Sensors

Research

16 pages, 8673 KiB

Open AccessArticle

Crop Leaf Phenotypic Parameter Measurement Based on the RKM-D Point Cloud Method

by Weiyi Mu, Yuanxin Li, Mingjiang Deng, Ning Han and Xin Guo

Sensors 2024, 24(6), 1998; https://doi.org/10.3390/s24061998 - 21 Mar 2024

Viewed by 420

Crop leaf length, perimeter, and area serve as vital phenotypic indicators of crop growth status, the measurement of which is important for crop monitoring and yield estimation. However, processing a leaf point cloud is often challenging due to cluttered, fluctuating, and uncertain points, [...] Read more.

Crop leaf length, perimeter, and area serve as vital phenotypic indicators of crop growth status, the measurement of which is important for crop monitoring and yield estimation. However, processing a leaf point cloud is often challenging due to cluttered, fluctuating, and uncertain points, which culminate in inaccurate measurements of leaf phenotypic parameters. To tackle this issue, the RKM-D point cloud method for measuring leaf phenotypic parameters is proposed, which is based on the fusion of improved Random Sample Consensus with a ground point removal (R) algorithm, the K-means clustering (K) algorithm, the Moving Least Squares (M) method, and the Euclidean distance (D) algorithm. Pepper leaves were obtained from three growth periods on the 14th, 28th, and 42nd days as experimental subjects, and a stereo camera was employed to capture point clouds. The experimental results reveal that the RKM-D point cloud method delivers high precision in measuring leaf phenotypic parameters. (i) For leaf length, the coefficient of determination (R²) surpasses 0.81, the mean absolute error (MAE) is less than 3.50 mm, the mean relative error (MRE) is less than 5.93%, and the root mean square error (RMSE) is less than 3.73 mm. (ii) For leaf perimeter, the R² surpasses 0.82, the MAE is less than 7.30 mm, the MRE is less than 4.50%, and the RMSE is less than 8.37 mm. (iii) For leaf area, the R² surpasses 0.97, the MAE is less than 64.66 mm², the MRE is less than 4.96%, and the RMSE is less than 73.06 mm². The results show that the proposed RKM-D point cloud method offers a robust solution for the precise measurement of crop leaf phenotypic parameters. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

19 pages, 13296 KiB

Open AccessArticle

Multimodal Mobile Robotic Dataset for a Typical Mediterranean Greenhouse: The GREENBOT Dataset

by Fernando Cañadas-Aránega, Jose Luis Blanco-Claraco, Jose Carlos Moreno and Francisco Rodriguez-Diaz

Sensors 2024, 24(6), 1874; https://doi.org/10.3390/s24061874 - 14 Mar 2024

Viewed by 760

Abstract

This paper presents an innovative dataset designed explicitly for challenging agricultural environments, such as greenhouses, where precise location is crucial, but GNNS accuracy may be compromised by construction elements and the crop. The dataset was collected using a mobile platform equipped with a [...] Read more.

This paper presents an innovative dataset designed explicitly for challenging agricultural environments, such as greenhouses, where precise location is crucial, but GNNS accuracy may be compromised by construction elements and the crop. The dataset was collected using a mobile platform equipped with a set of sensors typically used in mobile robots as it was moved through all the corridors of a typical Mediterranean greenhouse featuring tomato crops. This dataset presents a unique opportunity for constructing detailed 3D models of plants in such indoor-like spaces, with potential applications such as robotized spraying. For the first time, to the authors’ knowledge, a dataset suitable to test simultaneous localization and mapping (SLAM) methods is presented in a greenhouse environment, which poses unique challenges. The suitability of the dataset for this purpose is assessed by presenting SLAM results with state-of-the-art algorithms. The dataset is available online. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

14 pages, 24774 KiB

Open AccessArticle

Effects of Harvesting Grabbing Type on Grabbing Force and Leaf Injury of Lettuce

by Yidong Ma, Pengzhan Hu, Xinping Li, Xin Jin, Huankun Wang and Chao Zhang

Sensors 2023, 23(13), 6047; https://doi.org/10.3390/s23136047 - 29 Jun 2023

Cited by 1 | Viewed by 979

Abstract

Hydroponic lettuce is the main cultivated leafy vegetable in plant factories, and its scattered leaves are delicate and easily injured. Harvesting is an important process in the production of hydroponic lettuce. To reduce the injury level of hydroponic lettuce during harvesting, the impacts [...] Read more.

Hydroponic lettuce is the main cultivated leafy vegetable in plant factories, and its scattered leaves are delicate and easily injured. Harvesting is an important process in the production of hydroponic lettuce. To reduce the injury level of hydroponic lettuce during harvesting, the impacts of the flexible finger-grabbing position applied on the grabbing force and the area of the injured leaves were investigated in this study by utilizing thin-film sensors and a high-speed video camera. According to the overlapping structural characteristics of adjacent leaves on lettuce, flexible finger-grabbing positions were divided into areas of the surface of the leaves and the intersections of the leaves. Three grabbing types—which are referred to in this paper as Grabbing Types A, B, and C—were identified according to the number of flexible fingers grabbing the leaf surface and the intersection area of the leaves. The force curves of all the flexible fingers were measured by thin film sensors, and the injury area of the leaves was detected using an image processing method. The results showed the consistency of the grabbing force curves and the motion characteristic parameters of the four flexible fingers. The maximum grabbing force of each flexible finger appeared at the stage of pulling the lettuce. The grabbing force of the flexible fingers acting on the intersection areas of the leaves was less than that acting on the leaf surface. As the number of flexible fingers acting on the intersection areas of the leaves increased, both the injury area of the leaves and the grabbing force decreased gradually. Grabbing Type C had the smallest injury area of the leaves: 120.3 ± 13.6 mm² with an 11.4% coefficient of variation. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

18 pages, 6712 KiB

Open AccessArticle

Structural Optimisation and Design of a Cable-Driven Hyper-Redundant Manipulator for Confined Semi-Structured Environments

by Rami Al-Khulaidi, Rini Akmeliawati, Steven Grainger and Tien-Fu Lu

Sensors 2022, 22(22), 8632; https://doi.org/10.3390/s22228632 - 09 Nov 2022

Cited by 1 | Viewed by 1505

Abstract

Structural optimisation of robotic manipulators is critical for any manipulator used in confined semi-structured environments, such as in agriculture. Many robotic manipulators utilised in semi-structured environments retain the same characteristics and dimensions as those used in fully-structured industrial environments, which have been proven [...] Read more.

Structural optimisation of robotic manipulators is critical for any manipulator used in confined semi-structured environments, such as in agriculture. Many robotic manipulators utilised in semi-structured environments retain the same characteristics and dimensions as those used in fully-structured industrial environments, which have been proven to experience low dexterity and singularity issues in challenging environments due to their structural limitations. When implemented in environments other than fully-structured industrial environments, conventional manipulators are liable to singularity, joint limits and workspace obstacles. This makes them inapplicable in confined semi-structured environments, as they lack the flexibility to operate dexterously in such challenging environments. In this paper, structural optimisation of a hyper-redundant cable-driven manipulator is proposed to improve its performance in semi-structured and challenging confined spaces, such as in agricultural settings. The optimisation of the manipulator design is performed in terms of its manipulability and kinematics. The lengths of the links and the joint angles are optimised to minimise any error between the actual and desired position/orientation of the end-effector in a confined semi-structured task space, as well as to provide optimal flexibility for the manipulators to generate different joint configurations for obstacle avoidance in confined environments. The results of the optimisation suggest that the use of a redundant manipulator with rigid short links can result in performance with higher dexterity in confined, semi-structured environments, such as agricultural greenhouses. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

15 pages, 6234 KiB

Open AccessArticle

Anomaly Detection for Agricultural Vehicles Using Autoencoders

by Esma Mujkic, Mark P. Philipsen, Thomas B. Moeslund, Martin P. Christiansen and Ole Ravn

Sensors 2022, 22(10), 3608; https://doi.org/10.3390/s22103608 - 10 May 2022

Cited by 12 | Viewed by 2856

Abstract

The safe in-field operation of autonomous agricultural vehicles requires detecting all objects that pose a risk of collision. Current vision-based algorithms for object detection and classification are unable to detect unknown classes of objects. In this paper, the problem is posed as anomaly [...] Read more.

The safe in-field operation of autonomous agricultural vehicles requires detecting all objects that pose a risk of collision. Current vision-based algorithms for object detection and classification are unable to detect unknown classes of objects. In this paper, the problem is posed as anomaly detection instead, where convolutional autoencoders are applied to identify any objects deviating from the normal pattern. Training an autoencoder network to reconstruct normal patterns in agricultural fields makes it possible to detect unknown objects by high reconstruction error. Basic autoencoder (AE), vector-quantized variational autoencoder (VQ-VAE), denoising autoencoder (DAE) and semisupervised autoencoder (SSAE) with a max-margin-inspired loss function are investigated and compared with a baseline object detector based on YOLOv5. Results indicate that SSAE with an area under the curve for precision/recall (PR AUC) of 0.9353 outperforms other autoencoder models and is comparable to an object detector with a PR AUC of 0.9794. Qualitative results show that SSAE is capable of detecting unknown objects, whereas the object detector is unable to do so and fails to identify known classes of objects in specific cases. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

16 pages, 1973 KiB

Open AccessArticle

Early Detection of Grapevine (Vitis vinifera) Downy Mildew (Peronospora) and Diurnal Variations Using Thermal Imaging

by Bar Cohen, Yael Edan, Asher Levi and Victor Alchanatis

Sensors 2022, 22(9), 3585; https://doi.org/10.3390/s22093585 - 08 May 2022

Cited by 12 | Viewed by 2802

Abstract

Agricultural industry is facing a serious threat from plant diseases that cause production and economic losses. Early information on disease development can improve disease control using suitable management strategies. This study sought to detect downy mildew (Peronospora) on grapevine (Vitis [...] Read more.

Agricultural industry is facing a serious threat from plant diseases that cause production and economic losses. Early information on disease development can improve disease control using suitable management strategies. This study sought to detect downy mildew (Peronospora) on grapevine (Vitis vinifera) leaves at early stages of development using thermal imaging technology and to determine the best time during the day for image acquisition. In controlled experiments, 1587 thermal images of grapevines grown in a greenhouse were acquired around midday, before inoculation, 1, 2, 4, 5, 6, and 7 days after an inoculation. In addition, images of healthy and infected leaves were acquired at seven different times during the day between 7:00 a.m. and 4:30 p.m. Leaves were segmented using the active contour algorithm. Twelve features were derived from the leaf mask and from meteorological measurements. Stepwise logistic regression revealed five significant features used in five classification models. Performance was evaluated using K-folds cross-validation. The support vector machine model produced the best classification accuracy of 81.6%, F1 score of 77.5% and area under the curve (AUC) of 0.874. Acquiring images in the morning between 10:40 a.m. and 11:30 a.m. resulted in 80.7% accuracy, 80.5% F1 score, and 0.895 AUC. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

19 pages, 6776 KiB

Open AccessArticle

Portable Deep Learning-Driven Ion-Sensitive Field-Effect Transistor Scheme for Measurement of Carbaryl Pesticide

by Nongluck Houngkamhang and Pattarapong Phasukkit

Sensors 2022, 22(9), 3543; https://doi.org/10.3390/s22093543 - 06 May 2022

Cited by 3 | Viewed by 1828

Abstract

This research proposes a multiple-input deep learning-driven ion-sensitive field-effect transistor (ISFET) scheme to predict the concentrations of carbaryl pesticide. In the study, the carbaryl concentrations are varied between 1 × 10⁻⁷–1 × 10⁻³ M, and the temperatures of solutions between [...] Read more.

This research proposes a multiple-input deep learning-driven ion-sensitive field-effect transistor (ISFET) scheme to predict the concentrations of carbaryl pesticide. In the study, the carbaryl concentrations are varied between 1 × 10⁻⁷–1 × 10⁻³ M, and the temperatures of solutions between 20–35 °C. To validate the multiple-input deep learning regression model, the proposed ISFET scheme is deployed onsite (a field test) to measure pesticide concentrations in the carbaryl-spiked vegetable extract. The advantage of this research lies in the use of a deep learning algorithm with an ISFET sensor to effectively predict the pesticide concentrations, in addition to improving the prediction accuracy. The results demonstrate the very high predictive ability of the proposed ISFET scheme, given an MSE, MAE, and R² of 0.007%, 0.016%, and 0.992, respectively. The proposed multiple-input deep learning regression model with signal compensation is applicable to a wide range of solution temperatures which is convenient for onsite measurement. Essentially, the proposed multiple-input deep learning regression model could be adopted as an effective alternative to the conventional statistics-based regression to predict pesticide concentrations. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Graphical abstract

18 pages, 7792 KiB

Open AccessArticle

Effects of Apple Vinegar Addition on Aerobic Deterioration of Fermented High Moisture Maize Using Infrared Thermography as an Indicator

by Aylin Agma Okur, Kerem Gozluklu, Ersen Okur, Berrin Okuyucu, Fisun Koc and Mehmet Levent Ozduven

Sensors 2022, 22(3), 771; https://doi.org/10.3390/s22030771 - 20 Jan 2022

Cited by 6 | Viewed by 1615

Abstract

This study was carried out to determine the effects of apple vinegar and sodium diacetate addition on the aerobic stability of fermented high moisture maize grain (HMM) silage after opening. In the study, the effect of three different levels (0%, 0.5% and 1%) [...] Read more.

This study was carried out to determine the effects of apple vinegar and sodium diacetate addition on the aerobic stability of fermented high moisture maize grain (HMM) silage after opening. In the study, the effect of three different levels (0%, 0.5% and 1%) of apple vinegar (AV) and sodium diacetate (SDA) supplementation to fermented HMM at two different storage conditions (27–29 °C, 48% Humidity; 35–37 °C, 26% Humidity) were investigated. The material of the study was fermented rolled maize grain with 62% moisture content stored for about 120 days. Silage samples were subjected to aerobic stability test with three replicates for each treatment group. Wendee and microbiological analyses were made at 0, 2, 4, 7, and 12 days. Meanwhile, samples were displayed in the T200 IR brand thermal camera. According to the thermogram results, 1% SDA addition positively affected HMM silages at the second and fourth days of aerobic stability at both storage conditions (p < 0.05). Aerobic stability and infrared thermography analysis indicated that 1% AV, 0.5%, and 1% SDA additions to HMM silages had promising effects. Due to our results, we concluded that thermal camera images might be used as an alternative quality indicator for silages in laboratory conditions. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

16 pages, 6720 KiB

Open AccessArticle

Performance Evaluation of an Autonomously Driven Agricultural Vehicle in an Orchard Environment

by Joong-hee Han, Chi-ho Park, Young Yoon Jang, Ja Duck Gu and Chan Young Kim

Sensors 2022, 22(1), 114; https://doi.org/10.3390/s22010114 - 24 Dec 2021

Cited by 11 | Viewed by 3635

Abstract

To address the problems of inefficient agricultural production and labor shortages, there has been active research to develop autonomously driven agricultural machines, using advanced sensors and ICT technology. Autonomously driven speed sprayers can also reduce accidents such as the pesticide poisoning of farmers, [...] Read more.

To address the problems of inefficient agricultural production and labor shortages, there has been active research to develop autonomously driven agricultural machines, using advanced sensors and ICT technology. Autonomously driven speed sprayers can also reduce accidents such as the pesticide poisoning of farmers, and vehicle overturn that frequently occur during spraying work in orchards. To develop a commercial, autonomously driven speed sprayer, we developed a prototype of an autonomously driven agricultural vehicle, and conducted performance evaluations in an orchard environment. A prototype of the agricultural vehicle was created using a rubber-tracked vehicle equipped with two AC motors. A prototype of the autonomous driving hardware consisted of a GNSS module, a motion sensor, an embedded board, and an LTE module, and it was made for less than $1000. Additional software, including a sensor fusion algorithm for positioning and a path-tracking algorithm for autonomous driving, were implemented. Then, the performance of the autonomous driving agricultural vehicle was evaluated based on two trajectories in an apple farm. The results of the field test determined the RMS, and the maximums of the path-following errors were 0.10 m, 0.34 m, respectively. Full article

(This article belongs to the Special Issue Robotics and Sensors Technology in Agriculture)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Robotics and Sensors Technology in Agriculture

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI