Infrared Visible Image Registration Based on Gabor Representation Feature Descriptor

Jing Xu; Lidong Bao; Ming Fang; Tianjiao Du

doi:10.3788/LOP232611

Laser & Optoelectronics Progress, Volume. 61, Issue 14, 1437007(2024)

Infrared Visible Image Registration Based on Gabor Representation Feature Descriptor

Jing Xu^1、*, Lidong Bao¹, Ming Fang^2,3, and Tianjiao Du¹

¹School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, Jilin , China

²School of Artificial Intelligence, Changchun University of Science and Technology, Changchun 130022, Jilin , China

³Zhongshan Institute of Changchun University of Science and Technology, Zhongshan 528403, Guangdong , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Infrared visible image registration flow chart

Download full size

Fig. 2. Key point detection result. (a) Original image, infrared image (left), visible light image (right); (b) moment analysis equation weight results; (c) Harris algorithm detection results on original image; (d) Harris algorithm detection results on moment analysis equation weights

Download full size

Fig. 3. Registration results of CVC-15 stereo dataset

Download full size

Fig. 4. Registration results of RGB-LWIR infrared wavelength dataset

Download full size

Fig. 5. Registration results of homemade datasets

Download full size

Fig. 6. Evaluation results of registration performance of eight algorithms. (a) NCM evaluation results on CVC-15 stereo dataset; (b) NCM evaluation results on RGB-LWIR infrared wavelength dataset; (c) NCM evaluation results on homemade dataset; (d) RMSE evaluation results on CVC-15 stereo dataset; (e) RMSE evaluation results on RGB-LWIR infrared wavelength dataset; (f) RMSE evaluation results on homemade dataset

Download full size

Table 1. Successful matching rates of eight methods on three datasets
View table
Table 1. Successful matching rates of eight methods on three datasets
Dataset SIFT MS-PIIFD LPSO RIFT CMM-Net SuperGlue SGMNet RI-GRFD
CVC-15 16 59 19 36 80 86 75 46
RGB-LWIR 29 63 46 67 59 69 65 72
Homemade 55 13 37 48 60 54 62

Table 2. Running time of different algorithms
View table
Table 2. Running time of different algorithms
Dataset SIFT MS-PIIFD LPSO RIFT CMM-Net SuperGlue SGMNet RI-GRFD
CVC-15 8.93 10.30 9.30 4.65 4.93 10.50 8.80 6.88
RGB-LWIR 9.54 11.83 10.18 12.21 9.30 15.41 13.54 7.80
Homemade 15.69 12.99 12.08 10.20 17.22 12.91 9.63

Tools

Get Citation

Copy Citation Text

Jing Xu, Lidong Bao, Ming Fang, Tianjiao Du. Infrared Visible Image Registration Based on Gabor Representation Feature Descriptor[J]. Laser & Optoelectronics Progress, 2024, 61(14): 1437007

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites