EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Salient Preprocessing: Robotic ICP Pose Estimation Based on SIFT Features

Lihe Hu, Yi Zhang, Yang Wang, Gengyu Ge, Wei Wang

Machines · 23.01.2023 · 11 (2) · 157

DOI: 10.3390/machines11020157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 23.01.2023. Verfasst von Lihe Hu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Project of China Disabled Persons Federation on assistive technology, Science and Technology Planning Project of Chongqing Changshou District, National Nature Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The pose estimation can be effectively solved according to the feature point matching relationship in RGB-D. However, the extraction and matching process based on the whole image’s feature point is very computationally intensive and lacks robustness, which is the bottleneck of the traditional ICP algorithm. This paper proposes representing the whole image’s feature points by the salient objects’ robustness SIFT feature points through the salient preprocessing, and further solving the pose estimation. The steps are as follows: (1) salient preprocessing; (2) salient object’s SIFT feature extraction and matching; (3) RANSAC removes mismatching salient feature points; (4) ICP pose estimation. This paper proposes salient preprocessing aided by RANSAC processing based on the SIFT feature for pose estimation for the first time, which is a coarse-to-fine method. The experimental results show that our salient preprocessing algorithm can coarsely reduce the feature points’ extractable range and interfere. Furthermore, the results are processed by RANSAC good optimization, reducing the calculation amount in the feature points’ extraction process and improving the matching quality of the point pairs. Finally, the calculation amount of solving R, t based on all the matching feature points is reduced and provides a new idea for related research.

Förderung

  • Research Project of China Disabled Persons Federation on assistive technology
  • Science and Technology Planning Project of Chongqing Changshou District
  • National Nature Science Foundation of China
  • Scientific and Technological Research Program of Chongqing Municipal Education Commission

Zitieren

APA

Hu, L., Zhang, Y., Wang, Y., Ge, G., & Wang, W. (2023). Salient Preprocessing: Robotic ICP Pose Estimation Based on SIFT Features. Machines, 11(2), 157. https://doi.org/10.3390/machines11020157

Vancouver

Hu L, Zhang Y, Wang Y, Ge G, Wang W. Salient Preprocessing: Robotic ICP Pose Estimation Based on SIFT Features. Machines. 2023;11(2):157. doi:10.3390/machines11020157

BibTeX
@article{Hu2023,
  author = {Hu, Lihe and Zhang, Yi and Wang, Yang and Ge, Gengyu and Wang, Wei},
  title = {Salient Preprocessing: Robotic ICP Pose Estimation Based on SIFT Features},
  journal = {Machines},
  year = {2023},
  volume = {11},
  number = {2},
  pages = {157},
  doi = {10.3390/machines11020157}
}
Kostenlos starten →