基于二维熵和粒子群优化的红外检测与跟踪

摘要

To shorten the time cost of infrared image target detection and improve the accuracy of the target tracking, the optimal threshold value of the target detection was determined using the two-dimensional entropy, and the particle swarm optimization algorithm was used for sampling.Using the two-dimensional information entropy in target detection, the biggest sum of two-dimensional entropy of the target and the background was used as a segmentation condition to obtain the optimal threshold in the research.To shorten the delay caused by the two-dimensional entropy large computation, the coarse search was used to look for maximum entropy point, and then precise search was used to look for the rest points around this point.Among them, the recursive way was used in the calculation process.In the process of target tracking, particle swarm optimization was used to optimize the filter, and the particle swarm optimization algorithm was used to optimize the sampling, which increased the diversity of the samples and ensured the quality of the samples, as well as the accuracy and robustness of tracking.%为缩短红外图像目标检测的时间并提高目标跟踪的准确度,采用二维熵确定目标检测的最佳阈值,用粒子群优化滤波法进行采样.运用信息二维熵于目标检测中,将目标和背景的二维熵和最大作为分割条件取得最佳阈值;为缩短二维熵带来的大运算量而造成的延时,通过粗搜索寻找熵值最大点,精准搜索该点的周围点,计算过程采取递推的方式,目标跟踪过程采取粒子群优化滤波方法,采用粒子群优化法优化采样,增加其样本的多样性,保证其质量,以及跟踪的精确性与鲁棒性.