基于多尺度纹理特征的最小二乘法深度信息估计方法  

The Least- square Depth Information Estimation Method based on Multi- scale Texture Features

作　　者：牛连丁[1] 陈婷婷[2] 张立志[2] 

机构地区：[1]哈尔滨商业大学网络与教育技术中心,哈尔滨150028 [2]哈尔滨商业大学计算机与信息工程学院,哈尔滨150028

出　　处：《智能计算机与应用》2015年第4期71-74,共4页Intelligent Computer and Applications

基　　金：黑龙江省自然科学基金(F201245)

摘　　要：由于二维图像三维化技术重建三维场景可以低成本、高效率地提供三维显示资源,使得该技术成为图像处理领域重要的研究课题。深度线索的提取是重建三维场景的重要研究内容之一。为了更好地描述纹理特征与场景深度之间的关系,提出了一种基于多尺度纹理特征的最小二乘深度信息估计方法。通过构建多尺度模型、纹理滤波的方法捕捉头像的多尺度纹理梯度、纹理变化等特征作为训练样本;并进行训练,得到纹理线索与场景深度间的关系参量;最后用该参量来估计待测样本的深度。实验结果表明,该方法对场景深度信息的估计具有较好的效果。With the advantage of low cost and high efficiency for 3D display market,the technique of 3D scene reconstruction from 2D scene image has been the main research contents in the field of image processing. For the 3D reconstruction,the extraction of depth cues is one of the most important contents. Therefore,the paper proposes a least- square depth estimation method based on multi- scale texture features,which can better describe the relationship between the texture features and the scene depth. By using the methods of constructing multi- scale model and texture filtering,the paper captures the features of the texture gradient and texture variations as the training sample sets,and then trains these samples to get the relationship parameters between texture cues and scene depth,which can finally be applied to estimate the depth of the test sample sets. The experimental results show that the proposed method performs well in scene depth information extraction.

关 键 词：多尺度纹理 最小二乘方法 深度估计 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]