Depth extraction of low-texture region using a light field camera

Depth extraction of low-texture region using a light field camera
复制标题

使用光场相机提取低纹理区域的深度

DOI:
10.1117/1.oe.56.7.073110
复制
发表时间:
2017-07
影响因子:
1.3
通讯作者:
Shoujiang Zhao
Shoujiang Zhao
中科院分区:
工程技术4区
文献类型:
--
作者:
Hongying Zhao;Miao Zheng;Peng Yang;Shoujiang Zhao

文献摘要

参考文献

相似文献

摘要。提出了一种利用光场相机对低纹理区域进行深度提取的方法,扩大了该方法的应用范围。通过对LF数据的分析,证明了单幅LF图像可以估计出深度信息。此外,由于小透镜LF数据可以被解码成一个子图像阵列,并且子图像之间的关系被证明是仿射变换,因此我们使用三角形网格面积分割比表示的几何关系来代替低纹理区域不可靠的灰度值进行立体匹配。此外,为了获得准确的比例值,使用投影仪投影预设点以丰富纹理,方便可靠。与传统的LF方法相比,该方法明显提高了低纹理区域深度提取的精度,并通过实验对结果进行了验证。
Abstract. A method is proposed for depth extraction of low-texture region with a light field (LF) camera, which expands the application. Based on the analysis of LF data, it is proven that the depth information can be estimated from a single LF image. Furthermore, as the lenslet LF data can be decoded into a subimages array, and the relationship among subimages is proven to be affine transformation, we used the geometry relationship, which is represented by partition ratio of triangle grids area, to replace the unreliable gray value of low-texture region for stereo matching. In addition, to obtain accurate ratio values, preset points are projected to enrich the texture with a projector, which is convenient and reliable. The proposed method improves the accuracy of the depth extraction obviously at low-texture region compared with the traditional state-of-the-art LF method, and results are validated by experiments.
DOI: 10.1109/tpami.2013.147
发表时间: 2014-03-01
影响因子: 23.6
作者:
Wanner, Sven;Goldluecke, Bastian
通讯作者: Goldluecke, Bastian
DOI: 10.1016/j.cviu.2004.06.001
发表时间: 2005-01-01
影响因子: 4.5
作者:
Criminisi, A;Kang, SB;Anandan, P
通讯作者: Anandan, P
DOI: 10.1016/j.cviu.2015.12.007
发表时间: 2016-04-01
影响因子: 4.5
作者:
Zhang, Shuo;Sheng, Hao;Xiong, Zhang
通讯作者: Xiong, Zhang
DOI: 10.1007/bf00977785
发表时间: 1980-01-01
期刊: INTERNATIONAL JOURNAL OF COMPUTER & INFORMATION SCIENCES
影响因子: --
作者:
LEE, DT;SCHACHTER, BJ
通讯作者: SCHACHTER, BJ
DOI: 10.1109/tip.2012.2207393
发表时间: 2012-10
影响因子: 10.6
作者:
Qingxiong Yang;N. Ahuja
通讯作者: Qingxiong Yang;N. Ahuja