基于双目立体视觉的乘员运动姿态测量方法研究  

Research on test method of occupant motion attitude measurement based on binocular stereo vision

在线阅读下载全文

作  者:凌雄娟[1] 周云郊[2,3] 彭建喜[1] Ling Xiongjuan;Zhou Yunjiao;Peng Jianxi(School of Electronic Information,Foshan Polytechnic Institute,Guangdong Foshan,528000,China;School of Mechanical and Automotive Engineering,South China University of Technology,Guangdong Guangzhou,510640,China;Guangdong Provincial Key Laboratory of Automotive,Guangdong Guangzhou,510640,China)

机构地区:[1]佛山职业技术学院电子信息学院,广东佛山528000 [2]华南理工大学机械与汽车工程学院,广东广州510640 [3]广东省汽车工程重点实验室,广东广州510640

出  处:《机械设计与制造工程》2024年第1期126-130,共5页Machine Design and Manufacturing Engineering

基  金:佛山市教育局2021年高校教师特色创新研究项目(2021DZXX02);广东省自然科学基金(2021A1515010912);广东省教育厅普通高校重点科研平台项目(2022KCXT060);佛山职业技术学院2023年质量工程项目(2023SZTD-004)。

摘  要:提出了基于双目立体视觉的汽车乘员运动姿态测量方法。首先使用自主搭建的双目立体视觉系统,按照张正友标定法标定相机并对图像进行立体校正;然后提出基于邻域的SGBM单参数优化算法,并依此建立乘员关键特征点与三维空间坐标间的映射关系,实现了对乘员运动姿态的非接触动态测量。实验结果表明,该方法可以有效地测量乘员运动姿态,且测量精度较高,对汽车乘员非标准坐姿下的保护策略制定具有重要的参考价值。This paper presents a method based on binocular stereo vision to solve the dynamic measurement of occupant motion attitude in collision experiment.Using the binocular stereo vision system,the camera is calibrated according to Zhang Zhengyou calibration method and then conduct the stereo rectification.A neighborhood-based SGBM single parameter optimization algorithm is proposed to establish the mapping relationship between the occupant feature points and the three-dimensional space coordinates,and obtain the three-dimensional space coordinates of the occupant attitude.Experiments show that this method can effectively measure the occupant attitude position,and the measurement accuracy is high.It is of great significance to the development of the protection strategy for vehicle safety,especially for the non regulatory standard sitting posture of the occupant.

关 键 词:双目立体视觉 乘员姿态测量 半全局匹配算法 

分 类 号:U467.14[机械工程—车辆工程]

 

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