Automated Spike Detection in Diverse European Wheat Plants Using Textural Features and the Frangi Filter in 2D Greenhouse Images

Narisetti, Narendra; Neumann, Kerstin; Röder, Marion S.; Gladilin, Evgeny

doi:10.3389/fpls.2020.00666

Cited by 13 publications

(17 citation statements)

References 29 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10 Amara et al Qiongyan et al presented a shallow artificial neural network for segmentation of wheat spikes, which showed a satisfactory performance on wheat cultivars exhibiting spikes growing on the top of the plant ('top spikes'). 11 However, in our previous work, 12 we have found out that such a shallow ANN is rather restricted to detection of similar top spikes and does not perform that good for more bushy European wheat cultivars that exhibit spikes in the middle of the plant surrounded and partially overlaid by leaves. Improvements introduced to the shallow ANN architecture such as Frangi line filters could enhance the final segmentation results, however, this framework still requires substantial efforts for manual adjustment by application to the new image data.…”

Section: Introductionmentioning

confidence: 86%

See 1 more Smart Citation

Automated Detection and Segmentation of Grain Spikes in Greenhouse Images Using Shallow and Deep Learning Neural Networks: A Comparison of Six Methods

Ullah¹,

Henke²,

Narisetti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Image-based plant phenotyping is the major approach to quantitative assessment of important plant properties. For automated analysis of a large amount of image data from high-throughput greenhouse measurements, efficient techniques for image segmentation are required. However, conventional approaches to whole plant and plant organ segmentation are hampered by high variability of plant and background illumination, and naturally occurring changes in geometry and colors of growing plants. Consequently, application of advanced machine learning techniques for automated image segmentation is required. Here, we investigate six advanced neural network (NN) methods for detection and segmentation of grain spikes in RGB images including three detection deep NNs (SSD, Faster-RCNN, YOLOv3/v4), two deep (U-Net, DeepLabv3+) and one shallow segmentation NNs. Our experimental results show superior performance of deep learning NNs that achieve in average more than 90% accuracy by detection and segmentation of wheat as well as barley and rye spikes. However, different methods demonstrate different performance on matured, emergent and occluded spikes. In addition to comprehensive comparison of six NN methods, a GUI-based tool (SpikeApp) provided with this work demonstrates the application of detection and segmentation NNs to fully automated spike phenotyping. Further improvements of evaluated NN approaches are discussed.

show abstract

Section: Introductionmentioning

confidence: 86%

“…The shallow artificial neural network (ANN) approach from 11 with extensions introduced in 12 was retrained with ground truth segmentation data for leaf and spike patterns from the training set. Texture law energy well known from several previous works 7,25,26 was used in this approach as the main feature.…”

Section: Shallow Artificial Neural Networkmentioning

confidence: 99%

Automated Detection and Segmentation of Grain Spikes in Greenhouse Images Using Shallow and Deep Learning Neural Networks: A Comparison of Six Methods

Ullah¹,

Henke²,

Narisetti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Qiongyan et al presented a spike segmentation framework based on artificial (shallow) neural networks (ANNs), which was trained and evaluated only on images of wheat species exhibiting spikes on the top of the plant (further termed 'top spikes') and almost no leaf-covered ('inner') or occluded spikes [12]. In our previous work, we extended the ANN approach to the detection of more difficult bushy European wheat phenotypes [13]. Improvements introduced to the shallow ANN architecture, such as Frangi line filters, could enhance the final segmentation results; however, this ANN framework still requires substantial efforts, such as parameter adjustment by application to new image data.…”

Section: Publicationsmentioning

confidence: 99%

“…The shallow artificial neural network (ANN) approach from [12] with extensions introduced in [13] was retrained with ground truth segmentation data for leaf and spike patterns from the training set. The texture law energy, well known from several previous works [9,25,26], was used in this approach as the main feature.…”

Section: Shallow Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods

Ullah

Henke

Narisetti

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Automated analysis of small and optically variable plant organs, such as grain spikes, is highly demanded in quantitative plant science and breeding. Previous works primarily focused on the detection of prominently visible spikes emerging on the top of the grain plants growing in field conditions. However, accurate and automated analysis of all fully and partially visible spikes in greenhouse images renders a more challenging task, which was rarely addressed in the past. A particular difficulty for image analysis is represented by leaf-covered, occluded but also matured spikes of bushy crop cultivars that can hardly be differentiated from the remaining plant biomass. To address the challenge of automated analysis of arbitrary spike phenotypes in different grain crops and optical setups, here, we performed a comparative investigation of six neural network methods for pattern detection and segmentation in RGB images, including five deep and one shallow neural network. Our experimental results demonstrate that advanced deep learning methods show superior performance, achieving over 90% accuracy by detection and segmentation of spikes in wheat, barley and rye images. However, spike detection in new crop phenotypes can be performed more accurately than segmentation. Furthermore, the detection and segmentation of matured, partially visible and occluded spikes, for which phenotypes substantially deviate from the training set of regular spikes, still represent a challenge to neural network models trained on a limited set of a few hundreds of manually labeled ground truth images. Limitations and further potential improvements of the presented algorithmic frameworks for spike image analysis are discussed. Besides theoretical and experimental investigations, we provide a GUI-based tool (SpikeApp), which shows the application of pre-trained neural networks to fully automate spike detection, segmentation and phenotyping in images of greenhouse-grown plants.

show abstract

Heading percentage estimation in proso millet (Panicum miliaceum L.) using aerial imagery and deep learning

Zhao

Khound

Ghimire

et al. 2022

The Plant Phenome Journal

View full text Add to dashboard Cite

Proso millet (Panicum miliaceum L.), one of the major cultivated millets, serves as a complement to major cereal crops due to its drought tolerance and low input demands. Timing of heading is one of the key agronomic traits associated with its adaptation to a target environment and a major focus in breeding. Conventionally, heading percentage of a plot (genotype) was rated visually by breeders in field. Despite many successful studies reported in automatic head detections in other small grain species, little progress had been made to estimate heading percentage especially when multiple tillers exist. This study aimed to develop a method for automatic proso millet panicle detection and, more importantly, heading percentage estimation using regular red‐green‐blue images collected by an unmanned aerial vehicle. Aerial images of two dates were collected at heading stage in 2020 in Scottsbluff, NE. Faster regions with convolutional neural network models were trained to detect and count proso millet panicles in each plot. Then, using a sigmoid model, the number of detected panicles was converted to heading percentage without having the information of stand count and the number of tillers. Overall, the system achieved the highest coefficient of determination of 0.728 for proso millet heading percentage estimation, and an accuracy of 92.4% in determining whether a plot reached a certain threshold of heading (50% in this study). The methods developed in this study on heading percentage estimation can directly aid in decision making in proso millet breeding and can be ultimately incorporated into an automated proso millet high‐throughput phenotyping pipeline.

show abstract

Automated Spike Detection in Diverse European Wheat Plants Using Textural Features and the Frangi Filter in 2D Greenhouse Images

Cited by 13 publications

References 29 publications

Automated Detection and Segmentation of Grain Spikes in Greenhouse Images Using Shallow and Deep Learning Neural Networks: A Comparison of Six Methods

Automated Detection and Segmentation of Grain Spikes in Greenhouse Images Using Shallow and Deep Learning Neural Networks: A Comparison of Six Methods

Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods

Heading percentage estimation in proso millet (Panicum miliaceum L.) using aerial imagery and deep learning

Contact Info

Product

Resources

About