Implementation of A Fast ORB Keypoints Extraction Algorithm Based on Grid Division

Yuan Cao; Jun Lu; Xu Zhang

doi:10.62051/ijcsit.v2n2.15

Authors

Yuan Cao
Jun Lu
Xu Zhang

DOI:

https://doi.org/10.62051/ijcsit.v2n2.15

Keywords:

Keypoints extraction; Visual SLAM; ORB features

Abstract

Synchronous Localization and Mapping (SLAM) is a research hotspot in the field of mobile robots. However, visual SLAM faces a high computational burden in feature point extraction and other processes, thus requiring powerful computing and memory resources as support. This article proposes a fast ORB feature point extraction method based on grid partitioning to meet the requirements of fast and efficient feature point extraction in visual SLAM. This method can significantly reduce the time required for feature point extraction and also meet the requirement of uniform distribution of feature points in images in visual SLAM. Finally, in the experiment, the algorithm proposed in this paper was compared with the traditional ORB feature point extraction algorithm, verifying that this method has significant advantages in extraction speed.

Downloads

Download data is not yet available.

References

Takashi Tsubouchi. Introduction to Simultaneous Localization and Mapping. Journal of Robotics and Mechatronics, 2019, 31(3):367-374.

Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110.

Bay H, Tuytelaars T, Van Gool L. “Surf: Speeded up robust features”, Computer Vision–ECCV 2006, pp. 404–417, Springer.

Rublee E, Rabaud V, Konolige K, Bradski G. “Orb: an efficient alternative to sift or surf”. 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2564–2571,

Suo Chunbao, Yang Dongqing, Liu Yunpeng. “Compare SIFT, SURF, BRISK, ORB, and FREAK algorithms from multiple perspectives”. Beijing Surveying and Mapping 2014 (04): 22-26

MUR-ARTAL R, TARDÓS J D. “ORB-SLAM2: an opensource SLAM system for monocular, stereo, and RGB-D cameras. IEEE transactions on robotics, 2017, 33(5): 1255–1262

Li Guojun, Xu Yanhai, Duan Jiewen, Han Shilei. Extracting ORB-SLAM keypoints using local adaptive threshold method. Bulletin of Surveying and Mapping, 2021(09):32-36

Calonder M, Lepetit V, Strecha C, Fua P. Brief: Binary robust independent elementary features. European conference on computer vision, pp. 778–792, Springer, 2010

Mur-Artal R, Montiel J, Tardós J D. Orb-slam: a versatile and accurate monocular slam system. IEEE T ROBOT, 2015. 31(5):1147-1163.