Disparity Statistics for Pedestrian Detection: Combining Appearance, Motion and Stereo
Conference paper
Abstract
Pedestrian detection is an important problem in computer vision due to its importance for applications such as visual surveillance, robotics, and automotive safety. This paper pushes the state-of-the-art of pedestrian detection in two ways. First, we propose a simple yet highly effective novel feature based on binocular disparity, outperforming previously proposed stereo features. Second, we show that the combination of different classifiers often improves performance even when classifiers are based on the same feature or feature combination. These two extensions result in significantly improved performance over the state-of-the-art on two challenging datasets.
Keywords
Ground Plane Motion Information Human Detection Pedestrian Detection Disparity Statistics
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.
Download
to read the full conference paper text
References
- 1.Gavrila, D.M., Munder, S.: Multi-cue pedestrian detection and tracking from a moving vehicle. IJCV 73, 41–59 (2007)CrossRefGoogle Scholar
- 2.Ess, A., Leibe, B., Schindler, K., van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR (2008)Google Scholar
- 3.Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428–441. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 4.Wojek, C., Walk, S., Schiele, B.: Multi-cue onboard pedestrian detection. In: CVPR (2009)Google Scholar
- 5.Papageorgiou, C., Poggio, T.: A trainable system for object detection. IJCV 38, 15–33 (2000)zbMATHCrossRefGoogle Scholar
- 6.Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: ICCV (2003)Google Scholar
- 7.Enzweiler, M., Gavrila, D.M.: Monocular pedestrian detection: Survey and experiments. In: PAMI (2009)Google Scholar
- 8.Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: CVPR (2009)Google Scholar
- 9.Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: People detection and articulated pose estimation. In: CVPR (2009)Google Scholar
- 10.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
- 11.Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
- 12.Wang, X., Han, T.X., Yan, S.: A HOG-LBP human detector with partial occlusion handling. In: ICCV (2009)Google Scholar
- 13.Dalal, N.: Finding People in Images and Videos. PhD thesis, Institut National Polytechnique de Grenoble (2006)Google Scholar
- 14.Rohrbach, M., Enzweiler, M., Gavrila, D.M.: High-level fusion of depth and intensity for pedestrian classification. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 101–110. Springer, Heidelberg (2009)Google Scholar
- 15.Rapus, M., Munder, S., Baratoff, G., Denzler, J.: Pedestrian recognition using combined low-resolution depth and intensity images. In: IEEE Intelligent Vehicles Symposium (2008)Google Scholar
- 16.Shashua, A., Gdalyahu, Y., Hayun, G.: Pedestrian detection for driving assistance systems: Single-frame classification and system level performance. In: IVS (2004)Google Scholar
- 17.Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: CVPR (2007)Google Scholar
- 18.Lin, Z., Davis, L.S.: A pose-invariant descriptor for human detection and segmentation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 423–436. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 19.Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast human detection using a cascade of histograms of oriented gradients. In: CVPR (2006)Google Scholar
- 20.Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet part detectors. IJCV 75, 247–266 (2007)CrossRefGoogle Scholar
- 21.Duin, R.P.W., Tax, D.M.J.: Experiments with classifier combining rules. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, p. 16. Springer, Heidelberg (2000)CrossRefGoogle Scholar
- 22.Ess, A., Leibe, B., Schindler, K., van Gool, L.: Moving obstacle detection in highly dynamic scenes. In: ICRA (2009)Google Scholar
- 23.Ess, A., Leibe, B., Schindler, K., Van Gool, L.: Robust multi-person tracking from a mobile platform. PAMI 31(10), 1831–1846 (2009)Google Scholar
- 24.Babenko, B., Dollár, P., Tu, Z., Belongie, S.: Simultaneous learning and alignment: Multi-instance and multi-pose learning. In: ECCV workshop on Faces in Real-Life Images (2008)Google Scholar
- 25.Kim, T.K., Cipolla, R.: MCBoost: Multiple classifier boosting for perceptual co-clustering of images and visual features. In: NIPS (2008)Google Scholar
- 26.Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: BMVC (2009)Google Scholar
- 27.Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR (2008)Google Scholar
- 28.Gehler, P.V., Nowozin, S.: On feature combination for multiclass object classification. In: ICCV (2009)Google Scholar
- 29.Zach, C., Frahm, J.M., Niethammer, M.: Continuous maximal flows and Wulff shapes: Application to MRFs. In: CVPR (2009)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2010