Open Access

ARTICLE

Indoor Scene Splicing Based on Genetic Algorithm and ORB

Tao Zhang^1,*, Yi Cao²

1 School of Mechanical Engineering, North China University of Water Conservancy and Hydroelectric Power, Zhengzhou, 450045, China
2 Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, 9B 3P4, Canada

* Corresponding Author: Tao Zhang. Email:

Intelligent Automation & Soft Computing 2022, 33(3), 1677-1685. https://doi.org/10.32604/iasc.2022.027082

Received 10 January 2022; Accepted 10 February 2022; Issue published 24 March 2022

Abstract

The images generated by the image stitching algorithm have false shadow and poor real-time performance, and are difficult to maintain visual consistency. For this reason, a panoramic image stitching algorithm based on genetic algorithm is proposed. First, the oriented fast and rotated brief (ORB) algorithm is used to quickly perform detection and description of feature, then the initial feature point pairs are extracted according to the Euclidean distance for feature point rough matching, the parallelism of genetic algorithm is used to optimize the feature point matching performance. Finally, the PROSAC algorithm is used to remove mismatched point pairs and get the transformation matrix to complete the image stitching.

---

Keywords

---