Image matching is a key procedure in the process of generation of Digital Surface Models (DSM). We have developed a new approach for image matching and the related software package. This technique has proved its good performance in many applications. Here, we demonstrate its use in 3D tree modelling. After a brief description of our image matching technique, we show results from analogue and digital aerial images and high‐resolution satellite images (IKONOS). In some cases, comparisons with manual measurements and/or airborne laser data have been performed. The evaluation of the results, qualitative and quantitative, indicate the very good performance of our matcher. Depending on the data acquisition parameters, the photogrammetric DSM can be denser than a DSM generated by laser, and its accuracy may be better than that from laser, as in these investigations. The tree canopy is well modelled, without smoothing of small details and avoiding the canopy penetration occurring with laser. Depending on the image scale, not only dense forest areas but also individual trees can be modelled.

Hyperspectral sensors capture a portion of the visible and near-infrared spectrum with many narrow spectral bands. This makes it possible to better discriminate objects based on their reflectance spectra and to derive more detailed object properties. For technical reasons, the high spectral resolution comes at the cost of lower spatial resolution. To mitigate that problem, one may combine such images with conventional multispectral images of higher spatial, but lower spectral resolution. The process of fusing the two types of imagery into a product with both high spatial and spectral resolution is called hyperspectral super-resolution. We propose a method that performs hyperspectral super-resolution by jointly unmixing the two input images into pure reflectance spectra of the observed materials, along with the associated mixing coefficients. Joint super-resolution and unmixing is solved by a coupled matrix factorization, taking into account several useful physical constraints. The formulation also includes adaptive spatial regularization to exploit local geometric information from the multispectral image. Moreover, we estimate the relative spatial and spectral responses of the two sensors from the data. That information is required for the super-resolution, but often at most approximately known for real-world images. In experiments with five public datasets, we show that the proposed approach delivers up to 15% improved hyperspectral super-resolution.

Continuous observation of climate indicators, such as trends in lake freezing, is important to understand the dynamics of the local and global climate system. Consequently, lake ice has been included among the Essential Climate Variables (ECVs) of the Global Climate Observing System (GCOS), and there is a need to set up operational monitoring capabilities. Multi-temporal satellite images and publicly available webcam streams are among the viable data sources capable of monitoring lake ice. In this work we investigate machine learning-based image analysis as a tool to determine the spatio-temporal extent of ice on Swiss Alpine lakes as well as the ice-on and ice-off dates, from both multispectral optical satellite images (VIIRS and MODIS) and RGB webcam images. We model lake ice monitoring as a pixel-wise semantic segmentation problem, i.e., each pixel on the lake surface is classified to obtain a spatially explicit map of ice cover. We show experimentally that the proposed system produces consistently good results when tested on data from multiple winters and lakes. Our satellite-based method obtains mean Intersection-over-Union (mIoU) scores > 93%, for both sensors. It also generalises well across lakes and winters with mIoU scores > 78% and >80% respectively. On average, our webcam approach achieves mIoU values of ≈87% and generalisation scores of ≈71% and ≈69% across different cameras and winters respectively. Additionally, we generate and make available a new benchmark dataset of webcam images (Photi-LakeIce) which includes data from two winters and three cameras.

The geometric accuracy of 2008 AVHRR orthoimages from Metop-A, NOAA-17 and NOAA-18 satellites over Switzerland have been investigated here. The methods employed in the study are fully automated, with an accuracy of 0.1–0.2 pixels, however, blunders do occur and this requests a careful blunder detection approach. The investigations include analysis of relative, absolute and band-to-band registration (BBR) accuracy. Regarding relative accuracy, thousands of points are matched between Metop-A, NOAA-17 and NOAA-18 images of the same day. The accuracy is quite high with mean shifts between 0.2 and 0.4 pixels. Systematic stripes have been observed when NOAA-18 images are involved in matching. In spite of many efforts to find the source of this error, no explanation could be found. In addition, large shifts up to 2.9 pixels on some days between September and December 2008 were observed. Regarding absolute accuracy, digitized lakes as reference polygons have been used and a subpixel lake matching method has been applied. The mean shifts generally fulfilled EUMETSAT and GCOS specifications, although some partial results exceed them, especially for Metop-A. Regarding BBR accuracy, six multispectral bands have been compared, also with point matching. The EUMETSAT specification is 0.1 km, however, this specification refers to original images, not orthoimages. Taking also into account the matching errors of 0.1 km, the EUMETSAT specifications are in principle fulfilled in all cases except matching of Metop-A and NOAA-17 Band-2 images with Bands 4 and 5. The overall work showed that although, in general, accuracies are high and fulfill specifications, errors exceeding the specifications can occur and vary depending on the satellite used, time and location. Such errors influence subsequent geometric or thematic processing; thus, an automated and permanent quality control of such images should be executed.

Depleting lake ice is a climate change indicator, just like sea-level rise or glacial retreat. Monitoring Lake Ice Phenology (LIP) is useful because long-term freezing and thawing patterns serve as sentinels to understand regional and global climate change. We report a study for the Oberengadin region of Switzerland, where several small- and medium-sized mountain lakes are located. We observe the LIP events, such as freeze-up, break-up and ice cover duration, across two decades (2000–2020) from optical satellite images. We analyse the time series of MODIS imagery by estimating spatially resolved maps of lake ice for these Alpine lakes with supervised machine learning. To train the classifier we rely on reference data annotated manually based on webcam images. From the ice maps, we derive long-term LIP trends. Since the webcam data are only available for two winters, we cross-check our results against the operational MODIS and VIIRS snow products. We find a change in complete freeze duration of $$-\,0.76$$- 0.76 and $$-\,0.89$$- 0.89 days per annum for lakes Sils and Silvaplana, respectively. Furthermore, we observe plausible correlations of the LIP trends with climate data measured at nearby meteorological stations. We notice that mean winter air temperature has a negative correlation with the freeze duration and break-up events and a positive correlation with the freeze-up events. Additionally, we observe a strong negative correlation of sunshine during the winter months with the freeze duration and break-up events.

The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40->20 m, respectively 360->60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD. The code is available at https://github.com/lanha/DSen2