Imagery Processing Research Articles

Reviving Brasília Through Analyzing Historical Aerial Photographs

This study presents an optimized method for processing and retrieving digital data from 1950s aerial photographs of the Plano Piloto area in Brasília. In analogous contexts, internal orientation parameters are often unavailable, and external orientation parameters must be obtained through non-standard approaches, as the identification and geolocation of control points in the field becomes impractical in substantially altered landscapes. Nevertheless, advancements in computer vision techniques, integrated into modern photogrammetry software such as Agisoft Metashape®, provide a viable solution for mapping historical analog aerial photographs. The software successfully processed 156 aerial photographs, using 17 control points, yielding a historical orthoimage and a digital surface model with medium-scale accuracy. The generated model enabled precise identification of key features, including vegetation cover, land use, and terrain characteristics, providing valuable insights for the analysis of land occupation dynamics in the study area. The proposed methodology exhibits substantial potential for replication in similar cases, establishing a robust framework for the processing of historical aerial imagery.

Hyperspectral anomaly detection via low-rank and sparse decomposition with cluster subspace accumulation

Anomaly detection (AD) has emerged as a prominent area of research in hyperspectral imagery (HSI) processing. Traditional algorithms, such as low-rank and sparse matrix decomposition (LRaSMD), often struggle to effectively address challenges related to background interference, anomaly targets, and noise. To overcome these limitations, we propose a novel method that leverages both spatial and spectral features in HSI. Initially, the original HSI is segmented into several subspaces using the k-means method, which reduces redundancy among HSI bands. Subsequently, the fractional Fourier transform (FrFT) is applied within each subspace, enhancing the distinction between background and anomaly target information while simultaneously suppressing noise. To further improve the stability and discriminative power of the HSI, LRaSMD is employed. Finally, the modified Reed–Xiaoli (RX) detector is utilized to identify anomalies within each subspace. The results from these detections are then aggregated to produce a comprehensive final outcome. Experiments conducted on five real HSI data sets yield an average area under the curve (AUC) of 0.9761 with a standard deviation of 0.0156 for the proposed algorithm. These results indicate that our method is highly competitive in the field of anomaly detection.

K-means adaptive 2DSSA based on sparse representation model for hyperspectral target detection

Target detection is a hot spot in hyperspectral imagery (HSI) processing. The detection accuracy of target detection algorithms based on sparse representation (SR) models usually suffers from the high reconstruction residuals caused by inaccurate background estimations and insufficient target samples. Besides, with the development of hyperspectral imaging technology, the spatial resolution of HSI has been continuously enhanced, which can provide more spatial information for target detection. However, spatial information is often overlooked, leading to the underutilization of the pluralistic features of HSI. Target detection using only spectral information is susceptible to spectral variation, resulting in a high false alarm rate. To alleviate these problems, this paper proposes a joint spatial-spectral algorithm. In terms of spectra, a dictionary construction strategy (DCS) is designed for the sparse representation-based binary hypothesis (SRBBH) detector to reduce reconstruction residuals of target and background samples. In terms of space, k-means 2D adaptive singular spectrum analysis (KSSA) is used to extract spatial features in cluster units. Using spatial features can enhance the robustness of the algorithm to spectral variation, thereby reducing false alarms. The target detection results are obtained by applying DCS-SRBBH to the KSSA feature image. We evaluate the proposed algorithm on three datasets: two public and one of our own. Comprehensive experimental results indicate that the proposed algorithm outperforms other target detection algorithms in terms of accuracy.

Performance Mindfulness: Integrating ACT Matrix, Imagery and Mindfulness for Performance Enhancement

Mindfulness, imagery, and acceptance-based interventions have been widely applied within the sport and performance psychology domain. This paper presents a novel imagery method termed ‘Performance Mindfulness,’ which synthesizes insights from the Acceptance and Commitment Therapy (ACT) Matrix tool, the Physical, Environmental, Task, Timing, Learning, Emotion, Perspective (PETTLEP) imagery method, and principles of mindfulness. As existing imagery techniques are limited in effectively capturing the motivational and emotional dimensions of athletic performance, this integrated approach introduces a well-conceptualized, evidence-based framework rooted in Contextual Behavioral Science. This framework translates insights from the ACT Matrix into a practical tool within the imagery process and integrates principles of mindfulness to enhance the effectiveness of imagery. Performance Mindfulness is tailored for sport psychology practitioners who seek to incorporate acceptance and mindfulness principles into the mental preparation of athletes at various levels. The paper provides a detailed explanation of the technique, including concrete examples, and discusses its advantages and disadvantages comprehensively.

Boostering motor imagery processing to improve gait in patients with Parkinson disease and freezing of gait: A pilot study

BackgroundGiven that patients with Parkinson's Disease (PD) and Freezing of Gait (FoG) may lack the cognitive resources necessary to activate the motor imagery (MI) process, investigating how to boost MI vividness and accuracy could be a valuable therapeutic strategy in MI Practice (MIP). ObjectiveWe aim to evaluate the priming effect of visual, or auditory, or attentional stimuli in enhancing MI ability by using quantitative data on gait and turning performance. MethodsNineteen PD participants with FoG underwent four one-week sessions of MIP, with pre and post clinical assessments. Each session included MI alone or one of three booster MI tasks (Attentional, Action observation, or Auditory) before imagining and executing walking straight and performing a 180° turn. Gait and turning performances were evaluated using six inertial sensors before and after each session. ResultsOur findings showed that both MI and boosted MI induced similar improvement in gait (speed and stride length) and 180° (step number and velocity) and 360° turning (velocity, angle) parameters compared to baseline. When differences among “booster” tasks were analyzed, results showed that Auditory and Attentional boosted MI were superior to MI alone in some gait and turning parameters. At the end of the 4 sessions, MI ability measured by means of Kinesthetic and Visual Imagery Questionnaire and Gait Imagery Questionnaire and FoG symptoms were also improved. ConclusionOur preliminary results suggest that boosting MI is a feasible strategy for enhancing MI ability and addressing FoG symptoms. Auditory and Attentional conditions appear to enhance the priming effect of MI on gait and turning performance more effectively.

Unveiling the Power of Storytelling: A Comparative Analysis of Consumer vs. Brand Narratives in Shaping Favorable Attitude Toward Brands Through Emotions and Cognition

Storytelling, as an interactive form of communication, is key to delivering product information compellingly and fostering consumer acceptance and engagement. Stories may originate from companies or consumers. Brand storytelling has emerged as a pivotal component of companies' communication strategies, facilitating the expression of values and fostering robust customer relationships. This study explores the effectiveness of consumer storytelling versus brand storytelling in shaping brand attitudes. It was an experimental research involving 384 respondents randomly assigned to two groups that were either exposed to consumer or brand stories. Through comparative analysis, consumer storytelling emerged as superior in eliciting positive brand attitudes, cognition, and emotions. However, its direct impact on brand attitude was not significant. Instead, the study uncovers the mediating role of cognition and emotion, highlighting their crucial influence on shaping favorable brand perceptions. Consumer storytelling, characterized by its emphasis on real values and emotional engagement, enhances cognitive personalization and imagery processing, fostering deeper consumer-brand connections. These insights underscore the imperative for emotionally resonant and cognitively stimulating storytelling in brand communication. This study contributes to the scant literature on examining the comparative effectiveness of consumer brand storytelling versus firm-generated brand storytelling. It elucidates the underlying mechanisms driving the superiority of consumer storytelling in shaping favorable brand attitudes. Contextually situated within the Pakistani market, particularly focusing on clothing buying behavior, this research offers actionable insights for brand managers seeking to harness the power of storytelling to garner favorable consumer responses and enhance brand resonance.

Geometric Characterization of the Mateur Plain in Northern Tunisia Using Vertical Electrical Sounding and Remote Sensing Techniques

The Mateur aquifer system in Northern Tunisia was examined using data from 19 water boreholes, 69 vertical electrical sounding (VES) stations, and a Sentinel-2 satellite image. Available boreholes and their corresponding logs were compared to define precisely the multi-layer aquifer system, including the Quaternary and Campanian aquifers of the Mateur plain. Quantitative interpretation and qualitative evaluation of VES data were conducted to define the geometry of these reservoirs. These interpretations were enhanced by remote sensing imagery processing, which enabled the identification of the Mateur plain’s superficial lineaments. Based on well log information, the lithological columns show that the Quaternary series in the Ras El Ain region contains a layer of clayey, pebbly, and gravelly limestone. Additionally, in the Oued El Tine area, a clayey lithological unit has been identified as a multi-layer aquifer. The study area, exhibiting apparent resistivity values ranging between 20 and 170 Ohm·m, appears to be rich in groundwater resources. The correlation between the lithological columns and the interpreted VES data, presented as geoelectrical cross-sections, revealed variations in depth (8–106 m), thickness (10 to 55 m), and resistivity (20–98 Ohm·m) of a coarse unit corresponding to the Mateur aquifer. Twenty-three superficial lineaments were extracted from the Sentinel-2 image. Their common superposition indicated that both of them are in a good coincidence; these could be the result of normal faults, creating an aquifer system divided into raised and sunken blocks.

A systematic review and meta-analysis of experimental methods for modulating intrusive memories following lab-analogue trauma exposure in non-clinical populations.

Experiencing trauma leads to intrusive memories (IMs), a hallmark symptom of post-traumatic stress disorder (PTSD), which also occurs transdiagnostically. Understanding why IMs increase or decrease is pivotal in developing interventions to support mental health. In this preregistered meta-analysis (PROSPERO: CRD42021224835), we included 134 articles (131 techniques, 606 effect sizes and 12,074 non-clinical participants) to investigate how experimental techniques alter IM frequency, intrusion-related distress and symptoms arising from lab-analogue trauma exposure. Eligible articles were identified by searching eight databases until 12 December 2023. To test potential publication biases, we employed methods including Egger's test and three-parameter selection models. We employed three-level multilevel modelling and meta-regressions to examine whether and how experimental techniques would modulate IM frequency and associated outcomes. Results showed that techniques (behavioural, pharmacological, neuromodulation) significantly reduced intrusion frequency (g = 0.16, 95% confidence interval [0.09, 0.23]). Notably, techniques aimed to reduce IMs also ameliorated intrusion-related distress and symptoms, while techniques that increased IMs exacerbated these related outcomes, thus highlighting IM's centrality in PTSD-like symptoms. Techniques tapping into mental imagery processing (for example, trauma reminder followed by playing Tetris) reduced intrusions when administered immediately after, or at a delayed time after trauma. Although our meta-analysis is limited to symptoms induced by lab-analogue trauma exposure, some lab-based results have now generalized to real-world trauma and IMs, highlighting the promising utility of lab-analogue trauma paradigms for intervention development.

DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition

The integration of Unmanned Aerial Vehicles (UAVs) with artificial intelligence (AI) models for aerial imagery processing in disaster assessment, necessitates models that demonstrate exceptional accuracy, computational efficiency, and real-time processing capabilities. Traditionally Convolutional Neural Networks (CNNs), demonstrate efficiency in local feature extraction but are limited by their potential for global context interpretation. On the other hand, Vision Transformers (ViTs) show promise for improved global context interpretation through the use of attention mechanisms, although they still remain underinvestigated in UAV-based disaster response applications. Bridging this research gap, we introduce DiRecNetV2, an improved hybrid model that utilizes convolutional and transformer layers. It merges the inductive biases of CNNs for robust feature extraction with the global context understanding of Transformers, maintaining a low computational load ideal for UAV applications. Additionally, we introduce a new, compact multi-label dataset of disasters, to set an initial benchmark for future research, exploring how models trained on single-label data perform in a multi-label test set. The study assesses lightweight CNNs and ViTs on the AIDERSv2 dataset, based on the frames per second (FPS) for efficiency and the weighted F1 scores for classification performance. DiRecNetV2 not only achieves a weighted F1 score of 0.964 on a single-label test set but also demonstrates adaptability, with a score of 0.614 on a complex multi-label test set, while functioning at 176.13 FPS on the Nvidia Orin Jetson device.

The Identification, Spatial Distribution, and Reconstruction Mode of Abandoned Mining Areas

The rehabilitation of abandoned mining sites is an increasingly pressing issue in the context of sustainable development. Recent research has emphasized the need for a holistic approach to the abandoned mining sites and their environmental rehabilitation. Based on field analysis, environmental assessments, satellite imagery processing and geographic information operations, this paper pushes forward the existing knowledge by conducting a comprehensive assessment of abandoned mining sites in the Romanian Carpathians and by proposing innovative and sustainable rehabilitation solutions. Our findings highlight that abandoned mining sites and their surrounding territories in the Romanian mountains have significant ecological imbalances and complex socio-economic issues. The findings also suggest that by adopting innovative, integrated, and sustainability-oriented approaches, territories affected by mining can be transformed into valuable and sustainable spaces to meet human needs. We conclude by presenting the importance of innovation in ecological reconstruction and spatial–functional reintegration of mining sites in mountain areas as a useful tool in making fair decisions, both in the context of implementing appropriate development policies as well as for the resilience and environmental sustainability of mining-affected mountain areas.

Progressive updates of convolutional neural networks for enhanced reliability in small satellite applications

Small satellites enable many important applications for both economic and scientific purposes. Many of these applications are inherently data-centric and rely on large amounts of high-resolution satellite imagery to be delivered in a timely manner. However, communicating this data to Earth is challenging due to intermittent connectivity, high packet losses, low data rates, and similar issues. Therefore, efficient onboard prioritization and data processing are essential for future satellite missions. Machine learning methods, such as deep neural networks, are very suitable for such prioritization, as they are already used extensively for satellite imagery processing and they can be deployed onboard of satellites. However, updating them to support new classification requirements when the satellite is already in orbit is difficult, as often multiple passes are required to complete model transmission due to the communication challenges. To cope with this issue, we propose a progressive transmission mechanism for model updates, which leverages vector quantization and arithmetic coding. Our mechanism allows to achieve high accuracies even with partially updated models. Evaluation results show that our mechanism significantly outperforms other less optimized transmission schemes.

UAV Mapping for Flood Routing in Steep and Densely Vegetated Areas: Insights from the Contok River Basin, Garang Watershed, Indonesia

This research utilizes photogrammetry to assess flood routing dynamics in the Contok river basin, a sub-watershed with a challenging landscape characterized by steep slopes, dense vegetation, and meandering patterns. The objectives are to assess Unmanned Aerial Vehicle (UAV) mapping accuracy, evaluate the river's capacity for design flood volumes, quantify the impact of land cover changes on surface runoff, and provide insights for early warning systems and watershed conservation strategies. The study area, encompassing the Contok River Basin, a sub-watershed of the Garang Watershed, covers 7,413 km² and includes a stream length of 5,274 meters in Semarang City, Central Java, Indonesia. This research employed image processing of aerial photographs and satellite imagery. Aerial photos captured using UAV data were utilized to derive elevation data and cross-sectional profiles of the Contok River, essential for understanding channel morphology and hydraulic characteristics. Concurrently, satellite imagery was used for land cover analysis, identifying vegetation and built-up areas that influence surface runoff dynamics. Hydrological analysis was performed to quantify discharge magnitudes, simulated against river cross-sections to evaluate flood behavior under varying scenarios. Our proposed UAV mapping provides adequate accuracy for small and local areas. Furthermore, it remains reliable for flood routing analysis. We discovered that the capacity of the Contok River channel in the downstream area allows it to convey design flood discharges up to a 50-year return period, contrary to the upstream area, it overflows. Notably, the shift from vegetated to built-up and agricultural areas significantly contributes to the 10.6% increase in surface runoff. This research highlights the role of UAV-based photogrammetry in assessing and mitigating flood hazards amidst evolving land cover patterns. It also enhances the understanding of flood dynamics and thus provides insights that will serve as a reference for flood early warning systems, flood management practices, and watershed conservation.

EGMS-toolkit: a set of Python scripts for improved access to datasets from the European Ground Motion Service

Continental-scale, open-access datasets of ground surface displacement in all countries of the European Union, plus Norway, United Kingdom, and Iceland, are now available from the European Ground Motion Service (EGMS). Under the European Union’s Copernicus program, the EGMS has been available since the end of 2022 and will continue for the foreseeable future. The EGMS data are presently derived from Interferometric Synthetic Aperture Radar (InSAR) processing of the Sentinel-1 SAR satellite imagery, which has been collected from 2015 to date. While EGMS data can be visualised and obtained through an online platform (EGMS Explorer), the data access arrangements are inefficient for large-scale analysis of ground surface displacements due to the volume of data, the tile-formatting of datasets and some server limitations. Here we present a Python-based toolkit, named EGMS-toolkit, to provide a unified and more efficient workflow for accessing EGMS datasets. The toolkit can automatically detect and download EGMS datasets based on a Region of Interest provided by users, then it can merge, clip, and crop the results to that region regardless of its scale. The toolkit then produces files of EGMS ground surface motions in GIS-ready formats for further analysis.

Evaluating Linear Coral Growth Estimation Using Photogrammetry and Alternative Point Cloud Comparison Methods

Abstract. Corals are critical reef-building organisms, providing essential habitat and ecosystem services. Tracking coral growth over time indicates coral reef health, which can be measured using various established techniques. Several coral growth-related studies have successfully applied photogrammetry to a particular coral of various types. While the focus of previous work was on standardised data processing and, to a certain degree, on the assessment of different point cloud comparison methods (Lange et al. 2022), little attention has been given to the impact of camera calibration. This study measured the annual linear extension of five Acropora spp. colonies using photogrammetry and evaluated all stages of imagery processing. A high focus was given to the analysis of the camera calibration method and the validation of camera parameters derived using an in-situ calibration of coral images with scale bars placed in the camera's field of view. We demonstrate that this method is as reliable as the calibration using a calibration frame. This study also examined the impact of the different point cloud comparison methods for Acropora spp. More specifically, the derived point clouds are compared by applying the point-to-point and point-to-model methods and manually selecting 12 coral branch tips. Histograms derived from the comparison methods were analysed and deemed a suitable and efficient alternative approach for measuring the maximum growth rate of mature colonies over shorter time periods (1 year or less).

Presentation-order effect of product images on consumers’ mental imagery processing and purchase intentions

PurposeThis study aims to investigate how image-presentation-order influences mental imagery (MI) processing and purchase intentions. This study also examines the moderating effect of a series of images on the relationship between image-presentation-order and MI processing.Design/methodology/approachThis research conducted two studies using an experimental approach.FindingsTwo studies showed that MI processing was higher, when an apparel product image worn by a model with a background was shown after rather than before a simple product image (SPI), indicating the recency effect. In contrast, examining a series of images, consumers were more engaged in MI processing, when product image(s) worn by a model with a background were presented first, followed by the four SPIs, than the reversed order (primacy effect). The level of MI in two studies subsequently increased purchase intentions.Research limitations/implicationsResults of this study have the potential to provide guidance to online retailers for how to best order their product images on a website to help consumers form elaborated MI about the product and thus increase purchasing intentions.Originality/valueAlthough past research has examined presentation-order effect using textual information, very limited studies have explored presentation-order effect of pictorial information. To the best of the authors’ knowledge, this research is in the forefront of investigations about the joint effect of image-presentation-order and the number of images on individuals’ perceptions.

Inequivalent and uncorrelated response priming in motor imagery and execution.

Theoretical considerations on motor imagery and motor execution have long been dominated by the functional equivalence view. Previous empirical works comparing these two modes of actions, however, have largely relied on subjective judgments on the imagery process, which may be exposed to various biases. The current study aims to re-examine the commonality and distinguishable aspects of motor imagery and execution via a response repetition paradigm. This framework aims to offer an alternative approach devoid of self-reporting, opening the opportunity for less subjective evaluation of the disparities and correlations between motor imagery and motor execution. Participants performed manual speeded-choice on prime-probe pairs in each trial under three conditions distinguished by the modes of response on the prime: mere observation (Perceptual), imagining response (Imagery), and actual responses (Execution). Responses to the following probe were all actual execution of button press. While Experiment 1 compared the basic repetition effects in the three prime conditions, Experiment 2 extended the prime duration to enhance the quality of MI and monitored electromyography (EMG) for excluding prime imagery with muscle activities to enhance specificity of the underlying mechanism. In Experiment 1, there was no significant repetition effect after mere observation. However, significant repetition effects were observed in both imagery and execution conditions, respectively, which were also significantly correlated. In Experiment 2, trials with excessive EMG activities were excluded before further statistical analysis. A consistent repetition effect pattern in both Imagery and Execution but not the Perception condition. Now the correlation between Imagery and Execution conditions were not significant. Findings from the current study provide a novel application of a classical paradigm, aiming to minimize the subjectivity inherent in imagery assessments while examining the relationship between motor imagery and motor execution. By highlighting differences and the absence of correlation in repetition effects, the study challenges the functional equivalence hypothesis of imagery and execution. Motor representations of imagery and execution, when measured without subjective judgments, appear to be more distinguishable than traditionally thought. Future studies may examine the neural underpinnings of the response repetition paradigm to further elucidating the common and separable aspects of these two modes of action.

Betrayal in words: Examining the issues with translation difficulties

The translation has faced substantial opposition since its inception, as a multitude of scholars argue that it undermines the authenticity of the source material. Intentionally or unintentionally, challenges and acts of disloyalty occur during the translation process of grammatical structures, phrases, proverbs, quips, verbal imagery, poetry, and other components, according to this assertion. Additionally, translating commonly used terms that frequently conflict with the target language may present challenges. This subject is written in a descriptive and scholarly language. The research possesses importance in its translation, regardless of whether it is presented in prose or poetry format. It enhances the verbiage and fulfills the requirements of the audience. It also provides assistance to educators in the subject of education. Translation serves as a highly effective means of transmitting knowledge. Nonetheless, its efficacy and dependability are contingent on the subject matter's integrity being maintained. This objective can be realized when the translator demonstrates fluency in both languages and has in-depth understanding of the local customs, dialects, and subtleties.

Methods of studying the literary image in the works of poets-storytellers of the land of Syr at the university

Relevance. The relevance of the study is conditioned upon the fact that today, an important place in Kazakhstani and world literature is occupied by works that are related to religion, moral development, and education. The creativity of the poets-storytellers of the land of Syr has a special influence on the upbringing of the future generation and the cultivation of important positive qualities in them (honesty, erudition, loyalty, decency, morality). Their works have a great influence on the development of students' worldviews and raising the spiritual level of the people of Kazakhstan. Purpose. This study is aimed at investigating the religious and educational value of the creativity of the poets-storytellers of the land of Syr and the processes of studying their creativity in universities. Methodology. The leading methods of studying this problem are methods of analysis, classification, induction and deduction, generalisation, and comparison of approaches, which will help to identify and highlight the main aspects of the pedagogical problem of studying the imagery of poets of the Kyzylorda region. Results. The study covers aspects of the activity of the poets of the land of Syr; shows the process of teaching imagery in universities of Kazakhstan; demonstrates the factors and methods of this phenomenon; makes a detailed analysis of literature and clarifies the content, characteristics, and features of the works of Akyns who lived in the territory of the Kyzylorda region; covers the main points, themes, and motives of the poetry of representatives of the Akyns-Zhyrau school. Conclusions. The materials of the study are of practical and theoretical value for students, philologists, literary critics, and teachers at universities and educational organisations who need to know the specific features of methods and forms of teaching students the works of poets-storytellers of the land of Syr. Keywords: imagery; poets-storytellers; pedagogical process; zhyrau; Kazakh language; people

Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys.

Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.

An Introduction to Machine and Deep Learning Methods for Cloud Masking Applications

Cloud cover assessment is crucial for meteorology, Earth observation, and environmental monitoring, providing valuable data for weather forecasting, climate modeling, and remote sensing activities. Depending on the specific purpose, identifying and accounting for pixels affected by clouds is essential in spectral remote sensing imagery. In applications such as land monitoring and various remote sensing activities, detecting/removing cloud-contaminated pixels is crucial to ensuring the accuracy of advanced processing of satellite imagery. Typically, the objective of cloud masking is to produce an image where every pixel in a satellite spectral image is categorized as either clear or cloudy. Nevertheless, there is also a prevalent approach in the literature that yields a multi-class output. With the progress in Machine and Deep Learning, coupled with the accelerated capabilities of GPUs, and the abundance of available remote sensing data, novel opportunities and methods for cloud detection have emerged, improving the accuracy and the efficiency of the algorithms. This paper provides a review of these last methods for cloud masking in multispectral satellite imagery, with emphasis on the Deep Learning approach, highlighting their benefits and challenges.