CN111340732B - Low-illumination video image enhancement method and device - Google Patents
Low-illumination video image enhancement method and device Download PDFInfo
- Publication number
- CN111340732B CN111340732B CN202010129793.2A CN202010129793A CN111340732B CN 111340732 B CN111340732 B CN 111340732B CN 202010129793 A CN202010129793 A CN 202010129793A CN 111340732 B CN111340732 B CN 111340732B
- Authority
- CN
- China
- Prior art keywords
- illumination
- image
- frame image
- processing
- video image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005286 illumination Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000012545 processing Methods 0.000 claims abstract description 76
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 13
- 238000009432 framing Methods 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005316 response function Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000002708 enhancing effect Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/92—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The invention discloses a low-illumination video image enhancement method and device, relates to the technical field of image processing, can obtain better enhanced video images, and has the advantages of simple implementation steps and high efficiency. The main technical scheme of the invention is as follows: after a section of low-illumination video image data is acquired, performing framing processing on the video image data to obtain a plurality of continuous single-frame images corresponding to the video image data; processing the single-frame image by using a total variation method to generate an illumination map corresponding to the single-frame image; adjusting the brightness balance of the illumination image to obtain a corresponding exposure rate; and according to the exposure rate, obtaining a corresponding enhanced image by adjusting the single-frame image, and synthesizing an enhanced video by using a plurality of enhanced images. The method is mainly applied to the enhancement operation of the low-illumination video image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a low-illumination video image enhancement method and device.
Background
When the illumination is insufficient, the image obtained by the camera is low in visibility and high in noise, and the image details are covered. These problems have severely affected the performance of many computer vision algorithms that require high quality input images, such as image processing requirements for image segmentation, object detection, object recognition, and so forth. These problems are much more significant for public safety oriented video surveillance systems. In order to obtain a high-quality image with brightness, high visibility, reduced noise and rich details, it is necessary to research a low-illumination video image enhancement technique.
At present, the method for enhancing the low-illumination image mainly comprises the following steps: a deep learning based method, a histogram equalization method, a Retinex based method, a reverse defogging algorithm, and the like. However, there are still many problems in applying these existing methods to the process of enhancing low-illumination images, such as: the method based on deep learning needs to rely on a complex network structure and a large number of samples, so a large number of hardware resources are occupied in the training process, for example, hardware devices such as a Graphics Processing Unit (GPU), a Random Access Memory (RAM) and the like are occupied; by using the histogram equalization method, although the low-illumination video image can be entirely brightened, noise is amplified at the same time; for the implementation means for realizing the low-illumination video image based on the Retinex method, the performance of the implementation means is influenced by the illumination size and whether the reflection component estimation is accurate or not; the low-illumination video image enhancement is performed by using a reverse defogging algorithm, and physical theory support is lacked.
When the existing methods are applied to video image enhancement processing, the calculation speed is slow, or only global brightness improvement is considered, so that details of an original highlight area are submerged, and the low-illumination video image enhancement processing effect is poor and the efficiency is low.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for enhancing a low-illumination video image, and mainly aims to estimate an illumination component of a single-frame video image and perform a brightness balance adjustment and correction on an original single-frame image according to the illumination component, so as to suppress an enhancement effect of a highlight area while enhancing a brightness of a dark area, retain details of a highlight area of the original single-frame video image, and finally obtain a better enhanced video image.
In order to solve the above problems, the present invention mainly provides the following technical solutions:
in one aspect, the present invention provides a method for enhancing a low-illumination video image, including:
after a section of low-illumination video image data is acquired, performing framing processing on the video image data to obtain a plurality of continuous single-frame images corresponding to the video image data;
processing the single-frame image by using a total variation method to generate an illumination map corresponding to the single-frame image;
adjusting the brightness balance of the illumination graph to obtain a corresponding exposure rate;
and according to the exposure rate, obtaining a corresponding enhanced image by adjusting the single-frame image, and synthesizing an enhanced video by using a plurality of enhanced images.
Optionally, after obtaining a plurality of continuous single-frame images corresponding to the video image data, the method further includes:
converting the single frame image from an RGB color space to an HSV color space;
obtaining a brightness component of the HSV color space;
and processing the brightness component of the single-frame image by using a camera response function to obtain a real scene image corresponding to the single-frame image.
Optionally, the processing the single-frame image by using a total variation method to generate an illuminance map corresponding to the single-frame image includes:
processing a real scene image corresponding to the single frame image by using a total variation method, and estimating an illumination component existing in the real scene image;
and generating a corresponding illumination map according to the illumination component.
Optionally, the performing brightness balance adjustment on the illuminance map to obtain a corresponding exposure rate includes:
and correcting the illumination components of different areas in the illumination map by using self-adaptive gamma correction, and calculating the exposure rate obtained after correction.
Optionally, the obtaining a corresponding enhanced image by adjusting the single frame image according to the exposure rate includes:
inputting the single-frame image and the exposure rate into a preset brightness response function model, and outputting a target image;
denoising the target image;
and converting the target image subjected to denoising processing into an RGB color space to obtain an enhanced image.
In another aspect, the present invention further provides a low-illumination video image enhancement apparatus, including:
the first processing unit is used for performing framing processing on a section of low-illumination video image data after the video image data is acquired to obtain a plurality of continuous single-frame images corresponding to the video image data;
the generating unit is used for processing the single-frame image obtained by the first processing unit by using a total variation method to generate an illumination map corresponding to the single-frame image;
the adjusting unit is used for carrying out brightness balance adjustment on the illumination map generated by the generating unit to obtain the corresponding exposure rate;
the determining unit is used for obtaining a corresponding enhanced image by adjusting the single-frame image according to the exposure rate;
a synthesizing unit for synthesizing the enhanced video using the enhanced images determined by the plurality of determining units.
Optionally, the apparatus further comprises:
a conversion unit, configured to convert the single-frame image from an RGB color space to an HSV color space after the obtaining of the plurality of continuous single-frame images corresponding to the video image data;
an obtaining unit, configured to obtain the brightness component of the HSV color space obtained by the converting unit;
and the second processing unit is used for processing the brightness component of the single-frame image acquired by the acquisition unit by using a camera response function to obtain a real scene image corresponding to the single-frame image.
Optionally, the generating unit includes:
the estimation module is used for processing a real scene image corresponding to the single-frame image by using a total variation method and estimating an illumination component existing in the real scene image;
and the generating module is used for generating a corresponding illumination map according to the illumination component obtained by the estimating module.
Optionally, the adjusting unit includes:
and the calculation module is used for correcting the illumination components of different areas in the illumination map by using self-adaptive gamma correction and calculating the exposure rate obtained after correction.
Optionally, the determining unit includes:
the input module is used for inputting the single-frame image and the exposure rate into a preset brightness response function model;
an output module for outputting a target image;
the processing module is used for carrying out denoising processing on the target image output by the output module;
and the conversion module is used for converting the target image subjected to denoising processing into an RGB color space to obtain an enhanced image.
In yet another aspect, the present invention also provides an electronic device, including: a memory, a processor, and a program stored on the memory and executable on the processor, which when executed by the processor, implement the low-light video image enhancement method as described above.
In yet another aspect, the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed, implements the low-illumination video image enhancement method as described above.
By means of the technical scheme, the technical scheme provided by the invention at least has the following advantages:
the invention provides a low-illumination video image enhancement method and a device, the method comprises the steps of carrying out framing processing on a low-illumination video image in advance, estimating illumination components of a single-frame image to obtain an illumination image, correcting the illumination image to carry out brightness balance adjustment and obtain corresponding exposure rate, adjusting an original single-frame image according to the exposure rate to obtain a corresponding enhanced image, and synthesizing an enhanced video by utilizing a plurality of enhanced images. Compared with the prior art, the method and the device solve the problems of poor enhancement processing effect and low efficiency of the low-illumination video image, combine a total variation method and adaptive brightness balance adjustment, have simple implementation steps, inhibit the enhancement effect of a highlight area while improving the brightness of a dark area, retain the details of the high-brightness area of the original single-frame video image, finally obtain a better enhanced video image and improve the processing efficiency.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart of a method for enhancing a low-illumination video image according to an embodiment of the present invention;
fig. 2 is a flowchart of another low-illumination video image enhancement method according to an embodiment of the present invention;
fig. 3 is a block diagram of a low-illumination video image enhancement apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram of another low-illumination video image enhancement apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a low-illumination video image enhancement method, as shown in fig. 1, the method estimates illumination components of a single-frame video image, adjusts and corrects brightness balance according to the illumination components to obtain an enhanced image corresponding to the single-frame image, and then gathers a plurality of enhanced images to obtain a finally enhanced video, and the embodiment of the invention provides the following specific steps:
101. after a section of low-illumination video image data is acquired, frame division processing is carried out on the video image data to obtain a plurality of continuous single-frame images corresponding to the video image data.
In the embodiment of the invention, the low-illumination video image is subjected to framing processing in advance to obtain a plurality of continuous single-frame images corresponding to the low-illumination video image, and then the single-frame images are subjected to enhancement processing.
It should be noted that, by using the method for enhancing a single-frame image, the low-illumination video image can be optionally enhanced in the following two ways, which specifically include: the detail of the key frame image enhancement image in the video can be selected to be clear, and a high-quality key frame image with high contrast and certain brightness balance capability can be obtained; meanwhile, each single-frame image in the video can be enhanced optionally, so that the processing efficiency is improved, the algorithm can be simplified in the enhancing process, and the whole enhanced video with good visual effect and balanced brightness is obtained.
102. And processing the single-frame image by using a total variation method to generate an illumination map corresponding to the single-frame image.
In the embodiment of the present invention, the specific implementation step of performing enhancement processing on the single frame image includes first estimating the illuminance component of each unit area in the single frame image, and specifically, a total variation method may be adopted to collectively generate an illuminance map for the illuminance component of each unit area in the single frame image.
103. And carrying out brightness balance adjustment on the illumination image to obtain the corresponding exposure rate.
In the embodiment of the invention, the luminance balance adjustment is performed on the illumination map, and the functions are as follows: according to the illumination component estimation of the original single-frame image, which areas originally have lower brightness and which areas originally have higher brightness in the original single-frame image can be determined, the areas with lower brightness are promoted through brightness balance adjustment, excessive enhancement of the areas with higher brightness is restrained, and the situation that details are submerged due to the fact that the areas with higher brightness are not considered to be promoted because the original single-frame image is wholly promoted is avoided. For the embodiment of the invention, the brightness balance adjustment is equivalent to the brightness adjustment operation of adaptively distinguishing the high-brightness area and the low-dark area, and the exposure rate is obtained after the brightness balance adjustment operation and is used for representing the exposure degrees corresponding to different areas after the brightness balance adjustment.
104. And according to the exposure rate, obtaining a corresponding enhanced image by adjusting the single-frame image, and synthesizing an enhanced video by using a plurality of enhanced images.
In the embodiment of the invention, according to the exposure degrees corresponding to different areas after brightness balance adjustment, brightness enhancement operation is performed on the high brightness area or the low dark area of the original single-frame image in a targeted manner, such as: and performing operation on the increment of the low and dark areas to obtain enhanced images for the weak increment or the inhibition increment of the high-brightness area, and further performing corresponding sequencing on the enhanced images corresponding to each single-frame image according to the sequencing of each single-frame image in the original low-illumination video image to obtain an enhanced video, namely a processing result after the enhancement of the original low-illumination video image.
The embodiment of the invention provides a low-illumination video image enhancement method, which comprises the steps of carrying out framing processing on a low-illumination video image in advance, estimating illumination components of a single frame image to obtain an illumination image, correcting the illumination image to carry out brightness balance adjustment and obtain corresponding exposure rate, adjusting an original single frame image according to the exposure rate to obtain a corresponding enhanced image, and synthesizing an enhanced video by using a plurality of enhanced images. Compared with the prior art, the method and the device solve the problems of poor enhancement processing effect and low efficiency of the low-illumination video image, the embodiment of the invention combines a total variation method and self-adaptive brightness balance adjustment, has simple implementation steps, improves the brightness of a dark area, inhibits the enhancement effect of a highlight area, retains the details of the highlight area of the original single-frame video image, finally obtains a better enhanced video image and also improves the processing efficiency.
In order to explain the above embodiments in more detail, another low-luminance video image enhancement method is further provided in the embodiments of the present invention, as shown in fig. 2, the method processes the V component of the single-frame video image by using a total variation method to estimate the luminance component and performs adaptive gamma correction to perform brightness balance adjustment correction on the original single-frame image, and for this, the following specific steps are provided in the embodiments of the present invention:
201. after a section of low-illumination video image data is acquired, a plurality of continuous single-frame images corresponding to the video image data are obtained by performing framing processing on the video image data.
In the embodiment of the invention, the low-illumination video image is subjected to framing processing in advance to obtain a plurality of continuous single-frame images corresponding to the low-illumination video image, and then the single-frame images are subjected to enhancement processing.
202. The single frame image is converted from the RGB color space to the HSV space.
The RGB color space is based on three basic colors, red (R), green (G) and Blue (B), and is superimposed to different degrees to generate rich and wide colors, so it is commonly called as a three-primary-color mode.
The HSV color space is a color space created according to the intuitive characteristics of colors, and is also called a hexagonal pyramid Model (Hexcone Model), and the parameters of the colors in the Model are respectively: hue (Hue, H), saturation (S), lightness (Value, V).
In the embodiment of the present invention, when the illumination is insufficient, the image acquired by the camera is often low in visibility, noisy, and the details of the image are covered, so that the low-illumination video image referred to in the embodiment of the present invention is obtained, so that the enhancement processing for the low-illumination video image is not related to the color of the image, but is performed from the brightness detection and enhancement of the unit area in the image, so that in the embodiment of the present invention, the pre-processing may be performed on the single-frame image as follows: and converting the single-frame image from the RGB color space to the HSV space, thereby filtering out redundant and interference information which is irrelevant to the enhancement operation, and only acquiring the V component of the converted single-frame image HSV space to analyze which regions should be enhanced or inhibited from being enhanced in brightness.
203. And acquiring a V component of the HSV space.
In the embodiment of the present invention, the brightness component of the color space of the single frame image HSV is obtained, and it is analyzed according to the brightness component which region should be enhanced or inhibited from being enhanced.
204. And processing the V component of the single-frame image by using a camera response function to obtain a real scene image corresponding to the single-frame image.
In the embodiment of the invention, the effect of the camera response function on the processing of the single frame image is considered, the real scene image corresponding to the single frame image is restored, so that the real scene image is subsequently used for estimating the illumination component to generate the illumination map, and the method is convenient for more accurately analyzing which areas in the image should be enhanced or inhibited from being enhanced according to the illumination map.
205. And processing the single-frame image by using a total variation method to generate an illumination map corresponding to the single-frame image.
In the embodiment of the present invention, the specific implementation steps of estimating the illuminance map corresponding to the single frame image may be: firstly, processing a real scene image corresponding to a single frame image by using a total variation method, and estimating an illumination component existing in the real scene image; next, a corresponding illuminance map is generated from the illuminance components.
Further, in order to obtain a more accurate illumination map, a rigorous illumination estimation total variation equation is used, which is as follows:
wherein the content of the first and second substances,for the initial rough estimate of the luminance component, T is the ideal luminance component, D isAnd T. 1 is a matrix with elements all 1. ^ T and ^ D are gradients of T and D, respectively. c, lambda and tau 1 Is the weight of each item.
Furthermore, under the condition of not causing larger distortion, the calculated amount is reduced, the illumination component is estimated by applying the total variation algorithm with a simplified version, and in order to be beneficial to finally improving the processing efficiency of the implementation process of enhancing the low-illumination video image, for the embodiment of the invention, a simplified illumination estimation total variation equation is adopted, such as: the following formula:
wherein T is the obtained illumination component,an initially estimated luminance component, # T is a gradient of T, # 1 Are weights.
206. And carrying out brightness balance adjustment on the illumination map to obtain the corresponding exposure rate.
In the embodiment of the invention, the self-adaptive gamma correction is utilized to correct the illumination components of different areas in the illumination map, and the exposure rate obtained after correction is calculated. When contrast component brightness is adjusted, it is found that details of a high-brightness area can be excessively enhanced or the overall brightness of the enhanced image is insufficient, so that the adaptive gamma correction can obtain an illuminance map with balanced brightness, and specifically, the adaptive gamma correction algorithm has the following formula:
γ=α·β θT formula (3)
Wherein alpha, beta and theta are related parameters, and specific numerical values are obtained by experiments; t is the illumination component.
207. And according to the exposure rate, obtaining a corresponding enhanced image by adjusting the single-frame image, and synthesizing an enhanced video by using a plurality of enhanced images.
For the embodiment of the present invention, specifically, a preset luminance response function model may be used to input a single frame image to be processed and an obtained exposure rate, so as to output an enhanced target image.
Then, the enhanced target image is subjected to gaussian filtering processing, the enhanced target image subjected to denoising processing is converted into an RGB color space, and a final processing result of the original single-frame image is obtained, that is: the image is enhanced. Further, according to the sequence of each single frame image in the original low-illumination video image, the enhanced images corresponding to each single frame image are correspondingly sequenced to obtain an enhanced video, namely, the enhanced video image is subjected to post-processing results.
Further, as an implementation of the method shown in fig. 1 and fig. 2, an embodiment of the present invention provides a low-illumination video image enhancement apparatus. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. The device is applied to perform enhancement operation on a low-illumination video image, and particularly as shown in fig. 3, the device comprises:
the first processing unit 31 is configured to, after a piece of low-illumination video image data is acquired, perform framing processing on the video image data to obtain a plurality of continuous single-frame images corresponding to the video image data;
a generating unit 32, configured to process the single-frame image obtained by the first processing unit 31 by using a total variation method, and generate an illuminance map corresponding to the single-frame image;
an adjusting unit 33, configured to perform brightness balance adjustment on the illuminance map generated by the generating unit 32 to obtain a corresponding exposure rate;
a determining unit 34, configured to obtain a corresponding enhanced image by adjusting the single frame image according to the exposure rate;
a synthesizing unit 35 for synthesizing an enhanced video using the enhanced images determined by the plurality of determining units 34.
Further, as shown in fig. 4, the apparatus further includes:
a conversion unit 36, configured to convert the single-frame image from an RGB color space to an HSV color space after the obtaining of the multiple continuous single-frame images corresponding to the video image data;
an obtaining unit 37, configured to obtain the brightness component of the HSV color space obtained by the converting unit 36;
a second processing unit 38, configured to process the brightness component of the single-frame image acquired by the acquiring unit 37 by using a camera response function, so as to obtain a real scene image corresponding to the single-frame image.
Further, as shown in fig. 4, the generating unit 32 includes:
an estimating module 321, configured to process a real scene image corresponding to the single frame image by using a total variation method, and estimate an illumination component existing in the real scene image;
the generating module 322 is configured to generate a corresponding illuminance map according to the illuminance component obtained by the estimating module 321.
Further, as shown in fig. 4, the adjusting unit 33 includes:
the calculating module 331 is configured to perform correction processing on the illumination components in different areas in the illumination map by using adaptive gamma correction, and calculate an exposure rate obtained after the correction processing.
Further, as shown in fig. 4, the determining unit 34 includes:
an input module 341, configured to input the single frame image and the exposure rate into a preset luminance response function model;
an output module 342 for outputting a target image;
a processing module 343, configured to perform denoising processing on the target image output by the output module 342;
and a conversion module 344, configured to convert the target image subjected to the denoising processing into an RGB color space, so as to obtain an enhanced image.
In summary, in the method and apparatus for enhancing a low-illumination video image according to the embodiments of the present invention, a low-illumination video image is subjected to framing in advance, an illumination component is estimated for a single frame image to obtain an illumination map, the illumination map is corrected to perform brightness balance adjustment and obtain a corresponding exposure rate, an original single frame image is adjusted according to the exposure rate to obtain a corresponding enhanced image, and a plurality of enhanced images are used to synthesize an enhanced video. Compared with the prior art, the method and the device solve the problems of poor enhancement processing effect and low efficiency of the low-illumination video image, the embodiment of the invention combines a total variation method and self-adaptive brightness balance adjustment, has simple implementation steps, improves the brightness of a dark area, inhibits the enhancement effect of a highlight area, retains the details of the highlight area of the original single-frame video image, finally obtains a better enhanced video image and also improves the processing efficiency.
An embodiment of the present invention further provides an electronic device, including: a memory, a processor, and a program stored on the memory and executable on the processor, which when executed by the processor, implement the low-light video image enhancement method as described above.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the program is executed to implement the low-illumination video image enhancement method as described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (trahsity media) such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (5)
1. A method for low-light video image enhancement, the method comprising:
after a section of low-illumination video image data is acquired, framing processing is carried out on the video image data to obtain a plurality of continuous single-frame images corresponding to the video image data;
converting the single frame image from an RGB color space to an HSV color space; acquiring brightness components of the HSV color space; processing the brightness component of the single frame image by using a camera response function to obtain a real scene image corresponding to the single frame image;
processing the single-frame image by using a total variation method to generate an illumination map corresponding to the single-frame image, wherein the method comprises the following steps: processing a real scene image corresponding to the single frame image by using a total variation method, and estimating an illumination component existing in the real scene image; generating a corresponding illumination map according to the illumination components;
wherein, the illumination estimation total variation equation is used, and the following formula is adopted:
wherein the content of the first and second substances,for the initial rough estimate of the luminance component, T is the ideal luminance component, D isError from T; 1 is a matrix with elements all being 1;andgradients of T and D, respectively; c, lambda and tau 1 are weights of each item;
and adjusting the brightness balance of the illumination graph to obtain a corresponding exposure rate, wherein the adjusting comprises the following steps: correcting the illumination components of different areas in the illumination map by using self-adaptive gamma correction, and calculating the exposure rate obtained after correction;
and according to the exposure rate, obtaining a corresponding enhanced image by adjusting the single-frame image, and synthesizing an enhanced video by using a plurality of enhanced images.
2. The method according to claim 1, wherein the obtaining the corresponding enhanced image by adjusting the single frame image according to the exposure rate comprises:
inputting the single-frame image and the exposure rate into a preset brightness response function model, and outputting a target image;
denoising the target image;
and converting the target image subjected to denoising processing into an RGB color space to obtain an enhanced image.
3. A low-light video image enhancement apparatus, comprising:
the first processing unit is used for performing framing processing on a section of low-illumination video image data after the video image data is acquired to obtain a plurality of continuous single-frame images corresponding to the video image data;
a conversion unit, configured to convert the single-frame image from an RGB color space to an HSV color space after the obtaining of the plurality of continuous single-frame images corresponding to the video image data;
an obtaining unit, configured to obtain the brightness component of the HSV color space obtained by the converting unit;
the second processing unit is used for processing the brightness component of the single-frame image acquired by the acquisition unit by using a camera response function to obtain a real scene image corresponding to the single-frame image;
the generating unit is used for processing the single-frame image obtained by the first processing unit by using a total variation method to generate an illumination map corresponding to the single-frame image;
the estimation module is used for processing a real scene image corresponding to the single-frame image by using a total variation method and estimating an illumination component existing in the real scene image;
the generating module is used for generating a corresponding illumination map according to the illumination component obtained by the estimating module;
wherein, the illumination estimation total variation equation is used, and the following formula is adopted:
wherein the content of the first and second substances,for the initial rough estimate of the luminance component, T is the ideal luminance component, D isError from T; 1 is a matrix with elements all being 1;andgradients of T and D, respectively; c, lambda and tau 1 are weights of each item;
the adjusting unit is used for carrying out brightness balance adjustment on the illumination map generated by the generating unit to obtain the corresponding exposure rate;
the adjusting unit includes: the calculation module is used for correcting the illumination components of different areas in the illumination image by using self-adaptive gamma correction and calculating the exposure rate obtained after correction;
the determining unit is used for obtaining a corresponding enhanced image by adjusting the single-frame image according to the exposure rate;
a synthesizing unit for synthesizing the enhanced video using the enhanced images determined by the plurality of determining units.
4. An electronic device, comprising: a memory, a processor and a program stored on the memory and executable on the processor, the processor when executing the program implementing the low-illumination video image enhancement method as claimed in claim 1 or 2.
5. A computer-readable storage medium, on which a computer program is stored, which when executed implements the low-illumination video image enhancement method of claim 1 or 2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010129793.2A CN111340732B (en) | 2020-02-28 | 2020-02-28 | Low-illumination video image enhancement method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010129793.2A CN111340732B (en) | 2020-02-28 | 2020-02-28 | Low-illumination video image enhancement method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111340732A CN111340732A (en) | 2020-06-26 |
CN111340732B true CN111340732B (en) | 2022-10-14 |
Family
ID=71182031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010129793.2A Active CN111340732B (en) | 2020-02-28 | 2020-02-28 | Low-illumination video image enhancement method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111340732B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112508814B (en) * | 2020-12-07 | 2022-05-20 | 重庆邮电大学 | Image tone restoration type defogging enhancement method based on unmanned aerial vehicle at low altitude visual angle |
CN113961746B (en) * | 2021-09-29 | 2023-11-21 | 北京百度网讯科技有限公司 | Video generation method, device, electronic equipment and readable storage medium |
CN114049732B (en) * | 2021-09-29 | 2023-07-21 | 国网山东省电力公司郓城县供电公司 | Substation video monitoring method, system and storage medium |
CN117197004B (en) * | 2023-11-08 | 2024-01-26 | 广东鸿威国际会展集团有限公司 | Low-illumination image optimization enhancement method and system |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050073702A1 (en) * | 2003-10-02 | 2005-04-07 | Doron Shaked | Robust recursive envelope operators for fast retinex-type processing |
CN103593830B (en) * | 2013-11-29 | 2016-07-06 | 大连理工大学 | A kind of low illumination level video image enhancement |
CN104700364A (en) * | 2013-12-05 | 2015-06-10 | 大连掌控科技有限公司 | Video image enhancement method applied to players |
CN104700378A (en) * | 2013-12-05 | 2015-06-10 | 大连掌控科技有限公司 | Genetic algorithm based low-illumination video image processing method |
US10416087B2 (en) * | 2016-01-01 | 2019-09-17 | Kla-Tencor Corporation | Systems and methods for defect detection using image reconstruction |
CN107180418A (en) * | 2017-06-29 | 2017-09-19 | 新疆大学 | A kind of Enhancement Methods about Satellite Images and device converted based on Tetrolet |
CN109801238B (en) * | 2019-01-10 | 2023-05-23 | 南京信息职业技术学院 | Weak illumination image enhancement method based on simplified atmospheric scattering model |
CN109872285B (en) * | 2019-01-21 | 2022-06-10 | 电子科技大学 | Retinex low-illumination color image enhancement method based on variational constraint |
CN110136081A (en) * | 2019-05-13 | 2019-08-16 | 北京邮电大学 | A kind of image enchancing method based on Gaussian kernel skewness correction Mass filter |
CN110706180B (en) * | 2019-10-09 | 2022-02-11 | 山东大学 | Method, system, equipment and medium for improving visual quality of extremely dark image |
CN110827225A (en) * | 2019-11-13 | 2020-02-21 | 山东科技大学 | Non-uniform illumination underwater image enhancement method based on double exposure frame |
-
2020
- 2020-02-28 CN CN202010129793.2A patent/CN111340732B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111340732A (en) | 2020-06-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111340732B (en) | Low-illumination video image enhancement method and device | |
US10719918B2 (en) | Dynamically determining filtering strength for noise filtering in image processing | |
CN107527332B (en) | Low-illumination image color retention enhancement method based on improved Retinex | |
CN108205804B (en) | Image processing method and device and electronic equipment | |
US10580120B2 (en) | Image filtering based on image gradients | |
EP2187620B1 (en) | Digital image processing and enhancing system and method with function of removing noise | |
CN108694705B (en) | Multi-frame image registration and fusion denoising method | |
US20170365046A1 (en) | Algorithm and device for image processing | |
JP4460839B2 (en) | Digital image sharpening device | |
CN110276767A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
US20150109321A1 (en) | Tone Mapping | |
CN106846270B (en) | Image edge enhancement method and device | |
US8831346B2 (en) | Image processing apparatus and method, and program | |
JP2009093323A (en) | Image processing device and program | |
CN108133463B (en) | Noise reduction method and system for histogram equalization image | |
CN106412448B (en) | Wide dynamic range processing method and system based on single frame image | |
CN103310430A (en) | Method and apparatus for deblurring non-uniform motion blur | |
CN112734650A (en) | Virtual multi-exposure fusion based uneven illumination image enhancement method | |
CN112819721B (en) | Method and system for reducing noise of image color noise | |
Wang et al. | Enhancement for dust-sand storm images | |
Tan et al. | A real-time video denoising algorithm with FPGA implementation for Poisson–Gaussian noise | |
WO2020107308A1 (en) | Low-light-level image rapid enhancement method and apparatus based on retinex | |
CN113011433B (en) | Filtering parameter adjusting method and device | |
US9715720B1 (en) | System and method for reducing image noise | |
CN114862725B (en) | Method and device for realizing motion perception fuzzy special effect based on optical flow method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |