Eliminating Crop Shadows in Video Sequences by Probable Learning Pixel Classification

  • Tanghai Liu
  • Xiaoping Cheng
Conference paper
Part of the The International Federation for Information Processing book series (IFIPAICT, volume 259)

Shadows have been one of the most serious problems for vegetation segmetation, espescially under conditions of natural random airflow and human or vehicle disturbance. A video sequence processing method has developed in this paper to identify and eliminate crop shadows. The method comprises pixel models and algorithms explained in a probable learning framework. Expectation maximization (EM) for mixture models is established and an incremental EM method is proposed. This method performs a probable reasoning unsupervised classification of pixels for real-time implementation. The results show that the method is quite robust and can successfully remove shadows under natural lighting conditions.


probable learning shadows vegetation segmentation video processing 


  1. Andreasen, C., M. Rudemo, and S. Sevestre, Assessment of weed density at an early stage by use of image processing, Weed Research 37, 1997: 5-18.CrossRefGoogle Scholar
  2. Easton, D. T., and Easton, D. J, Device to measure and provide data for plant population and spacing variability, U. S. Patent No. 5, 568, 405, 1996.Google Scholar
  3. Jean-Baptiste Vioix, Jean-Paul Douzals, Frédéric Truchetet, Louis Assémat, and Jean- hilippe Guillemin, Spatial and spectral methods for weed detection and Localization, EURASIP Journal on Applied Signal Processing 2002, 7: 697-685.Google Scholar
  4. Meyer, G. E., T. Mehta, M. F. Kocher, D. A. Mortensen, and A. Samal, Textural imaging and discriminant analysis for distinguishing weeds for spot spraying, Trans. ASAE 1998, 41 (4): 1189-1197.CrossRefGoogle Scholar
  5. National Research Council, Geospatial and Information Technologies in Crop Management, Washington, D. C. National Academy Press, 1997.Google Scholar
  6. Neal, R. M., and G. E. Hinton, A new view of the EM algorithm that justifies incremental and other variants, Unpublished manuscript, 1993.Google Scholar
  7. Nowlan, S. J., Soft Competitive Adaptation: Neural Network Learning Algorithms based on Fitting Statistical Mixtures, PhD thesis, School of Computer Science, Carnegie Mellon University, 1991.Google Scholar
  8. Pérez, A. J., F. López, J. V. Benlloch, and S. Christensen, Colour and shape analysis techniques for weed detection in cereal fields, Computers and Electronics in Agriculture 2000, 25 (3): 197-212.CrossRefGoogle Scholar
  9. Robert, P. C, Precision agriculture: a challenge for crop nutrition management, Plant and Soil 2002, 247 (1): 143-149.CrossRefGoogle Scholar
  10. Shrestha, D. S., and B. L. Strward, Automatic corn plant population measurement using machine vision, Transactions of the ASAE 2003, 46 (2): 559-565.Google Scholar
  11. Steward, B. L., and L. F. Tian, Machine-vision weed density estimation for real-time outdoor lighting conditions, Transactions of the ASAE, 1999, 42 (6): 1897-1909.CrossRefGoogle Scholar
  12. Steward, B. L., L. F. Tian, D. Nettleton, and L. Tang, Reducee-dimension clustering for vegetation segmentation, Transactions of the ASAE, 2004, 47 (6): 609-616.CrossRefGoogle Scholar
  13. Tang, L., L. Tian, and B. L. Steward, Classification of broadleaf and grass weeds using gabor wavelets and an artificial neural network, Transactions of the ASEA, 2003, 46 (4): 1247-1254.Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Tanghai Liu
    • 1
  • Xiaoping Cheng
    • 1
  1. 1.Faculty of Computer and Information ScienceSouthwest UniversityChina

Personalised recommendations