Driving trajectory determination method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for determining a driving trajectory, and relates to the field of vehicle data interaction technology. The driving trajectory determination method includes: obtaining data uploaded by a Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes target image data of the vehicle's surrounding environment collected by the vehicle-mounted camera and target environment parameters around the vehicle detected by the on-board sensor; combining the data uploaded by the Tbox terminal device with data uploaded by other vehicles, and determining the accurate position and dynamic trajectory information of the target vehicle through comparative analysis of the environmental model library, wherein the environmental database at least includes position information and feature vectors associated with the position information. The present application can determine the position and dynamic trajectory information of the target vehicle, reduce the dependence on a single Tbox device, reduce the problem of inaccurate trajectory information caused by Tbox failure or signal problems, and enhance the data robustness of the system.

Description

Technical Field

[0001] The present application relates to the field of vehicle data interaction technology, and in particular to a method, device, equipment and storage medium for determining a vehicle trajectory. Background Art

[0002] With the development of intelligent transportation systems and autonomous driving technology, the demand for accurate monitoring of vehicle location and trajectory is increasing. This demand not only involves improving navigation accuracy, but also affects vehicle safety, traffic flow management, accident analysis and other aspects.

[0003] At present, the acquisition of vehicle trajectories mainly relies on the Tbox terminal device, which obtains the latitude and longitude information of the vehicle through the GPS module and uploads it to the server. The server then performs reverse address resolution, converts the latitude and longitude information into actual location names, and draws the vehicle's trajectory based on this information. This method can provide continuous vehicle location tracking under ideal circumstances, but there are some limitations in practical applications.

[0004] Although the Tbox terminal device provides a means of vehicle trajectory monitoring, its accuracy and reliability are limited by many factors. These factors may cause the actual position and trajectory of the vehicle to drift and fail to truly reflect the actual driving conditions of the vehicle. Therefore, how to improve the accuracy of vehicle trajectory has become an urgent problem to be solved. Summary of the invention

[0005] The purpose of this application is to provide a method, device, equipment and storage medium for determining a vehicle trajectory, aiming to solve the technical problem of how to improve the accuracy of the vehicle trajectory.

[0006] To achieve the above objectives, the present application proposes a method for determining a driving trajectory, the method comprising:

[0007] Acquire data uploaded by the Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes target image data of the vehicle surrounding environment collected by the vehicle-mounted camera and target environment parameters of the vehicle surrounding environment detected by the vehicle-mounted sensor;

[0008] The data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles, and the accurate position and dynamic trajectory information of the target vehicle are determined through comparative analysis of the environmental model library. The environmental database at least includes the position information and the feature vector associated with the position information.

[0009] In one embodiment, before obtaining the data uploaded by the Tbox terminal device, the method further includes:

[0010] Get the preset acquisition time threshold;

[0011] An information acquisition request is sent to a target vehicle according to the preset acquisition time threshold, so that the target vehicle feeds back a target data packet according to the information acquisition request, wherein the target data packet includes target image data, and the target image data is obtained based on the preset shooting time by an omnidirectional camera on the target vehicle and after caching and compression.

[0012] In one embodiment, before the data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles and compared and analyzed through the environment model library to determine the accurate position and dynamic trajectory information of the target vehicle, the following is also included:

[0013] Obtain reference image data and reference environment parameters based on data uploaded by other vehicles, wherein the reference image data at least includes surrounding building images, traffic sign images, and natural landscape images;

[0014] Extracting features from the image data and converting them into initial feature vectors;

[0015] The reference environment parameters are associated with the initial feature vector to construct an environment model library.

[0016] In one embodiment, associating the reference environment parameter with the initial feature vector to construct an environment model library includes:

[0017] Obtaining position parameters according to the reference environment parameters;

[0018] The position parameters are associated with the initial feature vector to construct an environment model library.

[0019] In one embodiment, after associating the reference environment parameter with the initial feature vector to construct an environment model library, the method further includes:

[0020] Get the preset update time threshold;

[0021] When the time for building the environment model library reaches a preset update time threshold, analyzing the extended data according to a machine learning algorithm to extract a reference feature vector, the extended data including extended image data and extended environment parameters, the extended data being obtained based on data uploaded by other vehicles before reaching the preset update time threshold;

[0022] The reference feature vector is associated with the extended environment parameter and updated to the environment model library.

[0023] In one embodiment, the data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles, and compared and analyzed through the environmental model library to determine the accurate position and dynamic trajectory information of the target vehicle, including:

[0024] Extracting the target image data to obtain a target feature vector;

[0025] Compare the target feature vector to the environment model library to obtain a corresponding matching feature vector;

[0026] Based on the matching feature vector, obtaining associated environment parameters;

[0027] Based on the associated environmental parameters and the target environmental parameters, the accurate position and dynamic trajectory information of the target vehicle are determined.

[0028] In one embodiment, determining the accurate position and dynamic trajectory information of the target vehicle based on the associated environment parameters and the target environment parameters includes:

[0029] Obtain corresponding reference trajectory information and initial trajectory information according to the associated environment parameters and the target environment parameters respectively;

[0030] The reference trajectory information and the initial trajectory information are combined to obtain the target vehicle position and target trajectory information.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle trajectory determination device, the device comprising:

[0032] An acquisition module, used to acquire data uploaded by a Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes image data of the vehicle's surrounding environment collected by an on-board camera and environmental parameters of the vehicle's surrounding environment detected by an on-board sensor;

[0033] The determination module is used to combine the data uploaded by the Tbox terminal device with the data uploaded by other vehicles, and determine the accurate position and dynamic trajectory information of the target vehicle through comparative analysis of the environmental model library. The environmental database at least includes the position information and the feature vector associated with the position information.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a driving trajectory determination device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the driving trajectory determination method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the driving trajectory determination method described above are implemented.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the driving trajectory determination method as described above are implemented.

[0037] One or more technical solutions proposed in this application have at least the following technical effects:

[0038] This application first uses the Tbox terminal device to collect the target image data of the vehicle's surroundings captured by the on-board camera and the parameters of the vehicle's surroundings detected by the on-board sensors to ensure that basic information about the vehicle and its environment is available. The data uploaded by the Tbox terminal device is then integrated with similar data uploaded by other vehicles. By aggregating data from multiple vehicles, the comprehensiveness and diversity of the information are enhanced. Finally, the collected data is compared and analyzed using the environmental model library, and the accuracy of positioning is improved by matching and comparing the data. This application can accurately determine the location and dynamic trajectory information of the target vehicle. Not only does it improve the accuracy of positioning, it also effectively solves the problem of single reliance on the Tbox device and improves the reliability of trajectory drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A flow chart of the first embodiment of the method for determining the driving trajectory of the present application;

[0042] Figure 2 A flow chart of the second embodiment of the method for determining the driving trajectory of the present application;

[0043] Figure 3 A schematic diagram of a brief process of a method for determining a vehicle trajectory according to an embodiment of the present application;

[0044] Figure 4 This is a schematic diagram of the module structure of the driving trajectory determination device according to an embodiment of the present application;

[0045] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the method for determining the driving trajectory in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] With the development of intelligent transportation systems and autonomous driving technology, the demand for accurate monitoring of vehicle location and trajectory is growing. This demand not only involves improving navigation accuracy, but also relates to vehicle safety, traffic flow management, and accident analysis. At present, the acquisition of vehicle trajectory mainly depends on the Tbox terminal device, which obtains the latitude and longitude information of the vehicle through the GPS module and uploads it to the server. The server then performs reverse address resolution, converts the latitude and longitude information into actual location names, and draws the trajectory of the vehicle based on this information. This method can provide continuous vehicle location tracking under ideal conditions, but there are some limitations in practical applications. Although the Tbox terminal device provides a means of vehicle trajectory monitoring, its accuracy and reliability are limited by many factors. These factors cause the actual position and trajectory of the vehicle to drift, and cannot truly reflect the actual driving conditions of the vehicle.

[0050] The main solution of the embodiment of the present application is: This embodiment first collects the target image data of the vehicle's surrounding environment captured by the vehicle-mounted camera and the vehicle's surrounding environment parameters detected by the on-board sensor through the Tbox terminal device to ensure that basic information about the vehicle and its environment is available. Then the data uploaded by the Tbox terminal device is integrated with similar data uploaded by other vehicles. By aggregating data from multiple vehicles, the comprehensiveness and diversity of the information are enhanced. Finally, the collected data is compared and analyzed using the environmental model library, and the accuracy of positioning is improved by matching and comparing the data. This embodiment can accurately determine the location and dynamic trajectory information of the target vehicle. Not only does it improve the accuracy of positioning, it also effectively solves the problem of single reliance on the Tbox device and improves the reliability of trajectory drawing.

[0051] It should be noted that the execution subject of the embodiment of the present application can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes the server as an example to illustrate this embodiment and the following embodiments.

[0052] Based on this, the embodiment of the present application provides a method for determining a driving trajectory, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for determining a vehicle trajectory of the present application.

[0053] In this embodiment, the driving trajectory determination method includes steps S10 to S20:

[0054] Step S10, obtaining data uploaded by the Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes target image data of the vehicle surrounding environment collected by the vehicle-mounted camera and target environment parameters of the vehicle surrounding environment detected by the vehicle-mounted sensor;

[0055] It should be noted that the Tbox terminal device can be a smart terminal device installed in the vehicle, which is responsible for collecting and transmitting various types of vehicle data. The data uploaded by the Tbox terminal device mainly includes target image data and target environmental parameters. The target image data can be image data of the vehicle's surrounding environment collected by the vehicle-mounted camera. These image data may include road condition information in front of, behind, and on both sides of the vehicle, such as road signs, traffic signals, surrounding buildings, natural landscapes and other visual information. These image data are essential for understanding the specific environment and traffic conditions in which the vehicle is located. The target environmental parameters can be parameters of the vehicle's surrounding environment detected by the on-board sensors, such as vehicle speed, acceleration, direction, temperature, humidity, positioning information, etc. These environmental parameters provide detailed information on the vehicle's operating status and external environmental conditions.

[0056] It is understandable that the Tbox terminal device is responsible for collecting and uploading key data of the vehicle, including image information about the vehicle's surrounding environment captured by the on-board camera, such as roads, traffic signs and surrounding buildings, as well as environmental parameters detected by the vehicle's sensors, such as vehicle speed, acceleration and temperature. These data together provide the necessary information for the vehicle's precise positioning and trajectory tracking.

[0057] As an example, before obtaining the data uploaded by the Tbox terminal device, it also includes: obtaining a preset acquisition time threshold; sending an information acquisition request to the target vehicle according to the preset acquisition time threshold, so that the target vehicle feeds back a target data packet according to the information acquisition request, and the target data packet includes target image data, and the target image data is based on the omnidirectional camera on the target vehicle according to the preset photo taking time, and is obtained after caching and compression.

[0058] The preset acquisition time threshold may be a preset time parameter used to define when to send a data acquisition request to the vehicle. This threshold may be based on a time interval (e.g., every 10 minutes) or a specific event trigger (e.g., when the vehicle enters a specific area). The information acquisition request may be a request signal sent to the target vehicle according to the preset acquisition time threshold, with the purpose of requesting the vehicle to provide current or recently collected data. This request may be automatic or triggered by an external event. The target data packet may be a collection of data fed back to the system by the target vehicle according to the information acquisition request. This data packet usually includes various sensor data of the vehicle and image data captured by the camera, which are used for subsequent vehicle position and trajectory analysis. The preset photo shooting time may be the time point at which the on-board camera automatically shoots images according to a preset time interval. These time points may be fixed (e.g., once every 30 seconds) or dynamically determined based on specific conditions (e.g., when the vehicle speed changes). The preset photo shooting time ensures the continuity and consistency of the image data, which is crucial for subsequent data analysis and determination of the vehicle trajectory. After receiving the information acquisition request, the camera will shoot in the direction set by the user and upload the image at least every 10 minutes, and the interval period can also be set by the user. The image materials obtained before uploading will be temporarily cached in the electronic control unit, and the cached and compressed material resources will be uploaded to the server through Tbox.

[0059] Specifically, a preset time threshold is first determined, that is, a specific time interval is set to trigger data collection. When this preset time point is reached, an information acquisition request is sent to the target vehicle, requesting the vehicle to upload the image data captured by its omnidirectional camera at the preset photo taking time point and processed by cache and compression. These image data are then packaged into target data packets and fed back to the system for further vehicle position and trajectory analysis.

[0060] Step S20, combining the data uploaded by the Tbox terminal device with the data uploaded by other vehicles, and determining the accurate position and dynamic trajectory information of the target vehicle through comparative analysis of the environmental model library, wherein the environmental database includes at least the position information and a feature vector associated with the position information.

[0061] It should be noted that the environmental model library can be a database that stores environmental parameters and feature information related to the vehicle's location, which may include but is not limited to images of surrounding buildings, traffic signs, natural landscapes, and reference image data and environmental parameters uploaded by other vehicles. This library is used to compare and analyze the data uploaded in real time to determine the exact location and trajectory of the vehicle. The accurate location and dynamic trajectory information can be obtained by analyzing and processing the data uploaded by the Tbox terminal device and comparing it with the data uploaded by other vehicles, and the exact location of the vehicle in a specific time and space and its movement path that changes over time. The target vehicle can be a vehicle that is tracked and analyzed in a specific scenario. In this solution, by combining the data uploaded by the target vehicle itself and the data provided by other vehicles, and using the environmental model library for comprehensive analysis, the location and trajectory of the target vehicle can be determined more accurately, thereby improving the accuracy of vehicle monitoring and navigation.

[0062] It is understandable that combining the data uploaded by the Tbox terminal device with the data uploaded by other vehicles can integrate the environmental images captured by the on-board camera of a single vehicle and the environmental parameters detected by the sensor, as well as similar data from other vehicles. These integrated data are compared and analyzed through comparative analysis of the environmental model library. Determine the exact location of the target vehicle, that is, the vehicle whose position and trajectory we are monitoring and analyzing, at any given point in time, as well as its movement path, that is, dynamic trajectory information. This method can improve the accuracy of positioning, especially when the GPS signal is weak or unavailable, through data sharing and environmental feature comparison between vehicles, to achieve accurate monitoring of the position and trajectory of the target vehicle.

[0063] As an example, before the data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles and compared and analyzed through the environmental model library to determine the accurate position and dynamic trajectory information of the target vehicle, it also includes: obtaining reference image data and reference environmental parameters based on the data uploaded by other vehicles, and the reference image data at least includes surrounding building images, traffic sign images, and natural landscape images; extracting features from the image data and converting them into initial feature vectors; associating the reference environmental parameters with the initial feature vectors to construct an environmental model library.

[0064] The reference image data includes the surrounding environment images captured by the on-board cameras of other vehicles, including at least the following types of images: surrounding building images, traffic sign images, and natural landscape images. The reference environment parameters may be environmental parameters associated with the reference image data, which may include but are not limited to vehicle speed, acceleration, temperature, humidity, etc. These parameters provide the specific environmental conditions of the vehicle when the image data was taken. The initial feature vector may be a numerical representation of the key visual features extracted from the reference image data, and the image is converted into a set of numerical values ​​that can be used for comparison and analysis through the feature extraction process. These features may include color histograms, texture features, shape descriptors, etc., which can represent the core visual information of the image and are used for subsequent image matching and analysis.

[0065] Specifically, reference image data, including images of surrounding buildings, traffic signs, and natural landscapes, are extracted from data collected by other vehicles, and then features are extracted from these images to convert them into initial feature vectors, which represent the key visual features of the images. Next, reference environmental parameters are associated with these initial feature vectors to build an environmental model library, which is used for subsequent vehicle position and trajectory determination, and improves positioning accuracy by matching the data uploaded by the target vehicle with the data in the library.

[0066] As an example, associating the reference environment parameters with the initial feature vector to construct an environment model library includes: obtaining position parameters according to the reference environment parameters; associating the position parameters with the initial feature vector to construct an environment model library.

[0067] Among them, the location parameters can be data directly related to the geographic location extracted or calculated from the reference environment parameters. These parameters can provide the exact location information of the vehicle in the physical world, usually including but not limited to latitude and longitude coordinates, which are the most commonly used location parameters, indicating the precise location of the vehicle in the global positioning system (GPS); altitude, that is, the height of the vehicle relative to the sea level, which is sometimes also considered as part of the location parameters; road information, that is, the name of the road where the vehicle is located, the type of road (such as highways, urban roads, etc.); surrounding points of interest (POI), that is, specific places near the vehicle, such as gas stations, restaurants, shopping malls, etc. By associating these location parameters with the initial feature vector (i.e., the visual features extracted from the image data), a rich environmental model library can be constructed. This library contains not only visual information, but also specific location information related to this visual information, so that when performing vehicle position and trajectory analysis, the visual data can be more accurately matched with the actual geographic location. This method of combining visual and location information improves the accuracy and reliability of vehicle positioning, especially in areas with similar visual environments or limited GPS signals.

[0068] Specifically, key location information, i.e., location parameters, are extracted from the reference environment parameters. These parameters directly indicate the geographic location of the vehicle, such as latitude and longitude coordinates, road information, etc. Subsequently, these location parameters are linked to the initial feature vector extracted from the reference image data, and the visual information is closely combined with the geographic location to jointly construct an environmental model library. This library can provide an accurate reference for subsequent vehicle location determination and trajectory tracking, so that by comparing the data uploaded by the target vehicle with the data in the library, the actual location and dynamic trajectory of the vehicle can be determined more accurately.

[0069] As an example, after associating the reference environmental parameters with the initial feature vector and constructing the environmental model library, it also includes: obtaining a preset update time threshold; when the time for constructing the environmental model library reaches the preset update time threshold, analyzing the extended data according to the machine learning algorithm, and extracting the reference feature vector, the extended data includes extended image data and extended environmental parameters, and the extended data is obtained based on data uploaded by other vehicles before reaching the preset update time threshold; associating the reference feature vector with the extended environmental parameters, and updating the environmental model library.

[0070] Among them, the preset update time threshold may be a set time parameter used to determine when to update the environment model library. When the time since the last update reaches this preset threshold, the update process is triggered. The machine learning algorithm may be an algorithm that learns and extracts patterns through data analysis, and is used to identify useful information and patterns from a large amount of data for prediction or classification. The time for building the environment model library may be the time since the last update of the environment model library. This time length is compared with the preset update time threshold to determine whether an update is required. The extended data may be new data uploaded based on other vehicles before the preset update time threshold is reached. These data are used to update and expand the environment model library. The reference feature vectors may be feature vectors extracted from the extended data, which represent the key visual features of the newly collected image data and are used to update the environment model library. The extended image data may be newly collected image data of the vehicle's surroundings, which may include new images of buildings, traffic signs, natural landscapes, etc. The extended environmental parameters may be environmental parameters associated with the extended image data, such as new location information, timestamps, meteorological conditions, etc.

[0071] Specifically, this process describes an automated environment model library update mechanism that first sets a preset update time threshold, and when the time since the last update reaches this threshold, the update process is initiated. At this point, the machine learning algorithm is applied to the extended data collected from other vehicles during this period, which includes additional image data and environmental parameters. The algorithm analyzes and extracts new reference feature vectors from these extended data, which capture the key visual features of the new image data. These newly extracted feature vectors are then associated with the corresponding extended environmental parameters and integrated into the environment model library to ensure that the data in the library remains up to date and accurate, thereby improving the accuracy of vehicle position and trajectory determination.

[0072] This embodiment provides a method for determining a driving trajectory. This embodiment first uses a Tbox terminal device to collect target image data of the vehicle's surroundings captured by the vehicle-mounted camera and parameters of the vehicle's surroundings detected by the on-board sensor to ensure that basic information about the vehicle and its environment is available. Then the data uploaded by the Tbox terminal device is integrated with similar data uploaded by other vehicles. By aggregating data from multiple vehicles, the comprehensiveness and diversity of the information are enhanced. Finally, the collected data is compared and analyzed using the environmental model library, and the accuracy of positioning is improved by matching and comparing the data. This embodiment can accurately determine the location and dynamic trajectory information of the target vehicle. Not only does it improve the accuracy of positioning, it also effectively solves the problem of single reliance on the Tbox device and improves the reliability of trajectory drawing.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the driving trajectory determination method of the present application. Step S20 of the driving trajectory determination method includes steps S21 to S24:

[0074] Step S21, extracting the target image data to obtain a target feature vector;

[0075] It should be noted that the target feature vector can be a set of feature values ​​extracted from the target image data, which can represent or describe the key information and significant attributes in the image. The target feature vector usually contains statistical features or visual features extracted from the vehicle surrounding environment image collected by the vehicle-mounted camera, such as edges, corners, textures, color distribution, etc. These feature vectors can be used to identify and compare the similarities between different images to help determine the precise position and trajectory of the vehicle. The target feature vector may include color features, texture features, shape features, spatial relationship features, depth features, etc. By quantifying these features into numerical vectors, they can be easily processed and compared in a computer system, thereby achieving accurate identification of the vehicle position and accurate drawing of the trajectory.

[0076] It can be understood that key visual features such as color, texture, shape and spatial relationship are identified and quantified from the images of the vehicle's surrounding environment captured by the on-board camera, and then these features are converted into a set of numerical values ​​to form a feature vector. This vector can represent the core information of the image and is used for subsequent comparative analysis of the environmental model library to determine the precise position and trajectory of the vehicle.

[0077] Step S22, comparing the target feature vector with the environment model library to obtain a corresponding matching feature vector;

[0078] It should be noted that the matching feature vector refers to the feature vector found in the environment model library that is most similar or matching to the target feature vector. This process usually involves feature extraction, library search, and then comparing the target feature vector with a large number of feature vectors stored in the environment model library. Then, through similarity calculation, the similarity or distance between the target feature vector and each feature vector in the library is calculated to determine which feature vectors are closest to the target feature vector. Finally, the feature vector with the highest similarity to the target feature vector is selected as the matching feature vector. These matching feature vectors represent the features in the environment model library that are closest to the current environment of the target vehicle.

[0079] It can be understood that the algorithm is used to search the environmental model library for the vector that is most similar to the target feature vector extracted from the image data collected by the vehicle-mounted camera. This process is achieved by calculating the similarity between the target feature vector and each feature vector stored in the library, and finally the feature vector with the highest match with the target feature vector is selected. These matching feature vectors can provide strong reference information for determining the precise position and trajectory of the vehicle.

[0080] Step S23, obtaining associated environment parameters based on the matching feature vector;

[0081] It should be noted that the associated environmental parameters can be a series of environmental parameters associated with the matching feature vector, which provide the actual environmental information corresponding to the feature vector. In the technical solution for determining the vehicle trajectory, these environmental parameters may include but are not limited to geographic location information, that is, the geographic location matched with the feature vector, such as latitude and longitude coordinates; timestamp, that is, the time information when the feature vector is collected or matched; meteorological conditions, such as temperature, humidity, wind speed, etc., which may affect vehicle driving and sensor readings; road characteristics, such as road type (highway, urban road, etc.), road surface conditions (slippery, icy, etc.); surrounding environmental characteristics, including descriptions of surrounding buildings, traffic signs, natural landscapes, etc. By combining the matching feature vector with these associated environmental parameters, the location of the vehicle can be determined more accurately because these parameters provide the environment in which the vehicle is located. This method enables accurate tracking of the vehicle's location and trajectory through the vehicle's sensor data and camera images, combined with the information in the environmental model library, even when the GPS signal is poor or missing.

[0082] It can be understood that after finding feature vectors that match the target feature vector in the environmental model library, specific environmental parameters associated with these matching feature vectors are extracted, such as latitude and longitude coordinates, timestamps, weather conditions, traffic conditions, and road characteristics. These parameters provide detailed environmental information about the vehicle's location and can more accurately determine the vehicle's precise location and trajectory.

[0083] Step S24, determining the accurate position and dynamic trajectory information of the target vehicle based on the associated environment parameters and the target environment parameters.

[0084] It can be understood that by using the associated environmental parameters matched with the target feature vector obtained from the environmental model library, combined with the target environmental parameters detected in real time by the vehicle sensor, the geographical location and motion state of the vehicle are comprehensively evaluated by comparing and analyzing these two parameters, so as to accurately determine the exact location of the target vehicle at a specific time point and the driving trajectory that changes over time. This process is equivalent to matching the actual perception data of the vehicle with the historical environmental data to achieve high-precision monitoring of the vehicle's location and trajectory.

[0085] As an example, based on the associated environment parameters and the target environment parameters, the accurate position and dynamic trajectory information of the target vehicle are determined, including: obtaining corresponding reference trajectory information and initial trajectory information according to the associated environment parameters and the target environment parameters respectively; and obtaining the target vehicle position and target trajectory information by combining the reference trajectory information and the initial trajectory information.

[0086] Among them, the reference trajectory information can be trajectory information obtained based on associated environmental parameters, which are associated with matching feature vectors in the environmental model library. The reference trajectory information usually contains the historical position and trajectory data of the vehicle under specific environmental characteristics, which are used as references for comparison with the real-time data of the target vehicle. The initial trajectory information can be trajectory information obtained directly from the data collected by the sensors and cameras of the target vehicle, that is, trajectory information obtained based on the data of the target vehicle itself before comparative analysis with the environmental model library. The position of the target vehicle can be the exact geographical location of the target vehicle at a specific time point determined after combining the reference trajectory information and the initial trajectory information, such as longitude and latitude coordinates. The target trajectory information can be the moving path of the target vehicle over time, which is the trajectory obtained after combining the reference trajectory information and the initial trajectory information. This trajectory information is more accurate and reliable because it combines the vehicle's own sensor data and the historical data in the environmental model library, and is optimized and corrected through comparative analysis.

[0087] Specifically, the target vehicle's associated environmental parameters (parameters associated with the matching feature vector obtained from the environmental model library) and the target environmental parameters (environmental parameters detected by the target vehicle in real time) are used to obtain two sets of trajectory information: reference trajectory information and initial trajectory information. The reference trajectory information is a trajectory derived based on historical data and environmental models, while the initial trajectory information is obtained directly from the real-time data of the target vehicle. Finally, by combining these two sets of information, calibrating and optimizing the trajectory data, a more accurate target vehicle position and complete target trajectory information are obtained, which helps to improve the accuracy of vehicle navigation and monitoring.

[0088] This embodiment first extracts key visual features from the target image data collected by the vehicle-mounted camera to form a target feature vector. This step provides basic data for subsequent environmental feature matching. Then the target feature vector is compared with a large number of feature vectors stored in the environmental model library to find the most matching feature vector. This step provides a possible reference point for determining the vehicle position through the data support in the library. Then the associated environmental parameters are extracted from the matching feature vector. These parameters provide environmental information closely related to the vehicle position and provide important clues for accurate positioning. Finally, the associated environmental parameters obtained by combining the matching feature vector and the target environmental parameters detected in real time by the vehicle sensor are comprehensively analyzed to determine the accurate position and dynamic trajectory information of the target vehicle. This step realizes accurate monitoring of the vehicle position. This embodiment improves the accuracy and reliability of vehicle positioning by fusing real-time data with historical model library data, especially in the case of poor or missing GPS signals. This method can provide an effective alternative positioning solution to ensure the continuity and accuracy of the vehicle trajectory.

[0089] For example, in order to help understand the implementation process of the vehicle trajectory determination method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flow chart of a method for determining a driving trajectory is provided, specifically:

[0090] First, the target image data captured by the vehicle camera and the target environment parameters detected by the on-board sensor are obtained from the Tbox terminal device. Then, these data are compared and analyzed through the environmental model library. The specific steps include extracting the target image data to obtain the target feature vector, comparing the target feature vector with the environmental model library to obtain the matching feature vector, obtaining the associated environmental parameters based on the matching feature vector, and finally combining the associated environmental parameters and the target environmental parameters to determine the accurate position and dynamic trajectory information of the target vehicle. In addition, the method also involves obtaining reference trajectory information and initial trajectory information according to the associated environmental parameters and the target environmental parameters, respectively, and combining this information to obtain more accurate target vehicle position and trajectory information.

[0091] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining the driving trajectory of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0092] This application also provides a vehicle trajectory determination device, please refer to Figure 4 , the vehicle trajectory determination device comprises:

[0093] The acquisition module 10 is used to acquire data uploaded by the Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes image data of the vehicle surrounding environment collected by the vehicle-mounted camera and environmental parameters of the vehicle surrounding environment detected by the vehicle-mounted sensor;

[0094] The determination module 20 is used to combine the data uploaded by the Tbox terminal device with the data uploaded by other vehicles, and determine the accurate position and dynamic trajectory information of the target vehicle through comparative analysis of the environmental model library. The environmental database at least includes the position information and the feature vector associated with the position information.

[0095] The vehicle trajectory determination device provided by the present application adopts the vehicle trajectory determination method in the above embodiment, which can solve the technical problem of how to improve the accuracy of the vehicle trajectory. Compared with the prior art, the beneficial effects of the vehicle trajectory determination device provided by the present application are the same as the beneficial effects of the vehicle trajectory determination method provided by the above embodiment, and other technical features in the vehicle trajectory determination device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0096] The present application provides a driving trajectory determination device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the driving trajectory determination method in the above-mentioned embodiment 1.

[0097] Reference below Figure 5 , which shows a schematic diagram of the structure of a vehicle trajectory determination device suitable for implementing the embodiment of the present application. The vehicle trajectory determination device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The driving trajectory determination device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0098] like Figure 5As shown, the vehicle trajectory determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle trajectory determination device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle trajectory determination device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a vehicle trajectory determination device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0099] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0100] The vehicle trajectory determination device provided by the present application adopts the vehicle trajectory determination method in the above embodiment, which can solve the technical problem of how to improve the accuracy of the vehicle trajectory. Compared with the prior art, the beneficial effects of the vehicle trajectory determination device provided by the present application are the same as the beneficial effects of the vehicle trajectory determination method provided by the above embodiment, and the other technical features in the vehicle trajectory determination device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0101] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0103] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle trajectory determination method in the above-mentioned embodiment.

[0104] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0105] The computer-readable storage medium may be included in the vehicle trajectory determination device; or may exist independently without being assembled into the vehicle trajectory determination device.

[0106] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the driving trajectory determination device, the driving trajectory determination device: obtains data uploaded by the Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes target image data of the vehicle's surrounding environment collected by the on-board camera and target environment parameters around the vehicle detected by the on-board sensor; combines the data uploaded by the Tbox terminal device with data uploaded by other vehicles, and determines the accurate position and dynamic trajectory information of the target vehicle through comparative analysis based on the environmental model library.

[0107] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0108] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0110] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle trajectory determination method, and can solve the technical problem of how to improve the accuracy of vehicle trajectory. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the vehicle trajectory determination method provided in the above-mentioned embodiment, and will not be elaborated here.

[0111] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned driving trajectory determination method when executed by a processor.

[0112] The computer program product provided by the present application can solve the technical problem of how to improve the accuracy of vehicle trajectory. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle trajectory determination method provided by the above embodiment, which will not be repeated here.

[0113] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining a vehicle trajectory, characterized in that: The method comprises: Acquire data uploaded by the Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes target image data of the vehicle surrounding environment collected by the vehicle-mounted camera and target environment parameters of the vehicle surrounding environment detected by the vehicle-mounted sensor; The data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles, and the accurate position and dynamic trajectory information of the target vehicle are determined through comparative analysis of the environmental model library, wherein the environmental database at least includes the position information and the feature vector associated with the position information; Before the data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles and compared and analyzed through the environment model library to determine the accurate position and dynamic trajectory information of the target vehicle, the method further includes: According to the data uploaded by other vehicles, reference image data and reference environment parameters are obtained, wherein the reference image data at least includes surrounding building images, traffic sign images, and natural landscape images, and the reference environment parameters are environment parameters associated with the reference image data; Extracting features from the image data and converting them into initial feature vectors, where the initial feature vectors are numerical representations of key visual features extracted from the reference image data. The feature extraction process converts the image into a set of numerical values ​​that can be used for comparison and analysis. The reference environment parameters are associated with the initial feature vector to construct an environment model library.

2. The method according to claim 1, characterized in that Before obtaining the data uploaded by the Tbox terminal device, the method further includes: Get the preset acquisition time threshold; An information acquisition request is sent to a target vehicle according to the preset acquisition time threshold, so that the target vehicle feeds back a target data packet according to the information acquisition request, wherein the target data packet includes target image data, and the target image data is obtained based on a preset photo taking time by an omnidirectional camera on the target vehicle and after caching and compression.

3. The method according to claim 1, characterized in that The step of associating the reference environment parameter with the initial feature vector to construct an environment model library includes: Obtaining position parameters according to the reference environment parameters; The position parameters are associated with the initial feature vector to construct an environment model library.

4. The method according to claim 1, characterized in that After associating the reference environment parameter with the initial feature vector to construct an environment model library, the method further includes: Get the preset update time threshold; When the time for building the environment model library reaches a preset update time threshold, analyzing the extended data according to a machine learning algorithm to extract a reference feature vector, the extended data including extended image data and extended environment parameters, the extended data being obtained based on data uploaded by other vehicles before reaching the preset update time threshold; The reference feature vector is associated with the extended environment parameter and updated to the environment model library.

5. The method according to claim 1, characterized in that The data uploaded by the Tbox terminal device is combined with the data uploaded by other vehicles, and the accurate position and dynamic trajectory information of the target vehicle are determined through comparative analysis of the environmental model library, including: Extracting the target image data to obtain a target feature vector; Compare the target feature vector to the environment model library to obtain a corresponding matching feature vector; Based on the matching feature vector, obtaining associated environment parameters; Based on the associated environmental parameters and the target environmental parameters, the accurate position and dynamic trajectory information of the target vehicle are determined.

6. The method according to claim 5, characterized in that The determining the accurate position and dynamic trajectory information of the target vehicle based on the associated environment parameters and the target environment parameters includes: Obtain corresponding reference trajectory information and initial trajectory information according to the associated environment parameters and the target environment parameters respectively; The reference trajectory information and the initial trajectory information are combined to obtain the target vehicle position and target trajectory information.

7. A vehicle trajectory determination device, characterized in that: The device comprises: An acquisition module, used to acquire data uploaded by a Tbox terminal device, wherein the data uploaded by the Tbox terminal device includes image data of the vehicle's surrounding environment collected by an on-board camera and environmental parameters of the vehicle's surrounding environment detected by an on-board sensor; A determination module, used to combine the data uploaded by the Tbox terminal device with the data uploaded by other vehicles, and determine the accurate position and dynamic trajectory information of the target vehicle through comparative analysis of the environmental model library, wherein the environmental database at least includes the position information and a feature vector associated with the position information; The acquisition module is further used to obtain reference image data and reference environment parameters based on data uploaded by other vehicles, wherein the reference image data at least includes surrounding building images, traffic sign images, and natural landscape images, and the reference environment parameters are environment parameters associated with the reference image data; Extracting features from the image data and converting them into initial feature vectors, where the initial feature vectors are numerical representations of key visual features extracted from the reference image data. The feature extraction process converts the image into a set of numerical values ​​that can be used for comparison and analysis. The reference environment parameters are associated with the initial feature vector to construct an environment model library.

8. A vehicle trajectory determination device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the driving trajectory determination method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the driving trajectory determination method according to any one of claims 1 to 6 are implemented.

Images