a discriminatively trained multiscale deformable part
play

A Discriminatively Trained, Multiscale, Deformable Part Model - PowerPoint PPT Presentation

Jan 18, 2024 •122 likes •846 views

A Discriminatively Trained, Multiscale, Deformable Part Model February 24, 2016 Adam Allevato CS 381V University of Texas at Austin Outline Partial matching Non-maximum suppression Train image results Live demo Outline

  1. A Discriminatively Trained, Multiscale, Deformable Part Model February 24, 2016 Adam Allevato CS 381V University of Texas at Austin

  2. Outline ● Partial matching ● Non-maximum suppression ● Train image results ● Live demo

  3. Outline ● Partial matching ● Non-maximum suppression ● Train image results ● Live demo

  4. Partial Matching ● Deformable Part Models allows parts of objects to shift around ● What happens when one of the parts is completely missing? ● What happens when the images are hacked to move parts of them around?

  5. Source Image

  6. Learned HOG Features from INRIA

  7. INRIA Person Dataset Matches

  8. Source Image

  9. Modified Source Image

  10. INRIA Person Dataset Matches

  11. Bad Background = Bad Detection

  12. Blocked Parts ● Take the list of part filter responses in a detection ● One by one, replace their area with black pixels ● Test intersection over union against ground truth

  13. Source Image

  14. Detection

  15. 1 Filter Blocked

  16. 3 Filters Blocked

  17. Degradation (VOC 2010 Detector)

  18. Source Image

  19. 0 Blocked Filters

  20. 1 Blocked Filters

  21. 2 Blocked Filters

  22. 3 Blocked Filters

  23. Degradation (VOC 2007 Detector)

  24. Source Image

  25. 0 Blocked Filters

  26. 1 Blocked Filter

  27. 2 Blocked Filters

  28. 3 Blocked Filters

  29. Degradation (VOC 2007 Detector)

  30. Blocked Filters ● DPM is great against this, especially with canonical views ● Shows robustness to occlusion

  31. Random Window Shifts ● Window is shifted by random amount ● The pixels covered are moved to the gap left behind ● All pixel information is maintained

  32. VOC 2010 Bicycle Detector

  33. Ground Truth

  34. No Shifts

  35. One Shift

  36. Static Parts to the Rescue

  37. One Shift

  38. Two Shifts

  39. Three Shifts

  40. Four Shifts

  41. Does how far we shift affect performance? Averaged across 30 trials!

  42. 10 10-Pixel Shifts Ground truth

  43. Does how many times we shift affect performance?

  44. Does how many times we shift affect performance?

  45. Window Shifts ● DPM is robust to small number of window shifts because some part filters still fire correctly ● More shifts give worse performance ● The shift distance does not have appreciable effect on the detection score loss

  46. Partial Matching ● DPM is robust to object parts moving around ● It can also infer positions of hidden or missing object parts ● Sometimes, IoU can actually increase with occlusion

  47. Outline ● Partial matching ● Non-maximum suppression ● Train image results ● Live demo

  48. Size-Matched Image

  49. Without NMS, N = 10

  50. Without NMS, N = 50 N = 44 N = 3 N = 4

  51. With NMS, N = 3

  52. Overlap = |B i ∩ B j | / |B j | Worse matches B i Better matches B j

  53. NMS Overlap ● 30 closely correlated matches are detected before the second person is detected ● 42 matches before third person is detected ● Repeated detections for similar objects rank similarly ● NMS helps highlight the weaker matches ● Asymmetric overlap metric allows good windows to subsume smaller windows that lie inside

  54. Non-Maximum Supression ● Helps avoid duplicates ● Also helps let the weaker data show itself when a limit is imposed on the total number of matches

  55. Outline ● Partial matching ● Non-maximum suppression ● Train image results ● Live demo

  56. Chicago Elevated Train

  57. VOC 2007 Train Model

  58. VOC 2007 Train Results, N = 1

  59. Without NMS, N=30

  60. Without NMS, N=30 ● Many different modes ● Overall high confusion ● Some lonesome outliers B i B j

  61. Chicago Elevated Train ● Most detected windows contain mostly train ● No single canonical detection window - “lots of trains” ● No window captures the entire train ● No learned DPM for “train” is long enough to capture this shape

  62. Outline ● Partial matching ● Non-maximum suppression ● Train image results ● Live demo

  63. Live Demo ● INRIA person dataset ● VOC 2010 dataset - “chair” ● Can we fool it?

  64. Summary ● Tested matches with parts of objects missing ● Surveyed non-max suppression effects ● Results on train image: technically correct, but still did not capture entire object ● Girshick's library is mature and can be easily integrated into live application

  65. References A Discriminatively Trained, Multiscale, Deformable Part Model. P. Felzenszwalb, D. McAllester, ● D. Ramanan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008 Original code available on GitHub: https://github.com/rbgirshick/voc-dpm ● My code available on GitHub: https://github.com/Kukanani/voc-dpm ● Images ● http://cdn.collider.com/wp-content/image- base/Movies/P/Princess_Bride/the_princess_bride_movie_image__1_.jpg http://www.planetizen.com/files/images/ChicagoEl.jpg http://www.brinoideas.xyz/wp-content/uploads/2015/11/open-design-living-room-ideas-with- black-drume-pendant-and-blue-sofa-and-unique-glass-coffee-table-and-lovely-black-white-area- rug-and-grey-cream-pouf-also-big-window.jpg http://i.telegraph.co.uk/multimedia/archive/01947/B084FX_1947399c.jpg http://images.glaciermedia.ca/polopoly_fs/1.1346352.1410102588!/fileImage/httpImage/image.j pg_gen/derivatives/landscape_563/10175643-1-jpg.jpg

  67. Live Cam Examples

  68. Input Image

  69. VOC 2010 Person Detector

  70. VOC 2010 Person Detector

  71. Chair Detector

  72. Chair Detector

Recommend

A Discriminatively Trained, Multiscale, Deformable Part Model by Pedro Felzenszwalb, David

A Discriminatively Trained, Multiscale, Deformable Part Model by Pedro Felzenszwalb, David

A Discriminatively Trained, Multiscale, Deformable Part Model by Pedro Felzenszwalb, David McAllester, and Deva Ramanan CS381V Visual Recognition - Paper Presentation Slide credit: Duan Tran Slide credit: Duan Tran Deformable Part Model

605 views • 24 slides
Discriminatively Trained Mixtures of Deformable Part Models Pedro Felzenszwalb and Ross Girshick

Discriminatively Trained Mixtures of Deformable Part Models Pedro Felzenszwalb and Ross Girshick

Discriminatively Trained Mixtures of Deformable Part Models Pedro Felzenszwalb and Ross Girshick University of Chicago David McAllester Toyota Technological Institute at Chicago Deva Ramanan UC Irvine http://www.cs.uchicago.edu/~pff/latent

216 views • 19 slides
Object Detection with Discriminatively Trained Part Based Models Pedro F . Felzenszwalb, Ross B.

Object Detection with Discriminatively Trained Part Based Models Pedro F . Felzenszwalb, Ross B.

Object Detection with Discriminatively Trained Part Based Models Pedro F . Felzenszwalb, Ross B. Girshick, David McAllester and Deva Ramanan Presented by Amy Bearman and Amani Peddada Roadmap 1. Introduction 2. Related Work 3. Model Overview

906 views • 59 slides
Stochastic multiscale modeling of subsurface and surface flows. Part I: Multiscale mortar mixed

Stochastic multiscale modeling of subsurface and surface flows. Part I: Multiscale mortar mixed

Stochastic multiscale modeling of subsurface and surface flows. Part I: Multiscale mortar mixed finite elements for Darcy flow Ivan Yotov Department of Mathematics, University of Pittsburgh KAUST WEP Workshop January 30February 1, 2010

498 views • 46 slides
Stochastic multiscale modeling of subsurface and surface flows. Part III: Multiscale mortar finite

Stochastic multiscale modeling of subsurface and surface flows. Part III: Multiscale mortar finite

Stochastic multiscale modeling of subsurface and surface flows. Part III: Multiscale mortar finite elements for coupled Stokes-Darcy flows Ivan Yotov Department of Mathematics, University of Pittsburgh KAUST WEP Workshop January 30February

838 views • 47 slides
The DPM Detector P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan Object Detection with

The DPM Detector P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan Object Detection with

The DPM Detector P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan Object Detection with Discriminatively Trained Part Based Models T-PAMI, 2010 Paper: http://cs.brown.edu/~pff/papers/lsvm-pami.pdf Code:

571 views • 44 slides
Multiscale Processing on Networks and Community Mining Part 2 - Spectral Graph Wavelets and

Multiscale Processing on Networks and Community Mining Part 2 - Spectral Graph Wavelets and

Introduction Spectral Graph Wavelets Multiscale community mining Developments; Stability of communities Conclusion Multiscale Processing on Networks and Community Mining Part 2 - Spectral Graph Wavelets and Multiscale Community Detection

901 views • 71 slides
Geometric Registration for Deformable Shapes 2.2 Deformable Registration Variational Model

Geometric Registration for Deformable Shapes 2.2 Deformable Registration Variational Model

Geometric Registration for Deformable Shapes 2.2 Deformable Registration Variational Model Deformable ICP Variational Model What is deformable shape matching? Example ? What are the Correspondences? 3 Eurographics 2010 Course

319 views • 30 slides
Manipulation of 1D and 2D Deformable Objects Without Modeling Deformation Dmitry Berenson

Manipulation of 1D and 2D Deformable Objects Without Modeling Deformation Dmitry Berenson

Autonomous and Human-Robot Collaborative Manipulation of 1D and 2D Deformable Objects Without Modeling Deformation Dmitry Berenson Assistant Professor Robotics Engineering Computer Science Manipulation of deformable objects Deformable

396 views • 23 slides
Simulation Deformable Objects High-quality deformable simulation is important Well-known

Simulation Deformable Objects High-quality deformable simulation is important Well-known

Accelerated Complex-Step RAN LUO, The University of New Mexico, Finite Difference for WEIWEI XU, Zhejiang University TIANJIA SHAO, University of Leeds Expedient Deformable HONGYI XU, Google AI YIN YANG, Clemson University Simulation

339 views • 23 slides
Deformable part models Ross Girshick UC Berkeley CS231B Stanford University Guest Lecture April

Deformable part models Ross Girshick UC Berkeley CS231B Stanford University Guest Lecture April

Deformable part models Ross Girshick UC Berkeley CS231B Stanford University Guest Lecture April 16, 2013 Image understanding Snack time in the lab photo by thomas pix http://www.flickr.com/photos/thomaspix/2591427106 What objects are

814 views • 68 slides
Multiscale Modeling of Membrane Distillation Wonyup Song September 26, 2016 Essence of

Multiscale Modeling of Membrane Distillation Wonyup Song September 26, 2016 Essence of

Multiscale Modeling of Membrane Distillation Wonyup Song September 26, 2016 Essence of Multiscale Modeling Goal: Develop system design criteria via multiscale modeling approach based on Holistic Integrated Multiscale Modeling (HIMM) and

348 views • 9 slides
Statistical Geometry Processing Winter Semester 2011/2012 (Deformable) Shape Matching Rigid Shape

Statistical Geometry Processing Winter Semester 2011/2012 (Deformable) Shape Matching Rigid Shape

Statistical Geometry Processing Winter Semester 2011/2012 (Deformable) Shape Matching Rigid Shape Matching Iterated Closest Points (ICP) Part B (moves, rotation & translation) Part A (stays fixed) The main idea: Pairwise matching

956 views • 82 slides
Sof oft-Bod ody y Dy Dyna namics cs Deformable Objects A difficult problem Lots of

Sof oft-Bod ody y Dy Dyna namics cs Deformable Objects A difficult problem Lots of

Deformable Physics Sof oft-Bod ody y Dy Dyna namics cs Deformable Objects A difficult problem Lots of specific solutions but no accepted general best method Applies to: Soft bodies incl. character animation Destruction Fluid

522 views • 41 slides
Connecting the Dots with Landmarks : Discriminatively Learning Domain-Invariant Features for

Connecting the Dots with Landmarks : Discriminatively Learning Domain-Invariant Features for

Connecting the Dots with Landmarks : Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation Boqing Gong University of Southern California Joint work with Kristen Grauman and Fei Sha The perils of mismatched

625 views • 58 slides
Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations LUBOMIR BOURDEV AND

Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations LUBOMIR BOURDEV AND

Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations LUBOMIR BOURDEV AND JITENDRA MALIK Outline H3D dataset Pipeline Analysis of Poselets fired Selective parts torso, legs and face Other cases Clutter, Rotation and

765 views • 37 slides
Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations Lubomir Bourdev and

Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations Lubomir Bourdev and

Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations Lubomir Bourdev and Jitendra Malik Experiments Presented by Randall Smith Friday, November 2, 12 1 Outline Introduction Dataset Overview Annotations

733 views • 52 slides
Tracking Deformable Objects with Point Clouds John Schulman, Alex

Tracking Deformable Objects with Point Clouds John Schulman, Alex

Tracking Deformable Objects with Point Clouds John Schulman, Alex Lee, Jonathan Ho, Pieter Abbeel UC Berkeley, EECS Department Thursday, July 4, 13 Goal Track deformable

647 views • 51 slides
Multiscale Conditional 1) Generalization of conditional random fields (CRF) to multiscale

Multiscale Conditional 1) Generalization of conditional random fields (CRF) to multiscale

Contributions Multiscale Conditional 1) Generalization of conditional random fields (CRF) to multiscale conditional Random Fields for Image random fields (mCRF) Labeling 2) Learning features of the random field at multiple scales Xuming He,

371 views • 8 slides
Object Category Detection Yusuf Aytar & Andrew Zisserman, Department of Engineering Science

Object Category Detection Yusuf Aytar & Andrew Zisserman, Department of Engineering Science

Tabula Rasa: Model Transfer for Object Category Detection Yusuf Aytar & Andrew Zisserman, Department of Engineering Science Oxford (Presented by Elad Liebman) General Intuition I We have: a discriminatively trained classification

653 views • 39 slides
Assembly of Nanoparticles in Multiscales and Multidimensions (Multiscale Architecturng):

Assembly of Nanoparticles in Multiscales and Multidimensions (Multiscale Architecturng):

Assembly of Nanoparticles in Multiscales and Multidimensions (Multiscale Architecturng): Platform for Convergence Technology Mansoo Choi Global Frontier Center for Multiscale Energy Systems School of Mechanical and Aerospace Engineering,

714 views • 49 slides
Last time Fitting an arbitrary shape with active deformable contours Segmentation

Last time Fitting an arbitrary shape with active deformable contours Segmentation

CS 376: Computer Vision - lecture 10 2/20/2018 Last time Fitting an arbitrary shape with active deformable contours Segmentation & Grouping Kristen Grauman, UT Austin Last time: deformable contours Review questions How does

557 views • 18 slides
Tracking deformable objects with WiSARD networks: a preliminary work INNOROBO 2014 European

Tracking deformable objects with WiSARD networks: a preliminary work INNOROBO 2014 European

Tracking deformable objects with WiSARD networks: a preliminary work INNOROBO 2014 European Workshop on Deformable Object Manipulation 20 March 2014 Lyon, France Massimo De Gregorio, Maurizio Giordano, Silvia Rossi, Mariacarla Staffa and

362 views • 25 slides
Janet Kittams-Lalley Helpline Center Available 24/7 Have staff that are trained to assess

Janet Kittams-Lalley Helpline Center Available 24/7 Have staff that are trained to assess

Janet Kittams-Lalley Helpline Center Available 24/7 Have staff that are trained to assess and manage suicide crisis situations Staff are trained in safety planning Staff are trained in means restriction, reducing access to lethal

96 views • 7 slides

More recommend