Page 84 - Read Online

Liu et al. Intell Robot 2024;4(3):256-75 I http://dx.doi.org/10.20517/ir.2024.17 Page 268

Figure 7. The feature matching results of different algorithms. (A) Original images in EuRoC sequence MH 01; (B) Matching result based
on Brute-Force algorithm; (C) Matching result based on RANSAC algorithm. RANSAC: Random Sample Consensus.

Table 2. Accuracy comparison of feature matching

Serial matching Parallel matching
algorithm algorithm
Number of Number of Successful Number of Successful
feature correct matching correct matching
points matches rate matches rate
100 99 99% 98 98%
200 194 97% 198 99%
400 389 97.25% 395 98.75%
800 796 99.5% 792 99%
1,600 1,590 99.38% 1,586 99.13%
3,200 3,184 99.5% 3,189 99.66%

accuracy for different numbers of feature point pairs, and compare it with the feature matching algorithm
implemented by OpenCV-CPU. The results are shown in Table 2. It can be seen that the matching accuracy
of the two algorithms is basically identical, indicating that the acceleration algorithm proposed in the paper is
effective.

Time consuming test is implemented on two 960*480 pixels images that have certain overlapping scenes. We
limit the number of features extracted in each image, and calculate the average runtime of serial and parallel
matching algorithms after executing 50 times. The results are shown in Figure 8.

As can be seen from Figure 8, the parallel feature matching algorithm takes much less time than the serial
matching algorithm. With the increase of the number of feature points, the speedup on both graphics cards
has improved, indicating that GPU has a better acceleration effect on large-scale data, but the improvement of
acceleration ratio slows down with the increase of the number of feature points. This is because data transfer