eCognition 10.5 – Release March 2025 – Highlights

© Trimble
eCognition 10.5 offers even more flexibility in using external CNN models
With the integration of the ONNX format (Open Neural Network Exchange), a wide range of pre-trained models can now be incorporated into the eCognition workflow.
ONNX Model Support
ONNX (Open Neural Network Exchange) models allow users to import and run models trained in different machine learning frameworks, such as TensorFlow and PyTorch, without needing to retrain them for a specific platform.
Point Cloud Editing Toolbar
The new toolbar designed specifically for point cloud editing enables manual editing capabilities, offering various modes for point selection and reclassification in both 2D and 3D views. The toolbar automatically opens when point cloud data is imported.
SAM-based Segmentation
Version 10.5 introducing a new algorithm for segmentation of image data based on the Segment Anything Model (SAM) algorithm*. The algorithm offers three input modes for segmentation flexibility: Everything | Bounding Boxes | Points
DBSCAN Clustering
The new density-based spatial clustering of applications with noise (DBSCAN)-based point cloud clustering algorithm groups points that are close to each other into one instance of an object based on the user input point cloud class. After automatic clustering, this enables easy object counting.
Office software
Trimble eCognition
Transform data into information.
Here you will find essential information about eCognition from Trimble.
eCognition Distribution & Services
We provide a tailor made offer matching the various possibilities of the software. You get our 4D Maintenance package including Software Maintenance, Level 1&2 Support, Ruleware Support and Advanced Training. Of course, you have access to our Webinars and Support & Coaching offers. To support you in a most proficient way our support is based on Tama Core Process
