Knowledge Base
Recent Changes

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Last revision Both sides next revision
recordings:tutorials:videos:pointcloud_labeling [2024/02/06 15:06]
arnaud 		recordings:tutorials:videos:pointcloud_labeling [2024/04/10 08:09]
arnaud
Line 1: Line 1:
-====== Pointcloud labeling for training ======+====== AI-labeling: Annotate pointcloud for AI training ======
  
  
-This video is about labeling pointcloud to serve custom AI-training jobs and create detectors to be used in the Analysis Engine AI. \\+This page is about labeling pointcloud to serve custom AI-training jobs and create detectors to be used in the Analysis Engine. \\
  
 ==== Step by step ==== ==== Step by step ====
  
   - Create a trajectory file that will be used as a canvas to easily navigate through the scene and label all elements of interest   - Create a trajectory file that will be used as a canvas to easily navigate through the scene and label all elements of interest
-  - Create an asset class that will be labeled (e.g: pylons) +      * Drag & drop your mapping run {{ :recordings:tutorials:videos:pointcloud_labeling_001.mp4?nolink&850x478 |}} 
-  - Select pointcloud to attribute to an asset object +      * Create a vector resource for trajectory to constraint navigation {{ :recordings:tutorials:videos:pointcloud_labeling_002.mp4?nolink&850x478 |}} 
-  - Generate consolidated classified pointcloud + assets to serve AI-detector training +      * Copy trajectory file in installation folder {{ :recordings:tutorials:videos:pointcloud_labeling_003.mp4?nolink&850x478 |}} 
-  - Pointcloud selection to classification+      * Define trajectory as linear reference and lock it {{ :recordings:tutorials:videos:pointcloud_labeling_004.mp4?nolink&850x478 |}} 
 +  - Create an asset class that will be labeled (e.g: pylons)  
 +      * Create asset ressource {{ :recordings:tutorials:videos:pointcloud_labeling_005.mp4?nolink&850x478 |}} 
 +      * Pinpoint asset objects in mapping run {{ :recordings:tutorials:videos:pointcloud_labeling_006.mp4?nolink&850x478 |}} 
 +  - Select pointcloud to attribute to an asset object  
 +      * Select associated pointcloud and add pointcloud selection to asset objects {{ :recordings:tutorials:videos:pointcloud_labeling_007.mp4?nolink&850x478 |}} 
 +      * Measure next asset object until the entire dataset is reviewed {{ :recordings:tutorials:videos:pointcloud_labeling_008.mp4?nolink&850x478 |}} 
 +  - Generate consolidated classified pointcloud + assets to serve AI-detector training  
 +      * Generate data and merge pointcloud selections {{ :recordings:tutorials:videos:pointcloud_labeling_009.mp4?nolink&850x478 |}} 
 +      * Pointcloud selection to classification {{ :recordings:tutorials:videos:pointcloud_labeling_010.mp4?nolink&850x478 |}} 
 +  - Upload classified pointcloud to enable detector training  
 +      * Upload classified OPC to Reality Management {{ :recordings:tutorials:videos:pointcloud_labeling_011.mp4?nolink&850x478 |}} 
 +      * Bentley team takes it from here and will start detector training 
 
Last modified:: 2024/04/10 08:37