红外技术, 2019, 41 (9): 837, 网络出版: 2019-10-14
基于多尺度 NNLoG特征提取的红外多目标检测遗传算法
Genetic Algorithm for Infrared Multi-target Detection Based on Multi-scale NNLoG Feature
摘要
本文提出了一种基于多尺度 NNLoG特征提取的红外多目标检测遗传算法。首先采用三维匹配滤波器对不同速度的目标进行基于归一化 LoG算子的目标检测, 然后采用遗传算法对程序进行优化及加速。与传统算法相比, 本文提出的方法检测效率高, 检测效果好。并且可以自适应不同大小的目标。实验结果表明, 提出的方法性能优良, 搜索目标效率较高。
Abstract
A genetic algorithm based on multi-scale NNLoG feature extraction for infrared multi-target detection is proposed in this study. First, a three dimensional matching filter is used to detect a target based on the normalized LoG operator for targets with different speeds. Subsequently, the genetic algorithm is used to optimize and accelerate the program. Compared to traditional algorithms, the proposed method has high detection efficiency and accuracy and can detect targets of different sizes. Experimental results show that the proposed method performs well with high search efficiency.
孙士新, 郑志蕴. 基于多尺度 NNLoG特征提取的红外多目标检测遗传算法[J]. 红外技术, 2019, 41(9): 837. SUN Shixin, ZHENG Zhiyun. Genetic Algorithm for Infrared Multi-target Detection Based on Multi-scale NNLoG Feature[J]. Infrared Technology, 2019, 41(9): 837.