Abstract
In this paper we improve the histogram of oriented gradients (HOG), a core descriptor of state-of-the-art object detection, by the use of higher-level information coming from image segmentation. The idea is to re-weight the descriptor while computing it without increasing its size. The benefits of the proposal are two-fold: (i) to improve the performance of the detector by enriching the descriptor information and (ii) take advantage of the information of image segmentation, which in fact is likely to be used in other stages of the detection system such as candidate generation or refinement.
We test our technique in the INRIA person dataset, which was originally developed to test HOG, embedding it in a human detection system. The well-known segmentation method, mean-shift (from smaller to larger super-pixels), and different methods to re-weight the original descriptor (constant, region-luminance, color or texture-dependent) has been evaluated. We achieve performance improvements of 4.47% in detection rate through the use of differences of color between contour pixel neighborhoods as re-weighting function.
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
Preview
Unable to display preview. Download preview PDF.
References
Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 99(1), 898–916 (2010)
Boix, X., Gonfaus, J., van de Weijer, J., Bagdanov, A., Serrat, J., Gonzàlez, J.: Harmony potentials for joint classification and segmentation. In: IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, USA (2010)
Carreira, J., Sminchisescu, C.: Constrained parametric min-cuts for automatic object segmentation. In: IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, USA (2010)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(5), 603–619 (2002)
Dalal, N.: Finding people in images and videos. PhD Thesis, Institut National Polytechnique de Grenoble / INRIA Rhône-Alpes (2006)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conf. on Computer Vision and Pattern Recognition, San Diego, CA, USA (2005)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. on Pattern Analysis and Machine Intelligence (2011) (in press)
Enzweiler, M., Gavrila, D.: Monocular pedestrian detection: survey and experiments. IEEE Trans. on Pattern Analysis and Machine Intelligence 31(12), 2179–2195 (2009)
Enzweiler, M., Gavrila, D.: A multi-level mixture-of-experts framework for pedestrian classification. IEEE Trans. on Image Processing (2011) (in press)
Everingham, M., van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. Journal on Computer Vision 88(2), 303–338 (2010)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: IEEE Conf. on Computer Vision and Pattern Recognition, Anchorage, AK, USA (2008)
Gandhi, T., Trivedi, M.: Pedestrian protection systems: issues, survey, and challenges. IEEE Trans. on Intelligent Transportation Systems 8(3), 413–430 (2007)
Gavrila, D.: A bayesian, exemplar-based approach to hierarchical shape matching. IEEE Trans. on Pattern Analysis and Machine Intelligence 29(8), 1408–1421 (2007)
Gerónimo, D., López, A., Sappa, A., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. on Pattern Analysis and Machine Intelligence 32(7), 1239–1258 (2010)
Gould, S., Gao, T., Koller, D.: Region-based segmentation and object detection. In: Advances in Neural Information Processing Systems, Vancouver, BC, Canada (2009)
Guo, Z., Zhang, L., Zhang, D.: A completed modeling of local binary pattern operator for texture classification. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(6), 1657–1663 (2010)
Jones, M., Snow, D.: Pedestrian detection using boosted features over many frames. In: IEEE Conf. on Computer Vision and Pattern Recognition, Anchorage, AK, USA (2008)
Kumar, M., Torr, P., Zisserman, A.: Objcut: Efficient segmentation using top-down and bottom-up cues. IEEE Trans. on Pattern Analysis and Machine Intelligence 32(3), 530–545 (2010)
Ladický, Ľ., Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, Where and How Many? Combining Object Detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 424–437. Springer, Heidelberg (2010)
Laptev, I.: Improving object detection with boosted histograms. Image and Vision Computing 27(5), 535–544 (2009)
Liao, C.T., Lai, S.H., Wang, W.H.: A hierarchical image kernel with application to pedestrian identification for video surveillance. In: IEEE Int. Conf. on Image Processing, Cairo, Egypt (2009)
Lin, Z., Davis, L.: Shape-based human detection and segmentation via hierarchical part-template matching. IEEE Trans. on Pattern Analysis and Machine Intelligence 32(4), 604–618 (2010)
Ott, P., Everingham, M.: Implicit color segmentation features for pedestrain and object detection. In: Int. Conf. on Computer Vision, Kyoto, Japan (2009)
Rao, M., Vázquez, D., López, A.: Color contribution to part-based person detection in different types of scenarios. In: International Conference on Computer Analysis of Images and Patterns, Seville, Spain (2011)
van de Sande, K., Uijlings, J., Gevers, T., Smeulders, A.: Segmentation as selective search for object recognition. In: Int. Conf. on Computer Vision, Barcelona, Spain (2011)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, HI, USA (2001)
Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. Int. Journal on Computer Vision 63(2), 153–161 (2005)
Wang, X., Han, T., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: Int. Conf. on Computer Vision, Kyoto, Japan (2009)
Watanabe, T., Ito, S., Yokoi, K.: Co-Occurrence Histograms of Oriented Gradients for Pedestrian Detection. In: Wada, T., Huang, F., Lin, S. (eds.) PSIVT 2009. LNCS, vol. 5414, pp. 37–47. Springer, Heidelberg (2009)
Wyszecki, G., Stiles, W.: Color science: concepts and methods, quantitative data and formulae. Wiley Series in Pure and Applied Optics (1982)
Zhang, J., Huang, K., Yu, Y., Tan, T.: Boosted local structured hog-lbp for object localization. In: IEEE Conf. on Computer Vision and Pattern Recognition, Providence, RI, USA (2011)
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
Socarrás Salas, Y., Vázquez Bermudez, D., López Peña, A.M., Gerónimo Gomez, D., Gevers, T. (2012). Improving HOG with Image Segmentation: Application to Human Detection. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P., Zemčík, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2012. Lecture Notes in Computer Science, vol 7517. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33140-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-33140-4_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33139-8
Online ISBN: 978-3-642-33140-4
eBook Packages: Computer ScienceComputer Science (R0)