Doing More With Less: A Multitask Deep Learning Approach in Plant Phenotyping

Dobrescu, Andrei; Giuffrida, Mario Valerio; Tsaftaris, Sotirios A.

doi:10.3389/fpls.2020.00141

Cited by 59 publications

(50 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first depends on more advanced models proposed by machine learning experts. Records for leaf counting accuracy of rosette plants continue to be broken in as new and better performing models and approaches are proposed and tested (Aich and Stavness, 2017;Ubbens et al, 2018;Dobrescu et al, 2020). The second depends on the availability and training of human annotators.…”

Section: Ct Of Llmentioning

confidence: 99%

Automation of Leaf Counting in Maize and Sorghum Using Deep Learning

Miao

Guo

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

Leaf number and leaf emergence rate are phenotypes of interest to plant breeders, plant geneticists, and crop modelers. Counting the extant leaves of an individual plant is straightforward even for an untrained individual, but manually tracking changes in leaf numbers for hundreds of individuals across multiple time points is logistically challenging. This study generated a dataset including over 150,000 maize and sorghum images for leaf counting projects. A subset of 17,783 images also includes annotations of the positions of individual leaf tips. With these annotated images, we evaluate two deep learning-based approaches for automated leaf counting: the first based on counting-by-regression from whole image analysis and a second based on counting-by-detection. Both approaches can achieve RMSE (root of mean square error) smaller than one leaf, only moderately inferior to the RMSE between human annotators of between 0.57 and 0.73 leaves. The counting-by-regression approach based on CNNs (convolutional neural networks) exhibited lower accuracy and increased bias for plants with extreme leaf numbers which are underrepresented in this dataset. The counting-by-detection approach based on Faster R-CNN object detection models achieve near human performance for plants where all leaf tips are visible. The annotated image data and model performance metrics generated as part of this study provide large scale resources for the comparison and improvement of algorithms for leaf counting from image data in grain crops.

show abstract

Section: Ct Of Llmentioning

confidence: 99%

Automation of Leaf Counting in Maize and Sorghum Using Deep Learning

Miao

Guo

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This helps the framework learn different tasks collectively. MTL allocates one shared model instead of using a separate model for different tasks, which helps reduce the storage space and training time [ 41 ]. Thus, from the given input, the proposed MTL-based CNN architecture can effectively identify the bearing health type under inconsistent working conditions, such as conditions with noise, compound faults, and variable motor speeds.…”

Section: Introductionmentioning

confidence: 99%

A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions

Hasan

Sohaib

Kim

2020

Sensors

View full text Add to dashboard Cite

Rolling element bearings are a vital part of rotating machines and their sudden failure can result in huge economic losses as well as physical causalities. Popular bearing fault diagnosis techniques include statistical feature analysis of time, frequency, or time-frequency domain data. These engineered features are susceptible to variations under inconsistent machine operation due to the non-stationary, non-linear, and complex nature of the recorded vibration signals. To address these issues, numerous deep learning-based frameworks have been proposed in the literature. However, the logical reasoning behind crack severities and the longer training times needed to identify multiple health characteristics at the same time still pose challenges. Therefore, in this work, a diagnosis framework is proposed that uses higher-order spectral analysis and multitask learning (MTL), while also incorporating transfer learning (TL). The idea is to first preprocess the vibration signals recorded from a bearing to look for distinct patterns for a given fault type under inconsistent working conditions, e.g., variable motor speeds and loads, multiple crack severities, compound faults, and ample noise. Later, these bispectra are provided as an input to the proposed MTL-based convolutional neural network (CNN) to identify the speed and the health conditions, simultaneously. Finally, the TL-based approach is adopted to identify bearing faults in the presence of multiple crack severities. The proposed diagnostic framework is evaluated on several datasets and the experimental results are compared with several state-of-the-art diagnostic techniques to validate the superiority of the proposed model under inconsistent working conditions.

show abstract

“…Bell et al [21] segmented leaves by edge classification and achieved good results for plant overlap. Dobrescu et al [22] proposed a multi-task deep learning framework for plant phenotypes and achieved good results in leaf counting. But the plant images of these studies were collected under indoor conditions, and images collected indoors tend to have a pure background and light uniformity [23].…”

Section: Introductionmentioning

confidence: 99%

Method for Obtaining Phenotypic Traits of Weeds in Complex Field Environments Based on Instance Segmentation

Quan

Mao

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Weeds are the biggest threat to crop growth, and leaf age and central area of weeds are important phenotypic traits of weeds. They have an important role in understanding the morphological structure of weeds, guiding precision for target weeding and reducing the use of herbicides. However, it is still a substantial challenge to obtain weed types, leaf age and central area in the complex field conditions of light changes, variation in appearance of plants, leaf occlusion. The latest developments in deep learning provide new tools for solving challenging computer vision tasks.Results: In this study, we present a weed phenotype segmentation method based on Mask R-CNN that obtains weed types, leaf age and central area in the complex field conditions. By shooting three different angles of the main weeds (Solanum nigrum, Barnyard grass, and Abutilon theophrasti Medicus) in the field through mobile devices, two datasets (data enhancement and without data enhancement) were produced and used as input to the network, two backbone networks was tested, namely ResNet50 and ResNet101, and the detection results and instance segmentation results of the model were evaluated. The results showed that data enhancement can improve the performance of the model. In the case of data enhancement, the F1 value with ResNet101 as the backbone network was 0.9214, the mAP scores were 0.6932 and 0.5244 (for IOU thresholds of 0.5 and 0.7, respectively), the mIOU reached 0.585, and the best segmentation performance example was obtained. Furthermore, the weed image taken from the top view angle compared to the other two angles achieved the highest detection accuracy.Conclusion: Mask R-CNN can achieve accurate segmentation of weeds to obtain the types, leaf age and central area of weeds. Data enhancement and the weed image taken from the top view angle can help to improve the performance of the model. This dataset and research results may provide important resources for the development of precision agriculture in the future.

show abstract

Doing More With Less: A Multitask Deep Learning Approach in Plant Phenotyping

Cited by 59 publications

References 40 publications

Automation of Leaf Counting in Maize and Sorghum Using Deep Learning

Automation of Leaf Counting in Maize and Sorghum Using Deep Learning

A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions

Method for Obtaining Phenotypic Traits of Weeds in Complex Field Environments Based on Instance Segmentation

Contact Info

Product

Resources

About