Author:
Ferreira Abreu Fernando,Antunes Rodrigues Luiz Henrique
Abstract
Yield is the most often used metric of crop performance, and it can be defined as the ratio between production, expressed as a function of mass or volume, and the cultivated area. Estimating fruit’s volume often relies on manual measurements, and the procedure precision can change from one person to another. Measuring fruits’ mass will also destroy the samples; consequently, the variation will be measured with different samples. Monitoring fruit’s growth is either based on destructive tests, limited by human labour, or too expensive to be scaled. In this work, we showed that the cluster visible area could be used to describe the growth of mini tomatoes in a greenhouse using image processing in a natural environment with a complex background. The proposed method is based on deep learning algorithms and allows continuous monitoring with no contact with the cluster. The images are collected and delivered from the greenhouse using low-cost equipment with minimal parameterisation. Our results demonstrate that the cluster visible area accumulation is highly correlated (R²=0.97) with growth described by a parameterised Gompertz curve, which is a well-known growth function. This work may also be a starting point for alternative growth monitoring methods based on image segmentation. The proposed U-Net architecture, the discussion about its architecture, and the challenges of the natural environment may be used for other tasks in the agricultural context.
Subject
Industrial and Manufacturing Engineering,Mechanical Engineering,Bioengineering
Reference36 articles.
1. Abreu F.F., Rodrigues L.H.A. 2022. MTIL - Mini tomato image library. Repositório de Dados de Pesquisa da Unicamp. Available from: https://doi.org/10.25824/redu/3CP9NK
2. Afonso M., Fonteijn H., Fiorentin F.S., Lensink D., Mooij M., Faber N., Polder G., Wehrens R. 2020. Tomato fruit detection and counting in greenhouses using deep learning. Front. Plant Sci. 11:571299.
3. Agrawal A., Mittal N. 2020. Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy. Visual Comput. 36:405-12.
4. Ali M., Gilani S.O., Waris A., Zafar K., Jamil M. 2020. Brain tumour image segmentation using deep networks. IEEE Access 8:153589-98.
5. Bragagnolo L., Da Silva R.V., Grzybowski J.M.V. 2021. Amazon forest cover change mapping based on semantic segmentation by U-Nets. Ecol. Inf. 62:101279.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献