Analysis of Regionlets for Pedestrian Detection

Niels Ole Salscheider, Eike Rehder, Martin Lauer


Human detection is an important task for many autonomous robots as well as automated driving systems. The Regionlets detector was one of the best-performing approaches for pedestrian detection on the KITTI dataset during 2015. We analysed the Regionlets detector and its performance. This paper discusses the improvements in accuracy that were achieved by the different ideas of the Regionlets detector. It also analyses what the boosting algorithm learns and how this relates to the expectations. We found that the random generation of regionlet configurations can be replaced by a regular grid of regionlets. Doing so reduces the dimensionality of the feature space drastically but does not decrease detection performance. This translates into a decrease in memory consumption and computing time during training.


  1. Ahonen, T., Hadid, A., and Pietikäinen, M. (2004). Face Recognition with Local Binary Patterns. In Pajdla, T. and Matas, J., editors, ECCV (1), volume 3021 of Lecture Notes in Computer Science, pages 469-481. Springer.
  2. Dalal, N. and Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. pages 886-893. IEEE Computer Society.
  3. Felzenszwalb, P., Mcallester, D., and Ramanan, D. (2008). A Discriminatively Trained, Multiscale, Deformable Part Model. Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on.
  4. Geiger, A., Lenz, P., and Urtasun, R. (2012). Are we ready for autonomous driving? The KITTI vision benchmark suite. In CVPR, pages 3354-3361. IEEE Computer Society.
  5. Huang, C., Ai, H., Wu, B., and Lao, S. (2004). Boosting Nested Cascade Detector for Multi-View Face Detection. In ICPR (2), pages 415-418. IEEE Computer Society.
  6. Ranft, B. and Strauß, T. (2014). Modeling Arbitrarily Oriented Slanted Planes for Efficient Stereo Vision based on Block Matching. pages 1941-1947.
  7. Schapire, R. E. and Singer, Y. (1999). Improved Boosting Algorithms Using Confidence-rated Predictions. Machine Learning, 37(3):297-336.
  8. van de Sande, K. E. A., Uijlings, J. R. R., Gevers, T., and Smeulders, A. W. M. (2011). Segmentation as Selective Search for Object Recognition. In Metaxas, D. N., Quan, L., Sanfeliu, A., and Gool, L. J. V., editors, ICCV, pages 1879-1886. IEEE.
  9. Vogel, J. and Schiele, B. (2007). Semantic Modeling of Natural Scenes for Content-Based Image Retrieval. International Journal of Computer Vision, 72(2):133-157.
  10. Wang, X., Yang, M., Zhu, S., and Lin, Y. (2013). Regionlets for Generic Object Detection. In ICCV, pages 17-24. IEEE.

Paper Citation

in Harvard Style

Salscheider N., Rehder E. and Lauer M. (2017). Analysis of Regionlets for Pedestrian Detection . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 26-32. DOI: 10.5220/0006094100260032

in Bibtex Style

author={Niels Ole Salscheider and Eike Rehder and Martin Lauer},
title={Analysis of Regionlets for Pedestrian Detection},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

in EndNote Style

JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Analysis of Regionlets for Pedestrian Detection
SN - 978-989-758-222-6
AU - Salscheider N.
AU - Rehder E.
AU - Lauer M.
PY - 2017
SP - 26
EP - 32
DO - 10.5220/0006094100260032