Koirala, A.; Walsh, K.B.; Wang, Z. Attempting to Estimate the Unseen—Correction for Occluded Fruit in Tree Fruit Load Estimation by Machine Vision with Deep Learning. Agronomy2021, 11, 347.
Koirala, A.; Walsh, K.B.; Wang, Z. Attempting to Estimate the Unseen—Correction for Occluded Fruit in Tree Fruit Load Estimation by Machine Vision with Deep Learning. Agronomy 2021, 11, 347.
Koirala, A.; Walsh, K.B.; Wang, Z. Attempting to Estimate the Unseen—Correction for Occluded Fruit in Tree Fruit Load Estimation by Machine Vision with Deep Learning. Agronomy2021, 11, 347.
Koirala, A.; Walsh, K.B.; Wang, Z. Attempting to Estimate the Unseen—Correction for Occluded Fruit in Tree Fruit Load Estimation by Machine Vision with Deep Learning. Agronomy 2021, 11, 347.
Abstract
Imaging systems mounted to ground vehicles are used to image fruit tree canopies for estimation of fruit load, but frequently need correction for fruit occluded by branches, foliage or other fruits. This can be achieved using an orchard ‘occlusion factor’, estimated from a manual count of fruit load on a sample of trees (referred to as the reference method). It was hypothesised that canopy images could hold information related to the number of occluded fruit. Five approaches to correct for occluded fruit based on canopy images were compared using data of three mango orchards in two seasons. However, no attribute correlates to the number of hidden fruit were identified. Several image features obtained through segmentation of fruit and canopy areas, such as the proportion of fruit that were partly occluded, were used in training Random forest and multi-layered perceptron (MLP) models for estimation of a correction factor per tree. In another approach, deep learning convolutional neural networks (CNNs) were directly trained against harvest fruit count on trees. The supervised machine learning methods for direct estimation of fruit load per tree delivered an improved prediction outcome over the reference method for data of the season/orchard from which training data was acquired. For a set of 2017 season tree images (n=98 trees), a R2 of 0.98 was achieved for the correlation of the number of fruits predicted by a Random forest model and the ground truth fruit count on the trees, compared to a R2 of 0.68 for the reference method. The best prediction of whole orchard (n = 880 trees) fruit load, in the season of the training data, was achieved by the MLP model, with an error to packhouse count of 1.6% compared to the reference method error of 13.6%. However, the performance of these models on new season data (test set images) was at best equivalent and generally poorer than the reference method. This result indicates that training on one season of data was insufficient for the development of a robust model. This outcome was attributed to variability in tree architecture and foliage density between seasons and between orchards, such that the characters of the canopy visible from the interrow that relate to the proportion of hidden fruit are not consistent. Training of these models across several seasons and orchards is recommended.
Keywords
fruit occlusion; deep learning; machine vision; yield estimation; fruit count; neural network; CNN; tree crop; Mangifera indica; MLP; canopy
Subject
Computer Science and Mathematics, Algebra and Number Theory
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
