CN110349114A - Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment - Google Patents
Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment Download PDFInfo
- Publication number
- CN110349114A CN110349114A CN201910442011.8A CN201910442011A CN110349114A CN 110349114 A CN110349114 A CN 110349114A CN 201910442011 A CN201910442011 A CN 201910442011A CN 110349114 A CN110349114 A CN 110349114A
- Authority
- CN
- China
- Prior art keywords
- image
- subregion
- histogram
- multispectral
- equipment
- 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 68
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 230000003287 optical effect Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000003384 imaging method Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 14
- 230000001186 cumulative effect Effects 0.000 claims description 9
- 238000005315 distribution function Methods 0.000 claims description 8
- 238000011946 reduction process Methods 0.000 claims description 5
- 230000000149 penetrating effect Effects 0.000 abstract description 22
- 230000000007 visual effect Effects 0.000 abstract description 10
- 238000001514 detection method Methods 0.000 abstract description 9
- 230000006872 improvement Effects 0.000 abstract description 8
- 230000002708 enhancing effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000003595 mist Substances 0.000 description 4
- 238000005303 weighing Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 210000003128 head Anatomy 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
-
- 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
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The embodiment of the invention provides a kind of image enchancing methods applied to AOI equipment, device and road video monitoring equipment, image enhancement is carried out by carrying out gray-level histogram equalizationization to multispectral image, so that intensity profile region is uniform, pixel grey scale spacing shared by image widens, increase image contrast, improve image visual effect, the imaging of this programme integrated optical, image signal process, video enhancement techniques, improve Penetrating Fog performance, image after Penetrating Fog is in clarity and details, larger improvement has all been obtained in terms of contrast, improve long-focus in the case of the greasy weather, the detection range of big zoom camera lens.
Description
Technical field
The present invention relates to field of image enhancement, in particular to it is a kind of applied to the image enchancing method of AOI equipment, device and
Road video monitoring equipment.
Background technique
During carrying out target area video monitoring, image can not during imaging, acquisition, transport, duplication etc.
Will cause with avoiding it is certain degrade, since optical system will lead to image fault, different illumination conditions such as in imaging process
The exposure of image can be made widely different, imaging can make image fuzzy under motion state, and in transmission process, various noises and
Interference is by pollution image, in addition for often there is the case where greasy weather, will appear in the picture of greasy weather video camera shooting fuzzy
Situation,
Have the modes such as optics Penetrating Fog and algorithm Penetrating Fog in currently existing scheme, the Penetrating Fog technology of early stage research, mainly from
As principle is started with, that is, optics Penetrating Fog, by fog penetration lens come influence of the impurity to image in air filtering, principle are as follows:
In the range of black light, the light of near infrared band can penetrate fog, and the black light of this frequency is imaged, from
And realize " perspective " that naked eyes cannot achieve.But it due to the wavelength different visible light of near infrared band, needs enterprising in video camera
Row acquisition, can be only achieved the purpose that it is imaged.Simultaneously because infrared band signal energy is low, signal-to-noise ratio is low, picture signal
It acquires sensor and treatment process is also different with visible light.
And utilize algorithm Penetrating Fog, the also referred to as anti-reflection technology of video image, refer generally to by because mist and steam dust etc. cause it is dim
Unclear image is apparent from, and is emphasized certain interested features in image, is inhibited uninterested feature, so that image
Quality improves, and information content is enhanced.The following are several implementations of algorithm Penetrating Fog.
It is the Penetrating Fog algorithm based on dark first, which is a kind of method based on defogging physical model, for mist
The degradation phenomena of its image carries out once restoring fog free images with the inverse process of imaging.The method specific aim is very strong, obtains
Arithmetic result is naturally, good defog effect can be obtained.But such method calculation amount is all very big, one sub-picture of processing needs
It takes a substantial amount of time, it is difficult to meet requirement of real-time, limit the algorithm in the extensive use of engineering field.And to remote red
It is outer that this case where not meeting greasy weather model is imaged and is not suitable for.
Second is traditional algorithm for image enhancement, and such as Retinex and CLAHE scheduling algorithm, this kind of algorithm for image enhancement is logical
Cross certain means to original image convert data, selectively protrude image in interested feature or inhibit image in it is certain not
The feature needed makes image match with eye response characteristic.In image enhancement processes, the reason of not analyzing image deterioration,
Treated, and image not necessarily approaches original image.As Retinex algorithm may be implemented the enhancing of multiple features, while there is also
Some shortcomings: there is enhancing in local detail, so that noise occurs in image, the strong part of image comparison of light and shade is also easy to produce
Halation phenomenon and the inadequate true nature of color keep.In some remote monitor application scenarios, since operating distance is remote, draws
Face visual field is small, and above-mentioned Penetrating Fog technical effect respectively has superiority and inferiority.
Summary of the invention
The embodiment of the invention provides a kind of applied to the image enchancing method of AOI equipment, device and road video monitoring
Equipment, the imaging of this programme integrated optical, image signal process, video enhancement techniques improve Penetrating Fog performance, the image after Penetrating Fog
Larger improvement has all been obtained in terms of clarity and details, contrast, has improved long-focus in the case of the greasy weather, big zoom camera lens
Detection range.
In a first aspect, the present invention provides a kind of image enchancing method applied to AOI equipment, which comprises
Obtain the multispectral image of target area；
Multiple continuous nonoverlapping subregions are divided into for the multispectral image；
It is intercepted using grey level histogram of the interception value to each subregion, and the pixel under interception is evenly distributed to
Each gray level obtains limiting contrast histogram；
Gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram and completes image enhancement.
As a kind of optional scheme, the multispectral image data for obtaining target area, comprising:
Obtain multispectral data of the target area under at least two wave bands.
It is described to be divided into multiple continuous nonoverlapping sub-districts for the multispectral image as a kind of optional scheme
Domain, comprising:
The subregion of the equal sized rectangle of equal portions is evenly dividing into for the multispectral image.
It is described to be intercepted using grey level histogram of the interception value to each subregion as a kind of optional scheme, and
Pixel under interception is evenly distributed and obtains limiting contrast histogram with each gray level, comprising:
The limited cutoff value of comparison is determined using the average sharpness value of the multispectral image；
It is straight that restriction contrast is obtained using grey level histogram degree of comparing clipping of the cutoff value to each subregion
Fang Tu.
It is described to be compared using grey level histogram of the cutoff value to each subregion as a kind of optional scheme
Degree clipping obtains limiting contrast histogram, comprising:
The son of each subregion sharpness value that is averaged is compared with the cutoff value, is greater than when described from averagely sharpness value
Then determine that there are interest characteristics in the subregion equal to the cutoff value, when the average sharpness value of the son is less than the cutoff value
It then determines that the region is single features region, noise reduction process is carried out to the region.
It is described that ash is carried out to the multispectral image according to the restriction contrast histogram as a kind of optional scheme
It spends linear interpolation processing and completes image enhancement, comprising:
Obtain the cumulative distribution function CDF and mapping relations of each subregion；
It completes to carry out all restriction contrast histograms using the Cumulative Distribution Function and the mapping relations equal
Weighing apparatusization handles to obtain the central point of each subregion, is carried out using the central point to each pixel in the multispectral image
Gray scale linear interpolation processing completes image enhancement.
Second aspect, the present invention provide a kind of image intensifier device applied to AOI equipment, and described device includes:
Image acquisition unit, for obtaining the multispectral image of target area；
Image processing unit is utilized for being divided into multiple continuous nonoverlapping subregions for the multispectral image
Interception value intercepts the grey level histogram of each subregion, and the pixel under interception is evenly distributed and is obtained with each gray level
To contrast histogram is limited, it is complete that gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram
At image enhancement.
Further include device control cell and imaging unit as a kind of optional scheme, the imaging unit include camera lens,
Optical filter and imaging sensor, the device control cell include Focussing module for being focused to the camera lens,
Optical filter switching control module for adjusting the cradle head control module of cloud platform rotation and for being switched over to the optical filter.
As a kind of optional scheme, the optical filter includes vision filter and the first infrared fileter, second infrared
Optical filter.
The third aspect, the present invention provide a kind of road video monitoring equipment, and the road video monitoring equipment has as above
The image intensifier device applied to AOI equipment stated.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantage that
The embodiment of the invention provides a kind of applied to the image enchancing method of AOI equipment, device and road video monitoring
Equipment carries out image enhancement by carrying out gray-level histogram equalizationization to multispectral image, so that intensity profile region is uniform, figure
As shared pixel grey scale spacing widens, image contrast is increased, improves image visual effect, the imaging of this programme integrated optical, figure
As signal processing, video enhancement techniques, Penetrating Fog performance is improved, the image after Penetrating Fog is in terms of clarity and details, contrast
Larger improvement has all been obtained, the detection range of long-focus in the case of the greasy weather, big zoom camera lens is improved.
Detailed description of the invention
Fig. 1 is a kind of flow chart of embodiment of the image enchancing method applied to AOI equipment provided by the invention；
Fig. 2 is the flow chart of the image enchancing method another kind embodiment provided by the invention applied to AOI equipment；
Fig. 3 is a kind of flow chart of embodiment of the image intensifier device applied to AOI equipment provided by the invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
Description and claims of this specification and term " first ", " second ", " third ", " in above-mentioned attached drawing
Four " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein or describing
Sequence other than appearance is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that covering is non-exclusive
Include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to clearly arrange
Those of out step or unit, but may include be not clearly listed or it is solid for these process, methods, product or equipment
The other step or units having.
As shown in connection with fig. 1, the present invention provides a kind of a kind of embodiment of image enchancing method applied to AOI equipment, institute
The method of stating includes:
S101, the multispectral image for obtaining target area.
S102, multiple continuous nonoverlapping subregions are divided into for the multispectral image.
S103, it is intercepted using grey level histogram of the interception value to each subregion, and the pixel under interception is uniform
Each gray level is assigned to obtain limiting contrast histogram.
S104, gray scale linear process completion image is carried out to the multispectral image according to the restriction contrast histogram
Enhancing.
The embodiment of the invention provides a kind of image enchancing method applied to AOI equipment, AOI (Automated
Optical Inspection, automatic optics inspection) equipment be based on optical principle come to encountered in welding production it is common lack
The equipment for being trapped into row detection, AOI equipment carry out image enhancement by carrying out gray-level histogram equalizationization to multispectral image, so that
Intensity profile region is uniform, and pixel grey scale spacing shared by image widens, and increases image contrast, improves image visual effect, this
Schemes synthesis optical imagery, image signal process, video enhancement techniques improve Penetrating Fog performance, and the image after Penetrating Fog is clear
Degree and details have all obtained larger improvement in terms of contrast, improve long-focus in the case of the greasy weather, big zoom camera lens detection away from
From.
The present invention provides a kind of image enchancing method another kind embodiment applied to AOI equipment, which comprises
S201, the multispectral image for obtaining target area.
Target area is the region monitored, such as road, crossing, warehouse region, obtains target area at least two waves
Multispectral data under section, two wave bands can be respectively visible light and infrared light, for infrared light can also be arranged it is multiple not
Same wave band, by being filtered using different optical filters, multispectral image may include the image of many bands, each
Band is a width gray level image, it indicates the scene brightness obtained according to the susceptibility for the sensor for being used to generate the band, Ke Yitong
Cross imaging unit carry out multispectral image acquisition, imaging unit be arranged on device control cell, imaging unit include camera lens,
Optical filter and imaging sensor, device control cell include Focussing module for being focused to the camera lens, are used for
The cradle head control module of cloud platform rotation and the optical filter switching control module for switching over to the optical filter are adjusted, is passed through
The switching of different optical filters may be implemented in optical filter switching control module.
S202, multiple continuous nonoverlapping subregions are divided into for the multispectral image.
Image enhancement is carried out using histogram, is evenly dividing into the equal sized rectangle of equal portions for the multispectral image
Subregion, the selection for size, herein without limitation.
S203, it is intercepted using grey level histogram of the interception value to each subregion, and the pixel under interception is uniform
Each gray level is assigned to obtain limiting contrast histogram.
The limited cutoff value of comparison is determined using the average sharpness value of the multispectral image, using the cutoff value to every
Grey level histogram degree of the comparing clipping of sub-regions obtains limiting contrast histogram, specifically, by each subregion
The average sharpness value of son is compared with the cutoff value, when described then determine from averagely sharpness value more than or equal to the cutoff value should
There are interest characteristics in subregion, then determine that the region is single features when the average sharpness value of the son is less than the cutoff value
Region carries out noise reduction process to the region.
S204, gray scale linear process completion image is carried out to the multispectral image according to the restriction contrast histogram
Enhancing.
The cumulative distribution function CDF and mapping relations of each subregion are obtained, mapping relations can be by accumulation histogram
Distribution curve obtains:
Wherein A0It is sum of all pixels (image area), DmaxFor maximum high-gray level value, DA、DBIt is the forward and backward ash of conversion respectively
Angle value, HiIt is the number of pixels of i-stage gray scale.It is completed using the Cumulative Distribution Function and the mapping relations limited to institute
Determine contrast histogram progress equalization processing and obtain the central point of each subregion, using the central point to described multispectral
Each pixel in image carries out gray scale linear interpolation processing and completes image enhancement.
The embodiment of the invention provides a kind of image enchancing method applied to AOI equipment, AOI equipment passes through to multispectral
Image carries out gray-level histogram equalizationization and carries out image enhancement, so that intensity profile region is uniform, pixel grey scale shared by image
Spacing widens, and increases image contrast, improves image visual effect, and the imaging of this programme integrated optical, image signal process, video increase
Strong technology improves Penetrating Fog performance, and the image after Penetrating Fog has all obtained larger improvement in terms of clarity and details, contrast,
Improve the detection range of long-focus in the case of the greasy weather, big zoom camera lens.
It should be noted that typically seen light monitoring due to focal length it is small, visual field is larger.So obtained image comparison
Preferably, dynamic range is larger, and noise is small, and color is truer, and can really reflect reality scene for degree.And infrared monitoring is due to effect
Distance is remote, and near-infrared response signal intensity is weak, and the contrast of image is caused to decline, and the dynamic range of image is smaller, and noise is larger,
Therefore it needs to pre-process multispectral image to enhance the visual effect of image.
The process of image preprocessing may include color interpolation, image denoising, sharpening, color conversion, color correction, Bai Ping
Weighing apparatus and image data statistics, specifically, when carrying out noise reduction process, due under remote monitoring condition, the noise of image compared with
Greatly, it is therefore desirable to noise elimination be carried out to image as far as possible, increase noise reduction levels, for the purpose of meeting human eye vision.Carrying out figure
As in sharpening process, since operating distance is remote, the interference such as dust, particle in weather leads to image subject edge blurry, details
It is unobvious.Sharpness parameter is reduced, is subject to and meets human eye vision.When carrying out tone mapping processing, tone mapping is inherently
For to solve the problems, such as being to carry out significantly contrast decaying scene brightness transformed to the range that can be shown, want simultaneously
Keep image detail and color etc. for showing the very important information of original scene.In different applications, tone mapping has
Different targets, under the environment that operating distance is remote, visual field is small, the target of tone mapping be emphasize to generate it is as much as possible thin
Section or maximum picture contrast, increase the dynamic range of image.Adjustment method is realized by the way of look-up table, such as
Effect after fruit correction meets human eye vision, is considered as having reached calibration result, it is no longer necessary to re-calibrate.
Grey level histogram is the function of gray level, describes the number of the pixel in image with the gray level.It determines
The intensity value ranges of image picture elements, are divided into several grades as unit of gradation intervals appropriate, indicate image with horizontal axis
Each gray level, the number of pixels that each gray scale occurs is indicated with the longitudinal axis, the bar shaped statistical chart made is grey level histogram,
Mathematically, normalized histogram is defined as the relative frequency of gray level appearance.
Histogram equalization is image pixel value to be redistributed, original image by carrying out certain transformation to original image
Grey level histogram become equally distributed form in whole tonal ranges from some gray scale interval for comparing concentration, to make
The histogram of original image is changed to equally distributed histogram, achievees the effect that enhance image overall contrast ratio.
As shown in connection with fig. 2, another embodiment of the image enhancement provided by the invention based on multispectral image, the figure
The implementation process of image intensifying algorithm includes:
S301, it is inputted using the grey level histogram of each subregion in statistical data as algorithm.
S302, the cutoff limiting that contrast-limited is determined using the size of the average acutance statistical value in statistical data.
S303, using cutoff limiting to region degree of the comparing clipping of each piecemeal.
When the average sharpness value of some block in image is greater than the threshold value of setting, judge that there are main bodys in bright image, and
Further protrude main body；When the average sharpness value of some block in image is less than the threshold value of setting, judge there are uniform background,
Uniform background is not operated, the excessive amplification of noise, prominent image emphasis main body are limited.
S304, the grey level histogram after each subregion contrast-limited is equalized, is obtained in each subregion
Heart point, using these central points as sample point.
S305, gray scale linear interpolation is carried out to each pixel of image, obtains enhanced image.
The present invention provides each of a kind of image enchancing method applied to AOI equipment, AOI equipment utilization statistical data
The grey level histogram of subregion is inputted as algorithm, and the cut-off of contrast-limited is determined using the size of average acutance statistical value
The limit, the main function of cutoff limiting is exactly region degree of the comparing clipping to each piecemeal, when some block in image
When averagely sharpness value is larger, illustrate that there may be main bodys in image, then just prominent main body, just increases accordingly by the limit.
When the average sharpness value of some block in image is smaller, it would be possible that there are the uniform backgrounds such as sky, then just to sky etc.
Uniform background does not operate, this can effectively be avoided algorithm to the excessive operation of the uniform backgrounds such as sky, limits the excessive of noise
Amplification, and image emphasis main body can be protruded, then the grey level histogram after each subregion contrast-limited is carried out equal
Weighing apparatusization obtains each subregion central point, using these central points as sample point, finally carries out again to each pixel of image
Gray scale linear interpolation, obtains enhanced image, and integrated optical imaging, image signal process, video enhancement techniques improve
Mist performance, the image after Penetrating Fog have all obtained larger improvement in terms of clarity and details, contrast, in the case of improving the greasy weather
The detection range of long-focus, big zoom camera lens.
As shown in connection with fig. 3, correspondingly, the present invention provides a kind of image intensifier device applied to AOI equipment, for executing
The above-mentioned image enchancing method applied to AOI equipment, described device include:
Image acquisition unit 401, for obtaining the multispectral image of target area；
Image processing unit 402, for being divided into multiple continuous nonoverlapping subregions, benefit for the multispectral image
It is intercepted with grey level histogram of the interception value to each subregion, and the pixel under interception is evenly distributed with each gray level
It obtains limiting contrast histogram, gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram
Complete image enhancement.
Image intensifier device applied to AOI equipment further includes device control cell 403 and imaging unit 404, it is described at
Picture unit 404 includes camera lens, optical filter and imaging sensor, and imaging unit 404 exports the multispectral image of acquisition to image
Acquisition unit 401, the device control cell 403 include Focussing module for being focused to the camera lens, are used for
Adjust the cradle head control module of cloud platform rotation and the optical filter switching control module for switching over to the optical filter, camera lens
Focussing and focusing can be carried out, has the characteristics that long-focus, big zoom camera lens, optical filter includes vision filter and first
Infrared fileter, the second infrared fileter, the first infrared fileter and the second infrared fileter have different wave bands, certainly also
It can according to need and increase more optical filters, specific wave band can not be limited this with flexible choice.
In the present embodiment, device control cell is electrically connected by 485 interfaces with imaging unit, and imaging sensor can use
Cmos sensor Sony IMX222, it should be noted that period type can flexible choice according to actual needs, this is not done
It limits.
The basic thought of histogram equalization is the gray scale for changing original image pixels, and each gray value represents 1 gray scale
Grade, gray level image possesses 256 gray levels, widens to the gray level more than number of pixels in the picture, few to number of pixels
Gray level reduced, so that the corresponding histogram of image is transformed to equally distributed form；To which the entirety for enhancing image is right
Than degree, achieve the purpose that make image clearly；At this point, the entropy of image is maximum, the information content that image is included is maximum.
The step of algorithm of histogram equalization:
S1, the statistics each gray-scale number of pixels of original image；
S2, the histogram for calculating original image, i.e., each gray-scale probability density；
S3, each gray-scale cumulative probability distribution is calculated；
S4, last output gray level is calculated；
S5, using mapping relations, modify the gray level of original image, obtain enhancing image so that image histogram be it is approximate
Even distribution.
The embodiment of the invention provides a kind of image intensifier device applied to AOI equipment, AOI equipment passes through to multispectral
Image carries out gray-level histogram equalizationization and carries out image enhancement, so that intensity profile region is uniform, pixel grey scale shared by image
Spacing widens, and increases image contrast, improves image visual effect, and the imaging of this programme integrated optical, image signal process, video increase
Strong technology improves Penetrating Fog performance, and the image after Penetrating Fog has all obtained larger improvement in terms of clarity and details, contrast,
Improve the detection range of long-focus in the case of the greasy weather, big zoom camera lens.
Correspondingly, a kind of road video monitoring equipment, the road video monitoring equipment tool are provided in the embodiment of the present invention
Just like the above-mentioned image intensifier device applied to AOI equipment, road video monitoring equipment can be arranged by the way of probe
In road cross, road video monitoring equipment is the important component of public security command system, is provided most intuitive to field condition
Reflection, be the basic guarantee for implementing accurately to dispatch, the headend equipment of emphasis place and monitoring point by video image with optical fiber or
The modes such as special line are sent to traffic control center, carry out the storage, processing and publication of information, make traffic guidance administrative staff to friendship
Timely, accurate judgement is made in logical violating the regulations, traffic jam, traffic accident and other emergency events, and accordingly adjusts every system
Control parameter and command scheduling strategy.
It provides to be also configured in a kind of road video monitoring equipment in the embodiment of the present invention and a kind of is applied to AOI for executing
The program of the image enchancing method of equipment, which comprises
Obtain the multispectral image of target area；
Multiple continuous nonoverlapping subregions are divided into for the multispectral image；
It is intercepted using grey level histogram of the interception value to each subregion, and the pixel under interception is evenly distributed to
Each gray level obtains limiting contrast histogram；
Gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram and completes image enhancement.
As a kind of optional scheme, the multispectral image data for obtaining target area, comprising:
Obtain multispectral data of the target area under at least two wave bands.
It is described to be divided into multiple continuous nonoverlapping sub-districts for the multispectral image as a kind of optional scheme
Domain, comprising:
The subregion of the equal sized rectangle of equal portions is evenly dividing into for the multispectral image.
It is described to be intercepted using grey level histogram of the interception value to each subregion as a kind of optional scheme, and
Pixel under interception is evenly distributed and obtains limiting contrast histogram with each gray level, comprising:
The limited cutoff value of comparison is determined using the average sharpness value of the multispectral image；
It is straight that restriction contrast is obtained using grey level histogram degree of comparing clipping of the cutoff value to each subregion
Fang Tu.
It is described to be compared using grey level histogram of the cutoff value to each subregion as a kind of optional scheme
Degree clipping obtains limiting contrast histogram, comprising:
The son of each subregion sharpness value that is averaged is compared with the cutoff value, is greater than when described from averagely sharpness value
Then determine that there are interest characteristics in the subregion equal to the cutoff value, when the average sharpness value of the son is less than the cutoff value
It then determines that the region is single features region, noise reduction process is carried out to the region.
It is described that ash is carried out to the multispectral image according to the restriction contrast histogram as a kind of optional scheme
It spends linear interpolation processing and completes image enhancement, comprising:
Obtain the cumulative distribution function CDF and mapping relations of each subregion；
It completes to carry out all restriction contrast histograms using the Cumulative Distribution Function and the mapping relations equal
Weighing apparatusization handles to obtain the central point of each subregion, is carried out using the central point to each pixel in the multispectral image
Gray scale linear interpolation processing completes image enhancement.
The embodiment of the invention provides a kind of road video monitoring equipments, by carrying out grey level histogram to multispectral image
Equalization carries out image enhancement, so that intensity profile region is uniform, pixel grey scale spacing shared by image is widened, and it is anti-to increase image
Difference improves image visual effect, and the imaging of this programme integrated optical, image signal process, video enhancement techniques improve mist transmitting
Can, the image after Penetrating Fog has all obtained larger improvement in terms of clarity and details, contrast, improves focal length in the case of the greasy weather
Detection range away from, big zoom camera lens.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
Above to provided by the present invention a kind of applied to the image enchancing method of AOI equipment, device and road video prison
Control equipment is described in detail, for those of ordinary skill in the art, thought according to an embodiment of the present invention, specific real
Apply in mode and application range that there will be changes, in conclusion the content of the present specification should not be construed as to limit of the invention
System.
Claims (10)
1. a kind of image enchancing method applied to AOI equipment, which is characterized in that the described method includes:
Obtain the multispectral image of target area；
Multiple continuous nonoverlapping subregions are divided into for the multispectral image；
Intercepted using grey level histogram of the interception value to each subregion, and by interception under pixel be evenly distributed to it is each
Gray level obtains limiting contrast histogram；
Gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram and completes image enhancement.
2. the image enchancing method according to claim 1 applied to AOI equipment, which is characterized in that the acquisition target
The multispectral image data in region, comprising:
Obtain multispectral data of the target area under at least two wave bands.
3. the image enchancing method according to claim 1 applied to AOI equipment, which is characterized in that described for described
Multispectral image is divided into multiple continuous nonoverlapping subregions, comprising:
The subregion of the equal sized rectangle of equal portions is evenly dividing into for the multispectral image.
4. the image enchancing method according to claim 1 applied to AOI equipment, which is characterized in that described to utilize interception
Value intercepts the grey level histogram of each subregion, and the pixel under interception is evenly distributed and is limited with each gray level
Determine contrast histogram, comprising:
The limited cutoff value of comparison is determined using the average sharpness value of the multispectral image；
It obtains limiting contrast histogram using grey level histogram degree of comparing clipping of the cutoff value to each subregion.
5. the image enchancing method according to claim 4 applied to AOI equipment, which is characterized in that described in the utilization
Cutoff value obtains grey level histogram degree of the comparing clipping of each subregion to limit contrast histogram, comprising:
The son of each subregion sharpness value that is averaged is compared with the cutoff value, is more than or equal to when described from averagely sharpness value
The cutoff value then determines that there are interest characteristics in the subregion, then true when the average sharpness value of the son is less than the cutoff value
The fixed region is single features region, carries out noise reduction process to the region.
6. the image enchancing method according to claim 4 applied to AOI equipment, which is characterized in that described according to
It limits contrast histogram and gray scale linear interpolation processing completion image enhancement is carried out to the multispectral image, comprising:
Obtain the cumulative distribution function CDF and mapping relations of each subregion；
All restriction contrast histograms are equalized using the Cumulative Distribution Function and mapping relations completion
Processing obtains the central point of each subregion, carries out gray scale to each pixel in the multispectral image using the central point
Linear interpolation processing completes image enhancement.
7. a kind of image intensifier device applied to AOI equipment, which is characterized in that described device includes:
Image acquisition unit, for obtaining the multispectral image of target area；
Image processing unit utilizes interception for being divided into multiple continuous nonoverlapping subregions for the multispectral image
Value intercepts the grey level histogram of each subregion, and the pixel under interception is evenly distributed and is limited with each gray level
Determine contrast histogram, gray scale linear process is carried out to the multispectral image according to the restriction contrast histogram and completes figure
Image intensifying.
8. the image intensifier device according to claim 7 applied to AOI equipment, which is characterized in that further include equipment control
Unit and imaging unit processed, the imaging unit include camera lens, optical filter and imaging sensor, and the device control cell includes
Focussing module for being focused to the camera lens, the cradle head control module for adjusting cloud platform rotation and for institute
State the optical filter switching control module that optical filter switches over.
9. the image intensifier device according to claim 8 applied to AOI equipment, which is characterized in that the optical filter packet
Include vision filter, the first infrared fileter and the second infrared fileter.
10. a kind of road video monitoring equipment, which is characterized in that the road video monitoring equipment has such as claim 8 or 9
Described in the image intensifier device applied to AOI equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910442011.8A CN110349114A (en) | 2019-05-24 | 2019-05-24 | Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910442011.8A CN110349114A (en) | 2019-05-24 | 2019-05-24 | Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110349114A true CN110349114A (en) | 2019-10-18 |
Family
ID=68173999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910442011.8A Pending CN110349114A (en) | 2019-05-24 | 2019-05-24 | Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349114A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127342A (en) * | 2019-12-05 | 2020-05-08 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and terminal equipment |
| CN111311526A (en) * | 2020-02-25 | 2020-06-19 | 深圳市朗驰欣创科技股份有限公司 | Video enhancement method, video enhancement device and terminal equipment |
| CN112884659A (en) * | 2019-11-29 | 2021-06-01 | 深圳市万普拉斯科技有限公司 | Image contrast enhancement method and device and display equipment |
| CN113032919A (en) * | 2021-03-12 | 2021-06-25 | 奥特斯科技(重庆)有限公司 | Component carrier manufacturing method, processing system, computer program and system architecture |
| CN113436162A (en) * | 2021-06-23 | 2021-09-24 | 湖南国天电子科技有限公司 | Method and device for identifying weld defects on surface of hydraulic oil pipeline of underwater robot |
| CN115131236A (en) * | 2022-06-23 | 2022-09-30 | 上海应用技术大学 | Self-adaptive arc light area repairing and enhancing method |
| CN116718353A (en) * | 2023-06-01 | 2023-09-08 | 信利光电股份有限公司 | Automatic optical detection method and device for display module |
| CN117115147A (en) * | 2023-10-19 | 2023-11-24 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831592A (en) * | 2012-08-10 | 2012-12-19 | 中国电子科技集团公司第四十一研究所 | Image nonlinearity enhancement method based on histogram subsection transformation |
| CN104899836A (en) * | 2015-05-06 | 2015-09-09 | 南京第五十五所技术开发有限公司 | Foggy image enhancing device and method based on near infrared multispectral imaging |
| CN106462956A (en) * | 2014-06-19 | 2017-02-22 | 高通股份有限公司 | Local adaptive histogram equalization |
| CN108765337A (en) * | 2018-05-28 | 2018-11-06 | 青岛大学 | A kind of single width color image defogging processing method based on dark primary priori Yu non local MTV models |
| CN109668904A (en) * | 2019-01-25 | 2019-04-23 | 南京理工大学 | A kind of optical element flaw inspection device and method |
-
2019
- 2019-05-24 CN CN201910442011.8A patent/CN110349114A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831592A (en) * | 2012-08-10 | 2012-12-19 | 中国电子科技集团公司第四十一研究所 | Image nonlinearity enhancement method based on histogram subsection transformation |
| CN106462956A (en) * | 2014-06-19 | 2017-02-22 | 高通股份有限公司 | Local adaptive histogram equalization |
| CN104899836A (en) * | 2015-05-06 | 2015-09-09 | 南京第五十五所技术开发有限公司 | Foggy image enhancing device and method based on near infrared multispectral imaging |
| CN108765337A (en) * | 2018-05-28 | 2018-11-06 | 青岛大学 | A kind of single width color image defogging processing method based on dark primary priori Yu non local MTV models |
| CN109668904A (en) * | 2019-01-25 | 2019-04-23 | 南京理工大学 | A kind of optical element flaw inspection device and method |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884659A (en) * | 2019-11-29 | 2021-06-01 | 深圳市万普拉斯科技有限公司 | Image contrast enhancement method and device and display equipment |
| CN111127342B (en) * | 2019-12-05 | 2023-08-08 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and terminal equipment |
| CN111127342A (en) * | 2019-12-05 | 2020-05-08 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and terminal equipment |
| CN111311526A (en) * | 2020-02-25 | 2020-06-19 | 深圳市朗驰欣创科技股份有限公司 | Video enhancement method, video enhancement device and terminal equipment |
| CN113032919A (en) * | 2021-03-12 | 2021-06-25 | 奥特斯科技(重庆)有限公司 | Component carrier manufacturing method, processing system, computer program and system architecture |
| CN113032919B (en) * | 2021-03-12 | 2022-03-04 | 奥特斯科技(重庆)有限公司 | Component carrier manufacturing method, processing system, computer program and system architecture |
| CN113436162A (en) * | 2021-06-23 | 2021-09-24 | 湖南国天电子科技有限公司 | Method and device for identifying weld defects on surface of hydraulic oil pipeline of underwater robot |
| CN113436162B (en) * | 2021-06-23 | 2022-12-09 | 湖南国天电子科技有限公司 | Method and device for identifying weld defects on surface of hydraulic oil pipeline of underwater robot |
| CN115131236A (en) * | 2022-06-23 | 2022-09-30 | 上海应用技术大学 | Self-adaptive arc light area repairing and enhancing method |
| CN116718353A (en) * | 2023-06-01 | 2023-09-08 | 信利光电股份有限公司 | Automatic optical detection method and device for display module |
| CN116718353B (en) * | 2023-06-01 | 2024-05-28 | 信利光电股份有限公司 | Automatic optical detection method and device for display module |
| CN117115147A (en) * | 2023-10-19 | 2023-11-24 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
| CN117115147B (en) * | 2023-10-19 | 2024-01-26 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349114A (en) | Applied to the image enchancing method of AOI equipment, device and road video monitoring equipment | |
| CN110599433B (en) | Double-exposure image fusion method based on dynamic scene | |
| CN104899836B (en) | A kind of Misty Image intensifier and method based near infrared multispectral imaging | |
| US6832000B2 (en) | Automatic segmentation-based grass detection for real-time video | |
| US20090317017A1 (en) | Image characteristic oriented tone mapping for high dynamic range images | |
| Zheng et al. | Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction | |
| CN110163807B (en) | Low-illumination image enhancement method based on expected bright channel | |
| CN111476732B (en) | Image fusion and denoising method and system | |
| CN108154492B (en) | A kind of image based on non-local mean filtering goes haze method | |
| CN104318529A (en) | Method for processing low-illumination images shot in severe environment | |
| CN110111269A (en) | Low-light-level imaging algorithm and device based on multiple dimensioned context converging network | |
| CN112967273B (en) | Image processing method, electronic device, and storage medium | |
| Joshi et al. | Quantification of retinex in enhancement of weather degraded images | |
| CN108093175A (en) | A kind of adaptive defogging method of real-time high-definition video and device | |
| CN116664460A (en) | Infrared night vision fusion method | |
| CN110349113A (en) | Self-adaptive image defogging method based on dark channel prior improvement | |
| CN111260588A (en) | Image enhancement method for high-definition digital CMOS imaging assembly | |
| EP2860692A1 (en) | Adaptive noise filtering | |
| US20230162473A1 (en) | Image processing method | |
| CN112747818B (en) | Blocked visual angle measuring platform, method and storage medium | |
| Dhingra et al. | Fusion of fuzzy enhanced overexposed and underexposed images | |
| Kaur et al. | Haze removal in remote sensing images for improved data analysis and extraction | |
| CN114025085A (en) | Method, device and equipment for switching working modes of camera equipment and storage medium | |
| Ganguly et al. | Fusion of Mathematical Morphology with Adaptive Gamma Correction for Dehazing and Visibility Enhancement of Images | |
| Kansal et al. | Fusion based fast de-fogging for foggy images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |