LDA Combined Depth Similarity and Gradient Features for Human Detection using a Time-of-Flight Sensor

Alexandros Gavriilidis, Carsten Stahlschmidt, Jörg Velten, Anton Kummert

2015

Abstract

Visual object detection is an important task for many research areas like driver assistance systems (DASs), industrial automation and various safety applications with human interaction. Since detection of pedestrians is a growing research area, different kinds of visual methods and sensors have been introduced to overcome this problem. This paper introduces new relational depth similarity features (RDSF) for the pedestrian detection using a Time-of-Flight (ToF) camera sensor. The new features are based on mean, variance, skewness and kurtosis values of local regions inside the depth image generated by the Time-of-Flight sensor. An evaluation between these new features, already existing relational depth similarity features using depth histograms of local regions and the well known histogram of oriented gradients (HOGs), which deliver very good results in the topic of pedestrian detection, will be presented. To incorporate more dimensional feature spaces, an existing AdaBoost algorithm, which uses linear discriminant analysis (LDA) for feature space reduction and new combination of already extracted features in the training procedure, will be presented too.

References

  1. Dalal, N. and Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. In Proceedings of the IEEE Computer Society Conference on Computer
  2. Vision and Pattern Recognition (CVPR'05), volume 1,
  3. pages 886-893, San Diego,California,USA.
  4. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2012). Pedestrian Detection: An Evaluation of the State of the Art. IEEE Transactions on Pattern Analysis and Machine Learning, 34(4):743 - 761.
  5. Enzweiler, M. and Gavrila, D. M. (2009). Monocular Pedestrian Detection: Survey and Experiments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12):2179 - 2195.
  6. Ikemura, S. and Fujiyoshi, H. (2010). Real-Time Human Detection using Relational Depth Similarity Features. In Proceedings of the 10th Asian Conference on Computer Vision (ACCV'10), pages 25 - 38, Queenstown,New Zealand.
  7. Izenman, A. J. (2008). Modern Multivariate Statistical Techniques - Regression, Classification, and Manifold Learning. Springer New York.
  8. Keller, C. G., Enzweiler, M., and Gavrila, D. M. (2011). A New Benchmark for Stereo-Based Pedestrian Detection. In IEEE Intelligent Vehicles Symposium (IV'11), pages 691 - 696, Baden-Baden,Germany.
  9. Mattheij, R., Postma, E., van den Hurk, Y., and Spronck, P. (2012). Depth-based detection using haar-like features. In Proceedings of the 24th BENELUX Conference on Artificial Intelligence (BNAIC'12), pages 162 - 169, Maastricht,Netherlands.
  10. Nunn, C., Müller, D., Meuter, M., Müller-Schneiders, S., and Kummert, A. (2009). An Improved Adaboost Learning Scheme using Lda Features for Object Recognition. In Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems (ITSC'09), pages 486 - 491, St. Louis,MO,USA.
  11. Shafait, F., Keysers, D., and Breuel, T. M. (2008). Efficient Implementation of Local Adaptive Thresholding Techniques Using Integral Images. In Yanikoglu, B. A. and Berkner, K., editors, Proceedings SPIE 6815,Document Recognition and Retrieval XV.
  12. Spinello, L. and Arras, K. O. (2011). People detection in RGB-D data. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'11), pages 3838 - 3843, San Francisco,CA,USA.
  13. Viola, P. and Jones, M. (2001a). Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade. In Advances in Neural Information Processing System 14, pages 1311 - 1318. MIT Press.
  14. Viola, P. and Jones, M. (2001b). Rapid Object Detection Using a Boosted Cascade of Simple Features. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'01), volume 1, pages 511 - 518, Kauai,HI,USA.
  15. Wang, N., Gong, X., and Liu, J. (2012). A New Depth Descriptor for Pedestrian Detection in RGB-D Images. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR'12), pages 3688 - 3691, Tsukuba,Japan.
  16. Wu, S., Yu, S., and Chen, W. (2011). An attempt to pedestrian detection in depth images. In Proccedings of the 3rd Chinese Conference on Intelligent Visual Surveillance (IVS'11), pages 97 - 100, Beijing,China.
Download


Paper Citation


in Harvard Style

Gavriilidis A., Stahlschmidt C., Velten J. and Kummert A. (2015). LDA Combined Depth Similarity and Gradient Features for Human Detection using a Time-of-Flight Sensor . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 349-356. DOI: 10.5220/0005257403490356


in Bibtex Style

@conference{visapp15,
author={Alexandros Gavriilidis and Carsten Stahlschmidt and Jörg Velten and Anton Kummert},
title={LDA Combined Depth Similarity and Gradient Features for Human Detection using a Time-of-Flight Sensor},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={349-356},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005257403490356},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - LDA Combined Depth Similarity and Gradient Features for Human Detection using a Time-of-Flight Sensor
SN - 978-989-758-089-5
AU - Gavriilidis A.
AU - Stahlschmidt C.
AU - Velten J.
AU - Kummert A.
PY - 2015
SP - 349
EP - 356
DO - 10.5220/0005257403490356