A METHOD FOR IMPROVING THE ACCURACY OF SFM 3D MEASUREMENTS BY RANDOM PATTERN PROJECTION

被引：0

作者：

Sugano M. ^{[1
]}

Kakizaki K. ^{[1
]}

Tominaga Y. ^{[1
]}

Araki S. ^{[1
]}

机构：

[1] Graduate School of Computer Science and Systems Engineering, Kyushu Institute of Technology

来源：

AIJ Journal of Technology and Design | 2023年 / 29卷 / 71期

关键词：

3D measurement; Measurement accuracy; Pattern projection; Point cloud; Random pattern; SfM;

D O I：

10.3130/AIJT.29.533

中图分类号：

学科分类号：

摘要：

SfM can reconstruct the 3D shape of an object with high accuracy if there are many feature points on the surface to be measured. However, in the field of architecture, there is a problem that building surfaces are beautifully preserved and the shape cannot be reconstructed because of the small number of feature points. In this study, we proposed a method to improve the measurement accuracy of SfM by projecting a random pattern on a wall surface and distributing a large number of feature points. Experiments confirmed that the measurement accuracy was as good as that of a laser scanner. © 2023 Architectural Institute of Japan. All rights reserved.

引用

页码：533 / 537

页数：4

共 4 条

[1]

Tomasi C., Kanade T., Shape and motion from image streams under orthography: a factorization method, Int' 1. J. Computer Vision, 9, 2, pp. 137-154, (1992)

[2]

Introduction to SIFT (Scale-Invariant Feature Transform)

[3]

Zhang Zhengyou, Microsoft Kinect Sensor and Its Effect, IEEE lultiMedia, 19, pp. 4-12, (2012)

[4]

Kakizaki K., Mukai T., Araki S., A HIGH-PRECISION 3D LASER MEASUREMENT METHOD BASED ON ESTIMATION OF TRUE VALUES BY HIGH-DENSITY MEASUREMENTS AND CALCULATION OF DIFFERENCES BETWEEN MEASUREMENT DATA OF TWO TIMES, AIJ Journal of Technology and Design, 28, 68, pp. 515-520, (2022)

← 1 →