CN112185126A - Method, device and equipment for determining polarization angle - Google Patents
Method, device and equipment for determining polarization angle Download PDFInfo
- Publication number
- CN112185126A CN112185126A CN202011031110.6A CN202011031110A CN112185126A CN 112185126 A CN112185126 A CN 112185126A CN 202011031110 A CN202011031110 A CN 202011031110A CN 112185126 A CN112185126 A CN 112185126A
- Authority
- CN
- China
- Prior art keywords
- target
- angle
- polarizer
- polarization
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method, a device and equipment for determining a polarization angle, wherein the method comprises the following steps: controlling a camera to acquire an initial image of a calibrated vehicle under the condition that a polarizer is at a plurality of polarization angles; when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in a calibrated vehicle and a reference image of the target object; selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum; the polarizer is adjusted to the target polarization angle. Through the technical scheme, the optimal polarization angle of the polarizer is adjusted in a self-adaptive mode according to the scene environment, the requirement for detecting the face in the vehicle is met, and the influence of rainbow lines on the face in the vehicle is relieved to the maximum extent.
Description
Technical Field
The application relates to the field of intelligent traffic, in particular to a method, a device and equipment for determining a polarization angle.
Background
In the field of intelligent transportation, an original image of a vehicle passing through a scene needs to be acquired, a face subimage is recognized from the original image, and a user to which a face in the vehicle belongs is recognized based on the face subimage. However, because the face is located in the vehicle, the outside of the vehicle usually has a vehicle film, and the vehicle film can generate rainbow lines on the vehicle window under natural light, thereby affecting the definition of the face in the vehicle, resulting in the reduction of the definition of the face subimages, and being unable to accurately identify which user the face in the vehicle belongs to based on the face subimages.
In order to reduce the influence of rainbow texture, a polarizer is disposed in the camera, and the influence of rainbow texture is reduced by using the polarizer. However, when the camera leaves the factory, the polarization angle of the polarizer is already fixed, that is, the polarization angle of the polarizer is not adjusted, and in all scenes, the polarization angle of the polarizer is a fixed angle, so that the polarizer cannot meet the actual requirements of all scenes. In some scenes, the effect of using the polarizer to reduce the rainbow texture may be poor, and the effect of the rainbow texture still cannot be effectively reduced.
Disclosure of Invention
The application provides a method for determining a polarization angle, wherein a camera and a calibration vehicle are deployed in a target scene, the camera comprises a polarizer, and the method comprises the following steps:
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles; when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle; selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum; adjusting the polarizer to the target polarization angle.
For example, the controlling the camera to acquire the initial image of the calibration vehicle under the condition that the polarizer is at a plurality of polarization angles includes: determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of polarization angles based on a preset step length; and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
For example, the controlling the camera to acquire the initial image of the calibration vehicle under the condition that the polarizer is at a plurality of polarization angles includes: determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length; controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on a target parameter corresponding to each initial angle; dividing all angle values between the first preliminary angle and the second preliminary angle into a plurality of polarization angles based on a preset second step length, wherein the preset second step length is smaller than the preset first step length; and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
Illustratively, the selecting a first preliminary angle and a second preliminary angle from the plurality of preliminary angles based on the target parameter corresponding to each preliminary angle includes: and selecting the preliminary angle corresponding to the maximum target parameter as a first preliminary angle and selecting the preliminary angle corresponding to the secondary large target parameter as a second preliminary angle based on the target parameter corresponding to each preliminary angle.
Illustratively, the determining the image to be compared of the target object based on the initial image acquired when the polarizer is at the polarization angle includes: carrying out image enhancement processing on the initial image to obtain a target image; and inputting the target image into a face recognition model, and carrying out face recognition on the target image through the face recognition model to obtain an image to be compared of the target face.
Illustratively, the determining the target parameter corresponding to each polarization angle when the polarizer is at each polarization angle includes: inputting the image to be compared of the target face and the reference image of the target face into a face similarity model, determining the similarity degree of the image to be compared of the target face and the reference image of the target face through the face similarity model, and determining the similarity degree as a target parameter corresponding to the polarization angle.
Illustratively, after the adjusting the polarizer to the target polarization angle, the method further comprises: and when the polarizer is at the target polarization angle, acquiring an original image of a passing vehicle in a target scene through the camera, wherein the original image is an original image optimized by the polarizer.
The application provides a polarization angle's confirming device, it has camera and calibration vehicle to dispose under the target scene, and the camera includes the polarizer, the device includes: the control module is used for controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles; the determination module is used for determining a target parameter corresponding to the polarization angle when the polarizer is at each polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle; and the processing module is used for selecting a target polarization angle from the plurality of polarization angles based on the target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is maximum, and the polarizer is adjusted to the target polarization angle.
For example, the control module controls the camera to specifically perform, when the polarizer is at a plurality of polarization angles, the following steps of: determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length; controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on a target parameter corresponding to each initial angle; dividing all angle values between the first preliminary angle and the second preliminary angle into a plurality of polarization angles based on a preset second step length, wherein the preset second step length is smaller than the preset first step length; and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
The application provides a polarization angle's definite equipment, it has camera and calibration vehicle to dispose under the target scene, and the camera includes the polarizer, polarization angle's definite equipment includes: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute machine executable instructions to perform the steps of:
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles; when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle; selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum; adjusting the polarizer to the target polarization angle.
According to the technical scheme, the target parameters corresponding to each polarization angle are determined by controlling the polarizer to be at the plurality of polarization angles, the target polarization angle is selected from the plurality of polarization angles based on the target parameters corresponding to each polarization angle, and the polarizer is adjusted to the target polarization angle (namely the optimal polarization angle), so that the optimal polarization angle of the polarizer is determined in a self-adaptive manner, the method is suitable for various target scenes, the optimal polarization angle of the polarizer can be adjusted in a self-adaptive manner according to the scene environment of the target scene, the requirement of detecting the human face in the vehicle is met, the influence of rainbow lines on the human face in the vehicle is relieved to the maximum extent, the influence of the rainbow lines can be effectively reduced, the method is suitable for various road environments, and the method has good universality, maintainability and detection accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments of the present application or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings of the embodiments of the present application.
Fig. 1A and 1B are schematic structural views of a camera according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for determining a polarization angle according to an embodiment of the present disclosure;
FIG. 3 is a flow chart illustrating a method for determining a polarization angle according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of an apparatus for determining a polarization angle according to an embodiment of the present disclosure;
fig. 5 is a hardware configuration diagram of a polarization angle determination device according to an embodiment of the present application.
Detailed Description
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein is meant to encompass any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application to describe various information, the information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Depending on the context, moreover, the word "if" as used may be interpreted as "at … …" or "when … …" or "in response to a determination".
Before the technical solution of the present application is introduced, the following concepts related to the present application are introduced:
rainbow pattern: the natural light generates film interference through the car film, interference fringes formed by the natural light at different angles are mutually overlapped, the contrast of the fringes in a certain area is enhanced, and obvious rainbow fringes are formed.
A polarizer: the polarizer has a function of selectively absorbing light vibration in different directions, so that the polarizer has a specific direction, when a beam of natural light strikes the polarizer, the light vibration component perpendicular to the specific direction is completely absorbed by the polarizer, and only the light vibration component parallel to the specific direction passes through the polarizer.
Definition: by increasing the sharpness of the image, the side closer to the edge, which is darker, becomes darker, and the side closer to the edge, which is brighter, becomes brighter, and the change in brightness contrast is localized to only the portion around the edge. By increasing the definition of the image, the white gradual change strip is added on the bright edge, and the black gradual change strip is added on the dark edge, so that the outline and the detail texture of the object are clearer.
Contrast ratio: the contrast is the light and shade contrast degree of the image picture, and the bright place in the image picture can be brighter, the dark place in the image picture can be darker and the light and shade contrast is enhanced by increasing the contrast of the image.
Polarization angle of polarizer: the polarizer is a rotatable optical device, the rotation angle of the polarizer may be 0 to 360 degrees, a certain angle of the polarizer may be defaulted as an initial angle, the initial angle is recorded as 0 degree, if an angle right above is the initial angle, an angle right below is the initial angle, an angle right to the right is the initial angle, an angle right to the left is the initial angle, and the like, which is not limited to this.
On the basis of the initial angle, if the polarizer is rotated in the clockwise direction by the rotation angle of M degrees, the polarization angle of the polarizer is M degrees, and if the polarizer is rotated in the counterclockwise direction by the rotation angle of M degrees, the polarization angle of the polarizer is (360-M) degrees. Alternatively, if the polarizer is rotated in the clockwise direction by M degrees, the polarization angle of the polarizer is (360-M) degrees, and if the polarizer is rotated in the counterclockwise direction by M degrees, the polarization angle of the polarizer is M degrees.
The working principle of the polarizer is as follows: referring to fig. 1A and 1B, which are schematic structural diagrams of a camera, the camera may include a polarizer, a lens, and a light sensing device. In fig. 1A, the polarizer is located in front of the lens, which is located in front of the light sensing device. In fig. 1B, the polarizer is located between the lens and the photosensitive device.
For fig. 1A, natural light first strikes the polarizer, the polarizer filters the natural light, the filtered natural light reaches the lens, and then reaches the light sensing device through the lens, the light sensing device converts an optical signal into an electrical signal, and then an image can be generated based on the electrical signal, and obviously, the image is an image optimized by the polarizer. For fig. 1B, natural light is incident on the polarizer through the lens, the polarizer filters the natural light, the filtered natural light reaches the photosensitive device, the photosensitive device converts the optical signal into an electrical signal, and an image can be generated based on the electrical signal, and obviously, the image is an image optimized by the polarizer.
In summary, by disposing a polarizer in the camera, the polarizer can be used to reduce the influence of rainbow texture. However, in the related art, when the camera leaves the factory, the polarization angle of the polarizer is already fixed, for example, the polarization angle is an initial angle, and the polarization angle of the polarizer is not adjusted, and in all scenes, the polarization angle of the polarizer is a fixed angle, so that the polarizer cannot meet the actual requirements of all scenes.
In view of the above findings, in the embodiment of the present application, the optimal polarization angle of the polarizer can be determined adaptively, the optimal polarization angle of the polarizer can be adjusted adaptively according to the scene environment of the target scene, the influence of the rainbow texture on the face in the vehicle can be alleviated to the maximum extent, and the influence of the rainbow texture can be effectively reduced.
The technical solutions of the embodiments of the present application are described below with reference to specific embodiments.
The embodiment of the application provides a method for determining a polarization angle, which can be applied to any application scene with a camera (such as an analog camera or a network camera) deployed, and for convenience in distinguishing, the application scene with the camera deployed is called a target scene (such as a highway scene, a common highway scene and the like), namely the camera is deployed under the target scene, and images of vehicles passing under the target scene are acquired through the camera.
In the embodiment of the application, in the erection process of the camera, a calibration vehicle needs to be deployed in a target scene, a target object exists in the calibration vehicle (for convenience in distinguishing, the object in the calibration vehicle is marked as the target object), the calibration vehicle is a vehicle located in the visual field range of the camera, and the camera can acquire an image of the calibration vehicle. The calibration vehicle is a vehicle with a vehicle film, and the vehicle film can generate rainbow patterns on vehicle windows under natural light.
To sum up, a camera and a calibration vehicle are deployed in a target scene, the camera includes a polarizer, a lens and a photosensitive device, and the polarizer may be located in front of the lens or between the lens and the photosensitive device.
Referring to fig. 2, a flow chart of a method for determining a polarization angle is schematically shown, and the method may include:
In one possible embodiment, the following steps may be taken to control the camera to acquire an initial image of the calibration vehicle with the polarizer at a plurality of polarization angles:
step S11: and determining the minimum value and the maximum value of the polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of polarization angles based on a preset step length.
For example, since the rotation angle of the polarizer may be 0 to 360 degrees, the minimum polarization angle may be 0 degree, and the maximum polarization angle may be 360 degrees, and certainly, the minimum polarization angle may also be other angles greater than 0 degree, such as 10 degrees, 20 degrees, and the like, without limitation, and the maximum polarization angle may also be other angles less than 360 degrees, such as 350 degrees, 340 degrees, and the like, without limitation.
For example, the preset step size may be configured empirically, such as 5 degrees, 10 degrees, 20 degrees, etc., and the preset step size is not limited, and for convenience of description, the preset step size is illustrated as 10 degrees.
In summary, when all angle values between the minimum polarization angle value and the maximum polarization angle value are divided into a plurality of polarization angles based on the preset step size, all angle values between 0 degrees and 360 degrees may be divided into 0 degrees, 10 degrees, 20 degrees, … degrees, 340 degrees, 350 degrees, and 360 degrees based on the preset step size (10 degrees).
Step S12: and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is sequentially positioned at the plurality of polarization angles.
For example, the polarizer is controlled to be at 0 degree, the camera collects an initial image of a calibrated vehicle when the polarizer is at 0 degree, and the subsequent steps are executed based on the initial image; then, controlling the polarizer to be at 10 degrees, collecting an initial image of the calibrated vehicle by the camera when the polarizer is at 10 degrees, and executing subsequent steps based on the initial image; then, controlling the polarizer to be at 20 degrees, collecting an initial image of the calibrated vehicle by the camera when the polarizer is at 20 degrees, and executing subsequent steps based on the initial image; and the like, until the polarizer is controlled to be in 360 degrees, the camera collects an initial image of the calibrated vehicle when the polarizer is in 360 degrees, and the subsequent steps are executed based on the initial image.
In another possible embodiment, the following steps may be taken to control the camera to acquire an initial image of the calibration vehicle with the polarizer at a plurality of polarization angles:
step S21: and determining a minimum value and a maximum value of the polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length.
For example, since the rotation angle of the polarizer may be 0 to 360 degrees, the minimum value of the polarization angle may be 0 degree, and the maximum value of the polarization angle may be 360 degrees. The preset first step length may be configured empirically, and the preset first step length may be a large step length, such as 10 degrees, 20 degrees, 30 degrees, etc., and the preset first step length is not limited, and for convenience of description, the preset first step length is illustrated as 30 degrees.
In summary, when all angle values between the minimum polarization angle value and the maximum polarization angle value are divided into a plurality of preliminary angles based on the preset first step, all angle values between 0 degrees and 360 degrees may be divided into 0 degrees, 30 degrees, 60 degrees, … degrees, 330 degrees, and 360 degrees based on the preset first step.
Step S22: and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is sequentially positioned at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on the target parameter corresponding to each initial angle.
For example, the polarizer is controlled to be at 0 degree, the camera collects an initial image of the calibrated vehicle when the polarizer is at 0 degree, and a target parameter corresponding to the initial angle of 0 degree is determined based on the initial image. And controlling the polarizer to be at 30 degrees, acquiring an initial image of the calibrated vehicle by the camera when the polarizer is at 30 degrees, and determining a target parameter corresponding to the 30 degrees of the initial angle based on the initial image. And the like, until the polarizer is controlled to be in 360 degrees, the camera collects an initial image of the calibrated vehicle when the polarizer is in 360 degrees, and the target parameter corresponding to the initial angle of 360 degrees is determined based on the initial image.
Regarding the manner of determining the target parameter corresponding to each preliminary angle, the manner of determining the target parameter corresponding to each polarization angle is similar, and for the specific determination process, reference is made to the subsequent embodiments, and details are not repeated here.
After the target parameter corresponding to each preliminary angle is obtained, a first preliminary angle and a second preliminary angle may be selected from the plurality of preliminary angles based on the target parameter corresponding to each preliminary angle. For example, based on the target parameter corresponding to each preliminary angle, the preliminary angle corresponding to the largest target parameter is selected as the first preliminary angle, and the preliminary angle corresponding to the second largest target parameter is selected as the second preliminary angle. For example, based on the target parameter corresponding to each preliminary angle, if the target parameter corresponding to the preliminary angle "30 degrees" is the maximum target parameter and the target parameter corresponding to the preliminary angle "60 degrees" is the second largest target parameter, the preliminary angle "30 degrees" may be used as the first preliminary angle, and the preliminary angle "60 degrees" may be used as the second preliminary angle.
Step S23: all angle values between the first preliminary angle and the second preliminary angle are divided into a plurality of polarization angles based on a preset second step length, which may be smaller than the preset first step length.
The preset second step length may be configured according to experience, and the preset second step length may be a small step length, and the preset second step length needs to be smaller than the preset first step length, such as 1 degree, 2 degrees, 3 degrees, 5 degrees, and the like.
For example, when all angle values between the first preliminary angle and the second preliminary angle are divided into a plurality of polarization angles based on the preset second step, all angle values between 30 degrees and 60 degrees may be divided into 30 degrees, 35 degrees, 40 degrees, … degrees, 55 degrees, 60 degrees based on the preset second step.
Step S24: and controlling a camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is sequentially positioned at the plurality of polarization angles.
For example, the polarizer is controlled to be at 30 degrees, the camera collects an initial image of a calibrated vehicle when the polarizer is at 30 degrees, and the subsequent steps are executed based on the initial image; then, controlling the polarizer to be at 35 degrees, collecting an initial image of the calibrated vehicle by the camera when the polarizer is at 35 degrees, and executing subsequent steps based on the initial image; and the like, until the polarizer is controlled to be at 60 degrees, the camera collects an initial image of the calibrated vehicle when the polarizer is at 60 degrees, and the subsequent steps are executed based on the initial image.
Of course, the above two methods are only examples of controlling the polarizer to be at a plurality of polarization angles, and the control method is not limited as long as the polarizer can be controlled to be at a plurality of polarization angles. For example, to control the polarizer at a certain polarization angle, the following method can be adopted: the camera may further include a motor connected to the polarizer, the motor is configured to rotate the polarizer, and when the polarizer needs to be controlled to be at M degrees, the motor rotates the polarizer, so as to rotate the polarizer to M degrees, and the control process is not limited.
For example, the target object in the calibration vehicle may include, but is not limited to, a target face, and of course, the target face is only an example, and is not limited thereto, such as target eyes, target human body features, and the like. Therefore, the image to be compared of the target object may be the image to be compared of the target face in the initial image.
In a possible implementation manner, when the polarizer is at each polarization angle (for convenience of description, one polarization angle is taken as an example in the following), the following steps are adopted to determine the target parameter corresponding to the polarization angle:
step S31: when the polarizer is at the polarization angle, an initial image of the calibration vehicle is acquired by the camera, and the initial image may include a target object, i.e., a target human face, in the calibration vehicle.
Step S32: an image to be compared of the target object is determined based on the initial image.
For example, the initial image may be subjected to image enhancement processing to obtain the target image. Then, the target image is input into a face recognition model, and the face recognition is carried out on the target image through the face recognition model to obtain an image to be compared of the target face, namely, a face region small image is intercepted from the target image.
The image enhancement processing is performed on the initial image, which may include but is not limited to: the ISP (Image Signal Processing) Processing is performed on the initial Image, and the ISP Processing is used to perform post-Processing on the initial Image, such as at least one of linear correction, noise removal, dead pixel removal, interpolation, white balance, and automatic exposure control on the initial Image.
The face recognition model is a model for recognizing a face from an image, and by inputting a target image into the face recognition model, the face recognition of the target image can be performed through the face recognition model to obtain an image to be compared of the target face.
Step S33: a reference image of the target object is acquired.
For example, a face image of a target face exists in the face database, and the face image is used as a reference image of the target face, where the reference image is a relatively clear image of the target face.
Step S34: the similarity between the image to be compared of the target object and the reference image of the target object is determined, and the similarity may be, for example, a target parameter corresponding to the polarization angle.
For example, the image to be compared of the target face and the reference image of the target face may be input into a face similarity model, and the degree of similarity between the image to be compared of the target face and the reference image of the target face is determined by the face similarity model, and the degree of similarity is determined as the target parameter corresponding to the polarization angle.
The face similarity model is a model for determining the face similarity, and the similarity between the image to be compared of the target face and the reference image of the target face can be determined through the face similarity model by inputting the image to be compared of the target face and the reference image of the target face into the face similarity model, for example, by using similarity calculation methods such as euclidean distance, chebyshev distance, cosine similarity and the like, the similarity between the image to be compared of the target face and the reference image of the target face is determined, and the determination process is not limited.
For example, based on the target parameter corresponding to each of the plurality of polarization angles, the polarization angle corresponding to the largest target parameter may be selected as the target polarization angle.
For example, when the polarizer is at each polarization angle, step 202 may be adopted to determine the target parameter corresponding to the polarization angle, so that the target parameter corresponding to each polarization angle can be obtained. Based on the target parameter corresponding to each polarization angle, a target polarization angle may be selected from the plurality of polarization angles.
For example, based on the target parameter corresponding to each polarization angle, if the target parameter corresponding to the polarization angle "50 degrees" is the maximum target parameter, the polarization angle "50 degrees" may be selected as the target polarization angle.
To adjust the polarizer to the target polarization angle, the following method can be adopted: the camera may further comprise a motor connected to the polarizer for rotating the polarizer, and when it is desired to control the polarizer to be at the target polarization angle, the motor rotates the polarizer to rotate the polarizer to the target polarization angle.
For example, when the polarizer is at the target polarization angle, the adjustment process of the polarizer is completed, that is, the determination process of the polarization angle is ended, the calibration vehicle is moved away from the target scene, and the target scene may pass through the vehicle in normal driving. When the polarizer is at the target polarization angle, an original image (i.e., a Bayer image) of a vehicle passing through the target scene (i.e., a vehicle traveling normally) can be captured by the camera, and the original image is an original image optimized by the polarizer, that is, rainbow fringes in the image are optimized.
In the above embodiment, steps 201-204 may be performed by a camera controlling a polarizer at a plurality of polarization angles. When the polarizer is at each polarization angle, the camera collects an initial image, and determines a target parameter corresponding to the polarization angle based on the initial image. The camera selects a target polarization angle from the plurality of polarization angles based on the target parameter corresponding to each polarization angle, and adjusts the polarizer to the target polarization angle.
Alternatively, steps 201-204 may be performed by a control device (e.g., a PC, a mobile terminal, etc.) that sends a control command to the camera by which to control the polarizer to be at multiple polarization angles. When the polarizer is at each polarization angle, the camera collects an initial image and sends the initial image to the control equipment, and the control equipment determines a target parameter corresponding to the polarization angle based on the initial image. The control equipment selects a target polarization angle from the plurality of polarization angles based on the target parameter corresponding to each polarization angle, sends a control command to the camera, and adjusts the polarizer to the target polarization angle through the control command.
Alternatively, the camera and the control device may perform steps 201 to 204 together, that is, the camera and the control device cooperate to implement steps 201 to 204. The camera controls the polarizer at a plurality of polarization angles. When the polarizer is at each polarization angle, the camera collects an initial image and sends the initial image to the control equipment, and the control equipment determines a target parameter corresponding to the polarization angle based on the initial image. The control equipment sends the target parameters corresponding to the polarization angles to the camera, the camera selects the target polarization angles from the multiple polarization angles based on the target parameters corresponding to each polarization angle, and the polarizer is adjusted to the target polarization angles.
Of course, the above is only an example, and the execution subject of the steps 201 to 204 is not limited.
In an example, the execution sequence is only an example given for convenience of description, and in practical applications, the execution sequence between steps may also be changed, and the execution sequence is not limited. Moreover, in other embodiments, the steps of the respective methods do not have to be performed in the order shown and described herein, and the methods may include more or less steps than those described herein. Moreover, a single step described in this specification may be broken down into multiple steps for description in other embodiments; multiple steps described in this specification may be combined into a single step in other embodiments.
According to the technical scheme, the target parameters corresponding to each polarization angle are determined by controlling the polarizer to be at the plurality of polarization angles, the target polarization angle is selected from the plurality of polarization angles based on the target parameters corresponding to each polarization angle, and the polarizer is adjusted to the target polarization angle (namely the optimal polarization angle), so that the optimal polarization angle of the polarizer is determined in a self-adaptive manner, the method is suitable for various target scenes, the optimal polarization angle of the polarizer can be adjusted in a self-adaptive manner according to the scene environment of the target scene, the requirement of detecting the human face in the vehicle is met, the influence of rainbow lines on the human face in the vehicle is relieved to the maximum extent, the influence of the rainbow lines can be effectively reduced, the method is suitable for various road environments, and the method has good universality, maintainability and detection accuracy.
The above technical solution of the embodiment of the present application is described below with reference to specific application scenarios.
Referring to fig. 3, a flowchart of a method for determining a polarization angle of a polarizer is shown, where the method may be applied to a camera, and the camera may include a polarizer, and the method may include:
For example, a camera may be deployed on a standard rack, a fill light may be built, a snapshot trigger line may be drawn, and snapshot parameters may be configured for the camera. The calibration vehicle is stopped at a prescribed position (e.g., a position prescribed by a snapshot trigger line) and the user is at the driving position of the calibration vehicle. Then, triggering snapshot operation, turning on a light supplement lamp, and acquiring an initial image (namely a Bayer image) of the calibrated vehicle by the camera based on the snapshot parameters.
And step 304, performing image enhancement processing on the initial image to obtain a target image.
By performing image enhancement processing (such as ISP processing, such as linear correction, noise removal, dead pixel removal, interpolation, white balance, automatic exposure control, and the like) on the initial image, image sharpness and contrast can be improved.
For example, the target image may be input into a face recognition model, and the face recognition model may be a model trained based on a deep learning algorithm, and is a model for recognizing a face from an image, and the face recognition model is not limited. After the face recognition model obtains the target image, face recognition is performed on the target image based on the characteristics of the target image, and face region information (such as rectangular frame information of the face region, such as start point coordinates, width, height, and the like) is obtained. And based on the face region information, intercepting a face region small image corresponding to the face region information from the target image, wherein the face region small image is an image to be compared of the target face.
For example, the image to be compared of the target face and the reference image of the target face may be input to a face similarity model, and the face similarity model may determine a similarity between the image to be compared of the target face and the reference image of the target face in a similarity calculation manner such as an euclidean distance, a chebyshev distance, a cosine similarity, and the like, where the similarity may be a face similarity score, that is, a face similarity score value.
In a possible implementation manner, the image to be compared of the target face may be input to a face similarity model, the face similarity model traverses each face image in a face database, similarity calculation manners such as an euclidean distance, a chebyshev distance, a cosine similarity are adopted to determine a similarity between the image to be compared of the target face and each face image, a maximum similarity is selected from all the determined similarities, the maximum similarity is determined as a similarity between the image to be compared of the target face and a reference image of the target face, and the similarity is used as a target parameter corresponding to a currently traversed polarization angle.
In step 308, since all the polarization angles have been traversed and the target parameter corresponding to each polarization angle is obtained, the polarization angle corresponding to the largest target parameter can be selected as the target polarization angle.
And when the polarizer is at the target polarization angle, finishing the adjustment process of the polarizer. When the polarizer is at the target polarization angle, an original image (i.e., a Bayer image) of a passing vehicle (i.e., a vehicle running normally) in a target scene, i.e., an image with reduced rainbow fringes, can be acquired (captured) by a camera, and the original image is subjected to image enhancement processing to obtain an image with minimal influence of the rainbow fringes on the vehicle window and the human face.
The embodiment of the application provides another method for determining the polarization angle of a polarizer, which comprises the following steps:
and step S41, determining the minimum value and the maximum value of the polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length.
And step 42, traversing a preliminary angle from the plurality of preliminary angles, and controlling the polarizer to be at the preliminary angle, wherein the traversed preliminary angle is an unretraversed preliminary angle.
Step S43, an initial image of the calibrated vehicle is acquired, the initial image including a target face in the calibrated vehicle.
Step S44, performs image enhancement processing on the initial image to obtain a target image.
Step S45, inputting the target image into a face recognition model, and performing face recognition on the target image through the face recognition model to obtain an image to be compared of the target face, namely, intercepting a face region thumbnail from the target image.
Step S46, inputting the image to be compared of the target face and the reference image of the target face into the face similarity model, determining the degree of similarity between the image to be compared of the target face and the reference image of the target face through the face similarity model, and determining the degree of similarity as the target parameter corresponding to the currently traversed preliminary angle.
And step S47, judging whether all the preliminary angles have been traversed or not according to a plurality of preliminary angles between the minimum value and the maximum value of the polarization angle, if so, executing step S48, if not, returning to step S42, traversing a new preliminary angle from the plurality of preliminary angles, and controlling the polarizer to be at the new preliminary angle.
In step S48, since all the preliminary angles have been traversed and the target parameter corresponding to each preliminary angle is obtained, the preliminary angle corresponding to the largest target parameter is selected as the first preliminary angle, and the preliminary angle corresponding to the second largest target parameter (i.e., the second largest target parameter) is selected as the second preliminary angle.
In step S49, all angle values between the first preliminary angle and the second preliminary angle are divided into a plurality of polarization angles based on a preset second step size, which may be smaller than the preset first step size.
Step S50, traversing a polarization angle from the plurality of polarization angles, and controlling the polarizer to be at the polarization angle, where the traversed polarization angle is an unretraversed polarization angle.
Step S51, an initial image of the calibrated vehicle is acquired, the initial image including a target face in the calibrated vehicle.
Step S52, performs image enhancement processing on the initial image to obtain a target image.
Step S53, inputting the target image into a face recognition model, and performing face recognition on the target image through the face recognition model to obtain an image to be compared of the target face, namely, intercepting a face region thumbnail from the target image.
Step S54, inputting the image to be compared of the target face and the reference image of the target face into the face similarity model, determining the degree of similarity between the image to be compared of the target face and the reference image of the target face through the face similarity model, and determining the degree of similarity as the target parameter corresponding to the currently traversed polarization angle.
And step S55, judging whether all polarization angles have been traversed according to a plurality of polarization angles between the first preliminary angle and the second preliminary angle, if so, executing step S56, if not, returning to step S50, traversing a new polarization angle from the plurality of polarization angles, and controlling the polarizer to be at the new polarization angle.
In step S56, since all the polarization angles have been traversed and the target parameter corresponding to each polarization angle is obtained, the polarization angle corresponding to the largest target parameter may be selected as the target polarization angle.
In step S57, the polarizer is adjusted to a target polarization angle (i.e., an optimal polarization angle).
Based on the same application concept as the method, an embodiment of the present application provides a device for determining a polarization angle, where a camera and a calibration vehicle are deployed in a target scene, and the camera includes a polarizer, as shown in fig. 4, which is a schematic structural diagram of the device, and the device may include:
the control module 41 is configured to control the camera to acquire an initial image of the calibrated vehicle when the polarizer is at a plurality of polarization angles;
a determining module 42, configured to determine, when the polarizer is at each polarization angle, a target parameter corresponding to the polarization angle, where the target parameter represents a similarity degree between an image to be compared of a target object in the calibration vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle;
a processing module 43, configured to select a target polarization angle from the multiple polarization angles based on a target parameter corresponding to each polarization angle, where a similarity degree represented by the target parameter corresponding to the target polarization angle is the largest, and adjust the polarizer to the target polarization angle.
For example, the control module 41 controls the camera to specifically:
determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of polarization angles based on a preset step length;
and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
For example, the control module 41 controls the camera to specifically:
determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length;
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on a target parameter corresponding to each initial angle;
dividing all angle values between the first preliminary angle and the second preliminary angle into a plurality of polarization angles based on a preset second step length, wherein the preset second step length is smaller than the preset first step length;
and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
For example, the control module 41 is specifically configured to, when selecting a first preliminary angle and a second preliminary angle from the plurality of preliminary angles based on the target parameter corresponding to each preliminary angle:
and selecting the preliminary angle corresponding to the maximum target parameter as a first preliminary angle and selecting the preliminary angle corresponding to the secondary large target parameter as a second preliminary angle based on the target parameter corresponding to each preliminary angle.
Illustratively, the target object includes a target face, and the determining module 42 is specifically configured to, when determining the image to be compared of the target object based on the initial image acquired when the polarizer is at the polarization angle:
carrying out image enhancement processing on the initial image to obtain a target image;
and inputting the target image into a face recognition model, and carrying out face recognition on the target image through the face recognition model to obtain an image to be compared of the target face.
Illustratively, the target object includes a target face, and the determining module 42 is specifically configured to, when the polarizer is at each polarization angle, determine a target parameter corresponding to the polarization angle: inputting the image to be compared of the target face and the reference image of the target face into a face similarity model, determining the similarity degree of the image to be compared of the target face and the reference image of the target face through the face similarity model, and determining the similarity degree as a target parameter corresponding to the polarization angle.
Based on the same application concept as the method, an embodiment of the present application provides a device (such as a camera or a control device) for determining a polarization angle, where the camera and a calibration vehicle are deployed in a target scene, and the camera includes a polarizer, as shown in fig. 5, the device for determining a polarization angle includes: a processor 51 and a machine-readable storage medium 52, the machine-readable storage medium 52 storing machine-executable instructions executable by the processor 51; the processor 51 is configured to execute machine executable instructions to perform the following steps:
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles;
when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle;
selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum;
adjusting the polarizer to the target polarization angle.
Based on the same application concept as the method, embodiments of the present application further provide a machine-readable storage medium, where several computer instructions are stored on the machine-readable storage medium, and when the computer instructions are executed by a processor, the method for determining a polarization angle disclosed in the above example of the present application can be implemented.
The machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: a RAM (random Access Memory), a volatile Memory, a non-volatile Memory, a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., an optical disk, a dvd, etc.), or similar storage medium, or a combination thereof.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Furthermore, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for determining a polarization angle is characterized in that a camera and a calibration vehicle are deployed in a target scene, the camera comprises a polarizer, and the method comprises the following steps:
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles;
when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle;
selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum;
adjusting the polarizer to the target polarization angle.
2. The method of claim 1, wherein controlling the camera to capture initial images of the calibration vehicle with the polarizer at a plurality of polarization angles comprises:
determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of polarization angles based on a preset step length;
and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
3. The method of claim 1, wherein controlling the camera to capture initial images of the calibration vehicle with the polarizer at a plurality of polarization angles comprises:
determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length;
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on a target parameter corresponding to each initial angle;
dividing all angle values between the first preliminary angle and the second preliminary angle into a plurality of polarization angles based on a preset second step length, wherein the preset second step length is smaller than the preset first step length;
and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
4. The method according to claim 3, wherein selecting a first preliminary angle and a second preliminary angle from the plurality of preliminary angles based on the target parameter corresponding to each preliminary angle comprises:
and selecting the preliminary angle corresponding to the maximum target parameter as a first preliminary angle and selecting the preliminary angle corresponding to the secondary large target parameter as a second preliminary angle based on the target parameter corresponding to each preliminary angle.
5. The method of claim 1, wherein the target object comprises a target human face, and wherein determining the image to be compared of the target object based on the initial image acquired with the polarizer at the polarization angle comprises:
carrying out image enhancement processing on the initial image to obtain a target image;
and inputting the target image into a face recognition model, and carrying out face recognition on the target image through the face recognition model to obtain an image to be compared of the target face.
6. The method of claim 1, wherein the target object comprises a target face, and wherein determining the target parameters corresponding to the polarization angles when the polarizer is at each polarization angle comprises:
inputting the image to be compared of the target face and the reference image of the target face into a face similarity model, determining the similarity degree of the image to be compared of the target face and the reference image of the target face through the face similarity model, and determining the similarity degree as a target parameter corresponding to the polarization angle.
7. The method according to any one of claims 1 to 6,
after the adjusting the polarizer to the target polarization angle, the method further comprises:
and when the polarizer is at the target polarization angle, acquiring an original image of a passing vehicle in a target scene through the camera, wherein the original image is an original image optimized by the polarizer.
8. A polarization angle determination apparatus, wherein a camera and a calibration vehicle are deployed in a target scene, and the camera includes a polarizer, the apparatus comprising:
the control module is used for controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles;
the determination module is used for determining a target parameter corresponding to the polarization angle when the polarizer is at each polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle;
and the processing module is used for selecting a target polarization angle from the plurality of polarization angles based on the target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is maximum, and the polarizer is adjusted to the target polarization angle.
9. The apparatus of claim 8,
the control module controls the camera to specifically use when acquiring the initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles:
determining a minimum value and a maximum value of a polarization angle, and dividing all angle values between the minimum value and the maximum value of the polarization angle into a plurality of preliminary angles based on a preset first step length;
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of initial angles, and selecting a first initial angle and a second initial angle from the plurality of initial angles based on a target parameter corresponding to each initial angle;
dividing all angle values between the first preliminary angle and the second preliminary angle into a plurality of polarization angles based on a preset second step length, wherein the preset second step length is smaller than the preset first step length;
and controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at the plurality of polarization angles.
10. A polarization angle determining device is characterized in that a camera and a calibration vehicle are deployed in a target scene, the camera comprises a polarizer, and the polarization angle determining device comprises: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute machine executable instructions to perform the steps of:
controlling the camera to acquire an initial image of the calibrated vehicle under the condition that the polarizer is at a plurality of polarization angles;
when the polarizer is at each polarization angle, determining a target parameter corresponding to the polarization angle, wherein the target parameter represents the similarity degree between an image to be compared of a target object in the calibrated vehicle and a reference image of the target object; determining an image to be compared of the target object based on an initial image acquired when the polarizer is at the polarization angle;
selecting a target polarization angle from the plurality of polarization angles based on a target parameter corresponding to each polarization angle, wherein the similarity degree represented by the target parameter corresponding to the target polarization angle is the maximum;
adjusting the polarizer to the target polarization angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031110.6A CN112185126B (en) | 2020-09-27 | 2020-09-27 | Method, device and equipment for determining polarization angle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031110.6A CN112185126B (en) | 2020-09-27 | 2020-09-27 | Method, device and equipment for determining polarization angle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112185126A true CN112185126A (en) | 2021-01-05 |
| CN112185126B CN112185126B (en) | 2022-01-25 |
Family
ID=73945050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011031110.6A Active CN112185126B (en) | 2020-09-27 | 2020-09-27 | Method, device and equipment for determining polarization angle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112185126B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1145320A (en) * | 1997-07-25 | 1999-02-16 | Yasuyoshi Ochiai | Storage card |
| CN1662931A (en) * | 2002-05-09 | 2005-08-31 | 索尼株式会社 | Bio-pattern detecting means, bio-pattern detecting device, biometrics method and biometrics device |
| CN1695154A (en) * | 2002-08-30 | 2005-11-09 | 深远研发公司 | Non-contact optical imaging system for biometric identification |
| JP2011165005A (en) * | 2010-02-10 | 2011-08-25 | Toshiba Corp | Imaging apparatus and toll collection system |
| EP2436190A1 (en) * | 2009-05-26 | 2012-04-04 | Robert Bosch GmbH | Image acquisition method for recording several images by an automotive camera system, and corresponding image acquisition device of the camera system |
| WO2015016291A1 (en) * | 2013-07-31 | 2015-02-05 | Canon Kabushiki Kaisha | Photography apparatus and photography method |
| WO2015154491A1 (en) * | 2014-09-10 | 2015-10-15 | 中兴通讯股份有限公司 | Photo shooting method and display method and device |
| CN105094307A (en) * | 2014-05-23 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Mobile equipment with front-facing camera |
| CN105989360A (en) * | 2015-03-20 | 2016-10-05 | 富士通株式会社 | Image pickup device |
| CN107106017A (en) * | 2014-10-30 | 2017-08-29 | 皇家飞利浦有限公司 | Equipment, system and method for extracting physiologic information |
| CN108021877A (en) * | 2017-11-30 | 2018-05-11 | 北京文安智能技术股份有限公司 | Face identification method, apparatus and system in a kind of driving vehicle |
| CN108900754A (en) * | 2018-08-27 | 2018-11-27 | 广州大学 | It is a kind of for eliminating the reflective photographic device of glasses mirror surface and its control method |
| US20200101906A1 (en) * | 2018-09-28 | 2020-04-02 | Panasonic I-Pro Sensing Solutions Co., Ltd. | Capturing camera |
| CN111080669A (en) * | 2019-11-04 | 2020-04-28 | 北京大学 | Image reflection separation method and device |
| CN111428673A (en) * | 2020-04-01 | 2020-07-17 | 天津大学前沿技术研究院有限公司 | Polarization vector color image fusion method for fingerprint enhancement display |
-
2020
- 2020-09-27 CN CN202011031110.6A patent/CN112185126B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1145320A (en) * | 1997-07-25 | 1999-02-16 | Yasuyoshi Ochiai | Storage card |
| CN1662931A (en) * | 2002-05-09 | 2005-08-31 | 索尼株式会社 | Bio-pattern detecting means, bio-pattern detecting device, biometrics method and biometrics device |
| CN1695154A (en) * | 2002-08-30 | 2005-11-09 | 深远研发公司 | Non-contact optical imaging system for biometric identification |
| EP2436190A1 (en) * | 2009-05-26 | 2012-04-04 | Robert Bosch GmbH | Image acquisition method for recording several images by an automotive camera system, and corresponding image acquisition device of the camera system |
| JP2011165005A (en) * | 2010-02-10 | 2011-08-25 | Toshiba Corp | Imaging apparatus and toll collection system |
| WO2015016291A1 (en) * | 2013-07-31 | 2015-02-05 | Canon Kabushiki Kaisha | Photography apparatus and photography method |
| CN105094307A (en) * | 2014-05-23 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Mobile equipment with front-facing camera |
| WO2015154491A1 (en) * | 2014-09-10 | 2015-10-15 | 中兴通讯股份有限公司 | Photo shooting method and display method and device |
| CN107106017A (en) * | 2014-10-30 | 2017-08-29 | 皇家飞利浦有限公司 | Equipment, system and method for extracting physiologic information |
| CN105989360A (en) * | 2015-03-20 | 2016-10-05 | 富士通株式会社 | Image pickup device |
| CN108021877A (en) * | 2017-11-30 | 2018-05-11 | 北京文安智能技术股份有限公司 | Face identification method, apparatus and system in a kind of driving vehicle |
| CN108900754A (en) * | 2018-08-27 | 2018-11-27 | 广州大学 | It is a kind of for eliminating the reflective photographic device of glasses mirror surface and its control method |
| US20200101906A1 (en) * | 2018-09-28 | 2020-04-02 | Panasonic I-Pro Sensing Solutions Co., Ltd. | Capturing camera |
| CN111080669A (en) * | 2019-11-04 | 2020-04-28 | 北京大学 | Image reflection separation method and device |
| CN111428673A (en) * | 2020-04-01 | 2020-07-17 | 天津大学前沿技术研究院有限公司 | Polarization vector color image fusion method for fingerprint enhancement display |
Non-Patent Citations (1)
| Title |
|---|
| 康晴 等: "多角度偏振成像仪系统级偏振定标方法研究", 《大气与环境光学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112185126B (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4664379B2 (en) | Electronic device and image data processing method for image data processing | |
| CN108322646B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| US20200145583A1 (en) | Image capture device control based on determination of blur value of objects in images | |
| WO2021057652A1 (en) | Focusing method and apparatus, electronic device, and computer readable storage medium | |
| CN105657238B (en) | Track focusing method and device | |
| US10491804B2 (en) | Focus window determining method, apparatus, and device | |
| CN111246093B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| JP2012113460A (en) | Information processor and method, and program | |
| CN113674303B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN111917991B (en) | Image quality control method, device, equipment and storage medium | |
| CN113313626A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN112261292B (en) | Image acquisition method, terminal, chip and storage medium | |
| CN106791353B (en) | The methods, devices and systems of auto-focusing | |
| CN111598065A (en) | Depth image acquisition method, living body identification method, apparatus, circuit, and medium | |
| CN114727024A (en) | Automatic exposure parameter adjusting method and device, storage medium and shooting equipment | |
| CN113225550A (en) | Offset detection method and device, camera module, terminal equipment and storage medium | |
| CN113673474B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN108765346B (en) | Auxiliary focusing method and device and readable medium | |
| CN117615252A (en) | Highly adaptive AOI camera definition calibration method and system | |
| CN112185126B (en) | Method, device and equipment for determining polarization angle | |
| CN111654685B (en) | Moving direction detection method and device, projection equipment and readable storage medium | |
| CN113962869A (en) | Moire pattern removing method, device and equipment | |
| JP4589646B2 (en) | Digital still camera and control method thereof | |
| CN112434659B (en) | Reflection characteristic point eliminating method, device, robot and readable storage medium | |
| CN115734086A (en) | Image processing method, device and system based on off-screen shooting and storage medium |
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 |