Computers and Electronics in Agriculture最新文献

{"title":"Validation of an indoor real-time location system for tracking sheep","authors":"","doi":"10.1016/j.compag.2024.109535","DOIUrl":"10.1016/j.compag.2024.109535","url":null,"abstract":"<div><div>Precision livestock technologies such as remote sensors are increasingly used to monitor the health, behavior, and welfare of livestock. We aimed to evaluate the performance of a commercially available ultra-wideband real-time location system (UWB RTLS) for tracking the 2D spatial locations and distances traveled by meat-breed ewes and lambs in an indoor barn. First, we assessed static performance by attaching the sensors to stationary posts and arranging them in a 1 × 1 m grid throughout the barn (29.0 × 11.8 m) for a total of 285 locations. At each post location, the sensors were placed at approximate ewe (0.9 m) and lamb (0.3 m) wither height. The precise 2D locations of each post were recorded using a laser tape measurer and used as the ground truth for comparison to the RTLS’ recorded <em>x</em> and <em>y</em> coordinates. Secondly, we conducted a dynamic validation test to evaluate the positional error and percent error of distances traveled while the sensors were worn by six free-roaming ewes and their singleton lambs. The ground truth locations of each sheep were recorded from video frames every second over 15 min and compared to the RTLS data. Overall static and dynamic error was 0.39 ± 0.20 m (mean ± SD) and 0.53 ± 0.31 m, respectively. Static error was lower in sensors positioned at lamb height than at ewe height, but the opposite pattern was true for dynamic error. Error was higher in pens further from the master anchor. Ground truth and RTLS distances traveled were positively correlated but the RTLS overestimated distances by 54 % on average. In conclusion, the UWB RTLS can acquire precise location estimates that are suitable for a range of scientific and practical applications, but distance estimates should be adjusted to account for overestimation.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of an autonomous drone spraying control system based on the coefficient of variation of spray distribution","authors":"","doi":"10.1016/j.compag.2024.109529","DOIUrl":"10.1016/j.compag.2024.109529","url":null,"abstract":"<div><div>Pests and disease prevention has long been a key area of focus in precision agriculture research. While unmanned aerial spraying systems have advanced significantly and gained widespread adoption in recent years, challenges persist, including the high cost of precision spraying drones and issues related to uneven spraying and over-application with conventional systems. To address these limitations, this paper introduces a low-cost, versatile, and modular autonomous spraying control system that includes a ground base station and a spraying control assistant. The system integrates a spraying uniformity control algorithm based on a regression forest model, ensuring a coefficient of variation (CV) below 30 %. It also collects real-time environmental data to optimize the drone’s spraying strategy. Environmental data and global positioning system’s correction signals are transmitted from the ground base station to the onboard spraying control system (mobile station) via LoRa communication, enabling precise positioning and real-time adjustments during spraying. Indoor spraying simulation experiments demonstrate that the autonomous spraying control system achieved a CV within the standardized requirement in 15 out of 23 trials, with an overall predicted CV of less than 30 %. In outdoor experiments, using a hypothetical prescription map for targeted precision spraying, the system successfully completed all prescribed spraying zones. All targeted zones met directed spraying performance indicators exceeding 0.87, demonstrating high accuracy. The system shows significant potential for enhancing the precision spraying capabilities of conventional drones while reducing pest and disease control costs.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated retrieval of cattle body measurements from unmanned aerial vehicle-based LiDAR point clouds","authors":"","doi":"10.1016/j.compag.2024.109521","DOIUrl":"10.1016/j.compag.2024.109521","url":null,"abstract":"<div><div>Accurate body measurements are crucial for effective management of cattle growth in precision livestock farming. This study introduces a novel noncontact approach that leverages point clouds acquired by unmanned aerial vehicle (UAV) based LiDAR to obtain body measurements of cattle within their natural husbandry conditions. The experiment encompasses 36 LiDAR scanning campaigns, six during the nighttime, using various combinations of flight speed and height. An automated procedure for retrieving body measurements is applied to pre-processed cattle point clouds, with a total of 276 individual animals segmented from campaign-generated point clouds using an automated segmentation procedure. The procedure uses identified body-marks to extract six body measurements from each cattle point cloud. To enhance the accuracy of the extracted body measurement dataset, multivariate analysis of variance (MANOVA) is used, facilitating the adjustment of the dataset that excludes data derived at flight heights of <span><math><mrow><mn>30</mn><mspace></mspace><mi>m</mi></mrow></math></span> and <span><math><mrow><mn>50</mn><mspace></mspace><mi>m</mi></mrow></math></span> or flight speeds of <span><math><mrow><mn>7</mn><mspace></mspace><mi>m/s</mi></mrow></math></span> and <span><math><mrow><mn>9</mn><mspace></mspace><mi>m/s</mi></mrow></math></span>. The reference dataset validates the adjustment effectiveness, demonstrating substantial reductions in mean absolute error (MAE), such as the vertical gap measurement (<span><math><mrow><mi>h</mi><mn>1</mn></mrow></math></span>) on reference objects, from <span><math><mrow><mn>2</mn><mspace></mspace><mi>cm</mi></mrow></math></span> to <span><math><mrow><mn>2</mn><mspace></mspace><mi>mm</mi></mrow></math></span>. Furthermore, the study delves into anatomical hip height (HH’) estimation by developing a 10-fold cross-validation linear regression model based on the training dataset of 136 pairs of waist height and hip height (HH) derived with a manually added auxiliary plane. The model yields the estimation of the HH’ with <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.84, MAE of <span><math><mrow><mn>0</mn><mo>.</mo><mn>012</mn><mspace></mspace><mi>m</mi></mrow></math></span>, and RMSE of <span><math><mrow><mn>0</mn><mo>.</mo><mn>015</mn><mspace></mspace><mi>m</mi></mrow></math></span>. Moreover, this study proposes a dual rotation algorithm to normalise cattle head orientation. The results of this study contribute to the advancement of using UAV-based LiDAR for cattle growth management.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heat transfer modeling with fixed and mobile heaters for frost protection in apple orchards","authors":"","doi":"10.1016/j.compag.2024.109525","DOIUrl":"10.1016/j.compag.2024.109525","url":null,"abstract":"<div><div>Effective heating is important for protection of commercial crops from frost. In this study, a three-dimensional computational fluid dynamics (CFD) orchard model was developed to predict temperature distributions in an apple orchard from two forced air heaters under different wind conditions and fixed heating layouts. The simulated results show that placing heaters angled upwind had a larger average volume percentage of protected canopy (VPPC) than angled downwind. Reducing the interaction of heat flows between heaters improved the average canopy temperature (ACT) and VPPC in the fixed heating layouts. However, the proposed fixed heating layouts provided insufficient protection performance of the canopy with only a maximum VPPC of 32.2%. A mobile heating case <em>i.e.,</em> moving the heaters from one end of the tree row to the other, was modeled based on a moving mesh simulation. Quantitative comparisons between the mobile heating case and three fixed heating cases, <em>i.e.,</em> placing the heaters angled 45° at one end of the tree row, the middle of the tree row, and the other end of the tree row were conducted. The results show that the simulated VPPC for the mobile heating case increased by 1,180.0% compared to the first fixed heating cases, and 141.5% compared to the second and third fixed heating cases.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Oil palm tree detection in UAV imagery using an enhanced RetinaNet","authors":"","doi":"10.1016/j.compag.2024.109530","DOIUrl":"10.1016/j.compag.2024.109530","url":null,"abstract":"<div><div>Accurate inventory management of oil palm trees is crucial for optimizing yield and monitoring the health and growth of plantations. However, detecting and counting oil palm trees, particularly young trees that blend into complex environments, presents significant challenges for deep learning models. While current methods perform well in detecting mature oil palm trees, they often struggle to generalize across the diverse variations found in both young and mature trees. In this study, we propose an enhanced RetinaNet model that incorporates deformable convolutions into the ResNet-50 backbone, deeper feature pyramid layers, and an intersection-over-union-aware branch in a multi-head configuration to improve detection performance. The model was evaluated using a diverse dataset of unmanned aerial vehicle imagery from multiple regions, encompassing oil palm and coconut trees, as well as banana plants. To refine detection, confidence thresholding and non-maximum suppression were applied during inference, filtering out low-confidence predictions and eliminating duplicate detections. Experimental results demonstrate that our method outperforms state-of-the-art models, achieving F1-scores of 0.947 and 0.902 for single- and dual-species detection tasks, respectively, surpassing existing approaches by 1.5–6.3%. These findings highlight the model’s ability to accurately detect oil palm trees, particularly young ones in complex backgrounds, offering a reliable solution to support sustainable agriculture and improved land management.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tomato fruit detection and phenotype calculation method based on the improved RTDETR model","authors":"","doi":"10.1016/j.compag.2024.109524","DOIUrl":"10.1016/j.compag.2024.109524","url":null,"abstract":"<div><div>Rapid detection of tomato fruits and accurate acquisition of phenotypic traits are of great significance for robotic automatic picking control, yield prediction, and variety breeding. Tomato fruits are often densely distributed in a complex canopy and obscured by branches and leaves, making it difficult to accurately detect tomato fruits and obtain phenotypic traits without damage. This paper proposes an automatic detection method for tomatoes based on an improved RTDETR model. Firstly, on the basis of the self-made calibration plate, the color image sensor is used to acquire the tomato image. Then, a CASA structure consisting of three modules: Multiscale Dilated Convolution (MDC), Focused Feature Downsampler (FFD) and Adaptive Feature Upsampler (AFU) was designed and embedded into the Neck structure of the RTDETR network to construct a tomato fruit detection method based on the improved RTDETR model. Finally, by integrating machine learning and graphics processing technology, a fruit color extraction method was established based on the CIELAB color space, a fruit diameter calculation method based on edge detection and Hough transform, and a fruit weight and circumference measurement method based on statistical regression models. The experimental results show that the <span><math><mrow><mi>m</mi><mi>A</mi><mi>P</mi><mi>_</mi><mn>0.5</mn></mrow></math></span> of the tomato fruit detection model established in this paper reaches 0.86, which is 3% higher than the original model; The correlation coefficient between the calculated and measured values of the horizontal and vertical diameters of the fruit was 0.79, and the mean square error (<span><math><mrow><mi>MSE</mi></mrow></math></span>) of the weight and circumference of the fruit was 0.26 and 0.27, respectively. This achievement has realized an accurate, lossless, and fast method for tomato fruit detection and phenotype calculation, providing quantitative reference indicators for fruit detection, positioning, and control of tomato automatic picking robots, and can provide technical support and guarantee for crop yield prediction and variety breeding.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing crop model parameter estimation across computing environments: Utilizing the GLUE method and parallel computing for determining genetic coefficients","authors":"","doi":"10.1016/j.compag.2024.109513","DOIUrl":"10.1016/j.compag.2024.109513","url":null,"abstract":"<div><div>Estimating genetic coefficients is essential to accurately simulate crop development and growth for modeling studies but has been challenging due to lack of robust and fast procedures. While there are several optimization techniques, the Generalized Likelihood Uncertainty Estimation (GLUE) is a Bayesian method that is popular among the modeling community due to its application for sensitivity and uncertainty analysis and capability to explore the global parameter space. However, the time required for its search method to estimate the optimal parameter set is a significant constraint and limitation. Parallel computing has emerged as a solution to boost the efficiency of genetic coefficient calibration using GLUE. In this study, we introduce a new system that leverages parallel computing for calibrating genetic inputs for crop growth models within the Cropping System Model (CSM) of the Decision Support System for Agrotechnology Transfer (DSSAT). Designed and tested for both conventional and High-Performance Computing (HPC) environments, the Generalized Likelihood Uncertainty Estimation Parallelized (GLUEP) is available for most crops that are simulated with DSSAT-CSM and provides a user-friendly graphical interface within the DSSAT software. It accelerates the genetic-specific parameter calibration process and adds new functionality that enables users to optimize intrinsic model parameters, which were previously unavailable for calibration purposes. Four case studies using cultivars for wheat, maize, soybean, and potato showcase the application of GLUEP. We also conducted a comparison with DSSAT-GLUE and evaluated the performance gains of GLUEP for multiple operational systems, including Windows, MacOS, and Linux, as well as under conventional and HPC environments. The multi-core processing results indicate performance improvements across all computer systems that were analyzed. The comparison between the sequential processing of DSSAT-GLUE and the parallel processing of GLUEP indicates a reduction in execution time ranging from 87.4% to 95.4%. These results highlight the GLUEP capabilities in streamlining the calibration process, enabling more efficient and accurate predictions for crop growth modeling studies.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hob-type smart weeding machine for use in wheat fields: Towards a low power consumption and high-efficiency design","authors":"","doi":"10.1016/j.compag.2024.109519","DOIUrl":"10.1016/j.compag.2024.109519","url":null,"abstract":"<div><div>Smart weeding machine is an important tool for control of farmland weeds. To solve the high power consumption, low weeding rate, and high seedling damage rate of existing smart weeding machine in wheat fields, a power consumption model was established for the weed-soil- machine interactions process and a hob-type smart weeding machine of wheat fields was designed. The cutting-edge angle, roller radius, number of hob blades, and hob blade thickness were separately 20°, 85 mm, 8, and 2 mm. A three-dimensional (3-d) structural model of the hob-type smart weeding machine was established on ProE and the operation process of the smart weeding machine’s actuator was dynamically simulated in the discrete element method environment. On this basis, changes in performance indices including the operating width, operating depth, soil-throwing width, accumulation thickness, and average power consumption during the operation were investigated. Field tests of the hob-type smart weeding machine show that the operation width is 202.8 mm, which covers the inter-row area in wheat fields; the operation depth is 36 mm, at which roots of most weeds in wheat fields can be cut or pulled out; the soil-throwing width is 304.2 mm and the accumulation thickness is not higher than 20 <!--> <!-->mm, which is much lower than the height of wheat plants in the tillering stage. The average power during operation is 197.70 W, the weeding rate is 98.93 % and the seedling damage rate is 4.35 %. Compared to existing weeding machines reported, when the weed removal rates are similar, the power consumption of the weeding actuator developed in this study for wheat fields is reduced by approximately 54 %. On the premise of a comparable seedling damage rate, the weeding rate is increased by approximately 10 %, demonstrating notable characteristics of low power consumption and high efficiency.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of agrifood supply chains using Hyperledger Fabric blockchain technology","authors":"","doi":"10.1016/j.compag.2024.109503","DOIUrl":"10.1016/j.compag.2024.109503","url":null,"abstract":"<div><div>Blockchain technology shows significant promise for addressing challenges within the agri-food supply chain. However, the effective application of blockchain platforms in this context is still an area of research. This study proposes a blockchain-based system that uses Hyperledger Fabric to manage agri-food supply chains based builder design patterns. The main focus is on preserving relationships, authorizations, and accurate traceability of food products throughout the supply chain. The system takes into account the various stakeholders involved in the food supply chain to ensure coordination and efficiency. It integrates multiple security mechanisms to enhance security and enforce adherence to chaincode, preventing unauthorised access to critical data or operations. Additionally, ownership and validity checks are incorporated for agreement issuance and asset generation, providing credentials for the legitimacy of linked agreements and organisational authorisation. The proposed system improves the security and integrity of the supply chain by using one-time agreements, which mitigates the risk of replay attacks or malicious activity. A web platform has been proposed to give users real-time visibility of a package’s movement through the supply chain. This enables access to a detailed chronology of the product’s movement and delivery steps by scanning the package’s QR code. The proposed system is evaluated for performance using the Caliper tool to measure network throughput and transaction latency, which demonstrates the feasibility and efficiency of Hyperledger Fabric in optimising agri-food supply chains.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pythagorean fuzzy SWARA weighting technique for soil quality modeling of cultivated land in semi-arid terrestrial ecosystems","authors":"","doi":"10.1016/j.compag.2024.109466","DOIUrl":"10.1016/j.compag.2024.109466","url":null,"abstract":"<div><div>Currently, the assessment of soil quality and creating digital soil maps are crucial for sustainable land management. In the present study, the main objective is to evaluate soil quality around Lake Van’s agricultural areas using Pythagorean Fuzzy SWARA (PF-SWARA) weighting for soil indicator assessment. Additionally, the predictability of soil quality is demonstrated through spatial distribution maps using random forest (RF) and artificial neural network (ANN) algorithms. PF-SWARA weighting assigns higher weights to indicators of physical quality. Soil quality index (SQI) values for the study area range between 0.36 and 0.74, classified as “from very low to high.” RF and ANN models provide Lin’s concordance correlation coefficient (LCCC) values of 0.93 and 0.87, respectively, for soil quality prediction. The RF model exhibits the lowest error rate (root mean square error (RMSE): 0.03; mean absolute percentage error (MAPE): 4.51%). The RF algorithm identified pH, available phosphorus, organic matter, CaCO₃ and electrical conductivity as the most effective soil properties for estimating SQI. Ordinary Kriging geostatistical interpolation is identified as the interpolation method with the lowest RMSE value based on observed and predicted values’ spatial distribution maps using Gaussian semivariogram from the geostatistical model. The study concludes that machine learning algorithms can be utilized alongside PF-SWARA approaches for digital soil quality mapping.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}