A method for optimizing calibration parameters of binocular stereo vision cameras

Abstract

The present invention discloses a method for optimizing calibration parameters of a binocular stereo vision camera, and relates to the technical field of computer vision. The method comprises the following steps: hierarchical optimization calibration of feature points of different scales in the extracted scene, establishing a multi-scale feature point model, and characterizing the scale difference of the feature points by a scale factor; using a time series analysis algorithm to dynamically optimize calibration data at different times and adjust the calibration parameters of the camera; establishing a self-learning calibration optimization mechanism, that is, performing error analysis based on real-time feedback data to automatically evaluate the accuracy of the current calibration parameters. The present invention performs hierarchical multi-scale modeling of feature points, introduces independent calibration parameters for feature points of different scales, enables the system to more effectively reduce calibration errors caused by parallax or perspective distortion, and also introduces a self-learning calibration optimization mechanism that can dynamically adjust calibration parameters based on real-time feedback data.

Description

Technical Field

[0001] The invention relates to the technical field of computer vision, and in particular to a method for optimizing calibration parameters of a binocular stereo vision camera. Background Art

[0002] Camera calibration, 3D reconstruction, augmented reality, etc. The accuracy of the calibration process directly affects the performance and effect of these systems, especially in complex scenes, where feature points of different distances and scales often increase the calibration error due to parallax, perspective distortion, etc., which in turn affects the reliability and stability of the overall system.

[0003] Traditional feature point calibration methods usually adopt a single-scale calibration strategy, ignoring the multi-scale characteristics of feature points, which easily leads to large calibration errors of distant feature points and unclear deviations of nearby feature points. The accumulation of such errors not only reduces the accuracy of calibration, but may also cause distortion or deviation in subsequent systems such as image processing, target tracking, and 3D modeling. With the increase in scene complexity, how to adjust calibration parameters in real time and improve calibration accuracy in dynamic scenes has become a technical problem that needs to be solved urgently.

[0004] In addition, existing calibration systems usually lack an adaptive mechanism, that is, they are unable to automatically adjust according to real-time feedback data and are unable to effectively compensate for significant changes in calibration errors, resulting in a decrease in the calibration accuracy of the system in actual applications, which in turn affects the operating performance of the entire system. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing method for optimizing calibration parameters of a binocular stereo vision camera, the present invention is proposed.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] A method for optimizing calibration parameters of a binocular stereo vision camera, characterized in that the method comprises the following steps:

[0009] Perform hierarchical optimization and calibration on the feature points of different scales in the extracted scene, establish a multi-scale feature point model, and characterize the scale difference of the feature points through the scale factor;

[0010] Use time series analysis algorithms to dynamically optimize calibration data at different times and adjust camera calibration parameters;

[0011] A self-learning calibration optimization mechanism is established, that is, error analysis is performed based on real-time feedback data to automatically evaluate the accuracy of the current calibration parameters. If a significant change in the calibration error is detected, the calibration parameters are further adjusted based on the feedback information.

[0012] As a preferred solution of the optimization method of the calibration parameters of a binocular stereo vision camera described in the present invention, the hierarchical optimization calibration method is:

[0013] S101: Capture multiple feature points in the scene at a distance and near by using a binocular stereo vision camera, and set the feature point set as , is the Nth feature point, each feature point contains its position, scale, and depth information;

[0014] S102: Quantify the scale of each feature point and express it as a scale factor , It is calculated based on the physical size and visual size of different feature points. The calculation formula is:

[0015]

[0016] in, is the depth information of the feature point, It is the reference depth value, which is used to normalize feature points at different depths.

[0017] As a preferred solution of the optimization method of calibration parameters of a binocular stereo vision camera described in the present invention, the method of dynamically optimizing the calibration data is:

[0018] S201: First, each feature point Theoretical calibration value It represents the calibration value of the feature point under ideal conditions, which is calculated by the camera model. The calculation formula is:

[0019]

[0020] in, is the focal length of the camera, B is the baseline distance, is the depth of the feature point;

[0021] S202: For each feature point, according to its scale and distance Calculating the calibration adjustment error ;

[0022] S203: comprehensively considering the calibration effects of all feature points, and performing weighted summation processing on all feature points;

[0023] S204: Constructing an interactive relationship between feature points in view of possible mutual interference between feature points at different times and locations;

[0024] S205: Dynamically adjust the calibration data at different times during the calibration process to ensure the stability and continuity of the calibration parameters, use time series integration to optimize the entire process, and finally obtain the optimized initialization calibration parameters .

[0025] As a preferred solution of the optimization method of calibration parameters of a binocular stereo vision camera described in the present invention, the calibration adjustment error formula is:

[0026]

[0027] in, is an attenuation coefficient used to control the influence of feature point distance on calibration error. The function is used to reduce the effect of error as the distance increases;

[0028] The weighted summation expression of all feature points is:

[0029]

[0030] in, is the weight of the i-th feature point, which is dynamically adjusted according to the importance and credibility of the feature point.

[0031] As a preferred solution of the optimization method of the calibration parameters of a binocular stereo vision camera described in the present invention, the exponential decay function expression used to represent the interaction relationship of feature points is:

[0032]

[0033] in, is the interaction weight between feature points, Control interaction sensitivity, represents the similarity between the i-th and j-th feature points, and M is the total number of feature points.

[0034] As a preferred solution of the optimization method of calibration parameters of a binocular stereo vision camera described in the present invention, the expression of the time series integral is:

[0035]

[0036] in Represents the calibration parameter adjustment within the time period [a, b] during the entire calibration process to ensure that the optimization result adapts to the dynamic changes of the scene.

[0037] As a preferred solution of the optimization method of calibration parameters of a binocular stereo vision camera described in the present invention, the self-learning calibration optimization mechanism includes the following steps:

[0038] S301: Collect calibration data in real time and calculate the current error E(t);

[0039] S302: Calculate the cumulative calibration error using an integral function , introducing the weight influence of historical errors;

[0040] S303: By analyzing the change rate of the cumulative error E(t) evaluates the dynamic trend of the calibration error;

[0041] S304: Based on cumulative error Dynamically adjust the calibration parameter P(t) based on the current error E(t) to ensure that the calibration parameter is adaptive;

[0042] S305: When a significant change in error is detected, further rapid adjustment of calibration parameters To improve the system calibration accuracy.

[0043] As a preferred solution of the optimization method of calibration parameters of a binocular stereo vision camera described in the present invention, the calculation formula of the error E(t) is:

[0044]

[0045] in, is the position of the feature point measured by the camera at the current time t, is the position of the ideal feature point, is the Euclidean distance between two position vectors, representing the calibration error at the current moment;

[0046] The cumulative error function The calculation formula is:

[0047]

[0048] in, is an exponential decay function that controls the weight of recent errors over past errors. is the weight attenuation coefficient. A larger value indicates that errors at more recent times have a greater impact.

[0049] The rate of change of the cumulative error The calculation formula is:

[0050]

[0051] The calculation formula of the calibration parameter P(t) is:

[0052]

[0053] in, is the error feedback adjustment coefficient, which controls the sensitivity of the accumulated error to parameter adjustment; It is the adjustment factor that directly affects the calibration parameters by the control error; N is the number of characteristic points;

[0054] Further quick adjustment of calibration parameters The calculation formula is:

[0055]

[0056] in, It is an adjustment factor used to amplify the error feedback to ensure that the calibration parameters can adapt to rapid adjustments when the error changes greatly.

[0057] The present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for optimizing calibration parameters of a binocular stereo vision camera when executing the computer program;

[0058] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for optimizing calibration parameters of a binocular stereo vision camera.

[0059] The beneficial effects of the present invention are as follows: by performing hierarchical multi-scale modeling on feature points and introducing independent calibration parameters for feature points of different scales, the system can more effectively reduce the calibration error caused by parallax or perspective distortion. In addition, the present invention also introduces a self-learning calibration optimization mechanism that can dynamically adjust the calibration parameters according to real-time feedback data and automatically compensate for significant error changes through cumulative error and change rate analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0061] Figure 1 A schematic diagram of the overall process of a binocular stereo vision camera calibration parameter optimization method proposed by the present invention;

[0062] Figure 2 Schematic diagram of calibration error comparison under different methods and environments. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0066] Reference Figure 1 , is an embodiment of the present invention, and provides a method for optimizing calibration parameters of a binocular stereo vision camera, the method comprising:

[0067] Firstly, the feature points of different scales in the extracted scene are optimized and calibrated hierarchically, a multi-scale feature point model is established, and the scale difference of the feature points is characterized by the scale factor.

[0068] Specifically, the method of hierarchical optimization calibration is:

[0069] S101: Capture multiple feature points in the scene at a distance and near by using a binocular stereo vision camera, and set the feature point set as , is the Nth feature point, each feature point contains its position, scale, and depth information;

[0070] S102: Quantify the scale of each feature point and express it as a scale factor , It is calculated based on the physical size and visual size of different feature points. The calculation formula is:

[0071]

[0072] in, is the depth information of the feature point, is the reference depth value, used to normalize feature points at different depths

[0073] Then, a time series analysis algorithm is used to dynamically optimize the calibration data at different times and adjust the calibration parameters of the camera, so that the calibration process is continuous and stable and can adapt to dynamic changes in the camera and the scene.

[0074] Specifically, the method for dynamic optimization of calibration data is:

[0075] S201: First, each feature point Theoretical calibration value It represents the calibration value of the feature point under ideal conditions, which is calculated by the camera model. The calculation formula is:

[0076]

[0077] in, is the focal length of the camera, B is the baseline distance, is the depth of the feature point;

[0078] S202: For each feature point, according to its scale and distance Calculating the calibration adjustment error ;

[0079]

[0080] in, is an attenuation coefficient used to control the influence of feature point distance on calibration error. The function is used to reduce the effect of error as the distance increases.

[0081] S203: comprehensively considering the calibration effects of all feature points, and performing weighted summation processing on all feature points;

[0082]

[0083] in, is the weight of the i-th feature point, which is dynamically adjusted according to the importance and credibility of the feature point.

[0084] S204: Constructing an interactive relationship between feature points in view of possible mutual interference between feature points at different times and locations.

[0085] The exponential decay function expression used to represent the interaction relationship of feature points is:

[0086]

[0087] in, is the interaction weight between feature points, Control interaction sensitivity, represents the similarity between the i-th and j-th feature points, and M is the total number of feature points.

[0088] S205: Dynamically adjust the calibration data at different times during the calibration process to ensure the stability and continuity of the calibration parameters, use time series integration to optimize the entire process, and finally obtain the optimized initialization calibration parameters ;

[0089] The expression for time series integration is:

[0090]

[0091] in Represents the calibration parameter adjustment within the time period [a, b] during the entire calibration process to ensure that the optimization result adapts to the dynamic changes of the scene

[0092] Finally, a self-learning calibration optimization mechanism is established, that is, error analysis is performed based on real-time feedback data to automatically evaluate the accuracy of current calibration parameters. If a significant change in the calibration error is detected, the calibration parameters are further adjusted based on the feedback information. The self-learning calibration optimization mechanism ensures that the system can be continuously optimized and improves the system's adaptability and robustness in complex dynamic scenarios.

[0093] Specifically, the mechanism includes:

[0094] S301: Collect calibration data in real time and calculate the current error E(t);

[0095]

[0096] in, is the position of the feature point measured by the camera at the current time t, is the position of the ideal feature point, is the Euclidean distance between two position vectors, representing the calibration error at the current moment;

[0097] S302: Calculate the cumulative calibration error using an integral function , introducing the weight influence of historical errors;

[0098] Cumulative error function The calculation formula is:

[0099]

[0100] in, is an exponential decay function that controls the weight of recent errors over past errors. is the weight attenuation coefficient. A larger value indicates that the error at a recent moment has a greater impact. It is an important indicator for subsequent error adjustment, which can reflect the trend of calibration error changes over the entire time period;

[0101] S303: By analyzing the change rate of the cumulative error E(t) evaluates the dynamic trend of the calibration error;

[0102]

[0103] S304: Based on cumulative error Dynamically adjust the calibration parameter P(t) based on the current error E(t) to ensure that the calibration parameter is adaptive;

[0104]

[0105] in, is the error feedback adjustment coefficient, which controls the sensitivity of the accumulated error to parameter adjustment; It is the adjustment factor that directly affects the calibration parameters by the control error; N is the number of feature points

[0106] S305: When a significant change in error is detected, further rapid adjustment of calibration parameters To improve the system calibration accuracy;

[0107]

[0108] in, It is an adjustment factor used to amplify the error feedback to ensure that the calibration parameters can adapt to rapid adjustments when the error changes greatly.

[0109] Reference Figure 2 In the experiment, the calibration accuracy, error analysis and dynamic adjustment effect of the method of the present invention and the traditional calibration method in different scenarios are compared. The specific experimental steps and results are analyzed as follows. Experimental environment: binocular stereo vision camera: resolution is 1920×1080, focal length is 25mm. Scene: contains three feature points of near, medium and far (at 1m, 5m and 10m respectively). Experimental setting: tested in static and dynamic scenes respectively. Measuring tools: calibration plate and automatic calibration software.

[0110] Experimental steps:

[0111] 1. Feature point extraction and hierarchical modeling

[0112] Extract feature points from the scene and divide them into three levels: near, medium, and far according to distance. Establish a multi-scale feature point model, calculate the corresponding scale factor for feature points of different scales, and use the formula To adjust the calibration parameters, ensure that the feature points of each scale can be accurately calibrated.

[0113] 、 Dynamically optimize calibration parameters

[0114] Use time series analysis algorithms to record calibration data at different times. Adjust calibration parameters according to dynamic changes of the camera and scene to ensure the continuity and stability of the calibration process. For slight movement of the camera, the system optimizes the calibration parameters in real time through feedback.

[0115] 、 Self-learning calibration optimization mechanism

[0116] The system analyzes real-time calibration data through an error feedback mechanism and automatically evaluates the accuracy of the current calibration parameters. When it detects that the calibration error changes exceed the set threshold, the system automatically triggers the error compensation mechanism and adjusts the calibration parameters.

[0117] In static and dynamic scenarios, we compared the calibration accuracy of the method of the present invention with that of the traditional calibration method. The experimental data are shown in Tables 1 to 3:

[0118] Table 1: Comparison of calibration errors of different methods in static scenes

[0119] method Close range calibration error (mm) Middle distance calibration error (mm) Long distance calibration error (mm) Traditional calibration method 0.85 2.15 5.32 Calibration method of the present invention 0.52 1.47 3.26

[0120] It can be seen from Table 1 that in static scenes, the calibration method of the present invention has significantly lower errors than the traditional method at all distances, especially in long-distance scenes, where the calibration error of the present invention is reduced by about 39%, thanks to the optimized design of the hierarchical multi-scale feature point model.

[0121] Table 2: Comparison of calibration errors of different methods in dynamic scenes

[0122] method Close range calibration error (mm) Middle distance calibration error (mm) Long distance calibration error (mm) Traditional calibration method 1.12 2.68 6.05 Calibration method of the present invention 0.71 1.92 4.18

[0123] Table 2 shows the calibration results in dynamic scenes. The method of the present invention is also significantly better than the traditional method at all distances, especially in the calibration of medium and long distances. The present invention uses a dynamic calibration optimization mechanism based on time series analysis to continuously adjust the calibration parameters when the camera and the scene change slightly, thus maintaining a high calibration accuracy.

[0124] Table 3: Calibration error adaptive adjustment effect

[0125] method Initial error (mm) Error after adaptive adjustment (mm) Error reduction percentage Traditional calibration method 3.26 1.85 43.25% Calibration method of the present invention 4.18 2.24 46.41%

[0126] It can be seen from Table 3 that the self-learning calibration optimization mechanism of the present invention can effectively reduce the calibration error. Through error analysis and feedback adjustment mechanism, the calibration error can be significantly reduced in both static and dynamic scenes, with the error reduction margin exceeding 40%, thus improving the stability and accuracy of the calibration.

[0127] In summary, the present invention effectively improves the calibration accuracy of feature points at different distances and reduces the calibration error by introducing a multi-scale feature point model. Through real-time feedback error analysis and cumulative error dynamic adjustment mechanism, the system is adaptive and can automatically adjust parameters when the calibration error changes significantly, thereby improving the stability and accuracy of the calibration. The self-learning calibration optimization mechanism ensures that the system can be continuously optimized, improving the system's adaptability and robustness in complex dynamic scenes.

[0128] This embodiment also provides a computer device, which is suitable for a method for optimizing the calibration parameters of a binocular stereo vision camera, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method for optimizing the calibration parameters of a binocular stereo vision camera as proposed in the above embodiment.

[0129] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0130] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method for optimizing the calibration parameters of a binocular stereoscopic vision camera as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage device, a flash memory, a disk or an optical disk.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing calibration parameters of a binocular stereo vision camera, characterized in that: The method comprises the following steps: Perform hierarchical optimization and calibration on the feature points of different scales in the extracted scene, establish a multi-scale feature point model, and characterize the scale difference of the feature points through the scale factor; Use time series analysis algorithms to dynamically optimize calibration data at different times and adjust camera calibration parameters; Establish a self-learning calibration optimization mechanism, that is, perform error analysis based on real-time feedback data to automatically evaluate the accuracy of the current calibration parameters. If a significant change in the calibration error is detected, further adjust the calibration parameters based on the feedback information; The hierarchical optimization calibration method is as follows: S101: Capture multiple feature points in the scene at a distance and near by using a binocular stereo vision camera, and set the feature point set as , is the Nth feature point, each feature point contains its position, scale, and depth information; S102: Quantify the scale of each feature point and express it as a scale factor , It is calculated based on the physical size and visual size of different feature points. The calculation formula is: in, is the depth information of the feature point, It is the reference depth value, which is used to normalize feature points at different depths.

2. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 1, characterized in that: The method for dynamically optimizing the calibration data is: S201: First, each feature point Theoretical calibration value It represents the calibration value of the feature point under ideal conditions, which is calculated by the camera model. The calculation formula is: in, is the focal length of the camera, B is the baseline distance, is the depth of the feature point; S202: For each feature point, according to its scale and distance Calculating the calibration adjustment error ; S203: comprehensively considering the calibration effects of all feature points, and performing weighted summation processing on all feature points; S204: constructing an interactive relationship between feature points based on mutual interference between feature points at different times and locations; S205: Dynamically adjust the calibration data at different times during the calibration process to ensure the stability and continuity of the calibration parameters, use time series integration to optimize the entire process, and finally obtain the optimized initialization calibration parameters .

3. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 2, characterized in that: The calibration adjustment error formula is: in, is an attenuation coefficient used to control the influence of feature point distance on calibration error. The function is used to reduce the effect of error as the distance increases; The weighted summation expression of all feature points is: in, is the weight of the i-th feature point, which is dynamically adjusted according to the importance and credibility of the feature point.

4. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 3, characterized in that: The exponential decay function expression used to represent the interaction relationship of feature points is: in, is the interaction weight between feature points, Control interaction sensitivity, represents the similarity between the i-th and j-th feature points, and M is the total number of feature points.

5. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 4, characterized in that: The expression of the time series integral is: in Represents the calibration parameter adjustment within the time period [a, b] during the entire calibration process to ensure that the optimization result adapts to the dynamic changes of the scene.

6. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 5, characterized in that: The self-learning calibration optimization mechanism comprises the following steps: S301: Collect calibration data in real time and calculate the current error E(t); S302: Calculate the cumulative calibration error using an integral function , introducing the weight influence of historical errors; S303: By analyzing the change rate of the cumulative error E(t) evaluates the dynamic trend of the calibration error; S304: Based on cumulative error Dynamically adjust the calibration parameter P(t) based on the current error E(t) to ensure that the calibration parameter is adaptive; S305: When a significant change in error is detected, further rapid adjustment of calibration parameters To improve the system calibration accuracy.

7. The method for optimizing calibration parameters of a binocular stereo vision camera according to claim 6, characterized in that: The calculation formula of the error E(t) is: in, is the position of the feature point measured by the camera at the current time t, is the position of the ideal feature point, is the Euclidean distance between two position vectors, representing the calibration error at the current moment; The cumulative error function The calculation formula is: in, is an exponential decay function, which is used to control the recent errors to have higher weights than the past errors. is the weight decay coefficient, The rate of change of the cumulative error The calculation formula is: The calculation formula of the calibration parameter P(t) is: in, is the error feedback adjustment coefficient, which controls the sensitivity of the accumulated error to parameter adjustment; It is the adjustment factor that directly affects the calibration parameters by the control error; N is the number of characteristic points; Further quick adjustment of calibration parameters The calculation formula is: in, It is an adjustment factor used to amplify the error feedback to ensure that the calibration parameters can adapt to rapid adjustments when the error changes greatly.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the calibration parameters of a binocular stereo vision camera as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for optimizing calibration parameters of a binocular stereo vision camera as described in any one of claims 1 to 7 are implemented.

Images