首页期刊导航|Computers and Electronics in Agriculture
期刊信息/Journal information
Computers and Electronics in Agriculture
Elsevier Science Publishers
Computers and Electronics in Agriculture

Elsevier Science Publishers

0168-1699

Computers and Electronics in Agriculture/Journal Computers and Electronics in AgricultureSCIEIISTP
正式出版
收录年代

    Simulation and parameter optimisation of pickup device for full-feed peanut combine harvester

    Wang S.Wang Y.Hu Z.Yao L....
    9页
    查看更多>>摘要：? 2021To reduce the pickup and pod drop losses of peanut picking combine harvesters, and to improve the quality of pickup work, a peanut pickup device is designed and a kinematics simulation analysis is conducted using ADAMS software in this study. According to the simulation analysis of the different ratio (λ) of the rotary linear speed of the spring-finger end to the forward speed of the harvester, the motion trajectory diagram of the spring-finger end was obtained, and the reasonable value range for λ was λ > 1. Through the simulation analysis of the missed pickup zone for different spring-finger rows, six was determined as a reasonable number of spring-finger rows. On this basis, the multi-index field orthogonal tests were performed with the pickup and pod drop rate as the performance indexes. The forward speed of the harvester, rotary angular speed of the spring-finger, and bend angle of the spring-fingertip were considered as the test factors. The test results showed that the pickup rate was positively correlated with the value of λ. When λ ≤ 1, the pickup rate was<95 %; when λ > 1, the pickup rate increased gradually with the increase in λ and tended to be constant, which is consistent with the simulation analysis results. There was no positive correlation between the pod drop rate and λ value. A comprehensive scoring method was employed to evaluate and analyse the two performance indexes to determine the optimal parameter combination: when the harvester's forward speed was 1.0 m/s, with a rotary angular speed of 4 rad/s, and spring-fingertip bend angle at 150°, the comprehensive pickup performance was optimum (with a comprehensive test score of 0.106). This study can provide relevant technical references for the research of both peanut pickup combine harvesters and rape and forage pickup devices.
      原文链接:
    • NSTL
    • Elsevier

    An intelligent system for crop identification and classification from UAV images using conjugated dense convolutional neural network

    Pandey A.Jain K.
    13页
    查看更多>>摘要：? 2021 Elsevier B.V.Crop identification and classification is an important aspect for modern agricultural sector. With development of unmanned aerial vehicle (UAV) systems, crop identification from RGB images is experiencing a paradigm shift from conventional image processing techniques to deep learning strategies because of successful breakthrough in convolutional neural networks (CNNs). UAV images are quite trustworthy to identify different crops due to its higher spatial resolution. For precision agriculture crop identification is the primal criteria. Identifying a specific type of crop in a land is essential for performing proper farming and that also helps to estimate the net yield production of a particular crop. Previous works are limited to identify a single crop from the RGB images captured by UAVs and have not explored the chance of multi-crop classification by implementing deep learning techniques. Multi crop identification tool is highly needed as designing separate tool for each type of crop is a cumbersome job, but if a tool can successfully differentiate multiple crops then that will be helpful for the agro experts. In contrast with the previous existing techniques, this article elucidates a new conjugated dense CNN (CD-CNN) architecture with a new activation function named SL-ReLU for intelligent classification of multiple crops from RGB images captured by UAV. CD-CNN integrates data fusion and feature map extraction in conjunction with classification process. Initially a dense block architecture is proposed with a new activation function, called SL-ReLU, associated with the convolution operation to mitigate the chance of unbounded convolved output and gradient explosion. Dense block architecture concatenates all the previous layer features for determining the new features. This reduces the chance of losing important features due to deepening of the CNN module. Later, two dense blocks are conjugated with the help of a conversion block for obtaining better performance. Unlike traditional CNN, CD-CNN omits the use of fully connected layer and that reduces the chance of feature loss due to random weight initialization. The proposed CD-CNN achieves a strong distinguishing capability from several classes of crops. Raw UAV images of five different crops are captured from different parts of India and then small candidate crop regions are extracted from the raw images with the help of Arc GIS 10.3.1 software and then the candidate regions are fed to CD-CNN for proper training purpose. Experimental results show that the proposed module can achieve an accuracy of 96.2% for the concerned data. Further, superiority of the proposed network is established after comparing with other machine learning techniques viz. RF-200 and SVM, and standard CNN architectures viz. AlexNet, VGG-16, VGG-19 and ResNet-50.
      原文链接:
    • NSTL
    • Elsevier

    Identifying causes of crop yield variability with interpretive machine learning

    Jones E.J.Bishop T.F.A.Whelan B.M.Filippi P....
    10页
    查看更多>>摘要：? 2021 Elsevier B.V.Machine learning approaches have been widely used for crop yield modelling and yield forecasting but there has been limited application to understanding site-specific yield constraints. Crop yield is driven by a complex interaction of spatial and temporal variables, which makes it challenging to define the exact cause of observed spatial yield variability explicitly. This makes it difficult to design efficient management strategies to address production constraints. There is a need for a more quantitative and systematic approach to identify and understand the causes of variation in crop yield in order to implement appropriate management responses. This study investigated the use of interpretive machine learning (IML) to address this need. The developed methodology was demonstrated on furrow-irrigated cotton fields totalling ～2000 ha in the Condamine-Balonne River catchment, Australia. Digital soil maps of important soil constraints were created at 20 m spatial resolution using 70 soil cores extracted to 1.4 m depth and a combination of on-farm and off-farm spatial data layers. Specifically, the soil constraints represented were exchangeable sodium percentage (ESP – sodicity), pH (alkalinity), and electrical conductivity (ECe – salinity). Terrain infrastructure variable maps of closed depressions, distance down furrow, and cut and fill (from landforming practices) were also developed. Empirical models of cotton lint yield were created with gradient boosted decision trees (XGBoost) using the digital soil maps and terrain infrastructure data as predictor variables. The models could describe the spatial variation in yield well, with a median Lin's concordance correlation coefficient of 0.67 and root-mean-square error of 0.75b ha?1. SHapley Additive exPlanations (SHAP), an IML approach based on game theory, was then used to identify the contribution of each variable to the modelled yield across the study area. The variable most decreasing yield at each point was identified and mapped across the study area, and the spatial extent represented by each variable quantified. The SHAP values for each predictor variable were also extracted and mapped for a case study field, which demonstrated the magnitude of the impact of each variable on yield with spatial context in easily interpretable units (b ha?1). The presented methodology is promising for cost-benefit analysis of implementing remediation strategies, or where not economically feasible, altering management inputs according to a constrained yield potential.
      原文链接:
    • NSTL
    • Elsevier

    Employing artificial neural network for effective biomass prediction: An alternative approach

    Guner S.T.Diamantopoulou M.J.Poudel K.P.Comez A....
    11页
    查看更多>>摘要：? 2021 Elsevier B.V.Wood products and energy production originating from harnessing the tree biomass require optimizing the forest management process so as to ensure the sustainability of the forest ecosystems. This optimization can also act as a preventive factor towards limiting the consequences of climate change given it is a contributing factor for maintaining healthy ecosystems. To that end, the need to develop methodologies that enable accurate prediction of biomass is more than evident. Nonlinear seemingly unrelated regressions, Dirichlet regressions, and the Levenberg-Marquardt artificial neural network (LMANN) modeling techniques have been applied for whole tree (above and below ground) biomass prediction as well as its components. We conducted a comparative analysis of these approaches using destructively sampled black pine (Pinus nigra Arnold.) trees. Results showed that the LMANN models are flexible and fit tree biomass data with the highest accuracy. Inherent deviations of the biomass data from regression assumptions further support the use of LMANN models as a reliable and promising alternative to the other modeling approaches.
      原文链接:
    • NSTL
    • Elsevier

    A real-time branch detection and reconstruction mechanism for harvesting robot via convolutional neural network and image segmentation

    Wan H.Fan Z.Yu X.Kang M....
    12页
    查看更多>>摘要：? 2021 Elsevier B.V.To alleviate the burden of fruit harvesting imposed by rising costs and decreasing labor supply, intelligent robots are highly desired in modern farms. A major problem, however, is how to detect and locate the tree branches for the robots to plan their arm movements during harvesting process. This study addresses the obscured branch detection and reconstruction problem, and proposes a real-time branch detection and reconstruction (RBDR) mechanism using convolutional neural networks (CNNs) and image processing techniques. Firstly, we build a Branch-CNN framework for detecting the bare branches and complete their rough localization, and then, realize the background segmentation in HSV space to obtain the precise branch regions. Finally, with the distance and angle constraints considered, a polynomial fit is conducted onto the precise boxes of the same branch to fill in the obscured areas. The proposed RBDR mechanism is applied onto a harvesting robot platform, and experiments with both lab simulated orchard environment and real pomegranate tree environment are conducted to verify its feasibility. Results show that under the simulation environment, at an Intersection over Union (IOU) threshold of 0.5, Branch-CNN achieves the best overall performance, with the average detection precision, recall rate, and F1-Score being 90.98%, 92%, and 91%, respectively, and the average reconstruction accuracy of RBDR is 88.76%. Under the real pomegranate tree environment, Branch-CNN achieves 90.7% detection precision, 89% recall rate, and 90% F1-Score, respectively. The overall reconstruction speed of RBDR is 22.7 frames per second (FPS) on image with a resolution of 960*720. Such results fully demonstrate the rationality and effectiveness of RBDR.
      原文链接:
    • NSTL
    • Elsevier

    Real-time adaptation of a greenhouse microclimate model using an online parameter estimator based on a bat algorithm variant

    Megherbi H.Guesbaya M.Garcia-Manas F.Rodriguez F....
    19页
    查看更多>>摘要：? 2021 Elsevier B.V.Greenhouse microclimate modelling is a difficult task mainly due to the strong nonlinearity of the phenomenon and the uncertainty of the involved physical and non-physical parameters. The uncertainty stems from the fact that the majority of these parameters are unmeasurable or difficult to be measured and some of them are time-varying, signifying the necessity to estimate them. In this paper, a methodology for online parameter estimation is proposed to deal with the estimation of the time-varying parameters of a simplified greenhouse temperature model for real-time model adaptation purposes. An online estimator is developed based on an enhanced variant of the Bat Algorithm called the Random Scaling-based Bat Algorithm. It allows the continuous adaptation of the internal air temperature model and the internal solar radiation sub-model, through estimating their parameters at the same time step by minimizing a cost function, intending to achieve global optimality. Constraints on the search ranges are imposed to respect the physical sense. The adaptation of the models was tested with recorded datasets of different agri-seasons and on a real greenhouse in real time. The evolutions of the time-varying parameters were graphically presented and thoroughly discussed. The experimental results illustrate the successful model adaptation, presenting an average error of less than 0.28 °C for air temperature prediction and 20Wm-2 for solar radiation simulation. This proves the usefulness of the proposed methodology under changing environmental conditions.
      原文链接:
    • NSTL
    • Elsevier

    Real-time strawberry detection using deep neural networks on embedded system (rtsd-net): An edge AI application

    Zhang Y.Yu J.Yang W.Zhang W....
    12页
    查看更多>>摘要：? 2021 Elsevier B.V.Computer vision is a key technique to make agricultural machinery smart. Deep neural network has achieved great success in computer vision. How to use it at a small size, low cost, low power consumption device with high accuracy and speed on strawberry harvesting machinery has drawn much research attention. Since the infield situation has reduced number of objects and that they are easier to be distinguished from the background compared to other computer vision datasets, the huge neural network structure can be simplified in order to speed up the detection inference without penalizing the detection accuracy. In this research, a new deep neural network called RTSD-Net is proposed based on stat-of-art light-weighted YOLOv4-tiny with reduced layers and modified structure for real-time strawberry detection under infield condition. The original CSPNet was replaced by 2 types of CSPNet designed with reduced parameters and a simplified structure and 4 new network structures are designed by combining these 2 types. The performances of the 4 networks were evaluated. It was observed that the number of parameters of these 4 networks and the detection speed of the model is negatively correlated. Simplified structure and reduced parameters can contribute to faster operational speed. The last one was selected and named as RTSD-Net. Comparing with YOLOv4 tiny, the accuracy of RTSD-Net is only reduced by 0.62% but the speed is increased by 25FPS, which is 25.93% higher than that of YOLOv4-tiny. Embedded system Jetson Nano was selected as the evaluation platform to evaluate the RTSD-Net's performance for edge computing. The original Open Neural Network Exchange (ONNX) model was loaded on Jetson Nano and the speed of RTSD-Net was 13.1FPS, which is 19.0% higher than that of YOLOv4-tiny. After speeded up by TensorRT method, the transformed model reached 25.20fps, which is twice as fast as the ONNX model, and 15% faster than the YOLOv4-tiny model. After speeding up, the efficiency of RTSD-Net is enough for computer vision based strawberry detection and harvesting. In summary, the proposed RTSD-Net has good potential in smart strawberry harvesting machinery and the idea of redesigning neural structure and reducing parameters to speed up the detection rate of deep neural network is expected to have good application in edge computing.
      原文链接:
    • NSTL
    • Elsevier

    Semantics-guided skeletonization of upright fruiting offshoot trees for robotic pruning

    You A.Grimm C.Davidson J.R.Silwal A....
    17页
    查看更多>>摘要：? 2021 Elsevier B.V.Dormant pruning for fresh market fruit trees is a relatively unexplored application of agricultural robotics for which few end-to-end systems exist. One of the biggest challenges in creating an autonomous pruning system is the need to reconstruct a model of a tree which is accurate and informative enough to be useful for deciding where to cut. One useful structure for modeling a tree is a skeleton: a 1D, lightweight representation of the geometry and the topology of a tree. This skeletonization problem is an important one within the field of computer graphics, and a number of algorithms have been specifically developed for the task of modeling trees. These skeletonization algorithms have largely addressed the problem as a geometric one. In agricultural contexts, however, the parts of the tree have distinct labels, such as the trunk, supporting branches, etc. This labeled structure is important for understanding where to prune. We introduce an algorithm which uses topological and geometric priors about Upright Fruiting Offshoot (UFO) trees to produce such a labeled skeleton. We test our skeletonization algorithm on point clouds from 29 UFO trees and, using an accuracy metric based on the number of correctly reconstructed and labeled skeleton segments, demonstrate a median construction accuracy of 70% with respect to a human-evaluated gold standard. We also make point cloud scans of 82 UFO trees open-source to other researchers. Our work represents a significant first step towards a robust tree modeling framework which can be used in an autonomous pruning system.
      原文链接:
    • NSTL
    • Elsevier

    Designing, manufacturing, and evaluating the diagnostic system of carob moth in pomegranate fruit using digital signal processing

    Janati S.Abdanan Mehdizadeh S.Heydari M.
    10页
    查看更多>>摘要：? 2021 Elsevier B.V.Sound analysis is one of the least destructive testing methods that have been developed for the determination of fruit quality. Therefore, in this research, a system was developed for analyzing the acoustic impulse response to determine the presence of carob moths in pomegranate fruit. For this purpose, acoustic signals generated from 100 pomegranate fruits were recorded (50 healthy and 50 infected). In order to record and extract the acoustic signals' characteristics (non-destructive test), a plastic pendulum hit the samples at three speeds (0.3, 0.9, and 1.5 m/s) and a microphone was located at three positions concerning impactor (0, 90, and 180°). For data classification, Fisher's linear discriminant classifier combined with three different feature selection methods was used. According to the statistical analysis, a speed of 0.9 m/s was selected as the optimum impact velocity. According to the classification results, the best features were natural frequency, spectral entropy, and zero-crossing, which had the least classification error. The application of these three features resulted in a classification accuracy of 97.55%.
      原文链接:
    • NSTL
    • Elsevier

    AdaHC: Adaptive hedge horizontal cross-section center detection algorithm

    Li Z.Zhang J.Meng Y.Wei J....
    10页
    查看更多>>摘要：? 2021Finding the center point of the hedge is the key to automated pruning. In a complex outdoor environment, since the horizontal cross-section of the hedge is not a regular circle, and has many approximate circular contours, the performance of mainstream circle detection algorithms is not ideal. To this end, we propose an adaptive hedge horizontal cross-section center detection algorithm, named AdaHC, which can obtain the horizontal cross-section center coordinates of the hedge in real time by inputting the top view image of the hedge. The experimental results show that our proposed algorithm is significantly better than other circle detection algorithms. Its recognition accuracy can reach 100%, the average accuracy is over 80% (corresponding to an accuracy of 1 cm), and the average time consumption is 11.6 ms, be robust to the variations in light, hedge color, and background, fully meets the industrial requirements, and lays a good foundation for automatic hedge trimming.
      原文链接:
    • NSTL
    • Elsevier