Figure - available via license: CC BY
Content may be subject to copyright.
Source publication
A machine vision system for detecting apples in orchards was developed. The system was designed to be used in harvesting robots and is based on a YOLOv3 algorithm with special pre- and post-processing. The proposed pre- and post-processing techniques made it possible to adapt the YOLOv3 algorithm to be used in an apple-harvesting robot machine visi...
Contexts in source publication
Context 1
... results of apple detection quality evaluation are presented in Table 2, and Figure 11 presents the Precision-Recall curves. ...Context 2
... results of apple detection quality evaluation are presented in Table 2, and Figure 11 presents the Precision-Recall curves. Table 2. Apple detection quality metrics. ...Citations
... Similarly, a previous study was conducted [21] by applying YOLO v3 with advanced pre-and post-processing techniques for apple identification, highlighting the evolution of computer vision algorithms to meet the demands of modern horticulture. The improvements implemented resulted in reduced error rates and average identification time, making the system more efficient and comprehensive than previous versions, such as the faster region-based convolutional neural network (RCNN) and dynamic activation sparsity network (DaSNet) v2. ...
The rapid evolution of digital technology and the increasing integration of artificial intelligence in agriculture have paved the way for groundbreaking solutions in plant identification. This research pioneers the development and training of a deep learning model to identify three aromatic plants—rosemary, mint, and bay leaf—using advanced computer-aided detection within the You Only Look Once (YOLO) framework. Employing the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology, the study meticulously covers data understanding, preparation, modeling, evaluation, and deployment phases. The dataset, consisting of images from diverse devices and annotated with bounding boxes, was instrumental in the training process. The model’s performance was evaluated using the mean average precision at a 50% intersection over union (mAP50), a metric that combines precision and recall. The results demonstrated that the model achieved a precision of 0.7 or higher for each herb, though recall values indicated potential over-detection, suggesting the need for database expansion and methodological enhancements. This research underscores the innovative potential of deep learning in aromatic plant identification and addresses both the challenges and advantages of this technique. The findings significantly advance the integration of artificial intelligence in agriculture, promoting greater efficiency and accuracy in plant identification.
... With a mean average precision of 97.13% for detecting apples, a recall rate of 90.00%, and a detection speed of 51 f/s, the Des-YOLO v4 network boasts excellent characteristics. Kuznetsova et al.[61] developed an automated technique for spotting apples in orchards. The system was created for harvesting robots based on the YOLOv3 algorithm with unique pre-and post-processing. ...
Harvesting apples is one of the most apple-challenging operations; its process is labor-intensive, and for various reasons, automation has yet to advance as swiftly as it might. Researchers have concentrated on developments in robotics and automated apple harvesting, two domains with a plethora of opportunities and difficulties that require more evaluation for future growth and quality. In this paper, we provide an overview of apple harvesting by beginning with a perspective that focuses on vision techniques and recognition systems. We then cover the outcomes, methods, time, and observations via robust analysis, including visible light, spectral, and thermal imaging. After that, we were followed by the localization of the apple, which aids in detaching apples from branches, leaves, and other overlapping apples, besides directing end-effectors to grip and remove apples. Next, the harvester robots progress includes developments in machinery and equipment that contain grippers, arms, and manipulators, which speed up operations and upgrade performance. Additionally, the platforms that provide aid for harvesting boost productivity, reduce the demand for strength, and lower the danger of accidents at work. Furthermore, the discussion part includes a comprehensive analysis covering works on apple detection systems and automated apple harvesting robot technology. Finally, we summarize the challenges, limitations, opportunities, and future perspectives and provide the trends and technologies. This research offers several avenues for future automated apple harvesting advancement and interaction with other fields that attract investment firms, such as sorting and bagging. Assist in sustaining the expansion of research communities and offering services to raise the yield and quality of apple fruit.
... In recent years, researchers both domestically and internationally have made remarkable strides in leveraging deep learning techniques coupled with computer vision technology for agricultural applications [4][5][6]. You Only Look Once (YOLO) has garnered considerable attention as an advanced real-time target detection algorithm owing to its exceptional efficiency, speed, and accuracy [7][8][9]. ...
Accurate detection of muskmelon fruit ripeness is crucial to ensure fruit quality, optimize picking time, and enhance economic benefits. This study proposes an improved lightweight YOLO-RFEW model based on YOLOv8n, aiming to address the challenges of low efficiency in muskmelon fruit ripeness detection and the complexity of deploying a target detection model to a muskmelon picking robot. Firstly, the RFAConv replaces the Conv in the backbone part of YOLOv8n, allowing the network to focus more on regions with significant contributions in feature extraction. Secondly, the feature extraction and fusion capability are enhanced by improving the C2f module into a C2f-FE module based on FasterNet and an Efficient Multi-Scale attention (EMA) mechanism within the lightweight model. Finally, Weighted Intersection over Union (WIoU) is optimized as the loss function to improve target frame prediction capability and enhance target detection accuracy. The experimental results demonstrate that the YOLO-RFEW model achieves high accuracy, with precision, recall, F1 score, and mean Average Precision (mAP) values of 93.16%, 83.22%, 87.91%, and 90.82%, respectively. Moreover, it maintains a lightweight design and high efficiency with a model size of 4.75 MB and an inference time of 1.5 ms. Additionally, in the two types of maturity tests (M-u and M-r), APs of 87.70% and 93.94% are obtained, respectively, by the YOLO-RFEW model. Compared to YOLOv8n, significant improvements in detection accuracy have been achieved while reducing both model size and computational complexity using the proposed approach for muskmelon picking robots’ real-time detection requirements. Furthermore, when compared to lightweight models such as YOLOv3-Tiny, YOLOv4-Tiny, YOLOv5s, YOLOv7-Tiny, YOLOv8s, and YOLOv8n, the YOLO-RFEW model demonstrates superior performance with only 28.55%, 22.42%, 24.50%, 40.56%, 22.12%, and 79.83% of their respective model sizes, respectively, while achieving the highest F1 score and mAP values among these seven models. The feasibility and effectiveness of our improved scheme are verified through comparisons between thermograms generated by YOLOv8n and YOLO-RFEW as well as detection images. In summary, the YOLO-RFEW model not only improves the accuracy rate of muskmelon ripeness detection but also successfully realizes the lightweight and efficient performance, which has important theoretical support and application value in the field of muskmelon picking robot development.
... Deep convolutional neural networks (CNN or DCNN) combine the ability to recognize objects by shape, color, and texture. Computer vision (CV) and YOLOv3 algorithm may be successfully used, with a precision of over 92%, by harvesting robots for fruit detection and yield counting, as described in [32]. AI, CV, and YOLO can also help in the real-time detection of crop diseases, e.g., early blight disease in potato fields, apple scab and rust, or grapevine disease, just to name a few [51]. ...
This study explores crop yield forecasting through weight agnostic neural networks (WANN) optimized by a modified metaheuristic. WANNs offer the potential for lighter networks with shared weights, utilizing a two-layer cooperative framework to optimize network architecture and shared weights. The proposed metaheuristic is tested on real-world crop datasets and benchmarked against state-of-the-art algorithms using standard regression metrics. While not claiming WANN as the definitive solution, the model demonstrates significant potential in crop forecasting with lightweight architectures. The optimized WANN models achieve a mean absolute error (MAE) of 0.017698 and an R-squared (R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$R^2$$\end{document}) score of 0.886555, indicating promising forecasting performance. Statistical analysis and Simulator for Autonomy and Generality Evaluation (SAGE) validate the improvement significance and feature importance of the proposed approach.
... In recent years, convolutional neural networks that can effectively learn features from training samples, particularly in image data analysis, have been widely used in agriculture and forestry. Kuznetsova et al. [15] used Yolov3 as the detection system for a fruitpicking robot and achieved the results, with an average apple detection time of 19 ms, 7.8% misidentified apples, and 9.2% unidentified apples. Cai et al. [16] proposed a method for segmenting spotted fragrant tree leaf images using a modified DeepLabv3+ network. ...
Wood volume is an important indicator in timber trading, and log diameter is one of the primary parameters used to calculate wood volume. Currently, the most common methods for measuring log diameters are manual measurement or visual estimation by log scalers, which are laborious, time consuming, costly, and error prone owing to the irregular placement of logs and large numbers of roots. Additionally, this approach can easily lead to misrepresentation of data for profit. This study proposes a model for automatic log diameter measurement that is based on deep learning and uses images to address the existing problems. The specific measures to improve the performance and accuracy of log-diameter detection are as follows: (1) A dual network model is constructed combining the Yolov3 algorithm and DeepLabv3+ architecture to adapt to different log-end color states that considers the complexity of log-end faces. (2) AprilTag vision library is added to estimate the camera position during image acquisition to achieve real-time adjustment of the shooting angle and reduce the effect of log-image deformation on the results. (3) The backbone network is replaced with a MobileNetv2 convolutional neural network to migrate the model to mobile devices, which reduces the number of network parameters while maintaining detection accuracy. The training results show that the mean average precision of log-diameter detection reaches 97.28% and the mean intersection over union (mIoU) of log segmentation reaches 92.22%. Comparisons with other measurement models demonstrate that the proposed model is accurate and stable in measuring log diameter under different environments and lighting conditions, with an average accuracy of 96.26%. In the forestry test, the measurement errors for the volume of an entire truckload of logs and a single log diameter are 1.20% and 0.73%, respectively, which are less than the corresponding error requirements specified in the industry standards. These results indicate that the proposed method can provide a viable and cost-effective solution for measuring log diameters and offering the potential to improve the efficiency of log measurement and promote fair trade practices in the lumber industry.
... Such techniques have proven crucial for addressing intricate challenges like crop detection, fruit segmentation, and produce classification. For example, in [20,21], deep learning algorithms were applied for apple detection and segmentation. For agricultural device optimization, the authors of [22][23][24] used deep learning techniques to estimate the cone angle of the spray and the droplet characteristics. ...
Soil sampling constitutes a fundamental process in agriculture, enabling precise soil analysis and optimal fertilization. The automated selection of accurate soil sampling locations representative of a given field is critical for informed soil treatment decisions. This study leverages recent advancements in deep learning to develop efficient tools for generating soil sampling maps. We proposed two models, namely UDL and UFN, which are the results of innovations in machine learning architecture design and integration. The models are meticulously trained on a comprehensive soil sampling dataset collected from local farms in South Dakota. The data include five key attributes: aspect, flow accumulation, slope, normalized difference vegetation index, and yield. The inputs to the models consist of multispectral images, and the ground truths are highly unbalanced binary images. To address this challenge, we innovate a feature extraction technique to find patterns and characteristics from the data before using these refined features for further processing and generating soil sampling maps. Our approach is centered around building a refiner that extracts fine features and a selector that utilizes these features to produce prediction maps containing the selected optimal soil sampling locations. Our experimental results demonstrate the superiority of our tools compared to existing methods. During testing, our proposed models exhibit outstanding performance, achieving the highest mean Intersection over Union of 60.82% and mean Dice Coefficient of 73.74%. The research not only introduces an innovative tool for soil sampling but also lays the foundation for the integration of traditional and modern soil sampling methods. This work provides a promising solution for precision agriculture and soil management.
... AI applications can be used in robotic applications as well as in the disease detection of fruits. Kuznetsova et al. (2020) detected the fruits on the apple tree and collected them by the harvesting robot using the YOLOv3 model and 91% accuracy was obtained using the data set consisting of 878 apples to detect apple fruit. YOLOv4 and YOLOv4-dense models were used to increase crop productivity by following the development of cherry trees (Gai et al., 2021). ...
Purpose
Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).
Design/methodology/approach
Two approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.
Findings
In Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.
Originality/value
An original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.
... Since 2019, Zhejiang waxberry has been exported to Europe, the United States and other regions, and the unit price of shipping a waxberry can reach 1 euro, and demand exceeds supply. However, Waxberry has a long growth cycle, with less than one month of picking time in a year, and is usually picked manually [2]. However, as the picking period is affected by typhoons and rain, some Waxberry fruits are not picked in time before the onset of the rainy season due to workforce shortages. ...
In order to solve the safety and efficiency problems in the picking process of Waxberry, the slow speed and low precision of high‐density Waxberry target detection under a complex background were studied. A lightweight Waxberry target detection algorithm based on YOLOv5 is studied. In this study, C3‐Faster1 and C3‐Faster2 modules are proposed, which are located in the backbone and neck of the network: C3‐Faster1 can improve the model speed with a simple structure; C3‐Faster2 integrates the context attention mechanism and transform module based on C3‐Faster1 to make the network pay attention to the information of Waxberry image context and expand the channel receptive field. A new pyramid module, SPPFCSPC, is proposed to expand the sensing field and improve the accuracy of boundary detection. It also combines the Coordinate Attention (CA) and Dyhead dynamic detection head to suppress useless information and enhance the detection ability of small targets. Compared to YOLOv4, YOLOv7, and YOLOv8, mean accuracy percentage (mAP) improved by 5.7%, 9.4%, 8.3%. Compared to the base YOLOv5 model, mAP has improved from 86.5% to 91.9%, running on 2 GB Jeston nano, and the improved model is 5.03 frames per second (FPS) faster than YOLOv5. Experiments show that the designed module is more effective in Waxberry detection tasks.
... Fruit and vegetable-picking robots are generally composed of robotic arm, end-effector, mobile mechanism, and control system. In recent years, scholars have conducted a series of studies on fruit and vegetable picking robots such as kiwifruit Gao et al., 2023), apple (Miao and Zheng, 2019;Kuznetsova et al., 2020), citrus (Mehta and Burks, 2014;Sun et al., 2023), tomato (Ling et al., 2019;Wang T. et al., 2023) and so on. For example, Williams et al. (2020) designed a four-armed parallel kiwifruitpicking robot, which separated the fruit from the stalk by rotation after the end-effector gripped the kiwifruit with two fingers, the fruit was automatically collected into a fruit box after each picking action the average time required for harvesting each fruit was 5.5 seconds, with a fruit recognition rate of 76.3% and a successful harvesting rate of 51%. ...
Currently kiwifruit picking process mainly leverages manual labor, which has low productivity and high labor intensity, meanwhile, the existing kiwifruit picking machinery also has low picking efficiency and easily damages fruits. In this regard, a kiwifruit picking robot suitable for orchard operations was developed in this paper for kiwifruit grown in orchard trellis style. First, based on the analysis of kiwifruit growth pattern and cultivation parameters, the expected design requirements and objectives of a kiwifruit picking robot were proposed, and the expected workflow of the robot in the kiwifruit orchard environment was given, which in turn led to a multi-fruit envelope-cutting kiwifruit picking robot was designed. Then, the D-H method was used to establish the kinematic Equations of the kiwifruit-picking robot, the forward and inverse kinematic calculations were carried out, and the Monte Carlo method was used to analyze the workspace of the robot. By planning the trajectory of the robotic arm and calculating critical nodes in the picking path, the scheme of trajectory planning of the robot was given, and MATLAB software was applied to simulate the motion trajectory as well as to verify the feasibility of the trajectory planning scheme and the picking strategy. Finally, a kiwifruit picking test bed was set up to conduct picking tests in the form of fruit clusters. The results show that the average time to pick each cluster of fruit was 9.7s, the picking success rate was 88.0%, and the picking damage rate was 7.3%. All the indicators met the requirements of the expected design of the kiwifruit-picking robot.
... Method Pros and cons 19,20 Threshold and circle fitting High false detection rate and lack of reliability 21,22 Support vector machine (SVM) Simple to implement, over fitting, and reduced detection accuracy [23][24][25] Digital twin (DT) and texture classifier Complex in detection, more time consumption for training and testing 26,27 Faster recurrent neural network (RCNN) High computational complexity, and lack of scalability [28][29][30] Semantic segmentation and VGG Over fitting, computational burden, and high training and testing time 31,32 Adaptive threshold and fusion Low detection rate, inaccurate, and lack of reliability [33][34][35] Single shot detection Ineffective, and high false detection ...
This paper proposes and executes an in-depth learning-based image processing approach for self-picking apples. The system includes a lightweight one-step detection network for fruit recognition. As well as computer vision to analyze the point class and anticipate a correct approach position for each fruit before grabbing. Using the raw inputs from a high-resolution camera, fruit recognition and instance segmentation are done on RGB photos. The computer vision classification and grasping systems are integrated and outcomes from tree-grown foods are provided as input information and output methodology poses for every apple and orange to robotic arm execution. Before RGB picture data is acquired from laboratory and plantation environments, the developed vision method will be evaluated. Robot harvest experiment is conducted in indoor as well as outdoor to evaluate the proposed harvesting system's performance. The research findings suggest that the proposed vision technique can control robotic harvesting effectively and precisely where the success rate of identification is increased above 95% in case of post prediction process with reattempts of less than 12%.
