Deep mango cultivars: Cultivar detection by classification method with maximum misidentification rate estimation

Borianne Philippe, Sarron Julien, Borne Frédéric, Faye Emile. 2023. Deep mango cultivars: Cultivar detection by classification method with maximum misidentification rate estimation. Precision Agriculture, 24 : 1619-1637.

https://doi.org/10.1007/s11119-023-10012-0

Article de revue ; Article de recherche ; Article de revue à facteur d'impact

	Version Online first - Anglais Accès réservé aux personnels Cirad Utilisation soumise à autorisation de l'auteur ou du Cirad. Borianne et al. - 2023 - Deep mango cultivars cultivar detection by classi.pdf Télécharger (1MB) \| Demander une copie
	Version publiée - Anglais Accès réservé aux personnels Cirad Utilisation soumise à autorisation de l'auteur ou du Cirad. 604384.pdf Télécharger (1MB) \| Demander une copie

Résumé : Deep learning techniques and computer vision systems offer effective fruit counting solutions for farm yield estimation. However, the performance of these solutions drops when identifying different cultivars of the same fruit species. This study clarified the differences between mango fruit detection and mango cultivar identification. An original double-threshold-based classification method for fruit cultivar identification, with estimation of the misidentification rate was proposed in order to significantly increase the performance of a specialised mango fruit detection method known as Faster R-CNN. This method was applied on images of mango trees of three cultivars taken in Senegalese orchards of different existing cropping systems, with varying tree features, planting patterns and acquisition contexts. Analysis of the results focused on the contributions of fruit detection errors and fruit cultivar confusion to the overall error of the network for fruit counts by cultivar class. The shift from fruit detection to cultivar identification resulted in a drop in the average prediction rate from 92 to 68%. With its explicitly independent fruit detection and cultivar identification steps, the double-threshold-based classification method increased the prediction rate to 86%, with a maximum identification error of 0.05%. This setting also led to relative equality between the recall and the precision of each cultivar class, making the network well suited for fruit counting by cultivar class. This work opened new perspectives for decision support tools for fruit growers that could provide more appropriate yield estimates per cultivar.

Mots-clés Agrovoc : variété, Mangifera indica, identification, sélection de cultivars

Mots-clés géographiques Agrovoc : Sénégal

Mots-clés libres : Faster R-CNN, Fruit detection, Cultivar identification, Neural Network, Africa

Classification Agris : F01 - Culture des plantes
F50 - Anatomie et morphologie des plantes
U10 - Informatique, mathématiques et statistiques

Champ stratégique Cirad : CTS 2 (2019-) - Transitions agroécologiques

Agences de financement hors UE : Agence Nationale de la Recherche, Région Occitanie Pyrénées-Méditerranée

Projets sur financement : (FRA) Institut Convergences en Agriculture Numérique, (FRA) PixFruit project

Auteurs et affiliations