Spectral imaging in crop monitoring and disease diagnosis: A comprehensive review

CABI Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 26, 2025

Abstract Spectral imaging is a technique that captures and analyzes the spectral information of an object, such as its reflectance, transmittance, or fluorescence. It has been widely used in various fields, remote sensing, food quality assessment. In recent years, also emerged promising tool for crop disease diagnosis, it can provide rapid, non-destructive, accurate detection plant pathogens symptoms. This review aims to concise overview principles, methods, applications, challenges diagnosis. First, we introduce basic sensing concepts types imaging, hyperspectral, multispectral imaging. Second, discuss main steps techniques involved analysis, image acquisition, processing, feature extraction, classification. Third, present some representative examples applications fungal, bacterial, viral, nematode infections. Finally, highlight importance artificial intelligence integration alongside current limitations future directions

Language: Английский

---

Advancing Urban Development: Applications of Hyperspectral Imaging in Smart City Innovations and Sustainable Solutions

Smart Cities, Journal Year: 2025, Volume and Issue: 8(2), P. 51 - 51

Published: March 14, 2025

Smart cities are urban areas that use advanced technologies to make living better through efficient resource management, sustainable development, and improved quality of life. Hyperspectral imaging (HSI) is a noninvasive nondestructive technique revolutionizing smart by offering real-time monitoring analysis capabilities across multiple sectors. In contrast with conventional technologies, HSI capable capturing data wider range wavelengths, obtaining more detailed spectral information, in turn, higher detection classification accuracies. This review explores the diverse applications cities, including air water monitoring, effective waste planning, transportation, energy management. study also examines advancements sensor data-processing techniques, integration Internet things, emerging trends, such as combining artificial intelligence machine learning for various city applications, providing real-time, data-driven insights enhance public health infrastructure. Although may generate complex tends cost much, its potential transform into smarter environments vast, discussed this review.

Language: Английский

---

Multi-Directional Dual-Window Method Using Fractional Optimal-Order Fourier Transform for Hyperspectral Anomaly Detection

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1321 - 1321

Published: April 8, 2025

Anomaly detection plays a vital role in the processing of hyperspectral images and has garnered significant attention recently. Hyperspectral are characterized by their “integration spatial spectral information” as well rich content. Therefore, effectively combining information thoroughly mining latent structural features data to achieve high-precision challenges anomaly detection. Traditional methods, which rely solely on raw features, often face limitations enhancing target signals suppressing background noise. To address these issues, we propose an innovative approach based fractional optimal-order Fourier transform combined with multi-directional dual-window detector. First, new criterion for determining optimal order is introduced. By applying transform, prominent extracted from data. Subsequently, band selection applied transformed remove redundant retain critical features. Additionally, sliding RAD detector designed. This fully utilizes pixel under test along its neighboring eight directions enhance accuracy. Furthermore, spatial–spectral saliency-weighted strategy developed fuse results various using weighted contributions, further improving distinction between anomalies background. The proposed method’s experimental six classic datasets demonstrate that it outperforms existing detectors, achieving superior performance.

Language: Английский

---

A lightweight spatial and spectral CNN model for classifying floating marine plastic debris using hyperspectral images

Marine Pollution Bulletin, Journal Year: 2025, Volume and Issue: 216, P. 117965 - 117965

Published: April 18, 2025

Marine plastic debris poses a significant environmental threat. In order to study and combat this pollution, efficient automated detection methods are essential. Hyperspectral imaging deep learning provide robust framework for classifying floating marine debris. However, approaches often suffer from high computational complexity limited interpretability. addition, hyperspectral images high-dimensional data that must be analyzed efficiently. To overcome these limitations, paper proposes the Lightweight Spatial Spectral CNN (LSS-HCNN), model designed enhance classification accuracy while improving efficiency The proposed first applies spatialwise convolutions extract spatial features individual spectral bands, then uses spectralwise relationships between bands. Additionally, Squeeze-and-Excitation (SE) block improves interpretability by focusing on most informative Experiments were conducted three datasets containing various materials four dedicated datasets, including new waste dataset. It provides in configurations: visible-near-infrared (VIS-NIR), near-infrared-shortwave-infrared (NIR-SWIR), fused domain. Results show LSS-HCNN outperforms traditional handcrafted descriptors deep-learning models, particularly plastics. achieves mean of 97.64% reducing complexity. Compared standard 2D-CNN, it reduces number parameters over 80% Floating Point Operations (FLOPS) factor 7. Moreover, SE analysis reveals NIR-SWIR bands contribute classification. This highlights as an model, supporting monitoring efforts.

Language: Английский

---

Modern Trends and Recent Applications of Hyperspectral Imaging: A Review

Technologies, Journal Year: 2025, Volume and Issue: 13(5), P. 170 - 170

Published: April 23, 2025

Hyperspectral imaging (HSI) is an advanced technique that captures detailed spectral information across multiple fields. This review explores its applications in counterfeit detection, remote sensing, agriculture, medical imaging, cancer environmental monitoring, mining, mineralogy, and food processing, specifically highlighting significant achievements from the past five years, providing a timely update several It also presents cross-disciplinary classification framework to systematically categorize medical, environment, industry. In HSI identified fake currency with high accuracy 400–500 nm range achieved 99.03% F1-score for alcohol detection. Remote sensing include hyperspectral satellites, which improve forest by 50%, soil organic matter, prediction reaching R2 = 0.6. HSI-TransUNet model 86.05% crop classification, disease detection reached 98.09% accuracy. Medical benefits HSI’s non-invasive diagnostics, distinguishing skin 87% sensitivity 88% specificity. colorectal identification 86% 95% Environmental PM2.5 pollution 85.93% marine plastic waste 70–80% egg freshness 91%, pine nut 100% Despite advantages, faces challenges like costs complex data processing. Advances artificial intelligence miniaturization are expected accessibility real-time applications. Future advancements anticipated concentrate on integration of deep learning models automated feature extraction decision-making analysis. The development lightweight, portable devices will enable more on-site healthcare, monitoring. Moreover, processing methods enhance efficiency field deployment. These improvements seek accessibility, practicality, efficacy both industrial clinical environments.

Language: Английский

---

Advances in vegetation mapping through remote sensing and machine learning techniques: a scientometric review

European Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 57(1)

Published: Oct. 30, 2024

This study explores the rapid growth in remote-sensing technologies for vegetation mapping, driven by integration of advanced machine learning techniques. An analysis publication trends from Scopus indicates significant expansion 2019 to 2023, reflecting technological advancements and improved accessibility. Incorporating algorithms like random forest, support vector machines, neural networks, XGBRFClassifier has enhanced monitoring dynamics at various scales. progress supports addressing global environmental challenges such as climate change providing timely data conservation strategies. China leads research output, followed United States India, underscoring field's significance. Key journals, including "Remote Sensing," conferences IGARSS, play pivotal roles disseminating findings. The majority publications are articles, emphasizing reliance on original empirical data. multidisciplinary nature is evident, with contributions spanning Earth Sciences, Agriculture, Environmental Science, Computer Science. Visualisations using VOSviewer reveal interconnected themes, highlighting topics land use, change, aboveground biomass. findings emphasise importance continued international collaboration develop innovative solutions sustainability.

Language: Английский

---

Towards the Future of Ubiquitous Hyperspectral Imaging: Innovations in Sensor Configurations and Cost Reduction for Widespread Applicability

Technologies, Journal Year: 2024, Volume and Issue: 12(11), P. 221 - 221

Published: Nov. 6, 2024

Hyperspectral imaging is currently under active development as a method for remote sensing, environmental monitoring and biomedical diagnostics. The of hyperspectral sensors aimed at their miniaturization reducing the cost components purpose widespread use such devices on unmanned aerial vehicles satellites. In this review, we present broad overview recent work devices’ configurations, studies modifying possibility devices. addition, will main trends in device configurations ubiquitous applications.

Language: Английский

---

Transforming High-Resolution Imaging: A Comprehensive Review of Advances in Metasurfaces and Metalenses

Materials Today Physics, Journal Year: 2024, Volume and Issue: unknown, P. 101628 - 101628

Published: Dec. 1, 2024

Language: Английский

---