GEOSPACE
FROM GEO4i

A multi-source IMINT-GEOINT data management and analytics platform

A dedicated big data platform

Highly Compatible

Easily ingest data through SecureWatch, AIS, Sentinel, ACLED, and more

Data management

Easy-to-use interface with advanced search and filter capabilities

powerful analytics

Label, compare, detect and identify features in any raster or vector dataset

Geo4i’s GeoSpace is a dedicated GEOINT & IMINT platform for processing and analysing geospatial imagery and Big Data. The platform is NATO STANAG 3569 compliant featuring automated detection workflows and other value-added tools allows for reporting and analysis. The intuitive interface and addons assist a range of applications with features including:

  • Data storage and management
  • Raster and Vector visualisation and processing
  • Multi-temporal spatial analysis
  • Third-party integrations (SecureWatch, AIS, Sentinel, ACLED)
  • Site digitalisation and labelling
  • Assisted image comparison
  • Seamless sync with Help4i
  • AI object detection
  • Automatic workflows for Sentinel data (change detection, ship/offshore platform detection, active fires)

EXPERIENCE GEOSPACE YOURSELF

Contact our sales team for a live demonstration of this powerful tool.

Watch & learn

INTEGRATE HELP4i FOR EQUIPMENT IDENTIFICATION

Help4i provides accurate, intuitive and easy to understand identification of civilian and military equipment with more than 6,000 items registered in the GeoSpace platform. With just a few measurements, you can refine the search to a list of potential candidates matching the equipment to be identified with functionality to overlap and compare models and thereby improve the confidence of the identification.

The product can be purchased as a stand-alone software option or as an add on tool of Geospace.

BOOST ANALYSIS WITH THE SITES4i ADDON

Sites4i is a module of GeoSpace providing a digitalisation and labelling environment to perform IMINT tasks.

Features include:

  • NATO STANAG 3596-compliant
  • Multi-temporal versioning
  • Dedicated resources to assist photo-interpretation
  • Sharing and reporting capabilities

ADD THE AI CHAIN FOR AUTOMATED DETECTION

The AI Chain from Geo4i is a GEOINT & IMINT API environment for the automatic detection of generic objects in satellite images. The product can be integrated into GeoSpace and is based on TensorFlow, tailored to fit D&I needs.

The training set is generated by the user’s imagery and the product can be deployed within the customers secured infrastructure. 

INGEST IMAGERY WITH SECUREWATCH

A SecureWatch subscription gives you instant access to the best satellite imagery and geospatial data via web browser or API integration; And you don’t have to be an imagery expert or have in-house tools.

SecureWatch is designed to make both fresh and archive imagery accessible to anyone who needs it, whether you’re concerned with a specific area or the entire globe.

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