Identifying Opportunities Together

In collaboration with Maxar, our parent company, Wovenware embarked on a mission to enrich the capabilities of SecureWatch, a cloud-based subscription service providing access to earth intelligence. The objective was clear: to implement advanced computer vision models for automated aircraft detection in global airports, thereby revolutionizing geospatial analysis.

Setting a Goal for Success

Maxar turned to Wovenware to enhance the insights delivered through SecureWatch, with the addition of computer vision models that would help it to automatically detect aircraft in airports around the world. AI-powered geospatial insights are generated on a daily basis as new satellite imagery becomes available.

Our Challenges
and Learnings

• Build a fast and efficient model to detect aircraft in 5,000 airports around the world in satellite imagery.

• Build a training data-set and an independent validation set with a wide range of geographies and diverse satellite image resolutions and angles.

• Build a model that is fast and cost-effective to maintain. Integrate the machine learning model with Maxar’s SecureWatch.

• Operationalize the retraining and deployment of new models to Maxar’s SecureWatch.

The Wovenware Approach

Wovenware employed its private crowd to meticulously annotate over 27,000 aircraft segmentations across 180 images from 42 global airports, utilizing computer vision techniques for precise labeling. Utilizing Maxar's proprietary toolkit, DeepCore Workbench, the team meticulously curated training datasets tailored to the unique demands of aircraft detection, employing computer vision algorithms for data preprocessing.

Drawing upon its Innovation Sprint methodology, Wovenware experimented with various deep learning architectures, including YOLOv5, fine-tuning hyperparameters and optimizing image sets for maximum accuracy and efficiency, leveraging computer vision techniques for model optimization.

Technologies we take advantage of

Building it Right

Wovenware worked with Maxar to optimize geospatial insights gained through SecureWatch earth intelligence system.

  • A private crowd annotated 27K aircraft segmentations over 180 images from 42 airports around the world using Maxar’s proprietary toolkit DeepCore Workbench.
  • The data science team built a YoloV5 deep learning model to detect aircraft, experimenting with several architectures, hyperparameter tuning, and balancing image sets.
  • The aircraft model was retrained every week with new imagery and labels and deployed to Maxar’s SecureWatch product.
  • Each version of the model was scored against an independent validation set to benchmark, measure and track performance improvements.
Let’s create useful technology together that empowers humans and delivers impact.