AI Evaluation

This page describes how to execute AI-Evaluation.

Main Toolbar > Extract > AI Evaluation

Ai-Evaluation compares the results of an AI-Detection against already annotated data considered ground-truth. It performs over 3D-Segmentation, 2D-Object detection and 2D-Segmentation.

1. Input:
   • Classified pointcloud
   • Annotated images
   • Result of AI-Detection
2. Output:
   • Classified pointcloud assessing quality against ground-truth
   • Annotated images
   • PDF report

Select the first pointcloud you want the comparison to be executed on.

Select an AI-Detection linked to source on which the AI-Evaluation will be executed on.

If not automatically selected from source, please select an annotated reality data of same format as source.

In case source and ground truth classes-names differ, this table can re-attribute classes to ensure consistent evaluation.

Submit job to run AI-Evaluation.