Image-based size estimation of broccoli heads under varying degrees of occlusion

Abstract

The growth and the harvestability of a broccoli crop is monitored by the size of the broccoli head. This size estimation is currently done by humans, and this is inconsistent and expensive. The goal of our work was to develop a software algorithm that can estimate the size of field-grown broccoli heads based on RGB-Depth (RGB-D) images. For the algorithm to be successful, the problem of occlusion must be solved, which is the partial visibility of the broccoli head due to overlapping leaves. This partial visibility causes sizing errors. In this research, we studied the use of deep-learning algorithms to deal with occlusions. We specifically applied the Occlusion Region-based Convolutional Neural Network (ORCNN) that segmented both the visible and the amodal region of the broccoli head (which is the visible and the occluded region combined). We hypothesised that ORCNN, with its amodal segmentation, can improve the size estimation of occluded broccoli heads. The ORCNN sizing method was compared with a Mask R–CNN sizing method that only used the visible broccoli region to estimate the size. The sizing performance of both methods was evaluated on a test set of 487 broccoli images with systematic levels of leaf occlusion. With a mean sizing error of 6.4 mm, ORCNN outperformed Mask R–CNN, which had a mean sizing error of 10.7 mm. Furthermore, ORCNN had a significantly lower absolute sizing error on 161 heavily occluded broccoli heads with an occlusion rate between 50% and 90%. Our software and data set are available on https://git.wur.nl/blok012/sizecnn.

Plant phenotyping relevance

RGB-D画像と深層学習によりブロッコリー頭部サイズを推定する手法を開発し、Mask R-CNNと比較検証しているため、植物形質取得法が研究の中心です。

Code and data availability

The authors explicitly release their broccoli sizing software, RGB-D image dataset with occlusion annotations, and trained ORCNN/Mask R-CNN models via their public WUR GitLab repository (sizecnn). This is a paper-specific, publicly actionable asset directly reproducing the paper's phenotyping measurements and analysis.