CN116188291A - Rapid airborne dim light image enhancement method - Google Patents
Rapid airborne dim light image enhancement method Download PDFInfo
- Publication number
- CN116188291A CN116188291A CN202211612414.0A CN202211612414A CN116188291A CN 116188291 A CN116188291 A CN 116188291A CN 202211612414 A CN202211612414 A CN 202211612414A CN 116188291 A CN116188291 A CN 116188291A
- Authority
- CN
- China
- Prior art keywords
- image
- dim light
- light image
- airborne
- enhancement
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000006243 chemical reaction Methods 0.000 claims abstract description 20
- 230000002708 enhancing effect Effects 0.000 claims abstract description 11
- 238000009499 grossing Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 230000009466 transformation Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 abstract description 5
- 230000001131 transforming effect Effects 0.000 abstract 1
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000007430 reference method Methods 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004298 light response Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
The invention provides a rapid airborne dim light image enhancement method, which comprises the following steps of 1, transforming an input airborne dim light image into an HSV color space through color conversion, and implementing a dim light enhancement algorithm on a V channel component of the HSV color space; step 2, filtering the brightness component through a guard smoothing operator; step 3, pre-enhancing the V channel component through the edge protection smooth component obtained in the step 2; step 4, enhancing the contrast of the image obtained in the step 3 through the high-order fractional model provided by the invention; and 5, carrying out brightness enhancement on the result obtained in the step 4 through the self-adaptive gamma conversion provided by the invention. The method provided by the invention can not only obtain excellent enhanced performance, but also be very efficient in processing speed; the enhancement performance of the dark part is excellent, and the requirements of dark part target identification and dark part information acquisition under an airborne scene are met.
Description
Technical Field
The invention relates to the technical field of airborne digital image processing, in particular to a rapid airborne dim light image enhancement method.
Background
When the high-speed or hypersonic aircraft flies, in order to ensure that the acquired ground or sky scene images do not have motion blur, the acquisition time of a single image signal of an onboard camera is generally required to be shortened. For the same aperture and sensor, the image frame rate acquired in unit time is improved along with the increase of the acquisition time of a single image, the shorter the acquisition time of the single image is, the weaker the response of the sensor to the illumination intensity is, and especially in a dark light environment, the situation of insufficient brightness of an airborne image can occur, so that the characteristics of a target in the acquired image are weakened, the later target detection, observation, identification, classification and the like are not facilitated, therefore, the airborne dark light image needs to be enhanced, but the calculation efficiency and the performance of an image enhancement method need to be considered simultaneously when the airborne dark light image is enhanced.
Currently, conventional dim light enhancement methods include a gamma conversion method, a histogram equalization method, a wavelet change method, and the like, but it is difficult to obtain excellent calculation efficiency and performance at the same time. Researchers have proposed Retinex enhancement theory by studying the color constancy characteristics of the human own vision system, which in turn produces a large number of model-based and learning-based Retinex enhancement methods, which typically require a high computational effort to ensure their excellent computational performance.
Disclosure of Invention
In order to solve the defect that the calculation efficiency and performance of the traditional methods such as the gamma conversion method, the histogram equalization method and the wavelet change method cannot be achieved, the invention designs a rapid airborne dim light image enhancement method which can rapidly enhance an airborne dim light image and ensure the calculation efficiency and performance of the airborne dim light image.
The technical scheme for realizing the aim of the invention is as follows: a fast airborne dim light image enhancement method comprises the following steps:
s1, inputting a dim light image, and performing color conversion transformation from an RGB color space to an HSV color space;
s2, extracting a V-channel component of the darklight image after color conversion to obtain a single-channel image I;
s5, based on a high-order fractional model, enhancing the contrast of the single-channel image to obtain a contrast enhanced dim light image I hc ；
S6, enhancing contrast and enhancing dim light image I based on self-adaptive gamma conversion method hc To obtain a dark enhanced image.
In one embodiment, before the enhancing the contrast of the single-channel image I, the method further comprises:
s3, filtering the single-channel image I based on the edge-preserving smoothing operator to obtain an edge-preserving smooth image I b Wherein I b =g (I), g (·) represents a guard smoothing operator;
s4, because the high-frequency information of the image edge collected in the dark environment is weaker, the edge-protecting smooth image I is required b Pre-enhancing to obtain pre-enhanced image I h Pre-enhanced image I h Is I h ＝(I-I b )a+I b A is a high-frequency information pre-enhancement coefficient.
Further, in the step S5, the i higher order partial model is
Wherein I is hc For contrast enhanced darklight images, n is a positive integer greater than 1.
Further, in the step S6, the dark-light enhanced image is
g (g is more than or equal to 0 and less than or equal to 1) is the self-adaptive gamma coefficient.
The contrast enhancement effect of the single-channel image is compared by the existing Retinex model and the high-order fractional model in the specific embodiment:
retinex theory states that an image can be decomposed into a reflection component independent of illumination and a reflection component independent of illuminationAmbient light intensity-dependent luminance component. First, the Retinex decomposition model is: i h ＝R*L，I h For pre-enhanced image, R is the reflection component, L is the luminance component, image I enhanced with the Retinex model e The method comprises the following steps: i e ＝R*L α Alpha is the conventional gamma transform coefficient.
Edge-preserving smooth image I with insufficient high-frequency information b Viewed as luminance component L, i.e. I b =l, then an R reflection component can be obtained that satisfies the following equation: i h ＝R*I b ＝R*L。
Through the above analysis, the darkness enhancement image in this embodiment can be changed to one by means of the Retinex decomposition model:
from the above equation, it can be demonstrated that when ng=1, the fast on-board dim light image enhancement method proposed by the present invention is equivalent to the Retinex model method.
Compared with the prior art, the invention has the beneficial effects that: the rapid airborne dim light image enhancement method designed by the invention not only can obtain excellent enhancement performance, but also is very efficient in processing speed; the enhancement performance of the dark part is excellent, and the requirements of dark part target identification and dark part information acquisition under an airborne scene are met.
Drawings
In order to more clearly illustrate the embodiments of the present invention, the drawings that are used in the description of the examples will be briefly described.
FIG. 1 is a flow chart of a fast on-board darkness image enhancement method in accordance with an embodiment;
FIG. 2 is a graph of gamma adaptation and conventional gamma conversion in an embodiment;
fig. 3 is a diagram showing a comparison of the adaptive gamma transformation and the conventional gamma (α=2.2) transformation according to the embodiment;
FIG. 4 is a graph showing experimental comparison results of the enhancement of an input image by using the existing reference method and the method of the present invention in the specific embodiment.
Detailed Description
The invention will be further described with reference to specific embodiments, and advantages and features of the invention will become apparent from the description. These examples are merely exemplary and do not limit the scope of the invention in any way. It will be understood by those skilled in the art that various changes and substitutions of details and forms of the technical solution of the present invention may be made without departing from the spirit and scope of the present invention, but these changes and substitutions fall within the scope of the present invention.
In order to overcome the defect that the calculation efficiency and the performance cannot be achieved when the traditional method is adopted to enhance the brightness of the dim light image, the embodiment discloses a rapid airborne dim light image enhancement method. The following describes, by way of specific example, a fast airborne darkness image enhancement method, as shown in fig. 1, which includes the following steps:
step 1: the input RGB image is converted into HSV space through color space transformation, a V channel brightness component I (namely a single channel image I) is extracted in the HSV space, and the method provided by the invention is implemented on the single channel image I, namely brightness enhancement is implemented on a dark light area with insufficient brightness.
Step 2: performing edge protection smoothing treatment on the single-channel image I to obtain an edge protection smoothed image I b Is I b =g (I), where g (·) represents the guard smoothing operator. Since the edge-preserving smoothing operators are very many, such as: bilateral filtering (Guided Image Filter), weight guided filtering (Weighted Guided Image Filter), and the like, the invention adopts guided filtering as a guard smoothing operator g (·) in view of computational efficiency and guard performance.
Step 3: the light response intensity of the sensor to the boundary of the object is weaker than that of the sensor to normal light under the dark light environment, so the invention pre-enhances the high-frequency information of the sensor, and pre-enhances the image I h Is I h Wherein a is a high-frequency information pre-emphasis coefficient.
Step 4: obtaining contrast enhanced dim light image I by high order partial model hc Of, higher order division typeThe model is as follows:
wherein n is a positive integer greater than 1.
Although the brightness can be improved by directly using gamma transformation, the contrast is reduced, and the contrast of a dark-light image can be improved by using the proposed high-order partial model, so that the contrast of image loss after gamma transformation is counteracted, and excellent visual effect is obtained. Referring to fig. 2, (a) shows an original dark image, (b) shows a conventional gamma change, (c) shows the results of the present invention after step 2, step 4, and conventional gamma conversion, which further demonstrate the excellent performance of the higher order partial model (n=2 case) proposed by the present invention;
step 5: dark portion lifting is not obvious enough because the bright portion of the image is overexposed directly by the traditional gamma conversion method. Therefore, the invention provides an adaptive gamma conversion method to alleviate the defects of the traditional adaptive gamma conversion.
Specifically, contrast-enhanced dim light image I by the adaptive gamma conversion proposed by the present invention hc To obtain a dark light enhanced image I of the V-channel component I e The method comprises the following steps:
wherein g (g is more than or equal to 0 and less than or equal to 1) is the self-adaptive gamma conversion coefficient provided by the invention.
Let g=0.3+i in the present invention 2 When the pixel value in the I is close to 0, g is close to 0.3, so that a better dark part brightness improvement effect than that of the traditional gamma conversion can be achieved; when the pixel value in I is close to 1, g is close to 1.3, and a better brightness suppression effect of the bright part can be achieved compared with the traditional gamma conversion, so that overexposure is prevented. Referring to fig. 3, a graph of the conventional gamma transformation and the gamma adaptation proposed by the present invention is shown, from which it is clear that the adaptation gamma proposed by the present invention is more remarkable to the dark portion enhancement. In an airborne scene, the better enhancement of the dark part is beneficial to detecting and finding the hidden target.
For the on-board scene, the operation time and the dark part enhancement effect of the method are also important, the effectiveness and the high efficiency of the method provided by the invention can be proved through some reference methods with excellent performances, and the general comparison method comprises the following steps: a histogram-based layer differential representation LDR method, a robust Retinex-based RRM method, a Retinex-based STAR method with structure and texture perception, a Zero-DCE++ method based on non-reference depth curve estimation, and the like.
In this embodiment, two sets of RGB color darklight images with the pixel size of 1280x720 pixels are selected, and the comparison of the running time of the method according to the present invention and the running time of the traditional method for processing the darklight images is performed through MATLAB-based platform test, which is shown in the following table, and is the comparison result of the running time of the method according to the present invention and the running time of the traditional method based on the model:
TABLE 1
| Method | LDR | RRM | STAR | The invention is that |
| Average run time(s) | 0.29 | 87 | 23 | 0.14 |
As can be seen from the above table, the method of the present invention has higher efficiency when processing the dark image, and the experimental comparison result between the reference method and the method of the present invention is shown in fig. 4.
The fast airborne dim light image enhancement method disclosed by the specific embodiment obtains a single-pass brightness image through converting a color space; performing edge-preserving smoothing treatment on the brightness image; pre-enhancing high-frequency information of the brightness image through the brightness image after edge protection smoothing; finally, the final airborne dim light enhanced image is obtained through the high-order fractional model and the self-adaptive gamma conversion. Compared with the existing reference method, the method has high execution efficiency and achieves very excellent dim light enhancement performance under the airborne dim light scene.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (5)
1. The quick airborne dim light image enhancement method is characterized by comprising the following steps of:
inputting a dim light image, and performing color conversion and transformation on the dim light image to an HSV color space;
extracting a V channel component of the darklight image after color conversion to obtain a single-channel image;
based on a high-order fractional model, enhancing the contrast of the single-channel image to obtain a contrast enhanced dim light image;
and (3) enhancing the brightness of the contrast enhanced dark-light image based on the self-adaptive gamma conversion method to obtain the dark-light enhanced image.
2. The fast on-board dim light image enhancement method according to claim 1, wherein: before the enhancing the contrast of the single-channel image, the method further comprises:
filtering the single-channel image based on the edge-preserving smoothing operator to obtain an edge-preserving smoothing image;
and pre-enhancing the edge-preserving smooth image to obtain a pre-enhanced image.
3. The fast on-board dim light image enhancement method according to claim 2, wherein: the pre-enhanced image I h Is I h ＝(I-I b )a+I b Wherein I h To pre-enhance the post-image, I b For edge-preserving smooth images, a is a pre-enhancement coefficient of high-frequency information.
4. A fast on-board dim light image enhancement method according to claim 3, wherein: the i higher order partial model is
Wherein I is hc For contrast enhanced darklight images, n is a positive integer greater than 1.
5. The fast on-board dim light image enhancement method according to claim 4, wherein: the dim light enhanced image is
g (g is more than or equal to 0 and less than or equal to 1) is the self-adaptive gamma coefficient. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211612414.0A CN116188291A (en) | 2022-12-15 | 2022-12-15 | Rapid airborne dim light image enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211612414.0A CN116188291A (en) | 2022-12-15 | 2022-12-15 | Rapid airborne dim light image enhancement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116188291A true CN116188291A (en) | 2023-05-30 |
Family
ID=86431678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211612414.0A Pending CN116188291A (en) | 2022-12-15 | 2022-12-15 | Rapid airborne dim light image enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116188291A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436058A (en) * | 2023-10-10 | 2024-01-23 | 国网湖北省电力有限公司 | Electric power information safety protection system |
-
2022
- 2022-12-15 CN CN202211612414.0A patent/CN116188291A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436058A (en) * | 2023-10-10 | 2024-01-23 | 国网湖北省电力有限公司 | Electric power information safety protection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104156921B (en) | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method | |
| CN111047530B (en) | Underwater image color correction and contrast enhancement method based on multi-feature fusion | |
| CN106846276B (en) | Image enhancement method and device | |
| WO2016206087A1 (en) | Low-illumination image processing method and device | |
| CN110889812B (en) | Underwater image enhancement method for multi-scale fusion of image characteristic information | |
| CN110211070B (en) | Low-illumination color image enhancement method based on local extreme value | |
| CN112561804A (en) | Low-illumination underwater image enhancement method based on multi-scale detail enhancement | |
| CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
| CN112116536A (en) | Low-illumination image enhancement method and system | |
| CN112541869A (en) | Retinex image defogging method based on matlab | |
| CN116188291A (en) | Rapid airborne dim light image enhancement method | |
| CN112750089B (en) | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior | |
| CN114037641A (en) | Low-illumination image enhancement method, device, equipment and medium | |
| CN112801899A (en) | Internal and external circulation driving image blind deblurring method and device based on complementary structure perception | |
| CN110545414B (en) | Image sharpening method | |
| CN110175959B (en) | Typhoon cloud picture enhancement method | |
| CN110136085B (en) | Image noise reduction method and device | |
| CN112465711A (en) | Degraded image enhancement method for foggy environment | |
| CN112308793A (en) | Novel method for enhancing contrast and detail of non-uniform illumination image | |
| CN106447616B (en) | Method and device for realizing wavelet denoising | |
| CN113256533B (en) | Self-adaptive low-illumination image enhancement method and system based on MSRCR | |
| Asadi et al. | Improving dark channel prior for single image dehazing | |
| CN109886901B (en) | Night image enhancement method based on multi-channel decomposition | |
| David | Low illumination image enhancement algorithm using iterative recursive filter and visual gamma transformation function | |
| CN106780381B (en) | Low-illumination image self-adaptive enhancement method based on dark primary color and bilateral filtering |
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 |