基于多特征仿生的车辆伪装防护设计  

Design of Vehicle Camouflage Protection Based on Multi Feature Bionics

在线阅读下载全文

作  者:董超逸 周宪 曹岩 朱子彦 邹易 Dong Chao-yi;Zhou Xian;Cao Yan;Zhu Zi-yan;Zou Yi(School of Mechatronic Engineering,Xi'an Technological University,Xi'an 710021,China;School of Art And Media,Xi'an Technological University,Xi'an 710021,China;School of Computer Science and Engineering,Xi'an Technological University,Xi'an 710021,China)

机构地区:[1]西安工业大学机电工程学院,西安710021 [2]西安工业大学艺术与传媒学院,西安710021 [3]西安工业大学计算机科学与工程学院,西安710021

出  处:《内燃机与配件》2022年第22期7-9,共3页Internal Combustion Engine & Parts

摘  要:针对传统采用附加组件提高伪装性的方法进步空间愈来愈小、单特征仿生提高伪装性的方法不具有针对性设计的问题,提出一种利用多特征仿生设计优化的方法。首先,利用建立源域生物以及载具部件形式化模型,通过分析相似性以及确定仿生本征次序进行多特征仿生,其次,利用基于图像变形的图像融合将源域与仿生域图像融合,然后,利用形状上下文检测与源域生物相似度;最后再利用形状上下文检测新造型对伪装的优劣,在悍马M1114基础上进行多特征仿生设计,选定林地为背景。实验结果表明新造型与源域生物相似度更高,并且伪装效果得到了明显的提升。Aiming at the problems that the traditional method of using additional components to improve camouflage has less room for improvement,and the method of single-feature bionic to improve camouflage does not have targeted design,a method for optimization using multi-feature bionic design is proposed.domain biology and vehicle parts formal models,multi-feature bionics are performed by analyzing similarity and determining bionic eigenorders;secondly,image fusion based on image warping is used to fuse source domain and bionic domain images;then,shape context detection and Biosimilarity of the source domain;finally,the shape context is used to detect the pros and cons of the new model for camouflage,and the multi-feature bionic design is carried out on the basis of Hummer M1114,and the forest land is selected as the background.The experimental results show that the new model has higher biological similarity with the source domain.,and the camouflage effect has been significantly improved.

关 键 词:形状上下文 图像融合 仿生 概念设计 伪装防护 

分 类 号:TJ812.8[兵器科学与技术—武器系统与运用工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象