Submit to Special Issue Submit Abstract to Special Issue Review for Agriculture Edit a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Special Issue "Application of Vision Technology and Artificial Intelligence in Smart Farming"

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Agriculture (ISSN 2077-0472). This special issue belongs to the section "Digital Agriculture".

Deadline for manuscript submissions: 10 July 2023 | Viewed by 14211

Share This Special Issue

Special Issue Editors

Dr. Xiuguo Zou

E-Mail Website
Guest Editor

College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
Interests: microclimate analytics of poultry houses; intelligent agricultural equipment; smart farming; non-destructive detection of meat quality; agricultural robot
Special Issues, Collections and Topics in MDPI journals

Dr. Zheng Liu

E-Mail Website
Guest Editor

School of Engineering, University of British Columbia, Okanagan, Kelowna, BC V1V 1V7, Canada
Interests: intelligent sensing, measurement, and instrumentation; diagnostics, prognostics, and health management; predictive maintenance; digital twins; computational intelligence and data/information fusion; non-destructive testing and evaluation; machine/computer vision; data analytics and machine learning
Special Issues, Collections and Topics in MDPI journals

Dr. Xiaochen Zhu

E-Mail Website
Guest Editor

School of Applied Meteorology, Nanjing University of Information Science and Technology, Nanjing 210044, China
Interests: climate-smart agriculture; AI meteorology
Special Issues, Collections and Topics in MDPI journals

Dr. Wentian Zhang
E-Mail Website
Guest Editor

Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia
Interests: prediction model; computer simulation
Special Issues, Collections and Topics in MDPI journals

Dr. Yan Qian
E-Mail Website
Guest Editor

College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
Interests: intelligent agricultural equipment; three-dimensional reconstruction
Special Issues, Collections and Topics in MDPI journals

Dr. Yuhua Li
E-Mail Website
Guest Editor

College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
Interests: intelligent agricultural equipment; disease detection
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Computer vision (CV) and artificial intelligence (AI) have been gaining traction in agriculture. From reducing production costs with intelligent automation to boosting productivity, CV and AI have massive potential to enhance the overall functioning of smart farming. Monitoring and analyzing specific behaviors of livestock and poultry in large-scale farms based on CV and AI to improve our knowledge of intensively raised livestock and poultry behaviors in relation to modern management techniques, allowing for improved health, welfare, and performance. In the field of planting, CV approaches are required to extract plant phenotypes from images and automate the detection of plants and plant organs. AI approaches give growers weapons against pests. Smart farming requires considerable processing power. The application of CV and AI helps crops to progress toward perfect ripeness.

This Special Issue focuses on the application of CV and AI in smart farming, including breeding and planting. Topics of interest include but are not limited to the following: design and optimization of agricultural sensors, behavior recognition of livestock and poultry based on vision technology and deep learning, automation technology in agricultural equipment based on vision technology, design and optimization of robots for livestock and poultry breeding based on vision technology and artificial intelligence, non-destructive detection of meat quality, and agricultural big data analytics based on sensor data and deep learning. Original research articles and reviews are welcome.

Dr. Xiuguo Zou
Dr. Zheng Liu
Dr. Xiaochen Zhu
Dr. Wentian Zhang
Dr. Yan Qian
Dr. Yuhua Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Agriculture is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

agricultural sensors
behavior recognition of livestock and poultry
agricultural automation equipment
agricultural intelligent robots
intelligent robotic arms
non-destructive detection of meat quality
agricultural big data analytics

Published Papers (16 papers)

Download All Papers

Research

Open AccessArticle

Research into Heat Stress Behavior Recognition and Evaluation Index for Yellow-Feathered Broilers, Based on Improved Cascade Region-Based Convolutional Neural Network

and

Agriculture 2023, 13(6), 1114; https://doi.org/10.3390/agriculture13061114 - 24 May 2023

Viewed by 254

Abstract

The heat stress response of broilers will adversely affect the large-scale and welfare of the breeding of broilers. In order to detect the heat stress state of broilers in time, make reasonable adjustments, and reduce losses, this paper proposed an improved Cascade R-CNN (Region-based Convolutional Neural Networks) model based on visual technology to identify the behavior of yellow-feathered broilers. The improvement of the model solved the problem of the behavior recognition not being accurate enough when broilers were gathered. The influence of different iterations on the model recognition effect was compared, and the optimal model was selected. The final average accuracy reached 88.4%. The behavioral image data with temperature and humidity data were combined, and the heat stress evaluation model was optimized using the PLSR (partial least squares regression) method. The behavior recognition results and optimization equations were verified, and the test accuracy reached 85.8%. This proves the feasibility of the heat stress evaluation optimization equation, which can be used for reasonably regulating the broiler chamber. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Method for Classifying Apple Leaf Diseases Based on Dual Attention and Multi-Scale Feature Extraction

and

Agriculture 2023, 13(5), 940; https://doi.org/10.3390/agriculture13050940 - 25 Apr 2023

Viewed by 366

Abstract

Image datasets acquired from orchards are commonly characterized by intricate backgrounds and an imbalanced distribution of disease categories, resulting in suboptimal recognition outcomes when attempting to identify apple leaf diseases. In this regard, we propose a novel apple leaf disease recognition model, named RFCA ResNet, equipped with a dual attention mechanism and multi-scale feature extraction capacity, to more effectively tackle these issues. The dual attention mechanism incorporated into RFCA ResNet is a potent tool for mitigating the detrimental effects of complex backdrops on recognition outcomes. Additionally, by utilizing the class balance technique in conjunction with focal loss, the adverse effects of an unbalanced dataset on classification accuracy can be effectively minimized. The RFB module enables us to expand the receptive field and achieve multi-scale feature extraction, both of which are critical for the superior performance of RFCA ResNet. Experimental results demonstrate that RFCA ResNet significantly outperforms the standard CNN network model, exhibiting marked improvements of 89.61%, 56.66%, 72.76%, and 58.77% in terms of accuracy rate, precision rate, recall rate, and F1 score, respectively. It is better than other approaches, performs well in generalization, and has some theoretical relevance and practical value. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Research on Provincial-Level Soil Moisture Prediction Based on Extreme Gradient Boosting Model

Yifang Ren

Fenghua Ling

and

Yong Wang

Agriculture 2023, 13(5), 927; https://doi.org/10.3390/agriculture13050927 - 24 Apr 2023

Viewed by 462

Abstract

As one of the physical quantities concerned in agricultural production, soil moisture can effectively guide field irrigation and evaluate the distribution of water resources for crop growth in various regions. However, the spatial variability of soil moisture is dramatic, and its time series data are highly noisy, nonlinear, and nonstationary, and thus hard to predict accurately. In this study, taking Jiangsu Province in China as an example, the data of 70 meteorological and soil moisture automatic observation stations from 2014 to 2022 were used to establish prediction models of 0–10 cm soil relative humidity (RH_s10cm) via the extreme gradient boosting (XGBoost) algorithm. Before constructing the model, according to the measured soil physical characteristics, the soil moisture observation data were divided into three categories: sandy soil, loam soil, and clay soil. Based on the impacts of various factors on the soil water budget balance, 14 predictors were chosen for constructing the model, among which atmospheric and soil factors accounted for 10 and 4, respectively. Considering the differences in soil physical characteristics and the lagged effects of environmental impacts, the best influence times of the predictors for different soil types were determined through correlation analysis to improve the rationality of the model construction. To better evaluate the importance of soil factors, two sets of models (Model_{_soil&atmo} and Model_{_atmo}) were designed by taking soil factors as optional predictors put into the XGBoost model. Meanwhile, the contributions of predictors to the prediction results were analyzed with Shapley additive explanation (SHAP). Six prediction effect indicators, as well as a typical drought process that happened in 2022, were analyzed to evaluate the prediction accuracy. The results show that the time with the highest correlations between environmental predictors and RH_s10cm varied but was similar between soil types. Among these predictors, the contribution rates of maximum air temperature (T_amax), cumulative precipitation (P_sum), and air relative humidity (RH_a) in atmospheric factors, which functioned as a critical factor affecting the variation in soil moisture, are relatively high in both models. In addition, adding soil factors could improve the accuracy of soil moisture prediction. To a certain extent, the XGBoost model performed better when compared with artificial neural networks (ANNs), random forests (RFs), and support vector machines (SVMs). The values of the correlation coefficient (R), root mean square error (RMSE), mean absolute error (MAE), mean absolute relative error (MARE), Nash–Sutcliffe efficiency coefficient (NSE), and accuracy (ACC) of Model_{_soil&atmo} were 0.69, 11.11, 4.87, 0.12, 0.50, and 88%, respectively. This study verified that the XGBoost model is applicable to the prediction of soil moisture at the provincial level, as it could reasonably predict the development processes of the typical drought event. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Design and Experiment of a Visual Detection System for Zanthoxylum-Harvesting Robot Based on Improved YOLOv5 Model

and

Agriculture 2023, 13(4), 821; https://doi.org/10.3390/agriculture13040821 - 31 Mar 2023

Viewed by 607

Abstract

In order to achieve accurate detection of mature Zanthoxylum in their natural environment, a Zanthoxylum detection network based on the YOLOv5 object detection model was proposed. It addresses the issues of irregular shape and occlusion caused by the growth of Zanthoxylum on trees and the overlapping of Zanthoxylum branches and leaves with the fruits, which affect the accuracy of Zanthoxylum detection. To improve the model’s generalization ability, data augmentation was performed using different methods. To enhance the directionality of feature extraction and enable the convolution kernel to be adjusted according to the actual shape of each Zanthoxylum cluster, the coordinate attention module and the deformable convolution module were integrated into the YOLOv5 network. Through ablation experiments, the impacts of the attention mechanism and deformable convolution on the performance of YOLOv5 were compared. Comparisons were made using the Faster R-CNN, SSD, and CenterNet algorithms. A Zanthoxylum harvesting robot vision detection platform was built, and the visual detection system was tested. The experimental results showed that using the improved YOLOv5 model, as compared to the original YOLOv5 network, the average detection accuracy for Zanthoxylum in its natural environment was increased by 4.6% and 6.9% in terms of [email protected] and [email protected]:0.95, respectively, showing a significant advantage over other network models. At the same time, on the test set of Zanthoxylum with occlusions, the improved model showed increased [email protected] and [email protected]:0.95 by 5.4% and 4.7%, respectively, compared to the original model. The improved model was tested on a mobile picking platform, and the results showed that the model was able to accurately identify mature Zanthoxylum in its natural environment at a detection speed of about 89.3 frames per second. This research provides technical support for the visual detection system of intelligent Zanthoxylum-harvesting robots. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Use of Computational Fluid Dynamics to Study Ammonia Concentrations at Pedestrian Height in Smart Broiler Chamber Clusters

and

Agriculture 2023, 13(3), 656; https://doi.org/10.3390/agriculture13030656 - 11 Mar 2023

Viewed by 518

Abstract

NH₃ emissions are an environmental issue that is of wide concern in livestock production. In intensive livestock farming, it is necessary to study outdoor ammonia concentrations under various conditions to maximize the protection of livestock caretakers’ health in and around the facilities. In this study, the ammonia concentrations outside smart broiler chambers in 60 scenarios, with conditions including 4 broiler chamber densities, 3 wind directions, and 5 outlet emission intensities, were simulated based on computational fluid dynamics (CFD) technology. The results show that (1) outdoor ammonia tends to accumulate near the outlet when the wind direction angle is small, while it has a wider range of influence when the angle is vertical; (2) building a smart broiler chamber cluster for intensive livestock farming is environmentally friendly; and (3) keeping the ammonia outlet perpendicular to the local dominant wind direction can effectively prevent high concentrations of ammonia around the chambers. In practical applications, the conclusions of this study can be used to arrange the layout and direction of smart broiler chamber clusters. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Multi-Modal Late Fusion Rice Seed Variety Classification Based on an Improved Voting Method

and

Agriculture 2023, 13(3), 597; https://doi.org/10.3390/agriculture13030597 - 01 Mar 2023

Viewed by 821

Abstract

Rice seed variety purity, an important index for measuring rice seed quality, has a great impact on the germination rate, yield, and quality of the final agricultural products. To classify rice varieties more efficiently and accurately, this study proposes a multimodal l fusion detection method based on an improved voting method. The experiment collected eight common rice seed types. Raytrix light field cameras were used to collect 2D images and 3D point cloud datasets, with a total of 3194 samples. The training and test sets were divided according to an 8:2 ratio. The experiment improved the traditional voting method. First, multiple models were used to predict the rice seed varieties. Then, the predicted probabilities were used as the late fusion input data. Next, a comprehensive score vector was calculated based on the performance of different models. In late fusion, the predicted probabilities from 2D and 3D were jointly weighted to obtain the final predicted probability. Finally, the predicted value with the highest probability was selected as the final value. In the experimental results, after late fusion of the predicted probabilities, the average accuracy rate reached 97.4%. Compared with the single support vector machine (SVM), k-nearest neighbors (kNN), convolutional neural network (CNN), MobileNet, and PointNet, the accuracy rates increased by 4.9%, 8.3%, 18.1%, 8.3%, and 9%, respectively. Among the eight varieties, the recognition accuracy of two rice varieties, Hannuo35 and Yuanhan35, by applying the voting method improved most significantly, from 73.9% and 77.7% in two dimensions to 92.4% and 96.3%, respectively. Thus, the improved voting method can combine the advantages of different data modalities and significantly improve the final prediction results. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Research on Winter Wheat Growth Stages Recognition Based on Mobile Edge Computing

and

Agriculture 2023, 13(3), 534; https://doi.org/10.3390/agriculture13030534 - 23 Feb 2023

Viewed by 780

Abstract

The application of deep learning (DL) technology to the identification of crop growth processes will become the trend of smart agriculture. However, using DL to identify wheat growth stages on mobile devices requires high battery energy consumption, significantly reducing the device’s operating time. However, implementing a DL framework on a remote server may result in low-quality service and delays in the wireless network. Thus, the DL method should be suitable for detecting wheat growth stages and implementable on mobile devices. A lightweight DL-based wheat growth stage detection model with low computational complexity and a computing time delay is proposed; aiming at the shortcomings of high energy consumption and a long computing time, a wheat growth period recognition model and dynamic migration algorithm based on deep reinforcement learning is proposed. The experimental results show that the proposed dynamic migration algorithm has 128.4% lower energy consumption and 121.2% higher efficiency than the local implementation at a wireless network data transmission rate of 0–8 MB/s. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Non-Destructive Detection of Chicken Freshness Based on Electronic Nose Technology and Transfer Learning

and

Agriculture 2023, 13(2), 496; https://doi.org/10.3390/agriculture13020496 - 20 Feb 2023

Cited by 1 | Viewed by 914

Abstract

As a non-destructive detection method, an electronic nose can be used to assess the freshness of meats by collecting and analyzing their odor information. Deep learning can automatically extract features and uncover potential patterns in data, minimizing the influence of subjective factors such as selecting features artificially. A transfer-learning-based model was proposed for the electronic nose to detect the freshness of chicken breasts in this study. First, a 3D-printed electronic nose system is used to collect the odor data from chicken breast samples stored at 4 °C for 1–7 d. Then, three conversion to images methods are used to feed the recorded time series data into the convolutional neural network. Finally, the pre-trained AlexNet, GoogLeNet, and ResNet models are retrained in the last three layers while being compared to classic machine learning methods such as K Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machines (SVM). The final accuracy of ResNet is 99.70%, which is higher than the 94.33% correct rate of the popular machine learning model SVM. Therefore, the electronic nose combined with conversion to images shows great potential for using deep transfer learning methods for chicken freshness classification. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Global Reconstruction Method of Maize Population at Seedling Stage Based on Kinect Sensor

and

Agriculture 2023, 13(2), 348; https://doi.org/10.3390/agriculture13020348 - 31 Jan 2023

Viewed by 724

Abstract

Automatic plant phenotype measurement technology based on the rapid and accurate reconstruction of maize structures at the seedling stage is essential for the early variety selection, cultivation, and scientific management of maize. Manual measurement is time-consuming, laborious, and error-prone. The lack of mobility of large equipment in the field make the high-throughput detection of maize plant phenotypes challenging. Therefore, a global 3D reconstruction algorithm was proposed for the high-throughput detection of maize phenotypic traits. First, a self-propelled mobile platform was used to automatically collect three-dimensional point clouds of maize seedling populations from multiple measurement points and perspectives. Second, the Harris corner detection algorithm and singular value decomposition (SVD) were used for the pre-calibration single measurement point multi-view alignment matrix. Finally, the multi-view registration algorithm and iterative nearest point algorithm (ICP) were used for the global 3D reconstruction of the maize seedling population. The results showed that the R² of the plant height and maximum width measured by the global 3D reconstruction of the seedling maize population were 0.98 and 0.99 with RMSE of 1.39 cm and 1.45 cm and mean absolute percentage errors (MAPEs) of 1.92% and 2.29%, respectively. For the standard sphere, the percentage of the Hausdorff distance set of reconstruction point clouds less than 0.5 cm was 55.26%, and the percentage was 76.88% for those less than 0.8 cm. The method proposed in this study provides a reference for the global reconstruction and phenotypic measurement of crop populations at the seedling stage, which aids in the early management of maize with precision and intelligence. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Risk Assessment and Application of Tea Frost Hazard in Hangzhou City Based on the Random Forest Algorithm

and

Agriculture 2023, 13(2), 327; https://doi.org/10.3390/agriculture13020327 - 29 Jan 2023

Viewed by 675

Abstract

Using traditional tea frost hazard risk assessment results as sample data, the four indicators of minimum temperature, altitude, tea planting area, and tea yield were selected to consider the risk of hazard-causing factors, the exposure of hazard-bearing bodies, and the vulnerability of hazard-bearing bodies. The random forest algorithm was used to construct the frost hazard risk assessment model of Hangzhou tea, and hazard risk assessment was carried out on tea with different cold resistances in Hangzhou. The model’s accuracy reached 93% after training, and the interpretation reached more than 0.937. According to the risk assessment results of tea with different cold resistance, the high-risk areas of weak cold resistance tea were the most, followed by medium cold resistance and the least strong cold resistance. Compared with the traditional method, the prediction result of the random forest model has a deviation of only 1.57%. Using the random forest model to replace the artificial setting of the weight factor in the traditional method has the advantages of simple operation, high time efficiency, and high result accuracy. The prediction results have been verified by the existing hazard data. The model conforms to the actual situation and has certain guiding for local agricultural production and early warning of hazards. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

A Cascaded Individual Cow Identification Method Based on DeepOtsu and EfficientNet

and

Agriculture 2023, 13(2), 279; https://doi.org/10.3390/agriculture13020279 - 23 Jan 2023

Cited by 1 | Viewed by 886

Abstract

Precision dairy farming technology is widely used to improve the management efficiency and reduce cost in large-scale dairy farms. Machine vision systems are non-contact technologies to obtain individual and behavioral information from animals. However, the accuracy of image-based individual identification of dairy cows is still inadequate, which limits the application of machine vision technologies in large-scale dairy farms. There are three key problems in dairy cattle identification based on images and biometrics: (1) the biometrics of different dairy cattle may be similar; (2) the complex shooting environment leads to the instability of image quality; and (3) for the end-to-end identification method, the identity of each cow corresponds to a pattern, and the increase in the number of cows will lead to a rapid increase in the number of outputs and parameters of the identification model. To solve the above problems, this paper proposes a cascaded dairy individual cow identification method based on DeepOtsu and EfficientNet, which can realize a breakthrough in dairy cow group identification accuracy and speed by binarization and cascaded classification of dairy cow body pattern images. The specific implementation steps of the proposed method are as follows. First, the YOLOX model was used to locate the trunk of the cow in the side-looking walking image to obtain the body pattern image, and then, the DeepOtsu model was used to binarize the body pattern image. After that, primary classification was carried out according to the proportion of black pixels in the binary image; then, for each subcategory obtained by the primary classification, the EfficientNet-B1 model was used for secondary classification to achieve accurate and rapid identification of dairy cows. A total of 11,800 side-looking walking images of 118 cows were used to construct the dataset; and the training set, validation set, and test set were constructed at a ratio of 5:3:2. The test results showed that the binarization segmentation accuracy of the body pattern image is 0.932, and the overall identification accuracy of the individual cow identification method is 0.985. The total processing time of a single image is 0.433 s. The proposed method outperforms the end-to-end dairy individual cow identification method in terms of efficiency and training speed. This study provides a new method for the identification of individual dairy cattle in large-scale dairy farms. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Extracting Tea Plantations from Multitemporal Sentinel-2 Images Based on Deep Learning Networks

and

Agriculture 2023, 13(1), 10; https://doi.org/10.3390/agriculture13010010 - 21 Dec 2022

Viewed by 1144

Abstract

Tea is a special economic crop that is widely distributed in tropical and subtropical areas. Timely and accurate access to the distribution of tea plantation areas is crucial for effective tea plantation supervision and sustainable agricultural development. Traditional methods for tea plantation extraction are highly dependent on feature engineering, which requires expensive human and material resources, and it is sometimes even difficult to achieve the expected results in terms of accuracy and robustness. To alleviate such problems, we took Xinchang County as the study area and proposed a method to extract tea plantations based on deep learning networks. Convolutional neural network (CNN) and recurrent neural network (RNN) modules were combined to build an R-CNN model that can automatically obtain both spatial and temporal information from multitemporal Sentinel-2 remote sensing images of tea plantations, and then the spatial distribution of tea plantations was predicted. To confirm the effectiveness of our method, support vector machine (SVM), random forest (RF), CNN, and RNN methods were used for comparative experiments. The results show that the R-CNN method has great potential in the tea plantation extraction task, with an F1 score and IoU of 0.885 and 0.793 on the test dataset, respectively. The overall classification accuracy and kappa coefficient for the whole region are 0.953 and 0.904, respectively, indicating that this method possesses higher extraction accuracy than the other four methods. In addition, we found that the distribution index of tea plantations in mountainous areas with gentle slopes is the highest in Xinchang County. This study can provide a reference basis for the fine mapping of tea plantation distributions. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Utility of Deep Learning Algorithms in Initial Flowering Period Prediction Models

and

Agriculture 2022, 12(12), 2161; https://doi.org/10.3390/agriculture12122161 - 15 Dec 2022

Viewed by 886

Abstract

The application of a deep learning algorithm (DL) can more accurately predict the initial flowering period of Platycladus orientalis (L.) Franco. In this research, we applied DL to establish a nationwide long-term prediction model of the initial flowering period of P. orientalis and analyzed the contribution rate of meteorological factors via Shapely Additive Explanation (SHAP). Based on the daily meteorological data of major meteorological stations in China from 1963–2015 and the observation of initial flowering data from 23 phenological stations, we established prediction models by using recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R²) were used as training effect indicators to evaluate the prediction accuracy. The simulation results show that the three models are applicable to the prediction of the initial flowering of P. orientalis nationwide in China, with the average accuracy of the GRU being the highest, followed by LSTM and the RNN, which is significantly higher than the prediction accuracy of the regression model based on accumulated air temperature. In the interpretability analysis, the factor contribution rates of the three models are similar, the 46 temperature type factors have the highest contribution rate with 58.6% of temperature factors’ contribution rate being higher than 0 and average contribution rate being 5.48 × 10⁻⁴, and the stability of the contribution rate of the factors related to the daily minimum temperature factor has obvious fluctuations with an average standard deviation of 8.57 × 10⁻³, which might be related to the plants being sensitive to low temperature stress. The GRU model can accurately predict the change rule of the initial flowering, with an average accuracy greater than 98%, and the simulation effect is the best, indicating that the potential application of the GRU model is the prediction of initial flowering. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Research on Laying Hens Feeding Behavior Detection and Model Visualization Based on Convolutional Neural Network

and

Agriculture 2022, 12(12), 2141; https://doi.org/10.3390/agriculture12122141 - 13 Dec 2022

Viewed by 795

Abstract

The feeding behavior of laying hens is closely related to their health and welfare status. In large-scale breeding farms, monitoring the feeding behavior of hens can effectively improve production management. However, manual monitoring is not only time-consuming but also reduces the welfare level of breeding staff. In order to realize automatic tracking of the feeding behavior of laying hens in the stacked cage laying houses, a feeding behavior detection network was constructed based on the Faster R-CNN network, which was characterized by the fusion of a 101 layers-deep residual network (ResNet101) and Path Aggregation Network (PAN) for feature extraction, and Intersection over Union (IoU) loss function for bounding box regression. The ablation experiments showed that the improved Faster R-CNN model enhanced precision, recall and F1-score from 84.40%, 72.67% and 0.781 to 90.12%, 79.14%, 0.843, respectively, which could enable the accurate detection of feeding behavior of laying hens. To understand the internal mechanism of the feeding behavior detection model, the convolutional kernel features and the feature maps output by the convolutional layers at each stage of the network were then visualized in an attempt to decipher the mechanisms within the Convolutional Neural Network(CNN) and provide a theoretical basis for optimizing the laying hens’ behavior recognition network. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Design of a Machine Vision-Based Automatic Digging Depth Control System for Garlic Combine Harvester

and

Agriculture 2022, 12(12), 2119; https://doi.org/10.3390/agriculture12122119 - 09 Dec 2022

Cited by 1 | Viewed by 1021

Abstract

The digging depth is an important factor affecting the mechanized garlic harvesting quality. At present, the digging depth of the garlic combine harvester (GCH) is adjusted manually, which leads to disadvantages such as slow response, poor accuracy, and being very dependent on the operator’s experience. To solve this problem, this paper proposes a machine vision-based automatic digging depth control system for the original garlic digging device. The system uses the improved YOLOv5 algorithm to calculate the length of the garlic root at the front end of the clamping conveyor chain in real-time, and the calculation result is sent back to the system as feedback. Then, the STM32 microcontroller is used to control the digging depth by expanding and contracting the electric putter of the garlic digging device. The experimental results of the presented control system show that the detection time of the system is 30.4 ms, the average accuracy of detection is 99.1%, and the space occupied by the model deployment is 11.4 MB, which suits the design of the real-time detection of the system. Moreover, the length of the excavated garlic roots is shorter than that of the system before modification, which represents a lower energy consumption of the system and a lower rate of impurities in harvesting, and the modified system is automatically controlled, reducing the operator’s workload. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Open AccessArticle

Frequency-Enhanced Channel-Spatial Attention Module for Grain Pests Classification

and

Agriculture 2022, 12(12), 2046; https://doi.org/10.3390/agriculture12122046 - 29 Nov 2022

Viewed by 1622

Abstract

For grain storage and protection, grain pest species recognition and population density estimation are of great significance. With the rapid development of deep learning technology, many studies have shown that convolutional neural networks (CNN)-based methods perform extremely well in image classification. However, such studies on grain pest classification are still limited in the following two aspects. Firstly, there is no high-quality dataset of primary insect pests specified by standard ISO 6322-3 and the Chinese Technical Criterion for Grain and Oil-seeds Storage (GB/T 29890). The images of realistic storage scenes bring great challenges to the identification of grain pests as the images have attributes of small objects, varying pest shapes and cluttered backgrounds. Secondly, existing studies mostly use channel or spatial attention mechanisms, and as a consequence, useful information in other domains has not been fully utilized. To address such limitations, we collect a dataset named GP10, which consists of 1082 primary insect pest images in 10 species. Moreover, we involve discrete wavelet transform (DWT) in a convolutional neural network to construct a novel triple-attention network (FcsNet) combined with frequency, channel and spatial attention modules. Next, we compare the network performance and parameters against several state-of-the-art networks based on different attention mechanisms. We evaluate the proposed network on our dataset GP10 and open dataset D0, achieving classification accuracy of 73.79% and 98.16%. The proposed network obtains more than 3% accuracy gains on the challenging dataset GP10 with parameters and computation operations slightly increased. Visualization with gradient-weighted class activation mapping (Grad-CAM) demonstrates that FcsNet has comparative advantages in image classification tasks. Full article

(This article belongs to the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Special Issue "Application of Vision Technology and Artificial Intelligence in Smart Farming"

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (16 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI