VIS-NIR hyperspectral cameras

Photoniques ◽  
2021 ◽  
pp. 58-64
Author(s):  
Stéphane Tisserand
Keyword(s):  
Multispectral Imaging ◽  
Three Dimensional ◽  
Spectral Domain ◽  
Spectral Bands ◽  
Cmos Sensors

Hyperspectral and multispectral imaging can record a single scene across a range of spectral bands. The resulting three-dimensional dataset is called a "hypercube". A spectrum is available for each point of the image. This makes it possible to analyse, quantify or differentiate the elements and materials constituting the scene. This article presents the existing technologies on the market and their main characteristics in the VIS/NIR spectral domain (400-1000 nm). It then focuses on a specific multispectral technology called snapshot multispectral imaging, combining CMOS sensors and pixelated multispectral filters (filtering at the pixel level).

scholarly journals Using high frame rate CMOS sensors for three-dimensional eye tracking

2002 ◽  
Vol 34 (4) ◽  
pp. 549-560 ◽  
Author(s):  
A. H. Clarke ◽  
J. Ditterich ◽  
K. Drüen ◽  
U. Schönfeld ◽  
C. Steineke
Keyword(s):  
Eye Tracking ◽  
Three Dimensional ◽  
Frame Rate ◽  
High Frame Rate ◽  
Cmos Sensors

scholarly journals Three-dimensional spectral domain optical coherence tomography in chronic exposure to welding arc

2014 ◽  
Vol 2014 (may14 4) ◽  
pp. bcr2013202220-bcr2013202220 ◽  
Author(s):  
S. Saxena ◽  
N. Mishra ◽  
C. H. Meyer
Keyword(s):  
Optical Coherence Tomography ◽  
Chronic Exposure ◽  
Three Dimensional ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Welding Arc

scholarly journals A Developed Siamese CNN with 3D Adaptive Spatial-Spectral Pyramid Pooling for Hyperspectral Image Classification

2020 ◽  
Vol 12 (12) ◽  
pp. 1964 ◽  
Author(s):  
Mengbin Rao ◽  
Ping Tang ◽  
Zheng Zhang
Keyword(s):  
Transfer Learning ◽  
Hyperspectral Image ◽  
Three Dimensional ◽  
Classification Performance ◽  
Generalization Capability ◽  
Training Strategy ◽  
Learning Framework ◽  
Spectral Bands ◽  
Learning Tasks ◽  
3D Information

Since hyperspectral images (HSI) captured by different sensors often contain different number of bands, but most of the convolutional neural networks (CNN) require a fixed-size input, the generalization capability of deep CNNs to use heterogeneous input to achieve better classification performance has become a research focus. For classification tasks with limited labeled samples, the training strategy of feeding CNNs with sample-pairs instead of single sample has proven to be an efficient approach. Following this strategy, we propose a Siamese CNN with three-dimensional (3D) adaptive spatial-spectral pyramid pooling (ASSP) layer, called ASSP-SCNN, that takes as input 3D sample-pair with varying size and can easily be transferred to another HSI dataset regardless of the number of spectral bands. The 3D ASSP layer can also extract different levels of 3D information to improve the classification performance of the equipped CNN. To evaluate the classification and generalization performance of ASSP-SCNN, our experiments consist of two parts: the experiments of ASSP-SCNN without pre-training and the experiments of ASSP-SCNN-based transfer learning framework. Experimental results on three HSI datasets demonstrate that both ASSP-SCNN without pre-training and transfer learning based on ASSP-SCNN achieve higher classification accuracies than several state-of-the-art CNN-based methods. Moreover, we also compare the performance of ASSP-SCNN on different transfer learning tasks, which further verifies that ASSP-SCNN has a strong generalization capability.

scholarly journals High-speed three-dimensional human retinal imaging by line-field spectral domain optical coherence tomography

2007 ◽  
Vol 15 (12) ◽  
pp. 7103 ◽  
Author(s):  
Yoshifumi Nakamura ◽  
Shuichi Makita ◽  
Masahiro Yamanari ◽  
Masahide Itoh ◽  
Toyohiko Yatagai ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
High Speed ◽  
Three Dimensional ◽  
Retinal Imaging ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Line Field
Sign in / Sign up

Export Citation Format

Share Document