摘要
当投影仪将图像投影到复杂表面时,为使观察者观看到不失真图像,提出了基于角点检测的几何校正方法。该方法利用对复杂表面投影白色区域图像的阈值分割来提取校正区域;进行横纵特征条纹的提取和处理,获取投影系统中特征点的坐标;通过对观察者所需的理想图像进行变换获得投影仪所需预变形图像。编写了基于OpenCV的校正软件。实验表明,该方法可以有效消除复杂表面引起的几何畸变,得到良好的观看效果。
When image is projected onto the complex surface, the geometric correction method based on corner detection is proposed in order to see the image without distortion. The method extracts areas of correctionly using threshold segmentation to white region image on complex surface. Then, the vertical and horizontal features stripes was extracted and processed to obtain the coordi- nates of feature points in the projection system. Finally, through the tronsfornmtion of the ideal image that observer required to get the pre-deformation image. The calibration software is completed based on OpenCV. The experiments show that this method can effectively eliminate the geometric distortion caused by the complex surface and get a good viewing experience.
出处
《微型机与应用》
2012年第24期32-34,共3页
Microcomputer & Its Applications
基金
国家科技支撑计划项目(2009BAE69B00)
关键词
曲面投影
几何校正
角点检测
projection on curved surface
geometric correction
corner detection