Image generating method, apparatus and image composition equipment

Abstract

The invention discloses a picture generating method, which comprises the following steps: generating at least two pictures with different exposure time; acquiring the pixel luminance values in the pictures with the different exposure time respectively; acquiring the pixel luminance reliability in the pictures with the different exposure time respectively; multiplying the corresponding pixel luminance values in the pictures with the different exposure times by the corresponding reliability respectively and adding up each multiplication result, and then acquiring the pixel luminance values in composite pictures to generate the composite pictures. By applying the technical proposal provided by the invention, the pictures with rich details can be generated in a real-time manner.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image generation method and device and image synthesis equipment. Background technique [0002] In a real scene, the dynamic range that the human eye can perceive is very large, and it can perceive that the brightness is 10 -3 cd / m 2 starlight, can also detect the brightness of 10 5 cd / m 2 sunlight, and the human eye can detect various details in the real scene even in very dark and very bright conditions. However, the brightness dynamic range of the current image acquisition equipment is low, and the corresponding bright details cannot be seen in particularly bright scenes, and the corresponding dark details cannot be seen in particularly dark scenes. The perceived brightness dynamic range varies greatly. [0003] The prior art provides a method for increasing details captured by an image acquisition device, and the method specifically includes: [0004...

AI Technical Summary

Problems solved by technology

[0013] In the prior art, in order to obtain an image with rich details, it is necessary to calculate the brightness of the corresponding pixels of the long-exposure image and the short-exposure image. For this image, the obtained large-scale synthetic image is tone-mapped, and the calculation amount of the brightness calculation and tone mapping of the pixels in the synthetic image is relatively large, the complexity is high, and it is difficult to generate a video image in real time

Images