查看更多>>摘要：? 2021Observing Forest attributes using small, weighted unmanned aerial systems (UASs) is increasing interest to forest ecologists and managers. Here, we provide a comprehensive model for estimating the relationship between diameter at breast height (DBH) and crown size for Japanese cypress (Chamaecyparis obtusa), intending to promote the use of UAS-acquired data. Aerial images were processed using Structure from Motion software to develop ortho-mosaicked imagery for the study sites. We also measured the DBH and height of 196 individual trees at these same sites. Crown size, estimated from the orthoimagery, was compared with DBH using multiple functional models. Model fit estimates has ranged from R2 = 0.6403–0.7584 and root mean square error (RMSE) = 6.34 cm–5.20 cm (relative RMSE (rRMSE) = 17.83–13.44%). Including tree height as a predictor improved model fit of both linear and Support Vector Regression (SVR) model, where the best result in Adjusted R2 = 0.834 and RMSE = 4.25 cm (rRMSE = 11.30%) for the SVR model. This study suggests the potential for accurately surveying forest attributes through UAS remote sensing, which has important implications for forest monitoring and management.
查看更多>>摘要：? 2021Accurate weed mapping is a prerequisite for site-specific weed management to enable sustainable agriculture. This work aims to analyse (spectrally) and mapping blackgrass weed in wheat fields by integrating Unmanned Aerial Vehicle (UAV), multispectral imagery and machine learning techniques. 18 widely-used Spectral Indices (SIs) are generated from 5 raw spectral bands. Then various feature selection algorithms are adopted to improve model simplicity and empirical interpretability. Random Forest classifier with Bayesian hyperparameter optimization is preferred as the classification algorithm. Image spatial information is also incorporated into the classification map by Guided Filter. The developed framework is illustrated with an experimentation case in a naturally blackgrass infected wheat field in Nottinghamshire, United Kingdom, where multispectral images were captured by RedEdge on-board DJI S-1000 at an altitude of 20 m with a ground spatial resolution of 1.16 cm/pixel. Experimental results show that: (i) a good result (an average precision, recall and accuracy of 93.8%, 93.8%, 93.0%) is achieved by the developed system; (ii) the most discriminating SI is triangular greenness index (TGI) composed of Green-NIR, while wrapper feature selection can not only reduce feature number but also achieve a better result than using all 23 features; (iii) spatial information from Guided filter also helps improve the classification performance and reduce noises.
查看更多>>摘要：? 2021 Elsevier B.V.To measure the total nitrogen (TN) content of large-scale farmland soil accurately in real time and guide field fertilization, a vehicle-mounted soil TN content prediction system based on the fusion of near-infrared spectroscopy and image information was developed. A combined algorithm of uniform variable illumination (UVE) and adaptive weighted sampling (CARS) were used to select the characteristic wavelength, and the selected characteristic wavelength was used as the soil spectral information. Multiple linear regression model, partial least squares regression model, BP neural network prediction model and Catboost prediction model were chosen to predict soil TN content. After comparison, Catboost was finally selected as the final prediction model. The prediction system was composed of a mechanical part, an optical part, and a control part. The mechanical part provided space support for the prediction system, the optical part obtained the spectrum and image information of the soil, mainly including seven single-band near-infrared (NIR) filters: 945, 1045, 1200, 1300, 1450, 1535, and 1615 nm; 1450 nm is the sensitive wavelength which is used to eliminate the effect of water. The control part realized spectral data collection, image feature processing, data fusion, and the prediction of soil TN content. Soil samples were used to test the accuracy of the spectrum collection of the system. The test results showed that the highest correlation coefficient between the reflectance of the prediction system at seven sensitive wavelengths and the reflectance of the NIRQuest 512 infrared spectrometer is above 0.943. The field test results show that the R2 between the predicted soil TN content by the prediction system and the value of laboratory standard detection method is greater than 0.80 and the relative errors are less than 10%. The results also show that data fusion of spectral data and image features highlighted the common contribution of the near infrared spectrum and visible light images in the detection of soil TN content, and it can improve the prediction accuracy of the instrument. Moreover, the system can provide guidance for farmland scientific variable fertilization.
查看更多>>摘要：? 2021 Elsevier B.V.Spectral analysis is one of the most important and widely used methods for chemometrics in the field of agriculture, and convolutional neural network (CNN) models have achieved excellent performance on spectral analysis. The critical drawback of the CNN approach is that it preserves the spatial relationships among adjacent wavelengths, which contribute to collinearity and redundancies rather than relevant effective information. To confirm this observation, the distribution of characteristic wavelengths extracted by different methods (include F-test, importance weights, and CNN) are visualized in this paper. A convolutional neural network for quantitative spectral analysis, named Mark-Spectra, is presented to overcome spatial relationships and to improve the model performance. A layer (Mark layer) is introduced as part of Mark-Spectra, which is used to overcome spatial relationship of raw spectral data. Mark-Spectra model is compared with three CNN models using three open accessed visible and near infrared spectroscopic datasets (corn, wheat and soil). Mark-Spectra model outperforms the other three convolutional neural network models on two datasets (except dataset of wheat, due to lesser number of features), and it cost much less training time than the others. In addition, this paper compares Mark-Spectra with two classical neural network-based algorithms, principal component analysis – artificial neural network (PCA-ANN) and extreme learning machine (ELM). Mark-Spectra performed best in soil dataset, and ELM performed best in corn and wheat datasets, respectively. These results can illustrate that Mark-Spectra is still limited with the characteristic of raw spectral data (e.g., the number of samples and features), which is a fundamental fact of deep learning-based methods, but it performed better than the other CNN models and reduced the dependence of sample size due to overcoming spatial relationships.
查看更多>>摘要：? 2021 Elsevier B.V.Date palm trees are an important economic crop in the Arabian Peninsula, Middle East, and North Africa. Counting the numbers and determining the locations of date palm trees are important for predicting the date production and plantation management. In this paper, we exploit the effective use of the state-of-the-art CNN, YOLO-V5, in detecting date palm trees in images captured by a camera onboard of a drone flying 122 m above farmlands in the Northern Emirates of the United Arab Emirates (UAE). In the dataset preparation process, we randomly selected 125 captured images and divided them into three datasets: training (60%), validation (20%), and testing (20%). The images of date palm trees in the training and validation datasets were manually annotated and those in the training dataset were used to train the four sub-versions of YOLO-V5 CNNs. The validation dataset was used during the training process to assess how well the network was performing during training. Finally, the images in the test dataset were used to evaluate the performance of the trained models. The results of using YOLO-V5 for date palm tree detection in drone imagery are compared with those obtainable with other popular CNN architectures, YOLO-V3, YOLO-V4, and SSD300, both quantitatively and qualitatively. The results show that for the amount of training data used, YOLO-V5m (medium depth) model records the highest accuracy, resulting in a mean average precision of 92.34%. Further it provides the ability to detect and localize date palm trees of different sizes, in crowded, overlapped environments and areas where the date palm tree distribution is sparse. Therefore, it is concluded that the method can be a useful component of an automated plantation management system and help forecast the quantities of date production and condition monitoring of the date palm trees.
查看更多>>摘要：? 2021 The AuthorsAs herd size on dairy farms continues to increase, automatic health monitoring of cows is gaining in interest. Lameness, a prevalent health disorder in dairy cows, is commonly detected by analyzing the gait of cows. A cow's gait can be tracked in videos using pose estimation models because models learn to automatically localize anatomical landmarks in images and videos. Most animal pose estimation models are static, that is, videos are processed frame by frame and do not use any temporal information. In this work, a static deep-learning model for animal-pose-estimation was extended to a temporal model that includes information from past frames. We compared the performance of the static and temporal pose estimation models. The data consisted of 1059 samples of 4 consecutive frames extracted from videos (30 fps) of 30 different dairy cows walking through an outdoor passageway. As farm environments are prone to occlusions, we tested the robustness of the static and temporal models by adding artificial occlusions to the videos. The experiments showed that, on non-occluded data, both static and temporal approaches achieved a Percentage of Correct Keypoints (PCKh@0.2) of 99%. On occluded data, our temporal approach outperformed the static one by up to 32.9%, suggesting that using temporal data was beneficial for pose estimation in environments prone to occlusions, such as dairy farms. The generalization capabilities of the temporal model was evaluated by testing it on data containing unknown cows (cows not present in the training set). The results showed that the average PCKh@0.2 was of 93.8% on known cows and 87.6% on unknown cows, indicating that the model was capable of generalizing well to new cows and that they could be easily fine-tuned to new herds. Finally, we showed that with harder tasks, such as occlusions and unknown cows, a deeper architecture was more beneficial.
查看更多>>摘要：? 2021 Elsevier B.V.Developing alternatives to the chemical weeding process usually carried out in vegetable crop farming is necessary in order to reach a more sustainable agriculture. However, a precise mechanical weeding requires specific sensors and advanced computer vision algorithms to process crop and weed discrimination in real-time. In this paper we propose an algorithm able to detect, locate, and track the stem position of crops in images which is suitable for precision actions in vegetable fields such as mechanical hoeing within crop rows. The algorithm is twofold: (i) a deep neural network for object detection is first used to detect crop stems in individual RGB images and then (ii) an aggregation algorithm further refines the detections taking advantage of the temporal redundancy in consecutive frames. We evaluated the pipeline on images of maize and bean crops at an early stage of development, acquired in field conditions with a camera embedded in an experimental mechanical weeding system. We reported F1-scores of respectively 94.74% and 93.82% with a location accuracy around 0.7 cm when compared with human annotation. Moreover, this pipeline can operate in real-time on an embedded computer consuming as little power as 30 W.
查看更多>>摘要：? 2021 Elsevier B.V.Empirical and process-based models are currently used to predict crop yield at field and regional levels. A mechanistic model named STICS (Multidisciplinary Simulator for Standard Crops) has been used to simulate soybean grain yield in several environments, including southern France. STICS simulates at a daily step the effects of climate, soil and management practices on plant growth, development and production. In spite of good performances to predict total aboveground biomass, poor results were obtained for final grain yield. In order to improve yield prediction, a surrogate model was developed from STICS dynamic simulations, feature selection techniques and regression learners. STICS was used to simulate functional variables at given growth stages and over selected phenological phases. The most representative variables were selected through feature selection techniques (filter, wrapper and embedded), and a subset of variables were used to train the regression learners Linear regression (LR), Support vector regression (SVR), Back propagation neural network (BPNN), Random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO) and M5 decision tree. The subset of variables selected by wrapper method combined with regression models SVR (R2 = 0. 7102; subset of variables = 6) and LR (R2 = 0. 6912; subset of variables = 14) provided the best results. SVR and LR models improved significantly the soybean yield predictions in southern France in comparison to STICS simulations (R2 = 0.040).
查看更多>>摘要：? 2021Coordination position control of multi-motors systems is widely applied in agricultural and industrial fields that require high precision and synchronization among motors. Current adjacent cross-coupled control is unable to change the control gains as motor states are time-variant. The invariant gain compensation will inevitably weaken the coordinated control performance, especially in the presence of load disturbances. To solve this issue, this paper proposes a variable-gain adjacent cross-coupled controller. A sliding mode controller is adopted to cope with the disturbances and uncertainties for each single permanent magnet linear synchronous motor (PMLSM). The motor state of each PMLSM can be detected through system identification in real time. According to the motor states of the PMLSMs based on the system identification technique, a fuzzy position control algorithm is implemented for regulating the gain compensation. A consistent steady-state performance is subsequently maintained even with the existence of system uncertainties and load disturbances. It is proved from the experimental results that, compared with fixed-gain adjacent cross-coupled control scheme, the proposed controller has a better synchronization, a higher tracking accuracy and synergistic accuracy, under both no load and time-varying load conditions. For the variable-gain adjacent cross-coupled control, a position tracking error and a synergistic error within 7 μm and 8 μm can be achieved, respectively.
Montoya-Cavero L.-E.Gomez-Espinosa A.Escobedo Cabello J.A.Diaz de Leon Torres R....
27页
查看更多>>摘要：? 2021 Elsevier B.V.In the last few years, the use of artificial intelligence and technological advances such as deep learning, new 3D-capable sensors, and edge computing embedded systems have increased produce detection and localization performance for harvesting robots. Unfortunately, this performance increase often requires large datasets that must be manually labeled, large periods for training, increased processing time and power for inference, and a high cost of powerful hardware to run the detection models. This work focuses on providing up-to-date information regarding the state of harvesting robots’ vision subsystems, focusing on produce detection and localization research with special attention to the new technology that is being used. A description and analysis of the challenges of introducing this technology to produce detection and localization methodologies are also present in this review. Finally, future trends for harvesting robots’ vision subsystems are described and discussed.
NSTL
Elsevier