Intelligent navigation algorithm of plant phenotype detection robot based on dynamic credibility evaluation

Due to the non-standardization and complexity of the farmland environment,Global Navigation Satellite System(GNSS)navigation signal may be affected by the tree shade,and visual navigation is susceptible to winged insect and mud,which makes the navigation information of the plant phenotype detection robot unreliable.To solve this problem,this study proposed a multi-sensor information fusion intelligent navigation algorithm based on dynamic credibility evaluation.First,three navigation methods were studied:GNSS and Inertial Navigation System(INS)deep coupling navigation,depth image-based visual navigation,and maize image sequence navigation.Then a credibility evaluation model based on a deep belief network was established,which used dynamically updated credibility to intelligently fuse navigation results to reduce data fusion errors and enhance navigation reliability.At last,the algorithm was loaded on the plant phenotype detection robot for experimental testing in the field.The result shows that the navigation error is 2.7 cm and the navigation effect of the multi-sensor information fusion method is better than that of the single navigation method in the case of multiple disturbances.The multi-sensor information fusion method proposed in this study uses the credibility model of the deep belief network to perform navigation information fusion,which can effectively solve the problem of reliable navigation of the plant phenotype detection robot in the complex environment of farmland,and has important application prospects.

A nondestructive method for estimating the total green leaf area of individual rice plants using multi-angle color images

Total green leaf area(GLA)is an important trait for agronomic studies.However,existing methods for estimating the GLA of individual rice plants are destructive and labor-intensive.A nondestructive method for estimating the total GLA of individual rice plants based on multi-angle color images is presented.Using projected areas of the plant in images,linear,quadratic,exponential and power regression models for estimating total GLA were evaluated.Tests demonstrated that the side-view projected area had a stronger relationship with the actual total leaf area than the top-projected area.And power models fit better than other models.In addition,the use of multiple side-view images was an efficient method for reducing the estimation error.The inclusion of the top-view projected area as a seoond predictor provided only a slight improvement of the total leaf area est imation.When the projected areas from multi angle images were used,the estimated leaf area(ELA)using the power model and the actual leaf area had a high correlation cofficient(R2>0.98),and the mean absolute percentage error(MAPE)was about 6%.The method was capable of estimating the total leaf area in a nondestructive,accurate and eficient manner,and it may be used for monitoring rice plant growth.

Phenotypic plasticity of floral traits and pollination adaption in an alpine plant Pedicularis siphonantha D. Don when transplanted from higher to lower elevation in Eastern Himalaya

Phenotypic plasticity and/or pollinatormediated selection may be responsible for the changes in floral traits of plants when they are forced to live in new conditions. Although the two events could be independent, we hypothesized that phenotypic plasticity in floral traits might help to coordinate plant-pollinator interactions and enhance plant reproductive success in changing habitats. To test this hypothesis, we investigated floral traits and pollination on three natural populations of a lousewort(Pedicularis siphonantha) ranging at different elevations, as well as two downward transplanted populations in Shangeri-La County and Deqin County, northwest Yunnan, China. The results indicated that floral traits, i.e. phenology, longevity,display size, corolla tube length and pollen production differed significantly among populations. Moreover,or the two transplanted populations, floral traits diverged from their original populations, but converged to their host populations. Although the phenotypic plasticity in floral traits might be a rapid response to abiotic factor such as warmer environment, the changes in floral traits were found to be well adapted to pollination environment of the host population. Compared with plants of their original habitats in higher elevation, the transplanted individuals advanced flowering time, shortened flower longevity, reduced floral display size and pollen production, received higher visiting frequency and yielded more seeds. These findings suggested that phenotypic plasticity of floral traits might help plants adjust their resource allocation strategy between preand post-pollination stages in response to harsh or temperate conditions, which might correspondingly meet a pollinator-poor or hyphen rich environment.This would be beneficial for the widely-distributed species to adapt to various environmental changes.

An unmanned ground vehicle phenotyping-based method to generate three-dimensional multispectral point clouds for deciphering spatial heterogeneity in plant traits

Fusing three-dimensional(3D)and multispectral(MS)imaging data holds promise for high-throughput and comprehensive plant phenotyping to decipher genome-to-phenome knowledge.Acquiring high-quality 3D MS point clouds(3DMPCs)of plants remains challenging because of poor 3D data quality and limited radiometric calibration methods for plants with a complex canopy structure.Here,we present a novel 3D spatial–spectral data fusion approach to collect high-quality 3DMPCs of plants by integrating the next-best-view planning for adaptive data acquisition and neural reference field(NeREF)for radiometric calibration.This approach was used to acquire 3DMPCs of perilla,tomato,and rapeseed plants with diverse plant architecture and leaf morphological features evaluated by the accuracy of chlorophyll content and equivalent water thickness(EWT)estimation.The results showed that the completeness of plant point clouds collected by this approach was improved by an average of 23.6%compared with the fixed viewpoints alone.The NeREF-based radiometric calibration with the hemispherical reference outperformed the conventional calibration method by reducing the root mean square error(RMSE)of 58.93%for extracted reflectance spectra.The RMSE for chlorophyll content and EWT predictions decreased by 21.25%and 14.13%using partial least squares regression with the generated 3DMPCs.Collectively,our study provides an effective and efficient way to collect high-quality 3DMPCs of plants under natural light conditions,which improves the accuracy and comprehensiveness of phenotyping plant morphological and physiological traits,and thus will facilitate plant biology and genetic studies as well as crop breeding.

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

In order to address the challenge of non-destructive detection of tomato fruit ripeness in controlled environments,this study proposed a real-time instance segmentation method based on the edge device.This method combined the principles of phenotype robots and machine vision based on deep learning.A compact and remotely controllable phenotype detection robot was employed to acquire precise data on tomato ripeness.The video data were then processed by using an efficient backbone and the FeatFlowNet structure for feature extraction and analysis of key-frame to non-key-frame mapping from video data.To enhance the diversity of training datasets and the generalization of the model,an innovative approach was chosen by using random enhancement techniques.Besides,the PolyLoss optimization technique was applied to further improve the accuracy of the ripeness multi-class detection tasks.Through validation,the method of this study achieved real-time processing speeds of 90.1 fps(RTX 3070Ti)and 65.5 fps(RTX 2060 S),with an average detection accuracy of 97%compared to manually measured results.This is more accurate and efficient than other instance segmentation models according to actual testing in a greenhouse.Therefore,the results of this research can be deployed in edge devices and provide technical support for unmanned greenhouse monitoring devices or fruit-picking robots in facility environments.

Liquid metal-based plant electronic tattoos for in-situ monitoring of plant physiology

Flexible plant sensors,as a noninvasive and real-time monitoring method for plant physiology,are becoming crucial for precision agriculture.However,integrating flexible devices with plants are challenging due to their fragility and complex surfaces.In this study,we introduce a liquid metal-based plant electronic tattoo(LM-PET)that can harmlessly and continuously monitor the loss of water content and plant electrical signals,which are critical parameters for analyzing plant physiological status.The LM-PET achieves double-sided conductivity through soluble electrostatic spinning films and transferring technology,effectively addressing the issue of mismatch between the rigid interface of electronic devices and the surface of delicate plants.The fabricated tattoo electrode can adhere tightly to the leaf surface for a long time and can significantly broaden the scope of moisture monitoring,even in cases of severe wrinkling caused by water loss.At the optimum operating frequency of 100 kHz,the sensitivity of LM-PET can reach 25.4 kΩ%^(-1).Thus,LM-PETs can record the electrical signals generated when abiotic stresses threaten plants.They are also significant in providing a deeper understanding of the drought adaptation mechanisms of plants and developing drought-resistant varieties.They offer data-driven crop management and decision-making guidance,which is imperative for advancing precision agriculture.Overall,our findings provide valuable insights into the performance of agricultural inputs and facilitate real-time monitoring of plant growth and development.

Research advance in phenotype detection robots for agriculture and forestry

The continuous development of robot technology has made phenotype detection robots a key for extracting and analyzing phenotyping data in agriculture and forestry.The different applications of agricultural robots and phenotype detection robots were discussed in this article.Further,the structural characteristics and information interaction modes of the current phenotype detection robots were summarized from the viewpoint of agriculture and forestry.The publications with keywords related to clustering distribution were analyzed and the currently available phenotype robots were classified.Additionally,a conclusion on the design criteria and evaluation system of plant phenotype detection robots was summarized and obtained,and the challenges and future development direction were proposed,which can provide a reference for the design and applications of agriculture and forestry robots.

Plant trait estimation and classification studies in plant phenotyping using machine vision - A review

Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques.Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field.Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red,green and blue(RGB)imaging,thermal imaging,chlorophyll fluorescence imaging(CFIM),hyperspectral imaging,3-dimensional(3-D)imaging or high resolution volumetric imaging.This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping.This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification.In this paper,information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods.This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural(2-D and 3-D),physiological and temporal trait estimation,and classification studies in plants.

Sensors for measuring plant phenotyping:A review

Food crisis is a matter of prime importance because it becomes more severe as the global population grows.Among the solutions to this crisis,breeding is deemed one of the most effective ways.However,traditional phenotyping in breeding is time consuming and laborious,and the database is insufficient to meet the requirements of plant breeders,which hinders the development of breeding.Accordingly,innovations in phenotyping are urgent to solve this bottleneck.The morphometric and physiological parameters of plant are particularly interested to breeders.Numerous sensors have been employed and novel algorithms have been proposed to collect data on such parameters.This paper presents a brief review on the parameter measurement for phenotyping to describe its development in recent years.Some parameters that have been measured in phenotyping are introduced and discussed,including plant height,leaf parameters,in-plant space,chlorophyll,water stress,and biomass.And the measurement methods of each parameter with different sensors were classified and compared.Some comprehensive measurement platforms were also summarized,which are able to measure several parameters simultaneously.Besides,some deficiencies of phenotyping should be addressed,and novel methods should be proposed to reduce cost,improve efficiency,and promote phenotyping in the future.

Estimation of flea beetle damage in the field using a multistage deep learning-based solution

Estimation of damage in plants is a key issue for crop protection.Currently,experts in the field manually assess the plots.This is a time-consuming task that can be automated thanks to the latest technology in computer vision(CV).The use of image-based systems and recently deep learning-based systems have provided good results in several agricultural applications.These image-based applications outperform expert evaluation in controlled environments,and now they are being progressively included in non-controlled field applications.A novel solution based on deep learning techniques in combination with image processingmethods is proposed to tackle the estimate of plant damage in the field.The proposed solution is a two-stage algorithm.In a first stage,the single plants in the plots are detected by an object detection YOLO based model.Then a regression model is applied to estimate the damage of each individual plant.The solution has been developed and validated in oilseed rape plants to estimate the damage caused by flea beetle.The crop detection model achieves a mean precision average of 91%with a mAP@0.50 of 0.99 and a mAP@0.95 of 0.91 for oilseed rape specifically.The regression model to estimate up to 60%of damage degree in single plants achieves a MAE of 7.11,and R2 of 0.46 in comparison with manual evaluations done plant by plant by experts.Models are deployed in a docker,and with a REST API communication protocol they can be inferred directly for images acquired in the field from a mobile device.

Image based leaf segmentation and counting in rosette plants

This paper proposes an efficient method to extract the leaf region and count the number of leaves in digital plant images.The plant image analysis plays a significant role in viable and productive agriculture.It is used to record the plant growth,plant yield,chlorophyll fluorescence,plant width and tallness,leaf area,etc.frequently and accurately.Plant growth is a major character to be analyzed among these plant characters and it directly depends on the number of leaves in the plants.In this paper,a new method is presented for leaf region extraction from plant images and counting the number of leaves.The proposed method has three steps.The first step involves a new statistical based technique for image enhancement.The second step involves in the extraction of leaf region in plant image using a graph based method.The third step involves in counting the number of leaves in the plant image by applying Circular Hough Transform(CHT).The proposed work has been experimented on benchmark datasets of Leaf Segmentation Challenge(LSC).The proposed method achieves the segmentation accuracy of 95.4%and it also achieves the counting accuracy of
0.7(DiC)and 2.3(|DiC|)for datasets(A1,A2 and A3),which are better than the state-of-the-art methods.

A novel artificial bee colony-optimized visible oblique dipyramid greenness index for visionbased aquaponic lettuce biophysical signatures estimation

In response to the challenges in providing real-time extraction of crop biophysical signatures,computer vision in computational crop phenotyping highlights the opportunities of computational intelligence solutions.Shadow and angular brightness due to the presence of photosynthetic light unevenly illuminate crop canopy.In this study,a novel vegetation index named artificial bee colony-optimized visible band oblique dipyramid greenness index(vODGIabc)was proposed to enhance vegetation pixels by correcting the saturation and brightness levels,and the ratio of visible RGB reflectance intensities.Consumer-grade smartphone was used to acquire indoor and outdoor aquaponic lettuce images daily for full 6-week crop life cycle.The introduced saturation rectification coeffi-cient(X),value rectification coefficient(m),green–red wavelength adjustment factor(a),and green–blue wavelength adjustment factor(b)on the original triangular greenness index resulted in 3D canopy reflectance spectrum with two oblique tetrahedrons formed by connecting the vertices of visible RGB band reflectance and maximum wavelength point map to corresponding saturation and value of lettuce-captured images.Hybrid neighborhood component analysis(NCA),minimum redundancy maximum relevance(MRMR),Pearson’s correlation coefficient(PCC),and analysis of variance(ANOVA)weighted most of the canopy area,energy,and homogeneity.Strong linear relationships were exhibited by using vODGIabc in estimating lettuce crop fresh weight,height,number of spanning leaves,leaf area index,and growth stage with R2 values of 0.9368 for InceptionV3,0.9574 for ResNet101,0.9612 for ResNet101,0.9999 for Gaussian processing regression,and accuracy of 88.89%for ResNet101,respectively.This low-cost approach on developing greenness index for biophysical signatures estimation proved to be more accurate than the previously established triangular greenness index(TGI)using RGB smartphone camera.

Evaluation of biogenic markers-based phenotyping for resistance to Aphanomyces root rot in field pea

Biogenic volatile organic compounds(VOCs)emitted by plants can reveal information about plant adaptation,defense processes,and biological pathways.Thus,such VOC data may be utilized to capture phenotypic plant responses to the environment.In this study,the main objective was to evaluate the potential of biogenic compounds,including VOCs,to phenotype two pea cultivars,Ariel(susceptible)and Hampton(high levels of partial resistance)for resistance to Aphanomyces root rot disease.Plants were monitored non-destructively for VOC emission at three-time points(15,20,and 30 days after inoculation,DAI)using dynamic headspace sampling with gas chromatography-flame ionization detec-tion(GC-FID)system,as well as destructively at the end of the experiments,using solvent extraction and pyrolysis of both shoot and root tissues.A non-inoculated control(mock-inoculated with distilled water)was utilized to compare the plant responses within a cul-tivar.The common chemical peaks between control and inoculated samples of both culti-vars(RT_(cm))were analyzed after normalizing the relative peak intensity of inoculated samples with those of control samples,prior to a comparison between cultivars.In addi-tion,unique chemical peaks(RT_(uq))present in inoculated samples,but not in control sam-ples were also identified and their relative peak intensities were compared.Among the released green leaf volatiles(RT_(cm)),the normalized relative peak intensity of hexanal emis-sion,at 20 DAI,was higher in Ariel than that of Hampton.In addition,several putative chemical peaks(both RT_(cm) and RT_(uq)),previously known as indicators for disease response,exhibited some differences in their emission rates between pea cultivars in at least one of the time points.The destructive sampling revealed that shoot samples produced more putative unique biomarkers(RT_(uq))than the root samples.Based on the differences in puta-tive chemical peaks between cultivars,this initial study supports the concept of utilization of biogenic biomarker-based phenotyping in distinguishing levels of resistance in the eval-uated pea cultivars.More research is needed to further this approach for phenotyping other plant cultivars.Upon validation,the VOC profile integrated with high-throughput VOC sensing techniques can serve as a novel mechanism for phenotyping disease responses in crops.