3D Descriptor for an Oriented-human Classification from Complete Point Cloud

Kyis Essmaeel, Cyrille Migniot, Albert Dipanda

2016

Abstract

In this paper we present a new 3D descriptor for the human classification. It is applied over a complete point cloud (i.e 360° view) acquired with a multi-kinect system. The proposed descriptor is derived from the Histogram of Oriented Gradient (HOG) descriptor: surface normal vectors are employed instead of gradients, 3D poins are expressed on a cylindrical space and 3D orientation quantization are computed by projecting the normal vectors on a regular polyhedron. Our descriptor is utilized through a Support Vector Machine (SVM) classifier. The SVM classifier is trained using an original database composed of data acquired by our multi-kinect system. The evaluation of the proposed 3D descriptor over a set of candidates shows very promising results. The descriptor can efficiently discriminate human from non-human candidates and provides the frontal direction of the human with a high precision. The comparison with a well known descriptor demonstrates significant improvements of results.

References

  1. Chang, C. C. and Lin, C. J. (2011). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Transactions on Intelligent Systems and Technology, 27:1-27.
  2. Choi, B., Mericli, C., Biswas, J., and Veloso, M. (2013). Fast human detection for indoor mobile robots using depth images. International Conference on Robotics and Automation, pages 1108-1113.
  3. Choi, B., Pantofaru, C., and Savarese, S. (2011). Detecting and tracking people using an rgb-d camera via multiple detector fusion. Conference on Computer Vision Workshops, pages 6-13.
  4. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition, I:886-893.
  5. Deveaux, J. C., Hadj-Abdelkader, H., and Colle, E. (2013). A multi-sensor calibration toolbox for kinect : Application to kinect and laser range finder fusion. International Conference on Advanced Robotics.
  6. Essmaeel, K., Gallo, L., Damiani, E., De Pietro, G., and Dipanda, A. (2012). Multiple structured light-based depth sensors for human motion analysis: A review. Ambient Assisted Living and Home Care, 7657:240- 247.
  7. Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24:381-395.
  8. Gond, L., Sayd, P., Chateau, T., and Dhome, M. (2008). A 3d shape descriptor for human pose recovery. Lecture Notes in Computer Science, 5098:370-379.
  9. Holz, D., Holzer, S., Rusu, R. B., and Benke, S. (2012). Real-time plane segmentation using rgb-d cameras. Lecture Notes in Computer Science, pages 306-317.
  10. Ikemura, S. and Fujiyoshi, H. (2011). Real-time human detection using relational depth similarity features. Asian Conference on Computer Vision, pages 25-38.
  11. Klaser, A., Marszalek, M., and Schmid, C. (2008). A spatiotemporal descriptor based on 3d-gradients. British Machine Vision Conference, pages 275:1-10.
  12. Munaro, M., Basso, F., and Menegatti, E. (2012). Tracking people within groups with rgb-d data. International Conference on Intelligent Robots and Systems, pages 2101-2107.
  13. Raposo, C., Barreto, J. P., and Nunes, U. (2013). Fast and accurate calibration of a kinect sensor. International Conference on 3D Vision, pages 342-349.
  14. Song, S. and Xiao, J. (2014). Sliding shapes for 3d object detection in depth images. European Conference on Computer Vision.
  15. Spinello, L. and Arras, K. O. (2011). People detection in rgb-d data. pages 3838-3843.
  16. Tang, S., Wang, X., Lv, X., Han, T. X., Keller, J., He, Z., Skubic, M., and Lao, S. (2012). Histogram of oriented normal vectors for object recognition with a depth sensor. Asian Conference on Computer Vision, 7725:525-538.
  17. Tian, Q., Zhou, B., Zhao, W., Wei, Y., and Fei, W. (2013). Human detection using hog features of head and shoulder based on depth map. Journal of Software, 8:2223-2230.
  18. Xia, L., Chen, C., and Aggarwal, J. K. (2011). Human detection using depth information by kinect. Computer Vision and Pattern Recognition Workshops, pages 15- 22.
Download


Paper Citation


in Harvard Style

Essmaeel K., Migniot C. and Dipanda A. (2016). 3D Descriptor for an Oriented-human Classification from Complete Point Cloud . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 353-360. DOI: 10.5220/0005679803530360


in Bibtex Style

@conference{visapp16,
author={Kyis Essmaeel and Cyrille Migniot and Albert Dipanda},
title={3D Descriptor for an Oriented-human Classification from Complete Point Cloud},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={353-360},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005679803530360},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - 3D Descriptor for an Oriented-human Classification from Complete Point Cloud
SN - 978-989-758-175-5
AU - Essmaeel K.
AU - Migniot C.
AU - Dipanda A.
PY - 2016
SP - 353
EP - 360
DO - 10.5220/0005679803530360