2024

Jump to: 2023, 2022, 2021

22 pages, 9421 KiB

Open AccessArticle

Low-Cost Plant-Protection Unmanned Ground Vehicle System for Variable Weeding Using Machine Vision

by Huangtao Dong, Jianxun Shen, Zhe Yu, Xiangyu Lu, Fei Liu and Wenwen Kong

Sensors 2024, 24(4), 1287; https://doi.org/10.3390/s24041287 - 17 Feb 2024

Viewed by 567

This study presents a machine vision-based variable weeding system for plant- protection unmanned ground vehicles (UGVs) to address the issues of pesticide waste and environmental pollution that are readily caused by traditional spraying agricultural machinery. The system utilizes fuzzy rules to achieve adaptive [...] Read more.

This study presents a machine vision-based variable weeding system for plant- protection unmanned ground vehicles (UGVs) to address the issues of pesticide waste and environmental pollution that are readily caused by traditional spraying agricultural machinery. The system utilizes fuzzy rules to achieve adaptive modification of the Kp, Ki, and Kd adjustment parameters of the PID control algorithm and combines them with an interleaved period PWM controller to reduce the impact of nonlinear variations in water pressure on the performance of the system, and to improve the stability and control accuracy of the system. After testing various image threshold segmentation and image graying algorithms, the normalized super green algorithm (2G-R-B) and the fast iterative threshold segmentation method were adopted as the best combination. This combination effectively distinguished between the vegetation and the background, and thus improved the accuracy of the pixel extraction algorithm for vegetation distribution. The results of orthogonal testing by selected four representative spraying duty cycles—25%, 50%, 75%, and 100%—showed that the pressure variation was less than 0.05 MPa, the average spraying error was less than 2%, and the highest error was less than 5% throughout the test. Finally, the performance of the system was comprehensively evaluated through field trials. The evaluation showed that the system was able to adjust the corresponding spraying volume in real time according to the vegetation distribution under the decision-making based on machine vision algorithms, which proved the low cost and effectiveness of the designed variable weed control system. Full article

► Show Figures

Figure 1

2023

Jump to: 2024, 2022, 2021

14 pages, 12050 KiB

Open AccessReview

Wireless Sensor Networks for Precision Agriculture: A Review of NPK Sensor Implementations

by Purnawarman Musa, Herik Sugeru and Eri Prasetyo Wibowo

Sensors 2024, 24(1), 51; https://doi.org/10.3390/s24010051 - 21 Dec 2023

Viewed by 2307

Abstract

The integration of Wireless Sensor Networks (WSNs) into agricultural areas has had a significant impact and has provided new, more complex, efficient, and structured solutions for enhancing crop production. This study reviews the role of Wireless Sensor Networks (WSNs) in monitoring the macronutrient [...] Read more.

The integration of Wireless Sensor Networks (WSNs) into agricultural areas has had a significant impact and has provided new, more complex, efficient, and structured solutions for enhancing crop production. This study reviews the role of Wireless Sensor Networks (WSNs) in monitoring the macronutrient content of plants. This review study focuses on identifying the types of sensors used to measure macronutrients, determining sensor placement within agricultural areas, implementing wireless technology for sensor communication, and selecting device transmission intervals and ratings. The study of NPK (nitrogen, phosphorus, potassium) monitoring using sensor technology in precision agriculture is of high significance in efforts to improve agricultural productivity and efficiency. Incorporating Wireless Sensor Networks (WSNs) into the ongoing progress of proposed sensor node placement design has been a significant facet of this study. Meanwhile, the assessment based on soil samples analyzed for macronutrient content, conducted directly in relation to the comparison between the NPK sensors deployed in this research and the laboratory control sensors, reveals an error rate of 8.47% and can be deemed as a relatively satisfactory outcome. In addition to fostering technological innovations and precision farming solutions, in future this research aims to increase agricultural yields, particularly by enabling the cultivation of certain crops in locations different from their original ones. Full article

► Show Figures

Figure 1

17 pages, 12647 KiB

Open AccessArticle

Blackberry Fruit Classification in Underexposed Images Combining Deep Learning and Image Fusion Methods

by Eduardo Morales-Vargas, Rita Q. Fuentes-Aguilar, Emanuel de-la-Cruz-Espinosa and Gustavo Hernández-Melgarejo

Sensors 2023, 23(23), 9543; https://doi.org/10.3390/s23239543 - 30 Nov 2023

Viewed by 708

Abstract

Berry production is increasing worldwide each year; however, high production leads to labor shortages and an increase in wasted fruit during harvest seasons. This problem opened new research opportunities in computer vision as one main challenge to address is the uncontrolled light conditions [...] Read more.

Berry production is increasing worldwide each year; however, high production leads to labor shortages and an increase in wasted fruit during harvest seasons. This problem opened new research opportunities in computer vision as one main challenge to address is the uncontrolled light conditions in greenhouses and open fields. The high light variations between zones can lead to underexposure of the regions of interest, making it difficult to classify between vegetation, ripe, and unripe blackberries due to their black color. Therefore, the aim of this work is to automate the process of classifying the ripeness stages of blackberries in normal and low-light conditions by exploring the use of image fusion methods to improve the quality of the input image before the inference process. The proposed algorithm adds information from three sources: visible, an improved version of the visible, and a sensor that captures images in the near-infrared spectra, obtaining a mean F1 score of

0.909 \pm 0.074

and

0.962 \pm 0.028

in underexposed images, without and with model fine-tuning, respectively, which in some cases is an increase of up to 12% in the classification rates. Furthermore, the analysis of the fusion metrics showed that the method could be used in outdoor images to enhance their quality; the weighted fusion helps to improve only underexposed vegetation, improving the contrast of objects in the image without significant changes in saturation and colorfulness. Full article

► Show Figures

Figure 1

2022

Jump to: 2024, 2023, 2021

22 pages, 968 KiB

Open AccessArticle

Improving Data Security with Blockchain and Internet of Things in the Gourmet Cocoa Bean Fermentation Process

by Jauberth Abijaude, Péricles Sobreira, Levy Santiago and Fabíola Greve

Sensors 2022, 22(8), 3029; https://doi.org/10.3390/s22083029 - 15 Apr 2022

Cited by 6 | Viewed by 2781

Abstract

Brazil was one of the largest cocoa producers in the world, mainly supported by the South of Bahia region. After the 1980s, the witch-broom disease demolished plantations, and farmers were forced into bankruptcy. The worldwide search for gourmet cocoa has rekindled interest in [...] Read more.

Brazil was one of the largest cocoa producers in the world, mainly supported by the South of Bahia region. After the 1980s, the witch-broom disease demolished plantations, and farmers were forced into bankruptcy. The worldwide search for gourmet cocoa has rekindled interest in this production, whose fermentation process is a key step in obtaining fine cocoa, thanks to the fact that many processing properties and sensory attributes are developed in this phase. This article presents a blockchain-IoT-based system for the control and monitoring of these events, aiming to catalog in smart contracts valuable information for improvement of the cocoa fermentation process, and future research. Blockchain is used as a distributed database that implements an application-level security layer. A proof of concept was modeled and the performance of the emulated system was evaluated in the OMNet simulator, where a technique based on the SNMP protocol was applied to reduce the amount of data exchanged and resources served/consumed in this representation. Then, a physical platform was developed and preliminary experiments were performed on a real farm, as a way to verify the improvement of the cocoa fermentation process when using a technological approach. Full article

► Show Figures

Figure 1

10 pages, 2013 KiB

Open AccessCommunication

Strawberry Maturity Recognition Algorithm Combining Dark Channel Enhancement and YOLOv5

by Youchen Fan, Shuya Zhang, Kai Feng, Kechang Qian, Yitong Wang and Shangzhi Qin

Sensors 2022, 22(2), 419; https://doi.org/10.3390/s22020419 - 06 Jan 2022

Cited by 30 | Viewed by 3456

Abstract

Aiming at the problems of low accuracy of strawberry fruit picking and large rate of mispicking or missed picking, YOLOv5 combined with dark channel enhancement is proposed. In “Fengxiang” strawberry, the criterion of “bad fruit” is added to the conventional three criteria of [...] Read more.

Aiming at the problems of low accuracy of strawberry fruit picking and large rate of mispicking or missed picking, YOLOv5 combined with dark channel enhancement is proposed. In “Fengxiang” strawberry, the criterion of “bad fruit” is added to the conventional three criteria of ripeness, near-ripeness, and immaturity, because some of the bad fruits are close to the color of ripe fruits, but the fruits are small and dry. The training accuracy of the four kinds of strawberries with different ripeness is above 85%, and the testing accuracy is above 90%. Then, to meet the demand of all-day picking and address the problem of low illumination of images collected at night, an enhancement algorithm is proposed to enhance the images, which are recognized. We compare the actual detection results of the five enhancement algorithms, i.e., histogram equalization, Laplace transform, gamma transform, logarithmic variation, and dark channel enhancement processing under the different numbers of fruits, periods, and video tests. The results show that combined with dark channel enhancement, YOLOv5 has the highest recognition rate. Finally, the experimental results demonstrate that YOLOv5 is better than SSD, DSSD, and EfficientDet in terms of recognition accuracy, and the correct rate can reach more than 90%. Meanwhile, the method has good robustness in complex environments such as partial occlusion and multiple fruits. Full article

► Show Figures

Figure 1

2021

Jump to: 2024, 2023, 2022

15 pages, 858 KiB

Open AccessArticle

Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD

by Thomas Hänel, Thomas Jarmer and Nils Aschenbruck

Sensors 2021, 21(21), 7296; https://doi.org/10.3390/s21217296 - 02 Nov 2021

Cited by 3 | Viewed by 1367

Abstract

A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them [...] Read more.

A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them a promising solution for the calibration of satellite data. In this paper, we explore an alternative approach for processing data from such a network. Hyperspectral sensors were found to be too complex for such a network. While previous work considered fusing the data from different multispectral sensors in order to derive hyperspectral data, we shift the assessment of the hyperspectral modeling in a separate preprocessing step based on machine learning. We then use the learned data as additional input while using identical multispectral sensors, further reducing the complexity of the sensors. Despite requiring careful parametrization, the approach delivers hyperspectral data of similar and in some cases even better quality. Full article

► Show Figures

Figure 1

24 pages, 46901 KiB

Open AccessArticle

A Novel Approach for Development and Evaluation of LiDAR Navigated Electronic Maize Seeding System Using Check Row Quality Index

by Nrusingh Charan Pradhan, Pramod Kumar Sahoo, Dilip Kumar Kushwaha, Indra Mani, Ankur Srivastava, Atish Sagar, Nikul Kumari, Susheel Kumar Sarkar and Yash Makwana

Sensors 2021, 21(17), 5934; https://doi.org/10.3390/s21175934 - 03 Sep 2021

Cited by 2 | Viewed by 2293

Abstract

Crop geometry plays a vital role in ensuring proper plant growth and yield. Check row planting allows adequate space for weeding in both direction and allowing sunlight down to the bottom of the crop. Therefore, a light detection and ranging (LiDAR) navigated electronic [...] Read more.

Crop geometry plays a vital role in ensuring proper plant growth and yield. Check row planting allows adequate space for weeding in both direction and allowing sunlight down to the bottom of the crop. Therefore, a light detection and ranging (LiDAR) navigated electronic seed metering system for check row planting of maize seeds was developed. The system is comprised of a LiDAR-based distance measurement unit, electronic seed metering mechanism and a wireless communication system. The electronic seed metering mechanism was evaluated in the laboratory for five different cell sizes (8.80, 9.73, 10.82, 11.90 and 12.83 mm) and linear cell speed (89.15, 99.46, 111.44, 123.41 and 133.72 mm·s⁻¹). The research shows the optimised values for the cell size and linear speed of cell were found to be 11.90 mm and 99.46 mm·s⁻¹ respectively. A light dependent resistor (LDR) and light emitting diode (LED)-based seed flow sensing system was developed to measure the lag time of seed flow from seed metering box to bottom of seed tube. The average lag time of seed fall was observed as 251.2

\pm

5.39 ms at an optimised linear speed of cell of 99.46 mm·s⁻¹ and forward speed of 2 km·h⁻¹. This lag time was minimized by advancing the seed drop on the basis of forward speed of tractor, lag time and targeted position. A check row quality index (

I_{C R Q}

) was developed to evaluate check row planter. While evaluating the developed system at different forward speeds (i.e., 2, 3 and 5 km·h⁻¹), higher standard deviation (14.14%) of check row quality index was observed at forward speed of 5 km·h⁻¹. Full article

► Show Figures

Graphical abstract

30 pages, 10803 KiB

Open AccessArticle

Assessment of Grain Harvest Moisture Content Using Machine Learning on Smartphone Images for Optimal Harvest Timing

by Ming-Der Yang, Yu-Chun Hsu, Wei-Cheng Tseng, Chian-Yu Lu, Chin-Ying Yang, Ming-Hsin Lai and Dong-Hong Wu

Sensors 2021, 21(17), 5875; https://doi.org/10.3390/s21175875 - 31 Aug 2021

Cited by 6 | Viewed by 4629

Abstract

Grain moisture content (GMC) is a key indicator of the appropriate harvest period of rice. Conventional testing is time-consuming and laborious, thus not to be implemented over vast areas and to enable the estimation of future changes for revealing optimal harvesting. Images of [...] Read more.

Grain moisture content (GMC) is a key indicator of the appropriate harvest period of rice. Conventional testing is time-consuming and laborious, thus not to be implemented over vast areas and to enable the estimation of future changes for revealing optimal harvesting. Images of single panicles were shot with smartphones and corrected using a spectral–geometric correction board. In total, 86 panicle samples were obtained each time and then dried at 80 °C for 7 days to acquire the wet-basis GMC. In total, 517 valid samples were obtained, in which 80% was randomly used for training and 20% was used for testing to construct the image-based GMC assessment model. In total, 17 GMC surveys from a total of 201 samples were also performed from an area of 1 m² representing on-site GMC, which enabled a multi-day GMC prediction. Eight color indices were selected using principal component analysis for building four machine learning models, including random forest, multilayer perceptron, support vector regression (SVR), and multivariate linear regression. The SVR model with a MAE of 1.23% was the most suitable for GMC of less than 40%. This study provides a real-time and cost-effective non-destructive GMC measurement using smartphones that enables on-farm prediction of harvest dates and facilitates the harvesting scheduling of agricultural machinery. Full article

► Show Figures

Graphical abstract

21 pages, 2839 KiB

Open AccessArticle

Dynamic Optimization Method for Broadband ADCP Waveform with Environment Constraints

by Yongshou Yang and Shiliang Fang

Sensors 2021, 21(11), 3768; https://doi.org/10.3390/s21113768 - 28 May 2021

Cited by 2 | Viewed by 2148

Abstract

Broadband acoustic Doppler current profiler (ADCP) is widely used in agricultural water resource explorations, such as river discharge monitoring and flood warning. Improving the velocity estimation accuracy of broadband ADCP by adjusting the waveform parameters of a phase-encoded signal will reduce the velocity [...] Read more.

Broadband acoustic Doppler current profiler (ADCP) is widely used in agricultural water resource explorations, such as river discharge monitoring and flood warning. Improving the velocity estimation accuracy of broadband ADCP by adjusting the waveform parameters of a phase-encoded signal will reduce the velocity measurement range and water stratification accuracy, while the promotion of stratification accuracy will degrade the velocity estimation accuracy. In order to minimize the impact of these two problems on the measurement results, the ADCP waveform optimization problem that satisfies the environment constraints while keeping high velocity estimation accuracy or stratification accuracy is studied. Firstly, the relationship between velocity or distance estimation accuracy and signal waveform parameters is studied by using an ambiguity function. Secondly, the constraints of current velocity range, velocity distribution and other environmental characteristics on the waveform parameters are studied. For two common measurement applications, two dynamic configuration methods of waveform parameters with environmental adaptability and optimal velocity estimation accuracy or stratification accuracy are proposed based on the nonlinear programming principle. Experimental results show that compared with the existing methods, the velocity estimation accuracy of the proposed method is improved by more than 50%, and the stratification accuracy is improved by more than 22%. Full article

► Show Figures

Figure 1

15 pages, 5048 KiB

Open AccessArticle

Grape Cluster Detection Using UAV Photogrammetric Point Clouds as a Low-Cost Tool for Yield Forecasting in Vineyards

by Jorge Torres-Sánchez, Francisco Javier Mesas-Carrascosa, Luis-Gonzaga Santesteban, Francisco Manuel Jiménez-Brenes, Oihane Oneka, Ana Villa-Llop, Maite Loidi and Francisca López-Granados

Sensors 2021, 21(9), 3083; https://doi.org/10.3390/s21093083 - 28 Apr 2021

Cited by 25 | Viewed by 4024

Abstract

Yield prediction is crucial for the management of harvest and scheduling wine production operations. Traditional yield prediction methods rely on manual sampling and are time-consuming, making it difficult to handle the intrinsic spatial variability of vineyards. There have been significant advances in automatic [...] Read more.

Yield prediction is crucial for the management of harvest and scheduling wine production operations. Traditional yield prediction methods rely on manual sampling and are time-consuming, making it difficult to handle the intrinsic spatial variability of vineyards. There have been significant advances in automatic yield estimation in vineyards from on-ground imagery, but terrestrial platforms have some limitations since they can cause soil compaction and have problems on sloping and ploughed land. The analysis of photogrammetric point clouds generated with unmanned aerial vehicles (UAV) imagery has shown its potential in the characterization of woody crops, and the point color analysis has been used for the detection of flowers in almond trees. For these reasons, the main objective of this work was to develop an unsupervised and automated workflow for detection of grape clusters in red grapevine varieties using UAV photogrammetric point clouds and color indices. As leaf occlusion is recognized as a major challenge in fruit detection, the influence of partial leaf removal in the accuracy of the workflow was assessed. UAV flights were performed over two commercial vineyards with different grape varieties in 2019 and 2020, and the photogrammetric point clouds generated from these flights were analyzed using an automatic and unsupervised algorithm developed using free software. The proposed methodology achieved R² values higher than 0.75 between the harvest weight and the projected area of the points classified as grapes in vines when partial two-sided removal treatment, and an R² of 0.82 was achieved in one of the datasets for vines with untouched full canopy. The accuracy achieved in grape detection opens the door to yield prediction in red grape vineyards. This would allow the creation of yield estimation maps that will ease the implementation of precision viticulture practices. To the authors’ knowledge, this is the first time that UAV photogrammetric point clouds have been used for grape clusters detection. Full article

► Show Figures

Figure 1

20 pages, 6824 KiB

Open AccessArticle

A LiDAR Sensor-Based Spray Boom Height Detection Method and the Corresponding Experimental Validation

by Hanjie Dou, Songlin Wang, Changyuan Zhai, Liping Chen, Xiu Wang and Xueguan Zhao

Sensors 2021, 21(6), 2107; https://doi.org/10.3390/s21062107 - 17 Mar 2021

Cited by 6 | Viewed by 2506

Abstract

Sprayer boom height (H_b) variations affect the deposition and distribution of droplets. An H_b control system is used to adjust H_b to maintain an optimum distance between the boom and the crop canopy, and an H_b detection [...] Read more.

Sprayer boom height (H_b) variations affect the deposition and distribution of droplets. An H_b control system is used to adjust H_b to maintain an optimum distance between the boom and the crop canopy, and an H_b detection sensor is a key component of the H_b control system. This study presents a new, low-cost light detection and ranging (LiDAR) sensor for H_b detection developed based on the principle of single-point ranging. To examine the detection performance of the LiDAR sensor, a step height detection experiment, a field ground detection experiment, and a wheat stubble (WS) height detection experiment as well as a comparison with an ultrasonic sensor were performed. The results showed that the LiDAR sensor could be used to detect H_b. When used to detect the WS height (H_WS), the LiDAR sensor primarily detected the WS roots and the inside of the WS canopy. H_WS and movement speed of the LiDAR sensor (V_LiDAR) has a greater impact on the detection performance of the LiDAR sensor for the WS canopy than that for the WS roots. The detection error of the LiDAR sensor for the WS roots is less than 5.00%, and the detection error of the LiDAR sensor for the WS canopy is greater than 8.00%. The detection value from the LiDAR sensor to the WS root multiplied by 1.05 can be used as a reference basis for adjusting H_b, and after the WS canopy height is added to the basis, the value can be used as an index for adjusting H_b in WS field spraying. The results of this study will promote research on the boom height detection method and autonomous H_b control system. Full article

► Show Figures

Figure 1

15 pages, 5907 KiB

Open AccessArticle

Estimation of Leaf Nitrogen Content in Wheat Based on Fusion of Spectral Features and Deep Features from Near Infrared Hyperspectral Imagery

by Baohua Yang, Jifeng Ma, Xia Yao, Weixing Cao and Yan Zhu

Sensors 2021, 21(2), 613; https://doi.org/10.3390/s21020613 - 17 Jan 2021

Cited by 22 | Viewed by 2979

Abstract

Nitrogen is an important indicator for monitoring wheat growth. The rapid development and wide application of non-destructive detection provide many approaches for estimating leaf nitrogen content (LNC) in wheat. Previous studies have shown that better results have been obtained in the estimation of [...] Read more.

Nitrogen is an important indicator for monitoring wheat growth. The rapid development and wide application of non-destructive detection provide many approaches for estimating leaf nitrogen content (LNC) in wheat. Previous studies have shown that better results have been obtained in the estimation of LNC in wheat based on spectral features. However, the lack of automatically extracted features leads to poor universality of the estimation model. Therefore, a feature fusion method for estimating LNC in wheat by combining spectral features with deep features (spatial features) was proposed. The deep features were automatically obtained with a convolutional neural network model based on the PyTorch framework. The spectral features were obtained using spectral information including position features (PFs) and vegetation indices (VIs). Different models based on feature combination for evaluating LNC in wheat were constructed: partial least squares regression (PLS), gradient boosting decision tree (GBDT), and support vector regression (SVR). The results indicate that the model based on the fusion feature from near-ground hyperspectral imagery has good estimation effect. In particular, the estimation accuracy of the GBDT model is the best (R² = 0.975 for calibration set, R² = 0.861 for validation set). These findings demonstrate that the approach proposed in this study improved the estimation performance of LNC in wheat, which could provide technical support in wheat growth monitoring. Full article

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Sensing Technology in Smart Agriculture

Share This Topical Collection

Editors

Topical Collection Information

Keywords

Published Papers (12 papers)

2024

Jump to: 2023, 2022, 2021

2023

Jump to: 2024, 2022, 2021

2022

Jump to: 2024, 2023, 2021

2021

Jump to: 2024, 2023, 2022

Further Information

Guidelines

MDPI Initiatives

Follow MDPI