弹丸目标红外图像的阈值分割算法研究  

A Threshold Segmentation Algorithm for Infrared Images of Projectile Target

作　　者：尚在飞[1] 王春平[1] 付强[1] 

机构地区：[1]军械工程学院,石家庄050003

出　　处：《电光与控制》2015年第1期34-38,共5页Electronics Optics & Control

基　　金：军队预研重点项目

摘　　要：针对红外弹丸目标图像的特点,在分析比较了几种传统的基于直方图阈值分割算法的基础上,探讨了提高该类算法实时性的途径。结合弹丸目标体积固定的特点,提出了一种基于p率直方图的快速算法。在分割效果上提高了对弹丸目标提取的准确性,在运行时间上与传统直方图阈值分割算法相比平均降低了30%以上。在Matlab环境下进行了仿真,验证了算法的有效性和实时性。According to the characteristics of infrared projectile target images,and on the foundation of analyzing several histogram-based threshold segmentation algorithms,a method for improving the real-time performance of such algorithms was studied. Considering the feature of fixed pixels of projectile images,we proposed a rapid algorithm based on p-tile histogram. On the segmentation effectiveness,the algorithm can improve the accuracy for extracting the projectile target. Compared with the traditional histogram-based thresholding algorithms,the algorithm can decrease the running time by 30%. Simulation based on Matlab shows the effectiveness and real-time performance of the algorithm.

关 键 词：红外小目标 目标检测 弹丸目标 图像分割 直方图方法 p率直方图 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TP751.1[自动化与计算机技术—检测技术与自动化装置]