Cloud cover remains a significant limitation to a broad range of applications relying on optical remote sensing imagery, including crop identification/yield prediction, climate monitoring, and land cover classification. A common approach to cloud removal treats the problem as an inpainting task and imputes optical data in the cloud-affected regions employing either mosaicing historical data or making use of sensing modalities not impacted by cloud obstructions, such as SAR. Recently, deep learning approaches have been explored in these applications; however, the majority of reported solutions rely on external learning practices, i.e., models trained on fixed datasets. Although these models perform well within the context of a particular dataset, a significant risk of spatial and temporal overfitting exists when applied in different locations or at different times. Here, cloud removal was implemented within an internal learning regime through an inpainting technique based on the deep image prior. The approach was evaluated on both a synthetic dataset with an exact ground truth, as well as real samples. The ability to inpaint the cloud-affected regions for varying weather conditions across a whole year with no prior training was demonstrated, and the performance of the approach was characterised.

Optical satellite images of Earth frequently contain cloud cover and shadows. This requires processing pipelines to recognize the presence, location, and features of the cloud-affected regions. Models that make predictions about the ground behind the clouds face the challenge of lacking ground truth information, i.e., the exact state of Earth’s surface. Currently, the solution to that is to either (i) create pairs from samples acquired at different times or (ii) simulate cloudy data based on a clear acquisition. This work follows the second approach and proposes an open-source simulation tool capable of generating a diverse and unlimited number of high-quality simulated pair data with controllable parameters to adjust cloud appearance, with no annotation cost. The tool is available as open-source. An indication of the quality and utility of the generated clouds is demonstrated by the models for cloud detection and cloud removal trained exclusively on simulated data, which approach the performance of their equivalents trained on real data.

Monitoring and classification of dairy cattle behaviours is essential for optimising milk yields. Early detection of illness, days before the critical conditions occur, together with automatic detection of the onset of oestrus cycles is crucial for obviating prolonged cattle treatments and improving the pregnancy rates. Accelerometer-based sensor systems are becoming increasingly popular, as they are automatically providing information about key cattle behaviours such as the level of restlessness and the time spent ruminating and eating, proxy measurements that indicate the onset of heat events and overall welfare, at an individual animal level. This paper reports on an approach to the development of algorithms that classify key cattle states based on a systematic dimensionality reduction process through two feature selection techniques. These are based on Mutual Information and Backward Feature Elimination and applied on knowledge-specific and generic time-series extracted from raw accelerometer data. The extracted features are then used to train classification models based on a Hidden Markov Model, Linear Discriminant Analysis and Partial Least Squares Discriminant Analysis. The proposed feature engineering methodology permits model deployment within the computing and memory restrictions imposed by operational settings. The models were based on measurement data from 18 steers, each animal equipped with an accelerometer-based neck-mounted collar and muzzle-mounted halter, the latter providing the truthing data. A total of 42 time-series features were initially extracted and the trade-off between model performance, computational complexity and memory footprint was explored. Results show that the classification model that best balances performance and computation complexity is based on Linear Discriminant Analysis using features selected through Backward Feature Elimination. The final model requires 1.83 ± 1.00 ms to perform feature extraction with 0.05 ± 0.01 ms for inference with an overall balanced accuracy of 0.83.

The paper investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artefacts and that a simple alternative of self-supervised internal inpainting achieves a higher quality of synthesis.

The rich, complementary data provided by Sentinel-1 and Sentinel-2 satellite constellations host considerable potential to transform Earth observation (EO) applications. However, a substantial amount of effort and infrastructure is still required for the generation of analysis-ready data (ARD) from the low-level products provided by the European Space Agency (ESA). Here, a flexible Python framework able to generate a range of consistent ARD aligned with the ESA-recommended processing pipeline is detailed. Sentinel-1 Synthetic Aperture Radar (SAR) data are radiometrically calibrated, speckle-filtered and terrain-corrected, and Sentinel-2 multi-spectral data resampled in order to harmonise the spatial resolution between the two streams and to allow stacking with multiple scene classification masks. The global coverage and flexibility of the framework allows users to define a specific region of interest (ROI) and time window to create geo-referenced Sentinel-1 and Sentinel-2 images, or a combination of both with closest temporal alignment. The framework can be applied to any location and is user-centric and versatile in generating multi-modal and multi-temporal ARD. Finally, the framework handles automatically the inherent challenges in processing Sentinel data, such as boundary regions with missing values within Sentinel-1 and the filtering of Sentinel-2 scenes based on ROI cloud coverage.

The treatment of interfering motion contributions remains one of the key challenges in the domain of radar-based vital sign monitoring. Removal of the interference to extract the vital sign contributions is demanding due to overlapping Doppler bands, the complex structure of the interference motions and significant variations in the power levels of their contributions. A novel approach to the removal of interference through the use of a probabilistic deep learning model is presented. Results show that a convolutional encoder-decoder neural network with a variational objective is capable of learning a meaningful representation space of vital sign Doppler-time distribution facilitating their extraction from a mixture signal. The approach is tested on semi-experimental data containing real vital sign signatures and simulated returns from interfering body motions. It is demonstrated that the application of the proposed network enhances the extraction of the micro-Doppler frequency corresponding to the respiration rate.