Image generation apparatus and image generation method

Abstract

Provided is an image forming device capable of forming a new motion image integrated from a plurality of motion images containing an image area, for which a corresponding point detection or a motion detection cannot be precisely performed. The image forming device comprises an image input unit (101) for accepting a first motion image and a second motion image, which has taken the same event as that of the first motion image, which has a higher resolution than that of the first motion image, and each frame of which is taken by a longer exposure than one frame time of the first motion image. Further comprised is an image integration unit (104) for forming a new motion image having a frame rate equal to or higher than that of the first motion image and a resolution equal to or higher than that of the second motion image, from the first motion image and the second motion image, by reducing the error between the frame of the second motion image and the average of the frames of the new motion image corresponding to the exposure period of the frame of the second motion image.

Description

technical field [0001] The present invention relates to an image generating device for generating a moving image, and more particularly to a moving image generating device for generating a new moving image by using a plurality of moving images, and the new moving image has the superior characteristics of the plurality of moving images respectively. Background technique [0002] With the development of digital imaging equipment, it is increasingly possible to capture still images with high spatial resolution at a lower cost. However, there are still challenges in realizing smooth moving images (for example, about 30 frames per second) or achieving higher-speed shooting while maintaining the high spatial resolution of such still images. [0003] The reason for this problem is that since the amount of image information obtained per unit time increases, the transmission rate of image information in imaging equipment is insufficient, or special imaging equipment for parallel tran...

AI Technical Summary

Problems solved by technology

[0013] However, the premise of the above-mentioned conventional technology is that the correspondence relationship between adjacent frames in the high-speed image can be accurately obtained, or the motion detection can be accurately performed, but there is a problem that when the accurate correspondence relationship cannot be obtained , or in cases where motion detection is not possible, result in reduced quality of the resulting image, or simply upscale the low-resolution image

Generally speaking, when the movement of a moving object in an image is complicated, or when the lighting state changes, occlusion or aperture problems occur, it is difficult to correctly obtain the corresponding points between frames, and it is also difficult to All pixels for correct motion detection

[0014] Specifically, in the presence of frames of high-resolution images, the high-resolution images themselves can be used to generate high-definition images, but if only frames of low-resolution images appear repeatedly afterwards, the resulting The quality of the resulting image, and, if a frame of the high-resolution image appears again later, suddenly a high-resolution image is generated again without loss of quality

This variation in image sharpness that occurs between frames can be perceived as incongruous

Images