Abstract
Histogram of Oriented Gradients (HOG) features have laid solid foundation for object detection in recent years for its both accuracy and speed. However, the expressivity of HOG is limited because the simple gradient features may ignore some important local information about objects and HOG is actually data-independent. In this paper, we propose to replace HOG by a parts-based representation, Histogram of Local Parts (HLP), for object detection under sliding window framework. HLP can capture richer and larger local patterns of objects and are more expressive than HOG. Specifically, we adopt Sparse Nonnegative Matrix Factorization to learn an over-complete parts-based dictionary from data. Then we can obtain HLP representation for a local patch by aggregating the Local Parts coefficients of pixels in this patch. Like DPM, we can train a supervised model with HLP given the latent positions of roots and parts of objects. Extensive experiments on INRIA and PASCAL datasets verify the superiority of HLP to state-of-the-art HOG-based methods for object detection, which shows that HLP is more effective than HOG.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3d human pose annotations. In: ICCV (2009)
Cai, D., He, X., Han, J., Huang, T.S.: Graph regularized nonnegative matrix factorization for data representation. TPAMI 33(8), 1548–1560 (2011)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Dikmen, M., Hoiem, D., Huang, T.S.: A data-driven method for feature transformation. In: CVPR (2012)
Ding, G., Guo, Y., Zhou, J.: Collective matrix factorization hashing for multimodal data. In: CVPR (2014)
Divvala, S., Efros, A., Hebert, M.: How important are deformable parts in the deformable parts model? In: ECCV (2012)
Dollar, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: BMVC (2009)
Everingham, M., Gool, L.V., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88(2), 303–338 (2010)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9), 1627–1645 (2010)
Girshick, R., Felzenszwalb, P., McAllester, D.: Object detection with grammar models. In: NIPS (2011)
Guo, Y., Ding, G., Jin, X., Wang, J.: Learning predictable and discriminative attributes for visual recognition. In: AAAI (2015)
Hoyer, P.O.: Non-negative matrix factorization with sparseness constraints. JMLR 5, 1457–1469 (2004)
Hussain, S., Kuntzmann, L., Triggs, B.: Feature sets and dimensionality reduction for visual object detection. In: BMVC (2010)
Lee, D.D., Seung, H.S.: Learning the parts of objects by nonnegative matrix factorization. Nature 401(6755), 788–791 (1999)
Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV (1999)
Malisiewicz, T., Gupta, A., Efros, A.: Ensemble of exemplar-svms for object detection and beyond. In: ICCV (2011)
Pirsiavash, H., Ramanan, D., Fowlkes, C.: Bilinear classifiers for visual recognition. In: NIPS (2009)
Ren, X., Ramanan, D.: Histograms of sparse codes for object detection. In: CVPR (2013)
Roshtkhari, M.J., Levine, M.D.: Online dominant and anomalous behavior detection in videos. In: CVPR (2013)
Schwartz, W., Kembhavi, A., Harwood, D., Davis, L.: Human detection using partial least squares analysis. In: ICCV (2009)
Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: ICCV (2009)
Vijayanarasimhan, S., Grauman, K.: Efficient region search for object detection. In: CVPR (2011)
Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)
Wachsmuth, M.W.O.E., Perrett, D.I.: Recognition of objects and their component parts: responses of single units in the temporal cortex of the macaque. Cereb. Cortex 4(5), 509–522 (1994)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T.S., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR 2010 (2010)
Xiao, J., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)
Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR (2011)
Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: CVPR (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Huang, C., Qin, Z., Xu, K., Wang, G., Xu, T. (2015). Beyond HOG: Learning Local Parts for Object Detection. In: Ho, YS., Sang, J., Ro, Y., Kim, J., Wu, F. (eds) Advances in Multimedia Information Processing -- PCM 2015. PCM 2015. Lecture Notes in Computer Science(), vol 9314. Springer, Cham. https://doi.org/10.1007/978-3-319-24075-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-24075-6_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24074-9
Online ISBN: 978-3-319-24075-6
eBook Packages: Computer ScienceComputer Science (R0)