Camera online calibration control method, device and vehicle

Abstract

The present application provides a camera online calibration control method, device and vehicle, and relates to the field of camera calibration technology. After determining the target driving route of the vehicle where the target camera is located, the method predicts the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver, so as to determine whether to enter the online calibration process of the target camera based on the calibration achievement rate. The calibration achievement rate represents the probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route. Therefore, according to the prediction result of the calibration achievement rate corresponding to the target driving route, it can be effectively determined whether to enter the online calibration process of the target camera. Therefore, after entering the online calibration process of the target camera, the probability of successful calibration of the target camera can be greatly improved, and the frequent abnormal exit of the target camera during the online calibration process can be avoided, which causes a great increase in the computing power of the online calibration.

Description

Technical Field

[0001] The present application relates to the field of camera calibration technology, and in particular to a camera online calibration control method, device and vehicle. Background Art

[0002] Online camera calibration is an important process in machine vision products such as intelligent driving vehicles and mobile robots. By calibrating the camera online, the camera parameters can be dynamically adjusted and optimized to ensure that the camera can maintain high-precision performance in different environments and conditions.

[0003] At present, in the process of online calibration of the camera, the online calibration process is usually abnormally exited before the camera online calibration is completed due to factors such as the road environment, making it difficult to achieve successful camera calibration and causing a significant increase in the computing power of the camera online calibration. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, the present application provides a camera online calibration control method, device and vehicle to solve the problems in the prior art that the success rate of camera online calibration is low and the computing power requirement is large.

[0005] To achieve the above technical objectives, the present application provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present specification provides a camera online calibration control method, including:

[0007] After determining a target driving route of the vehicle where the target camera is located, predicting a calibration achievement rate corresponding to the target driving route based on road feature data of the target driving route and / or historical driving habit data of the driver; the calibration achievement rate corresponding to the target driving route represents a probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route;

[0008] Based on the calibration achievement rate, it is determined whether to switch to an online calibration process of the target camera.

[0009] In one embodiment, the predicting the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver includes:

[0010] Determining whether the target driving route meets the online calibration requirements based on the road feature data;

[0011] When the target driving route meets the online calibration requirement, determining a calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data;

[0012] When the target driving route does not meet the online calibration requirement, the calibration achievement rate corresponding to the target driving route is determined to be 0.

[0013] In one implementation, determining the calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data includes:

[0014] Determining the length of a target road section in the target driving route and parameter values ​​of predetermined parameters in the target driving route based on the road feature data; the target road section includes a road section that meets the online calibration conditions of the target camera; the predetermined parameters include parameters that affect driving stability;

[0015] Determining a first probability based on the length of the target road section, and determining a second probability based on the parameter value of the predetermined parameter and the historical driving habit data; the first probability represents the calibration success probability corresponding to the road factor, and the second probability represents the calibration success probability corresponding to the driving factor;

[0016] The first probability and the second probability are weightedly summed based on a predetermined weight coefficient to obtain a calibration achievement rate corresponding to the target driving route.

[0017] In one implementation, determining the first probability based on the length of the target road segment includes:

[0018] The first probability is determined based on a ratio of the length of the target road section to the required road section length calibrated online by the target camera.

[0019] In one embodiment, the determining the second probability based on the parameter value of the predetermined parameter and the historical driving habit data comprises:

[0020] Determining statistical data of target driving actions based on the historical driving habit data; the target driving actions include driving actions that affect the driving stability;

[0021] The second probability is determined based on the statistical data of the target driving action and the parameter value of the predetermined parameter.

[0022] In one embodiment, it further includes:

[0023] When the target driving route meets the online calibration requirement, a historical calibration state corresponding to the target driving route is obtained; the historical calibration state represents a calibration state of online calibration of the target camera on the target driving route at a historical moment;

[0024] If there is at least one of the historical calibration states indicating a successful calibration, the calibration achievement rate corresponding to the target driving route is determined to be 1.

[0025] In one embodiment, after entering the online calibration process of the target camera, the method further includes:

[0026] When the driving route of the vehicle changes, obtaining the current calibration progress of the target camera;

[0027] Based on the current calibration progress of the target camera, it is determined whether to cut out the online calibration process of the target camera.

[0028] In one embodiment, after switching into the online calibration process of the target camera, the method further includes: when a condition for switching out of the online calibration process is met, saving the calibration state of the target camera in the current online calibration;

[0029] and / or,

[0030] After determining the target driving route of the vehicle where the target camera is located, it also includes: while the vehicle is driving along the target driving route, obtaining driving parameter data of the vehicle, the driving parameter data is used to determine driving habit data corresponding to the target driving route.

[0031] In a second aspect, an embodiment of the present specification provides a camera online calibration control device, including:

[0032] A first processing module is used to predict a calibration achievement rate corresponding to the target driving route based on road feature data of the target driving route and / or historical driving habit data of the driver after determining a target driving route of the vehicle where the target camera is located; the calibration achievement rate corresponding to the target driving route represents a probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route;

[0033] The second processing module is used to determine whether to switch to the online calibration process of the target camera based on the calibration achievement rate.

[0034] In a third aspect, an embodiment of the present specification provides a vehicle, including a camera and a camera online calibration control device as described above.

[0035] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the camera online calibration control method as described in any one of the above items is implemented.

[0036] In a fifth aspect, an embodiment of the present specification provides a computer program product or a computer program, wherein the computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and when the processor executes the computer program, it implements the camera online calibration control method as described in any one of the above items.

[0037] It can be seen from the above technical scheme that the embodiments of the present application provide a camera online calibration control method, device and vehicle. After determining the target driving route of the vehicle where the target camera is located, the method predicts the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver, so as to determine whether to enter the online calibration process of the target camera based on the calibration achievement rate, wherein the calibration achievement rate corresponding to the target driving route represents the probability of successful online calibration of the target camera when the target camera is online calibrated on the target driving route, so that according to the prediction result of the calibration achievement rate corresponding to the target driving route, it can be effectively determined whether to enter the online calibration process of the target camera, thereby, after entering the online calibration process of the target camera, the probability of successful calibration of the target camera can be greatly improved, and the frequent abnormal exit of the target camera during the online calibration process can be avoided, which causes a great increase in the computing power of the online calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0039] Figure 1 A flowchart of a camera online calibration control method provided for an implementation of this specification.

[0040] Figure 2 A flowchart of another camera online calibration control method provided for an implementation of this specification.

[0041] Figure 3 A schematic structural diagram of a camera online calibration control device provided in an implementation manner of this specification. DETAILED DESCRIPTION

[0042] Unless otherwise defined, the technical terms or scientific terms used in the embodiments of this specification shall have the common meanings understood by persons with ordinary skills in the field to which this specification belongs. The words "first", "second" and similar words used in the embodiments of this specification do not indicate any order, quantity or importance, but are only used to avoid confusion of constituent elements.

[0043] Unless the context requires otherwise, throughout the specification, "plurality" means "at least two", and "including" is interpreted as an open, inclusive meaning, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" are intended to indicate that a particular feature, structure, material or characteristic associated with the embodiment or example is included in at least one embodiment or example of the specification. The schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0044] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0045] Overview

[0046] As described in the background technology, online camera calibration is an important process in machine vision products such as intelligent driving vehicles and mobile robots. By calibrating the camera online, the camera parameters can be dynamically adjusted and optimized to ensure that the camera can maintain high-precision performance in different environments and conditions.

[0047] At present, in the process of online calibration of the camera, the online calibration process is usually abnormally exited before the camera online calibration is completed due to factors such as the road environment, making it difficult to achieve successful camera calibration and causing a significant increase in the computing power of the camera online calibration.

[0048] In order to solve the problem that traditional methods cannot effectively improve the low success rate of camera online calibration and the large computing power requirement, in the technical solution of the present application, the camera online calibration control method, after determining the target driving route of the vehicle where the target camera is located, predicts the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver, so as to determine whether to enter the online calibration process of the target camera based on the calibration achievement rate, wherein the calibration achievement rate corresponding to the target driving route represents the probability of successful online calibration of the target camera when the target camera is online calibrated on the target driving route, so that according to the prediction result of the calibration achievement rate corresponding to the target driving route, it can be effectively determined whether to enter the online calibration process of the target camera, thereby, after entering the online calibration process of the target camera, the probability of successful calibration of the target camera can be greatly improved, and the frequent abnormal exit of the target camera during the online calibration process can be avoided, which causes a great increase in the computing power of the online calibration.

[0049] Based on the above-mentioned inventive concept, the camera online calibration control method provided in the embodiment of this specification is exemplarily described below.

[0050] Exemplary Methods

[0051] The embodiments of this specification provide a camera online calibration control method, such as Figure 1 As shown, including:

[0052] S101. After determining a target driving route of a vehicle where a target camera is located, predicting a calibration achievement rate corresponding to the target driving route based on road feature data of the target driving route and / or historical driving habit data of the driver; the calibration achievement rate corresponding to the target driving route represents a probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route.

[0053] Specifically, the target camera may be a camera to be calibrated online. The target driving route of the vehicle where the target camera is located may be a driving route planned according to the departure and destination of the vehicle where the target camera is located. For example, the navigation map or high-precision map in the vehicle can automatically generate a map-planned route from the departure point to the destination according to the destination input by the user in the human driving mode. When there is only one map-planned route, the map-planned route can be used as the target driving route. When there are multiple map-planned routes, the target driving route can be determined in response to the user's selection operation of the map-planned route.

[0054] The road feature data of the target driving route may include the road geometry feature data and road environment feature data of the target driving route. The road geometry feature data may include the length of the road, the curvature of the road, the number of lane lines, etc. The road environment feature data may include the road illumination intensity (e.g., daytime, dusk, night, etc.), weather conditions (e.g., clear, cloudy, rain, snow, fog, haze, dust, etc.), road scene information (e.g., urban area, suburbs, villages, fields, mountains, deserts, snow, etc.), road types (e.g., bridges, tunnels, etc.), the number of traffic lights on the road, abnormal conditions of the road (e.g., maintenance, congestion, accidents, etc.), road speed limit information, etc. In implementation, the road feature data may be obtained by subscription.

[0055] The driver's historical driving habit data may include the driving habit data of the driver of the vehicle at a historical moment, for example, the driving habit data may include driving speed, steering wheel turning data, lane change data, overtaking data, rapid acceleration and deceleration data, etc. In implementation, during the driving process of the vehicle, the vehicle's driving parameter data and the driving route information and driver information corresponding to the driving parameter data may be recorded to determine the driver's driving habit data on the driving route according to the driving parameter data. Thus, during the online calibration of the target camera, it may be determined whether there is the historical driving habit data of the current driver on the target driving route, and the current driver is the driver of the vehicle at the current moment; if there is, the calibration achievement rate corresponding to the target driving route is predicted based on the historical driving habit data of the current driver on the target driving route; if not, the calibration achievement rate corresponding to the target driving route may be predicted based on the historical driving habit data of the current driver on other driving routes with similar road conditions.

[0056] During implementation, after determining the target driving route of the vehicle where the target camera is located, it can be determined whether the target camera has an online calibration requirement. For example, during the current life cycle of the intelligent driving controller from startup to shutdown, if the number of successful online calibrations of the target camera is less than or equal to a preset number (e.g., once), it can be determined that the target camera has an online calibration requirement; it can also be determined that the target camera has an online calibration requirement when the current moment is within the effective duration of the last online calibration of the target camera (e.g., 24 hours); it can also be determined that the target camera has an online calibration requirement when the software and / or hardware of the target camera is updated.

[0057] When the target camera has an online calibration requirement, the calibration achievement rate corresponding to the target driving route can be predicted based on the road feature data of the target driving route and / or the driver's historical driving habit data. The calibration achievement rate corresponding to the target driving route can be used to characterize the probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route, that is, when the target camera is calibrated online while the vehicle is traveling along the target driving route. For example, the calibration achievement rate corresponding to the target driving route can be determined based on a predetermined correspondence between the road feature data of the target driving route and / or the driver's historical driving habit data and the calibration achievement rate. A first probability can also be determined based on the road feature data of the target driving route, and a second probability can be determined based on the driver's historical driving habit data. The calibration achievement rate corresponding to the target driving route can be determined based on the first probability and the second probability, wherein the first probability can characterize the calibration success probability corresponding to the road factor, and the second probability can characterize the calibration success probability corresponding to the driving factor.

[0058] Therefore, based on the road characteristic data of the target driving route and / or the driver's historical driving habit data, the calibration achievement rate corresponding to the target driving route can be predicted quickly and accurately.

[0059] S102: Determine whether to start an online calibration process of the target camera based on the calibration achievement rate.

[0060] Specifically, whether to enter the online calibration process of the target camera can be determined based on the calibration achievement rate corresponding to the target driving route. In implementation, whether to enter the online calibration process of the target camera can be determined based on the relationship between the calibration achievement rate corresponding to the target driving route and the predetermined achievement rate threshold. The predetermined achievement rate threshold can be set according to actual needs. For example, the value range of the predetermined achievement rate threshold can be 70%~100% (including 70% and 100%). The stricter the requirements of the online calibration strategy on road conditions and driving conditions, the higher the predetermined achievement rate threshold. For example, the predetermined achievement rate threshold can be set to 90%.

[0061] During implementation, when the calibration achievement rate is greater than or equal to a predetermined achievement rate threshold, the online calibration process of the target camera can be switched to, so that the target camera can be calibrated online through the online calibration process while the vehicle is traveling on the target driving route, thereby effectively reducing the probability of abnormal exit of the online calibration process when the online calibration of the target camera is not completed, and increasing the probability of successful online calibration of the target camera; in addition, when the calibration achievement rate is less than the predetermined achievement rate threshold, the online calibration process of the target camera is not switched to, thereby effectively avoiding the computing power consumption caused by the failure of the online calibration of the target camera while the vehicle is traveling on the target driving route.

[0062] In a feasible implementation manner, the predicting of the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver includes:

[0063] Determining whether the target driving route meets the online calibration requirements based on the road feature data;

[0064] When the target driving route meets the online calibration requirement, determining a calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data;

[0065] When the target driving route does not meet the online calibration requirement, the calibration achievement rate corresponding to the target driving route is determined to be 0.

[0066] Specifically, in the process of predicting the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver, first, whether the target driving route meets the online calibration requirements can be determined based on the road feature data. The online calibration requirements can be set according to actual requirements. For example, the online calibration requirements can include that the length of the road in the target driving route that meets the online calibration conditions is greater than or equal to the predetermined road length, and meeting the online calibration conditions can include that the length of the target driving route is greater than or equal to the predetermined route length, and can also include that the target road length in the target driving route is greater than or equal to the first predetermined length, and can also include that the target lane line length in the target driving route is greater than or equal to the second predetermined length, wherein the target road can include a straight road, such as a curved road, an uphill and downhill road, a road outside a bridge and a tunnel in the target driving route, and the target lane line can include two or more lane lines, such as the target lane line can not include a curb and a lane line with an obstruction (such as a green belt, a fence, etc.) between the two-way lanes.

[0067] The online calibration requirement may also include that the light intensity in the driving time interval corresponding to the target driving route is greater than or equal to a predetermined light intensity. For example, when the driving time interval is at night or at dusk, it may be determined that the online calibration requirement is not met.

[0068] The online calibration requirements may also include whether the weather conditions corresponding to the target driving route meet the predetermined weather conditions, wherein the predetermined weather conditions may be weather conditions where visibility is greater than or equal to a predetermined visibility, such as moderate or above levels of rain, snow, fog, haze, dust and other weather conditions, which may be determined to not meet the online calibration requirements.

[0069] The online calibration requirements may also include that the effective length of the target lane line is greater than or equal to the predetermined lane line length, and the effective length of the target lane line may include the length of the section other than the abnormal section in the section where the target lane line is located in the target driving route, and the abnormal section may include the maintenance section, the congested section, the accident section, the section with a speed limit less than the preset speed (e.g., 30Km / h), the bumpy section, etc. Among them, the bumpy section can be determined based on the fluctuation frequency of the RTK (Real Time Kinematic) data, the combined inertial navigation data, etc. in the historical driving parameter data corresponding to the target driving route. The greater the fluctuation frequency of the data, the bumpier the target driving route.

[0070] The online calibration requirement may also include that the number of environmental features on both sides of the road (eg, static features such as trees and buildings) is greater than or equal to a predetermined number of features. For example, in road environments such as deserts and snowy areas, it is determined that the online calibration requirement is not met.

[0071] When the target driving route does not meet the online calibration requirements, the calibration achievement rate corresponding to the target driving route can be directly determined to be 0, that is, the online calibration process of the target camera is not started. At this time, the online calibration control process of the target camera can be terminated.

[0072] When the target driving route meets the online calibration requirements, the calibration achievement rate corresponding to the target driving route can be further determined based on the road feature data of the target driving route and the driver's historical driving habit data.

[0073] As an optional implementation, it is possible to first determine whether the target driving route meets the online calibration conditions based on the road feature data of the target driving route to make a preliminary decision, and when the preliminary decision result is that the online calibration conditions are met, it is further determined whether the target driving route meets other online calibration requirements, and when the preliminary decision result is that the online calibration conditions are not met, the online calibration control process of the target camera is terminated. For example, the preliminary decision process may include:

[0074] Determine whether the length of the target driving route is greater than or equal to the length of the predetermined route. If not, determine that the calibration achievement rate corresponding to the target driving route is 0, and end the online calibration control process of the target camera. If yes, continue to perform subsequent judgments; wherein the predetermined route length can be 3 km~10 km;

[0075] Determine whether the target road length in the target driving route is greater than or equal to the first predetermined length. If not, determine that the calibration achievement rate corresponding to the target driving route is 0, and end the online calibration control process of the target camera. If yes, continue to perform subsequent judgments;

[0076] Determine whether the length of the target lane line in the target driving route is greater than or equal to the second predetermined length. If not, determine that the calibration achievement rate corresponding to the target driving route is 0, and end the online calibration control process of the target camera. If so, the preliminary decision result is that the online calibration conditions are met, and further determine whether the target driving route meets other online calibration requirements.

[0077] In a feasible implementation manner, determining the calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data includes:

[0078] Determining the length of a target road section in the target driving route and parameter values ​​of predetermined parameters in the target driving route based on the road feature data; the target road section includes a road section that meets the online calibration conditions of the target camera; the predetermined parameters include parameters that affect driving stability;

[0079] Determining a first probability based on the length of the target road section, and determining a second probability based on the parameter value of the predetermined parameter and the historical driving habit data; the first probability represents the calibration success probability corresponding to the road factor, and the second probability represents the calibration success probability corresponding to the driving factor;

[0080] The first probability and the second probability are weightedly summed based on a predetermined weight coefficient to obtain a calibration achievement rate corresponding to the target driving route.

[0081] Specifically, the target road section in the target driving route may include a road section that meets the online calibration conditions, for example, may include a road section other than an abnormal road section in the road section where the target lane line is located in the road section that meets the online calibration conditions.

[0082] The predetermined parameters may include parameters that affect driving stability, for example, the maximum number of traffic lights within a unit distance (e.g., 1 km) in the target driving route. It is understood that when there are multiple traffic lights at the same intersection, each traffic light is calculated only once, and traffic lights that do not affect the lane in the same direction are not included in the calculation.

[0083] During implementation, the first probability can be determined based on the length of the target section. The first probability can characterize the calibration success probability corresponding to the road factor. For example, the size of the first probability can be determined based on the length of the target section and the predetermined corresponding relationship between the length of the target section and the first probability.

[0084] At the same time, a second probability can be determined based on the parameter value of the predetermined parameter and the historical driving habit data. The second probability can characterize the calibration success probability corresponding to the driving factor. For example, the size of the second probability can be determined based on the parameter value of the predetermined parameter and the historical driving habit data, as well as the predetermined correspondence between the predetermined driving parameters and driving habit data and the second probability.

[0085] The first probability and the second probability may be weighted and summed based on a predetermined weight coefficient to obtain a calibration success probability corresponding to the target driving route. For example, the calibration success probability P corresponding to the target driving route may be as shown in formula (1):

[0086] P=w*P1+(1-w)*P2 (1)

[0087] Wherein, P1 is the first probability, P2 is the second probability, w is the predetermined weight coefficient, 0<w<1, for example, w can be set to 0.8; the value ranges of P, P1 and P2 are all 0~1 (including 0 and 1).

[0088] Therefore, by comprehensively considering the impact of road factors and driving factors on the probability of successful calibration, the accuracy of the calibration achievement rate corresponding to the target driving route can be effectively guaranteed. In the process of determining whether to start the online calibration process of the target camera according to the calibration achievement rate corresponding to the target driving route, the probability of successful calibration of the target camera can be effectively improved, thereby reducing the computing power consumption of the online calibration of the target camera.

[0089] In a feasible implementation manner, determining the first probability based on the length of the target road segment includes:

[0090] The first probability is determined based on a ratio of the length of the target road section to the required road section length calibrated online by the target camera.

[0091] Specifically, the required road section length for the online calibration of the target camera may include a minimum length of the target road section required during the online calibration of the target camera.

[0092] During implementation, the first probability can be determined based on the ratio of the length of the target section in the target driving route to the length of the required section. For example, the first probability can be positively correlated with the ratio. The larger the ratio is, the more the length of the target road can meet the required section length for online calibration of the target camera, and the higher the probability of successful calibration corresponding to the road factor, thereby enabling the size of the first probability to be determined quickly and accurately.

[0093] As an optional implementation, the first probability P1 may be expressed as formula (2):

[0094] P1=len 有效 / (s*Len需求 ) (2)

[0095] In the formula, len 有效 is the length of the target section, Len 需求 is the required road section length for online calibration of the target camera, s is the correction coefficient, the larger s is, the higher the probability of successful calibration is, the smaller s is, the lower the probability of successful calibration is, the value range of s can be 1.0~2.0, preferably, s can be set to 1.2.

[0096] Among them, in len 有效 / (s*Len 需求 )≥1, P1=1.

[0097] In a feasible implementation manner, the determining the second probability based on the parameter value of the predetermined parameter and the historical driving habit data includes:

[0098] Determining statistical data of target driving actions based on the historical driving habit data; the target driving actions include driving actions that affect the driving stability;

[0099] The second probability is determined based on the statistical data of the target driving action and the parameter value of the predetermined parameter.

[0100] Specifically, the target driving action may include driving actions that affect driving stability, for example, rapid acceleration and deceleration actions, steering actions greater than a predetermined amplitude, etc. The statistical data of the target driving action may be determined based on the driver's historical driving habit data, and the statistical data of the target driving action may include the number of occurrences of the target driving action within a unit distance (e.g., 1 km).

[0101] In implementation, the second probability may be determined based on the statistical data of the target driving action and the parameter value of the predetermined parameter. For example, the second probability may be determined based on the statistical data of the target driving action, the parameter value of the predetermined parameter, and the target correspondence relationship. The target correspondence relationship may characterize the correspondence between the second probability and the statistical data of the target driving action and the parameter value of the predetermined parameter. The second probability may be negatively correlated with the statistical data of the target driving action and the parameter value of the predetermined parameter, that is, the larger the statistical data of the target driving action or the parameter value of the predetermined parameter, the smaller the second probability, and the smaller the probability of successful calibration corresponding to the driving factor, so that the size of the second probability can be determined quickly and accurately.

[0102] As an optional implementation, the target correspondence relationship can be shown as formula (3):

[0103] P2=F max / (f s +f TL ) (3)

[0104] In the formula, f s is the number of target driving actions within a unit distance; f TL is the maximum number of traffic lights per unit distance in the target driving route; F max It is the upper limit of the sum of the number of target driving actions within a unit distance and the number of traffic lights, for example, it can be set to 10.

[0105] Among them, in F max / (f s +f TL )≥1, P2=1.

[0106] In a feasible implementation, it also includes:

[0107] When the target driving route meets the online calibration requirement, a historical calibration state corresponding to the target driving route is obtained; the historical calibration state represents a calibration state of online calibration of the target camera on the target driving route at a historical moment;

[0108] If there is at least one of the historical calibration states indicating a successful calibration, the calibration achievement rate corresponding to the target driving route is determined to be 1.

[0109] Specifically, the historical calibration status corresponding to the target driving route can be used to characterize the online calibration status of the target camera during the online calibration of the target camera on the target driving route at a historical moment, and the online calibration status can include calibration success and calibration failure.

[0110] In implementation, when the target driving route meets the online calibration requirements, before determining the calibration achievement rate corresponding to the target driving route based on the road feature data and the driver's historical driving habit data, the historical calibration status corresponding to the target driving route can also be obtained. It is understandable that during the online calibration of the target camera on the target driving route, if the driving route is switched or switched to the intelligent driving mode before the calibration is completed, the calibration status of this time will not be used for the subsequent judgment of the entry timing.

[0111] If there is at least one historical calibration state corresponding to the target driving route that indicates that the online calibration of the target camera is successful, the calibration achievement rate corresponding to the target driving route can be directly determined as 1, that is, there is no need to determine the calibration achievement rate corresponding to the target driving route based on the road feature data and the driver's historical driving habit data; if there is no historical calibration state corresponding to the target driving route, or all historical calibration states corresponding to the target driving route indicate that the online calibration of the target camera has failed, the calibration achievement rate corresponding to the target driving route can be further determined based on the road feature data and the driver's historical driving habit data, so that the calibration achievement rate corresponding to the target driving route can be determined quickly and effectively.

[0112] In a feasible implementation manner, after entering the online calibration process of the target camera, the method further includes:

[0113] When the driving route of the vehicle changes, obtaining the current calibration progress of the target camera;

[0114] Based on the current calibration progress of the target camera, it is determined whether to cut out the online calibration process of the target camera.

[0115] Specifically, during the online calibration of the target camera on the target driving route, if the driving route of the vehicle changes, the current calibration progress of the target camera can be obtained, and based on the current calibration progress of the target camera, it is determined whether to cut out the online calibration process of the target camera. The current calibration progress of the target camera can be the calibration progress of the target camera at the moment when the driving route of the vehicle changes.

[0116] In implementation, the current calibration progress of the target camera can be compared with a predetermined calibration progress threshold, and based on the magnitude relationship between the current calibration progress and the predetermined calibration progress threshold, it is determined whether to cut out the online calibration process of the target camera. For example, if the current calibration progress is greater than or equal to the predetermined calibration progress threshold, the online calibration process of the target camera is not cut out, that is, the online calibration of the target camera is continued until the online calibration is completed; if the current calibration progress is less than the predetermined calibration progress threshold, the online calibration process of the target camera is cut out, and when the conditions for cutting into the online calibration process of the target camera are met later, the target camera is re-calibrated online.

[0117] The predetermined calibration progress threshold may be determined according to the calibration strategy of the target camera. For example, the corresponding relationship between the calibration strategy and the calibration progress threshold may be preconfigured, and the predetermined calibration progress threshold may be determined according to the calibration strategy adopted in the online calibration process of the target camera. For example, for any calibration strategy, the calibration progress threshold corresponding to the calibration strategy may be determined based on the degree of dependence of each calibration stage in the calibration strategy on road conditions and driving conditions. For example, if only voting operations are performed within the last 10% of the online calibration progress and no longer rely on road conditions and driving conditions, the calibration progress threshold corresponding to the calibration strategy may be set to 90%.

[0118] Therefore, when the vehicle's driving route changes, determining whether to cut out the online calibration process of the target camera based on the current calibration progress of the target camera can further improve the probability of successful calibration of the target camera, thereby reducing the computing power consumption of the online calibration of the target camera.

[0119] In a feasible implementation manner, after switching into the online calibration process of the target camera, the method further includes: when a switching-out condition of the online calibration process is met, saving the calibration state of the target camera in the current online calibration;

[0120] and / or,

[0121] After determining the target driving route of the vehicle where the target camera is located, driving parameter data of the vehicle is obtained while the vehicle is driving along the target driving route, and the driving parameter data is used to determine driving habit data corresponding to the target driving route.

[0122] Specifically, after entering the online calibration process of the target camera, it can be determined in real time whether the target camera meets the conditions for exiting the online calibration process. The conditions for exiting the online calibration process may include the completion of the online calibration of the target camera, the change of the vehicle's driving route and the current calibration progress being less than a predetermined calibration progress threshold, and the vehicle's driving mode being switched to the intelligent driving mode.

[0123] During implementation, when the target camera meets the conditions for cutting out of the online calibration process, the calibration status of the target camera in the current online calibration can be saved, so that in the subsequent online calibration of the target camera on the target driving route, it can be determined whether to cut into the online calibration process of the target camera based on the historical calibration status corresponding to the target driving route.

[0124] Among them, when the calibration status of the current online calibration indicates that the calibration is successful, the calibration file or calibration parameters of the target camera can be updated according to the current online calibration result, and the time when the calibration is completed can also be recorded. When the calibration status of the current online calibration indicates that the calibration fails, the calibration process information (such as calibration log, etc.) of the current online calibration can be saved, and the time and error code of the calibration exit can be recorded.

[0125] In addition, after determining the target driving route of the vehicle where the target camera is located, when the vehicle is traveling along the target driving route, the driving parameter data of the vehicle can also be obtained in real time, so as to determine the driving habit data corresponding to the target driving route through the driving parameter data. The driving parameter data may include vehicle speed, wheel speed, steering wheel angle, lane change steering, RTK data, combined inertial navigation data, etc. At the same time, the driver's information can also be recorded, so that in the subsequent online calibration of the target camera on the target driving route, it can be determined whether to cut into the online calibration process of the target camera based on the driver's historical driving habit data on the target driving route, so as to form an effective closed loop of the online calibration control of the target camera, and provide data support for improving the success rate of the online calibration of the target camera.

[0126] The following is an example of an implementation process of the camera online calibration control method of the present invention. Figure 2 , the camera online calibration control method may include:

[0127] S201, when the vehicle is in a human driving mode, obtaining a target driving route of the vehicle;

[0128] S202, subscribing to road feature data on the target driving route;

[0129] S203, determining whether the online calibration requirements of the target camera are met based on the road feature data of the target driving route; if not, executing step S209; if so, executing step S204;

[0130] S204, determining a calibration achievement rate corresponding to the target driving route based on the road feature data and the driver's historical driving habit data;

[0131] S205, determining whether the conditions for entering the online calibration process of the target camera are met based on the calibration achievement rate corresponding to the target driving route; if so, executing step S206; if not, executing step S209;

[0132] S206, entering the online calibration process of the target camera;

[0133] S207, determining whether the cut-out condition of the online calibration process is met, if so, executing step S208, if not, executing step S207; wherein the cut-out condition of the online calibration process is met includes: the vehicle's driving route changes and the current calibration progress of the target camera is less than a predetermined calibration progress threshold, the target camera calibration is completed, and the vehicle's driving mode is switched to the intelligent driving mode;

[0134] S208, saving the calibration status of the target camera in the current online calibration and exiting the online calibration process; if the calibration status indicates that the calibration is successful, then updating the calibration file or calibration parameters of the target camera and recording the time when the calibration is completed; if the calibration status indicates that the calibration fails, then saving the calibration process information of the current online calibration and recording the time and error code when the calibration is exited, and the process ends;

[0135] S209: Do not start the online calibration process of the target camera during this trip of the vehicle, and the process ends.

[0136] Exemplary Devices

[0137] In an exemplary embodiment of the present specification, a camera online calibration control device is also provided, such as Figure 3 As shown, including:

[0138] The first processing module 301 is used to predict the calibration achievement rate corresponding to the target driving route based on the road feature data of the target driving route and / or the historical driving habit data of the driver after determining the target driving route of the vehicle where the target camera is located; the calibration achievement rate corresponding to the target driving route represents the probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route;

[0139] The second processing module 302 is used to determine whether to switch to the online calibration process of the target camera based on the calibration achievement rate.

[0140] In a feasible implementation manner, the first processing module 301 is specifically configured to:

[0141] Determining whether the target driving route meets the online calibration requirements based on the road feature data;

[0142] When the target driving route meets the online calibration requirement, determining a calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data;

[0143] When the target driving route does not meet the online calibration requirement, the calibration achievement rate corresponding to the target driving route is determined to be 0.

[0144] In a feasible implementation manner, the first processing module 301 is specifically configured to:

[0145] Determining the length of a target road section in the target driving route and parameter values ​​of predetermined parameters in the target driving route based on the road feature data; the target road section includes a road section that meets the online calibration conditions of the target camera; the predetermined parameters include parameters that affect driving stability;

[0146] Determining a first probability based on the length of the target road section, and determining a second probability based on the parameter value of the predetermined parameter and the historical driving habit data; the first probability represents the calibration success probability corresponding to the road factor, and the second probability represents the calibration success probability corresponding to the driving factor;

[0147] The first probability and the second probability are weightedly summed based on a predetermined weight coefficient to obtain a calibration achievement rate corresponding to the target driving route.

[0148] In a feasible implementation manner, the first processing module 301 is specifically configured to:

[0149] The first probability is determined based on a ratio of the length of the target road section to the required road section length calibrated online by the target camera.

[0150] In a feasible implementation manner, the first processing module 301 is specifically configured to:

[0151] Determining statistical data of target driving actions based on the historical driving habit data; the target driving actions include driving actions that affect the driving stability;

[0152] The second probability is determined based on the statistical data of the target driving action and the parameter value of the predetermined parameter.

[0153] In a feasible implementation manner, the first processing module 301 is further configured to:

[0154] When the target driving route meets the online calibration requirement, a historical calibration state corresponding to the target driving route is obtained; the historical calibration state represents a calibration state of online calibration of the target camera on the target driving route at a historical moment;

[0155] If there is at least one of the historical calibration states indicating a successful calibration, the calibration achievement rate corresponding to the target driving route is determined to be 1.

[0156] In a feasible implementation manner, after entering the online calibration process of the target camera, the second processing module 302 is further configured to:

[0157] When the driving route of the vehicle changes, obtaining the current calibration progress of the target camera;

[0158] Based on the current calibration progress of the target camera, it is determined whether to cut out the online calibration process of the target camera.

[0159] In a feasible implementation manner, after entering the online calibration process of the target camera, the second processing module 302 is further used to: save the calibration state of the target camera in the current online calibration when the exit condition of the online calibration process is met;

[0160] and / or,

[0161] After determining the target driving route of the vehicle where the target camera is located, the first processing module 301 is also used to: obtain driving parameter data of the vehicle while the vehicle is driving along the target driving route, and the driving parameter data is used to determine the driving habit data corresponding to the target driving route.

[0162] The camera online calibration control device provided in this embodiment belongs to the same application concept as the camera online calibration control method provided in the above embodiments of this application, and can execute the camera online calibration control method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the camera online calibration control method. For technical details not fully described in this embodiment, please refer to the specific processing content of the camera online calibration control method provided in the above embodiments of this application, and will not be repeated here.

[0163] Exemplary Devices

[0164] In an exemplary embodiment of the present specification, an electronic device is also provided, comprising at least one processor and at least one memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the camera online calibration control method as described in any one of the above embodiments is implemented.

[0165] Example Vehicles

[0166] In an exemplary embodiment of the present specification, a vehicle is further provided, comprising a camera and a camera online calibration control device as described in any one of the above embodiments.

[0167] Exemplary computer program products and storage media

[0168] In addition to the above-mentioned methods and devices, the camera online calibration control method provided in the embodiments of this specification may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the camera online calibration control method according to various embodiments of this specification described in the above “Exemplary Method” section of this specification.

[0169] The computer program product can be written in any combination of one or more programming languages ​​to write program codes for executing the operations of the embodiments of this specification, and the programming languages ​​include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as "C" language or similar programming languages.

[0170] In addition, an embodiment of the present specification also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the camera online calibration control method according to various embodiments of the present specification described in the above "Exemplary Method" section of the present specification.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this specification may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0172] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0173] The above-mentioned embodiments only express several implementation methods of this specification, and the descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the solutions provided by the embodiments of this specification. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of this specification, which all belong to the protection scope of this specification. Therefore, the protection scope of the patent of this specification shall be based on the attached claims.

Claims

1. A camera online calibration control method, characterized in that: include: After determining a target driving route of the vehicle where the target camera is located, when determining based on road feature data of the target driving route that the target driving route meets the online calibration requirement, determining a calibration achievement rate corresponding to the target driving route based on the road feature data and the historical driving habit data of the driver; The calibration achievement rate corresponding to the target driving route represents the probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route; Whether to start the online calibration process of the target camera is determined based on the calibration achievement rate.

2. The method according to claim 1, characterized in that Also includes: When the target driving route does not meet the online calibration requirement, the calibration achievement rate corresponding to the target driving route is determined to be 0.

3. The method according to claim 1, characterized in that The determining, based on the road feature data and the driver's historical driving habit data, of the calibration achievement rate corresponding to the target driving route includes: Determine the length of a target road section in the target driving route and a parameter value of a predetermined parameter in the target driving route based on the road feature data; the target road section includes a road section that meets the online calibration conditions of the target camera; the predetermined parameter refers to the maximum number of traffic lights within a unit distance in the target driving route; Determining a first probability based on the length of the target road section, and determining a second probability based on the parameter value of the predetermined parameter and the historical driving habit data; the first probability represents the calibration success probability corresponding to the road factor, and the second probability represents the calibration success probability corresponding to the driving factor; The first probability and the second probability are weightedly summed based on a predetermined weight coefficient to obtain a calibration achievement rate corresponding to the target driving route.

4. The method according to claim 3, characterized in that: The determining the first probability based on the length of the target road section includes: The first probability is determined based on a ratio of the length of the target road section to the required road section length calibrated online by the target camera.

5. The method according to claim 3, characterized in that: The determining the second probability based on the parameter value of the predetermined parameter and the historical driving habit data comprises: Determining statistical data of target driving actions based on the historical driving habit data; the target driving actions include driving actions that affect driving stability; The second probability is determined based on the statistical data of the target driving action and the parameter value of the predetermined parameter.

6. The method according to claim 2, characterized in that Also includes: When the target driving route meets the online calibration requirement, obtaining a historical calibration state corresponding to the target driving route; The historical calibration state represents the calibration state of online calibration of the target camera on the target driving route at a historical moment; If there is at least one of the historical calibration states indicating a successful calibration, the calibration achievement rate corresponding to the target driving route is determined to be 1.

7. The method according to any one of claims 1 to 6, characterized in that: After entering the online calibration process of the target camera, the process further includes: When the driving route of the vehicle changes, obtaining the current calibration progress of the target camera; Based on the current calibration progress of the target camera, it is determined whether to cut out the online calibration process of the target camera.

8. The method according to any one of claims 1 to 6, characterized in that: After switching into the online calibration process of the target camera, the method further includes: when a switching-out condition of the online calibration process is met, saving the calibration state of the target camera in the current online calibration; and / or, After determining the target driving route of the vehicle where the target camera is located, it also includes: while the vehicle is driving along the target driving route, obtaining driving parameter data of the vehicle, the driving parameter data is used to determine driving habit data corresponding to the target driving route.

9. A camera online calibration control device, characterized in that: include: A first processing module is used to determine, after determining a target driving route of the vehicle where the target camera is located, determine, based on road feature data of the target driving route, that the target driving route meets the online calibration requirement, and determine, based on the road feature data and historical driving habit data of the driver, a calibration achievement rate corresponding to the target driving route; The calibration achievement rate corresponding to the target driving route represents the probability of successful online calibration of the target camera when the target camera is calibrated online on the target driving route; The second processing module is used to determine whether to switch to the online calibration process of the target camera based on the calibration achievement rate.

10. A vehicle, characterized in that: It comprises a camera and the camera online calibration control device as claimed in claim 9.

Images