3D Multi Sensor Fusion - User Documentation
  • Introduction
  • Account Activation
  • QuickServe Platform
  • Project Setup
    • Create Recipe
      • 1. Basic Details
      • 2. Classes
      • 3. Attributes
      • 4. Associations
      • 5. Publish Recipe
    • Create Taskflow
      • 1. Taskflow Details
      • 2. Taskflow Preview & Edit
      • 3. Publish Taskflow
    • Build Jobs
      • 1. Job Details
      • 2. Data Import
      • 3. Data Upload Status
      • 4. Launch Task
    • Batch Export
    • Reports
    • Pre-process Data
    • Storages
  • Annotation Tool
    • Tool Layout
    • Steps to Label
    • Drawing Tools
      • Cuboid
      • Polyline 3D
      • Polygon 3D
      • Brush Sphere
      • Rectangle
      • Polyline 2D
      • Polygon 2D
    • Key Features
      • Progress Bar
      • Keyframe Interpolation
      • Raycaster and Frustum
      • Focus Mode
      • Merged Point Cloud
      • Isolate
      • Outlier
      • Ground and Ceiling Mover
      • Project Points on Image
      • Task Level Attribute Propagation
      • Relationship
      • Intensity Filter and Picker
      • Image Settings Lock
      • Unify Dimension
      • Auto-Grounding for Cuboids and Polylines
    • Tool Shortcuts
  • Audit Tool
  • Visualization Tool
  • API Documentation
    • API Documentaion
Powered by GitBook
On this page
  • Benefits
  • Steps to use MPC
  • Partial Merged Point Cloud
  1. Annotation Tool
  2. Key Features

Merged Point Cloud

PreviousFocus ModeNextIsolate

Last updated 4 months ago

The Merged Point Cloud feature allows users to see all the points over time (across all the of a ) aggregated in the same coordinate system of the current frame resulting in one big point cloud. Therefore, ego motion data is mandatory for this type of scene.

It is used on sequential tasks to annotate stationary objects in a single .

By enabling the MPC, it's easy to detect and label all the stationary objects since they appear denser and brighter. While moving objects will leave a trail of points.

Benefits

  • Improve Efficiency: By allowing all data points to be merged in a single frame, the user no longer has to traverse the sequence to find the ideal frame where the most points of the object are captured.

    • Static objects are also much clearly visible with the accumulated points

  • Improve Accuracy: By integrating data from multiple frames, merged point clouds can enhance the accuracy of object annotation. Annotators can use the combined data to make more informed decisions about the precise location of objects within the point cloud.

Steps to use MPC

    • The Multi Sensor Fusion tool supports various mechanisms of aggregating the point clouds across the sequence:

      • all

      • using frame jump length

  1. Identify the stationary object (that is dense and bright)

    • If the object ceases to exist before the end of the frame, delete the annotation by right-clicking on it and selecting the delete option.

Partial Merged Point Cloud

MPC has further options for merging points across a range of frames.

  • The tool provides multiple options

    • select a predefined option from the list

    • use the customizable start/end frame and hit enter

  • After triggering the merged point cloud, the timeline introduces a yellow to indicate the frames that are merged.

Toggle the MPC switch on the header of the annotation tool. This will aggregate and merge points across all the of the , by default on the next 20 frames.

Select the and create the annotation on the object

If the annotation is a , it is propagated across all the frames.

cuboid
partial merged point cloud
frames
batch
frames
batch
drawing tool