节点文献

基于图像处理技术的自动报靶系统的设计与实现

A Design and Realization of Automatic Target-scoring System Based on Image Processing Technology

【作者】 张晓锟

【导师】 林嘉宇;

【作者基本信息】 国防科学技术大学 , 电子与通信工程, 2009, 硕士

【摘要】 当前,部队实弹射击训练大多依然采用传统的人工报靶方式,其存在着安全性差、效率低等弊端。而自动报靶系统具有快速、高效、精确的特点,相比人工报靶优势明显。因此,满足部队实训需求的自动报靶系统的研发,对于推动军队现代化建设进程具有重要意义。本文本着贴近部队、贴近实训的设计原则,对基于图像处理技术的自动报靶系统加以认真分析研究。论文详细阐述了自动报靶系统的设计和图像处理的相关算法,并进行了大量仿真试验。论文主要工作如下:一是介绍了论文研究的背景和当前自动报靶系统的研究现状,并对基于图像处理技术的自动报靶系统作了重点说明。二是结合部队射击训练的特点,本着功能齐全、便于实现、快速准确的设计要求,提出了一种基于图像处理技术的自动报靶系统设计方案。三是介绍了图像获取的相关知识,采用小波变换对采集图像进行了亚采样;分析研究了中值滤波、几何校正、图像差影和二值化等图像预处理的相关算法,并分别加以仿真实现。特别是在二值化环节,提出了一种改进的二维Otsu算法。四是在详细介绍了数学形态学和边缘检测相关知识的基础上,采用了形态学滤噪、Canny边缘检测等方法,得到了清晰的弹孔边缘;而后运用三点定圆的方法找到了弹心坐标。五是采用了提取靶心和各环线半径,进而创建环值区域,比较弹心坐标所在区域的方法来实现环值判定。经过大量的研究和仿真试验表明,本文提出的自动报靶系统总体设计和相关算法切实可行,不仅有效结合了部队射击训练的特点,且实现了快速、高效、精准判靶,能够较好地满足部队训练的需求,具有一定的学术和实用价值。

【Abstract】 At present, most of military shooting trainings are still using traditional manual target-scoring systems, which have some defects in security and efficiency. Automatic target-scoring system is fast, efficient and precise. It has advantages compared with the manual method. Therefore, the research on automatic target-scoring system for shooting will make great progress in the modernization of training for the army.Based on armed and practical training, this paper presents a lot of careful analysis and study on automatic target-scoring system. An automatic target-reporting system is designed and related image processing algorithms are studied in this thesis. A large number of simulation experiments are conducted.The main work of this paper is as follows:1. Background and status of current study on automatic target-scoring systems are described.2. An automatic target-scoring system based on image processing technologies is proposed. Hardware platform and software implementations are designed.3. Images of the target are captured, and then sub-sampled using wavelet transform. Furthermore, median filter, geometric correction, image subtraction and binarization algorithms are used to process the images. Especially, an improved two-dimensional Otsu algorithm is put forward.4. Morphological filtering, Canny edge detection are used to get clear edges of bullet-spot. Then Three-Points Circle Method is presented to find the core coordinate.5. According to the geometric relationship between the core point of the bullet-hole and the loop lines, the corresponding shooting score is calculated.Large amounts of simulating show that our automatic target-scoring system is efficient and precise. It can be settled for the military training.

节点文献中: 

本文链接的文献网络图示:

本文的引文网络