Infrared and Visible Image Registration Based on Automatic Robust Algorithm

Electronics

卷:11

Yongjiang Hu¹  Changlong Wang¹  Yuhua Zhang¹  Zhilong Lin¹  Jingyu Ji¹  Yongke Li¹  Jiangyi Yao² 

[1] Department of UAV, Army Engineering University, Shijiazhuang 050003, China;

[2] Equipment Simulation Training Center, Army Engineering University, Shijiazhuang 050003, China;

关键词: image extraction;    image matching;    deep convolutional network;    infrared and visible image;    image registration;   

DOI  :  10.3390/electronics11111674

来源: DOAJ

【 摘 要 】

Image registration is the base of subsequent image processing and has been widely utilized in computer vision. Aiming at the differences in the resolution, spectrum, and viewpoint of infrared and visible images, and in order to accurately register infrared and visible images, an automatic robust infrared and visible image registration algorithm, based on a deep convolutional network, was proposed. In order to precisely search and locate the feature points, a deep convolutional network is introduced, which solves the problem that a large number of feature points can still be extracted when the pixels of the infrared image are not clear. Then, in order to achieve accurate feature point matching, a rough-to-fine matching algorithm is designed. The rough matching is obtained by location orientation scale transform Euclidean distance, and then, the fine matching is performed based on the update global optimization, and finally, the image registration is realized. Experimental results show that the proposed algorithm has better robustness and accuracy than several advanced registration algorithms.

【 授权许可】

Unknown