CN110889810A - Method and system for extracting image through light filtering film based on polarization - Google Patents
Method and system for extracting image through light filtering film based on polarization Download PDFInfo
- Publication number
- CN110889810A CN110889810A CN201911199318.6A CN201911199318A CN110889810A CN 110889810 A CN110889810 A CN 110889810A CN 201911199318 A CN201911199318 A CN 201911199318A CN 110889810 A CN110889810 A CN 110889810A
- Authority
- CN
- China
- Prior art keywords
- image
- polarization
- highlight
- enhanced
- texture
- 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
Images
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
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/49—Analysis of texture based on structural texture description, e.g. using primitives or placement rules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for extracting an image by using a polarization-based light filtering film. The method comprises the following steps: obtaining a polarization image of a scene with a filtering film; highlight inhibition is carried out on the polarization image to obtain a highlight inhibition image; carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image; and carrying out texture description on the enhanced image to obtain a target characteristic image. The method and the system for extracting the image by using the polarization-based light filtering film provided by the invention are adopted to combine the technical means of polarization imaging, highlight inhibition, image enhancement and target identification, thereby realizing effective extraction of image information for the image with the light filtering film.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method and a system for extracting an image by using a light filtering film based on polarization.
Background
In actual life, in scenes such as a security monitoring system and a target tracking system which need to acquire detailed information, a lot of problems that image information cannot be extracted are often caused due to the existence of a light filtering film. The technical means at the present stage can not solve the problems.
Disclosure of Invention
The invention aims to provide a method and a system for extracting an image by using a polarization-based light filtering film, so that image information can be effectively extracted.
In order to achieve the purpose, the invention provides the following scheme:
a method for extracting an image based on a polarization-based filter film, comprising:
obtaining a polarization image of a scene with a filtering film;
highlight inhibition is carried out on the polarization image to obtain a highlight inhibition image;
carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image;
and carrying out texture description on the enhanced image to obtain a target characteristic image.
Optionally, the acquiring a polarization image specifically includes:
collecting original polarization images of a scene with a light filtering film from three different angles;
and constructing a polarization image by adopting a Stokes vector method for the original polarization image.
Optionally, the highlight suppression is performed on the polarization image to obtain a highlight-suppressed image, and the method specifically includes:
performing highlight region detection on the polarization image to obtain a highlight region detection result;
marking according to the detection result of the highlight area to obtain a highlight area mark;
and obtaining a highlight-inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight-inhibited polarization image is the highlight-inhibited image.
Optionally, the performing polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image specifically includes:
acquiring polarization degree texture data of the highlight inhibition image;
and obtaining an enhanced polarization image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarization image is the enhanced image.
Optionally, the texture description is performed on the enhanced image to obtain a target feature image, where the target feature image is an image extracted under a filter film, and the method specifically includes:
acquiring a texture descriptor of the enhanced image;
and acquiring a target texture feature image according to the texture descriptor.
In order to achieve the above purpose, the invention also provides the following scheme:
a polarization based filter film extraction imaging system, comprising:
the polarized image acquisition module is used for acquiring a polarized image of a scene with the filtering film;
the highlight inhibition image acquisition module is used for carrying out highlight inhibition on the polarization image to obtain a highlight inhibition image;
the enhanced image acquisition module is used for carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image;
and the target characteristic image determining module is used for performing texture description on the enhanced image to obtain a target characteristic image.
Optionally, the polarization image obtaining module specifically includes:
the polarization subimage acquisition unit is used for acquiring original polarization images of a scene with the filtering film from three different angles;
and the polarized image reconstruction unit is used for constructing a polarized image by adopting a Stokes vector method for the original polarized image.
Optionally, the highlight suppression image obtaining module specifically includes:
the detection result determining unit is used for carrying out highlight region detection on the polarization image to obtain a highlight region detection result;
the mark determining unit is used for marking according to the detection result of the highlight area to obtain a highlight area mark;
and the highlight inhibition image determining unit is used for obtaining a highlight inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight inhibited polarization image is the highlight inhibition image.
Optionally, the enhanced image obtaining module specifically includes:
the texture data acquisition unit is used for acquiring polarization degree texture data of the highlight inhibition image;
and the enhanced image determining unit is used for obtaining an enhanced polarized image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarized image is the enhanced image.
Optionally, the target feature image determining module specifically includes:
a texture descriptor acquiring unit, configured to acquire a texture descriptor of the enhanced image;
and the target texture characteristic image determining unit is used for acquiring a target texture characteristic image according to the texture descriptor.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method for extracting an image by using a polarization-based light filtering film. Firstly, acquiring a polarization image; then, performing highlight inhibition on the polarization image to obtain a highlight inhibition image; then, carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image; and finally, carrying out texture description on the enhanced image to obtain a target characteristic image. Obviously, the invention realizes effective extraction of image information for the image with the filter film by combining the technical means of polarization imaging, highlight inhibition, image enhancement and target identification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for extracting an image by using a polarization-based filter film according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a light passing through a polarizer according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the reflection and refraction of light according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an image enhancement effect according to an embodiment of the present invention;
FIG. 5 is a diagram of a system for extracting images based on a polarizing filter film according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for extracting an image by using a polarization-based light filtering film, so that image information can be effectively extracted.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
FIG. 1 is a flowchart of a method for extracting an image by using a polarization-based filter film according to an embodiment of the present invention. As shown in fig. 1, a method for extracting an image based on a polarization filtering film includes:
step 101: acquiring a polarization image of a scene with a filter film, specifically comprising: collecting original polarization images of a scene with a light filtering film from three different angles; and constructing a polarization image by adopting a Stokes vector method for the original polarization image.
Step 102: performing highlight inhibition on the polarization image to obtain a highlight inhibition image, which specifically comprises the following steps: performing highlight region detection on the polarization image to obtain a highlight region detection result; marking according to the detection result of the highlight area to obtain a highlight area mark; and obtaining a highlight-inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight-inhibited polarization image is the highlight-inhibited image.
Step 103: carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image, which specifically comprises the following steps: acquiring polarization degree texture data of the highlight inhibition image; and obtaining an enhanced polarization image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarization image is the enhanced image.
Step 104: performing texture description on the enhanced image to obtain a target feature image, which specifically comprises: acquiring a texture descriptor of the enhanced image; and acquiring a target texture feature image according to the texture descriptor.
The invention effectively extracts the image information of the image with the filtering film by combining the technical means of polarization imaging, highlight inhibition, image enhancement and target identification.
In step 101, when obtaining a polarization image of a scene with a filtering film, a stokes vector method is mainly used to describe the polarization state of a beam of light, which is defined as:
the four parameters are all time average values of light intensity, I represents total light intensity, Q represents the difference between components of linearly polarized light in the 0-90 ° direction, U represents the difference between components of linearly polarized light in the ± 45 ° direction, V represents the difference between components of left-handed circularly polarized light and right-handed circularly polarized light, and the described light can be fully polarized light, partially polarized light, and fully unpolarized light. The Stokes vector is adopted to express the polarized light, so that the four parameters are all the light intensity dimensions and can be measured, and each parameter can be solved by adopting a characteristic polarizing device.
Under certain conditions, the reflection and refraction of light have certain polarization characteristics, and simultaneously the light is transmitted in a scattering medium, the backward scattering light of the particles also has the polarization characteristics, and the atmospheric light acts with the particles in the atmosphere in the transmission process to form light with a certain polarization state.
When the polarized light with known polarization state passes through the optical element, there is a certain relation between the polarization state of the outgoing light and the polarization state of the incoming light. Stokes vector S of incident light through Mueller matrixiStokes vector S of emergent lightoHaving established connection with the optical element, FIG. 2 is a schematic view of the embodiment of the invention, i.e., the light passes through the polarizer and is incident on the optical element SiThe emergent light obtained by the polarization device M is SoThe expression is:
in the above formula, M is a 4 × 4 Mueller matrix, i.e., a transmission matrix of the optical element, the transmission matrix of the optical element is related to the optical element itself, and the transmission matrix of different optical elements is different. If the incident light passes through n polarizers, their corresponding Mueller matrix is MiThen the Stokes vector of the outgoing light can be expressed as:
So＝Mn·Mn-1…M2·M1·Si
according to the relationship between the Stokes vector and the Mueller matrix, the Stokes vector of a polarized light beam is S ═ (I, Q, U)TAfter passing through the polarizer with the polarization angle θ, the obtained polarized image light intensity I (θ) can be expressed as the following formula:
according to the formula, when the scene images under at least 3 different polarization angles are obtained, the Stokes vectors of the scene images can be solved.
For example, when the polarization film is rotated to collect polarization pictures at 0 °, 60 °, and 120 °, respectively, the value of the Stokes vector is solved as follows:
when a light beam is transmitted from one medium to another medium, the phenomenon that part of the light beam changes the propagation direction and returns to the original substance at an interface is called reflection, the reflection of light is a common phenomenon in nature, a vision system can see an object just because of the reflection of the light, the phenomenon that the light beam enters another medium through the interface and the transmission direction is changed is called refraction, and the refraction of the light follows the refraction law. The french physicist fresnel proposed a well-known fresnel formula through the research on the reflected light and the refracted light, which well explains the polarization characteristics of the reflected light and the refracted light, as shown in fig. 3, and fig. 3 is a schematic diagram of the reflection and refraction of the light according to the embodiment of the present invention.
The highlight inhibition method is realized based on a double-color reflection model proposed by Shafer and the like. The model considers that the illumination of the object surface is mainly composed of diffuse reflection and specular reflection. In the RGB space, pixels and highlight pixels form a T-shaped distribution. And (3) sequentially analyzing main components of the diffuse reflection area and the highlight area, fitting a diffuse reflection vector and a light source color vector, and projecting by using the two vectors to quickly remove highlight. But there will be numerical errors in the fitting of the diffuse reflection to the light source color vector. The diffuse reflection light is light that is reflected from the inside of an object after incident light is refracted by the object, and reflects the color of the object. Specularly reflected light is light that is reflected directly off the surface of an object, reflecting the color of the light source. The intensity of the specularly reflected light is dependent on the viewing angle and, as such, the specularly reflected light forms a high light at the surface of the object. The effect of suppressing highlight is achieved by filtering specular reflection light through the additional polarization light supplementing module matched with the polarization image acquisition module.
According to the two-color reflection model, for each pixel of high light, it is a linear superposition of a diffuse reflection component and a strong reflection component. The expression is as follows:
A(X)＝α(X)∫ΩS(λ，X)B(λ)Q(λ)dλ+β(X)∫ΩB(λ)Q(λ)dλ
where a (X) is a color vector, α (X) is a diffuse reflection weighting factor, β (X) is a strong reflection weighting factor, X ═ X, y is a pixel coordinate, S (λ, X) is a diffuse reflection power spectrum, B (λ) is a strong reflection power spectrum, Q (λ) is a sensor sensitivity, the above formula is simplified as follows for simplicity:
A(X)＝A(α)D(X)+β(X)S
wherein d (x) ═ jjΩS(λ，X)B(λ)Q(λ)dλ，S＝∫ΩB(λ)Q(λ)dλ。
In the two-color reflection model, the chromaticity of an image needs to be known, and the definition formula is as follows:
wherein, I (X) represents the chroma of the image pixel point, A (X) represents the color vector of the image pixel point, Ar(X)、Ag(X)、AbAnd (X) respectively representing the intensity values of RGB channels of the image pixel points.
When a pixel contains only diffuse reflectance components, i.e., β ═ 0, then its chroma value is independent of the strong reflectance weighting factor.
Wherein M (X) represents diffuse reflectance chromaticity, D (X) represents diffuse reflectance color vector, Dr(X)、Dg(X)、Db(X) respectively represent intensity values of the diffuse reflection RGB channels.
Similarly, when a pixel contains only a strong reflection component, i.e., α ═ 0, its chromaticity value is independent of the diffuse reflection weighting factor.
Wherein K (X) represents specular reflection chromaticity, S represents specular reflection color vector, Sr、Sg、SbRespectively, representing the intensity values of the specularly reflected RGB channels.
The chromaticity difference between the high light region and the non-high light region is utilized to detect and mark the high light region, the marked region is subjected to polarized light supplement, and diffuse reflection and light source color vectors are fitted by combining the polarization characteristic difference, so that the suppression of the high light region is realized.
The essence of image enhancement is that the overall and local contrast of an image is improved in a gray scale space within a certain range according to the distribution rule of gray scale values of pixel points of an original image. Meanwhile, the enhanced image is ensured to have better image quality by combining with related algorithms such as visual characteristics of human eyes, noise suppression, maximization of image information entropy, brightness maintenance and the like. FIG. 4 is a diagram illustrating an image enhancement effect according to an embodiment of the present invention.
The method of the self-adaptive bright channel is used for estimation, and the problem that objects with higher brightness can be excessively scratched when the images are reconstructed exists. Aiming at the problem of excessive image matting, the invention utilizes texture information contained in the polarization degree to reconstruct the part which is excessively scratched and whitened by an image enhancement method. As can be seen from the visual characteristics of human eyes, human eyes are more sensitive to local contrast than the contrast of the whole image, and the texture of the polarization degree image is clearer than that of the light intensity image. Therefore, after the reconstructed image is obtained, the polarization degree local index enhancement method is used, the enhancement parameters are calculated for each pixel point based on the neighborhood of each pixel point by using the formula (4) according to the texture distribution of the polarization degree image, and the enhancement parameters are substituted into the formula (5), so that the image after local contrast enhancement is finally obtained. The method solves the problem of excessive image matting of an object with higher brightness in a reconstruction algorithm, and plays a role in highlighting the objects which are hidden in the background but have different polarization characteristics.
The enhancement algorithm is as follows:
for the degree of polarization image DOP (x), the average value of each point in the neighborhood of Ω (x) is taken as
The value of the corresponding point of the image, n isThe enhancement factor takes the value 2. J obtained using this algorithmDOP(x) The image is fused with the texture information of the polarization degree on the basis of the reconstructed image J (x), the image details are enhanced, and the contrast of the target with different polarization characteristics in the image is improved.
And thinning the image information to pixel points, and artificially brightening the image information by matching with simulated secondary supplementary lighting. And obtaining highlight characteristic pixel points and diffuse reflection characteristic pixel points of the target, and analyzing the image by matching a characteristic extraction algorithm to obtain target characteristic information.
In an actual image, each area usually has its own gray distribution characteristic, and the gray distribution in many image areas is macroscopically periodic or structural, and the regularity of this gray distribution in a macroscopic non-strict sense is called image texture. The statistical method generally describes textures by means of a gray level co-occurrence matrix, the co-occurrence matrix is defined by joint probability density of pixels at two positions, and the gray level co-occurrence matrix of one image can reflect comprehensive information of image gray levels about direction, adjacent interval and variation range. If S is a set of pixel pairs having a specific spatial relationship in the feature region R, the co-occurrence matrix P is defined as follows:
in the formula (6), # denotes the number, and the molecules on the right indicate the specific spatial relationship and the gray values are g1And g2The denominator is the sum of the number of pixel pairs. On the basis of the co-occurrence matrix, a texture descriptor of the image can be defined, if the following data are defined:
where i 1,2, and N, j 1,2, a. Angular second moment descriptors.
The second moment is the sum of squares of the gray level co-occurrence matrix pixel values, also called energy, and is a measure of the uniformity of the image gray level distribution. When the value distribution of each P (i, j) is relatively uniform, W1Is small; and W when some P (i, j) values are larger and the rest are smaller1Is relatively large. When the texture is thick as viewed from the entire image, W is present1The value is larger, otherwise W1The value is small. It is understood that coarse textures contain more energy, while fine textures contain less energy.
FIG. 5 is a diagram of a system for extracting images based on a polarizing filter film according to an embodiment of the present invention. As shown in fig. 5, a polarization based filter film extraction imaging system, the system comprising:
a polarization image obtaining module 501, configured to obtain a polarization image of a scene where a filter film exists;
a highlight suppression image obtaining module 502, configured to perform highlight suppression on the polarization image to obtain a highlight suppression image;
an enhanced image obtaining module 503, configured to perform polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image;
and a target characteristic image determining module 504, configured to perform texture description on the enhanced image to obtain a target characteristic image.
The polarization image obtaining module 501 specifically includes:
the polarization subimage acquisition unit is used for acquiring original polarization images of a scene with the filtering film from three different angles;
and the polarized image reconstruction unit is used for constructing a polarized image by adopting a Stokes vector method for the original polarized image.
The highlight suppression image obtaining module 502 specifically includes:
the detection result determining unit is used for carrying out highlight region detection on the polarization image to obtain a highlight region detection result;
the mark determining unit is used for marking according to the detection result of the highlight area to obtain a highlight area mark;
and the highlight inhibition image determining unit is used for obtaining a highlight inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight inhibited polarization image is the highlight inhibition image.
The enhanced image obtaining module 503 specifically includes:
the texture data acquisition unit is used for acquiring polarization degree texture data of the highlight inhibition image;
and the enhanced image determining unit is used for obtaining an enhanced polarized image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarized image is the enhanced image.
The target feature image determining module 504 specifically includes:
a texture descriptor acquiring unit, configured to acquire a texture descriptor of the enhanced image;
and the target texture characteristic image determining unit is used for acquiring a target texture characteristic image according to the texture descriptor.
Compared with the common video monitoring, the invention has the following technical advantages:
(1) has the function of detecting the permeable membrane. The common video monitoring system has no penetrability to the common automobile filtering film in life, and cannot monitor, detect and identify the target shielded by the filtering film. The invention utilizes the polarization characteristic advantage of light to realize the penetrability of the light filtering film and has the capability of penetrating objects behind the car film detection film.
(2) The system has the capability of all-weather monitoring. Under the complicated weather conditions of rain, snow, fog and the like, the common monitoring system cannot achieve the monitoring effect due to poor imaging quality. The invention adopts the polarization imaging technology, can effectively obtain clear images under the complex weather conditions of rain, snow, fog and the like, and has the all-weather monitoring capability.
(3) The device has the capability of monitoring all the day. The invention can work day and night, and can realize day and night monitoring capability by utilizing the principle of polarization inhibition of strong light under the condition of properly supplementing light to a target at night, thereby effectively improving the membrane permeation efficiency at night.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method for extracting images by using a polarization-based filter film is characterized by comprising the following steps:
obtaining a polarization image of a scene with a filtering film;
highlight inhibition is carried out on the polarization image to obtain a highlight inhibition image;
carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image;
and carrying out texture description on the enhanced image to obtain a target characteristic image.
2. The method for extracting an image through a polarization-based filter film according to claim 1, wherein the obtaining of the polarization image of the scene with the filter film specifically comprises:
collecting original polarization images of a scene with a light filtering film from three different angles;
and constructing a polarization image by adopting a Stokes vector method for the original polarization image.
3. The method for extracting an image through a polarization-based filter film according to claim 1, wherein the highlight suppression is performed on the polarized image to obtain a highlight-suppressed image, and specifically comprises:
performing highlight region detection on the polarization image to obtain a highlight region detection result;
marking according to the detection result of the highlight area to obtain a highlight area mark;
and obtaining a highlight-inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight-inhibited polarization image is the highlight-inhibited image.
4. The method for extracting an image through a polarization-based filter film according to claim 1, wherein the polarization degree enhancement calculation is performed on the highlight inhibition image to obtain an enhanced image, and specifically comprises:
acquiring polarization degree texture data of the highlight inhibition image;
and obtaining an enhanced polarization image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarization image is the enhanced image.
5. The method according to claim 1, wherein the texture description is performed on the enhanced image to obtain a target feature image, and the target feature image is an image extracted under the filter film, and specifically includes:
acquiring a texture descriptor of the enhanced image;
and acquiring a target texture feature image according to the texture descriptor.
6. A polarization based filter film extraction imaging system, comprising:
the polarized image acquisition module is used for acquiring a polarized image of a scene with the filtering film;
the highlight inhibition image acquisition module is used for carrying out highlight inhibition on the polarization image to obtain a highlight inhibition image;
the enhanced image acquisition module is used for carrying out polarization degree enhancement calculation on the highlight inhibition image to obtain an enhanced image;
and the target characteristic image determining module is used for performing texture description on the enhanced image to obtain a target characteristic image.
7. The polarization-based filter film extraction imaging system of claim 6, wherein the polarization image acquisition module specifically comprises:
the polarization subimage acquisition unit is used for acquiring original polarization images of a scene with the filtering film from three different angles;
and the polarized image reconstruction unit is used for constructing a polarized image by adopting a Stokes vector method for the original polarized image.
8. The polarization-based filter film extraction imaging system of claim 6, wherein the high light rejection image capture module comprises:
the detection result determining unit is used for carrying out highlight region detection on the polarization image to obtain a highlight region detection result;
the mark determining unit is used for marking according to the detection result of the highlight area to obtain a highlight area mark;
and the highlight inhibition image determining unit is used for obtaining a highlight inhibited polarization image by adopting a polarization light supplementing method according to the highlight region mark, wherein the highlight inhibited polarization image is the highlight inhibition image.
9. The polarization-based filter film extraction imaging system of claim 6, wherein the enhanced image acquisition module comprises:
the texture data acquisition unit is used for acquiring polarization degree texture data of the highlight inhibition image;
and the enhanced image determining unit is used for obtaining an enhanced polarized image by adopting an enhancement algorithm on the polarization degree texture data, wherein the enhanced polarized image is the enhanced image.
10. The polarization-based filter film extraction imaging system of claim 6, wherein the target feature image determination module specifically comprises:
a texture descriptor acquiring unit, configured to acquire a texture descriptor of the enhanced image;
and the target texture characteristic image determining unit is used for acquiring a target texture characteristic image according to the texture descriptor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911199318.6A CN110889810A (en) | 2019-11-29 | 2019-11-29 | Method and system for extracting image through light filtering film based on polarization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911199318.6A CN110889810A (en) | 2019-11-29 | 2019-11-29 | Method and system for extracting image through light filtering film based on polarization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110889810A true CN110889810A (en) | 2020-03-17 |
Family
ID=69749420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911199318.6A Pending CN110889810A (en) | 2019-11-29 | 2019-11-29 | Method and system for extracting image through light filtering film based on polarization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110889810A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114167602A (en) * | 2021-12-10 | 2022-03-11 | 中国科学院长春光学精密机械与物理研究所 | Mueller matrix-based polarization characteristic analysis method for optical lens after film coating |
| CN115612765A (en) * | 2022-10-14 | 2023-01-17 | 合肥视展光电科技有限公司 | Real-time detection control method and system for state of blast furnace taphole |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743758A (en) * | 2014-01-15 | 2014-04-23 | 唐山英莱科技有限公司 | Visual inspection system for high-reflective metal surface based on cross-polarization |
| CN105678713A (en) * | 2016-02-03 | 2016-06-15 | 哈尔滨理工大学 | Highlight removing method based on linear diffusion plate and reflection component separation theory |
| CN105741249A (en) * | 2016-02-03 | 2016-07-06 | 哈尔滨理工大学 | Highlight removal method for high reflective surface |
| CN106033599A (en) * | 2015-03-20 | 2016-10-19 | 南京理工大学 | Visible light enhancement method based on polarized imaging |
| CN107607040A (en) * | 2017-08-11 | 2018-01-19 | 天津大学 | A kind of three-dimensional scanning measurement device and method suitable for High Reflective Surface |
| CN110425983A (en) * | 2019-07-26 | 2019-11-08 | 杭州电子科技大学 | A kind of monocular vision three-dimensional reconstruction distance measuring method based on polarization multi-spectrum |
-
2019
- 2019-11-29 CN CN201911199318.6A patent/CN110889810A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743758A (en) * | 2014-01-15 | 2014-04-23 | 唐山英莱科技有限公司 | Visual inspection system for high-reflective metal surface based on cross-polarization |
| CN106033599A (en) * | 2015-03-20 | 2016-10-19 | 南京理工大学 | Visible light enhancement method based on polarized imaging |
| CN105678713A (en) * | 2016-02-03 | 2016-06-15 | 哈尔滨理工大学 | Highlight removing method based on linear diffusion plate and reflection component separation theory |
| CN105741249A (en) * | 2016-02-03 | 2016-07-06 | 哈尔滨理工大学 | Highlight removal method for high reflective surface |
| CN107607040A (en) * | 2017-08-11 | 2018-01-19 | 天津大学 | A kind of three-dimensional scanning measurement device and method suitable for High Reflective Surface |
| CN110425983A (en) * | 2019-07-26 | 2019-11-08 | 杭州电子科技大学 | A kind of monocular vision three-dimensional reconstruction distance measuring method based on polarization multi-spectrum |
Non-Patent Citations (3)
| Title |
|---|
| 于晓洋等: "反射分量分离与像素填补结合的高光抑制方法", 《哈尔滨理工大学学报》 * |
| 宋强: "基于偏振信息的水下图像复原方法", 《中国优秀硕士学位论文全文数据库》 * |
| 李芳: "基于偏振光原理的图像高光消除方法", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114167602A (en) * | 2021-12-10 | 2022-03-11 | 中国科学院长春光学精密机械与物理研究所 | Mueller matrix-based polarization characteristic analysis method for optical lens after film coating |
| CN115612765A (en) * | 2022-10-14 | 2023-01-17 | 合肥视展光电科技有限公司 | Real-time detection control method and system for state of blast furnace taphole |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4563513B2 (en) | Image processing apparatus and pseudo-stereoscopic image generation apparatus | |
| Schechner et al. | Clear underwater vision | |
| CN106548467B (en) | The method and device of infrared image and visual image fusion | |
| Fattal | Dehazing using color-lines | |
| Schettini et al. | Underwater image processing: state of the art of restoration and image enhancement methods | |
| Wang et al. | Underwater image restoration via maximum attenuation identification | |
| Artusi et al. | A survey of specularity removal methods | |
| US8396319B2 (en) | Separation and contrast enhancement of overlapping cast shadow components and target detection in shadow using polarization | |
| US20110043603A1 (en) | System And Method For Dehazing | |
| Tripathi et al. | Removal of fog from images: A review | |
| Yang et al. | Underwater polarimetric imaging for visibility enhancement utilizing active unpolarized illumination | |
| CN102901489B (en) | Surface gathered water accumulated ice detection method and device | |
| WO2005076736A2 (en) | Enhanced underwater imaging | |
| WO2006073450A3 (en) | Polarization and reflection based non-contact latent fingerprint imaging and lifting | |
| Raskar et al. | Computational photography | |
| CN113554575B (en) | High-reflection object surface highlight removing method based on polarization principle | |
| CN103617617A (en) | Underwater image quality evaluating and measuring method based on power spectrum description | |
| CN109886883A (en) | Real-time polarization fog-penetrating imaging image enhancement processing method | |
| CN110889810A (en) | Method and system for extracting image through light filtering film based on polarization | |
| Asmare et al. | Image Enhancement by Fusion in Contourlet Transform. | |
| Chen et al. | Weighted sparse representation and gradient domain guided filter pyramid image fusion based on low-light-level dual-channel camera | |
| Fang et al. | Image quality assessment on image haze removal | |
| Wang et al. | Specular reflection removal of ocean surface remote sensing images from UAVs | |
| CN117350925A (en) | Inspection image infrared visible light image fusion method, device and equipment | |
| Al-Zubaidy et al. | Removal of atmospheric particles in poor visibility outdoor 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: 20200317 |