Recent advances in single-and multi-image superresolution have revealed the limitations of classical image similarity metrics (like peak signal-to-noise ratio), as they often fail to align with human perception when evaluating the visual quality of super-resolved outputs.In this paper, we explore how to exploit keypoint-based metrics to evaluate super-resolution image quality.Specifically, we explore two correlated metrics: (i) a multiscale index proposal measure capturing salience of keypoints, and (ii) a repeatability metric quantifying how consistently the corresponding keypoints are identified in super-resolved and ground-truth images.Experiments on several simulated and real-world datasets show that the repeatability correlates with subjective judgments, and multi-scale index proposal can be helpful for difficult datasets when other metrics are insufficient.

Fuzzy data processing enables data enrichment and increases data interpretation in industrial environments. In the cloud-based IoT data ingestion pipelines, fuzzy data processing can be implemented in several locations, closer to the IoT events gateways, stream processors, or the persistence layer before the data is visualized. Since Automated Guided Vehicles (AGV)-enabled manufacturing can produce vast amounts of data, the decision on the placement of the fuzzy data processing can be important for secondary processes performed on the enriched data, like the predictive maintenance inferencing. In this paper, we analyze two locations of fuzzy data processing in the cloud-based environment built for monitoring AGVs in smart factories - by formulating fuzzy queries against data streams on stream processing units and data at rest in a database. The querying scenarios cover fuzzy filtering with simple and complex criteria, fuzzy filtering through assignment to a linguistic variable, and joining data streams by representing joining attributes as fuzzy numbers. The experimental results show that querying the data stream can be more efficient and profitable in the scalable environment of many AGVs. However, the enrichment provided for the data at rest is also beneficial when gathering data for building future predictive maintenance models.

Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images of high perceptual quality. However, it often remains unclear whether the reconstructed details are close to the actual ground-truth information and whether they constitute a more valuable source for image analysis algorithms. In the reported work, we address the latter problem, and we present our efforts toward learning super-resolution algorithms in a task-driven way to make them suitable for generating high-resolution images that can be exploited for automated image analysis. In the reported initial research, we propose a methodological approach for assessing the existing models that perform computer vision tasks in terms of whether they can be used for evaluating super-resolution reconstruction algorithms, as well as training them in a task-driven way. We support our analysis with experimental study and we expect it to establish a solid foundation for selecting appropriate computer vision tasks that will advance the capabilities of real-world super-resolution.

Detection and prediction of failures in Automated Guided Vehicles (AGV) are essential for the uninterrupted operation of production plants. Anomaly detection is usually achieved by comparing expected measurement values with actual observations. Thus, it is crucial to predict telemetry signals properly. In this paper, we research the prediction of energy consumption using state-of-the-art Artificial Neural Networks architectures (SCINet) compared with other Recurrent Neural Network (RNN) approaches on the data streams acquired from CoBotAGV. We especially focus on the possibility of applying feature weighting. We show that it can improve prediction capabilities. We also investigate resource utilization in terms of time to fit the embedded AGV environment.

Super-resolution (SR), i.e. reconstruction of high-resolution (HR) images from low-resolution (LR) samples, plays a vital role in remote sensing. Multi-image SR (MISR) methods leverage information fusion from a series of LR images acquired over time to reconstruct HR images. Deep neural networks form the foundation of state-of-the-art MISR techniques, and selecting an appropriate metric for training them is crucial to obtain reliable results. In this paper, we propose a novel approach for training MISR networks by incorporating the learned perceptual image patch similarity (LPIPS) metric as the loss function. Traditionally, SR methods rely on metrics based on pixel-wise similarity, which may not be optimal when LR and HR images differ significantly in histogram characteristics. By utilizing the LPIPS metric, which is consistent with human perception, the training process is directed towards better reconstruction of image details rather than strict pixel-wise compliance. Experimental results on the MuS2 dataset, consisting of LR images from Sentinel-2 and HR images from WorldView-2, demonstrate the effectiveness of our approach.

Super-resolution is aimed at enhancing image spatial resolution and it has been intensively explored for many years. The recent advancements, underpinned with deep learning, also include techniques developed specifically for hyper-spectral data. However, most of the emerging methods are validated in application-independent scenarios, which often rely on an unrealistic experimental setup—the reconstruction is performed from simulated low-resolution images (degraded from an original image) with the goal of inverting the degradation process and restoring the original image. This leads to over-optimistic assessment of super-resolution capabilities and limits their practical applications. In this paper, we demonstrate task-based validation for different types of hyperspectral PRISMA image super-resolution, including pan-sharpening, fusion of multispectral and hyperspectral data, as well as single-image super-resolution. The obtained results reported in the paper are encouraging and they help better understand the value of super-resolved PRISMA images.

In this paper, we present our study focused on applying a vision transformer-based pansharpening technique to enhance PRISMA satellite hyperspectral data. The PRISMA mission, launched by the Italian Space Agency, captures hyperspectral images comprising visible and near infra-red, as well as short-wave infra-red channels. By integrating the panchromatic image of high spatial resolution with the hyperspectral data of high spectral resolution, the pansharpening process consists in producing spatially-enhanced hyperspectral imagery. Our research involves modifying and adapting the state-of-the-art HyperTransformer architecture to effectively process real-life PRISMA data. The evaluation of our model’s performance utilizes PRISMA L2D data, encompassing simulated low-resolution data and real-life data. We employ quantitative metrics and visual examination to assess the results. We also highlight the importance of choosing right PRISMA data processing level for the pansharpening process. The proposed pansharpening model successfully enhances PRISMA data for practical applications, contributing to the advancement of Earth observation techniques.

Class imbalance is a common problem with datasets relating to various areas of life. It causes many traditional machine learning algorithms to tend to misclassify minority samples as majority ones. Despite various studies, the class imbalance still remains a relevant problem for which no one-size-fits-all solution has been found. In this paper, an undersampling method based on clustering is presented. In the proposed approach K-means algorithm is used to cluster data. In homogenous "majority" clusters, i.e., clusters containing objects of only the majority class, objects within the specified distance from the center are removed. In the case of non-homogeneous clusters, objects located at the class decision boundary are removed using the KNN algorithm. As tests have shown, the clustering-based solution can improve classification quality. The results of experiments show that in many cases the proposed solution outperformed other undersampling techniques described in the literature.

Automated guided vehicles (AGV) provide a cost-efficient transportation method in smart industrial plants. Their continuous operation is crucial for production flow. However, while detection of typical failures, e.g., those related to battery voltage, can be performed in an automated manner, more complex scenarios require expert knowledge and human monitoring. In this paper, we evaluate recurrent neural network-based (RNN) energy consumption forecasting using other telemetry features. We aim to find models well suited for anomaly detection methods working on the analysis of error between forecasted and actual values. We compare the results of RNN architectures on our data and public vehicle energy datasets. We demonstrate that RNN-based forecasting, together with a proper selection of telemetry features used in prediction, can be effectively utilized on AGV telemetry data as a first step in anomaly detection schemes.

Super-resolution (SR) reconstruction is a common term for techniques aimed at generating a high-resolution image from a single low-resolution image or multiple images showing the same scene. Multiple-image SR benefits from data fusion which allows for more accurate reconstruction of the underlying high-resolution information. Deep learning is extensively used for single-image SR, but its application to multiple-image SR is much less explored. Recently, several deep networks were proposed to enhance Proba-V images, and in this paper, we focus on employing them to super-resolve the Sentinel-2 images. In particular, we investigate the influence of the training data, including real and simulated low-resolution images, on the final SR outcome. Also, we make the simulated data publicly available.

Super-resolution reconstruction is a process aimed at enhancing image spatial resolution. To evaluate the quality of super-resolution, the reconstruction outcome is compared with a ground-truth reference image, and the dissimilarity between them is commonly treated as a determinant of the reconstruction quality. While this is straightforward for simulated data, it becomes more challenging for real-world scenarios, in which reference images and the reconstruction inputs are acquired using different imaging sensors. In such cases, the dissimilarity also results from other factors concerned with different sensor characteristics. In a recently organized Proba-V Super Resolution Challenge, the reconstruction quality was assessed using a modified peak signal-to-noise ratio which compensates for small shifts and global changes in the brightness. In the study reported here, we investigate a number of image similarity metrics to verify their robustness against different levels of distortions applied to Proba-V images. We expect that the reported results will help in choosing appropriate metrics while developing new super-resolution solutions aimed at real-world scenarios.

Super-resolution (SR) reconstruction is a process aimed at enhancing the spatial resolution of images, either from a single observation, based on the learned relation between low and high resolution, or from multiple images presenting the same scene. SR is particularly important, if it is not feasible to acquire images at the desired resolution, while there are single or many observations available at lower resolution - this is inherent to a variety of remote sensing scenarios. Recently, we have witnessed substantial improvement in single-image SR attributed to the use of deep neural networks for learning the relation between low and high resolution. Importantly, deep learning has not been widely exploited for multiple-image super-resolution, which benefits from information fusion and in general allows for achieving higher reconstruction accuracy. In this letter, we introduce a new approach to combine the advantages of multiple-image fusion with learning the low-to-high resolution mapping using deep networks. The results of our extensive experiments indicate that the proposed framework outperforms the state-of-the-art SR methods.

The capabilities of super-resolution (SR) reconstruction (i.e., techniques for enhancing image spatial resolution) have been boosted recently by the use of deep convolutional neural networks. For SR, they are learned using huge training sets composed of original images, each of which is coupled with a low-resolution counterpart. In this paper, we explore how the SR performance depends on the procedure employed to obtain the training data. Up to date, this has not been given much attention-commonly, bicubic downsampling is used. Our extensive experimental study indicates that the training data characteristics have a large impact on the reconstruction accuracy, and the widely-adopted approach is not the most effective for dealing with satellite images. Overall, we argue that developing better training data preparation routines may be pivotal in making SR suitable for real-world applications.