Skip to main content

2018 | OriginalPaper | Buchkapitel

Automatic Detection of Thistle-Weeds in Cereal Crops from Aerial RGB Images

verfasst von : Camilo Franco, Carely Guada, J. Tinguaro Rodríguez, Jon Nielsen, Jesper Rasmussen, Daniel Gómez, Javier Montero

Erschienen in: Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Capturing aerial images by Unmanned Aerial Vehicles (UAV) allows gathering a general view of an agricultural site together with a detailed exploration of its relevant aspects for operational actions. Here we explore the challenging task of detecting cirsium arvense, a thistle-weed species, from aerial images of barley-cereal crops taken from 50 m above the ground, with the purpose of applying herbicide for site-specific weed treatment. The methods for automatic detection are based on object-based annotations, pointing out the RGB attributes of the Weed or Cereal classes for an entire group of pixels, referring to a crop area which will have to be treated if it is classified as being of the Weed class. In this way, an annotation belongs to the Weed class if more than half of its area is known to be covered by thistle weeds. Hence, based on object and pixel-level analysis, we compare the use of k-Nearest Neighbours (k-NN) and (feed-forward, one-hidden layer) neural networks, obtaining the best results for weed detection based on pixel-level analysis, based on a soft measure given by the proportion of predicted weed pixels per object, with a global accuracy of over 98%.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Andrew, M.E., Ustin, S.L.: The role of environmental context in mapping invasive plants with hyperspectral image data. Remote Sens. Environ. 112, 4301–4317 (2008)CrossRef Andrew, M.E., Ustin, S.L.: The role of environmental context in mapping invasive plants with hyperspectral image data. Remote Sens. Environ. 112, 4301–4317 (2008)CrossRef
2.
Zurück zum Zitat Blaschke, T.: Object based image analysis for remote sensing. ISPRS J. Photogrammetry Remote Sens. 65, 2–16 (2010)CrossRef Blaschke, T.: Object based image analysis for remote sensing. ISPRS J. Photogrammetry Remote Sens. 65, 2–16 (2010)CrossRef
3.
Zurück zum Zitat Blaschke, T., Burnett, C., Pekkarinen, A.: New contextual approaches using image segmentation for object-based classification. In: De Meer, F., de Jong, S. (eds.) Remote Sensing Image Analysis: Including the Spatial Domain, pp. 211–236. Kluver Academic Publishers, Dordrecht (2004)CrossRef Blaschke, T., Burnett, C., Pekkarinen, A.: New contextual approaches using image segmentation for object-based classification. In: De Meer, F., de Jong, S. (eds.) Remote Sensing Image Analysis: Including the Spatial Domain, pp. 211–236. Kluver Academic Publishers, Dordrecht (2004)CrossRef
4.
Zurück zum Zitat Duro, D.C., Franklin, S.E., Dubé, M.G.: A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sens. Environ. 118, 259–272 (2012)CrossRef Duro, D.C., Franklin, S.E., Dubé, M.G.: A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sens. Environ. 118, 259–272 (2012)CrossRef
5.
Zurück zum Zitat Egorov, A.V., Hansen, M.C., Roya, D.P., Kommareddy, A., Potapov, P.V.: Image interpretation-guided supervised classification using nested segmentation. Remote Sens. Environ. 165, 135–147 (2015)CrossRef Egorov, A.V., Hansen, M.C., Roya, D.P., Kommareddy, A., Potapov, P.V.: Image interpretation-guided supervised classification using nested segmentation. Remote Sens. Environ. 165, 135–147 (2015)CrossRef
6.
Zurück zum Zitat Franco, C., Pedersen, S.M., Papaharalampos, H., Ørum, J.E.: The value of precision for image-based decision support in weed management. Precis. Agric. 18, 366–382 (2017)CrossRef Franco, C., Pedersen, S.M., Papaharalampos, H., Ørum, J.E.: The value of precision for image-based decision support in weed management. Precis. Agric. 18, 366–382 (2017)CrossRef
7.
Zurück zum Zitat Gómez, D., Biging, G., Montero, J.: Accuracy statistics for judging soft classification. Int. J. Remote Sens. 29, 693–709 (2008)CrossRef Gómez, D., Biging, G., Montero, J.: Accuracy statistics for judging soft classification. Int. J. Remote Sens. 29, 693–709 (2008)CrossRef
8.
Zurück zum Zitat Gómez, D., Biging, G.S., Montero, J.: Accuracy assessment for soft classification maps. In: Wang, G., Weng, Q. (eds.) Remote Sensing of Natural Resources, pp. 57–86. CRC Press, Boca Raton (2014)CrossRef Gómez, D., Biging, G.S., Montero, J.: Accuracy assessment for soft classification maps. In: Wang, G., Weng, Q. (eds.) Remote Sensing of Natural Resources, pp. 57–86. CRC Press, Boca Raton (2014)CrossRef
9.
Zurück zum Zitat Guada, C., Gómez, D., Rodríguez, J.T., Yáñez, J., Montero, J.: Classifying image analysis techniques from their output. Int. J. Comput. Intell. Syst. 9, 43–68 (2016)CrossRef Guada, C., Gómez, D., Rodríguez, J.T., Yáñez, J., Montero, J.: Classifying image analysis techniques from their output. Int. J. Comput. Intell. Syst. 9, 43–68 (2016)CrossRef
10.
Zurück zum Zitat Guada, C., Zarrazola, E., Yáñez, J., Rodríguez, J.T., Gómez, D., Montero, J.: A novel edge detection algorithm based on a hierarchical graph-partition approach. J. Intell. Fuzzy Syst. 34(3), 1875–1892 (2018, in press)CrossRef Guada, C., Zarrazola, E., Yáñez, J., Rodríguez, J.T., Gómez, D., Montero, J.: A novel edge detection algorithm based on a hierarchical graph-partition approach. J. Intell. Fuzzy Syst. 34(3), 1875–1892 (2018, in press)CrossRef
11.
Zurück zum Zitat Haykin, S.: Neural Networks. A Comprehensive Foundation. Prentice Hall International, Upper Saddle River (1999)MATH Haykin, S.: Neural Networks. A Comprehensive Foundation. Prentice Hall International, Upper Saddle River (1999)MATH
12.
Zurück zum Zitat Lamb, D.W., Brown, R.B.: Remote-sensing and mapping of weeds in crops. Agri. Eng. Res. 78, 117–125 (2001)CrossRef Lamb, D.W., Brown, R.B.: Remote-sensing and mapping of weeds in crops. Agri. Eng. Res. 78, 117–125 (2001)CrossRef
13.
Zurück zum Zitat Moran, M.S., Inoue, Y., Barnes, E.M.: Opportunities and limitations for image-based remote sensing in precision crop management. Remote Sens. Environ. 61, 319–346 (1997)CrossRef Moran, M.S., Inoue, Y., Barnes, E.M.: Opportunities and limitations for image-based remote sensing in precision crop management. Remote Sens. Environ. 61, 319–346 (1997)CrossRef
14.
Zurück zum Zitat Myint, S.W., Gober, P., Brazel, A., Grossman-Clarke, S., Weng, Q.: Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens. Environ. 115, 1145–1161 (2011)CrossRef Myint, S.W., Gober, P., Brazel, A., Grossman-Clarke, S., Weng, Q.: Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens. Environ. 115, 1145–1161 (2011)CrossRef
15.
Zurück zum Zitat Rasmussen, J., Nielsen, J., Garcia-Ruiz, F., Christensen, S., Streibig, J.C.: Potential uses of small unmanned aircraft systems (UAS) in weed research. Weed Res. 53, 242–248 (2013)CrossRef Rasmussen, J., Nielsen, J., Garcia-Ruiz, F., Christensen, S., Streibig, J.C.: Potential uses of small unmanned aircraft systems (UAS) in weed research. Weed Res. 53, 242–248 (2013)CrossRef
16.
Zurück zum Zitat Robertson, L.D., King, D.J.: Comparison of pixel and object based classification in land cover mapping. Int. J. Remote Sens. 32, 1505–1529 (2011)CrossRef Robertson, L.D., King, D.J.: Comparison of pixel and object based classification in land cover mapping. Int. J. Remote Sens. 32, 1505–1529 (2011)CrossRef
17.
Zurück zum Zitat Seelan, S.K., Laguette, S., Casady, G.M., Seielstad, G.A.: Remote sensing applications for precision agriculture: a learning community approach. Remote Sens. Environ. 88, 157–169 (2003)CrossRef Seelan, S.K., Laguette, S., Casady, G.M., Seielstad, G.A.: Remote sensing applications for precision agriculture: a learning community approach. Remote Sens. Environ. 88, 157–169 (2003)CrossRef
18.
Zurück zum Zitat Slaughter, D.C., Giles, D.K., Downey, D.: Autonomous robotic weed control systems: a review. Comput. Electron. Agric. 61, 63–78 (2008)CrossRef Slaughter, D.C., Giles, D.K., Downey, D.: Autonomous robotic weed control systems: a review. Comput. Electron. Agric. 61, 63–78 (2008)CrossRef
19.
Zurück zum Zitat Sørensen, R., Rasmussen, J., Nielsen, J., Jørgensen, R.N.: Thistle detection using convolutional neural networks. In: Proceedings EFITA-WCCA 2017 Conference, Montpellier, France, paper 75, 2–6 July 2017 Sørensen, R., Rasmussen, J., Nielsen, J., Jørgensen, R.N.: Thistle detection using convolutional neural networks. In: Proceedings EFITA-WCCA 2017 Conference, Montpellier, France, paper 75, 2–6 July 2017
20.
Zurück zum Zitat Tellaeche, A., Pajares, G., Burgos-Artizzu, X.P., Ribeiro, A.: A computer vision approach for weeds identification through support vector machines. Appl. Soft Comput. 11, 908–915 (2011)CrossRef Tellaeche, A., Pajares, G., Burgos-Artizzu, X.P., Ribeiro, A.: A computer vision approach for weeds identification through support vector machines. Appl. Soft Comput. 11, 908–915 (2011)CrossRef
21.
Zurück zum Zitat Whiteside, T.G., Boggs, G.S., Maier, S.W.: Comparing object-based and pixel-based classifications for mapping savannas. Appl. Earth Obs. Geoinf. 13, 884–893 (2011)CrossRef Whiteside, T.G., Boggs, G.S., Maier, S.W.: Comparing object-based and pixel-based classifications for mapping savannas. Appl. Earth Obs. Geoinf. 13, 884–893 (2011)CrossRef
Metadaten
Titel
Automatic Detection of Thistle-Weeds in Cereal Crops from Aerial RGB Images
verfasst von
Camilo Franco
Carely Guada
J. Tinguaro Rodríguez
Jon Nielsen
Jesper Rasmussen
Daniel Gómez
Javier Montero
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-91479-4_37