|
- 2016
基于柯西分布的单幅图像深度估计
|
Abstract:
单幅图像深度估计是目前计算机视觉和计算机图形学中的一个挑战性问题。基于柯西分布的点扩散函数模型(point spread function,PSF),给出了一种以计算物体图像边沿散焦模糊量实现单幅图像场景深度估计的方法。将原始散焦图像分别用两个柯西分布核重新模糊,用两模糊图像的梯度比值计算边沿散焦模糊量,得到稀疏深度估计,再通过内插方法取得场景的全深度估计。多种真实场景图像的实验结果表明,本方法能够从非标定单幅散焦图像中较好地估计场景深度,且对图像噪声、边沿误差和邻近边沿的干扰具有较好的鲁棒性,综合性能优于现有基于高斯PSF模型的方法;同时,验证了也可用非高斯模型建模PSF
[1] | Veeraraghavan A, Raskar R, Agrawal A, et al. Dappled Photography:Mask Enhanced Cameras for Heterodyned Light Fields and Coded Aperture Refocusing[C]. ACM SIGGRAPH, San Diego, 2007 |
[2] | Levin A, Fergus R, Durand F, et al. Image and Depth from a Conventional Camera with a Coded Aperture[C]. ACM SIGGRAPH, San Diego, 2007 |
[3] | Ens J, Lawrence P. An Investigation of Methods for Determining Depth from Focus[J]. <em>IEEE Transactions on Pattern Analysis and Machine Intelligence</em>, 1993, 15(2):97-108 |
[4] | Pentland A P. A New Sense for Depth of Field[J].<em>IEEE Transactions on Pattern Analysis and Machine Intelligence</em>, 1987, 9(4):523-531 |
[5] | Zhuo S, Sim T. Recovering Depth from a Single Defocused Image[J]. <em>Pattern Recognition</em>, 2011, 44(9):1852-1858 |
[6] | Fang S, Qin T, Cao Y, et al. Depth Recovery from a Single Defocused Image Based on Depth Locally Consistency[C]. The 5th International Conference on Internet Multimedia Computing and Service, Huangshan, China, 2013 |
[7] | Ming Ying, Jiang Jingjue. Moving Objects Detection and Shadows Elimination for Video Sequence[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2008, 33(12):1216-1220(明英,蒋晶珏.视频序列图像中运动目标检测与阴影去除[J].武汉大学学报·信息科学版,2008,33(12):1216-1220) |
[8] | Moreno-Noguer F, Belhumeur P N, Nayar S K. Active Refocusing of Images and Videos[J]. <em>ACM Trans Graphics</em>, 2007, 26(3):67-75 |
[9] | Subbarao M, Gurumoorthy N. Depth Recovery from Blurred Edges[C]. Computer Society Conference on Computer Vision and Pattern Recognition, Michigan, 1988 |
[10] | Lee S, Lee J, Hayes M H, et al. Single Camera-based Full Depth Map Estimation Using Color Shifting Property of a Multiple Color-Filter Aperture[C]. ICASSP, Kyoto, Japan, 2012 |
[11] | Namboodiri V P, Chaudhuri S. Recovery of Relative Depth from a Single Observation Using an Uncalibrated (Real-Aperture) Camera[C]. IEEE Conference on Computer Vision and Pattern Recognition, Alaska, 2008 |