An Improved YOLO Model for UAV Fuzzy Small Target Image Detection

Chang, Yanlong; Li, Dong; Gao, Yunlong; Su, Yuehua; Jia, Xiaoqiang

doi:10.3390/app13095409

Cited by 14 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FLOPs and model size are used to measure the model’s computational complexity. FLOPs refer to the number of floating-point operations in the model [ 34 ]. Higher FLOPs mean higher computational complexity of the model, which may require more computational resources.…”

Section: Methodsmentioning

confidence: 99%

YOLOv5-Atn: An Algorithm for Residual Film Detection in Farmland Combined with an Attention Mechanism

Lin

Zhang

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

The application of mulching film has significantly contributed to improving agricultural output and benefits, but residual film has caused severe impacts on agricultural production and the environment. In order to realize the accurate recycling of agricultural residual film, the detection of residual film is the first problem to be solved. The difference in color and texture between residual film and bare soil is not obvious, and residual film is of various sizes and morphologies. To solve these problems, the paper proposes a method for detecting residual film in agricultural fields that uses the attention mechanism. First, a two-stage pre-training approach with strengthened memory is proposed to enable the model to better understand the residual film features with limited data. Second, a multi-scale feature fusion module with adaptive weights is proposed to enhance the recognition of small targets of residual film by using attention. Finally, an inter-feature cross-attention mechanism that can realize full interaction between shallow and deep feature information to reduce the useless noise extracted from residual film images is designed. The experimental results on a self-made residual film dataset show that the improved model improves precision, recall, and mAP by 5.39%, 2.02%, and 3.95%, respectively, compared with the original model, and it also outperforms other recent detection models. The method provides strong technical support for accurately identifying farmland residual film and has the potential to be applied to mechanical equipment for the recycling of residual film.

show abstract

Section: Methodsmentioning

confidence: 99%

YOLOv5-Atn: An Algorithm for Residual Film Detection in Farmland Combined with an Attention Mechanism

Lin

Zhang

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The IOU loss function in YOLOv8 is the same as that in YOLOv5, and its calculation formula is shown in Equation (16), where IOU represents the intersection over union, b and b gt represent the centroids of two rectangular boxes, p represents the Euclidean distance between the two rectangular boxes, c represents the diagonal distance of the enclosed regions of the two rectangular boxes, v is used to measure the consistency of the relative proportions of the two rectangular boxes, and a is the weighting coefficient [35].…”

Section: Fusion Loss Functionmentioning

confidence: 99%

Early Drought Detection in Maize Using UAV Images and YOLOv8+

Niu,

Nie,

et al. 2024

Drones

View full text Add to dashboard Cite

The escalating global climate change significantly impacts the yield and quality of maize, a vital staple crop worldwide, especially during seedling stage droughts. Traditional detection methods are limited by their single-scenario approach, requiring substantial human labor and time, and lack accuracy in the real-time monitoring and precise assessment of drought severity. In this study, a novel early drought detection method for maize based on unmanned aerial vehicle (UAV) images and Yolov8+ is proposed. In the Backbone section, the C2F-Conv module is adopted to reduce model parameters and deployment costs, while incorporating the CA attention mechanism module to effectively capture tiny feature information in the images. The Neck section utilizes the BiFPN fusion architecture and spatial attention mechanism to enhance the model’s ability to recognize small and occluded targets. The Head section introduces an additional 10 × 10 output, integrates loss functions, and enhances accuracy by 1.46%, reduces training time by 30.2%, and improves robustness. The experimental results demonstrate that the improved Yolov8+ model achieves precision and recall rates of approximately 90.6% and 88.7%, respectively. The mAP@50 and mAP@50:95 reach 89.16% and 71.14%, respectively, representing respective increases of 3.9% and 3.3% compared to the original Yolov8. The UAV image detection speed of the model is up to 24.63 ms, with a model size of 13.76 MB, optimized by 31.6% and 28.8% compared to the original model, respectively. In comparison with the Yolov8, Yolov7, and Yolo5s models, the proposed method exhibits varying degrees of superiority in mAP@50, mAP@50:95, and other metrics, utilizing drone imagery and deep learning techniques to truly propel agricultural modernization.

show abstract

“…It directly compares the central point values of the boxes to improve bounding box regression accuracy. Chang et al [21] utilized the Alpha-IoU loss function to address slow convergence during training on small target images. Shang et al [22] employed Focal EIoU to replace the traditional CIoU in the model, accelerating network convergence speed and improving target box regression accuracy.…”

Section: Introductionmentioning

confidence: 99%

Research on YOLOv8 Object Detection Algorithm in UAV Scenarios

Li,

Chen,

Sun

et al. 2024

Preprint

View full text Add to dashboard Cite

Aerial images captured by Unmanned Aerial Vehicles (UAVs) often exhibit characteristics such as high object density, small targets, and wide coverage, which lead to the occurrence of false positives and false negatives in existing object detectors. In order to improve detection accuracy, this study proposes an enhanced YOLOv8 object detection model. Firstly, the Deformable Convolutional Networks v2 (DConv2) is incorporated into the backbone's C2F module to expand the receptive field of the image and enhance the detection accuracy of small objects. Secondly, the Fousion Block module is employed in the neck network to increase network depth and strengthen feature fusion capability. Subsequently, the model incorporates up sampling operations and discards large object detection layers, further improving the detection progress for small objects. Finally, the Efficient Intersection over Union (ECIoU) loss function is adopted to replace the Complete Intersection over Union (CIoU) loss function, accelerating the model's convergence speed and enhancing object detection precision. The improved model is validated using the VisDrone2019-DET-train dataset, and the results demonstrate that the enhanced model Yolov8s_UAU achieves anmAP of 49.5%, representing a 7.3% improvement over traditional models. With the capability to maintain UAV detection speed, the proposed model can more accurately accomplish the detection tasks for small targets during UAV aerial photography processes.

show abstract

An Improved YOLO Model for UAV Fuzzy Small Target Image Detection

Cited by 14 publications

References 23 publications

YOLOv5-Atn: An Algorithm for Residual Film Detection in Farmland Combined with an Attention Mechanism

YOLOv5-Atn: An Algorithm for Residual Film Detection in Farmland Combined with an Attention Mechanism

Early Drought Detection in Maize Using UAV Images and YOLOv8+

Research on YOLOv8 Object Detection Algorithm in UAV Scenarios

Contact Info

Product

Resources

About