CN112907487A - Binocular correction result determination method and device and electronic equipment - Google Patents
Binocular correction result determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN112907487A CN112907487A CN202110310854.XA CN202110310854A CN112907487A CN 112907487 A CN112907487 A CN 112907487A CN 202110310854 A CN202110310854 A CN 202110310854A CN 112907487 A CN112907487 A CN 112907487A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- feature point
- feature
- binocular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a method and a device for determining binocular correction results and electronic equipment, which relate to the technical field of binocular vision and comprise the following steps: acquiring a first image acquired by a first camera in binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object; determining pixel errors of the first image and the second image, wherein the pixel errors are used for representing the accuracy of a correction result of the binocular camera; and comparing the pixel error with a pixel error threshold value to determine a correction result, and verifying and optimizing the binocular correction result by the pixel error of the images of the two binocular cameras to ensure the accuracy of the binocular correction result.
Description
Technical Field
The invention relates to the technical field of binocular vision, in particular to a method and a device for determining a binocular correction result and electronic equipment.
Background
In order to ensure the detection precision, before the binocular camera is used, calibration of the binocular camera needs to be carried out, wherein the calibration mainly comprises independent internal reference calibration of the two cameras, external reference calibration of the relative positions of the two cameras and correction calibration. The binocular correction calibration is to correct two images acquired by a binocular camera for the same object from non-coplanarity into coplanar line alignment so as to improve the efficiency of matching search.
At present, for the result verification of binocular correction, the pixel positions of the same object on the left and right images are mainly compared by naked eyes so as to determine the correction effect. The inventor researches and finds that the verification method is troublesome, the correction condition cannot be accurately verified, sometimes, two pictures have different places, namely, the correction effect is different, and if the two pictures are observed by naked eyes, the condition is difficult to identify.
Disclosure of Invention
In view of this, the present invention aims to provide a method and an apparatus for determining a binocular correction result, and an electronic device, which perform verification and optimization on the binocular correction result by using pixel errors of two images of a binocular camera, so as to ensure accuracy of the binocular correction result.
In a first aspect, an embodiment provides a method for determining a binocular correction result, where the method includes:
acquiring a first image acquired by a first camera in binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object;
determining pixel errors of the first image and the second image, wherein the pixel errors are used for representing the accuracy of a correction result of the binocular camera;
and comparing the pixel error with a pixel error threshold value to determine the correction result.
In an optional embodiment, the step of comparing the pixel error with a pixel error threshold to determine the correction result includes:
if the comparison result of the pixel error and the pixel error threshold value meets the preset condition, the correction result passes the verification, and the correction result is determined to be a target result and the internal reference and the external reference calibrated by the binocular camera are accurate;
if the comparison result of the pixel error and the pixel error threshold value does not meet the preset condition, the correction result is not verified, the fact that the internal reference and/or the external reference calibrated by the binocular camera are inaccurate is determined, the internal reference and the external reference of the binocular camera are calibrated again, the binocular camera is corrected again until the correction result is verified to pass, and the optimized target result is obtained.
In an alternative embodiment, the first image and the second image are corrected images, and the step of determining the pixel error of the first image and the second image comprises:
and determining the pixel error average value of the binocular camera aiming at the acquired image of the target object according to the pixel error of each feature point matched in the first image and the second image.
In an alternative embodiment, the first image and the second image are uncorrected images, and the step of determining the pixel error of the first image and the second image further includes:
performing coplanarity correction according to the line pixels of each feature point matched in the first image and the second image;
and determining the pixel error average value of the binocular camera for the acquired image of the target object according to the row pixel error of each matched characteristic point in the corrected first image and the second image.
In an optional embodiment, the step of determining a pixel error average value of the captured image of the binocular camera for the target object according to the pixel error of each feature point matched in the first image and the second image includes:
extracting first feature point information corresponding to each first feature point from the first image, and extracting second feature point information corresponding to each second feature point from the second image, wherein the feature point information comprises pixel coordinates, pixel values and feature seeds;
determining a third feature point matched with each first feature point from the second feature points according to the feature;
and calculating the pixel error of each first characteristic point and the pixel error of each third characteristic point to obtain the pixel error average value of the binocular camera for the acquired image of the target object.
In an optional embodiment, before the step of extracting first feature point information corresponding to each first feature point from the first image and extracting second feature point information corresponding to each second feature point from the second image, the method further includes:
a first feature point is determined in the first image and a second feature point is determined in the second image.
In an alternative embodiment, the step of determining a first feature point in the first image comprises:
acquiring each pixel point in the first image;
and performing characteristic calculation on each pixel point and a plurality of adjacent pixel points to determine a first characteristic point.
In an optional embodiment, the feature is used to characterize feature information of each feature point, and the step of determining, from the second feature points, a third feature point matching each first feature point according to the feature includes repeatedly performing the following steps until each first feature point finds a matching third feature point:
matching the feature of the first feature point with the feature of each second feature point;
and determining a third feature point with the minimum feature sub-matching error from the second feature points.
In a second aspect, an embodiment provides an apparatus for determining a binocular correction result, the apparatus including:
the acquisition module acquires a first image acquired by a first camera in the binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object;
the first determining module is used for determining pixel errors of the first image and the second image, and the pixel errors are used for representing the accuracy of a correction result of the binocular camera;
and the second determining module is used for comparing the pixel error with a pixel error threshold value and determining the correction result.
In a third aspect, an embodiment provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and the processor implements the steps of the method described in any one of the foregoing embodiments when executing the computer program.
In a fourth aspect, embodiments provide a machine-readable storage medium having stored thereon machine-executable instructions that, when invoked and executed by a processor, cause the processor to carry out the steps of the method of any preceding embodiment.
According to the method and the device for determining the binocular correction result and the electronic equipment, the pixel errors of the whole images of the two binocular cameras are obtained and compared, the accuracy of the binocular correction result is verified according to the comparison result, the binocular correction result which does not meet the requirements is optimized, and the accurate binocular correction result is determined.
Additional features and advantages of the disclosure will be set forth in the description which follows, or in part may be learned by the practice of the above-described techniques of the disclosure, or may be learned by practice of the disclosure.
In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for determining a binocular correction result according to an embodiment of the present invention;
fig. 2 is a functional block diagram of a binocular correction result determining apparatus according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a hardware architecture of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The inventor finds that the verification of the binocular correction result can not only ensure that the images acquired by the two binocular cameras realize coplanar line alignment so as to greatly reduce the calculated amount in the subsequent searching or processing process, but also judge the accuracy of the pre-calibrated internal reference and external reference. Therefore, the importance of verifying the binocular correction result is known.
The current method for verifying the binocular correction result generally compares two images by naked eyes, but the verification method is not very accurate, for example, slight differences may exist on the two images, but the images cannot be recognized by naked eyes, and thus the binocular correction result cannot be accurately verified.
Based on this, the method and the device for determining the binocular correction result and the electronic device provided by the embodiment of the invention verify and optimize the binocular correction result through the pixel error of the images of the two binocular cameras, so that the accuracy of the binocular correction result is ensured.
To facilitate understanding of the present embodiment, a detailed description will be given first of all of a determination method of a binocular correction result disclosed in the embodiment of the present invention, which is applicable to a control apparatus that may be integrated with a binocular camera, integrated with a vehicle controller, or independently provided.
Fig. 1 is a flowchart of a method for determining a binocular correction result according to an embodiment of the present invention.
As shown in fig. 1, the method comprises the steps of:
step S102, acquiring a first image acquired by a first camera in the binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object;
the binocular camera can be arranged in front of a currently running vehicle and is used for collecting object vehicles in the vehicle running direction; the binocular camera may also be provided in the road infrastructure, i.e. the binocular camera is able to pick up obstacles or vehicles, etc. that are present in front of the binocular camera during the driving of the vehicle. The first camera and the second camera in the binocular camera may be set at any angle, such as up-down, left-right, etc., and may also be referred to as left camera and right camera. The first image and the second image both correspond to the same target object, that is, the target objects acquired by the first camera and the second camera are the same, and then the first image and the second image for the same target object are obtained. It is understood that the target object may be an obstacle, an obstacle vehicle, a pedestrian, or the like, which appears on a road during the traveling of the vehicle and may affect the traveling safety of the current vehicle. The target objects causing the influence may include a plurality of target objects, and in the binocular correction process, any one of the same target objects needs to be subjected to image acquisition through the first camera and the second camera.
Step S104, determining pixel errors of the first image and the second image, wherein the pixel errors are used for representing the accuracy of a correction result of the binocular camera;
here, as an alternative embodiment, the correction result of the binocular camera may be evaluated by the line pixel average error of the first image and the second image as a whole, as studied by the inventors. It should be noted that the binocular camera corrects two images aligned in a non-coplanar line to be aligned in a coplanar line, and therefore, it is understood that the pixel errors in the embodiment of the present invention both refer to line pixel average errors.
And step S106, comparing the pixel error with a pixel error threshold value, and determining the correction result.
In the preferred embodiment of practical application, the accurate binocular correction result is determined by acquiring the pixel errors of the whole images of the two binocular cameras, comparing the pixel errors, verifying the accuracy of the binocular correction result according to the comparison result, and optimizing the binocular correction result which does not meet the requirements.
In some embodiments, if the first image and the second image are corrected images, step S104 may include:
step 1.1), determining the pixel error average value of the binocular camera for the acquired image of the target object according to the pixel error of each feature point matched in the first image and the second image.
Here, the corrected binocular camera only needs to be verified at this time by the pixel errors of the first image and the second image. The pixel error here may also be a row pixel error.
This step 1.1) can also be achieved by:
step 1.1.1), extracting first feature point information corresponding to each first feature point from the first image, and extracting second feature point information corresponding to each second feature point from the second image, wherein the feature point information comprises pixel coordinates, pixel values and feature seeds;
in some embodiments, before step 1.1.1), further comprising: a first feature point is determined in the first image and a second feature point is determined in the second image.
Illustratively, each pixel point in the first image is acquired; and performing characteristic calculation on each pixel point and a plurality of adjacent pixel points to determine a first characteristic point. The feature calculation may include a laplacian calculation, a gradient calculation, and the like. For example, feature calculation such as laplacian calculation and gradient calculation is performed on a pixel point C in the first image and a surrounding adjacent pixel point, and if a feature calculation result meets a preset feature threshold condition, the pixel point C is determined as a first feature point.
The step of determining the second feature point is the same as the determination process of the first feature point, and is not described herein again.
As an optional embodiment, the feature points may include corner points, that is, gradient calculation is performed on a pixel point C in the first image and surrounding adjacent pixel points, and if a gradient calculation result satisfies a preset feature threshold condition, the pixel point C is determined as the first corner point. At this time, a second corner point is determined in the second image according to a gradient feature calculation mode, and matching of the corner points in the first image and the second image in the subsequent embodiment is completed according to features corresponding to the corner points.
Among them, a feature that can describe the point by an algorithm such as laplace, Gradient, etc., for example, a value of a Histogram of Oriented Gradients (HOG) feature is a kind of feature.
Step 1.1.2), determining third feature points matched with each first feature point from the second feature points according to the feature;
in some embodiments, since the first image and the second image are directed to the same target object, each first feature point on the first image can find a second feature point matching therewith in the second image, and this step 1.1.2) includes repeatedly performing the following steps until each of the first feature points finds a matching third feature point:
step 1.1.2.1), matching the characteristic seeds of the first characteristic points with the characteristic seeds of each second characteristic point;
step 1.1.2.2), determining a third feature point with the minimum feature matching error from the second feature points, wherein the third feature point with the closest feature description can be selected.
Step 1.1.3), pixel errors of the first characteristic points and the third characteristic points are calculated to obtain a pixel error average value of a binocular camera for a collected image of the target object.
For example, the coordinates (1.51, 2) of a first feature point a in the first image and the coordinates (1.7, 10) of a second feature point B in the second image matching the first feature point are calculated from the difference between the pixel values of the rows of A, B points, and the pixel error is obtained. Wherein, the pixel values of each row are floating point values.
After the row pixel errors of each pair of matched feature points are calculated, the row pixel errors of all the feature point pairs of the whole first image and the whole second image are averaged to obtain the pixel error average value of the binocular camera aiming at the collected image of the target object, and the pixel-level error calculation is realized.
In some embodiments, at this time, the first image and the second image are uncorrected images, and the embodiment of the present invention can further perform a correction step on the uncorrected image first, and then verify a correction result, where step S104 in the above embodiment further includes:
step 2.1), coplanar correction is carried out according to the line pixels of each characteristic point matched in the first image and the second image;
and 2.2) determining the pixel error average value of the binocular camera for the acquired image of the target object according to the row pixel error of each feature point matched in the corrected first image and the second image.
In some embodiments, the optimization and verification of the correction result is realized through step S106, which specifically includes the following steps:
step 1.1), if the comparison result of the pixel error and the pixel error threshold value meets a preset condition, the correction result passes verification, and the correction result is determined to be a target result and the internal reference and the external reference calibrated by the binocular camera are accurate;
the pixel error threshold can be selected from 0.5-1.5 pixels, preferably 0.5, 1, 1.5 pixels. Here, as an alternative embodiment, the pixel error is smaller than the pixel error threshold value, in order to satisfy the preset condition. According to the embodiment of the invention, the correction result of the binocular camera can be accurately verified, and the accurate target correction result and the corresponding accurate calibration internal reference and external reference are determined, so that the binocular camera can perform subsequent operation, or the image generated by the binocular camera can be used for subsequent scene operation, for example, the position of a target object in the image is identified according to the image, and accurate position information can be further obtained, so that automatic driving of a vehicle is realized, obstacles are avoided, and driving safety is ensured.
Step 1.2), if the comparison result of the pixel error and the pixel error threshold value does not meet the preset condition, the verification of the correction result is failed, the inaccuracy of the internal reference and/or the external reference calibrated by the binocular camera is determined, the internal reference and the external reference of the binocular camera are calibrated again, the binocular camera is corrected again until the verification of the correction result is passed, and the optimized target result is obtained.
Here, if it is verified that the correction result does not satisfy the preset condition, that is, the correction result is not accurate, at this time, the first image and the second image may still be in non-coplanar alignment, or the coplanar alignment is poor in accuracy, in order to ensure the accuracy of images acquired by the binocular camera and the accurate identification of obstacles in the scene, the internal reference and the external reference of the binocular camera are recalibrated, the correction steps in the foregoing embodiment are repeatedly performed, and the correction result is verified until the correction result passes verification.
It should be noted that, when the correction result in the embodiment of the present invention fails to be verified, at least one of the internal parameters and the external parameters is not accurate, but it cannot be further determined that the inaccuracy is the internal parameter, the external parameter, or both.
The embodiment of the invention can provide a relatively quick and convenient determination method for the binocular correction result, and can realize optimization and verification of the binocular correction result.
As shown in fig. 2, an embodiment of the present invention further provides an apparatus 200 for determining a binocular correction result, where the apparatus includes:
the acquiring module 201 acquires a first image acquired by a first camera of the binocular cameras and a second image acquired by a second camera of the binocular cameras for the same target object;
a first determining module 202, configured to determine pixel errors of the first image and the second image, where the pixel errors are used to characterize accuracy of correction results of the binocular camera;
the second determining module 203 compares the pixel error with a pixel error threshold to determine the correction result.
In a practical preferred embodiment, the correction effect of the binocular camera can be obtained quickly by determining the pixel errors of the first image and the second image respectively acquired by the two cameras aiming at the same target object, so as to decide not to use the internal parameters and the external parameters calibrated by the binocular camera continuously.
In an optional embodiment, the second determining module is further configured to, if the comparison result between the pixel error and the pixel error threshold meets a preset condition, verify that the correction result is passed, and determine that the correction result is a target result and the internal reference and the external reference calibrated by the binocular camera are accurate; if the comparison result of the pixel error and the pixel error threshold value does not meet the preset condition, the correction result is not verified, the fact that the internal reference and/or the external reference calibrated by the binocular camera are inaccurate is determined, the internal reference and the external reference of the binocular camera are calibrated again, the binocular camera is corrected again until the correction result is verified to pass, and the optimized target result is obtained.
In an optional embodiment, the first image and the second image are corrected images, and the first determining module is further configured to determine a pixel error average value of the captured image of the binocular camera for the target object according to a pixel error of each feature point in the first image and the second image that match.
In an alternative embodiment, the first image and the second image are uncorrected images, and the first determining module is further configured to perform coplanar correction according to the row pixels of each feature point matched in the first image and the second image; and determining the pixel error average value of the binocular camera for the acquired image of the target object according to the row pixel error of each matched characteristic point in the corrected first image and the second image.
In an optional embodiment, the first determining module is further configured to extract first feature point information corresponding to each first feature point from the first image, and extract second feature point information corresponding to each second feature point from the second image, where the feature point information includes pixel coordinates, pixel values, and feature seeds; determining a third feature point matched with each first feature point from the second feature points according to the feature; and calculating the pixel error of each first characteristic point and the pixel error of each third characteristic point to obtain the pixel error average value of the binocular camera for the acquired image of the target object.
In an alternative embodiment, the first determining module is further configured to determine the first feature point in the first image and determine the second feature point in the second image before the steps of extracting the first feature point information corresponding to each first feature point from the first image and extracting the second feature point information corresponding to each second feature point from the second image.
In an optional embodiment, the first determining module is further configured to obtain each pixel point in the first image; and performing characteristic calculation on each pixel point and a plurality of adjacent pixel points to determine a first characteristic point.
In an optional embodiment, the feature is used to characterize feature information of each feature point, and the first determining module is further configured to repeatedly perform the following steps until each first feature point finds a matching third feature point: matching the feature of the first feature point with the feature of each second feature point; and determining a third feature point with the minimum feature sub-matching error from the second feature points.
Fig. 3 is a schematic hardware architecture diagram of an electronic device 300 according to an embodiment of the present invention. Referring to fig. 3, the electronic device 300 includes: a machine-readable storage medium 301 and a processor 302, and may further include a non-volatile storage medium 303, a communication interface 304, and a bus 305; among other things, the machine-readable storage medium 301, the processor 302, the non-volatile storage medium 303, and the communication interface 304 communicate with each other via a bus 305. The processor 302 may perform the determination method of the binocular correction result described in the above embodiments by reading and executing machine-executable instructions of the verification of the binocular correction result in the machine-readable storage medium 301.
A machine-readable storage medium as referred to herein 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), any type of storage disk (e.g., an optical disk, a dvd, etc.), or similar storage medium, or a combination thereof.
The non-volatile medium may be non-volatile memory, flash memory, a storage drive (e.g., a hard drive), any type of storage disk (e.g., an optical disk, dvd, etc.), or similar non-volatile storage medium, or a combination thereof.
It can be understood that, for the specific operation method of each functional module in this embodiment, reference may be made to the detailed description of the corresponding step in the foregoing method embodiment, and no repeated description is provided herein.
The computer-readable storage medium provided in the embodiments of the present invention stores a computer program, and when executed, the computer program code may implement the method for determining a binocular correction result according to any one of the embodiments described above, and for specific implementation, reference may be made to the method embodiment, which is not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (11)
1. A method for determining binocular correction results, the method comprising:
acquiring a first image acquired by a first camera in binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object;
determining pixel errors of the first image and the second image, wherein the pixel errors are used for representing the accuracy of a correction result of the binocular camera;
and comparing the pixel error with a pixel error threshold value to determine the correction result.
2. The method of claim 1, wherein comparing the pixel error to a pixel error threshold to determine the correction comprises:
if the comparison result of the pixel error and the pixel error threshold value meets the preset condition, the correction result passes the verification, and the correction result is determined to be a target result and the internal reference and the external reference calibrated by the binocular camera are accurate;
if the comparison result of the pixel error and the pixel error threshold value does not meet the preset condition, the correction result is not verified, the fact that the internal reference and/or the external reference calibrated by the binocular camera are inaccurate is determined, the internal reference and the external reference of the binocular camera are calibrated again, the binocular camera is corrected again until the correction result is verified to pass, and the optimized target result is obtained.
3. The method of claim 1, wherein the first image and the second image are corrected images, and wherein determining the pixel error of the first image and the second image comprises:
and determining the pixel error average value of the binocular camera aiming at the acquired image of the target object according to the pixel error of each feature point matched in the first image and the second image.
4. The method of claim 1, wherein the first image and the second image are uncorrected images, and wherein the step of determining pixel errors for the first image and the second image further comprises:
performing coplanarity correction according to the line pixels of each feature point matched in the first image and the second image;
and determining the pixel error average value of the binocular camera for the acquired image of the target object according to the row pixel error of each matched characteristic point in the corrected first image and the second image.
5. The method of claim 3, wherein the step of determining an average of pixel errors for the captured images of the target object by the binocular camera based on the pixel error of each feature point in the first image and the second image that match comprises:
extracting first feature point information corresponding to each first feature point from the first image, and extracting second feature point information corresponding to each second feature point from the second image, wherein the feature point information comprises pixel coordinates, pixel values and feature seeds;
determining a third feature point matched with each first feature point from the second feature points according to the feature;
and calculating the pixel error of each first characteristic point and the pixel error of each third characteristic point to obtain the pixel error average value of the binocular camera for the acquired image of the target object.
6. The method according to claim 5, wherein the step of extracting first feature point information corresponding to each first feature point from the first image and extracting second feature point information corresponding to each second feature point from the second image is preceded by the step of:
a first feature point is determined in the first image and a second feature point is determined in the second image.
7. The method of claim 6, wherein the step of determining a first feature point in the first image comprises:
acquiring each pixel point in the first image;
and performing characteristic calculation on each pixel point and a plurality of adjacent pixel points to determine a first characteristic point.
8. The method according to claim 5, wherein the feature is used to characterize feature information of each feature point, and the step of determining a third feature point matching each of the first feature points from the second feature points according to the feature comprises repeating the following steps until each of the first feature points finds a matching third feature point:
matching the feature of the first feature point with the feature of each second feature point;
and determining a third feature point with the minimum feature sub-matching error from the second feature points.
9. An apparatus for determining a result of binocular correction, the apparatus comprising:
the acquisition module acquires a first image acquired by a first camera in the binocular cameras and a second image acquired by a second camera in the binocular cameras aiming at the same target object;
the first determining module is used for determining pixel errors of the first image and the second image, and the pixel errors are used for representing the accuracy of a correction result of the binocular camera;
and the second determining module is used for comparing the pixel error with a pixel error threshold value and determining the correction result.
10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program operable on the processor, and wherein the processor implements the steps of the method of any of claims 1 to 8 when executing the computer program.
11. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to carry out the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110310854.XA CN112907487A (en) | 2021-03-23 | 2021-03-23 | Binocular correction result determination method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110310854.XA CN112907487A (en) | 2021-03-23 | 2021-03-23 | Binocular correction result determination method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112907487A true CN112907487A (en) | 2021-06-04 |
Family
ID=76106162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110310854.XA Pending CN112907487A (en) | 2021-03-23 | 2021-03-23 | Binocular correction result determination method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907487A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680059A (en) * | 2017-09-30 | 2018-02-09 | 努比亚技术有限公司 | A kind of determination methods of image rectification, terminal and computer-readable recording medium |
| CN111862234A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862236A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Fixed-focus binocular camera self-calibration method and system |
-
2021
- 2021-03-23 CN CN202110310854.XA patent/CN112907487A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680059A (en) * | 2017-09-30 | 2018-02-09 | 努比亚技术有限公司 | A kind of determination methods of image rectification, terminal and computer-readable recording medium |
| CN111862234A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111862236A (en) * | 2020-07-22 | 2020-10-30 | 中国科学院上海微系统与信息技术研究所 | Fixed-focus binocular camera self-calibration method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109900254B (en) | Monocular vision road surface gradient calculation method and device | |
| US8121400B2 (en) | Method of comparing similarity of 3D visual objects | |
| JP6353289B2 (en) | Ranging correction device | |
| CN110211185B (en) | Method for identifying characteristic points of calibration pattern in group of candidate points | |
| EP2759959A2 (en) | Method and system for detecting multi-lanes | |
| US20200068186A1 (en) | Stereo camera | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| CN111340749B (en) | Image quality detection method, device, equipment and storage medium | |
| CN114255233B (en) | Speckle pattern quality evaluation method and device, electronic device and storage medium | |
| CN115578470B (en) | Monocular vision positioning method and device, storage medium and electronic equipment | |
| CN111386530B (en) | Vehicle detection method and apparatus | |
| JP2009009331A (en) | White line detector and white line detection method | |
| KR102022402B1 (en) | Calibration method and apparatus thereof | |
| CN112907487A (en) | Binocular correction result determination method and device and electronic equipment | |
| CN111462244B (en) | On-line calibration method, system and device for vehicle-mounted looking-around system | |
| US10339394B2 (en) | Step detection device and step detection method | |
| CN111260538B (en) | Positioning and vehicle-mounted terminal based on long-baseline binocular fisheye camera | |
| CN113674361B (en) | Vehicle-mounted all-round-looking calibration implementation method and system | |
| CN115802029A (en) | Image dead pixel detection method and terminal | |
| CN113450335B (en) | Road edge detection method, road edge detection device and road surface construction vehicle | |
| CN112233164B (en) | Method for identifying and correcting error points of disparity map | |
| US11178382B1 (en) | Auto-calibration of stereoscopic imaging device | |
| JP6521796B2 (en) | Stereo image processing device | |
| WO2020238116A1 (en) | Product positioning method | |
| CN114762019A (en) | Camera system |
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 |