A novel depth estimation method for uncalibrated stereo images

被引：0

作者：

Loghman, Maziar ^{[1
]}

Zarshenas, Amin ^{[1
]}

Chung, Kwang-Hoon ^{[2
]}

Lee, Yunsik ^{[3
]}

Kim, Loohee ^{[1
]}

机构：

[1] IIT, 3301 S Dearborn St, Chicago, IL 60616 USA

[2] Sane Syst, Anyang So, Gyunki Do, South Korea

[3] Korea Elect Tech Inst, Songnam, Gyungki Do, South Korea

来源：

2014 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC) | 2014年

关键词：

Stereo vision; depth estimation; image rectification; fundamental matrix;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, a depth map estimation algorithm that performs stereo matching without explicit image rectification has been proposed. In the proposed method, the fundamental matrix is estimated by using Random Sample Consensus and the 8-point algorithm. Then, the epilolar line equation obtained by the projective mapping is derived and the search for point correspondence is performed along the epilolar line. Simulation results show that the proposed method produces accurate depth maps for uncalibrated stereo images with reduced computational complexity.

引用

页码：186 / 187

页数：2

共 7 条

[1] RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY [J].