Mainstream Network Research Articles

FDT‐Net: Frequency‐Aware Dual‐Branch Transformer‐Based Optic Cup and Optic Disk Segmentation With Parallel Contour Information Mining and Uncertainty‐Guided Refinement

ABSTRACTAccurate segmentation of the optic cup and disc in fundus images is crucial for the prevention and diagnosis of glaucoma. However, challenges arise due to factors such as blood vessels, and mainstream networks often demonstrate limited capacity in extracting contour information. In this paper, we propose a segmentation framework named FDT‐Net, which is based on a frequency‐aware dual‐branch Transformer (FDBT) architecture with parallel contour information mining and uncertainty‐guided refinement. Specifically, we design a FDBT that operates in the frequency domain. This module leverages the inherent contextual awareness of Transformers and utilizes Discrete Cosine Transform (DCT) transformation to mitigate the impact of certain interference factors on segmentation. The FDBT comprises global and local branches that independently extract global and local information, thereby enhancing segmentation results. Moreover, to further mine additional contour information, this study develops the parallel contour information mining (PCIM) module to operate in parallel. These modules effectively capture more details from the edges of the optic cup and disc while avoiding mutual interference, thus optimizing segmentation performance in contour regions. Furthermore, we propose an uncertainty‐guided refinement (UGR) module, which generates and quantifies uncertainty mass and leverages it to enhance model performance based on subjective logic theory. The experimental results on two publicly available datasets demonstrate the superior performance and competitive advantages of our proposed FDT‐Net. The code for this project is available at https://github.com/Rookie49144/FDT‐Net.

CTAFFNet: CNN–Transformer Adaptive Feature Fusion Object Detection Algorithm for Complex Traffic Scenarios

As the core technology of an environmental perception system, object detection has received more and more attention and has become a hot research direction for intelligent driving vehicles. The CNN–Transformer hybrid model has poor generalization ability, making it difficult to meet the detection requirements for small objects in complex scenes. We propose a novel convolutional neural network (CNN)–Transformer Adaptive Feature Fusion Network (CTAFFNet) for object detection. First, we design a Local–Global Feature Fusion unit known as the Convolutional Transformation Adaptive Fusion Kernel (CTAFFK), which is integrated into CTAFFNet. The CTAFFK kernel utilizes two branches, namely CNN and Transformer, to extract local and global features from the image, and adaptively fuses the features from both branches. Subsequently, we develop an adaptive feature fusion strategy that combines local high-frequency and global low-frequency features to obtain comprehensive feature information. Finally, CTAFFNet employs an encoder–decoder structure to facilitate the flow of fused local–global information between different stages, ensuring the model’s generalization capabilities. Results from the experiment conducted on the large and challenging KITTI dataset demonstrate the effectiveness and efficiency of the proposed network. Compared with other mainstream networks, it achieves an average precision of 91.17%, particularly excelling in the detection of small objects at longer distances with a remarkable 70.18% accuracy, while also providing real-time detection capabilities.

Explainable Encoder-Prediction-Reconstruction Framework for the Prediction of Metasurface Absorption Spectra.

The correlation between metasurface structures and their corresponding absorption spectra is inherently complex due to intricate physical interactions. Additionally, the reliance on Maxwell's equations for simulating these relationships leads to extensive computational demands, significantly hindering rapid development in this area. Numerous researchers have employed artificial intelligence (AI) models to predict absorption spectra. However, these models often act as black boxes. Despite training high-performance models, it remains challenging to verify if they are fitting to rational patterns or merely guessing outcomes. To address these challenges, we introduce the Explainable Encoder-Prediction-Reconstruction (EEPR) framework, which separates the prediction process into feature extraction and spectra generation, facilitating a deeper understanding of the physical relationships between metasurface structures and spectra and unveiling the model's operations at the feature level. Our model achieves a 66.23% reduction in average Mean Square Error (MSE), with an MSE of 2.843 × 10-4 compared to the average MSE of 8.421×10-4 for mainstream networks. Additionally, our model operates approximately 500,000 times faster than traditional simulations based on Maxwell's equations, with a time of 3×10-3 seconds per sample, and demonstrates excellent generalization capabilities. By utilizing the EEPR framework, we achieve feature-level explainability and offer insights into the physical properties and their impact on metasurface structures, going beyond the pixel-level explanations provided by existing research. Additionally, we demonstrate the capability to adjust absorption by changing the metasurface at the feature level. These insights potentially empower designers to refine structures and enhance their trust in AI applications.

Automatic extraction and 3D modeling of real road scenes using UAV imagery and deep learning semantic segmentation

ABSTRACT The extraction of roads from UAV images is challenged by lighting, noise, occlusions, and similar non-road objects, making high-quality road extraction difficult. To addressing these issues, this study proposes an enhanced U-Net network to automate the extraction and 3D modeling of real road scenes using UAV imagery. Initially, a cascaded atrous spatial pyramid module was integrated into the encoder to capitalize on global context information, thereby refining the fuzzy segmentation outcomes. Subsequently, a module for augmenting road feature extraction was added within the channel, and a spatial attention mechanism was introduced in the decoder to enhance edge clarity. Experimental results demonstrated that this model captures more road information compared to mainstream networks and effectively incorporates topological structure perception for road extraction in complex scenarios, thus improving road connectivity. The model achieved an F1 score and mean Intersection over Union (mIoU) of 85.6% and 81.2%, respectively, on UAV images of road scenes – marking improvements of 3.9% and 3.4% over the traditional U-Net model, thereby exhibiting superior automatic road extraction capabilities. Ultimately, the model facilitated refined modeling and visual analysis of road scenes, achieving high overall accuracy and detailed local restoration of the actual scene.

Optimal deployment of private 5G multi-access edge computing systems at smart factories: Using hybrid crow search algorithm

In smart factories, an increasing number of mobile intelligent devices are deployed to meet the growing demands for flexible manufacturing. These devices, equipped with various sensors, synchronize a substantial amount of data with cloud servers for real-time monitoring and control. Fifth generation mobile networks (5G) combined with multi-access edge computing (MEC) provide the capabilities for multiple connections, large-scale data transmission, and efficient response times, becoming the mainstream network architectures for the needs. Additionally, with the emerging trend of energy-saving, recent works have addressed energy consumption as a significant cost factor. However, most previous studies tended to focus solely on cloud servers, neglecting energy consumption at edge computing and underestimating the impact of heterogeneous mobile device. As the scope of smart factory networks continues to expand, the challenges become increasingly critical. This study presents a private 5G MEC system architecture tailored for smart panel factories. The concerned problem is formulated as an integer programming model, which determines deployment locations and quantities for MEC servers and 5G small cells, including picocells and femtocells, so as to minimize the overall deployment costs while meeting the constraints of connectivity, capacity, latency, coverage, serviceability, and energy consumption. Since the edge server deployment problem is NP-hard, this study further proposes a hybrid metaheuristic algorithm, CSAVNS, which combines the strengths of crow search algorithm (CSA) and variable neighborhood search (VNS). In the global search phase of CSA, the VNS local search is introduced to enhance the algorithm's capabilities. Experimental analysis demonstrates that the proposed CSAVNS outperforms other algorithms in terms of solution solving capabilities.

Synergistic fusion network for landslide segmentation: the vital complementarity of geological information to remote sensing imagery

In the contemporary technological environment, access to a multitude of data sources, such as digital elevation models (DEM), slope data, and other geological information, has become essential for augmenting remote sensing imagery in landslide analysis. These datasets enhance landslide identification capabilities, but existing methods often fail to fully leverage their unique characteristics due to oversimplified fusion strategies. To overcome this challenge, we introduce the Synergistic Fusion Network (SFNet), which is specifically designed to utilize the complementary nature of geological data to significantly improve the accuracy and efficiency of landslide segmentation. SFNet incorporates Multi-Source Fusion Modules (MSFM) and Reverse Feature Refinement Modules(RFRM), through an innovative network architecture, enhancing remote sensing imagery with integrated geological information. In our experiments, SFNet outperforms existing mainstream networks, demonstrating superior F1 scores, thereby showcasing its ability to effectively segment landslide regions with high precision. This advancement highlights the importance of considering the unique contributions of each data source, especially the complementary effects of geological information.

Research on improved YOLOv8n based potato seedling detection in UAV remote sensing images.

Accurate detection of potato seedlings is crucial for obtaining information on potato seedlings and ultimately increasing potato yield. This study aims to enhance the detection of potato seedlings in drone-captured images through a novel lightweight model. We established a dataset of drone-captured images of potato seedlings and proposed the VBGS-YOLOv8n model, an improved version of YOLOv8n. This model employs a lighter VanillaNet as the backbone network in-stead of the original YOLOv8n model. To address the small target features of potato seedlings, we introduced a weighted bidirectional feature pyramid network to replace the path aggregation network, reducing information loss between network layers, facilitating rapid multi-scale feature fusion, and enhancing detection performance. Additionally, we incorporated GSConv and Slim-neck designs at the Neck section to balance accuracy while reducing model complexity. The VBGS-YOLOv8n model, with 1,524,943 parameters and 4.2 billion FLOPs, achieves a precision of 97.1%, a mean average precision of 98.4%, and an inference time of 2.0ms. Comparative tests reveal that VBGS-YOLOv8n strikes a balance between detection accuracy, speed, and model efficiency compared to YOLOv8 and other mainstream networks. Specifically, compared to YOLOv8, the model parameters and FLOPs are reduced by 51.7% and 52.8% respectively, while precision and a mean average precision are improved by 1.4% and 0.8% respectively, and the inference time is reduced by 31.0%. Comparative tests with mainstream models, including YOLOv7, YOLOv5, RetinaNet, and QueryDet, demonstrate that VBGS-YOLOv8n outperforms these models in terms of detection accuracy, speed, and efficiency. The research highlights the effectiveness of VBGS-YOLOv8n in the efficient detection of potato seedlings in drone remote sensing images, providing a valuable reference for subsequent identification and deployment on mobile devices.

Polymorphic Clustering and Approximate Masking Framework for Fine-Grained Insect Image Classification

Insect diversity monitoring is crucial for biological pest control in agriculture and forestry. Modern monitoring of insect species relies heavily on fine-grained image classification models. Fine-grained image classification faces challenges such as small inter-class differences and large intra-class variances, which are even more pronounced in insect scenes where insect species often exhibit significant morphological differences across multiple life stages. To address these challenges, we introduce segmentation and clustering operations into the image classification task and design a novel network model training framework for fine-grained classification of insect images using multi-modality clustering and approximate mask methods, named PCAM-Frame. In the first stage of the framework, we adopt the Polymorphic Clustering Module, and segmentation and clustering operations are employed to distinguish various morphologies of insects at different life stages, allowing the model to differentiate between samples at different life stages during training. The second stage consists of a feature extraction network, called Basenet, which can be any mainstream network that performs well in fine-grained image classification tasks, aiming to provide pre-classification confidence for the next stage. In the third stage, we apply the Approximate Masking Module to mask the common attention regions of the most likely classes and continuously adjust the convergence direction of the model during training using a Deviation Loss function. We apply PCAM-Frame with multiple classification networks as the Basenet in the second stage and conduct extensive experiments on the Insecta dataset of iNaturalist 2017 and IP102 dataset, achieving improvements of 2.2% and 1.4%, respectively. Generalization experiments on other fine-grained image classification datasets such as CUB200-2011 and Stanford Dogs also demonstrate positive effects. These experiments validate the pertinence and effectiveness of our framework PCAM-Frame in fine-grained image classification tasks under complex conditions, particularly in insect scenes.

Semantic segmentation of large-scale point cloud scenes via dual neighborhood feature and global spatial-aware

As a core task in 3D scene information extraction, point cloud semantic segmentation is crucial for understanding 3D scenes and environmental perception. While extracting local geometric structural features from point clouds, existing research often overlooks the long-range dependencies present in the scene, making it challenging to fully uncover the long-range contextual features hidden within point clouds. On this basis, we propose a segmentation algorithm (DG-Net) that integrates dual neighborhood features with global spatial-aware. Initially, the local structure information encoding module is designed to learn about local geometric shapes by encoding spatial position and directional features, thus supplementing structural information. Subsequently, a dual neighborhood features complementary module is introduced to merge the geometric structural and semantic features within local neighborhoods, learning local dependencies and capturing distinguishable local contextual features. Finally, these features are relayed to a global spatial-aware module equipped with a gated unit, which dynamically adjusts the weights of features at different stages, effectively modeling long-range dependencies between local structures and finely extracting long-range contextual features. We conducted experiments on benchmark datasets of point cloud scenes, and both quantitative and qualitative results demonstrate that our algorithm can accurately identify small-scale objects with complex geometric structures within scenes, surpassing other mainstream networks in segmentation performance. The mIoU on the S3DIS, Toronto3D, and SensatUrban datasets are 71.9 %, 82.1 %, and 59.8 %, respectively.

Detection of Gannan Navel Orange Ripeness in Natural Environment Based on YOLOv5-NMM

In order to achieve fast and accurate detection of Gannan navel orange fruits with different ripeness levels in a natural environment under all-weather scenarios and then to realise automated harvesting of Gannan navel oranges, this paper proposes a YOLOv5-NMM (YOLOv5 with Navel orange Measure Model) object detection model based on the improvement in the original YOLOv5 model. Based on the changes in the phenotypic characteristics of navel oranges and the Chinese national standard GB/T 21488-2008, the maturity of Gannan navel oranges is tested. And it addresses and improves the problems of occlusion, dense distribution, small target size, rainy days, and light changes in the detection of navel orange fruits. Firstly, a new detection head of 160 × 160 feature maps is constructed in the detection layer to improve the multi-scale target detection layer of YOLOv5 and to increase the detection accuracy of the different maturity levels of Gannan navel oranges of small sizes. Secondly, a convolutional block attention module is incorporated in its backbone layer to capture the correlations between features in different dimensions to improve the perceptual ability of the model. Then, the weighted bidirectional feature pyramid network structure is integrated into the Neck layer to improve the fusion efficiency of the network on the feature maps and reduce the amount of computation. Lastly, in order to reduce the loss of the target of the Gannan Navel Orange due to occlusion and overlapping, the detection frame is used to remove redundancy using the Soft-NMS algorithm to remove redundant candidate frames. The results show that the accuracy rate, recall rate, and average accuracy of the improved YOLOv5-NMM model are 93.2%, 89.6%, and 94.2%, respectively, and the number of parameters is only 7.2 M. Compared with the mainstream network models, such as Faster R-CNN, YOLOv3, the original model of YOLOv5, and YOLOv7-tiny, it is superior in terms of the accuracy rate, recall rate, and average accuracy mean, and also performs well in terms of the detection rate and memory occupation. This study shows that the YOLOv5-NMM model can effectively identify and detect the ripeness of Gannan navel oranges in natural environments, which provides an effective exploration of the automated harvesting of Gannan navel orange fruits.

SEHRNet: A lightweight, high‐resolution network for aircraft keypoint detection

AbstractCurrent research on apron conflict detection is often limited to the interaction between the aircraft as a whole and other objects, making it difficult to accomplish targeted identification of vulnerable and high‐cost aircraft components. However, the implementation of detailed aircraft identification is of great significance to enhance the safety of airport surface operations. Based on the excellent performance of High‐Resolution Network (HRNet) in keypoint detection, a lightweight end‐to‐end keypoint detection network, namely Squeeze and Excitation High‐Resolution Network (SEHRNet), is proposed in this paper to solve the problems of HRNet's slower computation and more redundancy. First, the errors arising from coordinate transformations in the coding and decoding process are solved by an improved feature map coding and decoding process. Second, replace the BasicBlock in HRNet with the Depthwise separable convolutions based on the Squeeze‐and‐Excitation Networks, which drastically cuts the computational cost of the network. Third, the improved Bottleneck module is used to further enhance the capability of feature extraction. Experimental results prove that, based on the aircraft keypoint detection dataset, the SEHRNet proposed in this paper shows stronger applicability compared to the current mainstream networks. Compared with the original HRNet, the improved network has higher accuracy, faster speed, and lighter model for aircraft keypoint detection.

An Oracle Bone Inscriptions Detection Algorithm Based on Improved YOLOv8

Ancient Chinese characters known as oracle bone inscriptions (OBIs) were inscribed on turtle shells and animal bones, and they boast a rich history dating back over 3600 years. The detection of OBIs is one of the most basic tasks in OBI research. The current research aimed to determine the precise location of OBIs with rubbing images. Given the low clarity, severe noise, and cracks in oracle bone inscriptions, the mainstream networks within the realm of deep learning possess low detection accuracy on the OBI detection dataset. To address this issue, this study analyzed the significant research progress in oracle bone script detection both domestically and internationally. Then, based on the YOLOv8 algorithm, according to the characteristics of OBI rubbing images, the algorithm was improved accordingly. The proposed algorithm added a small target detection head, modified the loss function, and embedded a CBAM. The results show that the improved model achieves an F-measure of 84.3%, surpassing the baseline model by approximately 1.8%.

A lightweight white blood cells detection network based on CenterNet and feature fusion modules

White blood cells (WBCs) detection is significant to the diagnosis of many diseases. However, the detection accuracy can be influenced by the significant differences in color, size and morphology of WBCs in the images. In this paper, an improved CenterNet with smaller model size, fewer parameters, and lower computational complexity is proposed for the WBCs accurate detection. Firstly, the lightweight backbone GhostNetv2 is selected to reduce the model size, parameters and computational complexity of the network. Then, a feature pyramid network with the efficient channel attention (ECA) attention mechanism and the multi-scale feature extraction modules is constructed to enhance the capability of feature extraction and focus more on WBCs. Finally, the heatmap loss function is modified by proposing an improved mean squared error loss function to enhance the fitting ability between the predicted values and the ground truth of the heatmap. Experimental results show that the model size of the proposed lightweight CenterNet is only 19.9 MB, and the mAP.5 is 97.36%. The model size is reduced by 84% while the mAP.5 and FPS are increased by 0.7% and 10.4 compared to the original CenterNet. Moreover, the detection accuracy of the proposed lightweight CenterNet is comparable to the existing mainstream networks and its detection performance on different datasets is good, while the model size, parameters and computational complexity of the network is significantly reduced, and can be used for WBCs detection effectively.

PatchDetector: Pluggable and non-intrusive patch for small object detection

Object detection is one of the core tasks in computer vision that serves as a crucial underpinning for numerous applications. In recent years, deep learning-based methods have achieved remarkable performance in object detection. However, the performance of small objects still remains unsatisfactory. Therefore, some specific architectures have been proposed to address this issue in certain areas, such as remote-sensing and UAV images. In this paper, we aim to design a pluggable and non-intrusive method, termed as PatchDetector, to improve the performance of small object detection, which can effectively avoid the time and resource overhead of retraining the entire network. To achieve that, we first analyze why the mainstream networks perform poorly on small objects and find out that the fundamental reason is that the features of small are superseded by the background, which leads to a significant semantic gap in multi-level layers. Then, significance analysis is conducted to find the essential features for improving the small object detection. Next, with the located significant features, we devise a pluggable patch network for extracting essential features for small objects, which is non-intrusive to the original network. Experiments on mainstream detectors, including YOLO series and Faster RCNN, show that the proposed PatchDetector achieves 0.4%∼2.0% mAP on small objects while not compromising the performance of medium and large objects.

A New Lunar Lineament Extraction Method Based on Improved UNet++ and YOLOv5.

Lineament is a unique geological structure. The study of Lunar lineament structure has great significance on understanding its history and evolution of Lunar surface. However, the existing geographic feature extraction methods are not suitable for the extraction of Lunar lineament structure. In this paper, a new lineament extraction method is proposed based on improved-UNet++ and YOLOv5. Firstly, new lineament dataset is created containing lineaments structure based on CCD data from LROC. At same time the residual blocks are replaced with the VGG blocks in the down sample part of the UNet++ with adding the attention block between each layer. Secondly, the improved-UNet++ and YOLO networks are trained to execute the object detection and semantic segmentation of lineament structure respectively. Finally, a polygon-match strategy is proposed to combine the results of object detection and semantic segmentation. The experiment result indicate that this new method has relatively better and more stable performance compared with current mainstream networks and the original UNet++ network in the instance segmentation of lineament structure. Additionally, the polygon-match strategy is able to perform preciser edge detail in the instance segmentation of lineament structure result.

Wheat Seed Detection and Counting Method Based on Improved YOLOv8 Model.

Wheat seed detection has important applications in calculating thousand-grain weight and crop breeding. In order to solve the problems of seed accumulation, adhesion, and occlusion that can lead to low counting accuracy, while ensuring fast detection speed with high accuracy, a wheat seed counting method is proposed to provide technical support for the development of the embedded platform of the seed counter. This study proposes a lightweight real-time wheat seed detection model, YOLOv8-HD, based on YOLOv8. Firstly, we introduce the concept of shared convolutional layers to improve the YOLOv8 detection head, reducing the number of parameters and achieving a lightweight design to improve runtime speed. Secondly, we incorporate the Vision Transformer with a Deformable Attention mechanism into the C2f module of the backbone network to enhance the network's feature extraction capability and improve detection accuracy. The results show that in the stacked scenes with impurities (severe seed adhesion), the YOLOv8-HD model achieves an average detection accuracy (mAP) of 77.6%, which is 9.1% higher than YOLOv8. In all scenes, the YOLOv8-HD model achieves an average detection accuracy (mAP) of 99.3%, which is 16.8% higher than YOLOv8. The memory size of the YOLOv8-HD model is 6.35 MB, approximately 4/5 of YOLOv8. The GFLOPs of YOLOv8-HD decrease by 16%. The inference time of YOLOv8-HD is 2.86 ms (on GPU), which is lower than YOLOv8. Finally, we conducted numerous experiments and the results showed that YOLOv8-HD outperforms other mainstream networks in terms of mAP, speed, and model size. Therefore, our YOLOv8-HD can efficiently detect wheat seeds in various scenarios, providing technical support for the development of seed counting instruments.

Recognizing landslides in remote sensing images based on enhancement of information in digital elevation models

ABSTRACT To address the landslide recognition problem in remote sensing images, this paper designs a visual transformer network model based on DEM (digital elevation model) feature enhancement, which is experimentally validated on the Bijie landslide dataset and Landslide4Sense2022 dataset. The lion optimizer is used during training. The results show that 98.49% accuracy and 97.24% F1 score are achieved on Bijie dataset, and 88.22% accuracy and 90.16% F1 score on Landslide4Sense2022 dataset, which is a significant improvement in landslide recognition compared with other mainstream network models. Therefore, it can be found that this paper’s method is effective in the recognition of landslide from remote sensing images.

Probabilistic Estimation of Tropical Cyclone Intensity Based on Multi-Source Satellite Remote Sensing Images

Estimating the intensity of tropical cyclones (TCs) is beneficial for preventing and reducing the impact of natural disasters. Most existing methods for estimating TC intensity utilize single-satellite or single-band remote sensing images, but they lack the ability to quantify the uncertainty of the estimation results. However, TC, as a typical chaotic system, often requires confidence intervals for intensity estimates in real-world emergency decision-making scenarios. Additionally, the use of multi-source image inputs contributes to the uncertainty of the model. Consequently, this study introduces a neural network (MTCIE) that utilizes multi-source satellite images to provide probabilistic estimates of TC intensity. The model utilizes infrared and microwave images from multiple satellites as inputs. It uses a dual-branch self-attention encoder to extract TC image features and provides uncertainty estimates for TC intensity. Furthermore, a dataset for estimating the intensity of multi-source TC remote sensing images (MTCID) is constructed through the registration of latitude, longitude, and time, along with data augmentation. The proposed method achieves a MAE of 7.42 kt in deterministic estimation, comparable to mainstream networks like TCIENet. In uncertain estimation, it outperforms methods like MC Dropout in the PICP metric, providing reliable probability estimates. This supports TC disaster emergency decision making, enhancing risk mitigation in real-world applications.

Construction of a Classification Model for Teacher and Student Behavior in Physical Education Classrooms –Based on Multimodal Data

Abstract The analysis of teachers' and students' behaviors in physical education classrooms is an important way to improve the quality of physical education teaching and teaching methods, which helps teachers to check the gaps and improve the teaching level. In this paper, for the problems of data differences between multiple modalities and the conflict between feature extraction modules of different modalities, we designed a dual-stream framework HRformer algorithm based on Transformer, which unifies the skeletal modalities and video modalities in the algorithm. The relationship between skeletal and video modalities is modeled using the self-attention mechanism, and the matching and fusion of skeletal features and video data is performed to construct a behavior recognition model for teachers and students in the sports classroom based on multimodal data. Then, the model is compared with mainstream networks on the dataset to verify its performance. To conduct model application and example analysis, a university collects data on physical education classroom teachers and students for a semester. It is found that the multimodal model in this paper has a classification F1 value of 95.61%, 93.19%, and 93.74% for the three types of behavior recognition, namely, skill training (ST), game activity (GA), and rest, respectively, which are higher than the two methods of single skeletal modality and video modality. The model has the highest recognition accuracy of 97.12% and 98.15% for Game Activity (GA). Based on real physical education classroom data, the practical application of the model in physical education teaching classrooms in this paper is fruitful, and the results of behavioral recognition classification are in line with the design expectation. This study develops an effective method for classifying teacher and student behaviors in a physical education classroom. It provides a useful exploration for the integration and innovation of physical education teaching and information technology.

DeeplabV3+-based navigation line extraction for the sunlight robust combine harvester.

Visual navigation is widely used in intelligent combine harvesters, but the existing algorithms do not have sufficiently high accuracy of the visual navigation line recognition under different sunlight conditions. To address this problem, this article proposes a sunlight-robust DeepLabV3+-based navigation line extraction method for combine harvesters. The navigation lines are extracted by constructing a new dataset and predicting the boundaries of the areas that have been and have not been cut. To address the problem that DeeplabV3+ is not sufficient light in the DCNN part, improvement is proposed by incorporating the MobileNetV2 module. In image segmentation, the prediction time is 22.5 ms, and the mean intersection over union (FMIOU) is 0.79. After image segmentation, the navigation lines are drawn using the line segment detection algorithm for the harvester. The proposed method is compared with other mainstream networks, and the prediction results are compared using the line segment detection method. The results show that this method can more quickly identify the navigation lines under different conditions of sunlight with less labeled data than the improved U-Net and DeeplabV3+, which uses Xception as the backbone. Compared to the traditional method and the improved U-Net, this method achieves good results and improves the recognition speed by 27 and 9 ms, respectively.