusiasts enabling technologies have matured quickly, and prices of consumer grade as well as semi-professional systems fell sharply. Especially multirotor vertical take-off and landing (VTOL) UAS have proven to be versatile and flexible platforms which can be equipped with a range of sensors capable of capturing aerial data for a variety of 2D and 3D mapping applications. Consumer grade, low weight systems as the DJI Phantom or 3DR Solo have a limited payload and can carry low weight action cameras like the GoPro Hero models which are capable of collecting video as well as still RGB and near-infrared imagery. Applying traditional Photogrammetric methods to imagery from low-cost UAS systems proved complex and impractical in the past. However modern the state-of-the-art structure from motion algorithms implemented in off the shelf software packages (sometimes referred as new Photogrammetry), cloud processing environments and available via open source libraries promise to generate dense 3D point clouds, textured models and orthomosaics in high quality and without much effort. How accurate and how reliable are data products generated from such systems? Expanding from a preliminary study (BACKES & TEASDALE 2015) we review the every progressing capabilities and features of COTS (commercial of the shelf) user and semi-professional UAS systems under the aspects of deployable sensors, ease of use, reliability as well as safety. We show the workflow from flight planning, data collection to dense pointclould matching using a range of software products. The resulting point clouds are evaluated and benchmarked using a highly accurate and dense reference data acquired via geodetic terrestrial survey and Laserscanning. The results of this evaluations allow conclusions on the current accuracy capabilities of this such low-cost systems. [less ▲]