Multispectral
& Hyperspectral

Access to the most spectral bands so you can see beyond the naked eye.

Santander_infrared

hundreds of band combinations

8

Multispectral bands

29

Hyperspectral Bands

8

SWIR Bands

The power to see beyond the visible light spectrum cannot be overstated. With hundreds of current applications and countless more waiting to be discovered, multispectral imagery is the key to unlocking insights in any industry. European Space Imaging captures imagery with up to 8 multispectral bands plus the ability to collect imagery in Shortwave Infrared (SWIR) and hyperspectral as well.

With 8-band multispectral imagery, you can answer questions like:

  • Is there excavated material from the construction of an underground facility?
  • Will the health of the crops in this area provide food security?
  • Are illicit crops being grown?
  • Is this location suitable for a beach landing?
  • Have reinforcing materials been applied to this facility?
  • Has equipment been camouflaged from view?
  • Is this material steel, polymer or paint?
  • Are there significant features that might otherwise be overlooked?

See how our imagery fits your project

Download imagery, mapping and 3D product samples.

Spectral Bands

Hyperspectral

Through our partnership with Satellogic, European Space Imaging offers 25 m resolution hyperspectral imagery. The key factor that separates Hyperspectral imagery is the width of the spectral bands. With 29 bands covering 460 – 830 nm, analytics become much more precise.

Only a small number of space-based imagery providers offer hyperspectral imagery, though the potential for industry disrupting applications are already making headway across the globe.

Spectral BandCenter Wavelength (nm)FWHM (nm)
1462.0314.66
2474.8415.37
3487.6616.07
4502.0716.86
5516.4817.66
6529.318.36
7550.1219.51
8569.3420.56
9582.1521.27
10594.9621.97
11607.7722.68
12615.7823.12
13670.2326.11
14679.8426.64
15689.4527.17
16700.6627.79
17710.2728.32
18719.8828.84
19729.4929.37
20740.729.99
21750.3130.52
22759.9231.05
23769.5331.57
24780.7432.19
25790.3532.72
26799.9633.25
27809.5733.78
28820.7834.39
29827.1934.75
Hyperspectral-karthoum-sudan_

False Colour Hperspectral Image | Khartoum, Sudan   

Scroll to Top

Architecture of ResNet34-UNet model

UNet architecture for semantic segmentation with ResNet34 as encoder or feature extraction part. ResNet34 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of VGG16-UNet model

UNet architecture for semantic segmentation with VGG16 as the encoder or feature extractor. VGG16 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of ResNet34-FCN model

In this model, ResNet34 is used for feature extraction and the FCN operation remains as is. The feature of ResNet architecture is exploited where just like VGG, as the number of filters double, the feature map size gets halved. This gives a similarity to VGG and ResNet architecture while supporting deeper architecture and addressing the issue of vanishing gradients while also being faster. The fully connected layer at the output of ResNet34 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

Architecture of VGG16-FCN model

In this model, VGG16 is used for feature extraction which also performs the function of an encoder. The fully connected layer of the VGG16 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

X