Skip to main content
Top

2016 | OriginalPaper | Chapter

In Defense of Gradient-Based Alignment on Densely Sampled Sparse Features

Authors : Hilton Bristow, Simon Lucey

Published in: Dense Image Correspondences for Computer Vision

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

In this chapter, we explore the surprising result that gradient-based continuous optimization methods perform well for the alignment of image/object models when using densely sampled sparse features (HOG, dense SIFT, etc.). Gradient-based approaches for image/object alignment have many desirable properties—inference is typically fast and exact, and diverse constraints can be imposed on the motion of points. However, the presumption that gradients predicted on sparse features would be poor estimators of the true descent direction has meant that gradient-based optimization is often overlooked in favor of graph-based optimization. We show that this intuition is only partly true: sparse features are indeed poor predictors of the error surface, but this has no impact on the actual alignment performance. In fact, for general object categories that exhibit large geometric and appearance variation, sparse features are integral to achieving any convergence whatsoever. How the descent directions are predicted becomes an important consideration for these descriptors. We explore a number of strategies for estimating gradients, and show that estimating gradients via regression in a manner that explicitly handles outliers improves alignment performance substantially. To illustrate the general applicability of gradient-based methods to the alignment of challenging object categories, we perform unsupervised ensemble alignment on a series of nonrigid animal classes from ImageNet.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Footnotes
1
In our experiments we actually estimate our linearization function from the template image \(\mathcal{T} (\mathbf{0}) \rightarrow \nabla \mathcal{T} (\mathbf{0})\) using a technique commonly known within LK literature as the inverse compositional approach. This was done due to the substantial computational benefit enjoyed by the inverse compositional approach, since one can estimate \(\mathcal{T} (\mathbf{0}) \rightarrow \nabla \mathcal{T} (\mathbf{0})\) once, as opposed to the classical approach of estimating \(\mathcal{R}(\mathbf{p}) \rightarrow \nabla \mathcal{R}(\mathbf{p})\) at each iteration. See [2, 3] for more details.
 
2
We removed those elephants whose out-of-plane rotation from the mean image could not be reasonably captured by an affine warp. The requirement of a single basis is a known limitation of the congealing algorithm.
 
Literature
1.
go back to reference Avidan, S.: Support vector tracking. Pattern Anal. Mach. Intell. (PAMI) 26(8), 1064–72 (2004) Avidan, S.: Support vector tracking. Pattern Anal. Mach. Intell. (PAMI) 26(8), 1064–72 (2004)
2.
go back to reference Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework: part 1. Int. J. Comput. Vis. 56(3), 221–255 (2004)CrossRef Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework: part 1. Int. J. Comput. Vis. 56(3), 221–255 (2004)CrossRef
3.
go back to reference Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework: part 2. Int. J. Comput. Vis. (IJCV) 56(3), 221–255 (2004) Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework: part 2. Int. J. Comput. Vis. (IJCV) 56(3), 221–255 (2004)
4.
go back to reference Black, M.J., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. Int. J. Comput. Vis. (IJCV) 26(1), 63–84 (1998) Black, M.J., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. Int. J. Comput. Vis. (IJCV) 26(1), 63–84 (1998)
5.
go back to reference Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 6, 681–685 (2001) Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 6, 681–685 (2001)
6.
go back to reference Cox, M., Sridharan, S., Lucey, S.: Least-squares congealing for large numbers of images. In: International Conference on Computer Vision (ICCV) (2009) Cox, M., Sridharan, S., Lucey, S.: Least-squares congealing for large numbers of images. In: International Conference on Computer Vision (ICCV) (2009)
7.
go back to reference Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 886–893 (2005) Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 886–893 (2005)
8.
go back to reference Dowson, N., Bowden, R.: Mutual information for Lucas-Kanade Tracking (MILK): an inverse compositional formulation. IEEE Trans. Pattern Anal. Mach. Intell. 30(1), 180–5 (2008)CrossRef Dowson, N., Bowden, R.: Mutual information for Lucas-Kanade Tracking (MILK): an inverse compositional formulation. IEEE Trans. Pattern Anal. Mach. Intell. 30(1), 180–5 (2008)CrossRef
9.
go back to reference Drucker, H., Burges, C., Kaufman, L., Smola, A., Vapnik, V.: Support vector regression machines. In: Advances in Neural Information Processing Systems (NIPS), pp. 155–161 (1997) Drucker, H., Burges, C., Kaufman, L., Smola, A., Vapnik, V.: Support vector regression machines. In: Advances in Neural Information Processing Systems (NIPS), pp. 155–161 (1997)
10.
go back to reference Felzenszwalb, P.F.: Representation and detection of deformable shapes. Pattern Anal. Mach. Intell. (PAMI) 27(2), 208–20 (2005) Felzenszwalb, P.F.: Representation and detection of deformable shapes. Pattern Anal. Mach. Intell. (PAMI) 27(2), 208–20 (2005)
11.
go back to reference Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. Pattern Anal. Mach. Intell. (PAMI) 32(9), 1627–45 (2010) Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. Pattern Anal. Mach. Intell. (PAMI) 32(9), 1627–45 (2010)
12.
go back to reference Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)CrossRef Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)CrossRef
13.
go back to reference Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. Pattern Anal. Mach. Intell. (PAMI) 33(5), 978–94 (2011) Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. Pattern Anal. Mach. Intell. (PAMI) 33(5), 978–94 (2011)
14.
go back to reference Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV) 60(2), 91–110 (2004) Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV) 60(2), 91–110 (2004)
15.
go back to reference Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence (IJCAI) (1981) Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence (IJCAI) (1981)
16.
go back to reference Rakêt, L., Roholm, L., Nielsen, M., Lauze, F.: TV-L 1 optical flow for vector valued images. In: Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 1–14 (2011) Rakêt, L., Roholm, L., Nielsen, M., Lauze, F.: TV-L 1 optical flow for vector valued images. In: Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 1–14 (2011)
17.
go back to reference Ramakrishna, V., Munoz, D., Hebert, M., Bagnell, J.A., Sheikh, Y.: Pose machines: articulated pose estimation via inference machines. In: European Conference on Computer Vision (ECCV), pp. 1–15 (2014) Ramakrishna, V., Munoz, D., Hebert, M., Bagnell, J.A., Sheikh, Y.: Pose machines: articulated pose estimation via inference machines. In: European Conference on Computer Vision (ECCV), pp. 1–15 (2014)
18.
go back to reference Saragih, J., Lucey, S., Cohn, J.: Face alignment through subspace constrained mean-shifts. In: International Conference on Computer Vision (ICCV) (2009) Saragih, J., Lucey, S., Cohn, J.: Face alignment through subspace constrained mean-shifts. In: International Conference on Computer Vision (ICCV) (2009)
19.
go back to reference Saragih, J.M., Lucey, S., Cohn, J.F.: Deformable model fitting by regularized landmark mean-shift. Int. J. Comput. Vis. (IJCV) 91(2), 200–215 (2011) Saragih, J.M., Lucey, S., Cohn, J.F.: Deformable model fitting by regularized landmark mean-shift. Int. J. Comput. Vis. (IJCV) 91(2), 200–215 (2011)
20.
go back to reference Simoncelli, E.P., Olshausen, B.A.: Natural image statistics and neural representation. Annu. Rev. Neurosci. 24(1), 1193–1216 (2001)CrossRef Simoncelli, E.P., Olshausen, B.A.: Natural image statistics and neural representation. Annu. Rev. Neurosci. 24(1), 1193–1216 (2001)CrossRef
21.
go back to reference Tsagkatakis, G., Tsakalides, P., Woiselle, A.: Compressed sensing reconstruction of convolved sparse signals. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014) Tsagkatakis, G., Tsakalides, P., Woiselle, A.: Compressed sensing reconstruction of convolved sparse signals. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014)
22.
go back to reference Viola, P., Jones, M.: Robust real-time object detection. Int. J. Comput. Vis. 4, 51–52 (2001) Viola, P., Jones, M.: Robust real-time object detection. Int. J. Comput. Vis. 4, 51–52 (2001)
23.
go back to reference Weber, J., Malik, J.: Robust computation of optical flow in a multi-scale differential framework. Int. J. Comput. Vis. (IJCV) 81, 67–81 (1995) Weber, J., Malik, J.: Robust computation of optical flow in a multi-scale differential framework. Int. J. Comput. Vis. (IJCV) 81, 67–81 (1995)
24.
go back to reference Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: International Conference on Computer Vision (ICCV), pp. 1385–1392 (2013) Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: International Conference on Computer Vision (ICCV), pp. 1385–1392 (2013)
25.
go back to reference Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 532–539 (2013) Xiong, X., De la Torre, F.: Supervised descent method and its applications to face alignment. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 532–539 (2013)
26.
go back to reference Yuille, A.: Deformable templates for face recognition. J. Cogn. Neurosci. 3(1), 59–70 (1991)CrossRef Yuille, A.: Deformable templates for face recognition. J. Cogn. Neurosci. 3(1), 59–70 (1991)CrossRef
27.
go back to reference Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 2879–2886 (2012) Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: International Conference of Computer Vision and Pattern Recognition (CVPR), pp. 2879–2886 (2012)
28.
go back to reference Zimmermann, K., Matas, J., Svoboda, T.: Tracking by an optimal sequence of linear predictors. Pattern Anal. Mach. Intell. (PAMI) 31(4), 677–92 (2009) Zimmermann, K., Matas, J., Svoboda, T.: Tracking by an optimal sequence of linear predictors. Pattern Anal. Mach. Intell. (PAMI) 31(4), 677–92 (2009)
Metadata
Title
In Defense of Gradient-Based Alignment on Densely Sampled Sparse Features
Authors
Hilton Bristow
Simon Lucey
Copyright Year
2016
DOI
https://doi.org/10.1007/978-3-319-23048-1_7