Video super-resolution method based on non-local regularization

Abstract

The invention provides a video super-resolution method based on non-local regularization. The method comprises the realization steps: (1) a video X is input; (2) bicubic interpolation amplification is carried out on a frame low-resolution image in the video X to obtain the amplified image, and high-pass filtering is carried out on a high-resolution image closest to the amplified image to obtain low and high frequency components; (3) image blocks are extracted from the amplified image and the low frequency component, the non-local regularization is carried out on the amplified image blocks, and k-means clustering is carried out on the low frequency image blocks; (4) the new amplified image blocks and a cluster center are compared, the most similar clusters are found out, and the similar low frequency image blocks are found out in the most similar clusters; (5) the corresponding high frequency image blocks are found out according to the similar low frequency image blocks, and non-local weighting is carried out on the high frequency image blocks to obtain a reconstructed high-resolution image; (6) the steps from (2) to (5) are repeated for each frame low-resolution image of the video to obtain a high-resolution video. The method is used for enhancing or restoring the video.

Description

technical field

[0001] The invention belongs to the technical field of video image processing, in particular to a video super-resolution method based on non-local regularization and key frames, which performs super-resolution on low-resolution videos and is applied to enhancement or restoration of video images. Background technique

[0002] Video super-resolution technology is a discipline that improves video clarity and suppresses noise through various technical means in order to obtain more accurate video information. It is an important and challenging research content in video image processing. For the video super-resolution problem, researchers have proposed many methods.

[0003] In 2008, Brandietal. et al. proposed an effective video super-resolution method. When transmitting compressed video, several frames of original uncompressed images are used as key frames, and these key frames are used as a database. Because of this Several key frames have a great similarity wi...

Examples

Embodiment 1

[0046] The present invention proposes a video super-resolution method based on non-local regularization and key frames, such as figure 1 Shown, the realization process of the present invention comprises the following steps:

[0047] Step 1, input video X, and extract each frame image.

[0048] Input video X, which includes high-resolution images and low-resolution images, and its image distribution relationship is: the first and last two frames are high-resolution images, and every eight frames of low-resolution images start from the first frame of high-resolution images It is a frame of high-resolution image until the end frame;

[0049] Extract each frame of image in video X to get high-resolution image frame X h ,h=1,...,M, and low resolution noisy image frame X t ,t=1,...,N, and define the high-resolution image frame X h As a key frame, define a low-resolution noisy image frame X t is a non-key frame, where M is the number of frames of high-resolution images in video ...

Embodiment 2

[0074] The video super-resolution method based on non-local regularization and key frame is the same as embodiment 1, and the effect of the present invention can be further illustrated by the following experimental simulation:

technical field

[0001] The invention belongs to the technical field of video image processing, in particular to a video super-resolution method based on non-local regularization and key frames, which performs super-resolution on low-resolution videos and is applied to enhancement or restoration of video images. Background technique

[0002] Video super-resolution technology is a discipline that improves video clarity and suppresses noise through various technical means in order to obtain more accurate video information. It is an important and challenging research content in video image processing. For the video super-resolution problem, researchers have proposed many methods.

[0003] In 2008, Brandietal. et al. proposed an effective video super-resolution method. When transmitting compressed video, several frames of original uncompressed images are used as key frames, and these key frames are used as a database. Because of this Several key frames have a great similarity wi...

Examples

Embodiment 1

[0046] The present invention proposes a video super-resolution method based on non-local regularization and key frames, such as figure 1 Shown, the realization process of the present invention comprises the following steps:

[0047] Step 1, input video X, and extract each frame image.

[0048] Input video X, which includes high-resolution images and low-resolution images, and its image distribution relationship is: the first and last two frames are high-resolution images, and every eight frames of low-resolution images start from the first frame of high-resolution images It is a frame of high-resolution image until the end frame;

[0049] Extract each frame of image in video X to get high-resolution image frame X h ,h=1,...,M, and low resolution noisy image frame X t ,t=1,...,N, and define the high-resolution image frame X h As a key frame, define a low-resolution noisy image frame X t is a non-key frame, where M is the number of frames of high-resolution images in video ...

Embodiment 2

[0074] The video super-resolution method based on non-local regularization and key frame is the same as embodiment 1, and the effect of the present invention can be further illustrated by the following experimental simulation:

Images