Publicação
Assessing berry number for grapevine yield estimation by image analysis: case study with the white variety “Arinto”
| Resumo: | Yield estimation in recent years is identified as one of more important topics in viticulture because it can lead to more efficiently managed vineyards producing wines of highly quality. Recently, to improve the efficiency of yield estimation, image analysis is becoming an important tool to collect detailed information from the vines regarding the yield. New technologies were developed for yield estimation using a new ground platform, such as VINBOT, using image analysis. This work was done in a vineyard of the “Instituto Superior de Agronomia”, with the aim to estimate the final yield, during the growing cycle 2019 of the variety “Arinto”, using images collected in three different modality: laboratory condition (1), field condition (2) and VINBOT robot. In the every condition, the images were captured with the RGB-D camera. For (1) and (2) the photos were acquired manually through the use of a digital camera placed on a tripod but in the (3) the RGB-D camera was fixed on the VINBOT robot. In this work, the correlation of yield components between field data and images data was evaluated. In addition, throught MATLAB, it was evaluate the number of visible berries in the images and the percentage of visible berries not occluded by leaves and by other berries. Througt the laboratory results was calculate a growth factor of bunches on the periods pea-size and veraison. On the VINBOT analysis the efficacy to estimate the total yield from the number of berries was higher at maturation with a 10% error ratio. The relationship between canopy porosity and exposed berries showed for all the stages high and significant R2 indicating that we can use it to estimate berries occlusion through image analysis. This accuracy makes the proposed methodology ideal for early yield prediction as a very helpful tool for the grape and wine industry |
|---|---|
| Autores principais: | Genuardi, Sergio |
| Assunto: | algorithms image analysis MATLAB yield estimation VINBOT |
| Ano: | 2021 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório da Universidade de Lisboa |
| Resumo: | Yield estimation in recent years is identified as one of more important topics in viticulture because it can lead to more efficiently managed vineyards producing wines of highly quality. Recently, to improve the efficiency of yield estimation, image analysis is becoming an important tool to collect detailed information from the vines regarding the yield. New technologies were developed for yield estimation using a new ground platform, such as VINBOT, using image analysis. This work was done in a vineyard of the “Instituto Superior de Agronomia”, with the aim to estimate the final yield, during the growing cycle 2019 of the variety “Arinto”, using images collected in three different modality: laboratory condition (1), field condition (2) and VINBOT robot. In the every condition, the images were captured with the RGB-D camera. For (1) and (2) the photos were acquired manually through the use of a digital camera placed on a tripod but in the (3) the RGB-D camera was fixed on the VINBOT robot. In this work, the correlation of yield components between field data and images data was evaluated. In addition, throught MATLAB, it was evaluate the number of visible berries in the images and the percentage of visible berries not occluded by leaves and by other berries. Througt the laboratory results was calculate a growth factor of bunches on the periods pea-size and veraison. On the VINBOT analysis the efficacy to estimate the total yield from the number of berries was higher at maturation with a 10% error ratio. The relationship between canopy porosity and exposed berries showed for all the stages high and significant R2 indicating that we can use it to estimate berries occlusion through image analysis. This accuracy makes the proposed methodology ideal for early yield prediction as a very helpful tool for the grape and wine industry |
|---|