Terahertz and visible light image registration method and device based on texture feature points
A texture feature, image registration technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as slow speed, unsatisfactory heterologous image registration effect, and failure to meet real-time requirements, to reduce interference , to achieve real-time registration fusion, good anti-mismatch performance
Pending Publication Date: 2021-02-19
SHANGHAI HENGLIN OPTIC ELECTRIC CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the registration effect of heterogeneous images is still not ideal, especially for images with large differences between terahertz and visible light, and the speed is relatively slow, which cannot meet the real-time requirements
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. Note that the aspects described below in conjunction with the drawings and specific embodiments are only exemplary, and should not be construed as limiting the protection scope of the present invention.
[0041] like Figure 9 As shown, the embodiment of the present invention provides a terahertz and visible light image registration method based on texture feature points, including the following steps:
[0042] S1, extracting the foreground image of the visible light image and the terahertz image;
[0043] In a possible embodiment, S1 includes: based on even-tree complex wavelet transform, performing foreground extraction on visible light images through frequency domain processing, and processing them into binarized images; for details, please refer to "A Transformation" by Yue Aiju et al. Domain Texture Image Feature Extraction and Segmentat...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a terahertz and visible light image registration method and device based on texture feature points. The method comprises the following steps: S1, extracting foreground images of a visible light image and a terahertz image; S2, extracting texture information from the foreground image to obtain a texture feature map; S3, extracting texture feature points in the texture feature map and performing feature point description; S4, performing feature point matching, registration parameter calculation and image registration; S5, judging whether correction is needed or not, if so, performing correction by utilizing a supervised descent method and then entering the next step, and if not, directly entering the next step; and S6, fusing the terahertz image and the visible lightimage. According to the method, the texture feature points are extracted, so that the interference caused by the environment is reduced, the similarity of the terahertz image and the visible light image can be described in the form of the feature points, and the real-time registration fusion of the visible light image and the terahertz image is realized.
Description
technical field [0001] The invention relates to the field of security inspection and protection, in particular to a method and device for terahertz and visible light image registration based on texture feature points. Background technique [0002] The information obtained by a single sensor is often relatively simple, and in most cases it cannot meet the actual needs, so the multi-sensor fusion scheme has a better effect. [0003] The same is true for terahertz security detectors. The concealed objects carried by the inspected person can be detected from the terahertz image. However, due to the imaging characteristics of the terahertz image, the appearance characteristics of the inspected person are seriously lost. Although the visible light image is not easy to detect Hidden objects, but contain rich appearance features, if the hidden object information of the terahertz image is fused with the appearance information of the visible light image, it will make the applicability...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/50G06T7/194G06T7/33G06T7/136
CPCG06T5/50G06T7/194G06T7/33G06T7/136G06T2207/20221
Inventor 罗贵友俞旭辉侯丽伟谢巍刘仕望孙义兴侯树海
Owner SHANGHAI HENGLIN OPTIC ELECTRIC CO LTD