Image-based size estimation of broccoli heads under varying degrees of occlusion
| Autor: | P.M. Blok, Gert Kootstra, Frits K. van Evert, Eldert J. van Henten |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Data set
Soil Science Farm Technology Deep-learning 01 natural sciences Convolutional neural network Software Occlusion Computer vision Segmentation Visibility Agro Field Technology Innovations Applied Ecology Mathematics business.industry Size estimation 010401 analytical chemistry Toegepaste Ecologie Agriculture 04 agricultural and veterinary sciences PE&RC Sizing 0104 chemical sciences Control and Systems Engineering Test set 040103 agronomy & agriculture 0401 agriculture forestry and fisheries Agrarische Bedrijfstechnologie Artificial intelligence business Agronomy and Crop Science Food Science |
| Zdroj: | Biosystems Engineering, 208, 213-233 Biosystems Engineering 208 (2021) |
| ISSN: | 1537-5110 |
| DOI: | 10.1016/j.biosystemseng.2021.06.001 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect