e, which goes from 14 14 (default pooling resolution) to 28 28. After the deconvolution, the data is flattened and fed to a linear layer that predicts the diameter for that mask. The developed network was implemented in the Pytorch framework and the code has been made publicly available jointly with the presented dataset at http://www.grap.udl.cat/en/publications/papple_rgb-d-size-dataset/.2.2.3. Network training and inference details a) Weight initialisation: Mask ReCNN has a set of weight initialisations pre-trained with different backbones on ImageNet (Deng et al., 2009). In our case, the used weights were pre-trained with a ResNet50 backbone. However, during the course of this projec
Open resource ↗pdf-raw-page:6 lines:1-143Unverified paper record
Simultaneous fruit detection and size estimation using multitask deep neural networks
Biosystems engineering. · 1 Sept 2023 · 10.1016/j.biosystemseng.2023.07.010
Abstract
The measurement of fruit size is of great interest to estimate the yield and predict the harvest resources in advance. This work proposes a novel technique for in-field apple detection and measurement based on Deep Neural Networks. The proposed framework was trained with RGB-D data and consists of an end-to-end multitask Deep Neural Network architecture specifically designed to perform the following tasks: 1) detection and segmentation of each fruit from its surroundings; 2) estimation of the diameter of each detected fruit. The methodology was tested with a total of 15,335 annotated apples at different growth stages, with diameters varying from 27 mm to 95 mm. Fruit detection results reported an F1-score for apple detection of 0.88 and a mean absolute error of diameter estimation of 5.64 mm. These are state-of-the-art results with the additional advantages of: a) using an end-to-end multitask trainable network; b) an efficient and fast inference speed; and c) being based on RGB-D data which can be acquired with affordable depth cameras. On the contrary, the main disadvantage is the need of annotating a large amount of data with fruit masks and diameter ground truth to train the model. Finally, a fruit visibility analysis showed an improvement in the prediction when limiting the measurement to apples above 65% of visibility (mean absolute error of 5.09 mm). This suggests that future works should develop a method for automatically identifying the most visible apples and discard the prediction of highly occluded fruits.
Plant phenotyping relevance
RGB-D画像と深層学習を用いて果実の検出・セグメンテーションおよび直径推定法を開発し、アノテーションデータで性能評価しているため、果実形質の取得手法が中心である。
abstractThis work proposes a novel technique for in-field apple detection and measurement based on Deep Neural Networks.
abstract1) detection and segmentation of each fruit from its surroundings; 2) estimation of the diameter of each detected fruit.
abstractFruit detection results reported an F1-score for apple detection of 0.88 and a mean absolute error of diameter estimation of 5.64 mm.
Code and data availability
The authors explicitly state that the code for their multitask Mask R-CNN diameter-regression network was made publicly available together with the annotated RGB-D apple dataset (masks, diameter ground truth, spherical mask projections) at the GRAP-UdL publication page. This is a paper-specific, public, actionable code
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.