html5-img
1 / 27

Toward Object Discovery and Modeling via 3-D Scene Comparison

Toward Object Discovery and Modeling via 3-D Scene Comparison. Evan Herbst , Peter Henry, Xiaofeng Ren , Dieter Fox University of Washington; Intel Research Seattle. Overview. Goal: learn about an environment by tracking changes in it over time

presencia
Télécharger la présentation

Toward Object Discovery and Modeling via 3-D Scene Comparison

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Toward Object Discovery and Modeling via 3-D Scene Comparison Evan Herbst, Peter Henry, XiaofengRen, Dieter Fox University of Washington; Intel Research Seattle

  2. Overview • Goal: learn about an environment by tracking changes in it over time • Detect objects that occur in different places at different times • Handle textureless objects • Avoid appearance/shape priors • Represent a map with static + dynamic parts

  3. Algorithm Outline • Input: two RGB-D videos • Mapping & reconstruction of each video • Interscene alignment • Change detection • Spatial regularization • Outputs: reconstructed static background; segmented movable objects

  4. Scene Reconstruction • Mapping based on RGB-D Mapping [Henry et al. ISER’10] • Visual odometry, loop-closure detection, pose-graph optimization, bundle adjustment

  5. Scene Reconstruction • Mapping based on RGB-D Mapping [Henry et al. ISER’10] • Surface representation: surfels

  6. Scene Differencing • Given two scenes, find parts that differ • Surfaces in two scenes similar iff object doesn’t move • Comparison at each surface point

  7. Scene Differencing • Given two scenes, find parts that differ • Comparison at each surface point • Start by globally aligning scenes (2-D) (3-D)

  8. Naïve Scene Differencing • Easy algorithm: closest point within δ→ same • Ignores color, surface orientation • Ignores occlusions

  9. Scene Differencing • Model probability that a surface point moved • Sensor readings z • Expected measurement z* • m ϵ {0, 1} z3 z2 z1 frame 49 frame 25 z0 z* frame 10 frame 0

  10. Sensor Models • Model probability that a surface point moved • Sensor readings z;expected measurement z* • By Bayes, • Two sensor measurement models • With no expected surface: • With expected surface:

  11. Sensor Models • Two sensor measurement models • With expected surface • Depth: uniform + exponential + Gaussian 1 • Color: uniform + Gaussian • Orientation: uniform + Gaussian zd* 1Thrunet al., Probabilistic Robotics, 2005

  12. Sensor Models • Two sensor measurement models • With expected surface • Depth: uniform + exponential + Gaussian 1 • Color: uniform + Gaussian • Orientation: uniform + Gaussian • With no expected surface • Depth: uniform + exponential • Color: uniform • Orientation: uniform zd* 1Thrunet al., Probabilistic Robotics, 2005

  13. Example Result Scene 1 Scene 2

  14. Spatial Regularization • Points treatedindependently so far • MRF to label each surfel moved or not moved • Data term given by pointwise evidence • Smoothness term: Potts, weighted by curvature

  15. Spatial Regularization • Points treatedindependently so far • MRF to label each surfel moved or not moved Scene 1 Scene 2 regularized pointwise

  16. Experiments • Trained MRF on four scenes (1.4M surfels) • Tested on twelve scene pairs (8.0M surfels) • 70% error reduction wrt max-class baseline Baseline Ours

  17. Experiments • Results: complex scene

  18. Experiments • Results: large object

  19. Conclusion • Segment movable objects in 3-D using scene changes over time • Represent a map as static + dynamic parts • Extensible sensor model for RGB-D sensors • Next steps • All scenes in one optimization • Model completion from many scenes • Train more supervised object segmentation

  20. Using More Than 2 Scenes • Given our framework, pretty easy to combine evidence from multiple scenes: • wscene could be chosen to weight all scenes (rather than frames) equally, or upweight those taken under good lighting • Other ways to subsample frames: as in keyframe selection in mapping

  21. First Sensor Model: Surface Didn’t Move • Modeling sensor measurements: • Depth: uniform + exponential + Gaussian * • Color, normal: uniform + Gaussian; mixing controlled by probability that beam hit expected surface zd* * Fox et al., “Markov Localization…”, JAIR ‘99

  22. Experiments • Trained MRF on four scenes (2.7 Msurfels) • Tested on twelve scene pairs (8.0 Msurfels) • 250k moved surfels; we get 4.5k FP, 51k FN • 65% error reduction wrt max-class baseline • Extract foreground segments as “objects”

  23. Overview • Many visits to same area over time • Find objects by motion

  24. (extra) Related Work • Prob. Sensor models • Depth only • Depth & color, extra indep. Assumptions • Static + dynamic maps • In 2-d • Usually not modeling objs

  25. Spatial Regularization • Pointwise only so far • MRF to label each surfel moved or not moved • Data termgiven by pointwise evidence • Smoothness term: Potts, weighted by curvature

  26. Depth-Dependent Color/Normal Model • Modeling sensor measurements: • Combine depth/color/normal:

  27. Scene Reconstruction • Mapping based on RGB-D Mapping [Henry et al. ISER’10] • Surface representation: surfels

More Related