.png)
Start using CVEDIA-RT
Aerial Ship Detector.
Detects and localizes maritime objects from aerial angles. Includes tankers, cargo ships, fishing boats, etc. Separates buoys, debris, and airplanes.
PERFORMANCE
Optimized for edge performance with a low power profile.
RANGE
Up to 2000 meters.
CONDITIONS
Dawn to dusk and Douglas Sea States 0 to 7.
CLASSES
Classifies buoys, debris, and airplanes as separate events.
ARCHITECTURE
Backbone: Resnet-101; Detector: RefineDet.
FUNCTIONALITY
Detection.
INPUT SIZE
512x512.
SENSOR MODALITY
Visible light.
Use cases.
Detect boats and ocean obstrusions from aerial perspectives.
Alternative data
The Aerial Ship Detector can be used to gather geospatial research regarding port activities, vessel travel patterns, and marine usage. Use data collected from this algorithm in large scale financial, environmental, and commercial traffic analysis.
Marine traffic
This algorithm can be used at lookout points at ports and marines to ensure safe docking and cargo transfer. Additional detection classes and classification parameters are available as our service add-ons.
Maritime security
Use it as an effective component of your maritime security system in order to track illegal fishing, piracy, border control, and maritime pollution. This algorithm is effective from various aerial angles, allowing it to be used through satellite imagery, airplane flyover, drone, and stationary lookout points.
Our services.
We offer maintenance services for our AI models and provide the option to add fine grain classification or additional classes through our in-house team. Our models are built with proprietary synthetic data technology, allowing for quick integration of new classes.
Maintenance
Each CVEDIA model comes backed with an ongoing maintenance agreement. Our team is available for continuous improvements and to ensure upkeep.
Fine classification
Discuss fine grain classification with our team and get an answer today. We'll work with you to build a synthetic-based model to meet your specifications.
Additional classes
Our models are built using proprietary synthetic data technology, meaning adding additional classes to your model is possible in a matter of weeks.
