Dataset Information

Estimation of Greenhouse Lettuce Growth Indices Based on a Two-Stage CNN Using RGB-D Images.

ABSTRACT: Growth indices can quantify crop productivity and establish optimal environmental, nutritional, and irrigation control strategies. A convolutional neural network (CNN)-based model is presented for estimating various growth indices (i.e., fresh weight, dry weight, height, leaf area, and diameter) of four varieties of greenhouse lettuce using red, green, blue, and depth (RGB-D) data obtained using a stereo camera. Data from an online autonomous greenhouse challenge (Wageningen University, June 2021) were employed in this study. The data were collected using an Intel RealSense D415 camera. The developed model has a two-stage CNN architecture based on ResNet50V2 layers. The developed model provided coefficients of determination from 0.88 to 0.95, with normalized root mean square errors of 6.09%, 6.30%, 7.65%, 7.92%, and 5.62% for fresh weight, dry weight, height, diameter, and leaf area, respectively, on unknown lettuce images. Using red, green, blue (RGB) and depth data employed in the CNN improved the determination accuracy for all five lettuce growth indices due to the ability of the stereo camera to extract height information on lettuce. The average time for processing each lettuce image using the developed CNN model run on a Jetson SUB mini-PC with a Jetson Xavier NX was 0.83 s, indicating the potential for the model in fast real-time sensing of lettuce growth indices.

SUBMITTER: Gang MS

PROVIDER: S-EPMC9331482 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimation of Greenhouse Lettuce Growth Indices Based on a Two-Stage CNN Using RGB-D Images.

Gang Min-Seok MS Kim Hak-Jin HJ Kim Dong-Wook DW

Sensors (Basel, Switzerland) 20220723 15

Growth indices can quantify crop productivity and establish optimal environmental, nutritional, and irrigation control strategies. A convolutional neural network (CNN)-based model is presented for estimating various growth indices (i.e., fresh weight, dry weight, height, leaf area, and diameter) of four varieties of greenhouse lettuce using red, green, blue, and depth (RGB-D) data obtained using a stereo camera. Data from an online autonomous greenhouse challenge (Wageningen University, June 202 ...[more]

PMID: 35898004

Similar Datasets

Project description:Yield monitoring is an important parameter to evaluate cotton productivity during cotton harvest. Nondestructive and accurate yield monitoring is of great significance to cotton production. Unmanned aerial vehicle (UAV) remote sensing has fast and repetitive acquisition ability. The visible vegetation indices has the advantages of low cost, small amount of calculation and high resolution. The combination of the UAV and visible vegetation indices has been more and more applied to crop yield monitoring. However, there are some shortcomings in estimating cotton yield based on visible vegetation indices only as the similarity between cotton and mulch film makes it difficult to differentiate them and yields may be saturated based on vegetation index estimates near harvest. Texture feature is another important remote sensing information that can provide geometric information of ground objects and enlarge the spatial information identification based on original image brightness. In this study, RGB images of cotton canopy were acquired by UAV carrying RGB sensors before cotton harvest. The visible vegetation indices and texture features were extracted from RGB images for cotton yield monitoring. Feature parameters were selected in different methods after extracting the information. Linear and nonlinear methods were used to build cotton yield monitoring models based on visible vegetation indices, texture features and their combinations. The results show that (1) vegetation indices and texture features extracted from the ultra-high-resolution RGB images obtained by UAVs were significantly correlated with the cotton yield; (2) The best model was that combined with vegetation indices and texture characteristics RF_ELM model, verification set R 2 was 0.9109, and RMSE was 0.91277 t.ha-1. rRMSE was 29.34%. In conclusion, the research results prove that UAV carrying RGB sensor has a certain potential in cotton yield monitoring, which can provide theoretical basis and technical support for field cotton production evaluation.

Project description:The enhancement of plant tolerance toward abiotic stresses is increasingly being supported by the application of biostimulants. Salinity represents a serious problem in the Mediterranean region. To verify the effects deriving from the application of biostimulants, trials on Romaine lettuce plants under salt exposure were performed, in greenhouse. Plants were subjected to three NaCl solutions with 0.8, 1.3, and 1.8 dS/m of electrical conductivity. The volume of the solution was 200 mL/plant and delivered every 3 days. Biostimulant treatments started after crop establishment and were: control (water) and two doses (0.1 or 0.2 mL/plant) of the commercial biostimulant Retrosal® (Valagro S.p.A), containing calcium, zinc, and specific active ingredients. Four Retrosal® treatments were applied, every 7 days, directly to the substrate. Non-destructive analyses were conducted to assess the effects on leaf photosynthetic efficiency. At harvest, plants fresh weight (FW) and dry weight were determined, as well as the concentration of chlorophylls, carotenoids, total sugars, nitrate, proline, and abscisic acid (ABA). The biostimulant tested increased significantly the FW of lettuce (+65% in the highest dose) compared to controls. Results indicate that treatments positively affected the chlorophyll content measured in vivo (+45% in the highest dose) and that a general positive effect was observable on net photosynthesis rate. Retrosal® seems to improve the gas exchanges under our experimental conditions. The total sugars levels were not affected by treatments. Biostimulant allowed maintaining nitrate concentration similar to the untreated and unstressed controls. The increasing levels of water salinity caused a raise in proline concentration in control plants (+85%); biostimulant treatments at 0.2 mL/plant dose kept lower the proline levels. All plants treated with the biostimulant showed lower value of ABA (-34%) compared to controls. Results revealed that Retrosal® is able to stimulate plant growth independently from the salinity exposure. However, treated plants reached faster the commercial maturity stage. The fresh biomass of control at the end of experiment, after 30 days, ranged from 15 to 42 g/head, while in biostimulant treated plants ranged from 45 to 94 g/head. The product applied at maximum dose seems to be the most effective in our experimental conditions.

Dataset Information

Estimation of Greenhouse Lettuce Growth Indices Based on a Two-Stage CNN Using RGB-D Images.

Publications

Estimation of Greenhouse Lettuce Growth Indices Based on a Two-Stage CNN Using RGB-D Images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets