On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model

المؤلفون المشاركون

Millan, Borja
Velasco-Forero, Santiago
Aquino, Arturo
Tardaguila, Javier

المصدر

Journal of Sensors

العدد

المجلد 2018، العدد 2018 (31 ديسمبر/كانون الأول 2018)، ص ص. 1-14، 14ص.

الناشر

Hindawi Publishing Corporation

تاريخ النشر

2018-12-16

دولة النشر

مصر

عدد الصفحات

14

التخصصات الرئيسية

هندسة مدنية

الملخص EN

This paper describes a new methodology for noninvasive, objective, and automated assessment of yield in vineyards using image analysis and Boolean model.

Image analysis, as an inexpensive and noninvasive procedure, has been studied for this purpose, but the effect of occlusions from the cluster or other organs of the vine has an impact that diminishes the quality of the results.

To reduce the influence of the occlusions in the estimation, the number of berries was assessed using the Boolean model.

To evaluate the methodology, three different datasets were studied: cluster images, manually acquired vine images, and vine images captured on-the-go using a quad.

The proposed algorithm estimated the number of berries in cluster images with a root mean square error (RMSE) of 20 and a coefficient of determination (R2) of 0.80.

Vine images manually taken were evaluated, providing 310 grams of mean error and R2=0.81.

Finally, images captured using a quad equipped with artificial light and automatic camera triggering were also analysed.

The estimation obtained applying the Boolean model had 610 grams of mean error per segment (three vines) and R2=0.78.

The reliability against occlusions and segmentation errors of the Boolean model makes it ideal for vineyard yield estimation.

Its application greatly improved the results when compared to a simpler estimator based on the relationship between cluster area and weight.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

Millan, Borja& Velasco-Forero, Santiago& Aquino, Arturo& Tardaguila, Javier. 2018. On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model. Journal of Sensors،Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1202304

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

Millan, Borja…[et al.]. On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model. Journal of Sensors No. 2018 (2018), pp.1-14.
https://search.emarefa.net/detail/BIM-1202304

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

Millan, Borja& Velasco-Forero, Santiago& Aquino, Arturo& Tardaguila, Javier. On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model. Journal of Sensors. 2018. Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1202304

نوع البيانات

مقالات

لغة النص

الإنجليزية

الملاحظات

Includes bibliographical references

رقم السجل

BIM-1202304