Discriminatively trained patch-based model for occupant classification

Access Full Text

Discriminatively trained patch-based model for occupant classification

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Intelligent Transport Systems — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Published

This study presents a vision-based occupant classification method which is essential for developing a system that can intelligently decide when to turn on airbags based on vehicle occupancy. To circumvent intra-class variance, this work considers the empty class as a reference and describes the occupant class by using appearance difference rather than the traditional methods of using appearance itself. Each class in this work is modelled using a set of representative parts called patches. Each patch is represented by a Gaussian distribution. This approach successfully alleviates the mis-classification problem resulting from severe lighting change which makes the image locally overexposed or underexposed. Instead of using maximum likelihood for patch selection and estimating the parameters of the proposed generative models, the proposed method discriminatively learns models through a boosting algorithm by minimising training error. Experimental results from many videos (approximately 1 630 000 frames) from a camera deployed on a moving platform demonstrate the effectiveness of the proposed approach.

Inspec keywords: computer vision; Gaussian distribution; learning (artificial intelligence); image classification; road safety; traffic engineering computing

Other keywords: misclassification problem; boosting algorithm; Gaussian distribution; intraclass variance; generative models; vehicle occupancy; vision-based occupant classification method; discriminatively trained patch-based model; patch selection

Subjects: Other topics in statistics; Computer vision and image processing techniques; Traffic engineering computing; Optical, image and video signal processing; Other topics in statistics; Knowledge engineering techniques

References

    1. 1)
    2. 2)
      • Zhang, Y., Kiselewich, S.J., Bauson, W.A.: `A monocular vision-based occupant classification approach for smart airbag', IEEE Proc. Intelligent Vehicle Symp., 2005, p. 632–637.
    3. 3)
    4. 4)
      • Deselaers, T., Keysers, D., Ney, H.: `Discriminative training for object recognition using image patches', IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2005, p. 20–25.
    5. 5)
      • Owechko, Y., Srinivasa, N., Medasani, S., Boscolo, R.: `Vision-based fusion system for smart airbag application', IEEE Proc. Intelligent Vehicle Symp., 2002, p. 245–250.
    6. 6)
      • Huang, S.S., Hsiao, P.Y.: `Occupant classification for smart airbag using bayesian filtering', Int. Conf. on Green Circuits and Systems, 2010.
    7. 7)
      • Owechko, Y., Srinivasa, N., Medasani, S., Boscolo, R.: `High performance sensor fusion architecture for vision-based occupant detection', IEEE Int. Conf. on Intelligent Transportation Systems, 2003, p. 1128–1132.
    8. 8)
    9. 9)
      • Weiss, Y.: `Deriving intrinsic images from image sequences', IEEE Conf. on Computer Vision, 2001, 1, p. 68–75.
    10. 10)
      • Krumm, J., Kirk, G.: `Video occupant detection for airbag deployment', IEEE Workshop on Applications of Computer Vision, 1998, p. 30–35.
    11. 11)
      • Hillel, A.B., Hertz, T., Weinshall, D.: `Object class recognition by boosting a part-based model', IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2005, p. 702–709.
    12. 12)
      • Farmer, M.E., Jain, A.K.: `Occupant classification system for automotive airbag suppression', IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2003, 1, p. 756–761.
    13. 13)
      • L. Mason , J. Baxter , P. Bartlett , M. Frean . Boosting algorithm as gradient descent. Neural Inform. Process. Syst. , 512 - 518
    14. 14)
      • R.E. Fan , P.H. Chen , C.J. Lin . Working set selection using second order information for training support vector machines. J. Mach. Learning Res. , 1889 - 1918
    15. 15)
      • Dalal, N., Triggs, B.: `Histograms of oriented gradients for human detection', IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2005, 1, p. 886–893.
    16. 16)
      • Stefano, L.D., Tombari, F., Mottoccia, S.: `Robust and accurate change detection under sudden illumination variations', Asia Conf. on Computer Vision, 2007, p. 103–109.
    17. 17)
    18. 18)
    19. 19)
      • Leibe, B., Leonardis, A., Schiele, B.: `Combined object categorization and segmentation with an implicit shape model', European Conf. on Computer Vision Workshop on Statistical Learning in Computer Vision, 2004, p. 17–32.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2011.0048
Loading

Related content

content/journals/10.1049/iet-its.2011.0048
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading