Stereo Ground Truth with Error Bars
Stereo Ground Truth with Error Bars
复制标题
DOI：
10.1007/978-3-319-16814-2_39
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
D. Kondermann;Rahul Nair;S. Meister;W. Mischler;Burkhard Güssefeld;Katrin Honauer;Sabine Hofmann
中科院分区：
文献类型：
--
作者：
D. Kondermann;Rahul Nair;S. Meister;W. Mischler;Burkhard Güssefeld;Katrin Honauer;Sabine Hofmann
基于真实的图像创建立体地面实况是一项测量任务。测量永远不会完全准确：每个像素的深度都遵循误差分布。估计测量质量的常用方法是误差条。在本文中，我们描述了一种方法来添加误差线的图像先前扫描的静态场景。基于此类数据的立体地面实况误差估计的主要挑战是2D图像与3D点的非线性匹配。我们的方法使用2D特征质量，3D点和校准精度以及束平差的协方差矩阵。我们对参考数据误差进行采样，参考数据误差是每个点投影到3D图像空间的3D深度分布。然后通过将参考数据误差的样本投影到2D图像平面上来估计每个像素位置处的视差分布。分析高斯误差传播被用来验证结果。作为概念证明，我们创建了具有100帧的图像序列的地面实况。结果表明，视差精度远低于一个像素，可以实现，虽然有很大的误差，主要是由不确定的估计相机位置造成的深度不连续。
Creating stereo ground truth based on real images is a measurement task. Measurements are never perfectly accurate: the depth at each pixel follows an error distribution. A common way to estimate the quality of measurements are error bars. In this paper we describe a methodology to add error bars to images of previously scanned static scenes. The main challenge for stereo ground truth error estimates based on such data is the nonlinear matching of 2D images to 3D points. Our method uses 2D feature quality, 3D point and calibration accuracy as well as covariance matrices of bundle adjustments. We sample thereference data errorwhich is the 3D depth distribution of each point projected into 3D image space. Thedisparity distributionat each pixel location is then estimated by projecting samples of the reference data error on the 2D image plane. An analytical Gaussian error propagation is used to validate the results. As proof of concept, we created ground truth of an image sequence with 100 frames. Results show that disparity accuracies well below one pixel can be achieved, albeit with much large errors at depth discontinuities mainly caused by uncertain estimates of the camera location.