A series of conjugated copolymers derived from 9-ethylhexyl-2,7-carbazole(Cz)and 4,7-di(4-hexylthien-2-yl)- 2,1,3-benzothiadiazole(DHTBT)was synthesized by Suzuki polycondensation.The photo-and electro-luminescent pro...A series of conjugated copolymers derived from 9-ethylhexyl-2,7-carbazole(Cz)and 4,7-di(4-hexylthien-2-yl)- 2,1,3-benzothiadiazole(DHTBT)was synthesized by Suzuki polycondensation.The photo-and electro-luminescent properties of these polymers were investigated.Efficient energy transfer from the Cz segment to the DHTBT unit occurs even if the DHTBT content as low as 1 mol%.PL emission was red-shifted significantly from 645 nm to 700 nm with the increase in DHTBT content by 1-50 mol%.PL efficiencies decreased...展开更多
针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max poolin...针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max pooling-attention),使得模型更加关注小目标的特征,提高小目标检测精度。为了加强对小目标的细节感知能力,使用DCNv3(deformable convolution network v3)替换骨干网络中的二维卷积,以此构建新的层聚合模块ELAN-D。为网络设计新的小目标检测层以获取更精细的特征信息,从而提升模型的鲁棒性。同时使用MPDIoU(minimum point distance based IoU)替换原模型中的CIoU来优化损失函数,以适应遥感图像的尺度变化。实验表明,所提出的方法在DOTA-v1.0数据集上取得了良好效果,准确率、召回率和平均准确率(mean average precision,mAP)相比原模型分别提升了0.4、4.0、2.3个百分点,证明了该方法能够有效提升遥感图像中小目标的检测效果。展开更多
基金This work was supported by the Ministry of Science and Technology of China(No.2002CB613402)the National Natural Science Foundation of China(No.50433030).
文摘A series of conjugated copolymers derived from 9-ethylhexyl-2,7-carbazole(Cz)and 4,7-di(4-hexylthien-2-yl)- 2,1,3-benzothiadiazole(DHTBT)was synthesized by Suzuki polycondensation.The photo-and electro-luminescent properties of these polymers were investigated.Efficient energy transfer from the Cz segment to the DHTBT unit occurs even if the DHTBT content as low as 1 mol%.PL emission was red-shifted significantly from 645 nm to 700 nm with the increase in DHTBT content by 1-50 mol%.PL efficiencies decreased...
文摘针对遥感图像中小目标数量众多且背景复杂所导致的识别精度低的问题,提出了一种改进的遥感图像小目标检测方法。该方法基于改进的YOLOv7网络模型,将双级路由注意力机制加入至下采样阶段以构建针对小目标的特征提取模块MP-ATT(max pooling-attention),使得模型更加关注小目标的特征,提高小目标检测精度。为了加强对小目标的细节感知能力,使用DCNv3(deformable convolution network v3)替换骨干网络中的二维卷积,以此构建新的层聚合模块ELAN-D。为网络设计新的小目标检测层以获取更精细的特征信息,从而提升模型的鲁棒性。同时使用MPDIoU(minimum point distance based IoU)替换原模型中的CIoU来优化损失函数,以适应遥感图像的尺度变化。实验表明,所提出的方法在DOTA-v1.0数据集上取得了良好效果,准确率、召回率和平均准确率(mean average precision,mAP)相比原模型分别提升了0.4、4.0、2.3个百分点,证明了该方法能够有效提升遥感图像中小目标的检测效果。