Abstract
Computing part scores is the main computational bottleneck in object detection with Deformable Part Models. In this work we introduce an efficient method to obtain bounds on part scores, which we then integrate with deformable model detection. As in [1] we rapidly approximate the inner product between a weight vector and HOG-based features by quantizing the HOG cells onto a codebook and replace their inner product with the lookup of a precomputed score. The novelty in our work consists in combining this lookup-based estimate with the codebook quantization error so as to construct probabilistic bounds to the exact inner product.
In particular we use Chebyshev’s inequality to obtain probably correct bounds for the inner product at each image location. We integrate these bounds with both the Dual-Tree Branch-and-Bound work of [2,3] and the Cascade-DPMs of [4]; in both cases the bounds are used in a first phase to conservatively construct a short-list of locations, for which the exact inner products are subsequently evaluated.
We quantitatively evaluate our method and demonstrate that it allows for approximately a twofold speedup over both [2] and [4] with negligible loss in accuracy.
Chapter PDF
Similar content being viewed by others
References
Vedaldi, A., Zisserman, A.: Sparse Kernel Approximations for Efficient Classification and Detection. In: CVPR (2012)
Kokkinos, I.: Rapid deformable object detection using dual-tree branch-and-bound. In: NIPS (2011)
Kokkinos, I.: Rapid Deformable Object Detection using Bounding-based Techniques. Technical Report 7940, INRIA (2012)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A.: Cascade object detection with deformable part models. In: CVPR (2010)
Felzenszwalb, P.F., Huttenlocher, D.: Efficient Matching of Pictorial Structures. In: CVPR (2000)
Felzenszwalb, P.F., Girshick, R., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. IEEE T. PAMI (2010)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Discriminatively trained deformable part models, release 4, http://people.cs.uchicago.edu/~pff/latent-release4/
Pedersoli, M., Vedaldi, A., Gonzàlez, J.: A coarse-to-fine approach for fast deformable object detection. In: CVPR (2011)
Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: CVPR (2001)
Fleuret, F., Geman, D.: Coarse-to-fine face detection. IJCV (2001)
Sapp, B., Toshev, A., Taskar, B.: Cascaded Models for Articulated Pose Estimation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 406–420. Springer, Heidelberg (2010)
Lampert, C., Blaschko, M., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR (2008)
Lampert, C.H.: An efficient divide-and-conquer cascade for nonlinear object detection. In: CVPR (2010)
Kokkinos, I., Yuille, A.: HOP: Hierarchical Object Parsing. In: CVPR (2009)
Sun, M., Telaprolu, M., Lee, H., Savarese, S.: An efficient branch-and-bound algorithm for optimal human pose estimation. In: CVPR (2012)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 2, pp. 886–893 (2005)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
Mitzenmacher, M., Upfal, E.: Probability and computing - randomized algorithms and probabilistic analysis. Cambridge University Press (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kokkinos, I. (2012). Bounding Part Scores for Rapid Detection with Deformable Part Models. In: Fusiello, A., Murino, V., Cucchiara, R. (eds) Computer Vision – ECCV 2012. Workshops and Demonstrations. ECCV 2012. Lecture Notes in Computer Science, vol 7585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33885-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-33885-4_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33884-7
Online ISBN: 978-3-642-33885-4
eBook Packages: Computer ScienceComputer Science (R0)