基于方向累积的运动点目标检测新算法

A New Detection Algorithm of Moving Point Target Based on Directional Cumulation

针对从低信噪比图像序列中检测点目标运动轨迹问题,提出了基于方向累积的新方法。首先进行单帧检测,然后由多帧逻辑投影构成二维平面上的组合帧,再基于点目标运动轨迹的连续性,用方向累积来滤波并进行二次检测,最终提取目标运动轨迹及参数。仿真实验结果表明这种方法在对速度没有约束的情况下能够有效地检测出低信噪比条件下做直线或曲线运动的点目标,且运算复杂度很低。

A new algorithm based on directional cumulation is presented to detect the moving trajectory of a point target from image sequences in low SNR environments. First, single frame detection is performed, and then the logical ＂or＂ operation of multi-frame images are used to obtain a binary planar projective image. With that based on the continuity of the moving trajectory of the point target, directional cumulation is used to carry on the second detection. In the last the moving trajectory and it＇s parameters of targets can be acquired. The result of experiments shows that the proposed method is effective to detect and track targets moving along linear or curvilinear trajectory under the condition of unrestricted velocity in low SNR.