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

    Special report: The Internet of Things for Precision Agriculture (IoT4Ag)

    Cappelleri D.J.Keske C.M.Turner K.T.Kagan C.R....
    6页
    查看更多>>摘要：? 2022 Elsevier B.V.The National Science Foundation (NSF) Engineering Research Center (ERC) for the Internet of Things for Precision Agriculture (IoT4Ag) was established on September 1, 2020 and launched its collaborative programs across the four NSF ERC pillars of convergent research, engineering workforce development, diversity and culture of inclusion, and innovation ecosystem. IoT4Ag unites an interdisciplinary cadre of faculty and students from the University of Pennsylvania, Purdue University, the University of California-Merced, and the University of Florida, with partners in education, government, industry, and the end-user farming community. The IoT4Ag mission is to create and translate to practice Internet of Things (IoT) technologies for precision agriculture and to train an educated and diverse workforce that will address the societal grand challenge of food, energy, and water security for decades to come.
      原文链接:
    • NSTL
    • Elsevier

    LodgeNet: Improved rice lodging recognition using semantic segmentation of UAV high-resolution remote sensing images

    Su Z.Wang Y.Xu Q.Gao R....
    14页
    查看更多>>摘要：? 2022 Elsevier B.V.Rice lodging not only causes difficulty in harvest operations, but also drastically reduces yield. Therefore, it is very important to identify rice lodging efficiently. For unmanned aerial vehicle (UAV) remote sensing images, this paper combines the advantages of dense block, DenseNet, attention mechanism, and jump connection on the basis of U-Net network to propose an end-to-end, pixel-to-pixel semantic segmentation method to identify rice lodging. And the method can process the input multi-band image. The accuracy of the model proposed in this paper was 97.30% on rice lodging images, which performed better than other comparison methods in the test. At the same time, it has good effect on small sample data set. The results show that it is feasible to use the improved U-Net network model to extract the lodging area of rice, which provide a useful reference for rice breeding and agricultural insurance claims.
      原文链接:
    • NSTL
    • Elsevier

    Improving leaf area index estimation accuracy of wheat by involving leaf chlorophyll content information

    Jia K.Xia M.Yao Y.Zhang X....
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.Red-edge band is widely used for LAI estimation as it is highly correlated to vegetation growth conditions. Canopy reflectance is affected by both vegetation biophysical and biochemical characteristics. However, estimating LAI using satellite reflectance data as input rarely considers the influence of leaf chlorophyll content (LCC). This study tested the hypothesis whether LAI estimation accuracy can be improved by involving LCC information. Firstly, the sensitivities of seven PROSAIL simulated Sentinel-2 bands to LAI and LCC were investigated, and related vegetation indices (VIs) were constructed using these sensitive bands (including LAI-sensitive VIs and LCC-sensitive VIs). Then, the LAI estimation model taking sensitive VIs as input and LCC estimation model taking sensitive VIs as input were generated by random forest regression algorithm. Finally, the improved LAI estimation model involving LCC information was proposed using three different methods: (1) PROSAIL simulated LCC, (2) simulated LCC with noise, and (3) functional equation of LCC. The results indicated that the three LCC information introducing methods all improved the LAI estimation accuracy, while using the functional equation of LCC (growth equation) performed best with RMSE of 0.736, which is 11.54% higher when compared to the basic LAI estimation model.
      原文链接:
    • NSTL
    • Elsevier

    Acoustic sensor determination of repeatable cow urinations traits in winter and spring

    Shorten P.R.Welten B.G.
    13页
    查看更多>>摘要：? 2022 Elsevier B.V.Urinary nitrogen (N) excreted by grazing ruminants is the predominant source of N loss from pasture-grazed agricultural systems. The aim of this study was to use cow-attached acoustic sensors to measure the between-cow repeatability in the frequency, flow rate, duration, volume and N load of urination events from 140 grazing cattle in winter and spring. The urination event classifier had an F1 statistic of 0.946 based on 6122 urination events from 215 cows in the calibration dataset. The performance statistics for the validation of the urination event classifier were F1 = 0.91 (range 0.89–0.96 between trials), precision = 0.98 (range 0.93–0.99 between trials) and sensitivity = 0.85 (range 0.81–0.92 between trials). Urination event duration had a model validation R2 = 0.90 and RMSE of 2.0 s (with a range 1.8–2.2 s between trials), which compares with 1.70 s for the calibration dataset. Acoustic sensor determination of urination flow rate had an estimated error of 0.028 L s?1, and the average cow urination flow rate was 0.26 L s?1. The between-cow variation in urination traits had a coefficient of variation of 10–15% and the urination traits were repeatable between winter and spring trials. We also found that potassium and beta-hydroxybutyrate were the blood metabolites with the largest influence on N load per event and that total protein and albumin were the two blood metabolites that were the best predictors of total daily nitrogen (TDN) output. This study demonstrates the performance of a novel acoustic technology that has been tested on 355 cows and has the potential to inform strategies to reduce environmental N losses from grazed pastoral systems.
      原文链接:
    • NSTL
    • Elsevier

    Analysis and experiment of feeding material process of Hermetia illucens L. frass bucket wheel based on DEM

    Peng C.Zhou T.Song S.Sun S....
    15页
    查看更多>>摘要：? 2022 Elsevier B.V.This study aims to improve the load factor and reduce the residual rate of the Hermetia illucens L. feeding bucket. Based on the sand bucket feeding conveyor designed in the early stage, the technological characteristics of biotransformation of pig manure with Hermetia illucens L., and the mechanism of the bucket shape feeding and transport, the 4-day-old Hermetia illucens L. larvae was firstly inoculated in the pig manure environment with a water content of 75% at 26℃. Then, the single factor experiment was conducted to compare the effect of pig-manure bulking thickness on the biotransformation efficiency of Hermetia illucens L. The results demonstrated that when the thickness of pig manure was 0.10–0.15 m, the biotransformation efficiency of Hermetia illucens L. was relatively high, and the weight loss rate of pig manure was more than 50%. Hence, the thickness of pig manure was an essential factor influencing the efficiency of bucket feeding transportation. On this basis, the physical parameters such as shape size, particle size distribution, and water content of the Hermetia illucens L. sand particles after biotransformation of pig manure were determined. Furthermore, the discrete element method was adopted to establish the numerical simulation model of the bucket shape feeding conveyer under the combination of discrete element simulation and bench test, so as to simulate the bucket shape feeding transport process with insect sands after cleaning the Hermetia illucens L. larva as the test object. Meanwhile, a mechanics and kinematics analysis was conducted for the stress of the horizontal and vertical directions, the mass of materials in the bucket, and the leakage area of the bucket to reveal the mechanism of feeding filling conveying and leakage bucket. Additionally, the main factors influencing the bucket material feeding transport efficiency were comprehensively determined, including feed speed, bucket rotating speed, and feeding depth. The test indicators such as bucket load factor, variation coefficient, and residual rate were established. Besides, a three-factor three-level orthogonal combination experiment was conducted by combining with the Box-Behnken test method. Then, the regression mathematical model between the indexes and factors was set up to analyze the influence law of various factors on the evaluation indicators. The parameters were optimized with the regression model. The model validation test results suggested that the bucket rotating speed was 6.5r·min-1 when the feed speed was 45 mm·s?1; the experimental values of the load factor, variation coefficient, and residual rate were consistent with the theoretical optimization values when the feeding depth was 15 cm, with the relative errors of 2.14%, 5.84%, and 6.40%, respectively. Thus, the model optimization is reliable. Under the condition of the optimization parameters, the bench test equipment was established, and the experiment was performed. With the mixture of Hermetia illucens L. insect sand as the experimental material, its load factor, variation coefficient, sand retention rate, and larvae loss rate were 81.23%, 1.48%, 1.85%, and 3.75%, respectively, which met the experimental and actual production requirements. The research results provided a theoretical reference for the design and optimization of the bucket shape feeding conveying machinery of Hermetia illucens L. insect sand.
      原文链接:
    • NSTL
    • Elsevier

    Deep transfer learning based photonics sensor for assessment of seed-quality

    Singh Thakur P.Tiwari B.Kumar A.Gedam B....
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.Seed-quality is one of the most important factors for achieving the objectives of uniform seedling establishment and high crop yield. In this work, we propose laser backscattering and deep transfer learning (TL) based photonics sensor for automatic identification and classification of high-quality seeds. The proposed sensor is based on capturing a single backscattered image of a seed sample and processing the acquired images by using deep learning (DL) based algorithms. Advantages of the proposed sensor include its ability to characterize morphological and biological changes related to seed-quality, lower memory requirement, robustness against external noise and vibration, easy alignments, and low complexity of acquisition and processing units. Furthermore, use of DL based processing frameworks including convolution neural network (CNN) and various TL models (VGG16, VGG19, InceptionV3, and ResNet50) extract abstract features from the images without any additional image processing and accelerate classification efficiency. Obtained results indicate that all the DL models performed significantly well with higher accuracy; however, InceptionV3 outperformed rest of the models with accuracy reaching up to 98.31%. To validate performance of the proposed sensor standard quality parameters comprising percentage imbibition (PI), radicle length, and germination percentage (GP) were also calculated. Significant change (p < 0.05) in these parameters show that the proposed sensor can accurately monitor the quality of seeds with higher accuracy. Moreover, experimental simplicity and DL based automatic classification make the sensor suitable for real-time applications.
      原文链接:
    • NSTL
    • Elsevier

    Hyperspectral classification of poisonous solanaceous weeds in processing Phaseolus vulgaris L. and Spinacia oleracea L.

    Lauwers M.De Cauwer B.Pieters J.Nuyttens D....
    16页
    查看更多>>摘要：? 2022Poisonous weeds can occasionally unintentionally be co-harvested and pose a threat to human health as separation techniques during processing are not sufficient. Hence, elimination prior to harvest is required. For this reason, an exploratory study is performed to investigate the possibilities of an automatic detection system. The objective of this article is, firstly, to know if Phaseolus vulgaris and Spinacia oleracea are hyperspectrally separable from Solanum nigrum, Solanum tuberosum and Datura stramonium using spectrometer measurements. Secondly, the influence of different varieties/populations and of different pedohydrological and climatic conditions on this classification is investigated. Finally, it is examined whether it is possible to appoint discriminative wavelengths. To this means, the following analyses were performed: I and II) crop and weed species, and different populations or varieties of these species in varying conditions, were classified using hyperspectral spectrometer measurements and regularized logistic regression (RLR), III) data of consecutive years were investigated for similarities in order to indicate robust important regions in the electromagnetic spectrum with the use of RLR and IV) a subset of commercial off-the-shelf (COTS) filters was created for further research in the field. Results showed that the poisonous weed species D. stramonium, S. nigrum and S. tuberosum are hyperspectrally separable from the investigated crops. The accuracy of the two-class classification of poisonous weeds with S. oleracea and of these weeds with P. vulgaris was 0.982 and 0.977, respectively (I). Inclusion of different crop varieties, weed populations or different growing conditions in the model with S. oleracea and poisonous weeds resulted in a small decrease in weed recall (0.95 vs. 0.99) and crop precision (0.93 vs. 0.97). In future research, care must be taken to proper sample fields to cover the genetic variation present within weed populations and crop varieties, and diverse growing conditions (II). The bands selected using RLR did not show any consistency when using data of consecutive years and, therefore, RLR is not a suitable method to select robust wavelength regions for detection of poisonous weeds in vegetable crops to guide future research (III). With the use of COTS filters it was possible to select ten filters that worked sufficiently for both crops and are recommended for further research in the field. In addition, the authors recommend the use of a high resolution RGB camera to benefit from object-based image analysis to increase classification accuracy (IV).
      原文链接:
    • NSTL
    • Elsevier

    Frequency modulated continuous wave radar-based system for monitoring dairy cow respiration rate

    Rustia D.J.A.Lin T.-T.Hsu J.-T.Tuan S.-A....
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.Heat stress is one of the major challenges in livestock production and management. Due to heat stress, dairy cows experience health and fertility problems as well as lower milk production, resulting in great economic losses to dairy farmers. One of the approaches to assessing heat stress in dairy cows is by monitoring their respiration rate (RR). Many studies show that the RR of dairy cows is highly correlated to heat stress. The measurement of RR is most commonly taken by counting flank movements via human observation, which is labor-intensive and may vary across observers. This paper presents a non-contact system for RR monitoring of dairy cows using millimeter-wave frequency modulated continuous wave (FMCW) radar. The system utilizes an integrated sensor node that collects the data from a FMCW radar and a temperature-humidity sensor. The sensor node was installed in the milking parlor of an experimental dairy farm to continuously measure the displacements from cows’ flank movements. The radar data was converted by the sensor node into RR measurements and sent together with the environmental data to a remote server for post-processing. A dairy cow RR measurement algorithm was developed to process the radar data; it can be divided into three parts: cow presence state determination, timestamp labelling, and individual dairy cow RR matching. A model trained to automatically determine the presence of cows from the collected radar data had an F1-score of 0.95, as verified by manual observation. The timestamp labelling sub-routine was used to merge the predicted states and perform gap and chunk analyses for removing outliers and merging consecutive chunks. Finally, the RR measurements were matched to each timestamp in order to identify the RR of each cow in specific time periods. The algorithm had an R2 of 0.995 and root mean square error (RMSE) of 1.582 breaths/min, also verified by manual observation. The system was operated for a year to investigate the relationship between the RR and temperature-humidity index (THI); this relationship was described using a piecewise linear-exponential regression model, which revealed the effect of THI on the level of heat stress among dairy cows in a subtropical region. The proposed system herein proved the feasibility of employing a novel dairy cow RR monitoring system using FMCW radar, and demonstrated its potential applications for automated assessment of dairy cow heat stress and health monitoring.
      原文链接:
    • NSTL
    • Elsevier

    Hyperspectral imaging facilitates early detection of Orobanche cumana below-ground parasitism on sunflower under field conditions

    Atsmon G.Nehurai O.Eizenberg H.Nisim Lati R....
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.Sunflower broomrape (Orobanche cumana) is a root parasitic weed that severely limits sunflower yield in large areas of Europe and Asia. Early detection of the parasite can facilitate site-specific control of this weed. However, most of its life-cycle takes place in the soil sub-surface and by the time that O. cumana shoots emerge, the damage to the crop is irreversible. The main aim of this study was to evaluate the potential use of hyperspectral imaging for the early detection of parasitism by monitoring changes in spectra obtained from the host plants. A field experiment was conducted on infested and non-infested sunflower plants, imaged by a ground-based hyperspectral camera at two early parasitism stages that are relevant for herbicide application. A logistic regression model was used to classify infected and non-infected plants, 31 and 38 days after sunflower planting, with 76 and 89% accuracy, respectively. A partial dataset, containing only 10 spectral bands of the hyperspectral dataset, gave 69 and 82% accuracy, indicating the potential of multi-spectral sensors for the detection task. Sampling pixels from specific sunflower leaf segments improved the classification compared to non-specific sampling. This study thus contributes to establishing a basis for future development of site-specific weed management of O. cumana and of other broomrape species.
      原文链接:
    • NSTL
    • Elsevier

    Vineyard classification using OBIA on UAV-based RGB and multispectral data: A case study in different wine regions

    Padua L.Matese A.Di Gennaro S.F.Morais R....
    15页
    查看更多>>摘要：? 2022 Elsevier B.V.Vineyard classification is an important process within viticulture-related decision-support systems. Indeed, it improves grapevine vegetation detection, enabling both the assessment of vineyard vegetative properties and the optimization of in-field management tasks. Aerial data acquired by sensors coupled to unmanned aerial vehicles (UAVs) may be used to achieve it. Flight campaigns were conducted to acquire both RGB and multispectral data from three vineyards located in Portugal and in Italy. Red, green, blue and near infrared orthorectified mosaics resulted from the photogrammetric processing of the acquired data. They were then used to calculate RGB and multispectral vegetation indices, as well as a crop surface model (CSM). Three different supervised machine learning (ML) approaches—support vector machine (SVM), random forest (RF) and artificial neural network (ANN)—were trained to classify elements present within each vineyard into one of four classes: grapevine, shadow, soil and other vegetation. The trained models were then used to classify vineyards objects, generated from an object-based image analysis (OBIA) approach, into the four classes. Classification outcomes were compared with an automatic point-cloud classification approach and threshold-based approaches. Results shown that ANN provided a better overall classification performance, regardless of the type of features used. Features based on RGB data showed better performance than the ones based only on multispectral data. However, a higher performance was achieved when using features from both sensors. The methods presented in this study that resort to data acquired from different sensors are suitable to be used in the vineyard classification process. Furthermore, they also may be applied in other land use classification scenarios.
      原文链接:
    • NSTL
    • Elsevier