基于多阶段轨迹融合的交叉多目标检测与跟踪算法

A New Method Based on Multi-Stages Trace Association for Detection and Tracking of Crossing Multi-Targets

构建了一种多阶段轨迹融合算法,预处理阶段利用局部对比度自适应门限抑制杂波,同时结合高阶相关滤波器剔除噪声和杂波边缘.在轨迹互联阶段,多阶段的双向搜索算法辅佐以目标航迹的能量累积,能够尽早锁定目标.实验分析表明,该方法能够准确的检测和跟踪作任意轨迹运动的多个点目标,在搜索空间和时间复杂度上明显优于传统的相关性算法.

Aiming at the detection and tracking of multiple point targets distributed in cl oudy background,a new method,namely the multi-stages trace association is pre se nted.In the preprocessing,a module based on local auto-adaptive contrast thres h old is given to remove the slowly varying clutter and at the same time,the nois e with high intensity and the edge of clutter are filtered with a bi-directional high order correlation filter.When constructing deep-searching trees the adopt ion of searching strategy from both directions can be pruned earlier.In the post pro cessing the energy along the candidate trajectories are accumulated and it can c ut the false traces efficiently.Moreover,for the spatial-temporal consistency a nd continuity of the targets it can lock the true targets as soon as possible.Th e experimental results show that it can detect and track dim overlapping point t a rgets with arbitrary trajectories accurately.It is advantageous over the traditi onal correlation algorithms in searching space and time complexity.