CN111553953B - System and method for calibrating pseudo color of night vision device - Google Patents
System and method for calibrating pseudo color of night vision device Download PDFInfo
- Publication number
- CN111553953B CN111553953B CN202010327905.5A CN202010327905A CN111553953B CN 111553953 B CN111553953 B CN 111553953B CN 202010327905 A CN202010327905 A CN 202010327905A CN 111553953 B CN111553953 B CN 111553953B
- Authority
- CN
- China
- Prior art keywords
- pseudo
- color
- image
- scene
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/55—Optical parts specially adapted for electronic image sensors; Mounting thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The pseudo-color calibration system of the night vision device comprises: the image acquisition unit is used for acquiring an image sample group and a display image, and the difference among image samples in the image sample group is kept; the processing unit is connected with the image acquisition unit and used for acquiring a pseudo color display image, and the processing unit comprises a background marking unit, a scene recognition unit and a pseudo color calling unit. The pseudo-color calibration method for the night vision device comprises the following steps: step one, an image acquisition unit acquires an image sample group; marking a specific background of the image sample in the image sample group by the processing unit to obtain a scene recognition model; step three, an image acquisition unit acquires a display image; and step four, the processing unit acquires a pseudo color display image. The system and the method for calibrating the pseudo-color of the night vision device realize the high-fidelity color display of multi-scene pseudo-color and solve the problem of the pseudo-color display distortion of the night vision device.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a night vision device pseudo-color calibration system and method.
Background
The prior commonly used night vision device mainly comprises three types, namely single glimmer, single infrared and integrated glimmer and infrared functions, and the three types of products have certain limitations in the use process due to the performance characteristics of glimmer or infrared devices.
In particular, in the output image, color images cannot be formed due to insufficient illuminance or the like, and only gray-scale images or even dark images can be formed. For forming a color image, means such as light supplement must be used, for example, a flash lamp is used, but not all scenes are used.
At the present stage, pseudo color calibration is also provided, the light energy intensity is corresponding to the color information, and color image output basically conforming to human eyes sense is realized through pseudo color display. Although the method can be used for the night vision device, when the using scene is inconsistent with the calibration scene, the color difference between the pseudo color display and the actual scene is too large, the color characteristics of the real scene are not met, and the human eyes are not comfortable.
Therefore, the problems of the prior art are to be further improved and developed.
Disclosure of Invention
The object of the invention is: in order to solve the problems in the prior art, the invention aims to provide a multi-scene pseudo color calibration and self-adaptive scene pseudo color output system and method for a night vision device.
The technical scheme is as follows: in order to solve the above technical problem, the present technical solution provides a pseudo-color calibration system for a night vision device, including:
the image acquisition unit is used for acquiring an image sample group and a display image, and the difference among image samples in the image sample group is kept;
the processing unit is connected with the image acquisition unit and comprises a background marking unit, a scene recognition unit and a pseudo color calling unit; the background marking unit is used for marking the specific background of the image sample in the image sample group and acquiring a scene recognition model; the scene identification unit is used for identifying a specific scene of the display image; and the pseudo color calling unit corresponds the gray value of the display image with the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain the pseudo color display image.
The night vision device pseudo-color calibration system is characterized in that the image samples are divided into different image sample groups according to specific backgrounds, and the number of the image samples in each image sample group is larger than or equal to 3000.
The night vision device pseudo-color calibration system comprises a background marking unit, a background detection unit and a scene acquisition unit, wherein the background marking unit comprises a marking module and a scene acquisition module, and the marking module marks the background of each image sample; the scene acquisition module inputs the image sample into the deep learning training model and acquires a scene recognition model of the background corresponding to the image sample.
The night vision device pseudo color calibration system is characterized in that the pseudo color calling unit comprises a gray level reading module, a scene pseudo color selection module and an image fusion module,
the gray scale reading module is used for reading gray scale values of the display images; the scene pseudo color selection module selects a pseudo color table according to a specific scene of a display image; and the image fusion module corresponds to the RGB color values of the display image according to the gray value of the display image in the pseudo color table, and writes the RGB color values corresponding to the display image into the display image to obtain the pseudo color display image.
The night vision device pseudo-color calibration system further comprises a pseudo-color display unit, wherein the pseudo-color display unit is connected with the processing unit and used for displaying a pseudo-color display image.
The pseudo-color calibration system of the night vision device further comprises a storage unit, wherein the storage unit is respectively connected with the image acquisition unit and the processing unit;
the storage unit comprises a sample storage module and a display storage module, wherein the sample storage module is used for storing a scene recognition model and an image sample; the display storage module is used for storing display images and pseudo color display images.
The night vision device pseudo color calibration system further comprises a data input unit, wherein the data input unit is connected with the storage unit, and the data input unit inputs a pseudo color table with gray values corresponding to RGB color values in a specific background.
The pseudo-color calibration system of the night vision device further comprises a power supply, wherein the power supply is connected with the processing unit and used for providing electric energy.
The pseudo-color calibration method for the night vision device comprises the following steps:
firstly, an image acquisition unit acquires an image sample group, wherein image samples in the image sample group directly keep difference;
marking a specific background of the image sample in the image sample group by the processing unit to obtain a scene recognition model;
step three, an image acquisition unit acquires a display image;
and fourthly, identifying the specific scene of the display image by the processing unit, and corresponding the gray value of the display image with the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain a pseudo color display image.
The night vision device pseudo-color calibration method comprises the following steps that a marking module marks the background of each image sample; the scene obtaining module inputs the image sample into the deep learning training model and obtains a scene recognition model of the background corresponding to the image sample.
(III) the beneficial effects are as follows: the invention provides a night vision device pseudo color calibration system and method, which adopt a background scene identification model to perform autonomous identification of a using scene, thereby loading pseudo color calibration parameters of a corresponding scene, realizing high-fidelity color display of multi-scene pseudo colors and solving the problem of pseudo color display distortion of a night vision device.
Drawings
FIG. 1 is a schematic diagram of the connection relationship of a pseudo-color calibration system of a night vision device according to the present invention;
FIG. 2 is a schematic diagram of the steps of the pseudo-color calibration method of the night vision device according to the invention.
Detailed Description
The present invention will be described in further detail with reference to preferred embodiments, and more details are set forth in the following description in order to provide a thorough understanding of the present invention, but it is apparent that the present invention can be embodied in many other forms different from the description herein and can be similarly generalized and deduced by those skilled in the art based on the practical application without departing from the spirit of the present invention, and therefore, the scope of the present invention should not be limited by the contents of this detailed embodiment.
The drawings are schematic representations of embodiments of the invention, and it is noted that the drawings are intended only as examples and are not drawn to scale and should not be construed as limiting the true scope of the invention.
As shown in fig. 2, the pseudo-color calibration method for night vision device includes:
firstly, an image acquisition unit acquires an image sample group, wherein image samples in the image sample group directly keep difference;
marking a specific background of the image sample in the image sample group by the processing unit to obtain a scene recognition model;
step three, an image acquisition unit acquires a display image;
and fourthly, identifying the specific scene of the display image by the processing unit, and corresponding the gray value of the display image with the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain a pseudo color display image.
The second step specifically comprises: the marking module marks the background of each image sample; the scene obtaining module inputs the image sample into the deep learning training model and obtains a scene recognition model of the background corresponding to the image sample.
The night vision device pseudo color calibration method further comprises a fifth step of displaying a pseudo color display image by the pseudo color display unit.
As shown in fig. 1, the pseudo-color calibration system for night vision device includes: the device comprises an image acquisition unit, a processing unit, a storage unit, a pseudo color display unit, a data input unit and a power supply.
The image acquisition unit may be a night vision lens for acquisition of the image sample set and the display image. The image samples are divided into different image sample groups according to specific backgrounds, and the number of the image samples in each image sample group is more than or equal to 3000. The set of image samples needs to cover the entire scene of the displayed image, and the difference between the image samples in the set of image samples is maintained. The display image is a target image displayed in pseudo color.
The processing unit is connected with the image acquisition unit and comprises a background marking unit, a scene recognition unit and a pseudo color calling unit.
The background marking unit is used for marking the specific background of the image samples in the image sample group and acquiring the scene recognition model. Specifically, the background marking unit comprises a marking module and a scene acquisition module.
The marking module marks the background of each image sample; the scene acquisition module inputs the image sample into the deep learning training model and acquires a scene recognition model of the background corresponding to the image sample.
And the scene identification unit is used for identifying a specific scene of the display image so as to acquire the RGB color values of the corresponding scene.
And the pseudo color calling unit corresponds the gray value of the display image with the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain the pseudo color display image. Specifically, the pseudo color calling unit comprises a gray level reading module, a scene pseudo color selection module and an image fusion module.
The gray scale reading module is used for reading gray scale values of the display images; the scene pseudo color selection module selects a pseudo color table according to a specific scene of a display image; and the image fusion module corresponds to the RGB color values of the display image according to the gray value of the display image in the pseudo color table, and writes the RGB color values corresponding to the display image into the display image to obtain the pseudo color display image.
The pseudo color display unit may include a display driving circuit, a projection chip, and an eyepiece, and the specific structure of the pseudo color display unit is not particularly limited. It should be noted that the pseudo color display unit is connected to the processing unit, and is used for displaying a pseudo color display image, or directly displaying a display image.
The storage unit is respectively connected with the image acquisition unit and the processing unit and is used for storing an image sample, a scene recognition model, a pseudo color table with gray values corresponding to RGB color values, a display image, a pseudo color display image and the like. Specifically, the storage unit comprises a sample storage module and a display storage module.
The sample storage module is used for storing data related to the image sample, such as the image sample, a scene recognition model, a pseudo color table with gray values corresponding to RGB color values and the like; the display storage module is used for storing display images, pseudo color display images and the like.
The data input unit is connected with the storage unit and used for inputting the pseudo color table corresponding to the gray value and the RGB color value under a specific background, and can also be used for inputting the deep learning training model and selecting a specific deep learning frame.
The power supply may be an external power supply or a built-in power supply, or may be set simultaneously with the external power supply and the built-in power supply, and is not limited specifically here. It should be noted that the power supply is connected with the processing unit to provide electric energy for the pseudo-color calibration system of the night vision device, so as to ensure the normal operation of the pseudo-color calibration system of the vision device.
The night vision device pseudo color calibration system and method adopts a background scene identification model to perform autonomous identification of a use scene, so as to load pseudo color calibration parameters of a corresponding scene, realize high-fidelity color display of multi-scene pseudo colors, and solve the problem of pseudo color display distortion of a night vision device.
The following is a description by combining the specific implementation steps of the pseudo-color calibration system of the night vision device:
the night vision instrument pseudo-color calibration system is placed in different scenes, the image acquisition unit shoots not less than 3000 image samples for different scenes of each scene, for example, 3000 images are acquired in a field forest background, and 3000 images are acquired in a city background.
The storage unit stores the image sample in the sample storage module, and is used for comparing and calling the original image of the image sample when a user inputs the pseudo color table corresponding to the gray value and the RGB color value.
The marking module performs background marking on each image sample.
The scene acquisition module inputs the image sample into the deep learning training model, and the scene recognition model corresponding to the background is trained through the background marked by the marking module on the image sample. The more framing of the scene participating in the training image sample, the more the number of pictures is, and the higher the scene recognition rate of the scene recognition model is.
The method is not limited to one type, marked picture samples can be input in deep learning, the samples need to meet a certain quantity and difference, an identification model is generated through learning operation according to a marked value, and the picture type can be quickly judged through the identification model in the using process.
The deep learning model can generate appropriate parameters through adaptive adjustment of parameters among the neural networks, the parameters and the neural networks form the model, the parameters cover but are not limited to texture and brightness information, the deep learning does not specify the meaning covered by the parameters, and the input and the selection of a user are not required.
In a target scene of the night vision device pseudo-color calibration system, the image acquisition unit shoots the target scene to acquire a display image.
Aiming at each different scene, performing pseudo-color calibration: the scene recognition unit recognizes a specific scene of a display image; the gray scale reading module reads the gray scale value of the display image; the scene pseudo color selection module selects a pseudo color table according to a specific scene of a display image; the image fusion module corresponds the gray value of the display image to the pseudo color table of the scene specifically corresponding to the display image to obtain the RGB color value of the display image corresponding to the gray value of the display image, and then writes the RGB color value corresponding to the display image into the display image to obtain the pseudo color display image. The pseudo color table with gray values corresponding to the RGB color values may be written manually.
For example, according to a forest background picture, according to the gray value of the image acquisition unit, a pseudo color table with the gray value corresponding to the RGB color value is manually written, the writing standard takes human eye sense as a standard, namely in the forest background, after the pseudo color display image is displayed, human eyes feel that the picture color information is basically consistent with the real forest color.
And storing a scene recognition model (training model) and a pseudo color table of a corresponding scene into the sample storage module. After the image acquisition module generates a gray value of an actual scene of a display image, the scene recognition module firstly judges the display image of the actual scene through a scene recognition model, judges whether the scene is a forest background, an urban background or other trained backgrounds, and calls a pseudo color table stored in the corresponding background according to the judged background. (ii) a And the image fusion module corresponds to the RGB color values of the display image according to the gray value of the display image in the pseudo color table, and writes the RGB color values corresponding to the display image into the display image to obtain the pseudo color display image.
The pseudo color display unit obtains a pseudo color display image and performs pseudo color display.
The image acquisition unit comprises a visible light shooting module, and the sample image correspondingly shoots the color sample. The night vision device pseudo-color calibration system also comprises a pseudo-color corresponding unit, wherein the pseudo-color corresponding unit is used for acquiring the sample image and the corresponding color sample pseudo-color data, comparing the same background pseudo-color data and selecting the best pseudo-color data. The selection of the pseudo color data may be an averaging, or may be based on other calculation methods, which is not limited herein. The night vision instrument pseudo-color calibration system further ensures the authenticity of colors of pseudo-color display images by acquiring pseudo-color data of actual sample images and corresponding color samples.
The shot color sample corresponding to the sample image has a time label and/or a weather condition label, and the time label comprises: the year-month-day-time information, the shooting color samples are set according to the time labels, and the images of the shooting time of the night vision device can be calculated more closely. The shooting color sample of the invention also has the weather label comprising the weather conditions in different time periods corresponding to the time label information: including information such as yin, sunny, rain, snow, fog, humidity, temperature, etc.
The night vision device pseudo-color calibration system comprises a time module and a weather identification module, when scene identification is carried out, time information and weather conditions on a night vision device system need to be input, and according to the time information and the weather conditions on the night vision device system, through machine learning, the most vivid color reappearance is given to pictures displayed by the night vision device, and the most vivid color reappearance comprises the color types of images and the brightness, the tone and the saturation of the images.
The pseudo color corresponding unit of the night vision device pseudo color calibration system also comprises an image processing module which comprises an amplifying block and a reducing block. The amplifying block is used for amplifying the shot image to the multiple of the threshold value, enabling the scene pixels in the amplified shot image to be in one-to-one correspondence with the pixels in the scene picture obtained through the depth learning, and then conducting one-to-one correspondence supplement on the pixel colors in the shot picture according to the colors in the scene picture obtained through the depth learning. And finally, the zooming-out module zooms out the zoomed-in shot picture to the actual size according to the threshold value for display.
The pseudo-color corresponding unit also comprises an image processing module, so that the picture precision of the picture shot by the pseudo-color calibration system of the night vision device can be improved, and the picture shot by the night vision device is not blurred any more, but is more precise and vivid.
The pseudo-color calibration system of the night vision device also comprises a user emotion recognition system, wherein a fingerprint recognition module and a grip strength recognition module are arranged on the night vision device, and the information of the fingerprint recognition module and the grip strength recognition module is sent to a server. The server can identify the user information of the night vision device according to the fingerprint identification module, and analyzes the emotion of the user according to the strength information and the time information of the grip strength identification module. A first grip value of the single user in a first time period is smaller, and the first grip value represents that the emotion of the user is relaxed; the single user has a high second grip value within a second time period, identifying that the user is more nervous in mood; and the change frequency of the third grip strength value of the single user in the third time period exceeds a second threshold value, and the emotional comparative anxiety of the user is identified.
According to the invention, the emotion of the user identified by the night vision device is associated with the pseudo-color corresponding unit by the image processing module, and the color tone value provided for the scene picture is increased to the third threshold value in the time period when the emotion of the user is relaxed, so that the user experience is more bright and faster; in a time period when the emotion of the user is tense, the color tone provided for the scene picture reaches a fourth threshold value, and the more cool tone is used to calm down the emotion of the user; and in the time period that the emotion of the user is more anxious, the color tone provided for the scene picture reaches a fifth threshold value, and a warmer tone is used to relieve the emotion of the user.
The night vision instrument pseudo color calibration system is used for respectively calibrating pseudo colors of images in various specific use scenes such as cities, forests, deserts, oceans and the like, forming a scene recognition model according to texture distribution and brightness distribution characteristics of each scene through a deep learning algorithm, and carrying out autonomous identification on the use scenes by adopting the scene recognition model, so that pseudo color calibration parameters of the corresponding scenes are loaded, and high-fidelity color reproduction of the pseudo colors is realized.
The above description is provided for the purpose of illustrating the preferred embodiments of the present invention and will assist those skilled in the art in more fully understanding the technical solutions of the present invention. However, these examples are merely illustrative, and the embodiments of the present invention are not to be considered as being limited to the description of these examples. For those skilled in the art to which the invention pertains, several simple deductions and changes can be made without departing from the inventive concept, and all should be considered as falling within the protection scope of the invention.
Claims (10)
1. The pseudo-color calibration system of the night vision device is characterized by comprising:
the image acquisition unit is used for acquiring an image sample group and a display image, and the difference among image samples in the image sample group is kept;
the processing unit is connected with the image acquisition unit and comprises a background marking unit, a scene recognition unit and a pseudo color calling unit; the background marking unit is used for marking the specific background of the image sample in the image sample group and acquiring a scene recognition model; the scene identification unit is used for identifying a specific scene of the display image; the pseudo color calling unit corresponds the gray value of the display image with the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain a pseudo color display image;
the night vision device also comprises a user emotion recognition system, wherein a grip strength recognition module is arranged on the night vision device;
analyzing the emotion of the user according to the strength information and the time information of the grip strength identification module;
a first grip value of a single user within a first time period representing emotional relaxation of the user; a second grip value of the single user over a second time period identifying an emotional tension of the user; the change frequency of a third grip strength value of the single user in a third time period exceeds a second threshold value, and emotional anxiety of the user is identified;
within a time period when the emotion of the user is relaxed, the color tone value provided for the scene picture is increased to a third threshold value; in the time period of emotional tension of the user, the color tone provided for the scene picture is adjusted to a fourth threshold value, and a cool tone is used; during the period of emotional anxiety of the user, the color tone provided for the scene picture is adjusted to the fifth threshold value, and a warm tone is used.
2. The pseudo-color calibration system for night vision device as claimed in claim 1, wherein the image samples are divided into different image sample groups according to specific backgrounds, and the number of the image samples in each image sample group is greater than or equal to 3000.
3. The pseudo-color calibration system for night vision devices as claimed in claim 1, wherein the background marking unit comprises a marking module and a scene acquisition module, the marking module marking the background of each image sample; the scene acquisition module inputs the image sample into the deep learning training model and acquires a scene recognition model of the background corresponding to the image sample.
4. The pseudo-color calibration system of night vision device as claimed in claim 1, wherein the pseudo-color calling unit comprises a gray scale reading module, a scene pseudo-color selecting module, an image fusion module,
the gray scale reading module is used for reading gray scale values of the display images; the scene pseudo color selection module selects a pseudo color table according to a specific scene of a display image; and the image fusion module corresponds to the RGB color values of the display image according to the gray value of the display image in the pseudo color table, and writes the RGB color values corresponding to the display image into the display image to obtain the pseudo color display image.
5. The pseudo-color calibration system for night vision devices as claimed in claim 1, further comprising a pseudo-color display unit connected to the processing unit for displaying a pseudo-color display image.
6. The pseudo-color calibration system for night vision devices as claimed in claim 1, further comprising a storage unit, wherein the storage unit is connected to the image acquisition unit and the processing unit respectively;
the storage unit comprises a sample storage module and a display storage module, wherein the sample storage module is used for storing a scene recognition model and an image sample; the display storage module is used for storing display images and pseudo color display images.
7. The pseudo-color calibration system for night vision devices as claimed in claim 1, further comprising a data input unit, wherein the data input unit is connected to the storage unit, and the data input unit inputs a pseudo-color table with gray values corresponding to RGB color values in a specific background.
8. The night vision device pseudo-color calibration system as claimed in claim 1, further comprising a power supply connected to the processing unit for providing electrical power.
9. The pseudo-color calibration method for the night vision device comprises the following steps:
firstly, an image acquisition unit acquires an image sample group, and differences among image samples in the image sample group are kept;
marking a specific background of the image sample in the image sample group by the processing unit to obtain a scene recognition model;
step three, an image acquisition unit acquires a display image;
identifying a specific scene of the display image by the processing unit, and corresponding the gray value of the display image to the RGB color value according to the identified pseudo color table of the specific scene of the display image to obtain a pseudo color display image;
analyzing the emotion of the user according to the strength information and the time information of the grip strength identification module;
a first grip value of a single user within a first time period representing emotional relaxation of the user; a second grip value of the single user over a second time period identifying an emotional tension of the user; the change frequency of a third grip strength value of the single user in a third time period exceeds a second threshold value, and emotional anxiety of the user is identified;
within a time period when the emotion of the user is relaxed, the color tone value provided for the scene picture is increased to a third threshold value; in the time period of emotional tension of the user, the color tone provided for the scene picture is adjusted to a fourth threshold value, and a cool tone is used; during the period of emotional anxiety of the user, the color tone provided for the scene picture is adjusted to the fifth threshold value, and a warm tone is used.
10. The pseudo-color calibration method for night vision device as claimed in claim 9, wherein the second step specifically comprises the steps of marking the background of each image sample by a marking module; the scene obtaining module inputs the image sample into the deep learning training model and obtains a scene recognition model of the background corresponding to the image sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010327905.5A CN111553953B (en) | 2020-04-23 | 2020-04-23 | System and method for calibrating pseudo color of night vision device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010327905.5A CN111553953B (en) | 2020-04-23 | 2020-04-23 | System and method for calibrating pseudo color of night vision device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553953A CN111553953A (en) | 2020-08-18 |
| CN111553953B true CN111553953B (en) | 2020-12-11 |
Family
ID=72005825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010327905.5A Active CN111553953B (en) | 2020-04-23 | 2020-04-23 | System and method for calibrating pseudo color of night vision device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553953B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899558A (en) * | 2015-05-25 | 2015-09-09 | 东华大学 | Scene recognition and colorization processing method for vehicle-mounted infrared image |
| CN106096542A (en) * | 2016-06-08 | 2016-11-09 | 中国科学院上海高等研究院 | Image/video scene recognition method based on range prediction information |
| CN106815826A (en) * | 2016-12-27 | 2017-06-09 | 上海交通大学 | Night vision image Color Fusion based on scene Recognition |
| CN109274945A (en) * | 2018-09-29 | 2019-01-25 | 合刃科技（深圳）有限公司 | A kind of adaptive method and system for carrying out the reduction of image true color |
| CN110651301A (en) * | 2017-05-24 | 2020-01-03 | 黑拉有限责任两合公司 | Method and system for automatically coloring night vision images |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006052260B3 (en) * | 2006-11-03 | 2008-07-17 | Duong, Gilbert, Dr. | Hand-operated pushing device |
| CN104346074A (en) * | 2014-10-23 | 2015-02-11 | 深圳市金立通信设备有限公司 | Terminal |
| US20180101776A1 (en) * | 2016-10-12 | 2018-04-12 | Microsoft Technology Licensing, Llc | Extracting An Emotional State From Device Data |
| CN110377380A (en) * | 2019-06-21 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Theme hue adjusting method, device, equipment and computer readable storage medium |
| CN110471534B (en) * | 2019-08-23 | 2022-11-04 | 靖江市人民医院 | Information processing method based on emotion recognition and remote medical management system |
-
2020
- 2020-04-23 CN CN202010327905.5A patent/CN111553953B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899558A (en) * | 2015-05-25 | 2015-09-09 | 东华大学 | Scene recognition and colorization processing method for vehicle-mounted infrared image |
| CN106096542A (en) * | 2016-06-08 | 2016-11-09 | 中国科学院上海高等研究院 | Image/video scene recognition method based on range prediction information |
| CN106815826A (en) * | 2016-12-27 | 2017-06-09 | 上海交通大学 | Night vision image Color Fusion based on scene Recognition |
| CN110651301A (en) * | 2017-05-24 | 2020-01-03 | 黑拉有限责任两合公司 | Method and system for automatically coloring night vision images |
| CN109274945A (en) * | 2018-09-29 | 2019-01-25 | 合刃科技（深圳）有限公司 | A kind of adaptive method and system for carrying out the reduction of image true color |
Non-Patent Citations (1)
| Title |
|---|
| progress in color night vision;Alexandar Toet;《optical engineering》;20120206;第1-20页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553953A (en) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104063846B (en) | Method and apparatus for handling image based on the information detected | |
| CN104240674B (en) | A kind of method regulating display unit and a kind of electronic equipment | |
| EP2767215A1 (en) | Endoscope apparatus and control method thereof | |
| CN107396079B (en) | White balance adjustment method and device | |
| CN107172354A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
| US20170154437A1 (en) | Image processing apparatus for performing smoothing on human face area | |
| CN113240112A (en) | Screen display adjusting method and device, electronic equipment and storage medium | |
| CN107909638A (en) | Rendering intent, medium, system and the electronic equipment of dummy object | |
| US11087700B1 (en) | System and method for image enhancement on a digital display device | |
| CN113191938B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN104869319B (en) | Image treatment method and image processor | |
| CN109035147A (en) | Image processing method and device, electronic device, storage medium and computer equipment | |
| CN111541937B (en) | Image quality adjusting method, television device and computer storage medium | |
| CN117746806B (en) | Driving method, device, equipment and storage medium of mini LED backlight module | |
| CN107920205A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN111127367A (en) | Method, device and system for processing face image | |
| WO2016078440A1 (en) | Method and apparatus for controlling screen of mobile terminal | |
| CN112788254B (en) | Camera image matting method, device, equipment and storage medium | |
| CN111553953B (en) | System and method for calibrating pseudo color of night vision device | |
| CN111275648B (en) | Face image processing method, device, equipment and computer readable storage medium | |
| CN109410308A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| US11410622B2 (en) | Display method and device, and storage medium | |
| CN109447927A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN114255193A (en) | Board card image enhancement method, device, equipment and readable storage medium | |
| CN115471887A (en) | Double-shot face recognition method, device and medium without white light fill-in lamp |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 100094 room 901, 9 / F, building 4, zone 1, 81 Beiqing Road, Haidian District, Beijing Patentee after: Guoke Tiancheng Technology Co.,Ltd. Address before: 10 / F, block A3, No.1 Zhongguancun, No.81 Beiqing Road, Haidian District, Beijing 100094 Patentee before: TEEMSUN (BEIJING) TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |