rgb d mapping using depth cameras for dense 3d modeling
play

RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor - PowerPoint PPT Presentation

RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments Peter Henry 1 , Michael Krainin 1 , Evan Herbst 1 , Xiaofeng Ren 2 , and Dieter Fox 1,2 1 University of Washington Computer Science and Engineering 2 Intel Labs


  1. RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments Peter Henry 1 , Michael Krainin 1 , Evan Herbst 1 , Xiaofeng Ren 2 , and Dieter Fox 1,2 1 University of Washington Computer Science and Engineering 2 Intel Labs Seattle (now ISTC at UW) 1

  2. The Kinect 2

  3. PrimeSense Technology 3

  4. RGB-D Data 4

  5. 5

  6. Related Work  SLAM  [Davison et al, PAMI 2007] (monocular)  [Konolige et al, IJR 2010] (stereo)  [Pollefeys et al, IJCV 2007] (multi-view stereo)  [Borrmann et al, RAS 2008] (3D laser)  [May et al, JFR 2009] (ToF sensor)  Loop Closure Detection  [Nister et al, CVPR 2006]  [Paul et al, ICRA 2010]  Photo collections  [Snavely et al, SIGGRAPH 2006]  [Furukawa et al, ICCV 2009] 6

  7. System Overview 1. Frame-to-frame alignment 2. Loop closure detection and global consistency 3. Map representation 7

  8. Alignment (RANSAC)  Visual features (from image) in 3D (from depth)  RANSAC alignment requires no initial estimate  Requires sufficient matched features 8

  9. RANSAC Details  Feature Detector / Descriptor Options  SIFT (SiftGPU)  SURF  FAST Detector / Calonder Descriptor  (All available in OpenCV)  Matching:  L2 descriptor distance  Either SIFT style matching or window matching 9

  10. RANSAC Failure Case 10

  11. Alignment (ICP)  Does not need visual features or color  Requires sufficient geometry and initial estimate 11

  12. ICP Failure Case 12

  13. Joint Optimization (RGBD-ICP) 13

  14. Optimal Transformation 14

  15. Two-Stage Alternative 15

  16. Loop Closure  Sequential alignments accumulate error  Revisiting a previous location results in an inconsistent map 16

  17. 17

  18. Loop Closure Detection  Detect by running RANSAC against previous frames  Pre-filter options (for efficiency):  Only a subset of frames ( keyframes )  Only keyframes with similar estimated 3D pose  Place recognition using vocabulary tree  Post-filter (avoid false positives)  Estimate maximum expected drift and reject detections changing pose too greatly 18

  19. Loop Closure Correction (TORO)  TORO [Grisetti 2007]:  Constraints between camera locations in pose graph  Maximum likelihood global camera poses 19

  20. Loop Closure Correction (SBA)  Minimize reprojection error of features 20

  21. Comparison (TORO) 21

  22. Comparison (SBA) 22

  23. A Second Comparison TORO SBA 23

  24. SBA on a tricky sequence 24

  25. 25

  26. Map Representation: Surfels  Surface Elements [Pfister 2000, Weise 2009, Krainin 2010]  Circular surface patches  Accumulate color / orientation / size information  Incremental, independent updates  Incorporate occlusion reasoning  750 million points reduced to 9 million surfels 26

  27. 27

  28. Experiments  Reprojection error is better for RANSAC:  Errors for variations of the algorithm:  Timing for variations of the algorithm: 28

  29. Experiments: Overlay 1 29

  30. Experiments: Overlay 2 30

  31. Application: Measurements 31

  32. Application: Quadrocopter  Collaboration with Albert Huang, Abe Bacharach, and Nicholas Roy from MIT 32

  33. 33

  34. 34

  35. 35

  36. Occupancy Map 36

  37. 37

  38. Resulting Map 38

  39. Conclusion  Kinect-style depth cameras have recently become available as consumer products  RGB-D Mapping can generate rich 3D maps using these cameras  RGBD-ICP combines visual and shape information for robust frame-to-frame alignment  Global consistency achieved via loop closure detection and optimization (RANSAC, TORO, SBA)  Surfels provide a compact map representation  ROS + OpenCV are powerful tools to enable these applications 39

  40. Open Questions  Which are the best features to use?  How to find more loop closure constraints between frames?  What is the right representation (point clouds, surfels, meshes, volumetric, geometric primitives, objects)?  How to generate increasingly photorealistic maps?  Autonomous exploration for map completeness?  Can we use these rich 3D maps for semantic mapping? 40

  41. Thank You! 41

  42. Links  www.ros.org  The following have nice ROS integration but also work separately:  http://opencv.willowgarage.com/wiki/  http://www.pointclouds.org/  Paper link on this page:  http://www.cs.washington.edu/homes/fox/abstracts/ 3d-mapping-iser-10.abstract.html 42

Recommend


More recommend