Search

The agriculture sector plays a very important role in the increasing population, year by year, to fulfill requirements and contributes significantly to the economy of the country. One of the main challenges in agriculture is the prevention and early detection of pest attack on crops. Farmers spend a significant amount of time and money in detecting pests and diseases, often by looking at plant leaves and analyzing the presence of diseases and pests. Late detection of pest attacks and improper use of pesticide application can cause damage to plants and compromise food quality. This problem can be solved through artificial intelligence, machine learning, and accurate image classification systems. In recent years, machine learning has made improvements in image recognition and classification. Hence, in this research article, we used convolutional neural network (CNN)-based models, such as the Cov2D library and VGG-16, to identify pest attacks. Our experiments involved a personal dataset consisting of 7000 images of pest-attacked leaf samples of different positions on maize plants, categorized into two classes. The Google Colab environment was used for experimentation and implementation, specially designed for cloud computing and machine learning. [ABSTRACT FROM AUTHOR]

In the present study, we used device visualization in tandem with deep learning to detect weeds in the wheat crop system in actual time. We selected the PMAS Arid Agriculture University research farm and wheat crop fields in diverse weather environments to collect the weed images. Some 6000 images were collected for the study. Throughout the season, tfhe databank was assembled to detect the weeds. For this study, we used two different frameworks, TensorFlow and PyTorch, to apply deep learning algorithms. PyTorch's implementation of deep learning algorithms performed comparatively better than that of TensorFlow. We concluded that the neural network implemented through the PyTorch framework achieves a superior outcome in speed and accuracy compared to other networks, such as YOLO variants. This work implemented deep learning models for weed detection using different frameworks. While working on real-time detection models, it is very important to consider the inference time and detection accuracy. Therefore, we have compared the results in terms of execution time and prediction accuracy. In particular, the accuracy of weed removal from wheat crops was judged to be 0.89 and 0.91, respectively, with inference times of 9.43 ms and 12.38 ms on the NVIDIA RTX2070 GPU for each picture (640 × 640). [ABSTRACT FROM AUTHOR]

The realization that mobile phones can detect rice diseases and insect pests not only solves the problems of low efficiency and poor accuracy from manually detection and reporting, but it also helps farmers detect and control them in the field in a timely fashion, thereby ensuring the quality of rice grains. This study examined two Improved detection models for the detection of six high-frequency diseases and insect pests. These models were the Improved You Only Look Once (YOLO)v5s and YOLOv7-tiny based on their lightweight object detection networks. The Improved YOLOv5s was introduced with the Ghost module to reduce computation and optimize the model structure, and the Improved YOLOv7-tiny was introduced with the Convolutional Block Attention Module (CBAM) and SIoU to improve model learning ability and accuracy. First, we evaluated and analyzed the detection accuracy and operational efficiency of the models. Then we deployed two proposed methods to a mobile phone. We also designed an application to further verify their practicality for detecting rice diseases and insect pests. The results showed that Improved YOLOv5s achieved the highest F1-Score of 0.931, 0.961 in mean average precision (mAP) (0.5), and 0.648 in mAP (0.5:0.9). It also reduced network parameters, model size, and the floating point operations per second (FLOPs) by 47.5, 45.7, and 48.7%, respectively. Furthermore, it increased the model inference speed by 38.6% compared with the original YOLOv5s model. Improved YOLOv7-tiny outperformed the original YOLOv7-tiny in detection accuracy, which was second only to Improved YOLOv5s. The probability heat maps of the detection results showed that Improved YOLOv5s performed better in detecting large target areas of rice diseases and insect pests, while Improved YOLOv7-tiny was more accurate in small target areas. On the mobile phone platform, the precision and recall of Improved YOLOv5s under FP16 accuracy were 0.925 and 0.939, and the inference speed was 374 ms/frame, which was superior to Improved YOLOv7-tiny. Both of the proposed improved models realized accurate identification of rice diseases and insect pests. Moreover, the constructed mobile phone application based on the improved detection models provided a reference for realizing fast and efficient field diagnoses. [ABSTRACT FROM AUTHOR]

During the operation of agricultural unmanned aerial vehicles (UAVs) in orchards, the presence of power poles and wires pose a serious threat to flight safety, and can even lead to crashes. Due to the difficulty of directly detecting wires, this research aimed to quickly and accurately detect wire poles, and proposed an improved Yolov5s deep learning object detection algorithm named Yolov5s-Pole. The algorithm enhances the model's generalization ability and robustness by applying Mixup data augmentation technique, replaces the C3 module with the GhostBottleneck module to reduce the model's parameters and computational complexity, and incorporates the Shuffle Attention (SA) module to improve its focus on small targets. The results show that when the improved Yolov5s-Pole model was used for detecting poles in orchards, its accuracy, recall, and mAP@50 were 0.803, 0.831, and 0.838 respectively, which increased by 0.5%, 10%, and 9.2% compared to the original Yolov5s model. Additionally, the weights, parameters, and GFLOPs of the Yolov5s-Pole model were 7.86 MB, 3,974,310, and 9, respectively. Compared to the original Yolov5s model, these represent compression rates of 42.2%, 43.4%, and 43.3%, respectively. The detection time for a single image using this model was 4.2 ms, and good robustness under different lighting conditions (dark, normal, and bright) was demonstrated. The model is suitable for deployment on agricultural UAVs' onboard equipment, and is of great practical significance for ensuring the efficiency and flight safety of agricultural UAVs. [ABSTRACT FROM AUTHOR]

Pine wilt disease (PWD) is one of the most destructive forest diseases in the world. Therefore, timely monitoring of PWD is essential to the preservation of the ecological environment. However, the complex topography of PWD-outbreak locations affords many limitations in the manual detection of the disease. The use of unmanned aerial vehicles (UAVs) and deep learning technology to detect PWD-infected trees has gained popularity in recent years. In this study, we configured the You Only Look Once version 3 (YOLOv3) model according to the characteristics of the three disease stages of PWD and proposed an improved model called Effi_YOLO_v3. The results revealed that the improved model achieved good detection performance. The proposed model yielded a mean average precision (mAP) of 94.39%, and the classification of the different infection stages was relatively accurate. The recall values for the classifications of trees in the early-infection, late-infection, and death stages were 89.15%, 86.13%, and 86.77%, respectively. This indicates that the model offers good applicability in detecting different stages of PWD in trees. [ABSTRACT FROM AUTHOR]

As an important factor determining the competitiveness of raw cotton, cotton fiber quality has received more and more attention. The results of traditional detection methods are accurate, but the sampling cost is high and has a hysteresis, which makes it difficult to measure cotton fiber quality parameters in real time and at a large scale. The purpose of this study is to use time-series UAV (Unmanned Aerial Vehicle) multispectral and RGB remote sensing images combined with machine learning to model four main quality indicators of cotton fibers. A deep learning algorithm is used to identify and extract cotton boll pixels in remote sensing images and improve the accuracy of quantitative extraction of spectral features. In order to simplify the input parameters of the model, the stepwise sensitivity analysis method is used to eliminate redundant variables and obtain the optimal input feature set. The results of this study show that the R2 of the prediction model established by a neural network is improved by 29.67% compared with the model established by linear regression. When the spectral index is calculated after removing the soil pixels used for prediction, R2 is improved by 4.01% compared with the ordinary method. The prediction model can well predict the average length, uniformity index, and micronaire value of the upper half. R2 is 0.8250, 0.8014, and 0.7722, respectively. This study provides a method to predict the cotton fiber quality in a large area without manual sampling, which provides a new idea for variety breeding and commercial decision-making in the cotton industry. [ABSTRACT FROM AUTHOR]

Obtaining the geographic coordinates of single fruit trees enables the variable rate application of agricultural production materials according to the growth differences of trees, which is of great significance to the precision management of citrus orchards. The traditional method of detecting and positioning fruit trees manually is time-consuming, labor-intensive, and inefficient. In order to obtain high-precision geographic coordinates of trees in a citrus orchard, this study proposes a method for citrus tree identification and coordinate extraction based on UAV remote sensing imagery and coordinate transformation. A high-precision orthophoto map of a citrus orchard was drawn from UAV remote sensing images. The YOLOv5 model was subsequently used to train the remote sensing dataset to efficiently identify the fruit trees and extract tree pixel coordinates from the orchard orthophoto map. According to the geographic information contained in the orthophoto map, the pixel coordinates were converted to UTM coordinates and the WGS84 coordinates of citrus trees were obtained using Gauss–Krüger inverse calculation. To simplify the coordinate conversion process and to improve the coordinate conversion efficiency, a coordinate conversion app was also developed to automatically implement the batch conversion of pixel coordinates to UTM coordinates and WGS84 coordinates. Results show that the Precision, Recall, and F1 Score for Scene 1 (after weeding) reach 0.89, 0.97, and 0.92, respectively; the Precision, Recall, and F1 Score for Scene 2 (before weeding) reach 0.91, 0.90 and 0.91, respectively. The accuracy of the orthophoto map generated using UAV remote sensing images is 0.15 m. The accuracy of converting pixel coordinates to UTM coordinates by the coordinate conversion app is reliable, and the accuracy of converting UTM coordinates to WGS84 coordinates is 0.01 m. The proposed method is capable of automatically obtaining the WGS84 coordinates of citrus trees with high precision. [ABSTRACT FROM AUTHOR]

With the rapid development in the field of computer vision, the vision-based approach to unmanned aerial vehicle (UAV) tracking and landing technology in weak global positioning system (GPS) or GPS-free environments has become prominent in military and civilian missions. However, this technique still suffers from problems such as interference by similar targets in the environment, low tracking accuracy, slow processing speed, and poor stability. To solve these problems, we propose the designated target anti-interference tracking (DTAT) method, which integrates YOLOv5 and SiamRPN, and built a system to achieve UAV tracking and the landing of a designated target in an environment with multiple interference targets. The system consists of the following parts: first, an image is acquired by a monocular camera to obtain the pixel position information of the designated target. Next, the position of the UAV relative to the target is estimated based on the pixel location information of the target and the known target size information. Finally, the discrete proportion integration differentiation (PID) control law is used to complete the target tracking and landing task of the UAV. To test the system performance, we deployed it on a robot operating system (ROS) platform, conducted many simulation experiments, and observed the real-time trajectories of the UAV and the target through Gazebo software. The results show that the relative distance between the UAV and the target during the tracking process when the target was moving at 0.6 m/s does not exceed 0.8 m, and the landing error of the UAV during the landing process after the target is stationary does not exceed 0.01 m. The results validate the effectiveness and robustness of the system and lay a foundation for subsequent research. [ABSTRACT FROM AUTHOR]

China has the largest output of litchi in the world. However, at present, litchi is mainly picked manually, fruit farmers have high labor intensity and low efficiency. This means the intelligent unmanned picking system has broad prospects. The precise location of the main stem picking point of litchi is very important for the path planning of an unmanned system. Some researchers have identified the fruit and branches of litchi; however, there is relatively little research on the location of the main stem picking point of litchi. So, this paper presents a new open-access workflow for detecting accurate picking locations on the main stems and presents data used in the case study. At the same time, this paper also compares several different network architectures for main stem detection and segmentation and selects YOLOv5 and PSPNet as the most promising models for main stem detection and segmentation tasks, respectively. The workflow combines deep learning and traditional image processing algorithms to calculate the accurate location information of litchi main stem picking points in the litchi image. This workflow takes YOLOv5 as the target detection model to detect the litchi main stem in the litchi image, then extracts the detected region of interest (ROI) of the litchi main stem, uses PSPNet semantic segmentation model to semantically segment the ROI image of the main stem, carries out image post-processing operation on the ROI image of the main stem after semantic segmentation, and obtains the pixel coordinates of picking points in the ROI image of the main stem. After coordinate conversion, the pixel coordinates of the main stem picking points of the original litchi image are obtained, and the picking points are drawn on the litchi image. At present, the workflow can obtain the accurate position information of the main stem picking point in the litchi image. The recall and precision of this method were 76.29% and 92.50%, respectively, which lays a foundation for the subsequent work of obtaining the three-dimensional coordinates of the main stem picking point according to the image depth information, even though we have not done this work in this paper. [ABSTRACT FROM AUTHOR]

Citrus psyllid is the only insect vector of citrus Huanglongbing (HLB), which is the most destructive disease in the citrus industry. There is no effective treatment for HLB, so detecting citrus psyllids as soon as possible is the key prevention measure for citrus HLB. It is time-consuming and laborious to search for citrus psyllids through artificial patrol, which is inconvenient for the management of citrus orchards. With the development of artificial intelligence technology, a computer vision method instead of the artificial patrol can be adopted for orchard management to reduce the cost and time. The citrus psyllid is small in shape and gray in color, similar to the stem, stump, and withered part of the leaves, leading to difficulty for the traditional target detection algorithm to achieve a good recognition effect. In this work, in order to make the model have good generalization ability under outdoor light condition, a high-definition camera to collect data set of citrus psyllids and citrus fruit flies under natural light condition was used, a method to increase the number of small target pests in citrus based on semantic segmentation algorithm was proposed, and the cascade region-based convolution neural networks (R-CNN) (convolutional neural network) algorithm was improved to enhance the recognition effect of small target pests using multiscale training, combining CBAM attention mechanism with high-resolution feature retention network high-resoultion network (HRNet) as feature extraction network, adding sawtooth atrous spatial pyramid pooling (ASPP) structure to fully extract high-resolution features from different scales, and adding feature pyramid networks (FPN) structure for feature fusion at different scales. To mine difficult samples more deeply, an online hard sample mining strategy was adopted in the process of model sampling. The results show that the improved cascade R-CNN algorithm after training has an average recognition accuracy of 88.78% for citrus psyllids. Compared with VGG16, ResNet50, and other common networks, the improved small target recognition algorithm obtains the highest recognition performance. Experimental results also show that the improved cascade R-CNN algorithm not only performs well in citrus psylla identification but also in other small targets such as citrus fruit flies, which makes it possible and feasible to detect small target pests with a field high-definition camera. [ABSTRACT FROM AUTHOR]

Deep learning has been widely used in various sensor detection fields to realize intelligent detection tasks. However, there are always restrictions on how these functions can be integrated into embedded devices to complete mobile and convenient sensing detection tasks. Therefore, the MobileNet_SSD, A lightweight model after simplification and optimization, is used in this paper to design a portable visual sensor system for the detection of spray droplet deposition in drone applications. The sensing system includes a droplet deposition image loop acquisition device and a supporting host computer interactive platform. It introduces the Sarsa algorithm to establish an adaptive model of light intensity to enhance the robustness and combines Deep Neural Networks and image processing technology to achieve rapid loop detection of droplet deposition parameters on the mobile terminal. Experimental results indicate that the proposed sensor can adapt to light changes in complex environments, and accurately measure the deposition parameters of different droplet density images. Furthermore, it is of great significance to detect the quality of drone sprays, master the rules of droplet deposition, and understand the effects of pesticide spraying. [ABSTRACT FROM AUTHOR]

The timely and efficient generation of weed maps is essential for weed control tasks and precise spraying applications. Based on the general concept of site-specific weed management (SSWM), many researchers have used unmanned aerial vehicle (UAV) remote sensing technology to monitor weed distributions, which can provide decision support information for precision spraying. However, image processing is mainly conducted offline, as the time gap between image collection and spraying significantly limits the applications of SSWM. In this study, we conducted real-time image processing onboard a UAV to reduce the time gap between image collection and herbicide treatment. First, we established a hardware environment for real-time image processing that integrates map visualization, flight control, image collection, and real-time image processing onboard a UAV based on secondary development. Second, we exploited the proposed model design to develop a lightweight network architecture for weed mapping tasks. The proposed network architecture was evaluated and compared with mainstream semantic segmentation models. Results demonstrate that the proposed network outperform contemporary networks in terms of efficiency with competitive accuracy. We also conducted optimization during the inference process. Precision calibration was applied to both the desktop and embedded devices and the precision was reduced from FP32 to FP16. Experimental results demonstrate that this precision calibration further improves inference speed while maintaining reasonable accuracy. Our modified network architecture achieved an accuracy of 80.9% on the testing samples and its inference speed was 4.5 fps on a Jetson TX2 module (Nvidia Corporation, Santa Clara, CA, USA), which demonstrates its potential for practical agricultural monitoring and precise spraying applications. [ABSTRACT FROM AUTHOR]

Rice is the most important food crop in the world, which is meaningful to ensure the quality and quantity of rice production. During the plantation process, weeds are the key factor to influence the rice yields. In recent years, the chemical control becomes the most widely used means to control the weed infestation because of its advantage in pesticide effects and efficiency. However, excessive use of herbicides has caused negative effects on the rice quality as well as the environment. An accurate weed cover map can provide support information for specific site weed management (SSWM) applications, which may well address the problem of traditional chemical controls. In this work, the unmanned aerial vehicle (UAV) imagery was captured on four different dates over two different rice fields. Object-based image analysis (OBIA) and deep learning approaches were applied to the weed mapping task of the UAV imagery. For the OBIA methods, the multiresolution segmentation and an improved k-means method were applied to segment the imagery into different objects; the colour and texture features were extracted and concatenated into a feature vector; back propagation (BP) neural network, support vector machine (SVM) and random forest were used for classification. After careful hyperparameter optimization and model selection, it was proven that the OBIA method achieved the accuracy of 66.6% mean intersection over union (MIU) on the testing set, and the inference speed is 2343.5 ms for an image sample. For the deep learning approach, the fully convolutional network (FCN) was applied for the pixel-wise classification task; transfer learning was used, and four pretrained convolutional neural networks (AlexNet, VGGNet, GoogLeNet, and ResNet) were transferred to our dataset via fine-tuning technique. Traditional skip architecture and fully connected conditional random fields (CRF) were used to improve the spatial details of FCN; after that, this work proposed to use a partially connected CRF as post processing, which may significantly accelerate the inference speed of fully connected CRF. Besides one single improvement method, hybrid improvement methods were applied and tested. Experimental results showed that the VGGNet-based FCN achieved the highest accuracy; for the improvement methods, the skip architecture and newly proposed partially connected CRF effectively improved the accuracy, and the hybrid improvement method (skip architecture and partially connected CRF) further improved the performance. The hybrid improvement method achieved 80.2% MIU on the testing set, and the inference speed for an image sample is 326.8 ms. The experimental results of this work demonstrated that the UAV remote-sensing utilizing deep learning method can provide reliable support information for SSWM applications in rice fields. [ABSTRACT FROM AUTHOR]

Soil moisture is an important factor determining yield. With the increasing demand for agricultural irrigation water resources, evaluating soil moisture in advance to create a reasonable irrigation schedule would help improve water resource utilization. This paper established a continuous system for collecting meteorological information and soil moisture data from a litchi orchard. With the acquired data, a time series model called Deep Long Short-Term Memory (Deep-LSTM) is proposed in this paper. The Deep-LSTM model has five layers with the fused time series data to predict the soil moisture of a litchi orchard in four different growth seasons. To optimize the data quality of the soil moisture sensor, the Symlet wavelet denoising algorithm was applied in the data preprocessing section. The threshold of the wavelets was determined based on the unbiased risk estimation method to obtain better sensor data that would help with the model learning. The results showed that the root mean square error (RMSE) values of the Deep-LSTM model were 0.36, 0.52, 0.32, and 0.48%, and the mean absolute percentage error (MAPE) values were 2.12, 2.35, 1.35, and 3.13%, respectively, in flowering, fruiting, autumn shoots, and flower bud differentiation stages. The determination coefficients (R2) were 0.94, 0.95, 0.93, and 0.94, respectively, in the four different stages. The results indicate that the proposed model was effective at predicting time series soil moisture data from a litchi orchard. This research was meaningful with regards to acquiring the soil moisture characteristics in advance and thereby providing a valuable reference for the litchi orchard's irrigation schedule. [ABSTRACT FROM AUTHOR]

At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering. [ABSTRACT FROM AUTHOR]

Instance segmentation of fruit tree canopies from images acquired by unmanned aerial vehicles (UAVs) is of significance for the precise management of orchards. Although deep learning methods have been widely used in the fields of feature extraction and classification, there are still phenomena of complex data and strong dependence on software performances. This paper proposes a deep learning-based instance segmentation method of litchi trees, which has a simple structure and lower requirements for data form. Considering that deep learning models require a large amount of training data, a labor-friendly semi-auto method for image annotation is introduced. The introduction of this method allows for a significant improvement in the efficiency of data pre-processing. Facing the high requirement of a deep learning method for computing resources, a partition-based method is presented for the segmentation of high-resolution digital orthophoto maps (DOMs). Citrus data is added to the training set to alleviate the lack of diversity of the original litchi dataset. The average precision (AP) is selected to evaluate the metric of the proposed model. The results show that with the help of training with the litchi-citrus datasets, the best AP on the test set reaches 96.25%. [ABSTRACT FROM AUTHOR]

Automatic acquisition of the canopy volume parameters of the Citrus reticulate Blanco cv. Shatangju tree is of great significance to precision management of the orchard. This research combined the point cloud deep learning algorithm with the volume calculation algorithm to segment the canopy of the Citrus reticulate Blanco cv. Shatangju trees. The 3D (Three-Dimensional) point cloud model of a Citrus reticulate Blanco cv. Shatangju orchard was generated using UAV tilt photogrammetry images. The segmentation effects of three deep learning models, PointNet++, MinkowskiNet and FPConv, on Shatangju trees and the ground were compared. The following three volume algorithms: convex hull by slices, voxel-based method and 3D convex hull were applied to calculate the volume of Shatangju trees. Model accuracy was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The results show that the overall accuracy of the MinkowskiNet model (94.57%) is higher than the other two models, which indicates the best segmentation effect. The 3D convex hull algorithm received the highest R2 (0.8215) and the lowest RMSE (0.3186 m3) for the canopy volume calculation, which best reflects the real volume of Citrus reticulate Blanco cv. Shatangju trees. The proposed method is capable of rapid and automatic acquisition for the canopy volume of Citrus reticulate Blanco cv. Shatangju trees. [ABSTRACT FROM AUTHOR]

Real-time monitoring of leaf area index (LAI) in cotton (Gossypium hirsutum L.) plays a vital role in guiding field fertilization, water management, growth observation and yield prediction. The use of unmanned aerial vehicles (UAVs) equipped with diverse sensors enables flexible and rapid LAI measurement across extensive areas. This study evaluates the efficacy of UAV-mounted LiDAR and high-resolution camera-derived point cloud data in LAI prediction. We assessed the integration of canopy spectral-textural characteristics from multispectral data with structural features from point cloud data for LAI forecasting. Furthermore, we compared various machine learning and deep learning models, selected the optimal one, and applied the SHAP (Shapley Additive Explanations) method to identify key features and their influence patterns in this model. The findings are distilled into four key points: (1) The performance of canopy structure metrics based on the two sensors varied across fertility periods due to differences in canopy closure; (2) The DNN-based (Deep Neural Network) LAI prediction model excelled with a single-period dataset, achieving an R2 of 0.81 and an RMSE% of 11.36 %. Similarly, in full-period multimodal data fusion, it demonstrated superior performance, evidenced by an R2 of 0.84 and an RMSE% of 9.94 %. (3) Compared to the unimodal data model, the multimodal data model yielded superior results and exhibited greater robustness. (4) In the DNN-based LAI prediction model utilizing multimodal data, texture features contributed most significantly. The results suggest that the DNN model, when employing multimodal data fusion, offers not only relatively precise and robust estimates of crop LAI but also contributes valuable insights for crop phenotyping and enhanced field management. This approach subsequently improves spatial prediction accuracy and the quality of decision-making in crop production. • Canopy structure metrics improve cotton LAI estimation accuracy. • Point cloud data and multispectral fusion improve LAI prediction accuracy. • Compared two sensors' structural indicators for LAI prediction. • DNN performs best in LAI prediction. [ABSTRACT FROM AUTHOR]

Gait recognition is an important biometric technology that allows for the remote collection of stakeholders' characteristics, without requiring their explicit cooperation. It has gained considerable attention in the fields of criminal investigation and intelligent security. Previous studies have shown that local gait features can enhance gait recognition performance by improving robustness to disturbances. However, global gait features also play a crucial role in gait recognition. Many researchers have utilized convolutional operations to extract global features, but these operations tend to focus on features within the receptive field, neglecting those outside of it. Therefore, the potential of global gait features has not been fully explored. In this paper, we propose a gait recognition framework based on vision transformers, aiming to enhance the extraction of global gait features. We introduce an adaptive multi-frame global feature mapping (AMGM) method to address the challenge of inconsistent feature dimensions caused by variations in the number of gait frames when fusing global and local features. We evaluate our model on the latest datasets, and the experimental results demonstrate a significant breakthrough. Notably, our model achieves state-of-the-art recognition accuracy, particularly in scenarios where subjects are wearing coats. Additionally, our model achieves remarkable improvements in recognition accuracy through training with small sample sets. [ABSTRACT FROM AUTHOR]

As the most important and widely used spice in the world, black pepper is known as the "king of spices." The geographical origin of black pepper greatly affects its quality and price. The existing physicochemical detection methods for distinguishing black pepper have inherent performance issues, such as expensive equipment, complex operations and high time consumption levels. This study proposes a novel method for identifying the origin of black pepper by synergically applying an E-tongue (ET), an E-nose (EN) and an E-eye (EE) in combination with a deep learning algorithm. First, taste and smell fingerprints were collected by ET and EN instruments, respectively, and the color, shape and texture information of different samples was collected by EE instruments. Three kinds of convolutional neural networks (CNNs) with one-dimensional or two-dimensional convolutional structures were designed and utilized to extract the feature information from the ET, EN and EE signals. Additionally, the Bayesian optimization algorithm (BOA) was applied to globally optimize the hyperparameters of the different CNN models. Then, a channel attention mechanism (CAM) module was introduced to achieve feature-level fusion for the three kinds of signals. Finally, a fully connected layer that uses a softmax algorithm was utilized for classifying the categories of black pepper. The experimental results showed that compared with employing a single sensory device, the proposed method yielded better recognition accuracy. Achieving accuracy, precision, recall and F 1 -score values of 99.71%, 0.997, 0.997 and 0.996 respectively, the proposed pattern recognition model obtained better classification results than the baseline models for the test set. This study introduces a rapid detection method for identifying the geographical origin of black pepper. [Display omitted] • A synergetic application of ET, EN and EE systems combined with deep learning is explored. • 1D and 2D CNN models are designed to process different signal of intelligent senses. • A CAM is applied to fuse the features of the ET, EN and EE signals. • A low-cost and accurate detection technique is proposed. [ABSTRACT FROM AUTHOR]

• A detection approach for late-autumn shoots of litchi tree based on UAV remote sensing is provided. • A remote sensing dataset of late-autumn shoots of litchi tree is constructed. • A deep learning model based on the combination of YOLOv5 and Swin-transformer is proposed. • The detection accuracy of late-autumn shoots in remote sensing images is improved. • It will provide technical support for other researchers on late-autumn shoots and orchards manager. Litchi is one of the most common economic fruits in southern China, however, the growth of late-autumn shoots of litchi hinders flower bud differentiation and reduces yield of fruit. The early identification of the late-autumn shoots is of great significance for orchard management to control shoots and then increase fruit yield. At present, the identification of late-autumn shoots still relies on manual methods, which is not suitable for smart orchard management in a large area due to low recognition efficiency and high subjectivity. Therefore, a convenient, fast and cost-effective method is urgently needed. In response to this problem, the paper proposes a method based on the combination of unmanned aerial vehicle (UAV) remote sensing and object detection algorithm to detect late-autumn shoots. For this purpose, a remote sensing dataset of late-autumn shoots of litchi is first constructed by UAV. An improved YOLOv5 algorithm called YOLOv5-SBiC is then developed for late-autumn shoots identification. In the YOLOv5-SBiC algorithm, the transformer module is introduced to speed up the convergence of the network and improve detection accuracy, the attention mechanism module is employed to help the model extracting details, and BiFPN is used to better solve the multi-scale problem in detecting and then improve the recognition effect of small-sized objects. In addition, CIOU is selected as the loss function of bounding boxes regression to achieve high-precision localization of the boxes. The test results demonstrate that the recognition accuracy of YOLOv5-SBiC reaches a relatively high value of 79.6%, which is 4.0% higher than that (75.6%) of the original YOLOv5 algorithm and 15.9% higher than that (63.7%) of the pure transformer algorithm. It's also demonstrated that YOLOv5-SBiC is more competitive than the mainstream target detection algorithms in the dataset of late-autumn shoots. [ABSTRACT FROM AUTHOR]

• Peanut seedling monitoring is limited by the difficulty in collecting data quickly. • Real-time peanut seedling video counting model was realized based on UAV platform. • Precision and recall of refined model in testing were 91.2% and 94%, respectively. • Via peanut counting/experience results, the emergence process was large-scale monitored. During the seedling stage, real-time monitoring and detection of seed germination are important for testing the quality of seeds, crop field management, and yield estimation. However, owing to the low efficiency of traditional manual seedling rate monitoring, survey methods have been gradually replaced by unmanned aerial vehicles (UAVs) and real-time peanut video counting models. In this study, we propose an efficient and fast real-time peanut video counting model (combining the improved YOLOV5s, DeepSort, and OpenCV programs) to accurately distinguish peanut seedlings from weeds, and to count peanut seedlings based on videos. The improved YOLOV5s combines a vision transformer with CSNet to replace the original CSNet backbone. The field experiment results show that the real-time peanut video counting model count capabilities is close to those of humans with an accuracy of 98.08%; however, the seedling calculation model takes only one-fifth of the time required for human detection. Therefore, the video-based model outperforms the image-based target detection algorithm, and was more suitable for application in practical germination rate investigation in peanut production. [ABSTRACT FROM AUTHOR]

[Display omitted] • Electronic tongue and eye are used to classify Pu-erh tea via feature-level fusion. • The deep learning is introduced to data fusion field of intelligent sensory system. • CNN structures are designed and optimized by Bayesian optimization. • The proposed model has better performance compared with conventional methods. This study proposed an efficient approach that an electronic tongue (ET) and an electronic eye (EE) combined with a deep learning algorithm were jointly leveraged to recognition Pu-erh tea. A one-dimensional convolutional neural network (1-D CNN) and a two-dimensional convolutional neural network (2-D CNN) were designed and optimized for the feature extraction of ET and EE signals, respectively. Then, a feature-level fusion strategy was introduced to address the feature vectors extracted from the different types of CNN models. To highlight the effect of data fusion, a backpropagation neural network (BPNN), a classifier similar to the fully connected layers of CNN models, was employed. Meanwhile, the Bayesian optimization algorithm (BOA) was employed for hyperparameter optimization of the identification models. The experimental results showed that the feature fusion strategy assimilated the merits of the ET and EE and gained better Pu-erh tea identification performance than an independent intelligent sensory system combined with CNN model. The results demonstrate that the feature-level fusion based on deep learning algorithm gained the best accuracy on the test set, with a precision, a recall, an F1-score and an AUC score of 99.07%, 99.2%, 0.992 and 0.994, respectively. This study shows that the simultaneous utilization of an ET and an EE combined with deep learning algorithm could function as a rapid detection method for discriminating the storage time of Pu-erh tea. [ABSTRACT FROM AUTHOR]

Pu-erh tea is a famous Chinese fermented tea, and its quality and flavor are closely related to the storage time used for its fermentation. This paper puts forward one method to discriminate the age of Pu-erh tea by employing a voltammetric electronic tongue (VE-Tongue) combined with deep learning and transfer learning techniques. To make the deep learning model suitable for processing VE-Tongue signals, a one-dimensional convolutional neural network (1-D CNN) was developed to automatically perform feature extraction and classification. Transfer learning (TL) was introduced to train the model to reduce the training complexity and enhance the generalization capability of the CNN. The performance of the proposed model was further compared with that of traditional machine learning methods such as the backpropagation neural network, support vector machine and extreme learning machine. The results showed that the proposed model exhibited better performance in classifying Pu-erh tea than other methods. Its accuracy for the test set, precision, recall and F1 score was 98.80%, 98.2%, 98%, and 0.98, respectively. This study found that the VE-Tongue combined with deep learning and TL algorithms could be a sensitive, reliable and effective detection method for identifying the amount of storage time of Pu-erh tea, which could further expand its applications to other related fields. Image 1 • Classification of Pu-erh tea is achieved by voltammetric electronic tongue system. • Pattern recognition method based on deep learning and transfer learning is proposed. • 1-D CNN model is design and optimized for analyzing electronic tongue signals. • The proposed model is superior to conventional pattern recognition methods. [ABSTRACT FROM AUTHOR]