Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 30127
RoboWeedSupport-Sub Millimeter Weed Image Acquisition in Cereal Crops with Speeds up till 50 Km/H

Authors: Morten Stigaard Laursen, Rasmus Nyholm Jørgensen, Mads Dyrmann, Robert Poulsen

Abstract:

For the past three years, the Danish project, RoboWeedSupport, has sought to bridge the gap between the potential herbicide savings using a decision support system and the required weed inspections. In order to automate the weed inspections it is desired to generate a map of the weed species present within the field, to generate the map images must be captured with samples covering the field. This paper investigates the economical cost of performing this data collection based on a camera system mounted on a all-terain vehicle (ATV) able to drive and collect data at up to 50 km/h while still maintaining a image quality sufficient for identifying newly emerged grass weeds. The economical estimates are based on approximately 100 hectares recorded at three different locations in Denmark. With an average image density of 99 images per hectare the ATV had an capacity of 28 ha per hour, which is estimated to cost 6.6 EUR/ha. Alternatively relying on a boom solution for an existing tracktor it was estimated that a cost of 2.4 EUR/ha is obtainable under equal conditions.

Keywords: Weed mapping, integrated weed management, weed recognition.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1130297

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 851

References:


[1] S. Haneklaus, H. Lilienthal, and E. Schnug, “25 years precision agriculture in germany–a retrospective,” in 13th International Conference on Precision Agriculture.
[2] S. Christensen, H. T. Søgaard, P. Kudsk, M. Nørremark, I. Lund, E. S. Nadimi, and R. Jørgensen, “Site-specific weed control technologies,” Weed Res., vol. 49, no. 3, pp. 233–241, 1 Jun. 2009.
[3] R. Gerhards, “Site-Specific weed control,” in Precision in Crop Farming. Springer Netherlands, 2013, pp. 273–294.
[4] C. Gutjahr, M. S¨okefeld, and R. Gerhards, “Evaluation of two patch spraying systems in winter wheat and maize,” Weed Res., vol. 52, no. 6, pp. 510–519, 1 Dec. 2012.
[5] D. L. Shaner and H. J. Beckie, “The future for weed control and technology,” Pest Manag. Sci., vol. 70, no. 9, pp. 1329–1339, Sep. 2014.
[6] R. B. Brown and S. D. Noble, “Site-specific weed management: sensing requirements— what do we need to see?” Weed Sci., vol. 53, no. 2, pp. 252–258, 2005.
[7] M. Weis, C. Gutjahr, V. R. Ayala, R. Gerhards, C. Ritter, and F. Sch¨olderle, “Precision farming for weed management: techniques,” Gesunde Pflanzen, vol. 60, no. 4, pp. 171–181, 2008.
[8] S. Trengove, “Weed mapping,” Developments & Demos, vol. 12, no. 2, pp. 20–22, 2016.
[9] H. Leithold, “Digital farming I using WEED SENSORS for efficient weed control,” 7 Mar. 2016.
[10] “AmaSpot sensor nozzle system,” http://press.lectura.de/en/amaspot-sensor-nozzle-system/22092, accessed: 2015-10-2.
[11] M. Laursen, R. Jørgensen, H. Midtiby, K. Jensen, M. Christiansen, T. Giselsson, A. Mortensen, and P. Jensen, “Dicotyledon weed quantification algorithm for selective herbicide application in maize crops,” Sensors, vol. 16, no. 11, p. 1848, 4 Nov. 2016.
[12] H. S. Midtiby, S. K. Mathiassen, K. J. Andersson, and R. N. Jørgensen, “Performance evaluation of a crop/weed discriminating microsprayer,” Comput. Electron. Agric., vol. 77, no. 1, pp. 35–40, Jun. 2011.
[13] P. Lottes, M. Hoeferlin, S. Sander, M. M¨uter, and others, “An effective classification system for separating sugar beets and weeds for precision farming applications,” Proceedings of the, 2016.
[14] M. Weis and R. Gerhards, “Feature extraction for the identification of weed species in digital images for the purpose of site-specific weed control,” in Precision agriculture’07. Papers presented at the 6th European Conference on Precision Agriculture, Skiathos, Greece, 3-6 June, 2007., 2007, pp. 537–544.
[15] H. T. Søgaard, “Weed classification by active shape models,” Biosystems Eng., vol. 91, no. 3, pp. 271–281, 2005.
[16] M. Dyrmann, R. N. Jørgensen, and H. S. Midtiby, “RoboWeedSupport - detection of weed locations in leaf occluded cereal crops using a fully convolutional neural network,” in ECPA 2017 - 11th European Conference on Precision Agriculture, 2017, submitted.
[17] Y. Zhang, E. S. Staab, D. C. Slaughter, D. K. Giles, and D. Downey, “Automated weed control in organic row crops using hyperspectral species identification and thermal micro-dosing,” Crop Prot., vol. 41, pp. 96–105, Nov. 2012.
[18] P. Rydahl, “A danish decision support system for integrated management of weeds,” Aspect.s of Applied Biology, vol. 72, 2004.
[19] L. N. Jørgensen, E. Noe, A. M. Langvad, J. E. Jensen, and others, “Decision support systems: barriers and farmers’ need for support,” EPPO, 2007.
[20] M. Sønderskov, P. Kudsk, S. K. Mathiassen, O. M. Bøjer, and P. Rydahl, “Decision support system for optimized herbicide dose in spring barley,” Weed Technol., vol. 28, no. 1, pp. 19–27, 2014.
[21] J. M. Montull, M. Soenderskov, P. Rydahl, O. M. Boejer, and A. Taberner, “Four years validation of decision support optimising herbicide dose in cereals under spanish conditions,” Crop Prot., vol. 64, pp. 110–114, Oct. 2014.
[22] M. Sønderskov, R. Fritzsche, F. de Mol, B. Gerowitt, S. Goltermann, R. Kierzek, R. Krawczyk, O. M. Bøjer, and P. Rydahl, “DSSHerbicide: Weed control in winter wheat with a decision support system in three south baltic regions – field experimental results,” Crop Prot., vol. 76, pp. 15–23, Oct. 2015.
[23] T. Been, A. Berti, N. Evans, D. Gouache, V. Gutsche, J. E. Jensen, J. Kapsa, N. Levay, N. Munier-Jolain, S. Nibouche, M. Raynal, and P. Rydahl, “Review of new technologies critical to effective implementation of decision support systems (DSSs) and farm management systems (FMSs),” Aarhus University, Tech. Rep., 6 Mar. 2009.
[24] P. Rydahl, N.-P. Jensen, M. Dyrmann, P. H. Nielsen, and R. N. Jørgensen, “RoboWeedSupport - presentation of a cloud based system bridging the gap between in-field weed inspections and decision support systems,” in ECPA 2017 - 11th European Conference on Precision Agriculture, 2017, submitted.
[25] S. L. Madsen, M. S. Laursen, R. N. Poulsen, and R. N. Jørgensen, “RoboWeedSupport - semi-automated UAS system for cost efficient high resolution i sub millimeter scale acquisition of weed images,” in ECPA 2017 - 11th European Conference on Precision Agriculture, 2017, submitted.
[26] R. N. Jørgensen, M. S. Laursen, M. Dymann, and R. N. Poulsen, “RoboWeedSupport - weed mapping with drones using a DJI phantom 4,” Denmark, 11 Oct. 2016.