Unlock instant, AI-driven research and patent intelligence for your innovation.

A low-light video enhancement method based on 3D convolutional neural network

A convolutional neural network and video enhancement technology, applied in the field of computer vision, can solve problems such as complex algorithms, achieve the effect of reducing time costs and improving effects

Active Publication Date: 2020-12-29
GUANGZHOU TUWEI NETWORK TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Firstly, the video is extracted into a continuous picture sequence, and then the algorithm is used to enhance each picture. The general algorithm of this method is relatively complicated, and the biggest defect is that it does not use inter-frame images (especially those collected by high-speed cameras) with many The same or similar information, just simply enhance each extracted picture independently

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A low-light video enhancement method based on 3D convolutional neural network
  • A low-light video enhancement method based on 3D convolutional neural network
  • A low-light video enhancement method based on 3D convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036]In order to make the above objectives, features and advantages of the present invention more obvious and easy to understand, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be pointed out that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, those of ordinary skill in the art can obtain all of them without creative work. Other embodiments fall within the protection scope of the present invention.

[0037]The present invention provides a low-illumination video enhancement method based on 3D convolutional neural network, including:

[0038]Step 1. Use multiple sets of continuous low-illuminance images and corresponding normal-illuminance images as samples to train the 3D convolutional neural network model. The 3D convolutional neural network model...

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

No PUM Login to View More

Abstract

The invention involves a low -illumination video enhancement method based on 3D convolutional neural networks, including: step 1, using multiple groups as multiple continuous low -illumination images as samples and corresponding normal illumination images to train 3D convolutional neural network models, The obtained 3D convolutional neural network model, the input is multiple low -illuminated images, the output is the enhanced normal illuminance image; step 2, obtain the low -illumination video to be enhanced, and decode the low -illumination video to be enhanced through the decoding2. Frames to get continuous picture sequences; step 3, select continuous multi -frame pictures in a sliding window to send them into the training 3D convolutional neural network model, and obtain continuous enhanced picture sequences in turn;Code the recovered picture sequence into a video.

Description

Technical field[0001]The invention relates to the technical field of computer vision, in particular to a low-illuminance video enhancement method based on a 3D convolutional neural network.Background technique[0002]In most computer vision technology scenarios, it is necessary to obtain clear image features to further analyze and process the video. However, under low illumination conditions (for example, at night), the quality of the captured video is relatively low due to weak light signals, and the target signal contained in the video is not clear, which further reduces the effect of subsequent video processing. Therefore, it is of great technical significance to study the restoration of low-illuminance video to normal-illumination video.[0003]The inventor found in research that the low-light video recovery in the traditional technology is essentially a low-light image recovery technology. First extract the video into a continuous picture sequence, and then use an algorithm to enha...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06T7/90G06N3/04G06N3/08
CPCG06T5/001G06T5/007G06T7/90G06N3/08G06T2207/10016G06N3/045
Inventor 孟焱鞠国栋沈良恒
Owner GUANGZHOU TUWEI NETWORK TECH