Many monographs point out that differential encoding and decoding is necessary for ef- fectual information transmission against phase ambiguity while seldom discuss the reason why phase ambiguity will emerge inevitabl...Many monographs point out that differential encoding and decoding is necessary for ef- fectual information transmission against phase ambiguity while seldom discuss the reason why phase ambiguity will emerge inevitably.Available algorithms are specially designed for certain modulation scheme;these algorithms cannot satisfy the requirement of soft-defined radio,which perhaps demands a uniform algorithm for different modulations.This paper proposes a new opinion on phase ambiguity from the view of probability.This opinion believes that modulating symbol sequence can affect,at optimum sampling epoch,the modulated waveform as oscillating carrier has done,and so the stochastic sequence leads to phase ambiguity.Based on a general signal model,this paper also puts forward a novel universal algorithm,which is suitable for different signals,even some new ones,by configuring several parameters.展开更多
目的相比于一般视频目标检测跟踪任务,视频羽毛球的实时定位跟踪主要面临两大难点:1)羽毛球属于小目标,同时伴有严重的运动模糊以及相似目标的干扰,使用基于矩形框的目标检测跟踪方法准确率低且会带来中心点误差问题;2)单帧图像很难准...目的相比于一般视频目标检测跟踪任务,视频羽毛球的实时定位跟踪主要面临两大难点:1)羽毛球属于小目标,同时伴有严重的运动模糊以及相似目标的干扰,使用基于矩形框的目标检测跟踪方法准确率低且会带来中心点误差问题;2)单帧图像很难准确定位羽毛球目标,利用视频前后帧的时域特征则可以跟踪到羽毛球目标,而现有提取时域特征的网络模块结构复杂,难以满足实时性要求。针对以上问题,本文使用热力图轮廓检测方法,提出了羽毛球运动小目标的定位跟踪网络算法(shuttlecock track net,STNet)。方法网络主体采用“U”型编解码结构;针对小目标像素信息少的问题,基于SE(squeeze and excitation)通道注意力与残差结构设计高效特征提取模块(SE channel attention and residual,SECAR),实现了空域信息的高效提取与传递,提高了网络的定位性能;针对目标丢失与相似目标干扰问题,设计了时序网络(temporal network,TPN)结构用于提取和记忆视频时域特征,提高了网络跟踪性能。结果在羽毛球比赛公开数据集TrackNetv2与自制数据集上的实验表明,本文方法在多个指标上取得了最好的性能表现。相较于现有性能较好的羽毛球定位跟踪方法TrackNetv2,本文方法在准确率、精确率和F1上分别提高7.5%、15.7%和7.5%,并且显著降低了参数量,满足实时处理需求(54帧/s)。结论本文提出的STNet羽毛球定位跟踪网络,在面对羽毛球目标外观剧烈变化以及背景干扰严重时,能够准确定位羽毛球比赛视频帧中可能存在的羽毛球,实现羽毛球的稳定跟踪,相比其他羽毛球定位跟踪网络,具有更优的性能。展开更多
基金Supported by Henan Prominent Talents Innovation Foundation (No.0421000100).
文摘Many monographs point out that differential encoding and decoding is necessary for ef- fectual information transmission against phase ambiguity while seldom discuss the reason why phase ambiguity will emerge inevitably.Available algorithms are specially designed for certain modulation scheme;these algorithms cannot satisfy the requirement of soft-defined radio,which perhaps demands a uniform algorithm for different modulations.This paper proposes a new opinion on phase ambiguity from the view of probability.This opinion believes that modulating symbol sequence can affect,at optimum sampling epoch,the modulated waveform as oscillating carrier has done,and so the stochastic sequence leads to phase ambiguity.Based on a general signal model,this paper also puts forward a novel universal algorithm,which is suitable for different signals,even some new ones,by configuring several parameters.
文摘目的相比于一般视频目标检测跟踪任务,视频羽毛球的实时定位跟踪主要面临两大难点:1)羽毛球属于小目标,同时伴有严重的运动模糊以及相似目标的干扰,使用基于矩形框的目标检测跟踪方法准确率低且会带来中心点误差问题;2)单帧图像很难准确定位羽毛球目标,利用视频前后帧的时域特征则可以跟踪到羽毛球目标,而现有提取时域特征的网络模块结构复杂,难以满足实时性要求。针对以上问题,本文使用热力图轮廓检测方法,提出了羽毛球运动小目标的定位跟踪网络算法(shuttlecock track net,STNet)。方法网络主体采用“U”型编解码结构;针对小目标像素信息少的问题,基于SE(squeeze and excitation)通道注意力与残差结构设计高效特征提取模块(SE channel attention and residual,SECAR),实现了空域信息的高效提取与传递,提高了网络的定位性能;针对目标丢失与相似目标干扰问题,设计了时序网络(temporal network,TPN)结构用于提取和记忆视频时域特征,提高了网络跟踪性能。结果在羽毛球比赛公开数据集TrackNetv2与自制数据集上的实验表明,本文方法在多个指标上取得了最好的性能表现。相较于现有性能较好的羽毛球定位跟踪方法TrackNetv2,本文方法在准确率、精确率和F1上分别提高7.5%、15.7%和7.5%,并且显著降低了参数量,满足实时处理需求(54帧/s)。结论本文提出的STNet羽毛球定位跟踪网络,在面对羽毛球目标外观剧烈变化以及背景干扰严重时,能够准确定位羽毛球比赛视频帧中可能存在的羽毛球,实现羽毛球的稳定跟踪,相比其他羽毛球定位跟踪网络,具有更优的性能。
