Abstract
Most of current pedestrian detectors have pursued high detection rate without carefully considering sample distributions. In this paper, we argue that the following characteristics must be considered; (1) large intra-class variation of pedestrians (multi-modality), and (2) data imbalance between positives and negatives. Pedestrian detection can be regarded as one of finding needles in a haystack problems (rare class detection). Inspired by a rare class detection technique, we propose a two-phase classifier integrating an existing baseline detector and a hard negative expert by separately conquering recall and precision. Main idea behind the hard negative expert is to reduce sample space to be learned, so that informative decision boundaries can be effectively learned. The multi-modality problem is dealt with a simple variant of a LDA based random forests as the hard negative expert. We optimally integrate two models by learned integration rules. By virtue of the two-phase structure, our method achieve competitive performance with only little additional computation. Our approach achieves 38.44 % mean miss-rate for the reasonable setting of Caltech Pedestrian Benchmark.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. PAMI 34, 743–761 (2012)
Dalal, N., Triggs, B.: Histogram of oriented gradient for human detection. In: CVPR (2005)
Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: ICCV (2009)
Walk, S., Majer, N., Schindler, K., Schiele, B.: New features and insights for pedestrian detection. In: CVPR (2010)
Dollár, P., Tu, Z., Perona, P., Belonggie, S.: Integral channel features. In: BMVC (2009)
Yan, J., Zhang, X., Lei, Z., Liao, S., Li, S.Z.: Robust multi-resolution pedestrian detection in traffic scenes. In: CVPR (2013)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. PAMI 32, 1627–1645 (2010)
Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: CVPR (2005)
Zhang, C., Viola, P.A.: Multiple-instance pruning for learning efficient cascade detectors. In: NIPS (2007)
Dollár, P., Appel, R., Kienzle, W.: Crosstalk cascades for frame-rate pedestrian detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 645–659. Springer, Heidelberg (2012)
Viola, P., Jones, M.J.: Robust real-time face detection. IJCV 52, 137–154 (2004)
Benenson, R., Mathias, M., Timofte, R., Van Gool, L.: Pedestrian detection at 100 frames per second. In: CVPR (2012)
Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. PAMI 36, 1532–1545 (2014)
Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: CVPR (2009)
Marín, J., Vazquez, D., Lopez, A.M., Amores, J., Leibe, B.: Random forests of local experts for pedestrian detection. In: ICCV (2013)
Joshi, M.V., Agarwal, R.C., Kumar, V.: Mining needles in a haystack: classifying rare classes via two-phase rule induction. In: ACM SIGMOD, pp. 91–102 (2001)
Weiss, G.M.: Mining with rarity: a unifying framework. In: ACM SIGKDD (2004)
Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Found. Trends in Comput. Graph. Vis. 7, 81–227 (2011)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7, 179–188 (1936)
Vondrick, C., Khosla, A., Malisiewicz, T., Torralba, A.: Hoggles: Visualizing object detection features. In: ICCV, IEEE (2013)
Geronimo, D., Lopez, A.M., Sappa, A.D., Graf, T.: Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. PAMI 32, 1239–1258 (2010)
Park, D., Zitnick, C.L., Ramanan, D., Dollar, P.: Exploring weak stabilization for motion feature extraction. In: CVPR (2013)
Ouyang, W., Wang, X.: Single-pedestrian detection aided by multi-pedestrian detection. In: CVPR (2013)
Park, D., Ramanan, D., Fowlkes, C.: Multiresolution models for object detection. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 241–254. Springer, Heidelberg (2010)
Hsu, W.H., Kennedy, L.S., Chang, S.F.: Reranking methods for visual search. IEEE MultiMed. 14, 14–22 (2007)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Lemmond, T.D., Chen, B.Y., Hatch, A.O., Hanley, W.G.: An extended study of the discriminant random forest. Data Mining 8, 123–146 (2010)
Yao, B., Khosla, A., Fei-Fei, L.: Combining randomization and discrimination for fine-grained image categorization. In: CVPR (2011)
Menze, B.H., Kelm, B.M., Splitthoff, D.N., Koethe, U., Hamprecht, F.A.: On oblique random forests. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part II. LNCS, vol. 6912, pp. 453–469. Springer, Heidelberg (2011)
Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley-Interscience, Hoboken (2001)
Hamsici, O.C., Martinez, A.M.: Bayes optimality in linear discriminant analysis. IEEE Trans. PAMI 30, 647–657 (2008)
Devijver, P.A., Kittler, J.: Pattern recognition: a statistical approach. Prentice-Hall, London (1982)
Joachims, T.: Optimizing search engines using clickthrough data. In: ACM SIGKDD (2002)
Flamary, R., Jrad, N., Phlypo, R., Congedo, M., Rakotomamonjy, A.: Mixed-norm regularization for brain decoding. Comput. Math. Methods Med. 2014, 1–13 (2014)
Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. IJCV 80, 3–15 (2008)
Opencv 3.0. http://opencv.org/
Acknowledgement
This work was supported by the Development of Autonomous Emergency Braking System for Pedestrian Protection project funded by the Ministry of Trade, Industry and Energy of Korea. (MOTIE)(No.10044775)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hwang, S., Oh, TH., Kweon, I.S. (2015). A Two Phase Approach for Pedestrian Detection. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9009. Springer, Cham. https://doi.org/10.1007/978-3-319-16631-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-16631-5_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16630-8
Online ISBN: 978-3-319-16631-5
eBook Packages: Computer ScienceComputer Science (R0)