Compressive sensing (CS) is a mathematically elegant tool for reducing the sensor sampling rate, potentially bringing context-awareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domains, especially among heterogeneous ubiquitous devices. Deep learning (DL) naturally complements CS for adapting the sampling matrix, reconstructing the signal, and learning from the compressed samples. While the CS–DL integration has received substantial research interest recently, it has not yet been thoroughly surveyed, nor has any light been shed on practical issues towards bringing the CS–DL to real world implementations in the ubiquitous computing domain. In this paper we identify main possible ways in which CS and DL can interplay, extract key ideas for making CS–DL efficient, outline major trends in the CS–DL research space, and derive guidelines for the future evolution of CS–DL within the ubiquitous computing domain.

Principal Component Analysis (PCA) is a method based on statistics and linear algebra techniques, used in hyperspectral satellite imagery for data dimensionality reduction required in order to speed up and increase the performance of subsequent hyperspectral image processing algorithms. This paper introduces the PCA approximation method based on a geometric construction approach (gaPCA) method, an alternative algorithm for computing the principal components based on a geometrical constructed approximation of the standard PCA and presents its application to remote sensing hyperspectral images. gaPCA has the potential of yielding better land classification results by preserving a higher degree of information related to the smaller objects of the scene (or to the rare spectral objects) than the standard PCA, being focused not on maximizing the variance of the data, but the range. The paper validates gaPCA on four distinct datasets and performs comparative evaluations and metrics with the standard PCA method. A comparative land classification benchmark of gaPCA and the standard PCA using statistical-based tools is also described. The results show gaPCA is an effective dimensionality-reduction tool, with performance similar to, and in several cases, even higher than standard PCA on specific image classification tasks. gaPCA was shown to be more suitable for hyperspectral images with small structures or objects that need to be detected or where preponderantly spectral classes or spectrally similar classes are present.

The limited processing capacity of computing equipment that is usually mounted on Unmanned Aerial Vehicles (UAVs) often prevents real-time execution of computer vision tasks, such as image segmentation. In this paper, we introduce SqueezeSlimU-Net (SSU-Net), an adaptive and efficient deep learning (DL) model designed to enhance UAV capabilities in performing complex image segmentation tasks under resource constraints, thereby advancing real-time UAV vision – a crucial technology in fields such as precision agriculture. SSU-Net combines benefits of three specialized DL architectures: the semantic segmentation capabilities of the U-Net architecture, the computational efficiency of SqueezeNet's fire modules, and the dynamic adaptability of Slimmable Neural Networks (SNNs). This integration allows SSU-Net to adjust its network width in real-time, thus striking the balance between inference accuracy and computational load based on the operational parameters such as task requirements and UAV's battery life. To validate SSU-Net's efficacy, we applied it to a weed detection task using two UAV-collected datasets and tested it on an edge computing platform for UAVs. Our experiments show that SSU-Net can reduce inference energy consumption by up to 65% with only a minimal 2% reduction in accuracy. A comparative evaluation with other state-of-the-art DL image segmentation approaches shows that SSU-Net achieves on par weed detection performance while requiring significantly fewer model parameters. Additionally, SSU-Net outperforms state-of-the-art network pruning techniques in balancing accuracy and resource usage. Timing benchmarks show SSU-Net fostering real-time weed detection even on low-resource UAVs, making it ideal for UAV remote sensing applications.

The human face exhibits a high level of complexity when it is regarded as a multidimensional visual model, leading to face recognition systems that require difficult and extensive computations for coding and decoding the face images. A well-established approach in this regard is based on using principle component analysis (PCA) for both feature extraction and face recognition, known as the eigenface approach. This technique, despite a good recognition rate, suffers from the disadvantage of high computation cost due to the complexity of the PCA algorithm. In this paper, we use a geometrical approximated PCA (gaPCA) algorithm for computing the eigenfaces for three different datasets. The face recognition task is performed using a similarity score based on the inverse Euclidean distance for the first two datasets and using a nerual network in the third case. All the results are compared to the case where standard PCA is used. These accuracy results show that gaPCA represents a viable alternative to the classical statistical approach for computing the principal components.

Synthetic Aperture Radar (SAR) images taken over a certain area at different bands and also with a short time interval are now more widely available. This is due to the increase of SAR acquisitions following the last space missions, such as Sentinel 1 and COSMO-SkyMed (CSK). New paradigms capable of performing effective analysis and synthesis stemming from such a type of information are then required in order to exploit better and disseminate the information contained in the data. In this letter, a data fusion technique between CSK and Sentinel-1 data is described. To this purpose, an ad hoc Nonlinear Principal Component Analysis (NLPCA) with Auto-Associative Neural Networks (AANNs) algorithm is designed and developed. The network extracts the most relevant features from the combination of the different scattering mechanisms. The extracted features are then used as inputs for a land cover classification exercise. A comparison between the results obtained with the original images and those yielded by the new synthesized data, with lower dimensionality, demonstrates the ability of the algorithm to generate useful final products.

Unmanned aerial vehicles (UAVs) have become essential tools for monitoring crop condition, detecting early signs of plant stress, and supporting timely interventions in modern precision agriculture. However, real-time onboard image analysis remains challenging due to the limited computational and energy resources of small embedded UAV platforms. This work presents a deployment-aware neural architecture search (NAS) framework for discovering lightweight object detection networks explicitly optimized for edge hardware constraints. Building on the YOLOv8n baseline, the proposed NAS procedure yields detector architectures that substantially reduce computational load while preserving high detection accuracy for agricultural field monitoring tasks. The best-discovered model reduces GFLOPs by 37.0% and parameters by 61.3% compared to YOLOv8n, with only a 1.96% decrease in mAP@50. When deployed on an NVIDIA Jetson Nano, it achieves a 28.1% increase in inference speed and an 18.5% improvement in energy efficiency under ONNX Runtime, with additional gains using TensorRT FP16. Evaluation on wheat head and cotton seedling datasets demonstrates strong generalization across crop types and varying imaging conditions. By enabling highly efficient onboard inference, the proposed NAS framework supports practical UAV-based crop monitoring workflows and contributes to the development of responsive, field-ready remote sensing systems in resource-limited environments.