Learning a Family of Detectors via Multiplicative Kernels

  • Quan Yuan
  • Ashwin Thangali
  • Vitaly Ablavsky
  • Stan Sclaroff
Chapter
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 8)

Abstract

Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. Model training is accomplished via standard SVM learning. When the foreground object masks are provided in training, the detectors can also produce object segmentations. A tracking-by-detection framework to recover foreground state in video sequences is also proposed with our model. The advantages of our method are demonstrated on tasks of object detection, view angle estimation and tracking. Our approach compares favorably to existing methods on hand and vehicle detection tasks. Quantitative tracking results are given on sequences of moving vehicles and human faces.

Keywords

Object recognition Object detection Object tracking Pose estimation Kernel methods 

Notes

Acknowledgments

This paper reports work that was supported in part by the U.S. National Science Foundation under grants IIS-0705749 and IIS-0713168.

References

  1. 1.
    Agarwal A, Triggs B (2004) 3D human pose from silhouettes by relevance vector regression. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  2. 2.
    Andriluka M, Roth S, Schiele B (2008) People-tracking-by-detection and people-detection-by-tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  3. 3.
    Athitsos V, Sclaroff S (2003) Estimating 3D hand pose from a cluttered image. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  4. 4.
    Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(24):509–522CrossRefGoogle Scholar
  5. 5.
    Bissacco A, Yang M, Soatto S (2006) Deteing humans via their pose. In: Proceedings of advances in neural information processing systemsGoogle Scholar
  6. 6.
    Blaschko MB, Lampert CH (2008) Learning to localize objects with structured output regression. In: Proceedings of the European conference on computer visionGoogle Scholar
  7. 7.
    Borenstein E, Ullman S (2002) Class-specific, top-down segmentation. In: Proceedings of the European conference on computer visionGoogle Scholar
  8. 8.
    Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297MATHGoogle Scholar
  9. 9.
    Crasborn O, van der Kooij E, Nonhebel A, Emmerik W (2004) ECHO data set for sign language of the Netherlands. Technical report Department of Linguistics, University NijmegenGoogle Scholar
  10. 10.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  11. 11.
    Damoulas T, Girolami MA (2008) Pattern recognition with a Bayesian kernel combination machine. Pattern Recogn Lett 30(1):46–54CrossRefGoogle Scholar
  12. 12.
    Enzweiler M, Gavrila DM (2008) A mixed generative-discriminative framework for pedestrian classification. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  13. 13.
    Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell (to appear)Google Scholar
  14. 14.
    Felzenszwalb PF, Huttenlocher DP (2005) Pictorial structures for object recognition. Int J Comput Vision 61:55–79CrossRefGoogle Scholar
  15. 15.
    Gavrila DM (2000) Pedestrian detection from a moving vehicle. In: Proceedings of the European conference on computer visionGoogle Scholar
  16. 16.
    Gross R, Matthews I, Cohn J, Kanade T, Baker S (2008) Multi-PIE. In: Proceedings of the IEEE international conference on face and gesture recognitionGoogle Scholar
  17. 17.
    Hoiem D, Efros AA, Hebert M (2008) Putting objects in perspective. Int J Comput Vision 80(1):3–15CrossRefGoogle Scholar
  18. 18.
    Huang C, Ai H, Li Y, Lao S (2007) High-performance rotation invariant multiview face detection. IEEE Trans Pattern Anal Mach Intell 29(4):671–686CrossRefGoogle Scholar
  19. 19.
    Ioffe C, Forsyth D (2001) Probabilistic methods for finding people. Int J Comput Vision 43(1):45–68MATHCrossRefGoogle Scholar
  20. 20.
    Ionescu C, Bo L, Sminchisescu C (2009) Structural SVM for visual localization and continuous state estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  21. 21.
    Isard M, Blake A (1998) CONDENSATION: Conditional density propagation for visual tracking. Int J Comput Vision 29(1):5–28CrossRefGoogle Scholar
  22. 22.
    Joachims T (1999) Making large-scale SVM learning practical. In: Scholkopf B, Burges C, Smola A (eds) Advances in Kernel methods—support vector learning. MIT Press, CambridgeGoogle Scholar
  23. 23.
    Kumar MP, Torr PHS, Zisserman A (2005) Obj Cut. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  24. 24.
    Leibe B, Cornelis N, Cornelis K, Gool LV (2007) Dynamic 3D scene analysis from a moving vehicle. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  25. 25.
    Leibe B, Leonardis A, Schiele B (2007) Robust object detection with interleaved categorization and segmentation. Int J Comput Vision 77(1):259–289CrossRefGoogle Scholar
  26. 26.
    Li S, Fu Q, Gu L, Scholkopf B, Cheng Y, Zhang H (2001) Kernel machine based learning for multi-view face detection and pose estimation. In: Proceedings of the IEEE international conference on computer visionGoogle Scholar
  27. 27.
    Li S, Zhang Z (2004) Floatboost learning and statistical face detection. IEEE Trans Pattern Anal Mach Intell 26(9):1112–1123CrossRefGoogle Scholar
  28. 28.
    Li Y, Ai H, Yamashita T, Lao S, Kawade M (2008) Tracking in low frame rate video: a cascade particle filter with discriminative observers of different life spans. IEEE Trans Pattern Anal Mach Intell 30(10):1728–1740CrossRefGoogle Scholar
  29. 29.
    Everingham M et al (2006) The 2005 PASCAL visual object class challenge. In: Machine learning challenges—evaluating predictive uncertainty, visual object classification, and recognising textual entailment, SpringerGoogle Scholar
  30. 30.
    Marszalek M, Schmid C, Harzallah H, van de Weijer J (2007) Learning object representations for visual object class recognition. In: Visual recognition challange workshop, in conjunction with ICCVGoogle Scholar
  31. 31.
    Murase H, Nayar SK (1995) Visual learning and recognition of 3D objects from appearance. Int J Comput Vision 14(1):5–24CrossRefGoogle Scholar
  32. 32.
    Neidle C (2003) ASLLRP signstream databases. Boston University, Boston. http://ling.bu.edu/asllrpdata/queryPages
  33. 33.
    Nocedal J, Wright SJ (2006) Numerical optimization. Springer, New YorkGoogle Scholar
  34. 34.
    Oikonomopoulos A, Patras I, Pantic M (2006) Kernel-based recognition of human actions using spatiotemporal salient points. In: Workshop on vision for human computer interactionGoogle Scholar
  35. 35.
    Okuma K, Taleghani A, Freitas ND, Little J, Lowe D (2004) A boosted particle filter: multitarget detection and tracking. In: Proceeedings of the European conference on computer visionGoogle Scholar
  36. 36.
    Ong E, Bowden R (2004) A boosted classifier tree for hand shape detection. In: Proceedings of the IEEE international conference on face and gesture recognitionGoogle Scholar
  37. 37.
    Osadchy R, Miller M, LeCun Y (2004) Synergistic face detection and pose estimation with energy-based model. In: Proceedings of advances in neural information processing systemsGoogle Scholar
  38. 38.
    Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vision 38(1):15–33MATHCrossRefGoogle Scholar
  39. 39.
    Pentland A, Moghaddam B, Starner T (1994) View-based and modular eigenspaces for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  40. 40.
    Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Smola A, Bartlett P, Scholkopf B, Schuurmans D (eds) Advances in large margin classifiers. MIT Press, CambridgeGoogle Scholar
  41. 41.
    Ramanan D, Forsyth DA, Zisserman A (2005) Strike a pose: tracking people by finding stylized poses. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  42. 42.
    Rifkin R, Klautau A (2004) In defense of one-vs-all classification. J Mach Learn Res 5:101–141Google Scholar
  43. 43.
    Rosales R, Sclaroff S (2002) Learning body pose via specialized maps. In: Proceedings of advances in neural information processing systemsGoogle Scholar
  44. 44.
    Russell BC, Torralba A, Murphy KP, Freeman WT (2005) LabelMe: a database and web-based tool for image annotation. Technical report, MIT Press, CambridgeGoogle Scholar
  45. 45.
    Seemann E, leibe B, Schiele B (2006) Multi-aspect detection of articulated objects. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  46. 46.
    Shakhnarovich G, Viola P, Darrell T (2003) Fast pose estimation with parameter-sensitive hashing. In: Proceedings of the IEEE international conference on computer visionGoogle Scholar
  47. 47.
    Shi J, Malik J (1997) Normalized cuts and image segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  48. 48.
    Sidenbladh H, Black MJ, Fleet DJ (2000) Stochastic tracking of 3D human figures using 2D image motion. In: Proceedings of the European conference on computer vision, pp 702–718Google Scholar
  49. 49.
    Sigal L, Bhatia S, Roth S, Black M, Isard M (2004) Tracking loose-limbed people. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  50. 50.
    Sminchisescu C, Kanaujia A, Metaxas D (2006) Learning joint top-down and bottom-up processes for 3D visual inference. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  51. 51.
    Stenger B, Thayananthan A, Torr P, Cipolla R (2003) Filtering using a tree-based estimator. In: Proceedings of the IEEE international conference on computer visionGoogle Scholar
  52. 52.
    Torralba A, Murphy K, Freeman W (2004) Sharing features: Efficient boosting procedures for multiclass object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  53. 53.
    Varma M, Ray D (2007) Learning the discriminative power-invariance trade-off. In: Proceedings of the IEEE international conference on computer vision. Rio de Janeiro, BrazilGoogle Scholar
  54. 54.
    Viola P, Jones M (2003) Fast multi-view face detection. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  55. 55.
    Viola P, Jones M (2004) Robust real time object detection. Int J Comput Vision 57(2):137–154CrossRefGoogle Scholar
  56. 56.
    Wang L, Shi J, Song G, Shen I (2007) Object detection combining recognition and segmentation. In: Proceedings of Asian conference on computer visionGoogle Scholar
  57. 57.
    Wu B, Nevatia R (2007) Cluster boosted tree classifier for multi-view multi-pose object detection. In: Proceedings of the IEEE international conference on computer visionGoogle Scholar
  58. 58.
    Wu B, Nevatia R (2007) Simultaneous object detection and segmentation by boosting local shape feature based classifier. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  59. 59.
    Yuan Q, Thangali A, Ablavsky V, Sclaroff S (2007) Parameter sensitive detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar
  60. 60.
    Zhu L, Chen Y, Lin C, Yuille AL (2007) Rapid inference on a novel and/or graph: detection, segmentation and parsing of articulated deformable objects in cluttered backgrounds. In: Proceedings of advances in neural information processing systemsGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Quan Yuan
    • 1
  • Ashwin Thangali
    • 2
  • Vitaly Ablavsky
    • 3
  • Stan Sclaroff
    • 2
  1. 1.Ventana Medical SystemsSunnyvaleUSA
  2. 2.Department of Computer ScienceBoston UniversityBostonUSA
  3. 3.EPFL IC-CVLabLausanneSwitzerland

Personalised recommendations