|Reference : Texture, Color and Frequential Proxy-Detection Image Processing for Crop Characteriza...|
|Parts of books : Contribution to collective works|
|Life sciences : Agriculture & agronomy|
Engineering, computing & technology : Multidisciplinary, general & others
|Texture, Color and Frequential Proxy-Detection Image Processing for Crop Characterization in a Context of Precision Agriculture|
|Cointault, Frédéric [AgroSup Dijon > > > >]|
|Journaux, Ludovic [AgroSup Dijon > > > >]|
|Rabatel, Gilles [Irstea Montpellier > > > >]|
|Germain, Christian [Bordeaux University > > > >]|
|Ooms, David [Université de Liège - ULg > > > >]|
|Destain, Marie-France [Université de Liège - ULg > Sciences et technologie de l'environnement > Mécanique et construction >]|
|Gorretta, Nathalie [Irstea Montpellier > > > >]|
|Grenier, Gilbert [Bordeaux University > > > >]|
|Lavialle, Olivier [Bordeaux University > > > >]|
|Marin, Ambroise [AgroSup Dijon > > > >]|
|[en] Image processing ; precision agriculture|
|[en] 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.
<br />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.
|Researchers ; Professionals ; Students|
|File(s) associated to this reference|
All documents in ORBi are protected by a user license.