论文部分内容阅读
针对低信噪比红外图像中弱小目标检测难的问题,在分析红外弱小目标各向梯度特征的基础上,提出了一种新的红外弱小目标检测算法。该算法基于红外弱小目标各向梯度均快速下降的特征,首先根据目标大小在待检测点上、下、左、右选取4个参考点,根据多步长下待检测点与参考点之间的最大梯度特征,判定潜在目标;然后通过连续3帧检测信息的融合,确定最终目标。该算法无需预测背景,计算简单,可在低信噪比、强度变化剧烈的图像中有效检测弱小目标。实验结果表明了算法的有效性。
Aiming at the difficulty in detecting small and weak targets in low SNR images, a new algorithm of infrared small target detection is proposed based on the analysis of the gradient characteristics of weak and weak infrared targets. The algorithm is based on the feature that the gradient of the gradient of the infrared weak target decreases rapidly. Firstly, according to the size of the target, four reference points are selected on the spot to be detected, down, left and right. According to the distance between the point to be detected and the reference point Maximum gradient characteristics, to determine potential targets; and then through the fusion of three consecutive detection information to determine the final target. The algorithm does not need to predict the background, the calculation is simple, and can effectively detect weak targets in images with low SNR and intense intensity. Experimental results show the effectiveness of the algorithm.