In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm...In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm based on YOLOv8 was proposed in this study.To begin with,the CoordAtt attention mechanism was employed to enhance the feature extraction capability of the backbone network,thereby reducing interference from backgrounds.Additionally,the BiFPN feature fusion network with an added small object detection layer was used to enhance the model's ability to perceive for small objects.Furthermore,a multi-level fusion module was designed and proposed to effectively integrate shallow and deep information.The use of an enhanced MPDIoU loss function further improved detection performance.The experimental results based on the publicly available VisDrone2019 dataset showed that the improved model outperformed the YOLOv8 baseline model,mAP@0.5 improved by 20%,and the improved method improved the detection accuracy of the model for small targets.展开更多
Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary a...Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary and drag-rise performance. Hicks-Henne shape functions are used to represent the bump shape. In the design optimization to increase lift-drag ratio, the objectives involve the cruise point and three other off-design points nearby. In the other optimization process to improve buffet and drag-rise performance, three buffet onset points near the cruise point and one drag-rise point are selected as the design points. Non-dominating sort genetic algorithm II （NSGA-II） is used in both processes. Additionally, individual analysis for every selected point on the Pareto frontier is conducted in order to avoid local convergence and achieve global optimum. Re- sults of optimization for aerodynamic efficiency show a decrease of 11 counts in drag at the cruise point. Drag at nearby off-design points are also reduced to some extent. Similar approaches are made to improve buffet and drag-rise characteristics, resulting in significant improvements in both ways.展开更多
文摘In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm based on YOLOv8 was proposed in this study.To begin with,the CoordAtt attention mechanism was employed to enhance the feature extraction capability of the backbone network,thereby reducing interference from backgrounds.Additionally,the BiFPN feature fusion network with an added small object detection layer was used to enhance the model's ability to perceive for small objects.Furthermore,a multi-level fusion module was designed and proposed to effectively integrate shallow and deep information.The use of an enhanced MPDIoU loss function further improved detection performance.The experimental results based on the publicly available VisDrone2019 dataset showed that the improved model outperformed the YOLOv8 baseline model,mAP@0.5 improved by 20%,and the improved method improved the detection accuracy of the model for small targets.
文摘Based on the supercritical ＂wingl＂ which was released in the DPW-III conference, multi-objective optimization has been done to increase the lift-drag ratio at cruise condition and improve transonic buffet boundary and drag-rise performance. Hicks-Henne shape functions are used to represent the bump shape. In the design optimization to increase lift-drag ratio, the objectives involve the cruise point and three other off-design points nearby. In the other optimization process to improve buffet and drag-rise performance, three buffet onset points near the cruise point and one drag-rise point are selected as the design points. Non-dominating sort genetic algorithm II （NSGA-II） is used in both processes. Additionally, individual analysis for every selected point on the Pareto frontier is conducted in order to avoid local convergence and achieve global optimum. Re- sults of optimization for aerodynamic efficiency show a decrease of 11 counts in drag at the cruise point. Drag at nearby off-design points are also reduced to some extent. Similar approaches are made to improve buffet and drag-rise characteristics, resulting in significant improvements in both ways.
