Advertisement

Green Coverage Detection on Sub-orbital Plantation Images Using Anomaly Detection

  • Gabriel B. P. Costa
  • Moacir Ponti
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)

Abstract

The green coverage region is a relevant information to be extracted from remote sensing agriculture images. Automatic methods based on threshold and vegetation indices are often applied to address this task. However, sub-orbital remote sensing images have elements that can hinder the automatic analysis. Also, supervised methods can suffer from imbalance since there is often many more green coverage samples available than regions of gaps, weed and degraded areas. We propose an anomaly detection approach to deal with these challenges. Parametric anomaly detection methods using the normal distribution were used and compared with vegetation indices, unsupervised and supervised learning methods. The results showed that anomaly detection algorithms can handle better the green coverage detection. The proposed methods showed similar or better accuracy when compared with the competing methods. It deals well with different images and with the imbalance problem, confirming the practical application of the approach.

Keywords

Anomaly outlier remote sensing 

References

  1. 1.
    Barnett, V., Lewis, T.: Outliers in statistical data. John Wiley & Sons (1994)Google Scholar
  2. 2.
    Chandola, V., Banerjee, A., Kumar, A.: Anomaly detection: A survey. ACM Computing Surveys 41(3), 15 (2009)CrossRefGoogle Scholar
  3. 3.
    Costa, G., Ponti, M., Frery, A.: Partially supervised anomaly detection using convex hulls on a 2D parameter space. In: Partially Supervised Learning. LNCS (LNAI), vol. 8183, pp. 1–8 (2013)Google Scholar
  4. 4.
    Gée, C., Bossu, J., Jones, G.: Truchetet: Crop/weed discrimination in perspective agronomic images. Comput. Electron. Agr. 62, 49–59 (2008)CrossRefGoogle Scholar
  5. 5.
    Haralick, R., Shanmugan, K., Dinstein, I.: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics SMC-3(6), 610–621 (1973)CrossRefGoogle Scholar
  6. 6.
    Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artificial Intelligence Review 22(2), 85–126 (2004)CrossRefzbMATHGoogle Scholar
  7. 7.
    Martins, F.C.M.: Evaluation of compact areas in the bean culture using remote sensing techniques. Master’s thesis, UFV, MG, Brazil (2010) (in Portuguese)Google Scholar
  8. 8.
    Pass, G., Zabih, R., Miller, J.: Comparing images using color coherence vectors. ACM Multimedia 96, 65–73 (1996)Google Scholar
  9. 9.
    Ponti, M.P.: Segmentation of low-cost remote sensing images combining vegetation indices and mean shift. IEEE Geoscience and Remote Sensing Letters 10(1), 67–70 (2013)CrossRefGoogle Scholar
  10. 10.
    Ponti Jr., M.P., Papa, J.P., Levada, A.L.M.: A Markov Random Field Model for Combining Optimum-Path Forest Classifiers Using Decision Graphs and Game Strategy Approach. In: San Martin, C., Kim, S.-W. (eds.) CIARP 2011. LNCS, vol. 7042, pp. 581–590. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Swain, K., Thomson, S., Jayasuriya, H.: Adoption of an unmanned helicopter for low-altitude remote sensing to estimate yield and total biomass of a rice crop. Transactions of the ASABE 53(1), 21–27 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Gabriel B. P. Costa
    • 1
  • Moacir Ponti
    • 1
  1. 1.Instituto de Ciências Matemáticas e de ComputaçãoUniversidade de São PauloSão CarlosBrazil

Personalised recommendations