Converting point clouds to 3D object maps Part of iTransit Annie - - PowerPoint PPT Presentation

▶
converting point clouds to 3d object maps
SMART_READER_LITE
LIVE PREVIEW

Converting point clouds to 3D object maps Part of iTransit Annie - - PowerPoint PPT Presentation

Aug 26, 2023 941 likes •1.12k views

Converting point clouds to 3D object maps Part of iTransit Annie Westerlund 2016-05-10 AstaZero Researchers day 1 Agenda Short background Overview of algorithm Description: Point cloud to 3D object map Final words 2

slide-1
SLIDE 1

1

Converting point clouds to 3D object maps

Part of iTransit

Annie Westerlund

2016-05-10

AstaZero Researchers’ day

slide-2
SLIDE 2

Agenda

  • Short background
  • Overview of algorithm
  • Description: Point cloud to 3D object map
  • Final words

2

slide-3
SLIDE 3

Background

3

slide-4
SLIDE 4

Background

Why should we process point clouds?

  • ~ 80 000 000 points.
  • ~2 GB
  • Real-time navigation and

positioning => need efficient solution.

4

slide-5
SLIDE 5

Overview of algorithm

5

slide-6
SLIDE 6

Overview of main algorithm

6

XYZRGBI point cloud Input Statistical classification Cylinder detector Road refiner Wall detector Lane marking detector Object map

slide-7
SLIDE 7

Description: Point cloud to 3D object map

7

slide-8
SLIDE 8

Statistical classification

8

  • Divide point cloud into XY

grid.

  • Fit plane to points in grid.
  • Statistical classification:
  • Variance XY plane
  • Variance Patch plane
  • Color
slide-9
SLIDE 9

Object detection

9

  • Wall detection:
  • Detect possible ”building clusters”.
  • Find vertical planes in clusters.
  • Find smallest enclosing cube.
  • Cylinder detection:
  • Detect poles.
  • Find cylinder parameters.
  • Lane marking detection:
  • Detect lane markings
  • Describe lane marking form one or more by cubes.
slide-10
SLIDE 10

10

  • Objects descibed in global coordinates.
  • Objects are stored in binary files.
  • The map can be visualized in different

layers.

  • 9 kB without road surface
  • 442 kB with road surface
  • Compare 2 GB point cloud

The object Map

slide-11
SLIDE 11

AstaZero city and part of rural road

11

slide-12
SLIDE 12

Describing details

  • 3D grid
  • Oriented bounding boxes
  • Extract main objects first, then describe details

12

slide-13
SLIDE 13

Final words

13

slide-14
SLIDE 14

Final words

  • Accuracy and resolution
  • Positioning – LiDAR and

camera map matching

  • Potential for expansion

14

slide-15
SLIDE 15

15

Thanks for the attention!