Figure - available from: Journal of Sensors
This content is subject to copyright. Terms and conditions apply.
Diagram of two algorithms and key steps. (a) Flow chart of fruit identification and positioning based on HOG + SVM algorithm. (b) Flow chart of fruit identification and positioning based on YOLOv5 algorithm.
Source publication
The mechanization and intelligentization of the production process are the main trends in research and development of agricultural products. The realization of an unmanned and automated picking process is also one of the main research hotspots in China’s agricultural product engineering technology field in recent years. The development of automated...
Similar publications
In the complex environment of orchards, in view of low fruit recognition accuracy, poor real-time and robustness of traditional recognition algorithms, this paper propose an improved fruit recognition algorithm based on deep learning. Firstly, the residual module was assembled with the cross stage parity network (CSP Net) to optimize recognition pe...
Citations
... In 2020, YOLOv5 [18] was introduced, shocking the world with its extremely fast detection speed, making it an ideal candidate for real-time conditions and mobile deployment environments. The related studies [19][20][21][22][23][24] have made lightweight improvements to the YOLOv5s version based on different domains. ...
Foreign objects easily attach to the transmission lines because of the various laying methods and the complex, changing environment. They have a significant impact on the safe operation capability of transmission lines if these foreign objects are not detected and removed in time. An improved YOLOv5 technique is provided to detect foreign objects in transmission lines due to the low-foreign object recognition accuracy image detection. The method first reduces the computation and memory consumption by introducing the RepConv structure, further improves the detection accuracy and speed of the model by embedding the C2F structure. This method finally is further optimized neural network by the Meta-ACON activation function. The results indicate that the average detection accuracy of the improved YOLOv5 network can reach 96.9%, which is 2.2% higher than before. Additionally, corresponding detection speed can reach 258.36 frames/second, which surpasses existing mainstream target detection models, performing better in terms of the balance of inference speed and detection accuracy. Consequently, the effectiveness and superiority of the algorithm have been proved.
... Uddhav Bhattarai and Manoj Karkee [19] proposed CountNet, a weakly supervised flower/fruit counting network based on deep learning, to learn the number of objects from image-level annotations as input, yielding good MAE and EMSE in an orchard setting. Qian et al. [20] proposed HOG+SVM and an improved YOLOv5-based method for fast recognition of multiple apples in complex environments with parameter reconstruction, the inclusion of an attention mechanism module and finetuning of the loss function to better extract the features of different apples and improve the recognition ability of the model. Jan Weyler et al. [21] proposed a method to predict the bounding boxes of crops and weeds automatically, as well as the key points of leaves, with a good ability to estimate leaf numbers, and this method achieved excellent performance in complex scenarios with overlapping plants at different growth stages compared to Mask R-CNN. ...
Weather disturbances, difficult backgrounds, the shading of fruit and foliage, and other elements can significantly affect automated yield estimation and picking in small target apple orchards in natural settings. This study uses the MinneApple public dataset, which is processed to construct a dataset of 829 images with complex weather, including 232 images of fog scenarios and 236 images of rain scenarios, and proposes a lightweight detection algorithm based on the upgraded YOLOv7-tiny. In this study, a backbone network was constructed by adding skip connections to shallow features, using P2BiFPN for multi-scale feature fusion and feature reuse at the neck, and incorporating a lightweight ULSAM attention mechanism to reduce the loss of small target features, focusing on the correct target and discard redundant features, thereby improving detection accuracy. The experimental results demonstrate that the model has an mAP of 80.4% and a loss rate of 0.0316. The mAP is 5.5% higher than the original model, and the model size is reduced by 15.81%, reducing the requirement for equipment; In terms of counts, the MAE and RMSE are 2.737 and 4.220, respectively, which are 5.69% and 8.97% lower than the original model. Because of its improved performance and stronger robustness, this experimental model offers fresh perspectives on hardware deployment and orchard yield estimation.
... For example, in [1] the authors try to detect leaf miners in tomato plants by applying two types of deep neural networks to classify and segment plant images, while in [2] a convolutional neural network is used to predict some growth indices of lettuce plants, always using image data. In [3] the target crop regards apples and in particular the classification of their maturation degree in order to facilitate the work of picking robots. This is achieved by exploiting histograms of oriented gradients, SVM, and a fast identification technique for multiple targets, very suitable for a complex occlusion environment. ...
Water stress and in particular drought are some of the most significant factors affecting plant growth, food production, and thus food security. Furthermore, the possibility to predict and shape irrigation on real plant demands is priceless. The objective of this study is to characterize, classify, and forecast water stress in tomato plants by means of in vivo real time data obtained through a novel sensor, named bioristor, and of different artificial intelligence models. First of all, we have applied classification models, namely Decision Trees and Random Forest, to try to distinguish four different stress statuses of tomato plants. Then we have predicted, through the help of recurrent neural networks, the future status of a plant when considering both a binary (water stressed and not water stressed) and a four-status scenario. The obtained results are very good in terms of accuracy, precision, recall, f-measure, and of the resulting confusion matrices, and they suggest that the considered novel data and features coming from the bioristor, together with the used AI models, can be successfully applied, in the future, to a real-world on-the-field smart irrigation scenario.
This study reviews the advancement of apple-related technology in six distinct domains: pruning, pollinating, thinning, bagging, harvesting, and sorting. Firstly, the pruning section discusses machine vision systems and moves on to mechanical branch-cutting methods, followed by automated apple pruning. Secondly, concerning pollination, we primarily focus on the growth of apple fruits, beginning with identifying blossoms, using artificial pollen, and mechanized pollination. Thirdly, in the thinning section, a review of achievements of the vision systems and mechanical and robotic thinning technologies. Fourthly, in apple bagging, we address the effects of apple bagging strategies, including the primary procedures, varieties of bags, and influencing aspects. Next, in the harvesting part, the view focuses on the vision strategies and recognition systems that include visible light,
spectral, and thermal imaging by means of thorough analysis that considers the time, observations, techniques, and findings. After that, the localization of the apple assists in separating apples such as leaves, branches, and other overlapping apples, in addition to instructing end-effectors on how to grasp and extract apples. Furthermore, harvester robots’ progress includes developments in machinery, grippers, arms, and manipulators, besides the assistance platforms for harvesting. Developing the machinery for sorting apples is the final area of focus. The
machinery includes conveyors, sorting executors, and bin fillers. Vision systems imaging types and methods are followed by illumination systems, and identification strategies such as machine and deep learning algorithms are considered. In limitations and future views, we summarize the challenges of the six distinct domains and provide opportunities and future perspectives. By confirming the economic advantages and sustaining the expansion of academic organizations for technology development and industry, the study assists in boosting apple fruit quality and production.
Red jujube is one of the most important crops in China. In order to meet the needs of the scientific and technological development of the jujube industry, solve the problem of poverty, realize the backward advantage, and promote economic development, smart agriculture is essential. The main objective of this study was to conduct an online detection study of unpicked red jujubes in order to detect as many red jujubes in the picture as possible while minimizing the occurrence of overfitting and underfitting. Experiments were conducted using the Histogram of Oriented Gradients + Support Vector Machine (HOG+SVM) traditional detection method and the You Only Look Once version 5 (YOLOV5) and Faster R-CNN modern deep learning detection methods. The precision, recall, and F1 score were compared to obtain a better algorithm. The study also introduced the AlexNet model with the main objective of attempting to combine it with other traditional algorithms to maximize accuracy. Labeling was used to label the training images in YOLOV5 and Faster Regions with CNN Features (Faster R-CNN) to train the machine model so that the computer recognized these features when it saw new unlabeled data in subsequent experiments. The experimental results show that in the online recognition detection of red jujubes, the YOLOV5 and Faster R-CNN algorithms performed better than the HOG + SVM algorithm, which presents precision, recall, and F1 score values of 93.55%, 82.79%, and 87.84% respectively; although the HOG + SVM algorithm was relatively quicker to perform. The precision of detection was obviously more important than the efficiency of detection in this study, so the YOLOV5 and Faster R-CNN algorithms were better than the HOG + SVM algorithm. In the experiments, the Faster R-CNN algorithm had 100% precision, 99.65% recall, an F1 score of 99.82%, and 83% non-underfitting images for the recognized images, all of which were higher than YOLOV5′s values, with 97.17% recall, an F1 score of 98.56%, and 64.42% non-underfitting. In this study, therefore, the Faster R-CNN algorithm works best.
