A5057941086- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Thermography and Photoacoustic Techniques
- Remote Sensing and Land Use
- Industrial Vision Systems and Defect Detection
- Image Enhancement Techniques
- Visual Attention and Saliency Detection
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Remote Sensing in Agriculture
- Music and Audio Processing
- Image Retrieval and Classification Techniques
- Spectroscopy and Chemometric Analyses
- Advanced Vision and Imaging
- Image and Signal Denoising Methods
- Advanced Decision-Making Techniques
- Advanced Chemical Sensor Technologies
- Photoacoustic and Ultrasonic Imaging
- Neuroscience and Music Perception
- Arctic and Antarctic ice dynamics
- Music Technology and Sound Studies
- Geochemistry and Geologic Mapping
- Evaluation and Optimization Models
- Water Quality Monitoring Technologies
- Marine and coastal ecosystems
Robert Gordon University
2021-2024
University of Dundee
2024
Northeast Electric Power University
2023-2024
University of Strathclyde
2016-2023
Sellafield (United Kingdom)
2023
National Nuclear Laboratory
2023
Systems Research Institute
2022
Chinese Academy of Sciences
1998-2022
University of Naples Federico II
2022
Universidad Nacional Autónoma de México
2022
This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., recovery of whole- scene hyperspectral (HS) information a 3-channel image. As in previous challenge, two tracks were provided: (i) "Clean" track where HS images are estimated noise-free RGBs, themselves calculated numerically using ground-truth and supplied sensitivity functions (ii) "Real World" track, simulating capture by an uncalibrated unknown camera, recovered noisy JPEG-compressed images. A new,...
As a fundamental task in remote sensing observation of the earth, change detection using hyperspectral images (HSI) features high accuracy due to combination rich spectral and spatial information, especially for identifying land-cover variations bi-temporal HSIs. Relying on image difference, existing HSI methods fail preserve characteristics suffer from data dimensionality, making them extremely challenging deal with changing areas various sizes. To tackle these challenges, we propose...
Despite of various approaches proposed to smooth the hyperspectral images (HSIs) before feature extraction, efficacy is still affected by noise, even using corrected dataset with noisy and water absorption bands discarded. In this study, a novel spectral-spatial mining framework, Multiscale Superpixelwise Prophet Model (MSPM), for noise-robust extraction effective classification HSI. The prophet model highly deeply digging into complex structured features thus enlarging interclass diversity...
Measuring the purity of metal powder is essential to maintain quality additive manufacturing products. Contamination a significant concern, leading cracks and malfunctions in final Conventional assessment methods focus more on physical integrity rather than material composition can be time-consuming. By capturing spectral data from wide frequency range along with spatial information, hyperspectral imaging (HSI) detect minor differences terms temperature, moisture, chemical tackle this...
As a fundamental task in remote sensing earth observation, hyperspectral change detection (HCD) aims to identify the changed pixels bi-temporal images (HSIs). However, water-absorption effect, poor weather conditions, noise and inconsistent illumination as well lack of accurate ground truth has made HCD particularly challenging. To tackle these challenges, novel Accumulated Band-wise Binary Distancing (ABBD) model was proposed for unsupervised parameter-free HCD. Rather than relying on...
In this paper, we present an efficient framework to cognitively detect and track salient objects from videos. general, colored visible image in red-green-blue (RGB) has better distinguishability human visual perception, yet it suffers the effect of illumination noise shadows. On contrary, thermal is less sensitive these effects though its varies according environmental settings. To end, cognitive fusion two modalities provides effective solution tackle problem. First, a background model...
Quantifying phenolic compound in peated barley malt and discriminating its origin are essential to maintain the aroma of high-quality Scottish whisky during manufacturing process. The content total phenol varies malts, which is critical measuring associated peatiness level. Existing methods for such phenols destructive and/or time-consuming. To tackle these issues, we propose this article a novel nondestructive system fast effective estimating concentrations their origins with near-infrared...
To improve the performance of sparse representation classification (SRC), we propose a superpixel-based feature specific framework (SPFS-SRC) for spectral-spatial hyperspectral images (HSI) at superpixel level. First, HSI is divided into different spatial regions, each region shape- and size-adapted considered as superpixel. For superpixel, it contains number pixels with similar spectral characteristic. Since utilization multiple features in has been proved to be an effective strategy, have...
Through capturing spectral data from a wide frequency range along with the spatial information, hyperspectral imaging (HSI) can detect minor differences in terms of temperature, moisture, and chemical composition. Therefore, HSI has been successfully applied various applications, including remote sensing for security defense, precision agriculture vegetation crop monitoring, food/drink, pharmaceuticals quality control. However, condition monitoring damage detection carbon fiber reinforced...
As an emerging research hotspot in contemporary remote sensing, hyperspectral change detection (HCD) has attracted increasing attention sensing Earth observation, covering land mapping changes and anomaly detection. This is primarily attributable to the unique capacity of imagery (HSI) amalgamate both spectral spatial information scene, facilitating a more exhaustive analysis on Earth’s surface, proving be successful across diverse domains, such as disaster monitoring geological surveys....
The novel coronavirus disease 2019 (COVID-19) pandemic has led to a worldwide crisis in public health. It is crucial we understand the epidemiological trends and impact of non-pharmacological interventions (NPIs), such as lockdowns for effective management control its spread. We develop validate intelligent computational model predict COVID-19, with parameters enabling an evaluation NPIs. By representing number daily confirmed cases (NDCC) time-series, assume that, or without NPIs, pattern...
The principal component analysis (PCA) and 2-D singular spectral (2DSSA) are widely used for spectral- spatial-domain feature extraction in hyperspectral images (HSIs). However, PCA itself suffers from low efficacy if no spatial information is combined, while 2DSSA can extract the yet has a high computing complexity. As result, we propose this letter domain approach spectral–spatial mining HSI. Specifically, its variation, folded (FPCA) fused with 2DSSA, as FPCA both global local features....
Traditional industry is seeing an increasing demand for more autonomous and flexible manufacturing in unstructured settings, a shift away from the fixed, isolated workspaces where robots perform predefined actions repetitively. This work presents case study which robotic manipulator, namely KUKA KR90 R3100, provided with smart sensing capabilities such as vision adaptive reasoning real-time collision avoidance online path planning dynamically-changing environments. A machine module based on...
Due to its uniqueness and high value in commercial side, logos trademarks play a key role e-business based global marketing. Detecting misused faked need designated accurate image processing retrieval techniques. However, existing colour shape techniques, which are mainly designed for natural images, cannot provide effective of logo images. In this paper, an approach is proposed content-based coloured trademarks. By extracting the dominant from quantization measuring spatial similarity,...
Efficient and accurate segmentation of sea ice floes from high-resolution optical (HRO) remote sensing images is crucial for understanding evolutions climate changes, especially in coping with the large data volume. Existing methods suffer noise interference mixture water caused high error less robustness. In this article, we propose a novel floe algorithm HRO based on texture-sensitive superpixeling two-stage thresholding. First, sparse components are extracted using robust principal...
In the Sellafield nuclear site, intermediate level waste and special material is stored above ground in stainless steel packages or containers, with thousands expected to be for several decades before permanent disposal a geological facility.During this storage, are susceptible corrosion, which can potentially undermine their structural integrity.Therefore, long term monitoring required.In work, hyperspectral imaging (HSI) was evaluated as non-destructive tool detecting corrosion on...
Abstract As one of the most important subtasks automatic music transcription (AMT), multi-pitch estimation (MPE) has been studied extensively for predicting fundamental frequencies in frames audio recordings during past decade. However, how to use perception and cognition MPE not yet thoroughly investigated. Motivated by this, this demonstrates effectively detect frequency harmonic structure polyphonic using a cognitive framework. Inspired neuroscience, an integration constant Q transform...
Dimensionality reduction is of high importance in hyperspectral data processing, which can effectively reduce the redundancy and computation time for improved classification accuracy. Band selection feature extraction methods are two widely used dimensionality techniques. By integrating advantages band extraction, authors propose a new method reducing dimension image data. First, fast algorithm proposed images based on an determinantal point process (DPP). To amount calculation, dual‐DPP...