摘要
以显著性标志物中的关键点为目标,探讨了一种基于计算机视觉的目标方位测量方法。在光学成像原理基础上,推算出目标二维成像点坐标与其空间三维坐标之间的映射关系,基于计算机视觉理论建立了测量目标方位的数学模型。考虑透镜畸变,基于Zhang平面标定法完成对摄像机参数的标定。对目标二维图像采用Harris算法进行特征角点检测,并通过亚像素技术对检测的目标特征点进行定位。实验结果表明,该方法能够有效提取被测目标特征角点并获取其像素坐标,用于测量目标相对视觉传感器的方位信息可达到较高精度,具备良好的实用价值。
Aiming at key point of obvious marker,an azimuth measuring method for targets based on computer vision system is investigated.According to the principle of projection imaging,the mapping relationship between the 3D position and the 2D image of the target is derived,and the target azimuth measuring mathematical model is established based on monocular vision system.Lens distortion has been taken into account during the implement of Zhang’s calibration method. Harris corner detector is brought to find the most characteristic corners on 2D image,and the sub-pixel orientation method is applied to the positioning of target feature points.The experimental results show that the method can effectively extract the target feature points and get its pixel coordinates,acquiring a relatively accurate target azimuth,which has good application value.
出处
《火力与指挥控制》
CSCD
北大核心
2016年第3期161-165,共5页
Fire Control & Command Control
基金
军内科研基金资助项目
关键词
计算机视觉
摄像机标定
角点检测
亚像素定位
目标方位
computer vision
camera calibration
corner detecting
sub-pixel orientation
target azimuth
