cmsc427 model capture creating 3d mesh from real world
play

CMSC427 Model capture Creating 3D mesh from real world data Models - PowerPoint PPT Presentation

CMSC427 Model capture Creating 3D mesh from real world data Models Sensor Point clouds Mesh from cloud How? Collect data 2D images 2 1/2 images Point clouds 1D scans Align and fuse data Create mesh from


  1. CMSC427 Model capture

  2. Creating 3D mesh from real world data • Models • Sensor • Point clouds • Mesh from cloud

  3. How? • Collect data • 2D images • 2 1/2 images • Point clouds • 1D scans • Align and fuse data • Create mesh from data • Data to point cloud • Point cloud to mesh

  4. Collect data • 2D images • Sequence or • simultaneously 4

  5. 2 ½ D scanner • Eg, MS Kinect. Image plus depth data (2 ½ D) • Structure.io 5

  6. 1-D scanners • Eg, Eora3D.com • Demo’d in class: Hokuyo URG-04LX 6

  7. Point scanners • Contact scanner • Laser range scanner • Adjustable sequence of points

  8. T wo primary approaches • Time of flight • LIDAR – Light Detection and Ranging

  9. T wo primary approaches • Triangulation • Camera to camera (stereo) • Laser to camera • Projector to camera • Problem: matching

  10. Kinect – structured projected infrared light • Emitter projects known pattern • Helps in matching

  11. Align and fuse data • Match data between images • Or point clouds

  12. Matching image points • Find distinctive points in each image • Match based on local properties

  13. Imtermediate objective – fused point cloud

  14. Final objective – point cloud to mesh • One tool: Meshlab

Recommend


More recommend