Stitching technique based on SURF for Hyperspectral Pushbroom Linescan Cameras

Villa, Miguel; Sancho, Jaime; Villanueva, Marta; Urbanos, Gemma; Sutradhar, Pallab; Rosa, Gonzalo; Vázquez, Guillermo; Martin, Alberto J. M.; Chavarrías, Miguel; Pérez, Luís Álvarez; Núñez, Ángel P.; Lagares, Alfonso; Juárez, E.; Sanz, C.

doi:10.1109/dcis53048.2021.9666155

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although three HS cameras have been utilized to acquire images, the captures taken from the Ximea linescan camera provided many difficulties when reconstructing HS cubes with the non-flat surface of the brains. Theses issues have been described in published works 30 , being the most noticeable one the fact the black stripes, with empty information, remain in the postprocess reconstructed HS cubes due to not moving precisely the actuator that holds the camera. Therefore, the corresponding hyperspectral cubes have not been reconstructed properly to be labeled.…”

Section: Technical Validationmentioning

confidence: 98%

SLIM Brain Database: A Multimodal Image Database of In-vivo Human Brains for Tumour Detection

Martín-Pérez,

Villa,

Olmeda

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Hyperspectral imaging (HSI) and machine learning (ML) have been employed in the medical field for classifying highly infiltrative brain tumors. Although existing HSI databases of in-vivo human brains are available, they present two main deficiencies. Firstly, the amount of labeled data is scarce and secondly, 3D-tissue information is unavailable. To address both issues, we present the SLIM Brain database, a multimodal image database of in-vivo human brains which provides HS brain tissue data within the 400-1000 nm spectrum, as well as RGB, depth and multi-view images. Two HS cameras, two depth cameras and different RGB sensors were used to capture images and videos from 193 patients. All data in the SLIM Brain database can be used in a variety of ways, for example to train ML models with more than 1 million HS pixels available and labeled by neurosurgeons, to reconstruct 3D scenes or to visualize RGB brain images with different pathologies, offering unprecedented flexibility for both the medical and engineering communities

show abstract

Section: Technical Validationmentioning

confidence: 98%

SLIM Brain Database: A Multimodal Image Database of In-vivo Human Brains for Tumour Detection

Martín-Pérez,

Villa,

Olmeda

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Transmittance Hyperspectral Capture System and Methodology Assessment for Blood-Liquid Serum Samples Analysis

Rosa,

Carabias,

Alves

et al. 2023

2023 26th Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

Double-dispersive spatio-spectral scanning for hyperspectral Earth observation

Hinderberger¹,

Grusche²,

Losekamm³

2023

Optica

View full text Add to dashboard Cite

Most instruments for hyperspectral Earth observation rely on dispersive image acquisition via spatial scanning. In such systems, the Earth’s surface is scanned line by line while the satellite carrying the instrument moves over it. The spatial and spectral resolutions of the image acquisition are directly coupled via a slit aperture and are thus difficult to adjust independently. Spatio-spectral scanning systems, on the other hand, can acquire 2D, spectrally coded images with decoupled spatial and spectral resolutions. Despite this advantage, they have so far been given little attention in the literature. Simple architectures using variable filters were proposed, but come with significant caveats. As an alternative, we investigated the use of two dispersion stages for spatio-spectral scanning. We provide a theoretical treatment and show by basic experiments that a double-dispersive system provides robust and flexible image acquisition. Based on our results, we suggest a system concept for the implementation of a demonstrator on a small satellite.

show abstract

Stitching technique based on SURF for Hyperspectral Pushbroom Linescan Cameras

Cited by 3 publications

References 6 publications

SLIM Brain Database: A Multimodal Image Database of In-vivo Human Brains for Tumour Detection

SLIM Brain Database: A Multimodal Image Database of In-vivo Human Brains for Tumour Detection

Transmittance Hyperspectral Capture System and Methodology Assessment for Blood-Liquid Serum Samples Analysis

Double-dispersive spatio-spectral scanning for hyperspectral Earth observation

Contact Info

Product

Resources

About