Abstract
Most current approaches to recognition aim to be scale-invariant. However, the cues available for recognizing a 300 pixel tall object are qualitatively different from those for recognizing a 3 pixel tall object. We argue that for sensors with finite resolution, one should instead use scale-variant, or multiresolution representations that adapt in complexity to the size of a putative detection window. We describe a multiresolution model that acts as a deformable part-based model when scoring large instances and a rigid template with scoring small instances. We also examine the interplay of resolution and context, and demonstrate that context is most helpful for detecting low-resolution instances when local models are limited in discriminative power. We demonstrate impressive results on the Caltech Pedestrian benchmark, which contains object instances at a wide range of scales. Whereas recent state-of-the-art methods demonstrate missed detection rates of 86%-37% at 1 false-positive-per-image, our multiresolution model reduces the rate to 29%.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. International Journal of Computer Vision 80(1), 3–15 (2008)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (2009)
Lindeberg, T.: Scale-space theory in computer vision. Springer, Heidelberg (1994)
Lowe, D.: Distinctive image features from scale-invariant keypoints. International journal of computer vision 60, 91–110 (2004)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision 60, 63–86 (2004)
Fergus, R., Perona, P., Zisserman, A., et al: Object class recognition by unsupervised scale-invariant learning. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2 (2003) Citeseer
Dorko, G., Schmid, C.: Selection of scale-invariant parts for object class recognition. In: ICCV 2003 (2003) Citeseer
Mallat, S., Zhong, S.: Characterization of signals from multiscale edges. IEEE Transactions on pattern analysis and machine intelligence 14, 710–732 (1992)
Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.: Pedestrian detection using wavelet templates. In: IEEE CVPR, pp. 193–199 (1997)
Schneiderman, H., Kanade, T.: A statistical method for 3D object detection applied to faces and cars. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, IEEE Computer Society, Los Alamitos (1999/2000)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Computer Vision and Pattern Recognition, Anchorage, USA (June 2008)
Gavrila, D.: Pedestrian detection from a moving vehicle. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 37–49. Springer, Heidelberg (2000)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. I886–I893 (2005)
Enzweiler, M., Gavrila, D.M.: Monocular pedestrian detection: Survey and experiments. IEEE PAMI 31, 2179–2195 (2009)
Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE PAMI 23, 349 (2001)
Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. IEEE PAMI 30, 1713–1727 (2008)
Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. International Journal of Computer Vision (2009)
Lin, Z., Hua, G., Davis, L.S.: Multiple instance feature for robust part-based object detection. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 405–412 (2009)
Maji, S., Berg, A., Malik, J.: Classification using intersection kernel SVMs is efficient. In: IEEE Conf. on Computer Vision and Pattern Recognition (2008)
Schwartz, W., Kembhavi, A., Harwood, D., Davis, L.: Human detection using partial least squares analysis. International Journal of Computer Vision (2009)
Wojek, C., Walk, S., Schiele, B.: Multi-cue onboard pedestrian detection. In: IEEE Conf. on Computer Vision and Pattern Recognition (2009)
Gavrila, D.M., Munder, S.: Multi-cue pedestrian detection and tracking from a moving vehicle. International journal of computer vision 73, 41–59 (2007)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE PAMI 99(5555)
Dollar, P., Babenko, B., Belongie, S., Perona, P., Tu, Z.: Multiple component learning for object detection. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 211–224. Springer, Heidelberg (2008)
Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: Proc. CVPR, pp. 1–8 (2007)
Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models of multi-class object layout. In: ICCV (2009)
Yu, C., Joachims, T.: Learning structural SVMs with latent variables. In: Proceedings of the 26th Annual International Conference on Machine Learning. ACM, New York (2009)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results (2007), http://www.pascal-network.org/challenges/VOC/voc2007/workshop
Dollár, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: BMVC (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, D., Ramanan, D., Fowlkes, C. (2010). Multiresolution Models for Object Detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6314. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15561-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-15561-1_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15560-4
Online ISBN: 978-3-642-15561-1
eBook Packages: Computer ScienceComputer Science (R0)