Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)

Narisetti, Narendra; Henke, M.; Neumann, Kerstin; Stolzenburg, Frieder; Altmann, Thomas; Gladilin, Evgeny

doi:10.3389/fpls.2022.906410

Cited by 10 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net is a popular deep learning network for semantic segmentation, which is famous in medical image segmentation applications [ 18 ]. Currently, there are also quite a few successful cases in plant phenotyping achieved by the U-Net, such as separating plants from the background [ 19 ] and plant root segmentation [ 20 ]. In this study, a simplified U-Net model was adopted for leaf disease spot segmentation.…”

Section: Methodsmentioning

confidence: 99%

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

et al. 2023

View full text Add to dashboard Cite

Deep learning and computer vision have become emerging tools for diseased plant phenotyping. Most previous studies focused on image-level disease classification. In this paper, pixel-level phenotypic feature (the distribution of spot) was analyzed by deep learning. Primarily, a diseased leaf dataset was collected and the corresponding pixel-level annotation was contributed. A dataset of apple leaves samples was used for training and optimization. Another set of grape and strawberry leaf samples was used as an extra testing dataset. Then, supervised convolutional neural networks were adopted for semantic segmentation. Moreover, the possibility of weakly supervised models for disease spot segmentation was also explored. Grad-CAM combined with ResNet-50 (ResNet-CAM), and that combined with a few-shot pretrained U-Net classifier for weakly supervised leaf spot segmentation (WSLSS), was designed. They were trained using image-level annotations (healthy versus diseased) to reduce the cost of annotation work. Results showed that the supervised DeepLab achieved the best performance (IoU = 0.829) on the apple leaf dataset. The weakly supervised WSLSS achieved an IoU of 0.434. When processing the extra testing dataset, WSLSS realized the best IoU of 0.511, which was even higher than fully supervised DeepLab (IoU = 0.458). Although there was a certain gap in IoU between the supervised models and weakly supervised ones, WSLSS showed stronger generalization ability than supervised models when processing the disease types not involved in the training procedure. Furthermore, the contributed dataset in this paper could help researchers get a quick start on designing their new segmentation methods in future studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The second is modeling, which involves examining the relationship between those pixels to digitally rebuild the phenotypic. The first one is usually the most challenging due to its high specificity between species and conditions (Narisetti et al ., 2022). Different segmentation algorithms can be performed using generic image-analysis software such as ImageJ or specific software for canopy traits: PlantCV, EasyPCC, PhenotyperCV, HPGA; or roots: EZ-Rhizo, SmartRoot, RootNav, ARIA, DIRT and RhizoVision Explorer.…”

Section: Discussionmentioning

confidence: 99%

Breeding for growth has resulted in increased tolerance to drought at the cost of genetic diversity in Scots pine

Gil-Muñoz,

Hayatgheibi,

Niemi

et al. 2023

Preprint

View full text Add to dashboard Cite

Climate change possess a threat to forests and forestry. Drought has been identified as a one of the main issues due to its interaction with other biotic and abiotic stresses. Few studies have been done regarding breeding effect on the adaptability to climate change. After a common garden experiment with seedling families of Scots pine from northern Sweden, we have found differences in drought tolerance between families of breeding and natural origin. We performed a high throughput analysis-based phenotyping on both canopy and root traits. Root architecture traits might be related to drought tolerance and show moderate to high heritability values. The heritability of root architecture traits can be useful not only for drought but also for adaptability to other abiotic stresses. Analysis on architecture traits show that, especially on canopy-traits, families from breeding origins show less phenotypic variance than the ones from natural origins. The methodology employed to evaluate drought tolerance and plant architecture might be useful for future research and forest management focused on climate change adaptability.

show abstract

“…Moris et al [ 14 ] also performed instance segmentation to detect and discriminate leaf boundaries, using a pyramid convolution neural network. Recently, Narisetti et al [ 15 ] developed a fully automated segmentation pipeline based on pretrained U-net deep learning models to phenotype shoots of different crops. Although deep learning methods have been extensively used in plant segmentation and phenotyping, they require a large-volume labelled dataset, which is not readily available [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping

Okyere

Cudjoe

Sadeghi‐Tehran

et al. 2023

Plants

View full text Add to dashboard Cite

Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust neural-network-based segmentation tool to phenotype plants in both field and glasshouse environments in a high-throughput manner. Digital images of cowpea (from glasshouse) and wheat (from field) with different nutrient supplies across their full growth cycle were acquired. Image patches from 20 randomly selected images from the acquired dataset were transformed from their original RGB format to multiple color spaces. The pixels in the patches were annotated as foreground and background with a pixel having a feature vector of 24 color properties. A feature selection technique was applied to choose the sensitive features, which were used to train a multilayer perceptron network (MLP) and two other traditional machine learning models: support vector machines (SVMs) and random forest (RF). The performance of these models, together with two standard color-index segmentation techniques (excess green (ExG) and excess green–red (ExGR)), was compared. The proposed method outperformed the other methods in producing quality segmented images with over 98%-pixel classification accuracy. Regression models developed from the different segmentation methods to predict Soil Plant Analysis Development (SPAD) values of cowpea and wheat showed that images from the proposed MLP method produced models with high predictive power and accuracy comparably. This method will be an essential tool for the development of a data analysis pipeline for high-throughput plant phenotyping. The proposed technique is capable of learning from different environmental conditions, with a high level of robustness.

show abstract

Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot)

Cited by 10 publications

References 39 publications

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

Breeding for growth has resulted in increased tolerance to drought at the cost of genetic diversity in Scots pine

Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping

Contact Info

Product

Resources

About