Low-light image enhancement method combining multi-scale feature aggregation and lifting strategy
A multi-scale feature and optical image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems that the details in the image cannot be guaranteed, noise removal, limited application scenarios and effects, loss of detail information, etc., to achieve Good recognition of image content, good recognition, and the effect of removing differences
Pending Publication Date: 2022-06-03
HUNAN UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, almost no deep learning-based methods focus on the details in the image in the process of enhancing low-light images, which leads to the loss of detail information in the enhanced image results, causing problems such as over-smoothing of the image
In addition, most deep learning-based methods retain the noise in the original image or even amplify it
To sum up, the current low-light image enhancement method based on deep learning cannot guarantee the preservation of details in the image and the removal of noise in the image, which limits the application scenarios and effects of this technology
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0011] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the specific embodiments and the accompanying drawings. It should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. Furthermore, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present invention;
In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other. The present invention will be described in more detail below with reference to the accompanying drawings. In the various figures, like elements are designated by like reference numerals. For the sake of clarity, various parts in the figures...
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
Login to View More Abstract
The invention relates to a low-light image enhancement method combining multi-scale feature aggregation and a lifting strategy, belongs to the technical field of image enhancement, and improves a low-light image enhancement model of a coding-decoding architecture based on a convolutional neural network. A multi-scale feature aggregation module (FBAM) and a noise removal module (BPM) combining a lifting strategy and a pixel attention mechanism are provided. The method has the beneficial effects that based on an error feedback mechanism, a back projection technology is used, and all previous features can be considered when current features are aggregated; the latter can improve the signal-to-noise ratio of the image, model the relationship between pixel points in the image, and help the network to better identify the image content, thereby emphasizing the generality and removing the difference.
Description
technical field [0001] The invention relates to a low-light image enhancement method combining multi-scale feature aggregation and promotion strategies, and belongs to the technical field of image enhancement. Background technique [0002] Low-light image enhancement is a research hotspot in the field of computer vision in recent years. It has been widely used in various advanced vision tasks, such as object detection, semantic segmentation, etc. At the same time, it has also been applied to all-day autonomous driving, visual surveillance and computational photography. in the real world. Low-light image enhancement technology can improve the visibility, contrast of photos taken in low light, backlight and extreme low light, enhance their content details, and enhance people's aesthetic perception of them. It can be seen that low-light image enhancement has strong practical significance and use value. There are two traditional low-light image enhancement algorithms, one is a...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T5/50G06N3/04G06N3/08
CPCG06T5/50G06N3/08G06T2207/20081G06T2207/20084G06T2207/20132G06N3/048G06N3/045G06T5/70
Inventor 蒋斌王仁君杨超
Owner HUNAN UNIV