Deep learning for white cabbage seedling prediction

Perugachi-Diaz, Yura; Tomczak, Jakub M.; Bhulai, Sandjai

doi:10.1016/j.compag.2021.106059

Cited by 23 publications

(15 citation statements)

References 33 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the reviewed accounts, plants and their corresponding growth stages can be categorized into four groups. The first is the seedling during vegetative growth (e.g., Arabidopsis [75], red clover, Alfalfa [73], white cabbage [77], lettuce [78][79][80], etc. ), which represents the majority.…”

Section: Generic Deep Learning Framework For Plant Growth Monitoringmentioning

confidence: 99%

Deep Learning for Image-Based Plant Growth Monitoring: A Review

Tong

Lee²,

Yen

2022

Int. j. eng. technol. innov.

View full text Add to dashboard Cite

Deep learning (DL) approaches have received extensive attention in plant growth monitoring due to their ground-breaking performance in image classification; however, the approaches have yet to be fully explored. This review article, therefore, aims to provide a comprehensive overview of the work and the DL developments accomplished over the years. This work includes a brief introduction on plant growth monitoring and the image-based techniques used for phenotyping. The bottleneck in image analysis is discussed and the need of DL methods in plant growth monitoring is highlighted. A number of research works focused on DL based plant growth monitoring-related applications published since 2017 have been identified and included in this work for review. The results show that the advancement in DL approaches has driven plant growth monitoring towards more complicated schemes, from simple growth stages identification towards temporal growth information extraction. The challenges, such as resource-demanding data annotation, data-hungriness for training, and extraction of both spatial and temporal features simultaneously for accurate plant growth prediction, however, remain unsolved.

show abstract

Section: Generic Deep Learning Framework For Plant Growth Monitoringmentioning

confidence: 99%

Deep Learning for Image-Based Plant Growth Monitoring: A Review

Tong

Lee²,

Yen

2022

Int. j. eng. technol. innov.

View full text Add to dashboard Cite

show abstract

“…The same Lipschitz constraint can also be applied to other networks [11]. In these architectures the multi-scale architecture used in RealNVPs [3] is not leveraged, and so no information is discarded by the model.…”

Section: Related Workmentioning

confidence: 99%

“…Advances in other areas of machine learning cannot be utilized as flow architectures because they are not typically seen as being invertible; this restricts the application of highly optimized architectures from many domains to density estimation, and the use of the likelihood for diagnosing these architectures. Methods using standard convolutions and residual layers for density estimation have been developed for architectures with specific properties [9][10][11][12]. These methods do not provide a recipe for converting general architectures into flows.…”

Section: Introductionmentioning

confidence: 99%

Flowification: Everything is a Normalizing Flow

Máté¹,

Klein²,

Golling³

et al. 2022

Preprint

View full text Add to dashboard Cite

We develop a method that can be used to turn any multi-layer perceptron or convolutional network into a normalizing flow. In some cases this requires the addition of uncorrelated noise to the model but in the simplest case no additional parameters. The technique we develop can be applied to a broad range of architectures, allowing them to be used for a wide range of tasks. Our models also allow existing density estimation techniques to be combined with high performance feature extractors. In contrast to standard density estimation techniques that require specific architectures and specialized knowledge, our approach can leverage design knowledge from other domains and is a step closer to the realization of general purpose architectures. We investigate the efficacy of linear and convolutional layers for the task of density estimation on standard datasets. Our results suggest standard layers lack something fundamental in comparison to other normalizing flows. * Equal contribution.Preprint. Under review.

show abstract

“…Yang et al [14] established a tomato growth model that can reflect the dynamic feedback results of the parameters from fruit setting to development and achieved quantitative results on tomato growth, but lacked accurate results. For the prediction of cabbage growth, Yura et al [15] proposed an image classification method for cabbage seedlings based on convolutional neural networks. By training the model to predict the probability of successful seedling growth, on the test set, AlexNet could accurately classify 94% of the seedlings, but it ignores seedlings with time, as the growth conditions changed.…”

Section: Introductionmentioning

confidence: 99%

A Prediction Method of Seedling Transplanting Time with DCNN-LSTM Based on the Attention Mechanism

Zhu

Liu

2022

Agronomy

View full text Add to dashboard Cite

To improve the production efficiency and reduce the labor cost of seedling operations, cabbage was selected as the research subject, and a novel approach based on the attention mechanism combining the deep convolutional neural network (DCNN) and long short-term memory (LSTM) is proposed. First, the cabbage growth data and environmental monitoring data were normalized, and input samples were obtained by sliding the time window. Then, the DCNN and the LSTM were used to extract the spatial feature information and temporal correlation of the samples, respectively. At the same time, the attention mechanism was used to set the weight coefficients of different feature information and highlight the role of the main features of the sample in the model, thereby improving the prediction accuracy. By analyzing the experimental data collected by the Shandong Seedling Plant, the DCNN-LSTM method based on the proposed attention mechanism achieved good prediction results, providing experience for the engineering application of decision-making regarding seedling transplanting time. The experimental data showed that the mean absolute error, root-mean-square error, mean absolute percentage error, and symmetric mean absolute percentage error of the prediction results of this method were 0.356, 0.507, 0.157, and 0.082, respectively. Compared with the CNN, LSTM, LSTM-Attention and CNN-LSTM models, this model showed higher prediction accuracy.

show abstract

Deep learning for white cabbage seedling prediction

Cited by 23 publications

References 33 publications

Deep Learning for Image-Based Plant Growth Monitoring: A Review

Deep Learning for Image-Based Plant Growth Monitoring: A Review

Flowification: Everything is a Normalizing Flow

A Prediction Method of Seedling Transplanting Time with DCNN-LSTM Based on the Attention Mechanism

Contact Info

Product

Resources

About