Opportunities and challenges in phenotyping row crops using drone‐based RGB imaging

Sweet, Dorothy D.; Tirado, Sara B.; Springer, Nathan M.; Hirsch, Candice N.

doi:10.1002/ppj2.20044

Cited by 20 publications

(21 citation statements)

References 159 publications

(298 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ndings in this study align with previous research indicating that the performance of CSM/DSM and PC for PH estimation may vary depending on the speci c environment and ight conditions [53,54,135]. Overall, the PC data source showed better accuracy in most cases, suggesting that it may be more suitable for PH estimation in HTP applications.…”

Section: Plant Height Accuracysupporting

confidence: 88%

“…In 2021 the CSM (i.e., the height of individual plot surfaces) was obtained by subtracting the DTM from the DSM raster. Data was extracted from the regions of interest by overlapping the CSM and the shape le [53,54]. However, in 2020 and 2022 ights the PH were obtained by classifying the DSM and PC into ground and non-ground (vegetation) points using an assigned quantile of the pixel's distribution for a given plot.…”

Section: Plant Height Estimationmentioning

confidence: 99%

“…Recent studies have demonstrated the potential of utilizing remote sensing data and advanced modeling techniques for accurate PH estimation in various crops, such as maize [42,45], wheat [45][46][47], sorghum [48,49], cotton [50], barley [51], and rice [52]. Drone-based PH estimation has proven to be highly accurate and e cient, enabling breeders to rapidly collect and analyze large-scale PH data [13,53,54]. However, the accuracy of height measurements from DSMs can be in uenced by inconsistencies in ground altitude [53].…”

Section: Introductionmentioning

confidence: 99%

“…Drone-based PH estimation has proven to be highly accurate and e cient, enabling breeders to rapidly collect and analyze large-scale PH data [13,53,54]. However, the accuracy of height measurements from DSMs can be in uenced by inconsistencies in ground altitude [53]. Some methods generally require data from a ight before crop establishment, such as soil elevation or a Digital Surface Model (DSM) to calculate PH using a Crop Surface Model (CSM) [54].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

Volpato

Wright

Gomez

2023

Preprint

View full text Add to dashboard Cite

Background Significant effort has been made in manually tracking plant maturity and to measure early-stage plant density, and crop height in experimental breeding plots. Agronomic traits such as relative maturity (RM), stand count (SC) and plant height (PH) are essential to cultivar development, production recommendations and management practices. The use of RGB images collected via drones may replace traditional measurements in field trials with improved throughput, accuracy, and reduced cost. Recent advances in deep learning (DL) approaches have enabled the development of automated high-throughput phenotyping (HTP) systems that can quickly and accurately measure target traits using low-cost RGB drones. In this study, a time series of drone images was employed to estimate dry bean relative maturity (RM) using a hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for features extraction and capturing the sequential behavior of time series data. The performance of the Faster-RCNN object detection algorithm was also examined for stand count (SC) assessment during the early growth stages of dry beans. Various factors, such as flight frequencies, image resolution, and data augmentation, along with pseudo-labeling techniques, were investigated to enhance the performance and accuracy of DL models. Traditional methods involving pre-processing of images were also compared to the DL models employed in this study. Moreover, plant architecture was analyzed to extract plant height (PH) using digital surface model (DSM) and point cloud (PC) data sources. Results The CNN-LSTM model demonstrated high performance in predicting the RM of plots across diverse environments and flight datasets, regardless of image size or flight frequency. The DL model consistently outperformed the pre-processing images approach using traditional analysis (LOESS and SEG models), particularly when comparing errors using mean absolute error (MAE), providing less than two days of error in prediction across all environments. When growing degree days (GDD) data was incorporated into the CNN-LSTM model, the performance improved in certain environments, especially under unfavorable environmental conditions or weather stress. However, in other environments, the CNN-LSTM model performed similarly to or slightly better than the CNN-LSTM + GDD model. Consequently, incorporating GDD may not be necessary unless weather conditions are extreme. The Faster R-CNN model employed in this study was successful in accurately identifying bean plants at early growth stages, with correlations between the predicted SC and ground truth (GT) measurements of 0.8. The model performed consistently across various flight altitudes, and its accuracy was better compared to traditional segmentation methods using pre-processing images in OpenCV and the watershed algorithm. An appropriate growth stage should be carefully targeted for optimal results, as well as precise boundary box annotations. On average, the PC data source marginally outperformed the CSM/DSM data to estimating PH, with average correlation results of 0.55 for PC and 0.52 for CSM/DSM. The choice between them may depend on the specific environment and flight conditions, as the PH performance estimation is similar in the analyzed scenarios. However, the ground and vegetation elevation estimates can be optimized by deploying different thresholds and metrics to classify the data and perform the height extraction, respectively. Conclusions The results demonstrate that the CNN-LSTM and Faster R-CNN deep learning models outperforms other state-of-the-art techniques to quantify, respectively, RM and SC. The subtraction method proposed for estimating PH in the absence of accurate ground elevation data yielded results comparable to the difference-based method. In addition, open-source software developed to conduct the PH and RM analyses can contribute greatly to the phenotyping community.

show abstract

Section: Plant Height Accuracysupporting

confidence: 88%

Section: Plant Height Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

Volpato

Wright

Gomez

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Multispectral indices such as the Normalized Difference Vegetation Index (NDVI) [20], Green Normalized Difference Vegetation Index (GNDVI) [21], Normalized Difference Red Edge Index (NDRE) [22], and Optimized Soil Adjusted Vegetation Index (OSAVI) [23] have been widely used in nutrient status [24], canopy height and biomass [25], yield prediction [26], drought stress [27] and pathogen detection [28] applications. In the case of RGB indices, Excess Green (ExG) [29], Green Area (GA) and Greener Green Area (GGA) [30] have been widely used for assessing the effect of abiotic stresses, vegetation analysis, crop phenotyping and monitoring, disease and yield prediction, and plant biomass detection [31].…”

Section: Introductionmentioning

confidence: 99%

Comparative leaf area index estimation using multispectral and RGB images from a UAV platform

Martínez

Swaef

Borra‐Serrano

et al. 2023

Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping VIII

View full text Add to dashboard Cite

Leaf area index (LAI) is one of the most effective biophysical parameters for characterizing vegetation dynamics and crop productivity. Acquiring a time series of accurately estimated LAI in rice canopies allows to monitor and analyze growth dynamics during the crop season and contributes to a better understanding of photosynthesis, water use, biomass, and yield. Advances in technology platforms and navigation systems have enabled the acquisition of high-resolution images, offering new insights in innovative ways in an era when climate change imposes severe challenges on the agricultural sector. Field trials were conducted during two growing seasons in 2021 and 2022 in the Nataima research center of Agrosavia in El Espinal, Tolima, Colombia. The field trial consisted of three irrigation techniques applied in four Fedearroz 67 rice variety replicates. Multispectral and RGB images were taken from the UAV at 40m (1.83cm/0.49cm GSD), 60m (2.8cm/0.75cm GSD), and 80m (3.77cm/1.0cm GSD) above the crop. Images were then processed using the ViCTool, to compute vegetation indices. In addition, ground-truth LAI was indirectly determined by measuring the fresh and dry weight. Comparative results report significant differences in specific indices and trends for the two growing seasons regarding multispectral vegetation indices (NDRE, NDVI, GNDVI, GVI, SR, OSAVI, and SAVI). For the assessed RGB indices (ExG, GA, and GGA), there were no matching patterns or trends between flight height differences along cycles. These findings also reveal that although significant differences are observed, no greater improvement is seen in the determination coefficients (R 2 ) for LAI estimation using linear regression at any height.

show abstract

UAV image acquisition and processing for high‐throughput phenotyping in agricultural research and breeding programs

Bongomin,

Lamo,

Guina

et al. 2024

The Plant Phenome Journal

View full text Add to dashboard Cite

We are in a race against time to combat climate change and increase food production by 70% to feed the ever‐growing world population, which is expected to double by 2050. Agricultural research plays a vital role in improving crops and livestock through breeding programs and good agricultural practices, enabling sustainable agriculture and food systems. While advanced molecular breeding technologies have been widely adopted, phenotyping as an essential aspect of agricultural research and breeding programs has seen little development in most African institutions and remains a traditional method. However, the concept of high‐throughput phenotyping (HTP) has been gaining momentum, particularly in the context of unmanned aerial vehicle (UAV)‐based phenotyping. Although research into UAV‐based phenotyping is still limited, this paper aimed to provide a comprehensive overview and understanding of the use of UAV platforms and image analytics for HTP in agricultural research and to identify the key challenges and opportunities in this area. The paper discusses field phenotyping concepts, UAV classification and specifications, use cases of UAV‐based phenotyping, UAV imaging systems for phenotyping, and image processing and analytics methods. However, more research is required to optimize UAVs’ performance for image data acquisition, as limited studies have focused on the effect of UAVs’ operational parameters on data acquisition.

show abstract

Opportunities and challenges in phenotyping row crops using drone‐based RGB imaging

Cited by 20 publications

References 159 publications

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

Comparative leaf area index estimation using multispectral and RGB images from a UAV platform

UAV image acquisition and processing for high‐throughput phenotyping in agricultural research and breeding programs

Contact Info

Product

Resources

About