摘要
激光红外图像中的小区域目标定位复杂程度较高,在提取图像特征过程中容易降低图像分辨率,导致小区域目标模糊,对目标定位精度产生一定影响。为了提高目标定位效果,引入投影变换矩阵,提出激光红外图像的小区域目标定位方法。采用小波变换方法分解激光红外图像,结合直方图均衡方法增强图像处理,通过卷积操作增强图像边缘点,提升激光红外图像对比度及分辨率。使用覆盖算子提取激光红外图像目标特征,根据特征点相似性确定小区域目标范围,建立投影变换矩阵匹配小区域目标,实现目标位置定位。实验结果表明,使用所提方法开展激光红外图像小区域目标定位时,定位误差为0.7%、定位精度平均为94.0%、算法计算效率为96.3%、定位匹配度为100%,可以准确定位目标位置。
Small area target location in laser infrared image is very complex,and it is easy to reduce the resolution of image,which leads to the blurring of small area target.In order to improve the effect of target location,the projection transformation matrix is introduced and a small area target location method of laser infrared image is proposed.Wavelet transform is used to decompose the laser infrared image,histogram equalization is used to enhance the image processing,and edge points are enhanced by convolution.The coverage operator is used to extract the target features of laser infrared image,and the target range is determined according to the similarity of feature points.Experimental results show that the proposed method can accurately locate small targets in infrared images with 0.7%localization error,94.0%average localization accuracy,96.3%computational efficiency and 100%matching degree.
作者
朱慧泉
付波
ZHU Huiquan;FU Bo(Department of Computer Science and Art Design,Henan Light Industry Vocational College,Zhengzhou He'nan 450000,China;School of Electrical and Electronic Engineering,Hubei University of Technology,Wuhan Hubei 430068,China)
出处
《电子器件》
CAS
2024年第5期1221-1226,共6页
Chinese Journal of Electron Devices
基金
激光图像技术国家重点实验室基金(554811511)。
关键词
激光红外图像
小区域
目标定位
小波分解
特征增强
变换矩阵
laser infrared image
small area
target positioning
wavelet decomposition
feature enhancement
transformation matrix
