Title :
A Fast Image Stitching Algorithm Based on Improved SURF
Author :
Zhu Lin ; Wang Ying ; Zhao Bo ; Zhang Xiaozheng
Author_Institution :
Dept. of Inf. & Control, China North Vehicle Res. Inst., Beijing, China
Abstract :
A fast image stitching algorithm based on improved speeded up robust feature (SURF) is proposed to overcome the real-time performance and robustness of the original SURF based stitching algorithms. The machine learning method is adopted to build a binary classifier, which identify the key feature points extracted by SURF and remove the non-key feature points. In addition, the RELIEF-F algorithm is used for dimension reduction and simplification of the improved SURF descriptor to achieve image registration. The threshold-based weighted fusion algorithm is used to achieve seamless image stitching. Finally, several experiments are conducted to verify the real-time performance and robustness of the improved algorithm.
Keywords :
feature extraction; image classification; image fusion; image registration; image sequences; learning (artificial intelligence); RELIEF-F algorithm; SURF based stitching algorithms; SURF descriptor; binary classifier; dimension reduction; fast image stitching algorithm; image fusion; key feature point extraction identification; machine learning method; nonkey feature point removal; spatial image sequence alignment; spatial image sequence registration; speeded up robust feature; threshold-based weighted fusion algorithm; Algorithm design and analysis; Classification algorithms; Feature extraction; Image fusion; Image registration; Machine learning algorithms; Robustness; RELIEF-F algorithm; SURF algorithm; fast image stitching; image fusion; machine learning;
Conference_Titel :
Computational Intelligence and Security (CIS), 2014 Tenth International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4799-7433-7
DOI :
10.1109/CIS.2014.67
