论文部分内容阅读
提出了利用粗糙集理论处理不完整信息的能力对红外弱小目标的运动轨迹进行辨识的检测方法。首先利用形态学滤波算法,分离出每帧图像中候选目标并提取其特征属性。把提取到的特征属性作为条件属性,把每帧图像中候选目标作为个体,构成知识决策系统。通过对决策表进行约简,得到决策系统的最小决策算法,并利用序列图像中目标运动的连续性和轨迹一致性来实现小目标的识别。实验表明,该方法能够有效解决目标跟踪过程中目标短暂丢失以及重现的问题,实现弱小目标的稳健检测和跟踪。
A method of detecting the motion trajectory of weak infrared targets using the ability of rough set theory to process incomplete information is proposed. First, the morphological filtering algorithm is used to separate the candidate objects in each frame of image and extract the feature attributes. The extracted feature attributes as the conditional attributes, the candidate images in each frame as an individual, constitute a knowledge decision-making system. Through the reduction of the decision table, the least decision algorithm of the decision-making system is obtained, and the recognition of the small target is realized by using the continuity and trajectory consistency of the target motion in the sequence image. Experimental results show that this method can effectively solve the problem of short-term target loss and reproduction in the target tracking process, and achieve robust detection and tracking of weak targets.