Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review

Wang, Yahong; Su, Wen-Hao

doi:10.3390/agronomy12112659

Cited by 44 publications

(24 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning strategies have also been used in agricultural studies (Wang and Su, 2022). Abdalla et al (2019) evaluated three transfer learning methods using a VGG-based encoder net for oilseed rapes image segmentation; Cai et al (2020) proposed a modified U-Net architecture with transfer learning strategy for detecting plant locations; utilized transfer learning with Mask R-CNN for soybean seed segmentation.…”

Section: Transfer Learningmentioning

confidence: 99%

See 1 more Smart Citation

A novel transfer learning framework for sorghum biomass prediction using UAV-based remote sensing data and genetic markers

2023

View full text Add to dashboard Cite

Yield for biofuel crops is measured in terms of biomass, so measurements throughout the growing season are crucial in breeding programs, yet traditionally time- and labor-consuming since they involve destructive sampling. Modern remote sensing platforms, such as unmanned aerial vehicles (UAVs), can carry multiple sensors and collect numerous phenotypic traits with efficient, non-invasive field surveys. However, modeling the complex relationships between the observed phenotypic traits and biomass remains a challenging task, as the ground reference data are very limited for each genotype in the breeding experiment. In this study, a Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) model is proposed for sorghum biomass prediction. The architecture is designed to exploit the time series remote sensing and weather data, as well as static genotypic information. As a large number of features have been derived from the remote sensing data, feature importance analysis is conducted to identify and remove redundant features. A strategy to extract representative information from high-dimensional genetic markers is proposed. To enhance generalization and minimize the need for ground reference data, transfer learning strategies are proposed for selecting the most informative training samples from the target domain. Consequently, a pre-trained model can be refined with limited training samples. Field experiments were conducted over a sorghum breeding trial planted in multiple years with more than 600 testcross hybrids. The results show that the proposed LSTM-based RNN model can achieve high accuracies for single year prediction. Further, with the proposed transfer learning strategies, a pre-trained model can be refined with limited training samples from the target domain and predict biomass with an accuracy comparable to that from a trained-from-scratch model for both multiple experiments within a given year and across multiple years.

show abstract

Section: Transfer Learningmentioning

confidence: 99%

“…Transfer learning strategies have also been used in agricultural studies ( Wang and Su, 2022 ). Abdalla et al.…”

Section: Related Workmentioning

confidence: 99%

A novel transfer learning framework for sorghum biomass prediction using UAV-based remote sensing data and genetic markers

2023

View full text Add to dashboard Cite

show abstract

“…However, the manual measurement method has disadvantages, such as strong randomness, low efficiency, high time consumption, and a small amount of information obtained. With the development of artificial intelligence, machine vision in agriculture can be used to quickly obtain phenotypic information about crops [5][6] . Furthermore, based on phenotypic information, crops can be effectively monitored dynamically, which is an important means of implementing precision agriculture.…”

Section: Introductionmentioning

confidence: 99%

AgriGAN: Unpaired image dehazing via A Cycle-Consistent Generative Adversarial Network for the Agricultural Plant Phenotype

Ding,

Peng,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

Artificially extracted agricultural phenotype information has high subjectivity and low accuracy, and the use of image extraction information is easily disturbed by haze. Moreover, the agricultural image dehazing method used to extract such information is ineffective, as the images often contain unclear texture information and image colors. To address these shortcomings, we propose unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype (AgriGAN). The algorithm improves the dehazing performance of the network by adding the atmospheric scattering model, which improves the discriminator model, and uses the whole-detail consistent discrimination method to improve the efficiency of the discriminator so that the adversarial network can accelerate the convergence to the Nashi equilibrium state. Finally, the dehazed images are obtained by training with network adversarial loss + cycle consistent loss. Experiments and a comparative analysis were conducted to evaluate the algorithm, and the results show that it improved the dehazing accuracy of agricultural images, retained detailed texture information, and mitigated the problem of color deviation. In turn, useful information was obtained, such as crop height, chlorophyll and nitrogen content, and the presence and extent of disease. The algorithm's object identification and information extraction can be useful in crop growth monitoring and yield and quality estimation.

show abstract

“…However, for these traditional reconstruction methods, although optimization algorithms have theoretical convergence guarantees, their high computational complexity disqualified them being applied to real-time scenarios. In recent years, with the development of deep learning technology, Convolutional Neural Networks (CNN) were widely used and achieved excellent results in multiple fields such as computer vision [9], image processing, and speech recognition [10].…”

Section: Introductionmentioning

confidence: 99%

A CNN reconstruction scheme with low and high frequency branches for image compressive sensing

Wang

Yang

2023

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023)

View full text Add to dashboard Cite

Recently, Convolutional Neural Network-based Compressive Sensing(CNN-CS) have drawn attentions of extensive researchers since it can achieve faster reconstruction speed than traditional ones. Instead of traditional iterative reconstruction algorithms, a CNN reconstruction network is used with the goal of extracting key features of the images. For this purpose, the network should be trained on large amount of image data. However, most images usually poses both abundant low-frequency components and sparse high-frequency components, thus it is unreasonable to extract image features through a single network as in most CNN-CS algorithms due to that they may degrade the feature extraction of each other. In order to get a better result, a two-branch CNN-CS is proposed in the paper. In the network, the image signals are decomposed into two parts according to frequency firstly, and one branch is dedicated to extract the features of low frequency components, while the other is used to learn the high frequency ones. Considering the sparsity of high frequency, Mean Absolute Error (MAE) is chosen as the training penalty loss function. As such, both low and high frequency components can be well reconstructed respectively. Experimental results show that our method is prior to all traditional CS methods and single network CNN-CS method(CSNet+). The gain of PSNR over CSNet+ can reach 0.45dB.

show abstract

Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review

Cited by 44 publications

References 136 publications

A novel transfer learning framework for sorghum biomass prediction using UAV-based remote sensing data and genetic markers

A novel transfer learning framework for sorghum biomass prediction using UAV-based remote sensing data and genetic markers

AgriGAN: Unpaired image dehazing via A Cycle-Consistent Generative Adversarial Network for the Agricultural Plant Phenotype

A CNN reconstruction scheme with low and high frequency branches for image compressive sensing

Contact Info

Product

Resources

About