Cross-Articulation Learning for Robust Detection of Pedestrians

  • Edgar Seemann
  • Bernt Schiele
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


Recognizing categories of articulated objects in real-world scenarios is a challenging problem for today’s vision algorithms. Due to the large appearance changes and intra-class variability of these objects, it is hard to define a model, which is both general and discriminative enough to capture the properties of the category. In this work, we propose an approach, which aims for a suitable trade-off for this problem. On the one hand, the approach is made more discriminant by explicitly distinguishing typical object shapes. On the other hand, the method generalizes well and requires relatively few training samples by cross-articulation learning. The effectiveness of the approach is shown and compared to previous approaches on two datasets containing pedestrians with different articulations.


Local Context Training Image Interest Point Training Instance Object Shape 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI (2002)Google Scholar
  2. 2.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  3. 3.
    Felzenszwalb, P., Huttenlocher, D.: Efficient matching of pictorial structures. In: CVPR (2000)Google Scholar
  4. 4.
    Forsyth, D., Fleck, M.: Body plans. In: CVPR (1997)Google Scholar
  5. 5.
    Gavrila, D.: Multi-feature hierarchical template matching using distance transforms. In: ICPR, vol. 1, pp. 439–444 (1998)Google Scholar
  6. 6.
    Leibe, B., Schiele, B.: Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 145–153. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: CVPR (2005)Google Scholar
  8. 8.
    Mikolajczyk, C., Schmid, C., Zisserman, A.: Human Detection Based on a Probabilistic Assembly of Robust Part Detectors. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 69–82. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27(10), 1615–1630 (2005)Google Scholar
  10. 10.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. PAMI 23(4), 349–361 (2001)Google Scholar
  11. 11.
    Papageorgiou, C., Poggio, T.: A trainable system for object detection. IJCV 38(1), 15–33 (2000)MATHCrossRefGoogle Scholar
  12. 12.
    Seemann, E., Leibe, B., Mikolajczyk, K., Schiele, B.: An evaluation of local shape-based features for pedestrian detection. In: BMVC (2005)Google Scholar
  13. 13.
    Seemann, E., Leibe, B., Schiele, B.: Multi-aspect detection of articulated objects. In: CVPR (2006)Google Scholar
  14. 14.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for realtime tracking. In: CVPR (1999)Google Scholar
  15. 15.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. PAMI (submitted, 2005)Google Scholar
  16. 16.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: ICCV, pp. 734–741 (2003)Google Scholar
  17. 17.
    Zhao, L., Thorpe, C.: Stereo and neural network-based pedestrian detection. IEEE Transactions on Intelligent Transportation Systems 1(3), 148–154 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Edgar Seemann
    • 1
  • Bernt Schiele
    • 1
  1. 1.Technical University of Darmstadt 

Personalised recommendations