A method for automatic segmentation and splitting of hyperspectral images of raspberry plants collected in field conditions

Williams, Dominic; Britten, Avril; McCallum, Susan; Jones, Hamlyn G.; Karley, Alison J.; Loades, Kenneth; Prashar, Ankush; Graham, Julie

doi:10.1186/s13007-017-0226-y

Cited by 32 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The watershed algorithm is also a popular image segmentation method, which is often used for single tree crown delineation and kernel and leaf segmentation [92]. In addition, some of the methods that have been applied effectively to gray-scale, color, and multispectral images have been optimized purposefully and play key roles in hyperspectral image segmentation, such as Grabcut [93], the method of Otsu [94], and edge detection [95,96].…”

Section: Diseases Classification Is the Attempt To Identify And Label The Pathogens Affecting The Plant Simultaneouslymentioning

confidence: 99%

A Review of Advanced Technologies and Development for Hyperspectral-Based Plant Disease Detection in the Past Three Decades

et al. 2020

View full text Add to dashboard Cite

The detection, quantification, diagnosis, and identification of plant diseases is particularly crucial for precision agriculture. Recently, traditional visual assessment technology has not been able to meet the needs of precision agricultural informatization development, and hyperspectral technology, as a typical type of non-invasive technology, has received increasing attention. On the basis of simply describing the types of pathogens and host–pathogen interaction processes, this review expounds the great advantages of hyperspectral technologies in plant disease detection. Then, in the process of describing the hyperspectral disease analysis steps, the articles, algorithms, and methods from disease detection to qualitative and quantitative evaluation are mainly summarizing. Additionally, according to the discussion of the current major problems in plant disease detection with hyperspectral technologies, we propose that different pathogens’ identification, biotic and abiotic stresses discrimination, plant disease early warning, and satellite-based hyperspectral technology are the primary challenges and pave the way for a targeted response.

show abstract

Section: Diseases Classification Is the Attempt To Identify And Label The Pathogens Affecting The Plant Simultaneouslymentioning

confidence: 99%

A Review of Advanced Technologies and Development for Hyperspectral-Based Plant Disease Detection in the Past Three Decades

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The effective monitoring of the vineyard can be performed in real time and georeferenced, taking advantage of the integration between sensors and computing. Some other published works support the viability of on-the-go hyperspectral imaging (Underwood et al, 2017 ; Wendel and Underwood, 2017 ; Williams et al, 2017 ). The methodology exposed in the present work takes into consideration the works and machinery that are employed in the vineyard.…”

Section: Discussionmentioning

confidence: 85%

“…This new application could be useful for commercial vineyards, nurseries, appellation boards, etc. Some authors have previously demonstrated the possibility of performing outdoor hyperspectral imaging in several crops (Underwood et al, 2017 ; Wendel and Underwood, 2017 ; Williams et al, 2017 ), and this bolsters the development of new on-the-go hyperspectral solutions for grapevine-related problems.…”

Section: Introductionmentioning

confidence: 99%

On-The-Go Hyperspectral Imaging Under Field Conditions and Machine Learning for the Classification of Grapevine Varieties

et al. 2018

View full text Add to dashboard Cite

Grapevine varietal classification is an important plant phenotyping issue for grape growing and wine industry. This task has been achieved from destructive techniques like classic ampelography and DNA analysis under laboratory conditions. This work displays a new approach for the classification of a high number of grapevine (Vitis vinifera L.) varieties under field conditions using on-the-go hyperspectral imaging and different machine learning algorithms. On-the-go imaging was performed under natural illumination using a hyperspectral camera mounted on an all-terrain vehicle at 5 km/h. Spectra were acquired over two different leaf phenological stages on the canopy of 30 different varieties on a commercial vineyard located in La Rioja, Spain. A total of 1,200 spectral samples were generated. Support vector machines (SVM) and artificial neural networks (multilayer perceptrons, MLP) were used for the development of a large number of models, testing different algorithm parameters and spectral pre-processing techniques. Both classifiers yielded notable performance values and were able to train models with recall F1 scores and area under the receiver operating characteristic curve marks up to 0.99 for 5-fold cross validation. Statistical analyses supported that the best SVM kernel was linear and the best activation function for MLP was the hyperbolic tangent function. The prediction performance for individual varieties of MLP ranged from 0.94 to 0.99, displaying low levels of variability. In the case of SVM, slightly higher differences were obtained, ranging from 0.83 to 0.97 for individual varieties. These results support the possibility of deploying an on-the-go hyperspectral imaging system in the field capable of successfully classifying leaves from different grapevine varieties. This technology could thus be considered as a new useful non-destructive tool for plant phenotyping under field conditions.

show abstract

“… High-throughput plant phenotyping platforms: (A) small scale phenotyping platform consisting of XYZ PlantScreen TM growth-chamber with automatic top view RGB imaging (Photon System Instruments, Czechia) for screening biostimulant substances based on the changes on Arabidopsis rosette growth in multi-well plates at Palacký University in Olomouc, Czechia; (B) medium-scale phenotyping platform PlantScreen TM Modular System (Photon System Instruments, Czechia) with integrated high-resolution RGB, chlorophyll fluorescence, thermal and both VNIR and SWIR hyperspectral imagers for high-precision digital plant phenotyping and plant cultivation of mid-scale size up to large plants in greenhouse or semi-controlled environment; (C) Phenomobile for fruit trees and berry bushes developed at the James Hutton Institute (Scotland, United Kingdom), with VNIR and SWIR hyperspectral imagers ( Williams et al, 2017 ; photo courtesy of H. G. Jones); (D) Large scale automated field phenotyping system. PlantScreen TM Field System is autonomous mobile platform with multi-functional sensor platform mounted on an XZ-robotic arm with high-resolution visible, chlorophyll fluorescence, thermal infrared, hyperspectral imagers, and 3D laser sensor (Photon System Instruments, Czechia).…”

Section: Plant Biostimulants: What They Are and Their Effects On Morpmentioning

confidence: 99%

High-Throughput Plant Phenotyping for Developing Novel Biostimulants: From Lab to Field or From Field to Lab?

et al. 2018

View full text Add to dashboard Cite

Plant biostimulants which include bioactive substances (humic acids, protein hydrolysates and seaweed extracts) and microorganisms (mycorrhizal fungi and plant growth promoting rhizobacteria of strains belonging to the genera Azospirillum, Azotobacter, and Rhizobium spp.) are gaining prominence in agricultural systems because of their potential for improving nutrient use efficiency, tolerance to abiotic stressors, and crop quality. Highly accurate non-destructive phenotyping techniques have attracted the interest of scientists and the biostimulant industry as an efficient means for elucidating the mode of biostimulant activity. High-throughput phenotyping technologies successfully employed in plant breeding and precision agriculture, could prove extremely useful in unraveling biostimulant-mediated modulation of key quantitative traits and would also facilitate the screening process for development of effective biostimulant products in controlled environments and field conditions. This perspective article provides an innovative discussion on how small, medium, and large high-throughput phenotyping platforms can accelerate efforts for screening numerous biostimulants and understanding their mode of action thanks to pioneering sensor and image-based phenotyping techniques. Potentiality and constraints of small-, medium-, and large-scale screening platforms are also discussed. Finally, the perspective addresses two screening approaches, “lab to field” and “field to lab,” used, respectively, by small/medium and large companies for developing novel and effective second generation biostimulant products.

show abstract

A method for automatic segmentation and splitting of hyperspectral images of raspberry plants collected in field conditions

Cited by 32 publications

References 35 publications

A Review of Advanced Technologies and Development for Hyperspectral-Based Plant Disease Detection in the Past Three Decades

A Review of Advanced Technologies and Development for Hyperspectral-Based Plant Disease Detection in the Past Three Decades

On-The-Go Hyperspectral Imaging Under Field Conditions and Machine Learning for the Classification of Grapevine Varieties

High-Throughput Plant Phenotyping for Developing Novel Biostimulants: From Lab to Field or From Field to Lab?

Contact Info

Product

Resources

About