Machine vision for precise control of weeds

Consumers demand for natural quality products and concern about the ecological impact of agriculture is growing in all European countries. For the farmers to follow the evolution of the market, new procedures have to be introduced in agriculture to obtain satisfactory production levels, keeping high...

Descripción completa

Detalles Bibliográficos
Autores principales: Blasco, José, Benlloch, J. V., Agustí, Manuel, Moltó, Enrique
Otros Autores: Meyer, GE DeShazer, JA
Formato: Artículo
Lenguaje:Inglés
Publicado: 2017
Acceso en línea:http://hdl.handle.net/20.500.11939/4861
_version_ 1855491826114363392
author Blasco, José
Benlloch, J. V.
Agustí, Manuel
Moltó, Enrique
author2 Meyer, GE DeShazer, JA
author_browse Agustí, Manuel
Benlloch, J. V.
Blasco, José
Meyer, GE DeShazer, JA
Moltó, Enrique
author_facet Meyer, GE DeShazer, JA
Blasco, José
Benlloch, J. V.
Agustí, Manuel
Moltó, Enrique
author_sort Blasco, José
collection ReDivia
description Consumers demand for natural quality products and concern about the ecological impact of agriculture is growing in all European countries. For the farmers to follow the evolution of the market, new procedures have to be introduced in agriculture to obtain satisfactory production levels, keeping high quality standards, without damaging the environment. Image processing techniques have been traditionally used in the industry, where controlling most of the environmental variables (mainly lighting, background and speed) uses to be easy. Although these techniques can be also useful in agriculture, working outdoors is much more complicated, mainly due to the variability of the natural objects and the environmental conditions. European Project AIR-CT93-1299 (PATCHWORK) was aimed at reducing or eliminating the use of chemicals by automatically detecting the position and/or density of weeds using computer vision and applying an herbicide treatment, which could be chemical or mechanical. This paper describes the work carried out in developing image. analysis procedures for two different purposes: In horticultural, row crops, the aim was to develop a real-time machine vision system that provides the position of weeds to a moving robot that will apply an electric discharge to them, thus eliminating the use of herbicides. - In cereals, the objective was to create weed density maps that will help an especial sprayer boom, incorporating a GPS sensor, to dose the herbicide at 4 concentrations, corresponding to 4 infestation levels during operation. The first system is based on a Bayesian algorithm for segmenting the images, which requires to be previously trained by an expert, who selects areas of different images, trying to represent the colour variability of the plants, the soil and the weeds. After segmentation, pixels belonging to class soil are correctly classified and morphological operations are applied to discriminate between plants and weeds. The system is able to properly locate more than 90% of weeds with very little confusion with the crop (1 %) in lettuce cultures. Current processing time is under 500 ms. The second vision system uses a normalised difference index (green and red channels) to enhance the contrast of the field images. Then, growing techniques are applied to discriminate between vegetation and background. Once plant pixels are identified, weeds are distinguished from the crop by estimating the position of the row and employing shape analysis techniques. The performance of the method showed that more than 85% of weeds were properly detected.
format Artículo
id ReDivia4861
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2017
publishDateRange 2017
publishDateSort 2017
record_format dspace
spelling ReDivia48612025-04-25T14:53:45Z Machine vision for precise control of weeds PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE) Blasco, José Benlloch, J. V. Agustí, Manuel Moltó, Enrique Meyer, GE DeShazer, JA Consumers demand for natural quality products and concern about the ecological impact of agriculture is growing in all European countries. For the farmers to follow the evolution of the market, new procedures have to be introduced in agriculture to obtain satisfactory production levels, keeping high quality standards, without damaging the environment. Image processing techniques have been traditionally used in the industry, where controlling most of the environmental variables (mainly lighting, background and speed) uses to be easy. Although these techniques can be also useful in agriculture, working outdoors is much more complicated, mainly due to the variability of the natural objects and the environmental conditions. European Project AIR-CT93-1299 (PATCHWORK) was aimed at reducing or eliminating the use of chemicals by automatically detecting the position and/or density of weeds using computer vision and applying an herbicide treatment, which could be chemical or mechanical. This paper describes the work carried out in developing image. analysis procedures for two different purposes: In horticultural, row crops, the aim was to develop a real-time machine vision system that provides the position of weeds to a moving robot that will apply an electric discharge to them, thus eliminating the use of herbicides. - In cereals, the objective was to create weed density maps that will help an especial sprayer boom, incorporating a GPS sensor, to dose the herbicide at 4 concentrations, corresponding to 4 infestation levels during operation. The first system is based on a Bayesian algorithm for segmenting the images, which requires to be previously trained by an expert, who selects areas of different images, trying to represent the colour variability of the plants, the soil and the weeds. After segmentation, pixels belonging to class soil are correctly classified and morphological operations are applied to discriminate between plants and weeds. The system is able to properly locate more than 90% of weeds with very little confusion with the crop (1 %) in lettuce cultures. Current processing time is under 500 ms. The second vision system uses a normalised difference index (green and red channels) to enhance the contrast of the field images. Then, growing techniques are applied to discriminate between vegetation and background. Once plant pixels are identified, weeds are distinguished from the crop by estimating the position of the row and employing shape analysis techniques. The performance of the method showed that more than 85% of weeds were properly detected. 2017-06-01T10:11:12Z 2017-06-01T10:11:12Z 1999 1999 article Blasco, J., Benlloch, J.V., Agusti, M., Molto, E. (1999). Machine vision for precise control of weeds. Precision Agriculture and Biological Quality, 3543, 336-343. 0277-786X; 0-8194-3155-9 http://hdl.handle.net/20.500.11939/4861 10.1117/12.336897 en openAccess Impreso
spellingShingle Blasco, José
Benlloch, J. V.
Agustí, Manuel
Moltó, Enrique
Machine vision for precise control of weeds
title Machine vision for precise control of weeds
title_full Machine vision for precise control of weeds
title_fullStr Machine vision for precise control of weeds
title_full_unstemmed Machine vision for precise control of weeds
title_short Machine vision for precise control of weeds
title_sort machine vision for precise control of weeds
url http://hdl.handle.net/20.500.11939/4861
work_keys_str_mv AT blascojose machinevisionforprecisecontrolofweeds
AT benllochjv machinevisionforprecisecontrolofweeds
AT agustimanuel machinevisionforprecisecontrolofweeds
AT moltoenrique machinevisionforprecisecontrolofweeds
AT blascojose proceedingsofthesocietyofphotoopticalinstrumentationengineersspie
AT benllochjv proceedingsofthesocietyofphotoopticalinstrumentationengineersspie
AT agustimanuel proceedingsofthesocietyofphotoopticalinstrumentationengineersspie
AT moltoenrique proceedingsofthesocietyofphotoopticalinstrumentationengineersspie