High speed photography technique is potentially the most effective way to measure the motion parameter of warhead fragment benefiting from its advantages of high accuracy,high resolution and high efficiency.However,it...High speed photography technique is potentially the most effective way to measure the motion parameter of warhead fragment benefiting from its advantages of high accuracy,high resolution and high efficiency.However,it faces challenge in dense objects tracking and 3D trajectories reconstruction due to the characteristics of small size and dense distribution of fragment swarm.To address these challenges,this work presents a warhead fragments motion trajectories tracking and spatio-temporal distribution reconstruction method based on high-speed stereo photography.Firstly,background difference algorithm is utilized to extract the center and area of each fragment in the image sequence.Subsequently,a multi-object tracking(MOT)algorithm using Kalman filtering and Hungarian optimal assignment is developed to realize real-time and robust trajectories tracking of fragment swarm.To reconstruct 3D motion trajectories,a global stereo trajectories matching strategy is presented,which takes advantages of epipolar constraint and continuity constraint to correctly retrieve stereo correspondence followed by 3D trajectories refinement using polynomial fitting.Finally,the simulation and experimental results demonstrate that the proposed method can accurately track the motion trajectories and reconstruct the spatio-temporal distribution of 1.0×10^(3)fragments in a field of view(FOV)of 3.2 m×2.5 m,and the accuracy of the velocity estimation can achieve 98.6%.展开更多
针对视觉算法在检测航拍图像中密集小目标时容易受到目标重叠、遮挡等情况干扰的现象,提出了一种基于高阶空间特征(目标形状、位置等信息的高级表示)提取的Transformer检测头HSF-TPH(Transformer prediction head with high-order spati...针对视觉算法在检测航拍图像中密集小目标时容易受到目标重叠、遮挡等情况干扰的现象,提出了一种基于高阶空间特征(目标形状、位置等信息的高级表示)提取的Transformer检测头HSF-TPH(Transformer prediction head with high-order spatial feature extraction)。所提检测头中将自注意力机制中的二阶交互扩展到三阶以生成高阶空间特征,提取更有区分度的空间关系,突出每一个小目标在空间上的语义信息。同时,为了缓解骨干网络过度下采样对小目标信息的压缩,设计了一种高分辨率特征图生成机制,增加头部网络的输入特征分辨率,以提升HSFTPH检测密集小目标的效果。设计了新的损失函数USIoU,降低算法位置偏差敏感性。在VisDrone2019数据集上开展实验证明,所提算法在面积最小、密度最高的人类目标的检测任务中实现了mAP50指标10个百分点以上的性能提升。展开更多
基金Key Basic Research Project of Strengthening the Foundations Plan of China (Grant No.2019-JCJQ-ZD-360-12)National Defense Basic Scientific Research Program of China (Grant No.JCKY2021208B011)to provide fund for conducting experiments。
文摘High speed photography technique is potentially the most effective way to measure the motion parameter of warhead fragment benefiting from its advantages of high accuracy,high resolution and high efficiency.However,it faces challenge in dense objects tracking and 3D trajectories reconstruction due to the characteristics of small size and dense distribution of fragment swarm.To address these challenges,this work presents a warhead fragments motion trajectories tracking and spatio-temporal distribution reconstruction method based on high-speed stereo photography.Firstly,background difference algorithm is utilized to extract the center and area of each fragment in the image sequence.Subsequently,a multi-object tracking(MOT)algorithm using Kalman filtering and Hungarian optimal assignment is developed to realize real-time and robust trajectories tracking of fragment swarm.To reconstruct 3D motion trajectories,a global stereo trajectories matching strategy is presented,which takes advantages of epipolar constraint and continuity constraint to correctly retrieve stereo correspondence followed by 3D trajectories refinement using polynomial fitting.Finally,the simulation and experimental results demonstrate that the proposed method can accurately track the motion trajectories and reconstruct the spatio-temporal distribution of 1.0×10^(3)fragments in a field of view(FOV)of 3.2 m×2.5 m,and the accuracy of the velocity estimation can achieve 98.6%.
文摘针对视觉算法在检测航拍图像中密集小目标时容易受到目标重叠、遮挡等情况干扰的现象,提出了一种基于高阶空间特征(目标形状、位置等信息的高级表示)提取的Transformer检测头HSF-TPH(Transformer prediction head with high-order spatial feature extraction)。所提检测头中将自注意力机制中的二阶交互扩展到三阶以生成高阶空间特征,提取更有区分度的空间关系,突出每一个小目标在空间上的语义信息。同时,为了缓解骨干网络过度下采样对小目标信息的压缩,设计了一种高分辨率特征图生成机制,增加头部网络的输入特征分辨率,以提升HSFTPH检测密集小目标的效果。设计了新的损失函数USIoU,降低算法位置偏差敏感性。在VisDrone2019数据集上开展实验证明,所提算法在面积最小、密度最高的人类目标的检测任务中实现了mAP50指标10个百分点以上的性能提升。
