物流智联网物(Internet of Things IoT)(下称物联网)代表了未来计算与通信技术发展的方向,被认为是继计算机、Internet之后,信息产业领域的第三次发展浪潮。本文在分析物流智联网的发展和F2C电子商务的三种商业模式,提出物联网下电子商...物流智联网物(Internet of Things IoT)(下称物联网)代表了未来计算与通信技术发展的方向,被认为是继计算机、Internet之后,信息产业领域的第三次发展浪潮。本文在分析物流智联网的发展和F2C电子商务的三种商业模式,提出物联网下电子商务业务模式的必然趋势,从而得出物流智联网对全球经济的意义。展开更多
This paper proposes the assumption of E-commerce platform of the agricultural products based on the F2C2B mode. The whole e-commerce model is guided by the idea of the supply chain management from the perspective of t...This paper proposes the assumption of E-commerce platform of the agricultural products based on the F2C2B mode. The whole e-commerce model is guided by the idea of the supply chain management from the perspective of the modern system, and the e-commerce integration model from customer to supplier is implemented, and the whole is optimized. E-commerce to cloud computing as the basic environment, the construction of public cloud services and private cloud resources, based on public cloud to the SaaS way to provide services to customers, focus on business search and business collaboration, make full use of the lnternet, modern communications technology to provide the real- service. The development of agricultural economy, no longer depends only on the number of some traditional agricultural resources, but also depends on the modern technology, information access and use. Through the development of basic network technology, by virtue of some modern electronic information technology and some other means that can improve the intelligence of agricultural use of the information resources, the proposed model provides the new methodology of the solution.展开更多
针对当前无人机(UAV)视角下小目标检测性能低以及漏检和误检的问题,提出基于YOLOv8改进的BDSYOLO(BiFPN-Dual-Small target detection-YOLO)模型。首先,使用RepViTBlock(Revisiting mobile CNN from ViT perspective Block)与EMA(Effici...针对当前无人机(UAV)视角下小目标检测性能低以及漏检和误检的问题,提出基于YOLOv8改进的BDSYOLO(BiFPN-Dual-Small target detection-YOLO)模型。首先,使用RepViTBlock(Revisiting mobile CNN from ViT perspective Block)与EMA(Efficient Multi-scale Attention)机制构造C2f-RE(C2f-RepViTBlock Efficient multi-scale attention)从而改进骨干网络中深层的C2f(faster implementation of CSP bottleneck with 2 Convolutions)模块,提升模型对小目标特征的提取能力并降低参数量;其次,使用双向特征金字塔网络(BiFPN)重构颈部网络,从而使不同层级的特征得以相互融合;然后,在改进颈部网络的基础上构造双重小目标检测层,并结合浅层和最浅层特征来提高模型对小目标的检测能力;最后,引入改进损失函数Inner-EIoU(Inner-Efficient-Intersection over Union),该函数使用更合理的宽高比衡量方式并解决交并比(IoU)自身的局限。实验结果表明,改进模型在VisDrone2019数据集上相对原始模型的精确率、召回率、mAP@50、mAP@50:95分别提升了8.5、7.7、9.2和6.3个百分点,而参数量仅为2.23×10~6,模型大小减小了19.1%。可见,所提模型在实现一定轻量化的同时显著提升了性能。展开更多
文摘物流智联网物(Internet of Things IoT)(下称物联网)代表了未来计算与通信技术发展的方向,被认为是继计算机、Internet之后,信息产业领域的第三次发展浪潮。本文在分析物流智联网的发展和F2C电子商务的三种商业模式,提出物联网下电子商务业务模式的必然趋势,从而得出物流智联网对全球经济的意义。
文摘This paper proposes the assumption of E-commerce platform of the agricultural products based on the F2C2B mode. The whole e-commerce model is guided by the idea of the supply chain management from the perspective of the modern system, and the e-commerce integration model from customer to supplier is implemented, and the whole is optimized. E-commerce to cloud computing as the basic environment, the construction of public cloud services and private cloud resources, based on public cloud to the SaaS way to provide services to customers, focus on business search and business collaboration, make full use of the lnternet, modern communications technology to provide the real- service. The development of agricultural economy, no longer depends only on the number of some traditional agricultural resources, but also depends on the modern technology, information access and use. Through the development of basic network technology, by virtue of some modern electronic information technology and some other means that can improve the intelligence of agricultural use of the information resources, the proposed model provides the new methodology of the solution.
文摘针对当前无人机(UAV)视角下小目标检测性能低以及漏检和误检的问题,提出基于YOLOv8改进的BDSYOLO(BiFPN-Dual-Small target detection-YOLO)模型。首先,使用RepViTBlock(Revisiting mobile CNN from ViT perspective Block)与EMA(Efficient Multi-scale Attention)机制构造C2f-RE(C2f-RepViTBlock Efficient multi-scale attention)从而改进骨干网络中深层的C2f(faster implementation of CSP bottleneck with 2 Convolutions)模块,提升模型对小目标特征的提取能力并降低参数量;其次,使用双向特征金字塔网络(BiFPN)重构颈部网络,从而使不同层级的特征得以相互融合;然后,在改进颈部网络的基础上构造双重小目标检测层,并结合浅层和最浅层特征来提高模型对小目标的检测能力;最后,引入改进损失函数Inner-EIoU(Inner-Efficient-Intersection over Union),该函数使用更合理的宽高比衡量方式并解决交并比(IoU)自身的局限。实验结果表明,改进模型在VisDrone2019数据集上相对原始模型的精确率、召回率、mAP@50、mAP@50:95分别提升了8.5、7.7、9.2和6.3个百分点,而参数量仅为2.23×10~6,模型大小减小了19.1%。可见,所提模型在实现一定轻量化的同时显著提升了性能。
