A positioning method and device integrating computer vision and inertial sensor

By analyzing the ambient light quality and information data synchronization, and choosing an appropriate fusion method to improve the accuracy of vehicle positioning, the problem of reduced positioning accuracy in the prior art is solved, and more efficient information data fusion is achieved.

CN118533186BActive Publication Date: 2024-11-08诚芯智联(武汉)科技技术有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410467325.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-18
Publication Date
2024-11-08
Estimated Expiration
2044-04-18

AI Technical Summary

Technical Problem

In the prior art, computer vision and inertial sensor data are fused, and the selection analysis of the synchronization of ambient light quality and information data is lacking, resulting in a reduction in positioning accuracy.

Method used

By obtaining the brightness data of the environmental image and the speed information of the inertial sensor, calculating the light quality performance value and information synchronization value, selecting the appropriate fusion method (loose coupling or tight coupling) to improve positioning effect and accuracy, and using analytical signals and deviation characteristics Values ​​are further optimized to adapt to different environments.

Benefits of technology

It improves the accuracy of vehicle positioning and the flexibility of information data fusion, solves the problem of reduced positioning accuracy caused by tight coupling when information data is highly out of synchronization, and enhances the accuracy of the fusion method.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118533186B_ABST
    Figure CN118533186B_ABST
Patent Text Reader

Abstract

The present invention relates to a positioning method and device integrating computer vision and inertial sensor, comprising: obtaining first posture information and second posture information of a vehicle; obtaining brightness data of an environment image, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image; obtaining acquisition time data of the environment image and time data of vehicle speed information captured by an inertial sensor, and processing the acquisition time data of the environment image and the time data of vehicle speed information captured by the inertial sensor to obtain an information synchronization value ZWe; respectively comparing the light quality performance value SDF and the information synchronization value ZWe with corresponding preset thresholds, and selecting a suitable fusion mode from information data fusion modes, i.e., loose coupling and tight coupling, according to the synchronization between the environment light quality and the information data to fuse the first posture information and the second posture information, thereby improving the positioning effect and accuracy of the vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of automobile positioning, and in particular to a positioning method and device integrating computer vision and inertial sensors. Background Art

[0002] With the continuous development of science and technology, positioning technology has been widely used in various fields, such as unmanned driving, robot navigation, virtual reality, etc. At present, the commonly used positioning methods mainly include GPS-based positioning, computer vision-based positioning, and inertial sensor-based positioning. However, each of these methods has certain limitations.

[0003] A Chinese invention patent with publication number CN112113564A discloses a positioning method and system based on image sensors and inertial sensors, including: obtaining the image sensor-based pose information and the inertial sensor-based pose information of the characteristic pattern deployed on the positioning target; then, using a graph optimization method to optimize the image sensor-based pose information and the inertial sensor-based pose information to obtain the orientation information of the positioning target.

[0004] In the above-mentioned prior art, the positioning of the target is achieved through data fusion optimization, and in the prior art, most of the data fusion methods are used for target positioning, but there is a lack of selection and analysis of the fusion method. Different fusion methods are closely related to the data acquisition environment and the synchronization between data. If the fusion method cannot be selected specifically according to the data acquisition environment and the synchronization between data, it is impossible to ensure that the target can be accurately positioned after data fusion optimization. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the present invention selects a suitable fusion method to fuse the first posture information and the second posture information in the information data fusion mode, namely, loose coupling and tight coupling, according to the synchronization between the ambient light quality and the information data, thereby improving the positioning effect and accuracy of the vehicle.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: A positioning method integrating computer vision and inertial sensors, comprising:

[0007] Step 1: Based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained;

[0008] Step 2: Obtaining brightness data of the environment image, wherein the brightness data includes a brightness value, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0009] Step 3: Obtaining the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information, wherein the acquisition time data of the environment image includes the acquisition time point of each frame of the environment image, and the time data of the inertial sensor capturing the vehicle speed information includes the time point when the inertial sensor captures the vehicle speed information each time, and processing the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information to obtain the information synchronization value ZWe;

[0010] Step 4: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0011] Step 5: Based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation characterization value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation characterization value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation characterization threshold respectively, and select the final fusion method according to the comparison results.

[0012] As a further technical solution of the present invention, the light quality performance value SDF is obtained by multiplying the ambient light illuminance mean ratio and the ambient light stability parameter;

[0013] Among them, the method for obtaining the average ratio of ambient light illumination is:

[0014] The ambient image is divided into several image unit areas of equal area, the brightness value of each image unit area is obtained, the brightness values ​​of all image unit sub-areas are summed and averaged to obtain the brightness value of the ambient image, the brightness values ​​of all ambient images are summed and averaged to obtain the ambient light brightness mean, the ambient light brightness mean is ratioed with the ambient light brightness threshold to obtain the ambient light brightness mean ratio.

[0015] As a further technical solution of the present invention, the method for obtaining the ambient light stability parameter is:

[0016] Mark the brightness values ​​of all environmental images in the XY two-dimensional coordinate system, and connect the marked brightness value points with a curve to obtain a brightness change curve. Mark the mean value of the ambient light illumination on the Y axis, draw a straight line parallel to the X axis through the mark point of the mean value of the ambient light illumination, and mark the straight line as the reference line;

[0017] The area enclosed by the reference line and the brightness change curve is measured and marked as the fluctuation area. The area enclosed by the reference line and the X-axis is measured and marked as the reference area. The fluctuation area and the reference area are ratio-processed to obtain the fluctuation area ratio.

[0018] The overlap length between the reference line and the brightness variation curve and the length of the reference line are measured, and the ratio is processed to obtain a stable overlap length ratio;

[0019] The vertical distances between all the peak points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the peak distance mean; the vertical distances between all the trough points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the trough distance mean; the peak distance mean and the trough distance mean are summed to obtain the fluctuation distance mean; the fluctuation distance mean is ratioed with the fluctuation distance mean threshold to obtain the fluctuation distance mean ratio;

[0020] The fluctuation area ratio, stable overlap length ratio and fluctuation distance mean ratio are marked as CV, CB and CM respectively, and the data are processed by the formula: The ambient light stability parameter CKg is obtained, wherein s1, s2 and s3 are all preset proportional coefficients.

[0021] As a further technical solution of the present invention, the information synchronization value ZWe is obtained by processing the obtained number proportion HU of the abnormal corresponding groups and the mean proportion HJ of the time difference of the abnormal corresponding groups, and using the formula: The information synchronization value ZWe is obtained, where a1 and a2 are both preset proportional coefficients;

[0022] The number ratio HU of the abnormal corresponding groups and the time difference mean ratio HJ of the abnormal corresponding groups are obtained by arranging each frame of the environment image in sequence according to the acquisition time point, and at the same time, arranging the vehicle speed information captured by the inertial sensor in sequence according to the time point of capturing the vehicle speed information;

[0023] Matching each frame of the environment image with the vehicle speed information captured by the inertial sensor each time, and integrating the corresponding environment image and vehicle speed information into a corresponding group;

[0024] In each corresponding group, the acquisition time point of the environment image in the corresponding group is matched with the capture time point of the vehicle speed information:

[0025] If the acquisition time point of the environment image successfully matches the capture time point of the vehicle speed information, the corresponding group is marked as a normal corresponding group;

[0026] If the acquisition time point of the environment image fails to match the capture time point of the vehicle speed information, the corresponding group is marked as an abnormal corresponding group;

[0027] Count the number of abnormal corresponding groups and the number of all corresponding groups, and perform ratio processing to obtain the number ratio HU of abnormal corresponding groups;

[0028] Obtaining the time difference between the acquisition time point of the environment image in the abnormal corresponding group and the capture time point of the vehicle speed information, and marking it as the time difference of the abnormal corresponding group;

[0029] The time differences of all abnormal corresponding groups are summed up and averaged to obtain the mean time difference of the abnormal corresponding group. The mean time difference of the abnormal corresponding group is ratioed with the acquisition duration of the environmental image to obtain the mean time difference ratio HJ of the abnormal corresponding group.

[0030] As a further technical solution of the present invention, the process of generating the analysis signal is:

[0031] If the light quality performance value SDF≥SDG and the information synchronization value ZWe<ZWg, a first analysis signal is generated;

[0032] If the light quality performance value SDF<SDG and the information synchronization value ZWe≥ZWg, a second analysis signal is generated;

[0033] If the light quality representation value SDF<SDG and the information synchronization value ZWe<ZWg, a third analysis signal is generated.

[0034] As a further technical solution of the present invention, the information synchronization difference ZWc is obtained by performing difference processing on the information synchronization value ZWe and the information synchronization threshold ZWg, and taking the absolute value of the difference;

[0035] The illumination quality performance difference SDe is obtained by performing difference processing on the illumination quality performance value SDF and the illumination quality performance threshold value SDG, and taking the absolute value of the difference;

[0036] The comprehensive deviation characterization value RG is obtained by multiplying the information synchronization difference ZWc and the illumination quality performance difference SDe.

[0037] As a further technical solution of the present invention, the process of selecting the final fusion method includes:

[0038] Based on the first analysis signal, if the information synchronization difference ZWc ≥ the information synchronization difference threshold, a loose coupling method is selected to fuse the first pose information and the second pose information;

[0039] If the information synchronization difference ZWc is less than the information synchronization difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information;

[0040] Based on the second analysis signal, if the illumination quality performance difference SDe ≥ the illumination quality performance difference threshold, a loosely coupled method is selected to fuse the first pose information and the second pose information;

[0041] If the illumination quality performance difference SDe is less than the illumination quality performance difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information;

[0042] Based on the third analysis signal, if the comprehensive deviation representation value RG is greater than or equal to the comprehensive deviation representation threshold, a loose coupling method is selected to fuse the first pose information and the second pose information;

[0043] If the comprehensive deviation characterization value RG is less than the comprehensive deviation characterization threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information.

[0044] A positioning device integrating computer vision and inertial sensors, comprising:

[0045] Information acquisition module: based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained;

[0046] The first data acquisition module is used to acquire brightness data of the environment image, wherein the brightness data includes a brightness value, and obtain a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0047] Second data acquisition module: environmental image acquisition time data and inertial sensor capture vehicle speed information time data, wherein the environmental image acquisition time data includes each frame of environmental image acquisition time point, the inertial sensor capture vehicle speed information time data includes each time point of the inertial sensor capture vehicle speed information, the environmental image acquisition time data and the inertial sensor capture vehicle speed information time data are processed to obtain the information synchronization value ZWe;

[0048] Preliminary selection module: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0049] Select the analysis module: based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation representation value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation representation value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation representation threshold respectively, and select the final fusion method according to the comparison results.

[0050] An electronic device, comprising:

[0051] Memory for storing computer software programs;

[0052] A processor is used to read and execute the computer software program, thereby implementing the positioning method integrating computer vision and inertial sensors as described in any one of claims 1 to 7.

[0053] A non-transitory computer-readable storage medium stores a computer software program, and when the computer software program is executed by a processor, the positioning method of integrating computer vision and inertial sensors is implemented.

[0054] The beneficial effects of the present invention are:

[0055] 1. The present invention obtains the first posture information of the vehicle based on the environmental image, obtains the second posture information of the vehicle based on the speed information of the vehicle, processes and analyzes the brightness of the environmental image to obtain a light quality performance value, analyzes and processes the acquisition time of the environmental image and the capture time of the vehicle information to obtain an information synchronization value, and overall, according to the synchronization between the environmental light quality and the information data, in the information data fusion mode, that is, loose coupling and tight coupling, a suitable fusion mode is selected to fuse the first posture information and the second posture information, thereby improving the positioning effect and accuracy of the vehicle, and by analyzing and selecting different fusion modes, while improving the flexibility of information data fusion, the problem of reduced positioning accuracy caused by tight coupling of information data under highly asynchronous conditions is solved.

[0056] 2. The present invention obtains the information synchronization difference ZWc based on the first analysis signal, obtains the lighting quality performance difference SDe based on the second analysis signal, and obtains the comprehensive deviation characterization value RG based on the third analysis signal when both the lighting quality performance value SDF and the information synchronization value ZWe are not greater than or equal to the corresponding preset threshold value or are not greater than or equal to the corresponding preset threshold value. The information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation characterization value RG are respectively compared with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation characterization threshold, and the final fusion method is selected according to the comparison result. When the lighting quality and information synchronization do not meet or do not meet the threshold standard, the present invention further analyzes the deviation of the lighting quality deviation and the information synchronization, and selects the final fusion method according to the size of the deviation. When the deviation is small, the misjudgment of the initial selection can be prevented, and the accuracy of the fusion method selection can be improved, thereby further improving the accuracy of vehicle positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of the method steps of Example 1 of the present invention;

[0058] Figure 2 This is a flow chart of the method steps of Embodiment 2 of the present invention;

[0059] Figure 3 is a flowchart of embodiment 3 of the present invention;

[0060] Figure 4 This is a diagram of an electronic device according to Embodiment 4 of the present invention;

[0061] Figure 5 This is a diagram of a non-transitory computer-readable storage medium according to Embodiment 5 of the present invention.

[0062] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0063] 500. Electronic device, 510. Memory, 511. Computer program, 520. Processor, 600. Computer-readable storage medium. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0065] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0066] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0067] Example 1

[0068] like Figure 1 As shown, a positioning method integrating computer vision and inertial sensors according to an embodiment of the present invention includes:

[0069] Step 1: collecting an environment image when the vehicle is traveling, obtaining the first posture information of the vehicle based on the processing of the environment image, collecting the speed information of the vehicle, and obtaining the second posture information of the vehicle based on the processing of the speed information of the vehicle, wherein the speed information of the vehicle includes acceleration and angular velocity;

[0070] In some embodiments, unique feature points are extracted from the environment through an image processing algorithm, and matching feature point pairs are found between environment images using a feature matching algorithm. The camera is calibrated to obtain the camera's intrinsic parameters and distortion parameters, and the relative position and orientation of the vehicle, i.e., the first pose information, is obtained using the feature point pairs and camera parameters and a PnP solution method.

[0071] In some embodiments, an inertial sensor is used to collect the acceleration and angular velocity of the vehicle, wherein the inertial sensor includes but is not limited to a gyroscope and an accelerometer, and the acceleration is double-integrated to obtain the relative displacement of the vehicle. At the same time, the angular velocity of the vehicle is measured by the gyroscope, and the attitude of the vehicle can be obtained by integrating the angular velocity, wherein the relative displacement of the vehicle and the attitude of the vehicle are the second posture information;

[0072] It should be noted that the acquisition time of the environment image is equal to the acquisition time of the acceleration information and angular velocity information of the vehicle;

[0073] Step 2: Obtaining brightness data of the environment image, wherein the brightness data includes a brightness value, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0074] Among them, the light quality performance value SDF is obtained by multiplying the ambient light illuminance mean ratio and the ambient light stability parameter;

[0075] Among them, the method for obtaining the average ratio of ambient light illumination is:

[0076] The environment image is divided into a number of image unit areas of equal area, the brightness value of each image unit area is obtained, the brightness values ​​of all image unit sub-areas are summed and averaged to obtain the brightness value of the environment image, the brightness values ​​of all environment images are summed and averaged to obtain the mean value of the ambient light illumination, the mean value of the ambient light illumination is processed by ratio processing with the ambient light illumination threshold value to obtain the ambient light illumination mean ratio;

[0077] In some embodiments, the image is read using the cv2.imread() function of OpenCV, and then the image is separated into red, green, and blue channels using the cv2.sp lit() function to obtain the values ​​of the red, green, and blue channels of the image, and the brightness value of the image is obtained according to the brightness formula: brightness = 0.299×R+0.587×G+0.114×B, where R, G, and B represent the values ​​of the red, green, and blue channels of the pixel, respectively. The method for obtaining the brightness value of the sub-area of ​​the image unit is the same;

[0078] The ambient light stability parameter is obtained based on the ambient light average illuminance ratio acquisition method. The ambient light stability parameter is obtained as follows:

[0079] Mark the brightness values ​​of all environmental images in the XY two-dimensional coordinate system, and connect the marked brightness value points with a curve to obtain a brightness change curve. Mark the mean value of the ambient light illumination on the Y axis, draw a straight line parallel to the X axis through the mark point of the mean value of the ambient light illumination, and mark the straight line as the reference line;

[0080] The constraint conditions of the baseline are: the length of the baseline is equal to the horizontal length of the brightness change curve;

[0081] The area enclosed by the reference line and the brightness change curve is measured and marked as the fluctuation area. The area enclosed by the reference line and the X-axis is measured and marked as the reference area. The fluctuation area and the reference area are ratio-processed to obtain the fluctuation area ratio.

[0082] The overlap length between the reference line and the brightness variation curve and the length of the reference line are measured, and the ratio is processed to obtain a stable overlap length ratio;

[0083] The vertical distances between all the peak points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the peak distance mean; the vertical distances between all the trough points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the trough distance mean; the peak distance mean and the trough distance mean are summed to obtain the fluctuation distance mean; the fluctuation distance mean is ratioed with the fluctuation distance mean threshold to obtain the fluctuation distance mean ratio;

[0084] The fluctuation area ratio, stable overlap length ratio, and fluctuation distance mean ratio are marked as CV, CB, and CM, respectively;

[0085] The fluctuation area ratio CV, the stable overlap length ratio CB and the fluctuation distance mean ratio CM are processed by the formula: Obtaining the ambient light stability parameter CKg, where s1, s2 and s3 are all preset proportional coefficients;

[0086] It should be noted that the purpose of obtaining the light quality performance value SDF is to select different fusion modes when fusing the first pose information and the second pose information later, wherein the fusion modes include tight coupling and loose coupling. The selection of the fusion mode has an impact on the sufficiency and stability of the ambient light. The embodiment of the present invention analyzes the sufficiency and stability of the ambient light through the brightness of the image and the brightness change between each frame of the image. The obtained light quality performance value SDF combines the ambient light luminance mean ratio and the ambient light stability parameter, and uses the light quality performance value SDF to reflect the sufficiency and stability of the ambient light as a whole.

[0087] Step 3: Obtaining the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information, wherein the acquisition time data of the environment image includes the acquisition time point of each frame of the environment image, and the time data of the inertial sensor capturing the vehicle speed information includes the time point when the inertial sensor captures the vehicle speed information each time, and processing and analyzing the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information to obtain information synchronization data, wherein the information synchronization data includes the information synchronization value ZWe;

[0088] Specifically, each frame of the environment image is arranged in sequence according to the acquisition time point, and at the same time, the vehicle speed information captured by the inertial sensor is also arranged in sequence according to the time point when the vehicle speed information is captured;

[0089] Matching each frame of the environment image with the vehicle speed information captured by the inertial sensor each time, and integrating the corresponding environment image and vehicle speed information into a corresponding group;

[0090] In each corresponding group, the acquisition time point of the environment image in the corresponding group is matched with the capture time point of the vehicle speed information:

[0091] If the acquisition time point of the environment image successfully matches the capture time point of the vehicle speed information, the corresponding group is marked as a normal corresponding group;

[0092] If the acquisition time point of the environment image fails to match the capture time point of the vehicle speed information, the corresponding group is marked as an abnormal corresponding group;

[0093] Count the number of abnormal corresponding groups and the number of all corresponding groups, and perform ratio processing to obtain the number ratio HU of abnormal corresponding groups;

[0094] Obtaining the time difference between the acquisition time point of the environment image in the abnormal corresponding group and the capture time point of the vehicle speed information, and marking it as the time difference of the abnormal corresponding group;

[0095] The time differences of all abnormal corresponding groups are summed and averaged to obtain the mean time difference of the abnormal corresponding group, and the mean time difference of the abnormal corresponding group is processed by ratio processing with the acquisition duration of the environmental image to obtain the mean time difference ratio HJ of the abnormal corresponding group;

[0096] The obtained data of the proportion of the number of abnormal corresponding groups HU and the proportion of the mean time difference of the abnormal corresponding groups HJ are processed by the formula: The information synchronization value ZWe is obtained, where a1 and a2 are both preset proportional coefficients;

[0097] It should be noted that the purpose of obtaining the information synchronization value ZWe is that the information synchronization value ZWe combines the number proportion HU of the abnormal corresponding group and the mean time difference proportion HJ of the abnormal corresponding group, reflecting the synchronization between the frame number of the environmental image and the vehicle information data obtained by the inertial sensor. The tightly coupled data fusion method is closely related to the synchronization between the data. If the data synchronization is not analyzed, the data will be fused in a tightly coupled manner, which will lead to inaccurate vehicle positioning results after fusion.

[0098] Step 4: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the illumination quality performance threshold and the information synchronization threshold; if the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information; if the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0099] Specifically, the preset illumination quality performance threshold is SDG, and the preset information synchronization threshold is ZWg;

[0100] If the light quality performance value SDF≥SDG and the information synchronization value ZWe≥ZWg, the first pose information and the second pose information are fused in a tightly coupled manner, and the fused output result is the vehicle positioning result;

[0101] If the light quality performance value SDF≥SDG and the information synchronization value ZWe<ZWg, a first analysis signal is generated;

[0102] If the light quality performance value SDF<SDG and the information synchronization value ZWe≥ZWg, a second analysis signal is generated;

[0103] If the illumination quality performance value SDF<SDG and the information synchronization value ZWe<ZWg, a third analysis signal is generated;

[0104] The technical solution of the embodiment of the present invention is: obtaining the first posture information of the vehicle based on the environmental image, obtaining the second posture information of the vehicle based on the speed information of the vehicle, processing and analyzing the brightness of the environmental image to obtain the light quality performance value, analyzing and processing the acquisition time of the environmental image and the capture time of the vehicle information to obtain the information synchronization value, and overall, according to the synchronization between the ambient light quality and the information data, in the information data fusion mode, that is, loose coupling and tight coupling, selecting a suitable fusion mode to fuse the first posture information and the second posture information, thereby improving the positioning effect and accuracy of the vehicle, and by analyzing and selecting different fusion modes, while improving the flexibility of information data fusion, the problem of reduced positioning accuracy caused by tight coupling of information data under highly asynchronous conditions is solved.

[0105] Example 2

[0106] Based on Example 1, Figure 2 As shown, a positioning method integrating computer vision and inertial sensors according to an embodiment of the present invention further includes:

[0107] Step 5: Based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the light quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation representation value RG, and compare the information synchronization difference ZWc, the light quality performance difference SDe and the comprehensive deviation representation value RG with the information synchronization difference threshold, the light quality performance difference threshold and the comprehensive deviation representation threshold respectively, and select the final fusion method according to the comparison results;

[0108] Specifically, the information synchronization difference ZWc is obtained by performing difference processing on the information synchronization value ZWe and the information synchronization threshold ZWg, and taking the absolute value of the difference;

[0109] The illumination quality performance difference SDe is obtained by performing difference processing between the illumination quality performance value SDF and the illumination quality performance threshold value SDG, and taking the absolute value of the difference;

[0110] The comprehensive deviation representation value RG is obtained by multiplying the information synchronization difference ZWc and the illumination quality performance difference SDe;

[0111] The information synchronization difference ZWc, the illumination quality difference SDe and the comprehensive deviation characterization value RG are respectively compared with the information synchronization difference threshold, the illumination quality difference threshold and the comprehensive deviation characterization threshold. The specific comparison process is as follows:

[0112] Based on the first analysis signal, if the information synchronization difference ZWc ≥ the information synchronization difference threshold, a loose coupling method is selected to fuse the first pose information and the second pose information;

[0113] If the information synchronization difference ZWc is less than the information synchronization difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information;

[0114] Based on the second analysis signal, if the illumination quality performance difference SDe ≥ the illumination quality performance difference threshold, a loosely coupled method is selected to fuse the first pose information and the second pose information;

[0115] If the illumination quality performance difference SDe is less than the illumination quality performance difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information;

[0116] Based on the third analysis signal, if the comprehensive deviation representation value RG is greater than or equal to the comprehensive deviation representation threshold, a loose coupling method is selected to fuse the first pose information and the second pose information;

[0117] If the comprehensive deviation characterization value RG is less than the comprehensive deviation characterization threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information;

[0118] The first pose information and the second pose information are fused through loose coupling or tight coupling, and the output result is the positioning result of the vehicle;

[0119] The technical solution of the embodiment of the present invention is: when the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset threshold or are not both greater than or equal to the corresponding preset threshold, based on the first analysis signal, the information synchronization difference ZWc is obtained, based on the second analysis signal, the illumination quality performance difference SDe is obtained, and based on the third analysis signal, the comprehensive deviation characterization value RG is obtained, and the information synchronization difference ZWc, the illumination quality performance difference SDe and the comprehensive deviation characterization value RG are respectively compared with the information synchronization difference threshold, the illumination quality performance difference threshold and the comprehensive deviation characterization threshold, and the final fusion method is selected according to the comparison result. When the illumination quality and information synchronization do not meet or do not meet the threshold standard, the present invention further analyzes the deviation of the illumination quality deviation and the information synchronization, and selects the final fusion method according to the size of the deviation. When the deviation is small, the misjudgment of the initial selection can be prevented, and the accuracy of the fusion method selection can be improved, thereby further improving the accuracy of vehicle positioning.

[0120] Example 3

[0121] like Figure 3 As shown, a positioning device integrating computer vision and inertial sensors according to an embodiment of the present invention includes:

[0122] Information acquisition module: based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained;

[0123] The first data acquisition module is used to acquire brightness data of the environment image, wherein the brightness data includes a brightness value, and obtain a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0124] Second data acquisition module: environmental image acquisition time data and inertial sensor capture vehicle speed information time data, wherein the environmental image acquisition time data includes each frame of environmental image acquisition time point, the inertial sensor capture vehicle speed information time data includes each time point of the inertial sensor capture vehicle speed information, the environmental image acquisition time data and the inertial sensor capture vehicle speed information time data are processed to obtain the information synchronization value ZWe;

[0125] Preliminary selection module: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0126] Select the analysis module: based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation representation value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation representation value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation representation threshold respectively, and select the final fusion method according to the comparison results.

[0127] Example 4

[0128] See also Figure 4 , Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0129] Step 1: Based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained;

[0130] Step 2: Obtaining brightness data of the environment image, wherein the brightness data includes a brightness value, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0131] Step 3: Obtaining the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information, wherein the acquisition time data of the environment image includes the acquisition time point of each frame of the environment image, and the time data of the inertial sensor capturing the vehicle speed information includes the time point when the inertial sensor captures the vehicle speed information each time, and processing the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information to obtain the information synchronization value ZWe;

[0132] Step 4: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0133] Step 5: Based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation characterization value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation characterization value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation characterization threshold respectively, and select the final fusion method according to the comparison results.

[0134] Example 5

[0135] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 511 is stored. When the computer program 511 is executed by the processor 520, the following steps are implemented:

[0136] Step 1: Based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained;

[0137] Step 2: Obtaining brightness data of the environment image, wherein the brightness data includes a brightness value, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image;

[0138] Step 3: Obtaining the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information, wherein the acquisition time data of the environment image includes the acquisition time point of each frame of the environment image, and the time data of the inertial sensor capturing the vehicle speed information includes the time point when the inertial sensor captures the vehicle speed information each time, and processing the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information to obtain the information synchronization value ZWe;

[0139] Step 4: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal;

[0140] Step 5: Based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation characterization value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation characterization value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation characterization threshold respectively, and select the final fusion method according to the comparison results.

[0141] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0147] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A positioning method integrating computer vision and inertial sensors, characterized in that: include: Step 1: Based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained; Step 2: Obtaining brightness data of the environment image, wherein the brightness data includes a brightness value, and obtaining a light quality performance value SDF based on processing and analyzing the brightness data of the environment image; The light quality performance value SDF is obtained by multiplying the ambient light luminance mean ratio and the ambient light stability parameter; Among them, the method for obtaining the average ratio of ambient light illumination is: The environment image is divided into a number of image unit areas of equal area, the brightness value of each image unit area is obtained, the brightness values ​​of all image unit sub-areas are summed and averaged to obtain the brightness value of the environment image, the brightness values ​​of all environment images are summed and averaged to obtain the mean value of the ambient light illumination, the mean value of the ambient light illumination is processed by ratio processing with the ambient light illumination threshold value to obtain the ambient light illumination mean ratio; The method for obtaining the ambient light stability parameter is as follows: Mark the brightness values ​​of all environmental images in the XY two-dimensional coordinate system, and connect the marked brightness value points with a curve to obtain a brightness change curve. Mark the mean value of the ambient light illumination on the Y axis, draw a straight line parallel to the X axis through the mark point of the mean value of the ambient light illumination, and mark the straight line as the reference line; The area enclosed by the reference line and the brightness change curve is measured and marked as the fluctuation area. The area enclosed by the reference line and the X-axis is measured and marked as the reference area. The fluctuation area and the reference area are ratio-processed to obtain the fluctuation area ratio. The overlap length between the reference line and the brightness variation curve and the length of the reference line are measured, and the ratio is processed to obtain a stable overlap length ratio; The vertical distances between all the peak points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the peak distance mean; the vertical distances between all the trough points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the trough distance mean; the peak distance mean and the trough distance mean are summed to obtain the fluctuation distance mean; the fluctuation distance mean is ratioed with the fluctuation distance mean threshold to obtain the fluctuation distance mean ratio; The fluctuation area ratio, stable overlap length ratio and fluctuation distance mean ratio are marked as CV, CB and CM respectively, and the data are processed by the formula: Obtaining the ambient light stability parameter CKg, where s1, s2 and s3 are all preset proportional coefficients; Step 3: Obtaining the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information, wherein the acquisition time data of the environment image includes the acquisition time point of each frame of the environment image, and the time data of the inertial sensor capturing the vehicle speed information includes the time point when the inertial sensor captures the vehicle speed information each time, and processing the acquisition time data of the environment image and the time data of the inertial sensor capturing the vehicle speed information to obtain the information synchronization value ZWe; Step 4: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal; Step 5: Based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation characterization value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation characterization value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation characterization threshold respectively, and select the final fusion method according to the comparison results.

2. The positioning method integrating computer vision and inertial sensor according to claim 1, characterized in that: The information synchronization value ZWe is obtained by processing the obtained number proportion HU of the abnormal corresponding groups and the mean proportion HJ of the time difference of the abnormal corresponding groups, and using the formula: ZWe= The information synchronization value ZWe is obtained, where a1 and a2 are both preset proportional coefficients; The number ratio HU of the abnormal corresponding groups and the time difference mean ratio HJ of the abnormal corresponding groups are obtained by arranging each frame of the environment image in sequence according to the acquisition time point, and at the same time, arranging the vehicle speed information captured by the inertial sensor in sequence according to the time point of capturing the vehicle speed information; Matching each frame of the environment image with the vehicle speed information captured by the inertial sensor each time, and integrating the corresponding environment image and vehicle speed information into a corresponding group; In each corresponding group, the acquisition time point of the environment image in the corresponding group is matched with the capture time point of the vehicle speed information: If the acquisition time point of the environment image successfully matches the capture time point of the vehicle speed information, the corresponding group is marked as a normal corresponding group; If the acquisition time point of the environment image fails to match the capture time point of the vehicle speed information, the corresponding group is marked as an abnormal corresponding group; Count the number of abnormal corresponding groups and the number of all corresponding groups, and perform ratio processing to obtain the number ratio HU of abnormal corresponding groups; Obtaining the time difference between the acquisition time point of the environment image in the abnormal corresponding group and the capture time point of the vehicle speed information, and marking it as the time difference of the abnormal corresponding group; The time differences of all abnormal corresponding groups are summed up and averaged to obtain the mean time difference of the abnormal corresponding group. The mean time difference of the abnormal corresponding group is ratioed with the acquisition duration of the environmental image to obtain the mean time difference ratio HJ of the abnormal corresponding group.

3. The positioning method integrating computer vision and inertial sensor according to claim 1, characterized in that: The process of generating the analysis signal is as follows: If the light quality performance value SDF≥SDG and the information synchronization value ZWe<ZWg, a first analysis signal is generated; If the light quality performance value SDF<SDG and the information synchronization value ZWe≥ZWg, a second analysis signal is generated; If the light quality representation value SDF<SDG and the information synchronization value ZWe<ZWg, a third analysis signal is generated.

4. The positioning method integrating computer vision and inertial sensor according to claim 1, characterized in that: The information synchronization difference ZWc is obtained by performing difference processing on the information synchronization value ZWe and the information synchronization threshold ZWg, and taking the absolute value of the difference; The illumination quality performance difference SDe is obtained by performing difference processing on the illumination quality performance value SDF and the illumination quality performance threshold value SDG, and taking the absolute value of the difference; The comprehensive deviation characterization value RG is obtained by multiplying the information synchronization difference ZWc and the illumination quality performance difference SDe.

5. The positioning method integrating computer vision and inertial sensor according to claim 3, characterized in that: The process of selecting the final fusion method according to the comparison result includes: Based on the first analysis signal, if the information synchronization difference ZWc ≥ the information synchronization difference threshold, a loose coupling method is selected to fuse the first pose information and the second pose information; If the information synchronization difference ZWc is less than the information synchronization difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information; Based on the second analysis signal, if the illumination quality performance difference SDe ≥ the illumination quality performance difference threshold, a loosely coupled method is selected to fuse the first pose information and the second pose information; If the illumination quality performance difference SDe is less than the illumination quality performance difference threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information; Based on the third analysis signal, if the comprehensive deviation representation value RG is greater than or equal to the comprehensive deviation representation threshold, a loose coupling method is selected to fuse the first pose information and the second pose information; If the comprehensive deviation characterization value RG is less than the comprehensive deviation characterization threshold, a tightly coupled method is selected to fuse the first pose information and the second pose information.

6. A positioning device integrating computer vision and inertial sensors, the device implementing the positioning method integrating computer vision and inertial sensors as claimed in any one of claims 1 to 5, characterized in that: include: Information acquisition module: based on the processing of the environment image, the first posture information of the vehicle is obtained, and based on the processing of the vehicle speed information, the second posture information of the vehicle is obtained; The first data acquisition module is used to acquire brightness data of the environment image, wherein the brightness data includes a brightness value, and obtain a light quality performance value SDF based on processing and analyzing the brightness data of the environment image; The light quality performance value SDF is obtained by multiplying the ambient light luminance mean ratio and the ambient light stability parameter; Among them, the method for obtaining the average ratio of ambient light illumination is: The environment image is divided into a number of image unit areas of equal area, the brightness value of each image unit area is obtained, the brightness values ​​of all image unit sub-areas are summed and averaged to obtain the brightness value of the environment image, the brightness values ​​of all environment images are summed and averaged to obtain the mean value of the ambient light illumination, the mean value of the ambient light illumination is processed by ratio processing with the ambient light illumination threshold value to obtain the ambient light illumination mean ratio; The method for obtaining the ambient light stability parameter is as follows: Mark the brightness values ​​of all environmental images in the XY two-dimensional coordinate system, and connect the marked brightness value points with a curve to obtain a brightness change curve. Mark the mean value of the ambient light illumination on the Y axis, draw a straight line parallel to the X axis through the mark point of the mean value of the ambient light illumination, and mark the straight line as the reference line; The area enclosed by the reference line and the brightness change curve is measured and marked as the fluctuation area. The area enclosed by the reference line and the X-axis is measured and marked as the reference area. The fluctuation area and the reference area are ratio-processed to obtain the fluctuation area ratio. The overlap length between the reference line and the brightness variation curve and the length of the reference line are measured, and the ratio is processed to obtain a stable overlap length ratio; The vertical distances between all the peak points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the peak distance mean; the vertical distances between all the trough points and the baseline in the brightness change curve are measured, and the sum and average are taken to obtain the trough distance mean; the peak distance mean and the trough distance mean are summed to obtain the fluctuation distance mean; the fluctuation distance mean is ratioed with the fluctuation distance mean threshold to obtain the fluctuation distance mean ratio; The fluctuation area ratio, stable overlap length ratio and fluctuation distance mean ratio are marked as CV, CB and CM respectively, and the data are processed by the formula: Obtaining the ambient light stability parameter CKg, where s1, s2 and s3 are all preset proportional coefficients; Second data acquisition module: environmental image acquisition time data and inertial sensor capture vehicle speed information time data, wherein the environmental image acquisition time data includes each frame of environmental image acquisition time point, the inertial sensor capture vehicle speed information time data includes each time point of the inertial sensor capture vehicle speed information, the environmental image acquisition time data and the inertial sensor capture vehicle speed information time data are processed to obtain the information synchronization value ZWe; Preliminary selection module: respectively compare the illumination quality performance value SDF and the information synchronization value ZWe with the corresponding preset thresholds. If the illumination quality performance value SDF and the information synchronization value ZWe are both greater than or equal to the corresponding preset thresholds, then select a tightly coupled method to fuse the first pose information and the second pose information to obtain the positioning result of the vehicle. If the illumination quality performance value SDF and the information synchronization value ZWe are both not greater than or equal to the corresponding preset thresholds or are not both greater than or equal to the corresponding preset thresholds, then generate an analysis signal according to the comparison result, wherein the analysis signal includes a first analysis signal, a second analysis signal and a third analysis signal; Select the analysis module: based on the first analysis signal, obtain the information synchronization difference ZWc, based on the second analysis signal, obtain the lighting quality performance difference SDe, based on the third analysis signal, obtain the comprehensive deviation representation value RG, and compare the information synchronization difference ZWc, the lighting quality performance difference SDe and the comprehensive deviation representation value RG with the information synchronization difference threshold, the lighting quality performance difference threshold and the comprehensive deviation representation threshold respectively, and select the final fusion method according to the comparison results.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the positioning method integrating computer vision and inertial sensors as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the positioning method for integrating computer vision and inertial sensors as described in any one of claims 1 to 5 is implemented.