The Cubert ULTRIS breaks new ground as the first HSI camera that is based on the light field technology. The camera features an Ultra-HD CMOS sensor with 20 MP, making it to the imaging spectrometer with the world-wide highest available resolution. The camera provides a native image resolution of 410×410 px with 100 spectral channels, continuously covering the wavelength range from 350 nm – 1000 nm (± 10nm).
The ULTRIS records an object with a multitude of images, each with its own optical bandpass filter with different center wavelength. This is made possible by combining a continuously variable bandpass filter with a lenslet array. Applying this concept to the UHD sensor, the previously unheard number of over 160,000 spectra is acquired simultaneously.
Nominee for SPIE 2021 Prism Award
GOLD Medal award winner of Vision
Systems Design Innovators 2020, USA
Nominee for inspect award 2021 based on Light Field Technology
wavelength range: VNIR 350-1000nm
(± 10nm), 100 bands
spatial resolution: 410×410 px
spectral (168,100 spectra per cube)
Light-Weight Design: <350g Standard, Industrial and Waterproof Housing available perClass Mira compatible
Technology: | Light Field |
Spectral Channels: | 164 |
Spectral throughput [spectra/capture]: | 168100 |
Wavelength range [nm]: | 350-1000 |
Cube resolution [pixel]: | 410 x 410 x 164 |
Cube rate [fps]: | max 8 (Complete data-cubes per second) |
Digitization [Bit]: | 12 |
Camera interface: | 1-2 Gig E |
Camera connections: | Power, Trigger In |
Camera storage: | ext. |
Operating temperature [°С]: | +5 – +65 |
Weight without lens [g]: | 350 |
Power [V, W]: | 12V / 10W |
Size Standard [mm]: | 60x60x57 |
Cubert systems fully supports perClass Mira, a user interface for interpretation of hyperspectral images. It allows users to define classification and regression solutions and deploy them in the live applications of Cubert cameras. Mira provides automatic machine learning without pro-gramming and enables the users to interactively improve their solutions.
perClass Mira, fully compatible to Cubert Utils camera control software, brings state-of-the-art machine learning research to industrial practitioners and researchers.
A conventional color image has three colors per pixel (red, green, and blue), but a hyperspectral image can have hundreds of colors across the electromagnetic spectrum.