本文将小目标的帧间信息和光流法紧密联系起来,把小目标的检测分为小目标的预处理、帧间差分和使用金字塔迭代Lucas-Kanade的光流法确定目标三个步骤进行。实验结果表明,该方法能够有效地检测运动小目标。
This paper presents a novel detection method of small moving target. The method combines the information in frames with optical flow. It is composed of three steps: preprocessing, temporal differencing and Lucas-Kanade optical flow based on pyramid construction. The experimental results have shown that the algorithm works well for small moving target detection in real image sequences.