红外运动弱小目标的动态规划检测

Dynamic Programming Approach to Small Moving Target Detection in Infrared Image Sequences

  • 摘要: 针对动态规划方法在对红外序列图像运动弱小目标进行检测时的能量扩散问题,提出了一种新的检测方法。该方法以目标的运动特性为基础,构造出一个高斯模板来描述目标在下一帧可能出现的位置,利用概率来描述目标可能的运动而不是直接的硬约束,能很好地克服目标运动的随机性。将该方法应用于实际的红外序列图像的运动弱小目标检测,实验结果表明,可以大幅降低动态规划方法的能量扩散问题。

     

    Abstract: A new small moving target detection algorithm in infrared image sequences is presented to reduce the energy scattering in dynamic programming-based algorithm. Based on the property of target motion, a Gaussian template is built to model target position in the next frame. Our algorithm uses probability not hard constrain, so it can overcome the randomicity of target motion. Experiments with real infrared image sequences show our algorithm can greatly reduce the energy scattering in dynamic programming-based algorithm.

     

/

返回文章
返回