**1. Introduction**

48 Agricultural Science

Wassmann, R., Neue, H.U., Ladha, J.K., & Aulakh, M.S. (2004). Mitigating greenhouse gas

Wheaton, H.N. & Roberts, C.A. (1993). Renovating grass sods with legumes. *Univ. of* 

Weaver, J.E. & Noll, W. (1935). Measurement of run-off and soil erosion by a single

West, T.O., & Post, W.M. (2002). Soil organic carbon sequestration rates by tillage and crop rotation; a global data analysis. *Soil Sci. Soc. Amer. J*. Vol. 66:1930-1946. West, J.M. (2004). King cotton: The fiber of slavery. *Slavery in America.* URL:

Wilhelm, W.W., Johnson, J.M.F., Karlen, D.L., & Lightle, D.T. (2007). Corn stover to sustain soil organic carbon further constrains biomass supply. *Agron. J.* Vol. 99:1665-1667. Woodruff, J.M., Durham, R.G. & Hancock, D.W. (2010). Forage establishment guidelines. *Univ. of Georgia College of Agriculture & Environmental Sciences.* URL:

Young, D.L., Hinman, H.R., & Schillinger, W. F. (2000). Economics of winter wheat-summer

http://www.caes.uga.edu/commodities/fieldcrops/forages/establishment.html#

fallow vs. continuous no-till spring wheat in the Horse Heaven Hills, Washington. Farm business management reports. EB1907. *Cooperative Extension Service*,

*Missouri Ext. G4651*. University of Missouri. Columbia, MO.

http://www.slaveryinamerica.org/history/hs\_es\_cotton.htm .

investigator. *Ecol.* Vol. 16:1-12.

Washington State University. Pullman, WA.

90.

pasture.

emissions from rice-wheat cropping systems in Asia. *Environ. Devel. Sust.* Vol. 6:65-

The concept of precision agriculture consists to spatially manage crop management practices according to in-field variability. This concept is principally dedicated to variable-rate application of inputs such as nitrogen, seeds and phytosanitary products, allowing for a better yield management and reduction on the use of pesticides, herbicides … In this general context, the development of ICT techniques has allowed relevant progresses for Leaf Area Index (LAI) (Richardson et al., 2009), crop density (Saeys et al., 2009), stress (Zygielbaum et al., 2009) … Most of the tools used for Precision Farming utilizes optical and/or imaging sensors and dedicated treatments, in real time or not, and eventually combined to 3D plant growth modeling or disease development (Fournier et al., 2003 ; Robert et al., 2008). To evaluate yields or to better define the appropriated periods for the spraying or fertilizer input, to detect crop, weeds, diseases …, the remote sensing imaging devices are often used to complete or replace embedded sensors onboard the agricultural machinery (Aparicio et al., 2000). Even if these tools provide sufficient accurate information, they get some drawbacks compared to "proxy-detection" optical sensors: resolution, easy-to-use tools, accessibility, cost, temporality, precision of the measurement … The use of specific image acquisition systems coupled to reliable image processing should allow for a reduction of working time, a lower work hardness and a reduction of the bias of the measurement according to the operator, or a better spatial sampling due to the rapidity of the image acquisition (instead of the use of remote sensing). The early evaluation of yield could allow farmers, for example, to adjust cultivation practices (e.g., last nitrogen (N) input), to organize harvest and storage logistics. The optimization of late N application could lead to significant improvements for the environment, one of the most important concerns that precision agriculture aims to address.

<sup>\*</sup> Journaux Ludovic1, Rabatel Gilles2, Germain Christian3, Ooms David4, Destain Marie-France4,

Gorretta Nathalie2, Grenier Gilbert3, Lavialle Olivier3 and Marin Ambroise1

*<sup>1</sup>AgroSup Dijon, France* 

*<sup>2</sup>Irstea Montpellier, France* 

*<sup>3</sup>IMS – Bordeaux University - Bordeaux Sciences Agro, France 4ULg (Gembloux Agro-BioTech), Belgium* 

Texture, Color and Frequential Proxy-Detection

vegetation (figure 3).

Fig. 3. Hyperspectral acquisition device

the blue light reflected by the object.

Avantes, Eerbeek, The Netherlands).

Image Processing for Crop Characterization in a Context of Precision Agriculture 51

Fig. 2. Example of image acquisition system (left) and its specific illumination by Led (right)

Proxy-Hyperspectral images can also be used and are obtained with specific sensors. As an illustration, images of wheat crop have been acquired in march 2011 on the domain of Melgueil (INRA, 34-France) by means of dedicated apparatus developed by the Cemagref. This device is constituted by a motorized rod installed on a tractor which allows a longitudinal displacement of a push-broom hyperspectral camera located 1 meter above the

Other imaging system is based on chlorophyll fluorescence. A xenon light source (Hamamatsu Lightingcure L8222, model LC5, 150 W) is used to produce a white light which passes through an interference filter (03FIB002, Melles Griot, Carlsbad, USA) with a central wavelength 410 nm and width at half-maximum 80 nm to excite the chlorophyll-a. The light is conducted to the seeds by an optical fiber. The blue light issued from the filter is absorbed by the seeds chlorophylls, which resulted in fluorescence emission. A high-pass filter (665 nm, 03FCG107, Melles Griot 03FCG107) ensured the selection of the fluorescent signal from

The images are acquired by a CCD monochrome camera (Hamamatsu C5405-70), with a resolution of 640 x 480 pixels and 256 gray levels. The system is enclosed within a black box to avoid interference from ambient light and is air-conditioned (Tectro TS27, PVG Int. B.V., Oss, The Netherlands) to maintain a temperature of 20°C. The lamp is optically isolated and white light did not escape inside the box. The blue filter transmitted an unexpected, small amount of infrared light between 770 and 900 nm (detected with spectrometer AVS-SD2000,

We propose in this chapter to explore the proxy-detection domain by focusing first on the development of robust image acquisition systems, and secondly on the use of image processing for different applications tied on one hand to wheat crop characterization, such as *the detection and counting of wheat ears per m² (in a context of yield prediction) and the weed detection*, and on the other hand to the evolution of seed development/germination performance of chicory achenes. Results of the different processing are presented in the last part just before a conclusion.
