Rain streaks in an image appear in different sizes and orientations,resulting in severe blurring and visual quality degradation.Previous CNNbased algorithms have achieved encouraging deraining results although there a...Rain streaks in an image appear in different sizes and orientations,resulting in severe blurring and visual quality degradation.Previous CNNbased algorithms have achieved encouraging deraining results although there are certain limitations in the description of rain streaks and the restoration of scene structures in different environments.In this paper,we propose an efficient multi-scale enhancement and aggregation network(MEAN)to solve the single-image deraining problem.Considering the importance of large receptive fields and multi-scale features,we introduce a multi-scale enhanced unit(MEU)to capture longrange dependencies and exploit features at different scales to depict rain.Simultaneously,an attentive aggregation unit(AAU)is designed to utilize the informative features in spatial and channel dimensions,thereby aggregating effective information to eliminate redundant features for rich scenario details.To improve the deraining performance of the encoder–decoder network,we utilized an AAU to filter the information in the encoder network and concatenated the useful features to the decoder network,which is conducive to predicting high-quality clean images.Experimental results on synthetic datasets and real-world samples show that the proposed method achieves a significant deraining performance compared to state-of-the-art approaches.展开更多
Inter-domain path computing is one big issue in multi-domain networks. The Hierarchical Path Computing Element (H-PCE) is a semi-central architecture for computing inter-domain path. To facilitate H-PCE in inter-domai...Inter-domain path computing is one big issue in multi-domain networks. The Hierarchical Path Computing Element (H-PCE) is a semi-central architecture for computing inter-domain path. To facilitate H-PCE in inter-domain path computing, this paper proposed a topology aggregation scheme to abstract the edge nodes and their connected inter-domain link as one vertex to achieve more optimal paths and confidentiality guarantee. The effectiveness of the scheme has been demonstrated on solving wavelength routing in multi-domain Wavelength Division Multiplexing (WDM) network via simulation. Simulation results show that this scheme reduces at least 10% inter-domain blocking probability, compared with the traditional Domain-to-the-Node (DtN) scheme.展开更多
检测与跟踪视频中的篮球可为教练复盘比赛提供关键信息。在比赛的视频流中,由于篮球目标较小,YOLOv5(You Only Look Once v5)算法对篮球与其他类圆形小目标的区分度较低。为此,在YOLOv5算法的基础上,首先采用V-C3(VoVNet C3)模块代替原C...检测与跟踪视频中的篮球可为教练复盘比赛提供关键信息。在比赛的视频流中,由于篮球目标较小,YOLOv5(You Only Look Once v5)算法对篮球与其他类圆形小目标的区分度较低。为此,在YOLOv5算法的基础上,首先采用V-C3(VoVNet C3)模块代替原C3模块,以解决篮球特征单一的问题,并通过K-L散度(Kullback-Leibler Divergence)验证改进的有效性。其次,采用桥式路径聚合网络(Bridge Path Aggregation Network,BPANet)代替原路径聚合网络(Path Aggregation Network,PANet),以解决场景中小目标篮球的检测问题。第三,构建分类惩罚机制,以降低篮球与相似目标的误检率。第四,探讨了各参数对篮球检测算法性能的影响,并探寻最佳参数取值和模型结构。实验结果表明,改进后算法的识别精度比原始YOLOv5算法提高了3个百分点,在COCO部分数据集上平均精度提高了2.4个百分点,算法的参数规模降低了5.3个百分点。本文对YOLOv5算法提出的4种改进策略,在保持较高实时性的基础上提高了视频中篮球目标的检测精度并降低模型规模,为类似的目标检测提供了一种新思路。展开更多
为提升弹载成像制导中运动模糊图像目标检测的精确性与效率,提出一种轻量化且高效的运动模糊图像目标检测(Lighter and More Effective Motion-blurred Image Object Detection,LEMBD)网络。通过深入分析运动模糊图像的成因,基于成像机...为提升弹载成像制导中运动模糊图像目标检测的精确性与效率,提出一种轻量化且高效的运动模糊图像目标检测(Lighter and More Effective Motion-blurred Image Object Detection,LEMBD)网络。通过深入分析运动模糊图像的成因,基于成像机理构建了专用的运动模糊图像数据集。在不增加网络参数的前提下,采用共享权重的孪生网络设计,并引入先验知识,将清晰图像的特征学习用于模糊图像的特征提取,以同时实现对清晰与模糊图像的精准检测。此外,设计了部分深度可分离卷积替代普通卷积,显著减少了网络的参数量与计算量,并提升了学习性能。为进一步优化特征融合质量,提出跨层路径聚合特征金字塔网络,有效利用低级特征的细节信息和高级特征的语义信息。实验结果表明,所提LEMBD网络在运动模糊图像目标检测任务中的性能优于传统目标检测方法和主流运动模糊检测算法,能够为精确制导任务提供更精准的目标相对位置信息。展开更多
基金supported by the National Natural Science Foundation of China(No.61972227)the Natural Science Foundation of Shandong Province(No.ZR201808160102)+4 种基金Shandong Provincial Natural Science Foundation Key Project(No.ZR2020KF015)the Key Research and Development Project of Shandong Province(No.2019GSF109112)the Science and Technology Plan for Young Talents in Colleges and Universities of Shandong Province(No.2020KJN007)the Scientific Research Studio in Colleges and Universities of Ji’nan City(No.2021GXRC092)the Science and Technology Research Program for Colleges and Universities in Shandong Province(No.KJ2018BZN029).
文摘Rain streaks in an image appear in different sizes and orientations,resulting in severe blurring and visual quality degradation.Previous CNNbased algorithms have achieved encouraging deraining results although there are certain limitations in the description of rain streaks and the restoration of scene structures in different environments.In this paper,we propose an efficient multi-scale enhancement and aggregation network(MEAN)to solve the single-image deraining problem.Considering the importance of large receptive fields and multi-scale features,we introduce a multi-scale enhanced unit(MEU)to capture longrange dependencies and exploit features at different scales to depict rain.Simultaneously,an attentive aggregation unit(AAU)is designed to utilize the informative features in spatial and channel dimensions,thereby aggregating effective information to eliminate redundant features for rich scenario details.To improve the deraining performance of the encoder–decoder network,we utilized an AAU to filter the information in the encoder network and concatenated the useful features to the decoder network,which is conducive to predicting high-quality clean images.Experimental results on synthetic datasets and real-world samples show that the proposed method achieves a significant deraining performance compared to state-of-the-art approaches.
基金Acknowledgements This work was supported by Chang Jiang Scholars Program of the Ministry of Education of China, National Science Fund for Distinguished Young Scholars under Grant No.60725104 the National Basic Research Program of China under Grant No. 2007CB310706+2 种基金 the National Natural Science Foundation of China under Ca＇ant No. 60932002, No. 60932005, No. 61071101 the Hi-Tech Research and Development Program of China under Grant No. 2009AA01Z254, No. 2009AA01Z215 NCEF Program of MoE of China, and Sichuan Youth Science and Technology Foundation under Crant No. 09ZQ026-032.
文摘Inter-domain path computing is one big issue in multi-domain networks. The Hierarchical Path Computing Element (H-PCE) is a semi-central architecture for computing inter-domain path. To facilitate H-PCE in inter-domain path computing, this paper proposed a topology aggregation scheme to abstract the edge nodes and their connected inter-domain link as one vertex to achieve more optimal paths and confidentiality guarantee. The effectiveness of the scheme has been demonstrated on solving wavelength routing in multi-domain Wavelength Division Multiplexing (WDM) network via simulation. Simulation results show that this scheme reduces at least 10% inter-domain blocking probability, compared with the traditional Domain-to-the-Node (DtN) scheme.
文摘为提升弹载成像制导中运动模糊图像目标检测的精确性与效率,提出一种轻量化且高效的运动模糊图像目标检测(Lighter and More Effective Motion-blurred Image Object Detection,LEMBD)网络。通过深入分析运动模糊图像的成因,基于成像机理构建了专用的运动模糊图像数据集。在不增加网络参数的前提下,采用共享权重的孪生网络设计,并引入先验知识,将清晰图像的特征学习用于模糊图像的特征提取,以同时实现对清晰与模糊图像的精准检测。此外,设计了部分深度可分离卷积替代普通卷积,显著减少了网络的参数量与计算量,并提升了学习性能。为进一步优化特征融合质量,提出跨层路径聚合特征金字塔网络,有效利用低级特征的细节信息和高级特征的语义信息。实验结果表明,所提LEMBD网络在运动模糊图像目标检测任务中的性能优于传统目标检测方法和主流运动模糊检测算法,能够为精确制导任务提供更精准的目标相对位置信息。
