Random micro-displacement-based super-resolution image reconstruction method

Abstract

The invention relates to visual detection and image processing. Aiming to improve the resolution of an image and the measurement accuracy of a system, the technical scheme of the invention is that: a random micro-displacement-based super-resolution image reconstruction method comprises the following steps of: calculating micro-displacement by utilizing characteristic points in images of image sequences with the random micro-displacement; performing high-accuracy extraction on coordinates of the same characteristic points; setting two original images with the pixel size of 2d, the resolution of N and the sub-pixel micro-displacement of a as A and B; and setting a to-be-reconstructed image with the resolution of 2N as H, and as the image sequences are displaced and then scenes corresponding to H0 and H1 in the image are imaged only in A and not in B, in the process of reconstructing H, making equal H0, H1 and A0, performing the reconstruction according to corresponding relationships between H2, H3 and the like, and A and B and own weights of H2, H3 and the like for H2, H3 and the like, and obtaining a formula by deduction to calculate gray values. The method is mainly applied to the image processing.

Description

technical field [0001] The invention belongs to the field of visual detection, in particular to a super-resolution image reconstruction method for image measurement that does not require precise micro-displacement, and specifically to a super-resolution image reconstruction method based on random micro-displacement. Background technique [0002] In order to further improve the accuracy of the high-precision image measurement system, how to improve the source of information—the quality of the image becomes the key. The parameter most closely related to the measurement accuracy in the image is the spatial resolution (if not specified in this article, the resolution mentioned refers to the spatial resolution). The image means that its imaging image plane has been sampled at a smaller interval, and contains more spatial detail information. Therefore, when using the same sub-pixel algorithm, theoretically, high-resolution images can effectively improve measurement accuracy. The...

AI Technical Summary

Problems solved by technology

However, due to the limitation of the current CCD camera processing technology level, when obtaining a higher resolution than mainstream industrial CCD cameras, the cost will increase geometrically, and the degree of improvement is very limited

2. The super-resolution reconstruction algorithm based on a single image is used. The essence of this type of method is still to use interpolation and other methods to obtain a resolution beyond the hardware level. Due to the lack of new information, only the gray value of the interpolation point is calculated. It is estimated that it is more used to increase the visual effect, and it has little effect on improving the accuracy of the image measurement system.

Since the motion estimation between the image sequences is known, the reconstructed high-resolution images also achieve good results. However, it is difficult to implement an accurate two-dimensional micro-displacement acquisition system and the cost is relatively high. Therefore, the image sequence super-resolution reconstruction technology using accurate two-dimensional micro-displacement is still difficult to apply in practical engineering.

Images