hyperspectral imaging
PulseAugur coverage of hyperspectral imaging — every cluster mentioning hyperspectral imaging across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New method uses hyperspectral imaging for occluded object localization
Researchers have explored a new method for localizing occluded objects in single hyperspectral images, leveraging material properties and optical blur. The proposed pipeline combines non-negative matrix factorization fo…
-
Hyperspectral Imaging Enhances Planetary Rover Navigation in SLAM Systems
Researchers have developed HyperLoop, a novel framework that integrates hyperspectral imaging (HSI) into 3D-SLAM systems for planetary exploration. This approach aims to improve autonomous navigation in visually repetit…
-
SPECTRA-VLA enhances hyperspectral imaging in frozen vision-language-action models
Researchers have introduced SPECTRA-VLA, a novel method for enhancing hyperspectral imaging capabilities within existing vision-language-action models. This approach allows for spectral upgrades without the need to retr…
-
AI-enhanced hyperspectral imaging shows promise for low-grade glioma detection
A new clinical study published on arXiv details the use of AI-enhanced hyperspectral imaging (HSI) for detecting low-grade gliomas (LGGs) during surgery. Unlike previous studies focusing on higher-grade tumors, this res…
-
Machine learning models improve perceptual color difference estimation
Researchers have developed a new machine learning approach to model perceptual color differences, aiming to improve upon existing metrics like CIEDE2000. By collecting similarity judgments from human observers on 2,000 …
-
New Functional Tucker Decomposition Enhances Tensor Analysis
Researchers have developed a novel functional Tucker decomposition (FTD) that embeds continuity constraints into tensor factorization. This method models continuous modes as functions within a reproducing kernel Hilbert…
-
New M2Heat Framework Fuses Hyperspectral and LiDAR Data for Interpretable Classification
Researchers have developed M2Heat, a novel framework for fusing hyperspectral and LiDAR data to improve land-cover classification. This physics-inspired approach models multimodal fusion using principles of heat conduct…
-
New OmniRSCLIP framework adapts language-image models for multi-source remote sensing
Researchers have developed OmniRSCLIP, a novel contrastive learning framework designed to adapt existing language-image models for multi-source remote sensing data. This framework extends the capabilities of CLIP beyond…
-
New HSR framework enhances detail transfer from RGB to hyperspectral images
Researchers have developed a new framework for RGB-guided hyperspectral super-resolution (HSR) that addresses limitations in existing methods. This framework combines cross-modal flow alignment with model-based Gram-Sch…
-
New dataset "Minerals in the Wild" released for mineral characterization
Researchers have introduced "Minerals in the Wild," a new dataset designed to advance mineral characterization using hyperspectral imaging and X-ray fluorescence. The dataset contains over 1,100 rock specimens from Euro…
-
New HyDiff-EI framework enhances hyperspectral image inpainting
Researchers have introduced Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI), a novel self-supervised framework designed for hyperspectral image inpainting. This method distinguishes itself by learning directly f…
-
ICE seeks access to US voter data for fraud detection, raising concerns
The U.S. Immigration and Customs Enforcement (ICE) agency is seeking a federal contractor to access and manage voter registration and history data from across the country. While ICE states the data is intended for fraud…
-
New deep learning models assess fish freshness using hyperspectral imaging · 2 papers
Researchers have developed two novel deep learning approaches for assessing fish freshness using hyperspectral imaging. The first, SGNet, is a lightweight architecture designed to efficiently extract spectral and spatia…
-
New AI framework enhances archaeological sensing data quality
Researchers have developed a multimodal machine-learning framework designed to improve the calibration and quality assessment of archaeological sensing workflows. This framework integrates various data types from photog…
-
UAV hyperspectral imaging paper details PFM-1 mine detection methods
This paper explores methods for detecting PFM-1 landmines using unmanned aerial vehicle (UAV) hyperspectral imaging (HSI). Researchers compared several detection algorithms, including spectral angle mapper (SAM), matche…
-
New Pipeline Maps 3D Hyperspectral Data of Surgical Specimens
Researchers have developed a new pipeline that combines hyperspectral imaging with 3D reconstruction for analyzing ex-vivo lumpectomy specimens. This system uses a deep-learning Structure-from-Motion backbone and ArUco …
-
New PGU-Net method enables blind spectral super-resolution
Researchers have developed a new physics-guided deep unfolding network called PGU-Net to tackle blind cross-sensor spectral super-resolution. This method can reconstruct hyperspectral images from multispectral images ev…
-
Phy-CoSF enables continuous spectral reconstruction and super-resolution for imaging
Researchers have introduced Phy-CoSF, a novel method for reconstructing and enhancing hyperspectral images captured by coded aperture snapshot spectral imaging (CASSI) systems. This approach utilizes deep unfolding netw…
-
Hyperspectral foundation models achieve better segmentation via cross-domain transfer
Researchers have introduced a novel cross-domain transfer method for hyperspectral imaging (HSI) semantic segmentation. This approach reuses HSI foundation models trained in remote sensing for proximal sensing applicati…
-
FOCUS framework enhances hyperspectral imaging interpretability for Vision Transformers
Researchers have developed FOCUS, a novel framework designed to enhance the interpretability of Vision Transformers (ViTs) when applied to hyperspectral imaging (HSI). This method addresses challenges in understanding V…