wORLDVIEW-3

WorldView-3 was launched on August 13 2014, and truly set a new standard for commercial satellites in-orbit. With 29 spectral sensors on-board, the data from WorldView-3 allows you to differentiate between objects with far greater accuracy. Additionally, WorldView-3 was the first satellite capable of delivering true 31 cm resolution and collects the industry’s best very high resolution imagery quickly and reliably.

0
CM RESOLUTION
0
MINUTES TO ORBIT EARTH
0
KM ORBITING ALTITUTE
0 000
SQ KM DAILY COLLECTION

SPECIFICATIONS

  • 617 km altitude
  • Sun synchronous orbit
  • Orbits Earth every 97 minutes
  • Estimated service life of 10-12 years
  • 5.7 x 2.5 x 7.1 m in size (including solar arrays); 2800 kg mass
  • 3.1 kW solar array, 100 Ah battery
  • Sensor bands
    Panchromatic: 450 – 800 nm
    Multispectral – Coastal: 397 – 454 nm | Blue: 445 – 517 nm | Green: 507 – 586 nm | Yellow: 580 – 629 nm | Red: 626 – 696 nm | Red edge: 698 – 749 nm | Near infrared 1: 780 – 920 nm | Near infrared 2: 857 – 1039 nm
    SWIR – SWIR-1: 1184 – 1235 nm | SWIR-2: 1546 – 1598 nm | SWIR-3: 1636 – 1686 nm | SWIR-4: 1702 – 1759 nm | SWIR-5: 2137 – 2191 nm | SWIR-6: 2174 – 2232 nm | SWIR-7: 2228 – 2292 nm | SWIR-8: 2285 – 2373 nm
    CAVIS – Desert Clouds: 405 – 420 nm | Aerosol-1: 459 -509 nm | Green: 525 – 585 nm | Aerosol-2: 635 – 685 nm | Water-1: 845 – 885 nm | Water-2: 897 – 927 nm | Water-3: 930 – 965 nm | NDVI-SWIR: 1220 – 1252 nm | Cirrus: 1365 – 1405 nm | Snow: 1620 – 1680 nm | Aerosol-3: 2105 – 2245 nm
  • Sensor resolution
    Panchromatic nadir: 0.31 m | 20° off-nadir: 0.34 m
    Multispectral nadir: 1.24 m | 20° off-nadir: 1.38 m
    SWIR nadir: 3.7 m | 20° off-nadir: 4.1 m
    CAVIS nadir: 30.00 m
  • Dynamic range
    Pan and multispectral: 11 bits per pixel
    SWIR: 14 bits per pixel
  • 13.1 km swath at nadir
  • 3-axis stabilized
  • Control moment gyroscope actuators
  • Sensors include star trackers, GPS, and a precision inertial reference unit (IRU)
  • 12 seconds to slew 200 km
  • 2199 GB solid state storage incorporating error detection and correction (EDAC)
  • 1200 Mbps max communications speed
  • 66.5 x 112 km maximum mono collection per pass (5 strips)
  • 26.6 x 112 km maximum stereo collection per pass (2 pairs)
  • Average revisit rate at 40° latitude is <1.0 day | 4.5 days at 20° off-nadir or less
  • 3.5 m CE90 accuracy
  • 680,000km2 collection capacity per day
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