Evaluation of Global Descriptor Methods for Appearance-Based Visual Place Recognition
Journal of Robotics · 22.04.2023 · 2023 · 1-17
DOI: 10.1155/2023/9150357 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Robotics, erschienen am 22.04.2023. Verfasst von Kangyu Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Basic Research Program of China.
Abstract (Originalsprache)
Visual place recognition (VPR) is considered among the most challenging problems due to the extreme variations in appearance and viewpoint. Essentially, appearance-based VPR can be considered as an image retrieval task, thus the key is to accurately and efficiently describe the images. Recently, global descriptor methods have attracted substantial attention from the VPR community, which has contributed to numerous important outcomes. Despite the growing number of global descriptors presented, little attention has been paid to the comparison and evaluation of these methods and so it remains difficult for researchers to disentangle the factors that led to better performance. This study provided comprehensive insight into global descriptors from a practical application perspective. We present a systematic evaluation that integrates 15 commonly used global descriptors, 6 benchmark datasets, and 5 evaluation metrics, and subsequently extended this evaluation to discuss the key factors impacting the matching performance and computational efficiency. We also report practical suggestions for constructing promising CNN descriptors, based on the experimental conclusions. Our analysis reveals both advantages and limitations of three different types of global descriptors, including handcrafted features-based ones, off-the-shelf CNN-based ones, and customized CNN-based ones. Finally, we evaluate the practicality of reported global descriptors to mediate the trade-offs between matching performance and computational efficiency.
Förderung
- National Basic Research Program of China
Zitieren
APA
Li, K., Ma, Y., Wang, X., Ji, L., & Geng, N. (2023). Evaluation of Global Descriptor Methods for Appearance-Based Visual Place Recognition. Journal of Robotics, 2023, 1-17. https://doi.org/10.1155/2023/9150357
Vancouver
Li K, Ma Y, Wang X, Ji L, Geng N. Evaluation of Global Descriptor Methods for Appearance-Based Visual Place Recognition. Journal of Robotics. 2023;2023:1-17. doi:10.1155/2023/9150357
BibTeX
@article{Li2023,
author = {Li, Kangyu and Ma, Yuhan and Wang, Xifeng and Ji, Lijuan and Geng, Niuniu},
title = {Evaluation of Global Descriptor Methods for Appearance-Based Visual Place Recognition},
journal = {Journal of Robotics},
year = {2023},
volume = {2023},
pages = {1--17},
doi = {10.1155/2023/9150357}
}
EUVIMED