3D reconstruction technique based on SURF-OKG feature matching

Table 1. Preliminary feature matching results of the SURF algorithm
View table
View in Article
Table 1. Preliminary feature matching results of the SURF algorithm
匹配数正确匹配数正确匹配率/%
传统SURF 71 49 69.01
改进SURF 75 57 76.65

Table 2. Secondary feature matching results of the SURF-OKG algorithm
View table
View in Article
Table 2. Secondary feature matching results of the SURF-OKG algorithm
匹配数正确匹配数正确匹配率/%
本文算法 202 185 91.58

Table 3. Feature point matching results of different algorithms
View table
View in Article
Table 3. Feature point matching results of different algorithms
匹配数正确匹配数正确匹配率/% 耗时/s
SIFT 454 388 85.26 4.023
SURF 182 142 78.42 0.748
ORB 498 364 73.27 1.631
SURF-OKG 485 448 92.47 2.891

Table 4. Binocular camera calibration results

View table

View in Article

Table 4. Binocular camera calibration results

内参矩阵

$M_{L} = [\begin{matrix} 3.581 121 46 \times 10^{3} & 0 & 1.259 401 42 \times 10^{3} \\ 0 & 3.577 615 47 \times 10^{3} & 1.032 672 79 \times 10^{3} \\ 0 & 0 & 1 \end{matrix}]$

$M_{R} = [\begin{matrix} 3.595 605 92 e + 03 & 0 & 1.194 383 20 \times 10^{3} \\ 0 & 3.597 358 98 \times 10^{3} & 1.010 168 02 \times 10^{3} \\ 0 & 0 & 1 \end{matrix}]$

外参矩阵

$\begin{array}{l} D_{L} = [\begin{matrix} - 3.508 331 74 \times 10^{- 2} & 2.568 322 66 \times 10^{- 1} & - 4.233 416 33 \times 10^{- 4} \end{matrix} \\ \begin{matrix} 5.586 009 70 \times 10^{- 5} & - 1.239 371 92 \times 10^{- 1} \end{matrix}] \end{array}$

$\begin{array}{l} D_{R} = [\begin{matrix} - 3.219 153 46 \times 10^{- 2} & 2.243 644 92 \times 10^{- 1} & - 2.211 489 98 \times 10^{- 4} \end{matrix} \\ \begin{matrix} - 8.376 793 01 \times 10^{- 4} & - 1.895 272 40 \times 10^{- 1} \end{matrix}] \end{array}$

旋转矩阵

R = [\begin{matrix} 9.323 543 05 \times 10^{- 1} & - 4.057 619 26 \times 10^{- 3} & 3.615 231 47 \times 10^{- 1} \\ 8.871 245 94 \times 10^{- 4} & 9.999 596 85 \times 10^{- 1} & 8.935 364 92 \times 10^{- 3} \\ - 3.615 448 28 \times 10^{- 1} & - 8.010 209 87 \times 10^{- 3} & 9.323 203 17 \times 10^{- 1} \end{matrix}]

平移矩阵

\begin{array}{l} D_{L} = [- 2.637 902 1 \times 10^{2} \begin{matrix} 1.013 302 0 \times 10^{- 1} \end{matrix} \\ \begin{matrix} 6.264 246 6 \times 10] \end{matrix} \end{array}

Tools

Get Citation

Copy Citation Text

Lei ZHANG, Yan SHI, Wenyong LU, Rui XU, Zhan JIN, Weijie LUO, Yi CEHN, Chunliu ZHAO, Chunlian ZHAN. 3D reconstruction technique based on SURF-OKG feature matching[J]. Optics and Precision Engineering, 2024, 32(6): 915

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites