Improved SIFT feature matching

Lifen Li ； Yu Li

《International Core Journal of Engineering》 5卷9期 (2019/08) Pp. 38-43

https://doi.org/10.6919/ICJE.201908_5(9).0006

摘要

in order to improve the matching rate and detection speed of UAV images, an improved SIFT algorithm, Markov distance and cosine similarity matching algorithm is proposed in this paper. The improved wavelet transform method is used to preprocess the image, the circular neighborhood dimension reduction is used to improve the speed of the algorithm, and the Markov distance and cosine similarity are combined to improve the matching accuracy of the algorithm. The images taken by UAV are collected in the experiment, and the experimental results show that the accuracy and speed of the improved algorithm in the image processing are obviously improved.

關鍵字

SIFT ； Wavelet transform ； cosine similarity

參考文獻

Lowe D G．Distinctive image features form scaleinvariant keypoints[J]．International Journal of Computer Vision，2004，60(2)：91-110.

Abdel-Hakim A E . Csift : A sift descriptor with color invariant characteristics[C]// 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 2006.

Li, B. , Kong, X. , Wang, Z. , & Fu, H. . (2009). SIFT-Based Image Retrieval Combining the Distance Measure of Global Image and Sub-Image. Fifth International Conference on Intelligent Information Hiding & Multimedia Signal Processing. IEEE Computer Society.

Sheng Mingwei, Zhou Hao, Huang Hai, & Qin Hongde. (2018) Research on underwater binocular vision ranging method. Journal of Huazhong University of Science and Technology (Natural Science Edition) (8), 93 / 98.

Cangyan, Yin Fengming, Bi Xiaojun. Improved binocular stereoscopic vision algorithm and its application[J]. Journal of Harbin University of Engineering, 2017(3).