Intelligent network connection automobile multi-source data confidence coefficient analysis method

Abstract

The invention provides an intelligent networked automobile multi-source data confidence coefficient analysis method, and aims to improve the data reliability of an automatic driving system. The method comprises the following steps: acquiring multi-source data of a plurality of sensors of an automobile, adding credibility to the data, and generating automobile environment cloud point data; establishing a database to store historical information of data of roads on which all vehicles pass; cleaning the current vehicle environment cloud point data, and removing dynamic information to obtain road static cloud point data; and comparing the current road static cloud point data obtained by the vehicle with the data in the database to obtain the confidence coefficient of the multi-source data of the vehicle. Through abnormal value identification and dynamic information removal, the accuracy and reliability of data are ensured, the reliability is dynamically adjusted in combination with the historical performance of the sensor and environmental factors, and the adaptability and universality of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving and relates to a confidence analysis method for multi-source data of an intelligent networked vehicle. Background Art

[0002] To operate safely, a vehicle should take into account objects such as vehicles, people, trees, animals, buildings, signs, and poles when planning a path through an environment. To do so, object detectors may be used to accurately detect objects depicted in one or more images (e.g., images captured using one or more sensors mounted on an autonomous vehicle) in real time.

[0003] In the existing field of autonomous driving, the data obtained by sensors are processed under the premise of being trustworthy. However, in actual applications, the credibility of the data cannot be guaranteed. If the sensor obtains unreliable data, it may miss or generate erroneous or delayed object detection, which may lead to inappropriate paths or even collisions. Summary of the invention

[0004] In order to solve the problems existing in the background technology, the present invention proposes a confidence analysis method for multi-source data of intelligent connected vehicles.

[0005] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows.

[0006] A confidence analysis method for multi-source data of an intelligent networked vehicle comprises the following steps: obtaining multi-source data obtained by multiple sensors of a vehicle, adding credibility to the data based on the attributes of the vehicle sensors, and generating current vehicle environment cloud point data through a point cloud detection algorithm; establishing a database to store historical information of road data traveled by all vehicles; cleaning the current vehicle environment cloud point data through a quartile algorithm, removing dynamic information in the current vehicle environment cloud point data through a Harris corner point detection algorithm, and obtaining current road static cloud point data; comparing the current road static cloud point data obtained by the vehicle with the data in the database, and adding a weighted algorithm based on the comparison result to obtain the confidence of the vehicle multi-source data.

[0007] Furthermore, the specific method for adding credibility to data based on the attributes of vehicle sensors is: setting different attributes based on the sensor device when the data source is acquired, and setting the initial credibility of the sensor attribute according to the nominal accuracy of the sensor; dynamically adjusting the initial credibility according to the historical performance of the sensor to generate the credibility of the sensor; adding the impact of environmental factors on the sensor data, and making corresponding temporary adjustments to the credibility of a certain attribute of the sensor.

[0008] Furthermore, the contents stored in the database include: vehicle ID, timestamp, location, speed, acceleration, sensor ID, sensor attributes, credibility field; road ID, historical road static cloud point data, and anchored road facilities.

[0009] Furthermore, the specific method for cleaning the current vehicle environment cloud point data is: first, identify outliers and calculate the first quartile of the current vehicle environment cloud point data. and the third quartile , the specific formula is: , , where the second quartile is the median of the current vehicle environment cloud point data; Based on the first quartile and the third quartile Calculate the interquartile range , the specific formula is: ; Based on interquartile range Determine the outlier threshold. The specific formula is: ; The current vehicle environment cloud point data is cleaned based on the outlier judgment method.

[0010] Furthermore, the specific method of removing dynamic information in the cloud point data of the current vehicle environment through the Harris corner detection algorithm is: establishing a cloud point data list based on multi-source data obtained by multiple sensors of the vehicle, establishing a time series based on the timestamps in the cloud point data list, comparing the data in the time series, and setting multiple comparison windows for comparison; judging the displacement of the information contained in any window in the time series, and judging the displacement of the cloud point based on the relative position of any cloud point and the current vehicle position; if the cloud point displacement speed is consistent with the current vehicle driving speed and in the opposite direction, then the cloud point is judged to be a static cloud point; judging the movement of cloud points in all windows, removing dynamic cloud points, and obtaining static cloud point data of the current road.

[0011] Furthermore, the specific method for comparing the current road static cloud point data obtained by the vehicle with the data in the database is: based on the road ID of the road on which the current vehicle is traveling, extract the road static cloud point data corresponding to the road ID from the database, obtain the current road static cloud point data obtained by the current vehicle, and use the Euclidean distance to determine the similarity between the current road static cloud point data and the data in the database; generate a similarity list based on multiple roads and multiple vehicles, and complete the comparison of the current road static cloud point data obtained by the current vehicle with the data in the database.

[0012] Furthermore, the specific method for obtaining the confidence of the multi-source automobile data is: using a weighted algorithm, combining the credibility of the sensor with the matching result of the similarity list, and calculating the comprehensive confidence of the current data.

[0013] Compared with the prior art, the present invention has the following beneficial effects:

[0014] The present invention can effectively clean the data acquired by the vehicle through the steps of outlier identification and removal of dynamic information, ensure the accuracy of static cloud point data, and make subsequent analysis more reliable. At the same time, the present invention allows dynamic adjustment of credibility based on the historical performance of the sensor and environmental factors, and can adapt to different driving environments and conditions in real time, thereby improving data accuracy.

[0015] The present invention can effectively identify and filter unreliable data sources by adding credibility to the data of different sensors, thereby improving the reliability of the overall data of the system. A weighted algorithm is used to combine the credibility of the sensor with the matching results of the similarity list to provide a method for comprehensively evaluating the confidence of the data, making the final result more credible.

[0016] The present invention is not only applicable to various vehicle models and sensor configurations, but can also be adjusted according to different driving scenarios, and has good versatility and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, the technical solution adopted by the present invention is as follows: a confidence analysis method for multi-source data of intelligent networked vehicles, comprising:

[0020] Acquire multi-source data from multiple sensors of the car, add credibility to the data based on the properties of the vehicle sensors, and generate cloud point data of the current vehicle environment through point cloud detection algorithms.

[0021] Establish a database to save the historical information of all road data traveled by vehicles.

[0022] The current vehicle environment cloud point data is cleaned by the quartile algorithm, and the dynamic information in the current vehicle environment cloud point data is removed by the Harris corner detection algorithm to obtain the current road static cloud point data.

[0023] The static cloud point data of the current road obtained by the vehicle is compared with the data in the database, and a weighted algorithm is added based on the comparison results to obtain the confidence of the multi-source data of the vehicle.

[0024] The present invention needs to establish a database to store the historical information of the road data traveled by all vehicles. The contents stored in the database include:

[0025] Vehicle ID, timestamp, location, speed, acceleration, sensor ID, sensor attributes, and credibility fields.

[0026] Contains vehicle-related information, including vehicle ID, which is used to uniquely identify each vehicle; timestamp, which accurately records the time when the data is generated; location, which specifies the specific geographical location of the vehicle; speed, which shows the vehicle's speed at the time; acceleration, which reflects the change in vehicle speed; sensor ID, which is used to distinguish different sensors; sensor properties, which describe the characteristics of the sensor itself; and credibility field, which is used to evaluate the reliability of the data.

[0027] Road ID, historical road static cloud point data, and anchored road facilities.

[0028] Data related to roads include road IDs to distinguish different roads; historical road static cloud point data, static information about road shape and characteristics, etc.; and anchored road facilities, which may be information related to some important facilities fixed on the road. These are of great significance for understanding road conditions and the relationship between vehicles and roads.

[0029] Here is a detailed description of how to add trustworthiness to data based on the properties of vehicle sensors:

[0030] First, different attributes are set according to the differences in the sensor devices involved in the acquisition of data sources. On this basis, the initial credibility of the sensor attributes is set according to the nominal accuracy of the sensor itself. This means that sensors with different accuracies are given corresponding credibility base values ​​at the initial stage.

[0031] Next, the initial credibility should be dynamically adjusted according to the historical performance of the sensor in actual use, so as to generate a more accurate credibility of the sensor. Through the analysis and evaluation of its past data, the credibility value is continuously optimized to make it more in line with the actual performance of the sensor.

[0032] In addition, the impact of adding environmental factors on sensor data must also be considered. When the environment changes, the credibility of a certain attribute of the sensor must be temporarily adjusted accordingly. For example, in severe weather conditions, the performance of some sensors may be affected. At this time, their credibility needs to be appropriately adjusted to ensure the reliability and accuracy of the data.

[0033] After obtaining the multi-source data obtained by the vehicle sensor, it is necessary to clean the current vehicle environment cloud point data. The specific method is as follows:

[0034] First, outliers are identified and the first quartile of the current vehicle environment cloud point data is calculated and the third quartile , the specific formula is: , , The second quartile It is the median of the current vehicle environment cloud point data.

[0035] The interquartile range (IQR) is a statistic based on the location of the data. It is calculated based on the quartiles of the data. is the 25th percentile, is the 50th percentile, The interquartile range is the 75th percentile. Compared with statistics such as the mean and standard deviation, it is not sensitive to outliers. For example, in a data set containing extremely large or extremely small values, the mean is easily affected by these outliers and becomes biased, while the interquartile range focuses on the middle part of the data and will not change significantly due to a few extreme values.

[0036] Based on the first quartile and the third quartile Calculate the interquartile range , the specific formula is: .

[0037] Based on interquartile range Determine the outlier threshold. The specific formula is: .

[0038] The current vehicle environment cloud point data is cleaned based on the outlier judgment method.

[0039] The interquartile range helps to understand the dispersion of the middle 50% of the data. In data cleaning, by observing the size of the interquartile range, you can judge the dispersion of the data. If the interquartile range is small, it means that the middle part of the data is more concentrated; if the interquartile range is large, it means that the middle part of the data is more dispersed.

[0040] After cleaning the data, it is necessary to remove the dynamic data and rely only on static data for subsequent analysis. The specific method for removing dynamic information is as follows:

[0041] First, we build a cloud point data list with the help of multi-source data acquired by multiple sensors of the car. On this basis, we create a time series based on the timestamps in the cloud point data list to analyze and process the time characteristics of the data. Then, we compare the data in the time series and set multiple comparison windows for detailed comparison operations.

[0042] During the comparison process, the displacement of the information contained in any window in the time series is determined. This requires a comparison based on the relative position of any cloud point and the current vehicle position, so as to accurately determine the displacement of the cloud point. Specifically, if the displacement speed of a cloud point is consistent with the current vehicle speed and in the opposite direction, then the cloud point can be determined to be a static cloud point. By judging the movement of cloud points in all windows one by one, the dynamic cloud points are identified and removed, and finally the static cloud point data of the current road is obtained. Such a processing process can effectively separate static cloud point data from complex multi-source data, provide a more accurate and purer data basis for subsequent data analysis and application, and help improve the accuracy and reliability of related research or applications.

[0043] The specific method for comparing the current road static cloud point data obtained by the vehicle with the data in the database is as follows:

[0044] First, based on the road ID of the current vehicle, the road static cloud point data corresponding to the road ID is accurately extracted from the database. At the same time, the current road static cloud point data collected by multiple sensors of the current vehicle is obtained. Then, the Euclidean distance is used to measure the similarity between the current road static cloud point data and the data in the database.

[0045] Euclidean distance is a commonly used method to measure the distance between two points in space. Here, it can effectively reflect the degree of difference between two sets of cloud point data in spatial position. By calculating the Euclidean distance, the similarity between two sets of data can be quantitatively judged.

[0046] Next, a similarity list is generated based on the relevant data of multiple roads and multiple vehicles. For the data collected from different roads and vehicles, the similarity with the corresponding road data in the database is calculated respectively, and these similarity results are sorted into a list. In this way, a comprehensive comparison between the static cloud point data of the current road acquired by the vehicle and the data in the database is completed, providing a basis for subsequent analysis and application.

[0047] Recently, the confidence of multi-source data of automobiles is calculated. In terms of obtaining the confidence of multi-source data of automobiles, a weighted algorithm is used. Specifically, the credibility of the sensor is combined with the matching results of the similarity list mentioned above. The credibility of the sensor reflects the reliability of the sensor data, while the matching results of the similarity list reflect the degree of consistency between the data obtained by the vehicle and the standard data in the database. By setting the weights reasonably, these two factors are comprehensively calculated to obtain the comprehensive confidence of the current data. This comprehensive confidence can more comprehensively and accurately evaluate the quality and reliability of multi-source data of automobiles, and provide strong support for related decisions and applications.

[0048] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A confidence analysis method for multi-source data of intelligent connected vehicles, characterized in that: Included are: Acquire multi-source data from multiple sensors of the car, add credibility to the data based on the attributes of the vehicle sensors, and generate cloud point data of the current vehicle environment through point cloud detection algorithms; Establish a database to save the historical information of all road data that vehicles have traveled; The current vehicle environment cloud point data is cleaned by using the quartile algorithm, and the dynamic information in the current vehicle environment cloud point data is removed by using the Harris corner detection algorithm to obtain the current road static cloud point data; Compare the current road static cloud point data obtained by the vehicle with the data in the database, and add a weighted algorithm based on the comparison results to obtain the confidence of the multi-source data of the vehicle; The specific method of adding credibility to data based on the attributes of vehicle sensors is as follows: Different attributes are set based on the sensor device when the data source is acquired, and the initial credibility of the sensor attribute is set according to the nominal accuracy of the sensor; Dynamically adjust the initial credibility based on the historical performance of the sensor to generate the credibility of the sensor; Add the impact of environmental factors on sensor data and make corresponding temporary adjustments to the credibility of a certain attribute of the sensor.

2. The method for analyzing the confidence of multi-source data of an intelligent connected vehicle according to claim 1, characterized in that: The contents stored in the database include: Vehicle ID, timestamp, location, speed, acceleration, sensor ID, sensor attributes, and credibility fields; Road ID, historical road static cloud point data, and anchored road facilities.

3. The method for analyzing the confidence of multi-source data of an intelligent connected vehicle according to claim 1, characterized in that: The specific method for cleaning the current vehicle environment cloud point data is: First, outliers are identified and the first quartile of the current vehicle environment cloud point data is calculated and the third quartile , the specific formula is: ， ， The second quartile is the median of the current vehicle environment cloud point data; Based on the first quartile and the third quartile Calculate the interquartile range , the specific formula is: ； Based on interquartile range Determine the outlier threshold. The specific formula is: ； The current vehicle environment cloud point data is cleaned based on the outlier judgment method.

4. The method for analyzing the confidence of multi-source data of an intelligent connected vehicle according to claim 1, characterized in that: The specific method of removing dynamic information in the current vehicle environment cloud point data by using the Harris corner detection algorithm is: Establish a cloud point data list based on multi-source data acquired by multiple sensors of the car, establish a time series based on the timestamps in the cloud point data list, compare the data in the time series, and set multiple comparison windows for comparison; Determine the displacement of the information contained in any window in the time series, and compare the relative position of any cloud point with the current vehicle position to determine the displacement of the cloud point. If the displacement speed of the cloud point is consistent with the current vehicle speed and in the opposite direction, the cloud point is determined to be a static cloud point. Determine the movement of cloud points in all windows, remove dynamic cloud points, and obtain static cloud point data of the current road.

5. The method for analyzing the confidence of multi-source data of an intelligent connected vehicle according to claim 1, characterized in that: The specific method of comparing the current road static cloud point data obtained by the vehicle with the data in the database is: Based on the road ID of the road on which the current vehicle is traveling, the road static cloud point data corresponding to the road ID is extracted from the database, the current road static cloud point data obtained by the current vehicle is obtained, and the Euclidean distance is used to determine the similarity between the current road static cloud point data and the data in the database; A similarity list is generated based on multiple roads and multiple vehicles to compare the static cloud point data of the current road obtained by the current vehicle with the data in the database.

6. The method for analyzing the confidence of multi-source data of an intelligent connected vehicle according to claim 5, characterized in that: The specific method for obtaining the confidence of automobile multi-source data is: A weighted algorithm is used to combine the sensor's credibility with the matching results of the similarity list to calculate the comprehensive confidence of the current data.

Images