摘要
针对利用Photoshop软件手工提取深度的精确度不高、造成立体视频闪烁的问题,提出在提取深度之前利用Canny算子进行边缘预分割的改进措施,提高了深度层,尤其是运动对象深度层边界的精度。对合成立体视频的立体显示实验证明改进方法有效地改善了合成立体视频的质量。
For manual depth extraction by Photoshop software would result in lower depth accuracy and video flickering, the images is pre-segmented by Canny edge extraction before depth extraction in this paper, which increase the accuracy of depth layers boundaries, especially the depth layers boundaries of moving objects. Experimental results in real stereoscopic display test show that the new method effectively improves the quality of the transformed 3D video.
出处
《电视技术》
北大核心
2009年第9期38-41,共4页
Video Engineering
基金
国家自然科学基金项目(60832003)
上海市科委重点项目(09511503700)
上海市大学生创新活动项目(CXSJ07-045)
关键词
立体显示器
立体视觉
深度提取
边缘检测
stereoscopic display
stereo vision
depth extraction
edge detection
