GLU-YOLOv8: An Improved Pest and Disease Target Detection Algorithm Based on YOLOv8

Aiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability in detecting small insect targets. The Convolutional Block Attention Module is employed to improve feature representation and attention focus. Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. The model oscillation has also been significantly improved. The enhanced I-YOLOv10-SC network effectively addresses the challenges of detecting small and incomplete insect targets in tea plantations, offering high precision and recall rates, thus providing a solid technical foundation for intelligent pest monitoring and precise prevention in smart tea gardens.

The key to precise weeding in the field lies in the efficient detection of weeds. There are no studies on weed detection in potato fields. In view of the difficulties brought by the cross-growth of potatoes and weeds to the detection of weeds, the existing detection methods cannot meet the requirements of detection speed and detection accuracy at the same time. This study proposes an improved YOLOv4 model for weed detection in potato fields. The proposed algorithm replaces the backbone network CSPDarknet53 in the YOLOv4 network structure with the lightweight MobileNetV3 network and introduces Depthwise separable convolutions instead of partial traditional convolutions in the Path Aggregation Network (PANet), which reduces the computational cost of the model and speeds up its detection. In order to improve the detection accuracy, the convolutional block attention module (CBAM) is fused into the PANet structure, and the CBAM will process the input feature map with a channel attention mechanism (CAM) and spatial attention mechanism (SAM), respectively, which can enhance the extraction of useful feature information. The K-means++ clustering algorithm is used instead of the K-means clustering algorithm to update the anchor box information of the model so that the anchor boxes are more suitable for the datasets in this study. Various image processing methods such as CLAHE, MSR, SSR, and gamma are used to increase the robustness of the model, which eliminates the problem of overfitting. CIoU is used as the loss function, and the cosine annealing decay method is used to adjust the learning rate to make the model converge faster. Based on the above-improved methods, we propose the MC-YOLOv4 model. The mAP value of the MC-YOLOv4 model in weed detection in the potato field was 98.52%, which was 3.2%, 4.48%, 2.32%, 0.06%, and 19.86% higher than YOLOv4, YOLOv4-tiny, Faster R-CNN, YOLOv5 l, and SSD(MobilenetV2), respectively, and the average detection time of a single image was 12.49ms. The results show that the optimized method proposed in this paper outperforms other commonly used target detection models in terms of model footprint, detection time consumption, and detection accuracy. This paper can provide a feasible real-time weed identification method for the system of precise weeding in potato fields with limited hardware resources. This model also provides a reference for the efficient detection of weeds in other crop fields and provides theoretical and technical support for the automatic control of weeds.

HighlightsFish posture recognition under high-density aquaculture conditions is realized.The improved model demonstrated good robustness to different light intensities and fish densities.The YOLOv5-CCM model indices mAP@0.5 improved by 5.03%.Abstract. The precise recognition of fish posture is crucial for monitoring their behavior, serving as a key indicator of well-being and early detection of diseases. This study introduces a gesture recognition model specifically designed for Pelteobagrus fulvidraco in dense aquaculture environments, utilizing an improved version of the YOLOv5s architecture. An underwater camera with a resolution of 1920×1080 captured the initial image of Pelteobagrus fulvidraco. To improve dataset quality in the challenging underwater environment, characterized by low visibility, the Multi-Scale Retinex with Color Restoration (MSRCR) algorithm enhanced the original image, forming the base image dataset. To preserve essential image features during convolution, the study replaced all incremental convolutional layers in the YOLOv5 feature extraction network with the Channel Conversion Module (CCM). The model further refined the fish posture recognition by incorporating a cross-attention mechanism and replacing the CIoU_Loss function with the SIoU_loss function, thereby improving detection accuracy. To reduce model complexity and increase inference speed, the detection header was decoupled. Experimental results reveal that the YOLOv5-CCM model achieves a significant 5.03% increase in detection mean average precision (mAP) compared to the standard YOLOv5s model. Compared to other target detection algorithms such as SSD, Faster R-CNN, YOLOv4, YOLOX, and YOLOv8s, the mAP@0.5 showed improvements of 10.74%, 4.63%, 7.39%, 5.42%, and 1.61%, respectively. The YOLOv5-CCM model notably enhances detection accuracy, proving highly effective in identifying the underwater posture of Pelteobagrus fulvidraco and advancing fish status monitoring efforts. Keywords: Attention mechanism, Channel conversion module, High-density farming, Pose recognition, YOLOv5s.

Citrus pests and diseases severely impact fruit yield and quality. However, existing object detection models face limitations in complex backgrounds, target occlusion, and small target recognition, and they struggle to be efficiently deployed on resource-constrained devices. To address these issues, this study proposes a lightweight pest and disease detection model, YOLOv11-RDTNet, based on the improved YOLOv11n. This model integrates multi-scale features and attention mechanisms to enhance recognition performance in complex scenarios, while adopting a lightweight design to reduce computational costs and improve deployment adaptability. The model introduces three key enhancement features: First, shallow RFD (SRFD) and deep RFD (DRFD) downsampling modules replace traditional convolution modules, improving image feature extraction accuracy and robustness. Second, the Dynamic Group Shuffle Transformer (DGST) module replaces the original C3k2 module, reducing the model’s parameter count and computational demand, further enhancing efficiency and performance. Lastly, the lightweight Task Align Dynamic Detection Head (TADDH) replaces the original detection head, significantly reducing the parameter count and improving accuracy in small-object detection. After processing the collected images, we obtained 1382 images and constructed a dataset containing five types of citrus pests and diseases: anthracnose, canker, yellow vein disease, coal pollution disease, and leaf miner moth. We applied data augmentation on the dataset and conducted experimental validation. Experimental results showed that the YOLOv11-RDTNet model had a parameter count of 1.54 MB, an mAP50 of 87.0%, and a model size of 3.4 MB. Compared to the original YOLOv11 model, the YOLOv11-RDTNet model reduced the parameter count by 40.3%, improved mAP50 by 4.8%, and reduced the model size from 5.5 MB to 3.4 MB. This model not only improved detection accuracy and reduced computational load but also achieved a balance in performance, size, and speed, making it more suitable for deployment on mobile devices. Additionally, the research findings provided an effective tool for citrus pest and disease detection with small sample sizes, offering valuable insights for citrus pest and disease detection in agricultural practices.

Background: Pest detection plays a crucial role in smart agriculture; it is one of the primary factors that significantly impact crop yield and quality. Objective: In actual field environments, pests often appear as dense and small objects, which pose a great challenge to field pest detection. Therefore, this paper addresses the problem of dense small pest detection. Methods: We combine a pyramid vision transformer and prime sample attention (named PVTPSA) to design an effective pest detection model. Firstly, a pyramid vision transformer is adopted to extract pest feature information. Pyramid vision transformer fuses multi-scale pest features through pyramid structure and can capture context information of small pests, which is conducive to the feature expression of small pests. Then, we design prime sample attention to guide the selection of pest samples in the model training process to alleviate the occlusion effect between dense pests and enhance the overall pest detection accuracy. Results: The effectiveness of each module is verified by the ablation experiment. According to the comparison experiment, the detection and inference performance of the PVT-PSA is better than the other eleven detectors in field pest detection. Finally, we deploy the PVT- PSA model on a terrestrial robot based on the Jetson TX2 motherboard for field pest detection. Conclusion: The pyramid vision transformer is utilized to extract relevant features of pests. Additionally, prime sample attention is employed to identify key samples that aid in effectively training the pest detection models. The model deployment further demonstrates the practicality and effectiveness of our proposed approach in smart agriculture applications.

Greenhouse crop production is growing throughout the world and early pest detection is of particular importance in terms of productivity and reduction of the use of pesticides. Conventional eye observation methods are nonefficient for large crops. Computer vision and recent advances in deep learning can play an important role in increasing the reliability and productivity. This paper presents the development and comparison of two different approaches for vision based automated pest detection and identification, using learning strategies. A solution that combines computer vision and machine learning is compared against a deep learning solution. The main focus of our work is on the selection of the best approach based on pest detection and identification accuracy. The inspection is focused on the most harmful pests on greenhouse tomato and pepper crops, Bemisia tabaci and Trialeurodes vaporariorum. A dataset with a huge number of infected tomato plants images was created to generate and evaluate machine learning and deep learning models. The results showed that the deep learning technique provides a better solution because (a) it achieves the disease detection and classification in one step, (b) gets better accuracy, (c) can distinguish better between Bemisia tabaci and Trialeurodes vaporariorum, and (d) allows balancing between speed and accuracy by choosing different models.

Flowering is a crucial developing stage for rapeseed (Brassica napus L.) plants. Flowers develop on the main and branch inflorescences of rapeseed plants and then grow into siliques. The seed yield of rapeseed heavily depends on the total flower numbers per area throughout the whole flowering period. The number of rapeseed inflorescences can reflect the richness of rapeseed flowers and provide useful information for yield prediction. To count rapeseed inflorescences automatically, we transferred the counting problem to a detection task. Then, we developed a low-cost approach for counting rapeseed inflorescences using YOLOv5 with the Convolutional Block Attention Module (CBAM) based on unmanned aerial vehicle (UAV) Red-Green-Blue (RGB) imagery. Moreover, we constructed a Rapeseed Inflorescence Benchmark (RIB) to verify the effectiveness of our model. The RIB dataset captured by DJI Phantom 4 Pro V2.0, including 165 plot images and 60,000 manual labels, is to be released. Experimental results showed that indicators R2 for counting and the mean Average Precision (mAP) for location were over 0.96 and 92%, respectively. Compared with Faster R-CNN, YOLOv4, CenterNet, and TasselNetV2+, the proposed method achieved state-of-the-art counting performance on RIB and had advantages in location accuracy. The counting results revealed a quantitative dynamic change in the number of rapeseed inflorescences in the time dimension. Furthermore, a significant positive correlation between the actual crop yield and the automatically obtained rapeseed inflorescence total number on a field plot level was identified. Thus, a set of UAV- assisted methods for better determination of the flower richness was developed, which can greatly support the breeding of high-yield rapeseed varieties.

The target detection algorithm for accurately locating the location of objects in the image and their categories is widely used in intelligent traffic, forest fire prevention, electric power patrol and other fields. Existing target detection algorithms detect objects in head-up images, and their accuracy is not high when used in aerial image detection. To solve this problem, a small target detection algorithm based on improved RetinaNet model is proposed. First, replace the ResNet101 deep residual network in the original network with ResNet152, Independent of image features, The model is accelerated by merging ScaleNet network structure; Besides, in order to increase the feeling of the small target detection, to upgrade the existing FPN network output, increase the P2 feature layer, improved the range makes the network overall receptive field and the robustness of small target detection. Through the experimental result shows that compared with the original RetinaNet algorithm, The performance index of the improved algorithm is obviously improved. the average detection accuracy of the improved algorithm for small target detection is quite high 6.21%, it has a good detection effect in many scenarios.

Crops play a vital role in the global food supply. Various environmental factors can cause crop diseases and insect pests, resulting in severe production losses. However, manual detection of crop diseases and insect pests is a time-consuming and error-prone process, which often fails to identify and prevent the spread of plant diseases in a timely and effective manner. To overcome these challenges, machine learning (ML) and deep learning (DL) technologies have been introduced in recent years to improve early identification and effective response to plant pests and diseases. In this article, the principles of convolutional neural network (CNN), recurrent neural network (RNN) and adversarial generative neural network (GAN) are explained, as well as the latest progress in the improvement and application of the three algorithms in plant disease detection and detection. By applying DL technology, efficient and accurate detection of pests and diseases can be achieved, thereby providing reliable support for agricultural production. It is hoped that this work will become a valuable resource for researchers studying plant pest and disease detection and provide guidance to further advance research and practice in this field. At the same time, some current challenges and issues that need to be solved are also discussed, such as data quality, target occlusion, model generalization ability, and adaptability in practical applications. Deep learning holds great promise in revolutionizing precision agriculture by providing efficient and accurate solutions for pest and disease management.

To address the challenges of limited small-target detection performance in unmanned aerial vehicle (UAV) applications within complex and occlusion-prone environments, this study introduces an enhanced object detection algorithm named PCCS-YOLOv8. Developed upon the YOLOv8 architecture, the proposed method implements structural optimizations across multiple dimensions: it incorporates a dedicated P2 small-target detection layer to improve sensitivity to smaller objects and integrates a hybrid module combining Spatial Pyramid Pooling (SPP) with Efficient Layer Aggregation Networks (ELAN) for enhanced multi-scale feature representation [1]. The Convolutional Block Attention Module (CBAM) is further embedded to emphasize salient features critical for accurate detection. To mitigate the computational burden introduced by the P2 layer, a carefully designed lightweight component is implemented, effectively balancing model complexity and operational efficiency. Experimental evaluations demonstrate that the PCCS-YOLOv8 algorithm achieves a mAP@0.5 of 94% and a mAP@0.5:0.95 of 50.6%, corresponding to improvements of 2.9% and 2.2% over baseline models. Moreover, the optimized network maintains computational efficiency with 11.1G FLOPs and 2.81M parameters, substantially outperforming conventional detection networks in both accuracy and operational economy.

Strawberry cultivation faces significant challenges from pests and diseases, which are difficult to detect due to complex natural backgrounds and the high visual similarity between targets and their surroundings. This study proposes an advanced and lightweight detection algorithm, YOLO10-SC, based on the YOLOv10 model, to address these challenges. The algorithm integrates the convolutional block attention module (CBAM) to enhance feature representation by focusing on critical disease-related information while suppressing irrelevant data. Additionally, the Spatial and Channel Reconstruction Convolution (SCConv) module is incorporated into the C2f module to improve the model’s ability to distinguish subtle differences among various pest and disease types. The introduction of DySample, an ultra-lightweight dynamic upsampler, further enhances feature boundary smoothness and detail preservation, ensuring efficient upsampling with minimal computational resources. Experimental results demonstrate that YOLO10-SC outperforms the original YOLOv10 and other mainstream algorithms in precision, recall, mAP50, F1 score, and FPS while reducing model parameters, GFLOPs, and size. These improvements significantly enhance detection accuracy and efficiency, making the model well-suited for real-time applications in natural agricultural environments. The proposed algorithm offers a robust solution for strawberry pest and disease detection, contributing to the advancement of smart agriculture.

Pest infestations have always been a major factor affecting tea production. Real-time detection of tea pests using machine vision is a mainstream method in modern agricultural pest control. Currently, there is a notable absence of machine vision devices capable of real-time monitoring for small-sized tea pests in the market, and the scarcity of open-source datasets available for tea pest detection remains a critical limitation. This manuscript proposes a YOLOv8-FasterTea pest detection algorithm based on cross-domain transfer learning, which was successfully deployed in a novel tea pest monitoring device. The proposed method leverages transfer learning from the natural language character domain to the tea pest detection domain, termed cross-domain transfer learning, which is based on the complex and small characteristics shared by natural language characters and tea pests. With sufficient samples in the language character domain, transfer learning can effectively enhance the tiny and complex feature extraction capabilities of deep networks in the pest domain and mitigate the few-shot learning problem in tea pest detection. The information and texture features of small tea pests are more likely to be lost with the layers of a neural network becoming deep. Therefore, the proposed method, YOLOv8-FasterTea, removes the P5 layer and adds a P2 small target detection layer based on the YOLOv8 model. Additionally, the original C2f module is replaced with lighter convolutional modules to reduce the loss of information about small target pests. Finally, this manuscript successfully applies the algorithm to outdoor pest monitoring equipment. Experimental results demonstrate that, on a small sample yellow board pest dataset, the mAP@.5 value of the model increased by approximately 6%, on average, after transfer learning. The YOLOv8-FasterTea model improved the mAP@.5 value by 3.7%, while the model size was reduced by 46.6%.

Traditional maize seedling detection mainly relies on manual observation and experience, which is time-consuming and prone to errors. With the rapid development of deep learning and object-detection technology, we propose a lightweight model LW-YOLOv7 to address the above issues. The new model can be deployed on mobile devices with limited memory and real-time detection of maize seedlings in the field. LW-YOLOv7 is based on YOLOv7 but incorporates GhostNet as the backbone network to reduce parameters. The Convolutional Block Attention Module (CBAM) enhances the network’s attention to the target region. In the head of the model, the Path Aggregation Network (PANet) is replaced with a Bi-Directional Feature Pyramid Network (BiFPN) to improve semantic and location information. The SIoU loss function is used during training to enhance bounding box regression speed and detection accuracy. Experimental results reveal that LW-YOLOv7 outperforms YOLOv7 in terms of accuracy and parameter reduction. Compared to other object-detection models like Faster RCNN, YOLOv3, YOLOv4, and YOLOv5l, LW-YOLOv7 demonstrates increased accuracy, reduced parameters, and improved detection speed. The results indicate that LW-YOLOv7 is suitable for real-time object detection of maize seedlings in field environments and provides a practical solution for efficiently counting the number of seedling maize plants.

With the rapid development of autonomous driving technology, traditional object detection algorithms often face challenges such as the trade-off between model parameters and recognition accuracy, insufficient detection accuracy, and slow detection speed when dealing with vehicle and pedestrian detection tasks in complex scenarios. To address these challenges, we propose a novel lightweight real-time driving scene detection network, FEEP-YOLO. Based on the YOLOv8 algorithm, our network not only maintains high detection accuracy but also achieves faster training speed and fewer model parameters. FEEP-YOLO employs a lightweight network, Faster Net, to significantly reduce model parameters, thereby accelerating detection speed and better meeting real-time requirements. To further improve detection accuracy, we introduce an EMA attention module into the network and optimize the bounding box loss function, adopting the EIOU loss function to enhance target features and reduce background interference. Additionally, to detect small objects more accurately, we add feature layers rich in semantic information to the detection end. Experimental results demonstrate that FEEP-YOLO outperforms YOLOv8 in terms of both detection speed and accuracy on the KITTI and SODA datasets, while significantly reducing the number of model parameters and model size. FEEP-YOLO achieves high detection speed while improving detection accuracy and reducing computational resource consumption, meeting the practical application requirements under limited computing power, memory space and power consumption. The key contribution of FEEP-YOLO lies in its ability to balance accuracy speed, and efficiency, making it a robust solution for real-time autonomous driving applications in complex environments.

With the rapid development of UAV and infrared imaging technology, the cost of UAV infrared imaging technology has decreased steadily. Small target detection technology in aerial infrared images has great potential for applications in many fields, especially in the field of traffic surveillance. Because of the low contrast and relatively limited feature information in infrared images compared to visible images, the difficulty involved in small road target detection in infrared aerial images has increased. To solve this problem, this study proposes a feature-enhanced attention and dual-GELAN net (FEADG-net) model. In this network model, the reliability and effectiveness of small target feature extraction is enhanced by a backbone network combined with low-frequency enhancement and a swin transformer. The multi-scale features of the target are fused using a dual-GELAN neck structure, and a detection head with the parameters of the auto-adjusted InnerIoU is constructed to improve the detection accuracy for small infrared targets. The viability of the method was proved using the HIT-UAV dataset and IRTS-AG dataset. According to a comparative experiment, the mAP50 of FEADG-net reached more than 90 percent, which was higher than that of any previous method and it met the real-time requirements. Finally, an ablation experiment was conducted to demonstrate that all three of the modules proposed in the method contributed to the improvement in the detection accuracy. This study not only designs a new algorithm for small road object detection in infrared remote sensing images from UAVs but also provides new ideas for small target detection in remote sensing images for other fields.