Dataset Information

A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique.

ABSTRACT: Farmers require accurate yield estimates, since they are key to predicting the volume of stock needed at supermarkets and to organizing harvesting operations. In many cases, the yield is visually estimated by the crop producer, but this approach is not accurate or time efficient. This study presents a rapid sensing and yield estimation scheme using off-the-shelf aerial imagery and deep learning. A Region-Convolutional Neural Network was trained to detect and count the number of apple fruit on individual trees located on the orthomosaic built from images taken by the unmanned aerial vehicle (UAV). The results obtained with the proposed approach were compared with apple counts made in situ by an agrotechnician, and an R2 value of 0.86 was acquired (MAE: 10.35 and RMSE: 13.56). As only parts of the tree fruits were visible in the top-view images, linear regression was used to estimate the number of total apples on each tree. An R2 value of 0.80 (MAE: 128.56 and RMSE: 130.56) was obtained. With the number of fruits detected and tree coordinates two shapefile using Python script in Google Colab were generated. With the previous information two yield maps were displayed: one with information per tree and another with information per tree row. We are confident that these results will help to maximize the crop producers' outputs via optimized orchard management.

SUBMITTER: Apolo-Apolo OE

PROVIDER: S-EPMC7378326 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique.

Apolo-Apolo Orly Enrique OE Pérez-Ruiz Manuel M Martínez-Guanter Jorge J Valente João J

Frontiers in plant science 20200715

Farmers require accurate yield estimates, since they are key to predicting the volume of stock needed at supermarkets and to organizing harvesting operations. In many cases, the yield is visually estimated by the crop producer, but this approach is not accurate or time efficient. This study presents a rapid sensing and yield estimation scheme using off-the-shelf aerial imagery and deep learning. A Region-Convolutional Neural Network was trained to detect and count the number of apple fruit on in ...[more]

PMID: 32765566

Similar Datasets

Project description:Lint yield in cotton is governed by light intercepted by the canopy (IPAR), radiation use efficiency (RUE), and harvest index (HI). However, the conventional methods of measuring these yield-governing physiological parameters are labor-intensive, time-consuming and requires destructive sampling. This study aimed to explore the use of low-cost and high-resolution UAV-based RGB and multispectral imagery 1) to estimate fraction of IPAR (IPARf), RUE, and biomass throughout the season, 2) to estimate lint yield using the cotton fiber index (CFI), and 3) to determine the potential use of biomass and lint yield models for estimating cotton HI. An experiment was conducted during the 2021 and 2022 growing seasons in Tifton, Georgia, USA in randomized complete block design with five different nitrogen treatments. Different nitrogen treatments were applied to generate substantial variability in canopy development and yield. UAV imagery was collected bi-weekly along with light interception and biomass measurements throughout the season, and 20 different vegetation indices (VIs) were computed from the imagery. Generalized linear regression was performed to develop models using VIs and growing degree days (GDDs). The IPARf models had R2 values ranging from 0.66 to 0.90, and models based on RVI and RECI explained the highest variation (93%) in IPARf during cross-validation. Similarly, cotton above-ground biomass was best estimated by models from MSAVI and OSAVI. Estimation of RUE using actual biomass measurement and RVI-based IPARf model was able to explain 84% of variation in RUE. CFI from UAV-based RGB imagery had strong relationship (R2 = 0.69) with machine harvested lint yield. The estimated HI from CFI-based lint yield and MSAVI-based biomass models was able to explain 40 to 49% of variation in measured HI for the 2022 growing season. The models developed to estimate the yield-contributing physiological parameters in cotton showed low to strong performance, with IPARf and above-ground biomass having greater prediction accuracy. Future studies on accurate estimation of lint yield is suggested for precise cotton HI prediction. This study is the first attempt of its kind and the results can be used to expand and improve research on predicting functional yield drivers of cotton.

Project description:Plant nitrogen concentration (PNC) is a critical indicator of N status for crops, and can be used for N nutrition diagnosis and management. This work aims to explore the potential of multispectral imagery from unmanned aerial vehicle (UAV) for PNC estimation and improve the estimation accuracy with hyperspectral data collected in the field with a hyperspectral radiometer. In this study we combined selected vegetation indices (VIs) and texture information to estimate PNC in rice. The VIs were calculated from ground and aerial platforms and the texture information was obtained from UAV-based multispectral imagery. Two consecutive years (2015 & 2016) of experiments were conducted, involving different N rates, planting densities and rice cultivars. Both UAV flights and ground spectral measurements were taken along with destructive samplings at critical growth stages of rice (Oryza sativa L.). After UAV imagery preprocessing, both VIs and texture measurements were calculated. Then the optimal normalized difference texture index (NDTI) from UAV imagery was determined for separated stage groups and the entire season. Results demonstrated that aerial VIs performed well only for pre-heading stages (R2 = 0.52-0.70), and photochemical reflectance index and blue N index from ground (PRIg and BNIg) performed consistently well across all growth stages (R2 = 0.48-0.65 and 0.39-0.68). Most texture measurements were weakly related to PNC, but the optimal NDTIs could explain 61 and 51% variability of PNC for separated stage groups and entire season, respectively. Moreover, stepwise multiple linear regression (SMLR) models combining aerial VIs and NDTIs did not significantly improve the accuracy of PNC estimation, while models composed of BNIg and optimal NDTIs exhibited significant improvement for PNC estimation across all growth stages. Therefore, the integration of ground-based narrow band spectral indices with UAV-based textural information might be a promising technique in crop growth monitoring.

Project description:Plant lodging is one of the most essential phenotypes for soybean breeding programs. Soybean lodging is conventionally evaluated visually by breeders, which is time-consuming and subject to human errors. This study aimed to investigate the potential of unmanned aerial vehicle (UAV)-based imagery and machine learning in assessing the lodging conditions of soybean breeding lines. A UAV imaging system equipped with an RGB (red-green-blue) camera was used to collect the imagery data of 1266 four-row plots in a soybean breeding field at the reproductive stage. Soybean lodging scores were visually assessed by experienced breeders, and the scores were grouped into four classes, i.e., non-lodging, moderate lodging, high lodging, and severe lodging. UAV images were stitched to build orthomosaics, and soybean plots were segmented using a grid method. Twelve image features were extracted from the collected images to assess the lodging scores of each breeding line. Four models, i.e., extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), were evaluated to classify soybean lodging classes. Five data preprocessing methods were used to treat the imbalanced dataset to improve classification accuracy. Results indicate that the preprocessing method SMOTE-ENN consistently performs well for all four (XGBoost, RF, KNN, and ANN) classifiers, achieving the highest overall accuracy (OA), lowest misclassification, higher F1-score, and higher Kappa coefficient. This suggests that Synthetic Minority Oversampling-Edited Nearest Neighbor (SMOTE-ENN) may be a good preprocessing method for using unbalanced datasets and the classification task. Furthermore, an overall accuracy of 96% was obtained using the SMOTE-ENN dataset and ANN classifier. The study indicated that an imagery-based classification model could be implemented in a breeding program to differentiate soybean lodging phenotype and classify lodging scores effectively.

Dataset Information

A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique.

Publications

A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets