Positioning Information Processing Method, Apparatus, Device, and Medium

Abstract

The present application relates to a method, apparatus, device and medium for processing positioning information, belonging to the field of navigation technology and applied to maps. The method includes: obtaining first positioning information to be corrected, where the first positioning information is obtained by dead reckoning based on inertial sensing information; performing a preliminary correction on the first positioning information in a first direction according to visual sensing information to obtain second positioning information; determining the distance between historical positioning information and the first positioning information, where the historical positioning information is obtained by correcting and compensating the previously reckoned positioning information, and the previously reckoned positioning information is the positioning information obtained by dead reckoning before the first positioning information; and performing an advanced correction on the second positioning information in a second direction according to the distance to obtain the target positioning information after correction and compensation. Using this method can improve the accuracy of positioning information.

Description

Technical Field

[0001] The present application relates to the field of electronic maps, and more particularly to navigation technologies, and especially to a method, apparatus, device, and medium for processing positioning information. Background Art

[0002] Navigation technology refers to the technology of measuring parameters related to the position of a target object at every moment, so as to achieve the positioning of the moving target object and correctly guide it from the starting point along a predetermined route to the destination safely, accurately, and economically. During the navigation process, it is necessary to continuously update the positioning information of the target object, and the accuracy of the positioning information of the target object is directly related to the accuracy of the navigation result.

[0003] In the traditional technology, the positioning information from satellites and the positioning information calculated based on inertial sensing information are simply fused as the final positioning information of the target object. However, in scenarios where satellite positioning information cannot be received, such as when the target object enters a tunnel or other special scenarios with poor signal reception capabilities, the accuracy of the positioning result for the target object will be relatively low. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, device, and medium for processing positioning information that can improve the positioning accuracy of the target object for the above technical problems.

[0005] In a first aspect, the present application provides a method for processing positioning information, the method including:

[0006] Obtain the first positioning information to be corrected corresponding to the target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object;

[0007] Perform a preliminary correction in a first direction on the first positioning information according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object;

[0008] Determine the distance between the historical positioning information and the first positioning information; the historical positioning information is obtained by correcting and compensating the previously calculated positioning information; the previously calculated positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information;

[0009] Perform an advanced correction in a second direction on the second positioning information according to the distance to obtain the target positioning information after correction and compensation.

[0010] In a second aspect, the present application provides a device for processing positioning information, the device including:

[0011] An acquisition module, configured to acquire first positioning information to be corrected corresponding to a target object; the first positioning information is obtained by dead reckoning based on inertial sensing information of the target object;

[0012] A correction module, configured to perform a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object, to obtain second positioning information corresponding to the target object;

[0013] A determination module, configured to determine the distance between historical positioning information and the first positioning information; the historical positioning information is obtained by correcting and compensating the previously dead-reckoned positioning information; the previously dead-reckoned positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information;

[0014] The correction module is further configured to perform an advanced correction on the second positioning information in a second direction according to the distance, to obtain target positioning information after correction and compensation.

[0015] In one embodiment, the distance between the historical positioning information and the first positioning information is a first distance; the correction module is further configured to determine a second distance according to the historical positioning information and the second positioning information; and perform an advanced correction on the second positioning information in a second direction according to the difference between the first distance and the second distance, to obtain target positioning information after correction and compensation.

[0016] In one embodiment, the second positioning information includes second lateral positioning information and second longitudinal positioning information; the correction module is further configured to perform a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance, to obtain longitudinally corrected positioning information; and determine the target positioning information after correction and compensation according to the second lateral positioning information and the longitudinally corrected positioning information.

[0017] In one embodiment, the first positioning information to be corrected is the positioning information respectively deduced at each positioning moment within the current compensation period; the determining module is further configured to, for the first positioning information deduced at each positioning moment within the current compensation period, respectively determine the distance between the first positioning information and the corresponding historical positioning information, so as to obtain the distance corresponding to each positioning moment; the historical positioning information is the target positioning information determined in the previous compensation period; the correcting module is further configured to, for each positioning moment within the current compensation period, determine and store the sub-compensation error corresponding to the positioning moment according to the distance corresponding to the positioning moment; perform smoothing processing on the sub-compensation errors respectively corresponding to the positioning moments within the current compensation period to obtain the target compensation error corresponding to the current compensation period; perform advanced correction on the second positioning information corresponding to the target positioning moment in the second direction according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; the target positioning moment is one of the positioning moments within the current compensation period.

[0018] In one embodiment, when the visual sensing information is available, notify the correcting module to perform preliminary correction on the first positioning information in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object; when the visual sensing information is unavailable, the determining module is further configured to use the first positioning information as the target positioning information of the target object.

[0019] In one embodiment, the correcting module is further configured to determine the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object; determine the compensation error according to the visual position information and the first positioning information; perform preliminary correction on the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

[0020] In one embodiment, the first positioning information includes first position information and first state information; the second positioning information includes second position information and second state information; the compensation error includes position error and state error; the correcting module is further configured to perform preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object; perform preliminary state correction on the first state information according to the state error to obtain the second state information corresponding to the target object.

[0021] In one embodiment, the correcting module is further configured to determine the position error according to the position difference between the visual position information and the first position information; perform error solution on a pre-constructed positioning error equation according to the position error to obtain the state error.

[0022] In one embodiment, the state error includes at least one of a platform misalignment angle error, a velocity error, a dead reckoning error, a gyro zero bias, an accelerometer zero bias, an installation error angle residual, a wheel speedometer scale factor error, or a time delay for transmitting the wheel speed to the inertial sensor.

[0023] In one embodiment, the first position information includes first lateral position information and first longitudinal position information; the correction module is further configured to perform a preliminary position correction on the first lateral position information according to the position error to obtain lateral corrected position information; and determine second position information corresponding to the target object according to the lateral corrected position information and the first longitudinal position information.

[0024] In one embodiment, the correction module is further configured to, when receiving the satellite positioning information of the target object, perform a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object to obtain the preliminarily corrected positioning information; and perform a correction on the preliminarily corrected positioning information in a second direction according to the longitudinal position information in the satellite positioning information to obtain second positioning information corresponding to the target object.

[0025] In one embodiment, the target object includes a target vehicle in a vehicle navigation scenario; the inertial sensing information is collected by a vehicle inertial sensor disposed on the target vehicle; the visual sensing information is collected by a vehicle visual sensor disposed on the target vehicle; the target positioning information is the corrected and compensated positioning information of the target vehicle; the apparatus further includes:

[0026] A rendering module, configured to render and display the vehicle position information in the target positioning information on an in-vehicle navigation map.

[0027] In a third aspect, the present application provides a computer device, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the steps in the method embodiments of the present application are implemented.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, the steps in the method embodiments of the present application are implemented.

[0029] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the method embodiments of the present application are implemented.

[0030] The above positioning information processing method, apparatus, device, medium and computer program product obtain the first positioning information to be corrected corresponding to the target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object; the first positioning information is preliminarily corrected in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object; determine the distance between the historical positioning information and the first positioning information; the historical positioning information is obtained after correcting and compensating the previously dead-reckoned positioning information; the previously dead-reckoned positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information; the second positioning information is further corrected in the second direction according to the distance. Equivalently, without relying on satellite positioning, the dead-reckoned positioning information is compensated and corrected in both the first direction and the second direction, so the finally obtained corrected and compensated target positioning information is more accurate, improving the positioning accuracy. Description of the Drawings

[0031] Figure 1 It is a diagram of the application environment of the positioning information processing method in an embodiment;

[0032] Figure 2 It is a schematic flowchart of the positioning information processing method in an embodiment;

[0033] Figure 3 It is a schematic diagram of the positioning correction principle in an embodiment;

[0034] Figure 4 It is a schematic flowchart of the positioning information processing method in another embodiment;

[0035] Figure 5 It is a schematic diagram of the effect when the target vehicle enters the tunnel in an embodiment;

[0036] Figure 6 It is a schematic diagram of the effect when the target vehicle exits the tunnel in an embodiment;

[0037] Figure 7 It is a schematic flowchart of the positioning information processing method in yet another embodiment;

[0038] Figure 8 It is a block diagram of the structure of the positioning information processing apparatus in an embodiment;

[0039] Figure 9 It is a block diagram of the structure of the positioning information processing apparatus in another embodiment;

[0040] Figure 10 It is an internal structure diagram of a computer device in an embodiment. Detailed Implementation Modes

[0041] To make the objectives, technical solutions, and advantages of this application more clear and understandable, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining this application and are not used to limit this application.

[0042] The positioning information processing method provided by this application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other servers. Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides network security services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, cloud security, host security, etc., CDN, as well as basic cloud computing services such as big data and artificial intelligence platforms. The terminal 102 and the server 104 can be directly or indirectly connected through wired or wireless communication methods, and this application does not make any restrictions here.

[0043] The terminal 102 can obtain the first positioning information to be corrected corresponding to the target object. The first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object. The terminal 102 can perform a preliminary correction in the first direction on the first positioning information according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object, and determine the distance between the historical positioning information and the first positioning information. The historical positioning information is obtained by correcting and compensating the previously reckoned positioning information. The previously reckoned positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information. The terminal 102 can perform an advanced correction in the second direction on the second positioning information according to the distance to obtain the target positioning information after correction and compensation.

[0044] It can be understood that the terminal 102 can render and display the target positioning information after correction and compensation. It can also be understood that the terminal 102 can also send the target positioning information after correction and compensation to the server 104, and the server 104 performs corresponding positioning data processing based on the target positioning information. This embodiment does not make any restrictions on this, and it can be understood that Figure 1 the application scenarios in are only for illustrative purposes and are not limited thereto.

[0045] In one embodiment, Figure 2 As shown, a positioning information processing method is provided. In this embodiment, the method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0046] Step 202, obtaining first positioning information to be corrected corresponding to the target object; the first positioning information is obtained by dead reckoning based on inertial sensor information of the target object.

[0047] Among them, the object is an entity with mobile function, and the terminal can be deployed on the object. For example, the object can be a vehicle. It can be understood that if the object is a vehicle, the terminal can be deployed on the vehicle. The current positioning moment is the moment when the target object is currently positioned. Inertial sensor information is information collected by an inertial sensor set on the target object. Inertial sensors include gyroscopes and accelerometers. The first positioning information is positioning information obtained by dead reckoning based on the inertial sensor information of the target object. Dead reckoning refers to a method of calculating the positioning information of the target object at the next moment through the collected inertial sensor information under the condition that the positioning information at the current moment is known during the navigation process of the target object, so as to realize the positioning of the target object.

[0048] Specifically, the terminal may collect information through an inertial sensor disposed on the target object to obtain inertial sensing information. Further, the terminal may perform dead reckoning based on the inertial sensing information of the target object to obtain the first positioning information to be corrected corresponding to the target object.

[0049] In one embodiment, Figure 3 As shown, the target object is a target vehicle, the terminal can be set on the target vehicle, and the target vehicle is also provided with a vehicle inertial sensor. The terminal can communicate with the vehicle inertial sensor and collect information through the vehicle inertial sensor to obtain the inertial sensor information of the target vehicle. It can be understood that the positioning information corresponding to point B is the first positioning information obtained by dead reckoning based on the inertial sensor information of the target vehicle.

[0050] Step 204 , performing preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object, to obtain second positioning information corresponding to the target object.

[0051] The visual sensing information is information collected by a visual sensor disposed on the target object. The first direction is a direction perpendicular to the moving direction of the target object, i.e., the horizontal direction. The second positioning information is positioning information obtained by making a preliminary correction in the first direction to the first positioning information based on the visual sensing information of the target object.

[0052] Specifically, the terminal can collect information through a visual sensor set on the target object to obtain visual sensing information. Furthermore, the terminal can perform a first-direction compensation and correction on the first positioning information based on the visual sensing information of the target object to obtain the second positioning information corresponding to the target object. It can be understood that the terminal can perform a horizontal compensation and correction on the first positioning information based on the visual sensing information to obtain the second positioning information corresponding to the target object.

[0053] In one embodiment, continuing to refer to Figure 3 , the terminal can perform a preliminary correction on the first positioning information, that is, the positioning information corresponding to point B, in the first direction (i.e., the BO direction) based on the visual sensing information of the target vehicle to obtain the second positioning information corresponding to the target vehicle, that is, the positioning information corresponding to point O.

[0054] In one embodiment, determine the visual position information corresponding to the target object according to the visual sensing information of the target object, and perform a preliminary correction on the first positioning information in the first direction according to the visual position information to obtain the second positioning information corresponding to the target object. Continuing to refer to Figure 3 , it can be understood that the position point corresponding to the visual position information is also point O.

[0055] In one embodiment, when the GPS (Global Positioning System) fails, that is, when the terminal cannot receive the satellite positioning information of the target object, the terminal can directly perform a preliminary correction on the first positioning information in the first direction based on the visual sensing information of the target object to obtain the second positioning information corresponding to the target object.

[0056] Step 206, determine the distance between the historical positioning information and the first positioning information; the historical positioning information is obtained after correcting and compensating the previously deduced positioning information; the previously deduced positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information.

[0057] Specifically, the terminal can obtain the historical positioning information of the target object, and determine the distance between the historical positioning information and the first positioning information according to the positions corresponding to the historical positioning information and the first positioning information.

[0058] In one embodiment, continuing to refer to Figure 3 , the terminal can correct and compensate the previously deduced positioning information to obtain the historical positioning information (i.e., the positioning information corresponding to point A). Furthermore, the terminal can determine the distance (i.e., AB) between the position point corresponding to the historical positioning information (i.e., point A) and the position point corresponding to the first positioning information (i.e., point B). Among them, the previously deduced positioning information is the positioning information obtained by dead reckoning for the target vehicle before the first positioning information.

[0059] In one embodiment, the first positioning information to be corrected is the positioning information estimated at the current positioning moment. The terminal can perform a preliminary correction in the first direction on the first positioning information according to the visual sensing information of the target object, obtain the second positioning information corresponding to the target object at the current positioning moment, and determine the distance between the historical positioning information and the first positioning information. Furthermore, the terminal can perform an advanced correction in the second direction on the second positioning information according to the distance, and obtain the target positioning information corresponding to the current positioning moment after correction compensation. It can be understood that the terminal can perform correction compensation for each positioning moment.

[0060] Step 208: Perform an advanced correction in the second direction on the second positioning information according to the distance, and obtain the target positioning information after correction compensation.

[0061] Wherein, the second direction is the direction along the advancing direction of the target object, that is, the longitudinal direction. The target positioning information is used to represent the final positioning result of the target object.

[0062] Specifically, the terminal can perform an advanced correction in the second direction on the second positioning information according to the distance between the historical positioning information and the first positioning information, and obtain the target positioning information after correction compensation. It can be understood that the terminal can perform an advanced longitudinal correction on the second positioning information according to the distance, and obtain the target positioning information after correction compensation. It can also be understood that the target positioning information has been corrected both horizontally and longitudinally compared with the first positioning information.

[0063] In one embodiment, continue to refer to Figure 3 , the terminal can perform an advanced correction in the second direction (i.e., the OX direction) on the position point corresponding to the second positioning information (i.e., point O) according to the distance (i.e., AB) between the position point corresponding to the historical positioning information and the position point corresponding to the first positioning information (i.e., point B), and obtain the target positioning information after correction compensation. It can be understood that if there is no deviation in the heading of the target vehicle, the position corresponding to point X is the true position of the target vehicle, that is, the closer the positioning point corresponding to the target positioning information after correction compensation of the present application is to point X, the better, and the closer the positioning point corresponding to the target positioning information is to point X, the higher the positioning accuracy.

[0064] In one embodiment, the distance between the historical positioning information and the first positioning information is used as the first distance. The terminal can determine the second distance according to the historical positioning information and the second positioning information, and perform an advanced correction in the second direction on the second positioning information according to the first distance and the second distance, and obtain the target positioning information after correction compensation.

[0065] In the above positioning information processing method, the first positioning information to be corrected corresponding to the target object is obtained; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object; the first positioning information is preliminarily corrected in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object; the distance between the historical positioning information and the first positioning information is determined; the historical positioning information is obtained by correcting and compensating the previously dead-reckoned positioning information; the previously dead-reckoned positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information; the second positioning information is further corrected in the second direction according to the distance. Equivalently, without relying on satellite positioning, the dead-reckoned positioning information is compensated and corrected in both the first direction and the second direction, so that the finally obtained corrected and compensated target positioning information is more accurate, improving the positioning accuracy.

[0066] In one embodiment, the distance between the historical positioning information and the first positioning information is the first distance; correcting the second positioning information in the second direction according to the distance to obtain the corrected and compensated target positioning information includes: determining a second distance according to the historical positioning information and the second positioning information; further correcting the second positioning information in the second direction according to the difference between the first distance and the second distance to obtain the corrected and compensated target positioning information.

[0067] Wherein, the first distance is the distance between the position point corresponding to the historical positioning information and the position point corresponding to the first positioning information. The second distance is the distance between the position point corresponding to the historical positioning information and the position point corresponding to the second positioning information.

[0068] Specifically, the terminal can determine the first distance according to the position point corresponding to the historical positioning information and the position point corresponding to the first positioning information, and determine the second distance according to the position point corresponding to the historical positioning information and the position point corresponding to the second positioning information. The terminal can further correct the second positioning information in the second direction according to the difference between the first distance and the second distance to obtain the corrected and compensated target positioning information.

[0069] In one embodiment, continue to refer to Figure 3 , the difference between the first distance and the second distance can be determined by the following formula:

[0070]

[0071] Wherein, That is, the first distance AB between the position point corresponding to the historical positioning information (i.e., point A) and the position point corresponding to the first positioning information (i.e., point B), and AO is the second distance between the position point corresponding to the historical positioning information and the second positioning information (i.e., point O).

[0072] In one embodiment, the terminal may perform an advanced correction in the second direction on the position information in the second positioning information according to the difference between the first distance and the second distance, so as to obtain target positioning information including the corrected and compensated position information.

[0073] In the above embodiment, by performing an advanced correction in the second direction on the second positioning information according to the difference between the first distance and the second distance, the accuracy of the obtained target positioning information can be improved, thereby further improving the accuracy of the positioning result of the target object.

[0074] In one embodiment, the second positioning information includes second lateral positioning information and second longitudinal positioning information; performing an advanced correction in the second direction on the second positioning information according to the difference between the first distance and the second distance to obtain the target positioning information after correction and compensation includes: performing a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance to obtain longitudinally corrected positioning information; determining the target positioning information after correction and compensation according to the second lateral positioning information and the longitudinally corrected positioning information.

[0075] Among them, the second lateral positioning information is the positioning information in the second positioning information that is perpendicular to the advancing direction of the target object. The second longitudinal positioning information is the positioning information in the second positioning information that is the same as the advancing direction of the target object. The longitudinally corrected positioning information is the positioning information in the longitudinal dimension obtained by performing a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance.

[0076] Specifically, the terminal may perform a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance to obtain longitudinally corrected positioning information, and determine the target positioning information after correction and compensation according to the second lateral positioning information and the longitudinally corrected positioning information. It can be understood that the target positioning information after correction and compensation includes the second lateral positioning information and the longitudinally corrected positioning information.

[0077] In one embodiment, the second lateral positioning information includes second lateral position information, the second longitudinal positioning information includes second longitudinal position information, and the longitudinally corrected positioning information includes longitudinally corrected position information. The terminal may perform a longitudinal advanced correction on the second longitudinal position information according to the difference between the first distance and the second distance to obtain longitudinally corrected position information, and determine the target positioning information after correction and compensation according to the second lateral position information and the longitudinally corrected position information. It can be understood that the laterally corrected position information is the position information in the longitudinal dimension obtained by performing a longitudinal advanced correction on the second longitudinal position information according to the difference between the first distance and the second distance. The target positioning information after correction and compensation includes the second lateral position information and the longitudinally corrected position information.

[0078] In the above embodiments, according to the difference between the first distance and the second distance, the second longitudinal positioning information is longitudinally advanced and corrected, and then according to the second lateral positioning information and the longitudinally corrected positioning information obtained after correction, the target positioning information after correction and compensation is determined, which can further improve the accuracy of the obtained target positioning information, thereby further improving the accuracy of the positioning result of the target object.

[0079] In one embodiment, the first positioning information to be corrected is the positioning information respectively deduced at each positioning moment within the current compensation period; determining the distance between the historical positioning information and the first positioning information includes: for the first positioning information deduced at each positioning moment within the current compensation period, respectively determining the distance between the first positioning information and the corresponding historical positioning information to obtain the distance corresponding to each positioning moment; the historical positioning information is the target positioning information determined in the previous compensation period; correcting and compensating the second positioning information in the second direction according to the distance to obtain the target positioning information after correction and compensation includes: for each positioning moment within the current compensation period, determining and storing the sub-compensation error corresponding to the positioning moment according to the distance corresponding to the positioning moment; smoothing the sub-compensation errors respectively corresponding to each positioning moment within the current compensation period to obtain the target compensation error corresponding to the current compensation period; correcting and advancing the second positioning information corresponding to the target positioning moment in the second direction according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; the target positioning moment is one of the positioning moments within the current compensation period.

[0080] Wherein, the current compensation period is the period for current correction and compensation. The current compensation period includes multiple positioning moments. The positioning moment refers to the moment when the positioning information of the target object is obtained. The sub-compensation error is the compensation error corresponding to each positioning moment within the current compensation period. The target compensation error is the compensation error obtained by smoothing the sub-compensation errors respectively corresponding to each positioning moment within the current compensation period.

[0081] Specifically, for the first positioning information deduced at each positioning moment within the current compensation period, the terminal can determine the distance between the first positioning information and the corresponding historical positioning information, and obtain the distance corresponding to this positioning moment. It can be understood that in this way, the distances corresponding to each positioning moment within the current compensation period can be obtained. For each positioning moment within the current compensation period, the terminal can determine and store the sub-compensation error corresponding to this positioning moment according to the distance corresponding to this positioning moment. Furthermore, the terminal can smooth the sub-compensation errors corresponding to each positioning moment within the current compensation period to obtain the target compensation error corresponding to the current compensation period, and perform an advanced correction in the second direction on the second positioning information corresponding to the target positioning moment according to the target compensation error to obtain the target positioning information corresponding to the current compensation period, where the target positioning moment is one of the positioning moments within the current compensation period.

[0082] In the above embodiment, since the visual sensing information corresponding to each positioning moment may fluctuate, the sub-compensation errors corresponding to each positioning moment may also fluctuate. By smoothing the sub-compensation errors corresponding to each positioning moment within the current compensation period, the target compensation error corresponding to the current compensation period can be obtained, thereby improving the accuracy of the obtained compensation error. Furthermore, by performing an advanced correction in the second direction on the second positioning information corresponding to the target positioning moment according to the relatively accurate target compensation error, the target positioning information corresponding to the current compensation period can be obtained, which can further improve the accuracy of the obtained target positioning information, and thus further improve the accuracy of the positioning result of the target object.

[0083] In one embodiment, the method further includes: when the visual sensing information is available, performing the step of preliminarily correcting the first positioning information in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object and subsequent steps; when the visual sensing information is unavailable, using the first positioning information as the target positioning information of the target object.

[0084] Specifically, the terminal can determine whether the visual sensing information collected by the visual sensor is available. When the visual sensing information is available, the terminal can perform a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object, and determine the distance between the historical positioning information and the first positioning information. Furthermore, the terminal can perform an advanced correction on the second positioning information in a second direction according to the distance to obtain the target positioning information after correction and compensation. When the visual sensing information is not available, the terminal can directly use the first positioning information as the target positioning information of the target object. It can be understood that when the visual sensing information is not available, in order to avoid incorrect correction and compensation, the first positioning information should not be corrected and compensated based on the visual sensing information, but directly used as the target positioning information of the target object.

[0085] For example, if the target object is a target vehicle, in the scenario of navigation and positioning for the target vehicle, the availability of the visual sensing information means that the lane lines collected by the visual sensor are clear and complete. The unavailability of the visual sensing information means that the lane lines collected by the visual sensor are blurred or incomplete.

[0086] In the above embodiments, by judging whether the visual sensing information is available and thus selecting the corresponding method for determining the target positioning information of the target object, the accuracy of the obtained target positioning information can be further improved, and thus the accuracy of the positioning result of the target object can be further improved.

[0087] In one embodiment, performing a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object includes: determining the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object; determining the compensation error according to the visual position information and the first positioning information; and performing a preliminary correction on the first positioning information in a first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

[0088] Among them, the lane line intercept information is the information used to represent the vertical distance from the current position of the target object observed by the visual sensor to the lane line. The visual position information is the position information determined according to the lane line intercept information of the target object. The compensation error is the information used to correct and compensate the first positioning information of the target object.

[0089] Specifically, the visual sensing information includes lane line intercept information. The terminal can determine the visual position information corresponding to the target object according to the lane line intercept information of the target object. It can be understood that the terminal can determine the visual position information based on the lane line intercept information, the position points corresponding to the historical positioning information, and the position points corresponding to the first positioning information, that is, the position points corresponding to the visual position information can be determined. Furthermore, the terminal can determine the compensation error according to the visual position information and the first positioning information, and perform a preliminary correction on the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

[0090] In one embodiment, the first positioning information includes first position information, and the second positioning information includes second position information. The compensation error includes a position error. The terminal can determine the position error according to the position difference between the position points corresponding to the visual position information and the position points corresponding to the first position information. The terminal can perform a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object. Among them, the position error is an error in the position dimension used to correct and compensate the first position information in the first positioning information.

[0091] In the above embodiment, by using the lane line intercept information in the visual sensing information of the target object to determine the visual position information corresponding to the target object, the accuracy of the visual position information can be improved. By determining the compensation error according to the relatively accurate visual position information and the first positioning information, the accuracy of the obtained compensation error can be improved. Furthermore, by performing a preliminary correction on the first positioning information in the first direction according to the relatively accurate compensation error to obtain the second positioning information corresponding to the target object, the accuracy of the second positioning information can be improved.

[0092] In one embodiment, the first positioning information includes first position information and first state information; the second positioning information includes second position information and second state information; the compensation error includes a position error and a state error; performing a preliminary correction on the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object includes: performing a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object; performing a preliminary state correction on the first state information according to the state error to obtain the second state information corresponding to the target object.

[0093] Among them, the state error is an error in the state dimension used to correct and compensate the first state information in the first positioning information.

[0094] Specifically, the terminal can perform a preliminary position correction in a first direction on the first position information belonging to the position dimension according to the position error to obtain the second position information corresponding to the target object. The terminal can perform a preliminary state correction on the first state information belonging to the state dimension according to the state error to obtain the second state information corresponding to the target object.

[0095] In the above embodiment, a preliminary position correction in a first direction is performed on the first position information through the position error to obtain the second position information corresponding to the target object, and a preliminary state correction is performed on the first state information according to the state error to obtain the second state information corresponding to the target object, thereby further improving the accuracy of the second positioning information.

[0096] In one embodiment, determining the compensation error according to the visual position information and the first positioning information includes: determining the position error according to the position difference between the visual position information and the first position information; solving the error of the pre-constructed positioning error equation according to the position error to obtain the state error.

[0097] Among them, the positioning error equation is a mathematical equation pre-constructed based on the position error to be solved and each state error. That is, the position error and the state error in the positioning error equation are unknowns.

[0098] Specifically, the terminal can determine the position error according to the position difference between the visual position information and the first position information. After determining the position error according to the position difference between the visual position information and the first position information, the terminal can substitute the position error into the positioning error equation to solve the error and solve each state error.

[0099] In one embodiment, the state error includes at least one of platform misalignment angle error, velocity error, dead reckoning error, gyro zero bias, accelerometer zero bias, installation error angle residual, wheel speedometer scale factor error, or time delay of the wheel speedometer transmitting to the inertial sensor. In this way, by providing multiple state errors and determining the second positioning information through the position error and multiple state errors, the accuracy of the second positioning information can be further improved.

[0100] In one embodiment, the positioning error equation can be a system of equations, and the system of equations includes a state equation and a measurement equation. The terminal can perform error solving through the following positioning error equation based on the position error to obtain each state error:

[0101]

[0102] Among them,

[0103]

[0104] Represents the state vector, Represents the result of differentiating with respect to x, F SINS / Is the state transition matrix of the system, That is the state equation. H SINS / Represents the measurement matrix of the system, z = SINS / x is the measurement equation, where, Represents the position information obtained by dead reckoning based on SINS (Strapdown inertial navigation system), Represents the position information obtained by dead reckoning based on DR (Dead Reckoning), p SINS Represents The true part of the position information in, δ is used to represent the error, vp SINS Represents The error in, p DR Represents The true part of the position information in, Represents The error in, M Dpv Represents the relationship matrix between the position and velocity corresponding to DR dead reckoning, Represents the velocity of DR dead reckoning, τ OD Represents the time delay of the wheel speedometer transmitted to the inertial sensor.

[0105] Among them, the state transition matrix of the system

[0106] The measurement matrix H of the system SINS / DR =[0 3×3 0 3×3 I 3×3 -I 3×3 0 3×3 0 3×3 0 3×2 0 3×1 -M Dpk .

[0107] Represents the platform misalignment angle error, among which, Respectively represent the platform misalignment angle errors in the three directions of northeast and sky in the northeast-sky coordinate system. Represents the velocity error, among which, Respectively represent the velocity errors in the three directions of northeast and sky in the northeast-sky coordinate system. δp = [δL δλ δλ] T Represents the position error, where δL, δλ, and δλ represent the error longitude, error latitude, and altitude error respectively. δpDR Indicates dead reckoning error, Indicates gyro zero bias, where, Respectively indicate the gyro zero bias in each direction in the vehicle coordinate system. Indicates accelerometer zero bias, where, Respectively indicate the accelerometer zero bias in each direction in the vehicle coordinate system. Indicates the installation error angle residual, where α θ Indicates the true pitch angle, α ψ Indicates the true heading angle, δα θ Indicates the pitch angle error, δα ψ Indicates the heading angle error. δK OD Indicates the wheel speedometer scale factor error. M aa Indicates the attitude relationship matrix, M av Indicates the relationship matrix between attitude and velocity, ap Indicates the relationship matrix between attitude and position, M va Indicates the relationship matrix between velocity and attitude, M vv Indicates the velocity relationship matrix, M vp Indicates the relationship matrix between velocity and position, M pv Indicates the relationship matrix between position and velocity, M pp Indicates the position relationship matrix, M Dpa Indicates the relationship matrix between the position and attitude corresponding to DR reckoning, M Dpp Indicates the position relationship matrix corresponding to DR reckoning, M Dpi Indicates the relationship matrix between the position corresponding to DR reckoning and time delay, M Dpk Indicates the relationship matrix between the position corresponding to DR reckoning and the wheel speedometer scale factor error, Indicates the true attitude rotation matrix from the b system (vehicle coordinate system) to the n system (north - east - up coordinate system), and I represents the identity matrix.

[0108] It should be noted that the above - mentioned relationship matrices are all determined based on at least one unknown quantity (position error and state error) in the state vector. It can be understood that the above - mentioned positioning error equations are all composed of various unknown quantities. After determining the position error according to the position difference between the visual position information and the first position information, the position error is substituted into the above - mentioned positioning error equation to solve for the error of the positioning error equation and obtain the state error.

[0109] In one embodiment, the first positioning information obtained based on DR reckoning includes the reckoning speed information in the n system, and this speed information can be expressed by the following formula:

[0110]

[0111] Among them, represents the estimated speed information in the n coordinate system, represents the estimated speed information of the system, represents the attitude rotation matrix obtained by estimation from the b coordinate system to the n coordinate system, represents the estimated pitch angle, represents the estimated heading angle, v OD represents the true speed information of the system, represents the true speed information in the n coordinate system, represents the speed error existing in

[0112] It can be understood that from the above derivation process of the estimated speed information in the n coordinate system, the speed error obtained by DR estimation mainly includes two aspects, namely attitude error (i.e., pitch angle error and heading angle error) and calibration factor error and installation angle error of the wheel speedometer. Starting from the causes of attitude error, this application makes an advanced correction to the first positioning information obtained by dead reckoning based on visual sensing information, which can further improve the accuracy of the positioning result of the target object. It can be understood that the reason for the attitude error is that there is a deviation in the heading of the target object, which leads to an error in speed decomposition, and then a position error is generated through integration.

[0113] In the above embodiment, by determining the position error through the position difference between the visual position information and the first position information, the accuracy of the position error can be improved. Solving the error of the pre-constructed positioning error equation according to the position error to obtain the state error can improve the accuracy of the state error, so that the state error of the more accurate position error can further improve the accuracy of the second positioning information.

[0114] In one embodiment, the first position information includes the first lateral position information and the first longitudinal position information; performing a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object, including: performing a preliminary position correction on the first lateral position information according to the position error to obtain the lateral corrected position information; determining the second position information corresponding to the target object according to the lateral corrected position information and the first longitudinal position information.

[0115] Among them, the lateral corrected position information is the position information that belongs to the lateral dimension and is obtained by performing a preliminary position correction on the first lateral position information according to the position error.

[0116] Specifically, the terminal can perform preliminary position correction on the first lateral position information according to the position error to obtain the lateral corrected position information, and determine the second position information corresponding to the target object according to the lateral corrected position information and the first longitudinal position information. It can be understood that the second position information includes the lateral corrected position information and the first longitudinal position information.

[0117] In the above embodiment, by performing preliminary position correction on the first lateral position information through the position error to obtain the lateral corrected position information, and determining the second position information corresponding to the target object according to the lateral corrected position information and the first longitudinal position information, the accuracy of the obtained second position information can be further improved.

[0118] In one embodiment, performing preliminary correction in the first direction on the first positioning information according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object includes: when receiving the satellite positioning information of the target object, performing preliminary correction in the first direction on the first positioning information according to the visual sensing information of the target object to obtain the preliminarily corrected positioning information; and performing correction in the second direction on the preliminarily corrected positioning information according to the longitudinal position information in the satellite positioning information to obtain the second positioning information corresponding to the target object.

[0119] Among them, the satellite positioning information is the positioning information provided by the satellite that locates the target object. The satellite positioning information includes the longitudinal position information. It can be understood that the satellite positioning information may further include at least one of the lateral position information, speed information, or heading information, etc.

[0120] Specifically, when the target object is in a position with good signal, the terminal set on the target object can receive the satellite positioning information obtained by the satellite for positioning the target object. When receiving the satellite positioning information of the target object, the terminal can perform preliminary correction in the first direction on the first positioning information according to the visual sensing information of the target object to obtain the preliminarily corrected positioning information, and then further perform correction in the second direction on the preliminarily corrected positioning information according to the longitudinal position information in the satellite positioning information to obtain the second positioning information corresponding to the target object.

[0121] In one embodiment, when the target object is in a position with poor signal or no signal, such as when the target object is in a tunnel, the terminal set on the target object cannot receive the satellite positioning information obtained by the satellite for positioning the target object. When the satellite positioning information of the target object cannot be received, the terminal can directly perform preliminary correction and advanced correction on the dead reckoning obtained first positioning information according to the visual sensing information of the target object, so as to obtain the corrected and compensated target positioning information.

[0122] In the above embodiments, when satellite positioning is effective, the first positioning information is initially corrected in a first direction through the visual sensing information of the target object to obtain the initially corrected positioning information. Then, according to the longitudinal position information in the satellite positioning information, the initially corrected positioning information is corrected in a second direction to obtain the second positioning information corresponding to the target object, which can further improve the accuracy of the obtained second positioning information.

[0123] In one embodiment, as Figure 4 shown, the terminal can determine whether satellite positioning fails. When satellite positioning fails, that is, when the satellite positioning information of the target object cannot be received, the terminal can continue to determine whether the visual sensing information is available. When the visual sensing information is not available, the terminal can clear the compensation error stored in the current compensation period and directly use the first positioning information obtained by dead reckoning based on the inertial sensing information of the target object as the target positioning information of the target object. When the visual sensing information is available, the first positioning information is initially corrected in a first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object. For the first positioning information calculated at each positioning moment in the current compensation period, the distance between the first positioning information and the corresponding historical positioning information is determined respectively to obtain the distance corresponding to each positioning moment. For each positioning moment in the current compensation period, according to the distance corresponding to the positioning moment, the sub-compensation error corresponding to the positioning moment is determined and stored, and the sub-compensation errors corresponding to each positioning moment in the current compensation period (for example, each compensation period is set at a preset time interval) are smoothed to obtain the target compensation error corresponding to the current compensation period. Then, the terminal can perform an advanced correction in a second direction on the second positioning information corresponding to the target positioning moment according to the target compensation error to obtain the target positioning information corresponding to the current compensation period.

[0124] In one embodiment, the target object includes a target vehicle in a vehicle navigation scenario; the inertial sensing information is collected by a vehicle inertial sensor provided on the target vehicle; the visual sensing information is collected by a vehicle visual sensor provided on the target vehicle; the target positioning information is the corrected and compensated positioning information of the target vehicle; the method further includes: rendering and displaying the vehicle position information in the target positioning information on an in-vehicle navigation map.

[0125] Specifically, obtain the first positioning information to be corrected corresponding to the target vehicle, and perform a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target vehicle to obtain the second positioning information corresponding to the target vehicle. The terminal can determine the distance between the historical positioning information and the first positioning information, and perform an advanced correction on the second positioning information in a second direction to obtain the corrected and compensated positioning information of the target vehicle after correction and compensation, and render and display the vehicle position information in the corrected and compensated positioning information on the in-vehicle navigation map.

[0126] In one embodiment, as Figure 5 shown, the target vehicle is entering a tunnel. The image shown in 501 is a real-scene image of the tunnel entrance collected by a camera installed in the target vehicle. It can be understood that the vehicle shown in 501 is another vehicle that is also traveling in the tunnel and is in front of the target vehicle, which is collected by the camera in the target vehicle. The image shown in 502 is a virtual image of the target vehicle itself entering the tunnel rendered and displayed by the terminal on the in-vehicle navigation map, which is used to indicate to the user that the target vehicle is entering the tunnel. It can be understood that the terminal can render and display the vehicle position information in the corrected and compensated positioning information (i.e., the corrected vehicle position information of the target vehicle itself) on the in-vehicle navigation map so that the user can more intuitively see the navigation positioning result of the target vehicle itself.

[0127] In one embodiment, as Figure 6 shown, the target vehicle is exiting the tunnel. The image shown in 601 is a real-scene image of the tunnel exit collected by a camera installed in the target vehicle. It can be understood that the vehicle shown in 601 is another vehicle that is also exiting the tunnel and is in front of the target vehicle, which is collected by the camera in the target vehicle. The image shown in 602 is a virtual image of the target vehicle itself exiting the tunnel rendered and displayed by the terminal on the in-vehicle navigation map, which is used to indicate to the user that the target vehicle is exiting the tunnel. It can be understood that the terminal can render and display the vehicle position information in the corrected and compensated positioning information on the in-vehicle navigation map so that the user can more intuitively see the navigation positioning result. By the positioning information processing method of the present application, the positioning accuracy of the target vehicle can be improved, so that the positioning result 602 displayed on the in-vehicle navigation map when the target vehicle exits the tunnel can be consistent with the real position of the target vehicle in the image shown in 601, avoiding the positioning result displayed on the in-vehicle navigation map lagging behind the real position of the target vehicle.

[0128] In the above embodiments, by applying the positioning information processing method of the present application to the vehicle navigation scenario, the accuracy of the navigation positioning result of the target vehicle can be improved.

[0129] As Figure 7As shown, in one embodiment, a method for processing positioning information is provided. In this embodiment, taking the method applied to the Figure 1 terminal 102 in [the text] as an example for illustration, the method specifically includes the following steps:

[0130] Step 702, obtain the first positioning information to be corrected corresponding to the target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object at each positioning moment within the current compensation period; the first positioning information includes the first position information and the first state information.

[0131] Step 704, when the visual sensing information is available, determine the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object.

[0132] Step 706, determine the position error according to the position difference between the visual position information and the first position information.

[0133] Step 708, solve the error of the pre-constructed positioning error equation according to the position error to obtain the state error.

[0134] In one embodiment, the state error includes at least one of platform misalignment angle error, speed error, dead reckoning error, gyro zero bias, accelerometer zero bias, installation error angle residual, wheel speedometer scale factor error, or time delay of the wheel speedometer transmitted to the inertial sensor.

[0135] Step 710, perform a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object.

[0136] Step 712, perform a preliminary state correction on the first state information according to the state error to obtain the second state information corresponding to the target object.

[0137] Step 714, for the first positioning information deduced at each positioning moment within the current compensation period, respectively determine the distance between the first positioning information and the corresponding historical positioning information to obtain the first distance corresponding to each positioning moment; the historical positioning information is the positioning information obtained by dead reckoning for the target object in the previous compensation period.

[0138] Step 716, determine the second distance according to the historical positioning information and the second positioning information; the second positioning information includes the second position information and the second state information.

[0139] Step 718, according to the difference between the first distance and the second distance, for each positioning moment within the current compensation period, determine the sub-compensation error corresponding to the positioning moment according to the difference between the first distance and the second distance corresponding to the positioning moment and store it.

[0140] Step 720, smooth the sub-compensation errors corresponding to each positioning moment in the current compensation period to obtain the target compensation error corresponding to the current compensation period.

[0141] Step 722, perform an advanced correction in the second direction on the second positioning information corresponding to the target positioning moment according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; the target positioning moment is one of the positioning moments in the current compensation period.

[0142] Step 724, in the case where the visual sensing information is unavailable, use the first positioning information as the target positioning information of the target object.

[0143] This application also provides an application scenario that applies the above positioning information processing method. Specifically, the positioning information processing method can be applied to the scenario of vehicle navigation. For example, the positioning information processing method can be applied to the lane-level vehicle navigation scenario. It can be understood that a terminal can be deployed on the target vehicle, and the terminal can obtain the first positioning information to be corrected corresponding to the target vehicle; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target vehicle at each positioning moment in the current compensation period; the first positioning information includes the first position information and the first state information; the inertial sensing information is collected by a vehicle inertial sensor provided on the target vehicle.

[0144] In the case where the visual sensing information is available, the terminal can determine the visual position information corresponding to the target vehicle according to the lane line intercept information in the visual sensing information of the target vehicle. Among them, the visual sensing information is collected by a vehicle visual sensor provided on the target vehicle. Determine the position error according to the position difference between the visual position information and the first position information. Solve the error of the pre-constructed positioning error equation according to the position error to obtain the state error. Perform a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target vehicle. Perform a preliminary state correction on the first state information according to the state error to obtain the second state information corresponding to the target vehicle.

[0145] For the first positioning information estimated at each positioning moment within the current compensation period, the terminal can respectively determine the distance between the first positioning information and the corresponding historical positioning information to obtain the first distance corresponding to each positioning moment; the historical positioning information is the positioning information obtained by dead reckoning for the target vehicle in the previous compensation period. Determine the second distance based on the historical positioning information and the second positioning information; the second positioning information includes second position information and second status information. According to the difference between the first distance and the second distance, for each positioning moment within the current compensation period, determine and store the sub-compensation error corresponding to the positioning moment according to the difference between the first distance and the second distance corresponding to the positioning moment. Smooth the sub-compensation errors corresponding to each positioning moment within the current compensation period to obtain the target compensation error corresponding to the current compensation period. Perform an advanced correction in the second direction on the second positioning information corresponding to the target positioning moment according to the target compensation error to obtain the corrected and compensated positioning information of the target vehicle corresponding to the current compensation period; the target positioning moment is one of the positioning moments within the current compensation period.

[0146] In the case where the visual sensing information is unavailable, the terminal can use the first positioning information as the corrected and compensated positioning information of the target vehicle.

[0147] This application also provides another application scenario, which applies the above positioning information processing method. Specifically, the positioning information processing method can be applied to scenarios for positioning a driving vehicle in autonomous driving and assisted driving. It can be understood that in autonomous driving and assisted driving, it is also necessary to position the driving vehicle to determine the location of the driving vehicle. Through the positioning information processing method of this application, more accurate vehicle positioning results for autonomous driving and assisted driving scenarios can be obtained. It can also be understood that the positioning information processing method of this application can also be applied to positioning scenarios for other mobile robots except vehicles, etc. Through the positioning information processing method of this application, more accurate positioning results for mobile robots can be obtained.

[0148] It should be understood that although the steps in the flowcharts of the above embodiments are shown in sequence, these steps are not necessarily executed in sequence. Unless there is a clear indication in this article, the execution of these steps has no strict sequence limit, and these steps can be executed in other sequences. Moreover, at least a part of the steps in the above embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same positioning moment, but can be executed at different positioning moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0149] In one embodiment, asFigure 8 As shown, a positioning information processing device 800 is provided. This device can be a software module, a hardware module, or a combination of both to form part of a computer device. Specifically, the device includes:

[0150] An acquisition module 802, configured to acquire first positioning information to be corrected corresponding to a target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object;

[0151] A correction module 804, configured to perform a preliminary correction on the first positioning information in a first direction according to the visual sensing information of the target object to obtain second positioning information corresponding to the target object;

[0152] A determination module 806, configured to determine the distance between historical positioning information and the first positioning information; the historical positioning information is obtained by performing correction and compensation on the previously dead-reckoned positioning information; the previously dead-reckoned positioning information is the positioning information obtained by dead reckoning for the target object before the first positioning information;

[0153] The correction module 804 is further configured to perform an advanced correction on the second positioning information in a second direction according to the distance to obtain the target positioning information after correction and compensation.

[0154] In one embodiment, the distance between the historical positioning information and the first positioning information is a first distance; the correction module 804 is further configured to determine a second distance according to the historical positioning information and the second positioning information; and perform an advanced correction on the second positioning information in a second direction according to the difference between the first distance and the second distance to obtain the target positioning information after correction and compensation.

[0155] In one embodiment, the second positioning information includes second lateral positioning information and second longitudinal positioning information; the correction module 804 is further configured to perform a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance to obtain longitudinally corrected positioning information; and determine the target positioning information after correction and compensation according to the second lateral positioning information and the longitudinally corrected positioning information.

[0156] In one embodiment, the first positioning information to be corrected is the positioning information respectively calculated at each positioning moment within the current compensation period; the determining module 806 is further configured to, for the first positioning information calculated at each positioning moment within the current compensation period, respectively determine the distance between the first positioning information and the corresponding historical positioning information, so as to obtain the distance corresponding to each positioning moment; the historical positioning information is the target positioning information determined in the previous compensation period; the correcting module 804 is further configured to, for each positioning moment within the current compensation period, determine and store the sub-compensation error corresponding to the positioning moment according to the distance corresponding to the positioning moment; perform smoothing processing on the sub-compensation errors respectively corresponding to the positioning moments within the current compensation period to obtain the target compensation error corresponding to the current compensation period; perform an advanced correction on the second positioning information corresponding to the target positioning moment in the second direction according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; the target positioning moment is one of the positioning moments within the current compensation period.

[0157] In one embodiment, when the visual sensing information is available, the step of notifying the correcting module 804 to perform a preliminary correction on the first positioning information in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object; when the visual sensing information is unavailable, the determining module 806 is further configured to use the first positioning information as the target positioning information of the target object.

[0158] In one embodiment, the correcting module 804 is further configured to determine the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object; determine the compensation error according to the visual position information and the first positioning information; perform a preliminary correction on the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

[0159] In one embodiment, the first positioning information includes first position information and first state information; the second positioning information includes second position information and second state information; the compensation error includes position error and state error; the correcting module 804 is further configured to perform a preliminary position correction on the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object; perform a preliminary state correction on the first state information according to the state error to obtain the second state information corresponding to the target object.

[0160] In one embodiment, the correcting module 804 is further configured to determine the position error according to the position difference between the visual position information and the first position information; perform error solving on the pre-constructed positioning error equation according to the position error to obtain the state error.

[0161] In one embodiment, the state error includes at least one of a platform misalignment angle error, a velocity error, a dead reckoning error, a gyroscope zero bias, an accelerometer zero bias, an installation error angle residual, a wheel speedometer scale factor error, or a time delay for transmitting the wheel speedometer to the inertial sensor.

[0162] In one embodiment, the first position information includes first lateral position information and first longitudinal position information; the correction module 804 is further configured to perform a preliminary position correction on the first lateral position information according to the position error to obtain lateral corrected position information; and determine second position information corresponding to the target object according to the lateral corrected position information and the first longitudinal position information.

[0163] In one embodiment, the correction module 804 is further configured to, when receiving satellite positioning information of the target object, perform a preliminary correction in a first direction on the first positioning information according to the visual sensing information of the target object to obtain the preliminarily corrected positioning information; and perform a correction in a second direction on the preliminarily corrected positioning information according to the longitudinal position information in the satellite positioning information to obtain second positioning information corresponding to the target object.

[0164] In one embodiment, the target object includes a target vehicle in a vehicle navigation scenario; the inertial sensing information is collected by a vehicle inertial sensor disposed on the target vehicle; the visual sensing information is collected by a vehicle visual sensor disposed on the target vehicle; the target positioning information is the corrected and compensated positioning information of the target vehicle; as Figure 9 shown, in addition to the acquisition module 802, the correction module 804, and the determination module 806, the above positioning information processing apparatus 800 further includes:

[0165] A rendering module 808, configured to render and display the vehicle position information in the target positioning information on an in-vehicle navigation map.

[0166] The above positioning information processing apparatus obtains the first positioning information to be corrected corresponding to the target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object; performs a preliminary correction in a first direction on the first positioning information according to the visual sensing information of the target object to obtain second positioning information corresponding to the target object; determines the distance between the historical positioning information and the first positioning information; the historical positioning information is obtained by correcting and compensating the previously dead-reckoned positioning information; the previously dead-reckoned positioning information is the dead-reckoned positioning information for the target object before the first positioning information; and performs an advanced correction in a second direction on the second positioning information according to the distance. Equivalently, without relying on satellite positioning, both the first-direction compensation correction and the second-direction compensation correction are realized for the dead-reckoned positioning information, so that the finally obtained corrected and compensated target positioning information is more accurate, improving the positioning accuracy.

[0167] Each module in the above positioning information processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0168] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structural diagram can be as Figure 10 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a positioning information processing method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0169] Those skilled in the art can understand that Figure 10 the structure shown in

[0170] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0171] In one embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the steps in the above-described method embodiments.

[0172] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the steps in the above-described method embodiments.

[0173] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0174] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0175] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0176] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A positioning information processing method, characterized in that, The method includes: Obtaining first positioning information to be corrected corresponding to a target object; the first positioning information is obtained by dead reckoning based on inertial sensing information of the target object; the first positioning information to be corrected is positioning information respectively reckoned at each positioning moment within the current compensation period; Performing a preliminary correction in a first direction on the first positioning information according to visual sensing information of the target object to obtain second positioning information corresponding to the target object; For the first positioning information reckoned at each positioning moment within the current compensation period, respectively determining the distance between the first positioning information and corresponding historical positioning information to obtain the distance corresponding to each positioning moment; the historical positioning information is the target positioning information determined in the previous compensation period; Performing an advanced correction in a second direction on the second positioning information according to the distance to obtain target positioning information after correction compensation; 2. The method according to claim 1, wherein The distance between the first positioning information and corresponding historical positioning information is a first distance; The performing an advanced correction in a second direction on the second positioning information according to the distance to obtain target positioning information after correction compensation includes: Determining a second distance according to the historical positioning information and the second positioning information; Performing an advanced correction in a second direction on the second positioning information according to the difference between the first distance and the second distance to obtain target positioning information after correction compensation; 3. The method according to claim 2, wherein The second positioning information includes second lateral positioning information and second longitudinal positioning information; The performing an advanced correction in a second direction on the second positioning information according to the difference between the first distance and the second distance to obtain target positioning information after correction compensation includes: Performing a longitudinal advanced correction on the second longitudinal positioning information according to the difference between the first distance and the second distance to obtain longitudinally corrected positioning information; Determining target positioning information after correction compensation according to the second lateral positioning information and the longitudinally corrected positioning information; 4. The method according to claim 1, wherein The performing an advanced correction in a second direction on the second positioning information according to the distance to obtain target positioning information after correction compensation includes: For each positioning moment within the current compensation period, determining and storing a sub-compensation error corresponding to the positioning moment according to the distance corresponding to the positioning moment; Smoothing the sub-compensation errors respectively corresponding to the positioning moments within the current compensation period to obtain a target compensation error corresponding to the current compensation period; Performing an advanced correction in a second direction on the second positioning information corresponding to a target positioning moment according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; the target positioning moment is one of the positioning moments within the current compensation period; 5. The method according to claim 1, characterized in that, The method further includes: When the visual sensing information is available, performing the step of performing a preliminary correction in a first direction on the first positioning information according to the visual sensing information of the target object to obtain second positioning information corresponding to the target object and subsequent steps; In the case where the visual sensing information is unavailable, use the first positioning information as the target positioning information of the target object.

6. The method according to claim 1, characterized in that, The first preliminary correction of the first positioning information in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object includes: Determine the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object; Determine the compensation error according to the visual position information and the first positioning information; Perform a first preliminary correction of the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

7. The method according to claim 6, characterized in that, The first positioning information includes first position information and first state information; the second positioning information includes second position information and second state information; the compensation error includes position error and state error; The first preliminary correction of the first positioning information in the first direction according to the compensation error to obtain the second positioning information corresponding to the target object includes: Perform a first preliminary position correction of the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object; Perform a preliminary state correction of the first state information according to the state error to obtain the second state information corresponding to the target object.

8. The method according to claim 7, wherein The determination of the compensation error according to the visual position information and the first positioning information includes: Determine the position error according to the position difference between the visual position information and the first position information; Solve the error of the pre-constructed positioning error equation according to the position error to obtain the state error.

9. The method according to claim 7, wherein The state error includes at least one of platform misalignment angle error, speed error, dead reckoning error, gyro zero bias, accelerometer zero bias, installation error angle residual, wheel speedometer scale factor error, or time delay of the wheel speedometer transmitted to the inertial sensor.

10. The method according to claim 7, characterized in that, The first position information includes first lateral position information and first longitudinal position information; The first preliminary position correction of the first position information in the first direction according to the position error to obtain the second position information corresponding to the target object includes: Perform a preliminary position correction of the first lateral position information according to the position error to obtain the laterally corrected position information; Determine the second position information corresponding to the target object according to the laterally corrected position information and the first longitudinal position information.

11. The method according to claim 1, characterized in that, The first preliminary correction of the first positioning information in the first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object includes: In the case of receiving the satellite positioning information of the target object, perform a first preliminary correction of the first positioning information in the first direction according to the visual sensing information of the target object to obtain the preliminarily corrected positioning information; Perform a second correction of the preliminarily corrected positioning information in the second direction according to the longitudinal position information in the satellite positioning information to obtain the second positioning information corresponding to the target object.

12. The method according to any one of claims 1 to 11, characterized in that, The target object includes a target vehicle in a vehicle navigation scenario; the inertial sensing information is collected by a vehicle inertial sensor disposed on the target vehicle; The visual sensing information is collected by a vehicle visual sensor disposed on the target vehicle; The target positioning information is the positioning information of the target vehicle after correction and compensation; The method further includes: Rendering and displaying the vehicle position information in the target positioning information on an in-vehicle navigation map.

13. A positioning information processing device, characterized in that, The device includes: An acquisition module, configured to acquire first positioning information to be corrected corresponding to a target object; the first positioning information is obtained by dead reckoning based on the inertial sensing information of the target object; the first positioning information to be corrected is the positioning information respectively reckoned at each positioning moment within a current compensation period; A correction module, configured to perform a preliminary correction in a first direction on the first positioning information according to the visual sensing information of the target object to obtain second positioning information corresponding to the target object; A determination module, configured to respectively determine a distance between the first positioning information and corresponding historical positioning information for the first positioning information reckoned at each positioning moment within the current compensation period, to obtain a distance corresponding to each positioning moment; the historical positioning information is the target positioning information determined in a previous compensation period; The correction module is further configured to perform an advanced correction in a second direction on the second positioning information according to the distance to obtain the target positioning information after correction and compensation.

14. The positioning information processing device according to claim 13, wherein The distance between the first positioning information and the corresponding historical positioning information is a first distance; The correction module is further configured to determine a second distance according to the historical positioning information and the second positioning information; and perform an advanced correction in a second direction on the second positioning information according to a difference between the first distance and the second distance to obtain the target positioning information after correction and compensation.

15. The positioning information processing apparatus according to claim 14, wherein The second positioning information includes second lateral positioning information and second longitudinal positioning information; The correction module is further configured to perform a longitudinal advanced correction on the second longitudinal positioning information according to a difference between the first distance and the second distance to obtain longitudinally corrected positioning information; Determine the target positioning information after correction and compensation according to the second lateral positioning information and the longitudinally corrected positioning information.

16. The positioning information processing apparatus according to claim 13, wherein The correction module is further configured to, for each positioning moment within the current compensation period, determine and store a sub-compensation error corresponding to the positioning moment according to the distance corresponding to the positioning moment; perform a smoothing process on the sub-compensation errors respectively corresponding to the positioning moments within the current compensation period to obtain a target compensation error corresponding to the current compensation period; and perform an advanced correction in a second direction on the second positioning information corresponding to a target positioning moment according to the target compensation error to obtain the target positioning information corresponding to the current compensation period; The target positioning moment is one of the positioning moments within the current compensation period.

17. The positioning information processing device according to claim 13, characterized in that The device further includes a judgment module, and the judgment module is configured to judge whether the visual sensing information is available; When the visual sensing information is available, the correction module performs the steps of preliminarily correcting the first positioning information in a first direction according to the visual sensing information of the target object to obtain the second positioning information corresponding to the target object and subsequent steps; When the visual sensing information is unavailable, the determination module is further configured to use the first positioning information as the target positioning information of the target object.

18. The positioning information processing apparatus according to claim 13, wherein The correction module is further configured to determine the visual position information corresponding to the target object according to the lane line intercept information in the visual sensing information of the target object; Determine a compensation error according to the visual position information and the first positioning information; perform a preliminary correction of the first positioning information in a first direction according to the compensation error to obtain the second positioning information corresponding to the target object.

19. The positioning information processing device according to claim 18, characterized in that, The first positioning information includes first position information and first state information; the second positioning information includes second position information and second state information; the compensation error includes a position error and a state error; The correction module is further configured to perform a preliminary position correction of the first position information in a first direction according to the position error to obtain the second position information corresponding to the target object; Perform a preliminary state correction of the first state information according to the state error to obtain the second state information corresponding to the target object.

20. The positioning information processing device according to claim 19, wherein The correction module is further configured to determine a position error according to the position difference between the visual position information and the first position information; perform error solving on a pre-constructed positioning error equation according to the position error to obtain a state error.

21. The positioning information processing device according to claim 19, characterized in that The state error includes at least one of a platform misalignment angle error, a speed error, a dead reckoning error, a gyro zero bias, an accelerometer zero bias, an installation error angle residual, a wheel speedometer scale factor error, or a time delay of the wheel speedometer transmitted to the inertial sensor.

22. The positioning information processing device according to claim 19, wherein The first position information includes first lateral position information and first longitudinal position information; The correction module is further configured to perform a preliminary position correction of the first lateral position information according to the position error to obtain laterally corrected position information; Determine the second position information corresponding to the target object according to the laterally corrected position information and the first longitudinal position information.

23. The positioning information processing apparatus according to claim 13, wherein When receiving the satellite positioning information of the target object, the correction module performs a preliminary correction of the first positioning information in a first direction according to the visual sensing information of the target object to obtain preliminarily corrected positioning information; perform a correction of the preliminarily corrected positioning information in a second direction according to the longitudinal position information in the satellite positioning information to obtain the second positioning information corresponding to the target object.

24. The positioning information processing device according to any one of claims 13 to 23, characterized in that, The target object includes a target vehicle in a vehicle navigation scenario; the inertial sensing information is collected by a vehicle inertial sensor disposed on the target vehicle; The visual sensing information is collected by a vehicle visual sensor disposed on the target vehicle; The target positioning information is the corrected and compensated positioning information of the target vehicle; The device further includes: A rendering module, configured to render and display the vehicle position information in the target positioning information on an in-vehicle navigation map.

25. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 12.

26. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

27. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

Images