Vehicle early warning method and device, vehicle and storage medium
By using Kalman filtering algorithm and weighted average algorithm to process the position measurement value of obstacles in the vehicle early warning system, the position judgment error problem caused by sensor measurement value jitter is solved, and the accuracy of early warning is improved.
Patent Information
- Application Number
- CN202510094568.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-21
- Publication Date
- 2025-04-11
AI Technical Summary
When the existing vehicle early warning system detects motion obstacles, due to the jitter of the sensor measurement value, there is an error in judging the position of the obstacle, which affects the accuracy of the early warning.
A combination of Kalman filtering algorithm and weighted averaging algorithm is used to eliminate noise in the target obstacle position measurement value and obtain a more accurate target position, thereby improving the accuracy of early warning.
By eliminating noise, the accuracy of obstacle position measurement is improved and the accuracy and reliability of the vehicle early warning system is enhanced.
Smart Images
Figure CN119796244A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle early warning method, device, vehicle and storage medium. Background Art
[0002] The safety of the vehicle after the user leaves the vehicle is a problem that has received much attention. For example, when the user leaves the vehicle in an unfamiliar and complex environment, the vehicle may be scratched by other pedestrians or deliberately damaged by people with bad intentions, resulting in a poor user experience. At present, with the development of smart cars, in order to solve the above problems, most vehicles are equipped with a sentinel function. After the user leaves the vehicle, the sentinel function is turned on to warn the vehicle when dangerous obstacles appear around the vehicle. When the vehicle turns on the sentinel function, the position of the obstacles appearing around the vehicle is usually detected by the sensors installed in the vehicle, so as to determine whether the obstacles pose a threat to the vehicle through the acquired position of the obstacles, thereby warning the vehicle. However, since the obstacles are moving, there will be a jitter problem when the position of the obstacles is acquired by the sensor, which will cause errors in the judgment of the threat to the vehicle based on the position of the obstacles, thereby affecting the accuracy of the vehicle warning. Summary of the invention
[0003] One of the purposes of the present application is to provide a vehicle warning method, which eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filtering algorithm and the weighted average algorithm, and obtains a more accurate target position of the target obstacle at the current moment, thereby ensuring the accuracy of warning the vehicle based on obstacles around the vehicle; the second purpose of the present application is to provide a vehicle warning device; the third purpose of the present application is to provide a vehicle; the fourth purpose of the present application is to provide a storage medium.
[0004] In order to achieve the above objectives, in a first aspect, the present application provides a vehicle early warning method, comprising:
[0005] When the vehicle is in a target mode, obtaining a first position measurement value corresponding to a target obstacle detected at a current moment and obtaining a first position estimation value corresponding to the target obstacle detected at a moment before the current moment, wherein the target mode is used to indicate that the vehicle detects surrounding obstacles when it is stopped;
[0006] Processing the first position measurement value and the first position estimate value by using a Kalman filter algorithm to determine a second position estimate value corresponding to the target obstacle at the current moment;
[0007] Performing weighted averaging processing on the first position estimation value and the second position estimation value to obtain a target position corresponding to the target obstacle at the current moment;
[0008] According to the target position, the vehicle is warned.
[0009] Optionally, the obtaining of a first position measurement value corresponding to a target obstacle detected at a current moment and the obtaining of a first position estimation value corresponding to the target obstacle detected at a moment before the current moment include:
[0010] If the target obstacle is detected to exist around the vehicle, a corresponding image frame set around the vehicle is acquired, wherein all image frames in the image frame set are continuous in time and the number of all image frames is a preset number;
[0011] When all the image frames in the image frame set contain the target obstacle, determining a first image frame from the image frame set, the time corresponding to the first image frame being the latest time among the times corresponding to all the image frames in the image frame set;
[0012] Starting from the moment corresponding to the first image frame, a first position measurement value corresponding to the target obstacle detected at the current moment is obtained, and a first position estimation value corresponding to the target obstacle detected at a moment before the current moment is obtained.
[0013] Optionally, when all the image frames in the image frame set contain the target obstacle, determining the first image frame from the image frame set includes:
[0014] When all the image frames in the image frame set contain the target obstacle, determining, for each of the image frames in the image frame set, a first distance between the target obstacle in the image frame and the vehicle to obtain a first distance set;
[0015] When all the first distances in the first distance set gradually decrease in order from small to large in time, a first image frame is determined from the image frame set.
[0016] Optionally, if the target obstacle is detected to exist around the vehicle, obtaining a corresponding image frame set around the vehicle includes:
[0017] If it is detected that the target obstacle exists around the vehicle, determining a second distance between the current target obstacle and the vehicle;
[0018] When the second distance is less than or equal to a first distance threshold, a set of image frames corresponding to the surroundings of the vehicle is acquired, wherein the first distance threshold represents an upper limit value of the second distance corresponding to the obstacle detection around the vehicle.
[0019] Optionally, a plurality of position measuring devices are provided in the vehicle;
[0020] The obtaining of a first position measurement value corresponding to the target obstacle detected at the current moment includes:
[0021] Acquire a plurality of initial position measurement values corresponding to the target obstacle detected at the current moment, the initial position measurement values being acquired by the position measurement device, and the initial position measurement values corresponding to the position measurement device one-to-one;
[0022] For each two position measurement devices in the vehicle, determining a credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices, so as to obtain a credible distance set corresponding to the vehicle;
[0023] Determine at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set, wherein the first position measurement device is a normal position measurement device;
[0024] A first position measurement value corresponding to the target obstacle detected at a current moment is determined according to the initial position measurement value corresponding to at least one of the first position measurement devices.
[0025] Optionally, determining the credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices includes:
[0026] determining an average value between a plurality of said initial position measurements to obtain a position measurement mean;
[0027] Determining a credible distance between the two position measurement devices according to the initial position measurement values and the position measurement mean values corresponding to the two position measurement devices;
[0028] The step of determining at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set comprises:
[0029] Acquire a target membership function, where the target membership function is a function for determining the support between the two position measurement devices based on the credible distance and a credible distance threshold;
[0030] At least one first position measurement device is determined from the plurality of position measurement devices according to the target membership function and the trusted distance set.
[0031] Optionally, after obtaining the credible distance set, the method further includes:
[0032] When a second position measurement device is determined from the plurality of position measurement devices according to the trusted distance set, a target number of times that the second position measurement device continuously becomes abnormal is determined, and the second position measurement device is the abnormal position measurement device;
[0033] When the target number reaches a preset number threshold, generating target prompt information corresponding to the second position measurement device, wherein the preset number threshold represents an upper limit value of the target number corresponding to the failure of the second position measurement device;
[0034] The target prompt information is pushed.
[0035] In order to achieve the above objectives, in a second aspect, the present application provides a vehicle warning device, comprising:
[0036] an acquisition module, used for acquiring a first position measurement value corresponding to a target obstacle detected at a current moment and acquiring a first position estimation value corresponding to the target obstacle detected at a previous moment before the current moment when the vehicle is in a target mode, wherein the target mode is used to indicate that the vehicle detects surrounding obstacles when it is stopped;
[0037] a processing module, configured to process the first position measurement value and the first position estimation value by using a Kalman filter algorithm to determine a second position estimation value corresponding to the target obstacle at the current moment;
[0038] The processing module is further used to perform weighted average processing on the first position estimation value and the second position estimation value to obtain the target position corresponding to the target obstacle at the current moment;
[0039] The early warning module is used to issue an early warning to the vehicle according to the target position.
[0040] To achieve the above objectives, in a third aspect, the present application also provides a vehicle, including: a processor and a memory, the processor being used to execute a vehicle warning program stored in the memory to implement the vehicle warning method as described above.
[0041] To achieve the above objectives, in a fourth aspect, the present application also provides a storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the vehicle warning method as described above.
[0042] Beneficial effects of the present application: The present application provides a vehicle warning method, which, when a vehicle stops and obstacles around the vehicle need to be detected, obtains a first position measurement value corresponding to the target obstacle detected at the current moment and a first position estimate value corresponding to the target obstacle detected at the previous moment before the current moment, so as to use a Kalman filter algorithm to process the first position measurement value and the first position estimate value to obtain a second position estimate value corresponding to the target obstacle at the current moment, and then uses a weighted average algorithm to process the first position estimate value and the second position estimate value to obtain the final target position of the target obstacle at the current moment, and then uses the target position to warn the vehicle. In this way, the present application jointly eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filter algorithm and the weighted average algorithm, obtains a more accurate target position of the target obstacle at the current moment, and improves the accuracy of warning the vehicle according to the obstacles around the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 A schematic diagram showing a process flow of a vehicle early warning method provided by an embodiment of the present application;
[0044] Figure 2 A schematic diagram showing a flow chart of another vehicle warning method provided in an embodiment of the present application;
[0045] Figure 3 A schematic diagram showing a flow chart of another vehicle warning method provided in an embodiment of the present application;
[0046] Figure 4 A schematic diagram showing a process flow of a Kalman filter algorithm provided in an embodiment of the present application;
[0047] Figure 5 A schematic diagram showing the structure of a vehicle warning device provided in an embodiment of the present application is shown;
[0048] Figure 6 A schematic structural diagram of a vehicle provided in an embodiment of the present application is shown.
[0049] in:
[0050] 10. Acquisition module; 20. Processing module; 30. Early warning module;
[0051] 600, vehicle; 601, processor; 602, memory; 6021, operating system; 6022, application; 603, user interface; 604, network interface; 605, bus system. DETAILED DESCRIPTION
[0052] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.
[0053] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.
[0054] To facilitate understanding of the embodiments of the present application, further explanation will be given below with reference to specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present application.
[0055] refer to Figure 1 , Figure 1 The flowchart of a vehicle early warning method provided in an embodiment of the present application is as follows:
[0056] S101: When the vehicle is in a target mode, a first position measurement value corresponding to a target obstacle detected at a current moment is obtained, and a first position estimation value corresponding to a target obstacle detected at a moment before the current moment is obtained.
[0057] In this embodiment, the target mode is used to represent the detection of obstacles around the vehicle when the vehicle is stopped. The target mode is actually a sentinel mode. When the user leaves the vehicle, the target mode of the vehicle can be turned on to put the vehicle in the target mode. When the vehicle is in the target mode, if obstacles are detected around the vehicle, the vehicle will be warned according to the threat level of the obstacles to the vehicle.
[0058] The vehicle is provided with a position measuring device, which may be a laser radar and / or a camera. The position measuring device may be selected according to actual needs, and the specific form of the position measuring device is not limited in this embodiment. It should be noted that the position measuring device is also used to detect whether there are obstacles around the vehicle.
[0059] Specifically, when a position measurement device is provided in the vehicle, if an obstacle is detected around the vehicle, the first position measurement value corresponding to the obstacle detected at the current moment can be obtained through the position measurement device. In order to ensure the accuracy of the obstacle position finally determined at the current moment, the Kalman filter algorithm can be used to determine the position estimation value corresponding to the obstacle detected at the current moment each time an obstacle is detected around the vehicle. It should be noted that if the first position estimation value corresponding to the target obstacle is not obtained by using the Kalman filter algorithm at the previous moment of the current moment, the position measurement value corresponding to the target obstacle at the previous moment of the current moment can be determined as the first position estimation value corresponding to the target obstacle.
[0060] S102: Processing the first position measurement value and the first position estimation value using a Kalman filter algorithm to determine a second position estimation value corresponding to the target obstacle at the current moment.
[0061] In this embodiment, when obtaining the first position measurement value corresponding to the target obstacle at the current moment and the first position estimation value corresponding to the target obstacle at the previous moment of the current moment, the Kalman filtering algorithm can be used to process the first position measurement value and the first position estimation value to obtain the second position estimation value corresponding to the target obstacle at the current moment.
[0062] The first position estimation value may be used to predict the position of the target obstacle at the current moment to obtain the first position prediction value. After obtaining the first position prediction value, the position of the target obstacle at the current moment may be updated according to the first position prediction value and the first position measurement value to obtain a second position estimation value corresponding to the target obstacle at the current moment.
[0063] Specifically, refer to Figure 4 Before executing the Kalman filter algorithm, the state transfer matrix, process noise covariance matrix, measurement matrix and measurement noise covariance matrix need to be initialized. The Kalman filter algorithm consists of two parts, one is the prediction process and the other is the update process. The prediction process includes state prediction and covariance prediction, where the state prediction and covariance prediction include the following formulas:
[0064] State prediction, based on the state at the previous moment, predict the state at the current moment:
[0065] Covariance prediction, based on the system dynamics model and process noise, predicts the covariance matrix of the state estimate: P k|k-1 =AP k-1|k-1 A T +Q.
[0066] In the above formula, represents the position prediction value of the state at time k, represents the estimated value of the state position at time k-1, A represents the state transfer matrix, A T is the transposed matrix of A, P k|k-1 represents the state covariance matrix predicted at time k, P k-1|k-1 represents the covariance matrix updated at time k-1, Q represents the process noise covariance matrix, A and Q can be set according to actual needs, and A and Q are not specifically limited in this embodiment.
[0067] The update process includes Kalman gain calculation, state update and covariance update, wherein Kalman gain calculation, state update and covariance update include the following formulas:
[0068] Kalman gain calculation, using the predicted state covariance matrix and the measurement noise covariance matrix to calculate the Kalman gain: K k =P k|k-1 H T (HP k|k-1 H T +R) -1 .
[0069] State update, update the state estimate based on the actual measurement data:
[0070] Covariance update, updates the covariance matrix of the state estimate to reflect the new uncertainty: P k|k =(IK K H)P k|k-1 .
[0071] In the above formula, K k represents the Kalman gain, H represents the measurement matrix, and H T is the transposed matrix of H, R represents the measurement noise covariance matrix, z k represents the position measurement value at time k, I is the unit matrix, P k|k Represents the covariance matrix after update at time k.
[0072] It should be noted that the covariance matrix represents the uncertainty of the current state, so when initializing the covariance matrix, the variable values in the covariance matrix can be selected as the square value of the position measurement value of the target obstacle when the target obstacle is first detected around the vehicle. When initializing the process noise covariance matrix, the variable values in the process noise covariance matrix can be set to a smaller value, such as 0.01, to represent the uncertainty of the position estimate. When initializing the measurement noise covariance matrix, the variable values in the measurement noise covariance matrix can be set according to the accuracy of the position measurement device. For example, if the standard deviation of each measurement by the position measurement device is 0.5 meters, it can be set to 0.5 2 .
[0073] More specifically, after using the Kalman filter algorithm to process the first position measurement value and the first position estimation value to obtain the second position estimation value corresponding to the target obstacle at the current moment, the position jitter of the measured obstacle caused by the noise of the position measurement device can be eliminated, thereby improving the reliability of the data and ensuring the accuracy of subsequent vehicle warnings based on the position of the obstacle.
[0074] S103: Perform weighted averaging processing on the first position estimation value and the second position estimation value to obtain a target position corresponding to the target obstacle at the current moment.
[0075] In this embodiment, when obtaining the second position estimation value corresponding to the target obstacle at the current moment and the first position estimation value corresponding to the target obstacle at the previous moment before the current moment, a weighted average algorithm is used to perform the first position estimation value and the second position estimation value to obtain a position weighted value, thereby determining the position weighted value as the target position corresponding to the target obstacle at the current moment.
[0076] Among them, the weights corresponding to the first position estimate and the second position estimate are both 0.5. When the second position estimate corresponding to the target obstacle at the current moment is obtained by the Kalman filter algorithm, the weighted average algorithm is further used for smoothing to further eliminate the position jitter of the measured obstacle caused by the noise of the position measurement device, thereby obtaining a more accurate target position corresponding to the target obstacle at the current moment, and then the target position can be used to warn the vehicle, so as to further ensure the accuracy of the vehicle warning according to the position of the obstacle.
[0077] S104: Issue an early warning to the vehicle according to the target location.
[0078] In this embodiment, the center of the vehicle is used as the origin, and the range of the vehicle is drawn according to the length and width of the vehicle. After the target position is obtained, the target position can be compared with the drawn range of the vehicle. If it is determined that the target position reaches a safe distance that threatens the safety of the vehicle, the vehicle is warned to ensure the safety of the user after leaving the vehicle.
[0079] The present embodiment provides a vehicle warning method. When the vehicle stops and obstacles around the vehicle need to be detected, a first position measurement value corresponding to the target obstacle detected at the current moment and a first position estimate value corresponding to the target obstacle detected at the previous moment are obtained, and the first position measurement value and the first position estimate value are processed by a Kalman filter algorithm to obtain a second position estimate value corresponding to the target obstacle at the current moment, and then the first position estimate value and the second position estimate value are processed by a weighted average algorithm to obtain the final target position of the target obstacle at the current moment, and then the target position is used to warn the vehicle. In this way, the present application jointly eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filter algorithm and the weighted average algorithm, and obtains a more accurate target position of the target obstacle at the current moment, thereby improving the accuracy of warning the vehicle according to the obstacles around the vehicle.
[0080] refer to Figure 2 , Figure 2 A flow chart of another vehicle warning method provided in an embodiment of the present application. A vehicle warning method provided in this embodiment includes the following steps:
[0081] S201: When the vehicle is in the target mode, if a target obstacle is detected around the vehicle, a corresponding image frame set around the vehicle is acquired.
[0082] S202: When all the image frames in the image frame set contain the target obstacle, determine a first image frame from the image frame set.
[0083] S203: Starting from the moment corresponding to the first image frame, obtaining a first position measurement value corresponding to the target obstacle detected at the current moment and obtaining a first position estimation value corresponding to the target obstacle detected at a moment before the current moment.
[0084] For the above steps S201 to S203, all the image frames in the image frame set are continuous in time and the number of all the image frames is a preset number. The time corresponding to the first image frame is the latest time among the times corresponding to all the image frames in the image frame set.
[0085] Wherein, when the vehicle is in the target mode, obstacles appearing around the vehicle are detected. If target obstacles are detected around the vehicle, in order to prevent unnecessary calculations, a preset number of continuous image frames around the vehicle are obtained. If each of the continuous image frames contains the target obstacle, it indicates that further calculations need to be performed on the target obstacle to determine whether the target obstacle poses a threat to the vehicle, so that the vehicle is warned when the target obstacle poses a threat to the vehicle. When each of the continuous image frames contains the target obstacle, the first image frame at the latest moment is determined from the image frame set, and starting from the first image frame, the steps of obtaining the first position measurement value corresponding to the target obstacle detected at the current moment and obtaining the first position estimation value corresponding to the target obstacle detected at the previous moment of the current moment in step S103 are executed. The preset number can be set according to actual needs. In this embodiment, the specific value of the preset number is not limited. For example, the preset number can be 5 frames.
[0086] Specifically, before executing step S103 of obtaining the first position measurement value corresponding to the target obstacle detected at the current moment and obtaining the first position estimation value corresponding to the target obstacle detected at the previous moment before the current moment, the Kalman filtering algorithm can be used to determine the position estimation value corresponding to each image frame in the continuous image frames, so that the first position estimation value corresponding to the target obstacle at the previous moment before the current moment can be obtained at the current moment.
[0087] It should be noted that the step of obtaining the first position measurement value corresponding to the target obstacle detected at the current moment and the step of obtaining the first position estimation value corresponding to the target obstacle detected at the previous moment in step S203 are consistent with the above-mentioned step S101. For details, please refer to the description of step S101, which will not be repeated in this embodiment.
[0088] In this embodiment, when all the image frames in the image frame set contain the target obstacle in step S202, determining the first image frame from the image frame set includes:
[0089] When all image frames in the image frame set contain the target obstacle, determining, for each image frame in the image frame set, a first distance between the target obstacle in the image frame and the vehicle to obtain a first distance set;
[0090] When all the first distances in the first distance set gradually decrease in order from small to large according to time, a first image frame is determined from the image frame set.
[0091] In the above, in order to further reduce unnecessary calculations and improve the accuracy of subsequent vehicle warnings, when all image frames in the image frame set contain target obstacles, the position measurement value of the target obstacle in each image frame measured by the position measurement device can be used to determine the first distance between the target obstacle and the vehicle (i.e., the center of the vehicle), thereby obtaining the first distance set corresponding to the image frame set. After obtaining the first distance set, the changes of all first distances in the first distance set can be determined in order from small to large in time. When the changes are gradually decreasing, it indicates that the target obstacles appearing around the vehicle may pose a threat to the vehicle, so further calculations are required to determine the degree of threat posed by the target obstacles to the vehicle, so that when it is determined that the target obstacles pose a greater threat to the vehicle, the vehicle is warned.
[0092] In this embodiment, if a target obstacle is detected around the vehicle in step S201, a corresponding image frame set around the vehicle is obtained, including:
[0093] If a target obstacle is detected around the vehicle, a second distance between the current target obstacle and the vehicle is determined;
[0094] When the second distance is less than or equal to the first distance threshold, a corresponding image frame set around the vehicle is acquired.
[0095] In the above, the first distance threshold represents the upper limit of the second distance corresponding to the obstacle detection around the vehicle. The first distance threshold can be set according to actual needs, and the specific value of the first distance threshold is not limited in this embodiment. In order to further reduce the waste of computing resources, if a target obstacle is detected around the vehicle, the distance between the position measurement value and the vehicle is determined according to the position measurement value of the target obstacle measured by the position measurement device at the current moment, so as to obtain the second distance between the current target obstacle and the vehicle. When the second distance is less than or equal to the first distance threshold, it indicates that the target obstacle may be approaching the vehicle, so the subsequent acquisition of the corresponding image frame set around the vehicle is executed to determine whether the target obstacle poses a real threat to the vehicle. When the second distance is greater than the first distance threshold, it indicates that the target obstacle is far away from the vehicle. At this time, there is no need to execute the subsequent acquisition of the corresponding image frame set around the vehicle to reduce the waste of computing resources.
[0096] S204: Processing the first position measurement value and the first position estimation value using a Kalman filter algorithm to determine a second position estimation value corresponding to the target obstacle at the current moment.
[0097] S205: Perform weighted averaging processing on the first position estimation value and the second position estimation value to obtain the target position corresponding to the target obstacle at the current moment.
[0098] S206: Issue a warning to the vehicle based on the target location.
[0099] Regarding the above-mentioned steps S204 to S206, step S204 is consistent with the above-mentioned step S102, step S205 is consistent with the above-mentioned step S103, and step S206 is consistent with the above-mentioned step S104. For details, please refer to the above-mentioned steps S102 to S104, which will not be repeated in this embodiment.
[0100] The present embodiment provides a vehicle warning method. When the vehicle stops and obstacles around the vehicle need to be detected, a first position measurement value corresponding to the target obstacle detected at the current moment and a first position estimate value corresponding to the target obstacle detected at the previous moment are obtained, and the first position measurement value and the first position estimate value are processed by a Kalman filter algorithm to obtain a second position estimate value corresponding to the target obstacle at the current moment, and then the first position estimate value and the second position estimate value are processed by a weighted average algorithm to obtain the final target position of the target obstacle at the current moment, and then the target position is used to warn the vehicle. In this way, the present application jointly eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filter algorithm and the weighted average algorithm, and obtains a more accurate target position of the target obstacle at the current moment, thereby improving the accuracy of warning the vehicle according to the obstacles around the vehicle.
[0101] refer to Figure 3 , Figure 3 A vehicle warning method provided in this embodiment includes the following steps:
[0102] S301: When the vehicle is in the target mode, a plurality of initial position measurement values corresponding to a target obstacle detected at a current moment are obtained, and a first position estimation value corresponding to a target obstacle detected at a moment before the current moment is obtained.
[0103] S302: For every two position measurement devices in the vehicle, determine a credible distance between the two position measurement devices according to initial position measurement values corresponding to the two position measurement devices, so as to obtain a credible distance set corresponding to the vehicle.
[0104] S303: Determine at least one first position measurement device from a plurality of position measurement devices according to the trusted distance set.
[0105] S304: Determine a first position measurement value corresponding to a target obstacle detected at a current moment according to an initial position measurement value corresponding to at least one first position measurement device.
[0106] With respect to the above-mentioned steps S301 to S304, the step of obtaining the first position estimation value corresponding to the target obstacle detected at the previous moment in step S301 is consistent with the above-mentioned step S101. For details, please refer to the above-mentioned step S101, which will not be described in detail in this embodiment.
[0107] Among them, a plurality of position measurement devices are provided in the vehicle, and the initial position measurement value is obtained by collecting the position measurement device, and the initial position measurement value corresponds to the position measurement device one by one, and the first position measurement device is a normal position measurement device. In order to improve the accuracy of obtaining the first position measurement value corresponding to the target obstacle detected at the current moment, so as to improve the accuracy of the subsequent determination of the target position corresponding to the target obstacle at the current moment by using the first position measurement device, thereby further improving the accuracy of the subsequent vehicle warning, in this embodiment, a plurality of position measurement devices are provided in the vehicle, so as to obtain the initial position measurement value corresponding to the target obstacle through the plurality of position measurement devices at the current moment, and perform a credible distance calculation on each two initial position measurement values, so as to obtain the credible distance between each two position measurement devices, and determine whether each position measurement device supports each other according to each credible distance obtained, and when each position measurement device supports each other, it is characterized that each position measurement device is normal, and when it is determined that the position measurement device does not support the other position measurement devices, it is characterized that the position measurement device is abnormal, and at this time, it is necessary to eliminate the initial position measurement value measured by the position measurement device, so as to obtain the first position measurement value corresponding to the target obstacle detected at the current moment by using the remaining initial position measurement values.
[0108] Specifically, after at least one first position measurement device is determined from multiple position measurement devices based on the trusted distance set, the initial position measurement values corresponding to the at least one first position measurement device are averaged to obtain a position measurement mean, and the position measurement mean is determined as the first position measurement value corresponding to the target obstacle detected at the current moment.
[0109] In this embodiment, determining the credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices in step S302 includes:
[0110] determining an average value between the plurality of initial position measurements, as the position measurement mean;
[0111] A credible distance between the two position measurement devices is determined according to the initial position measurement values and the position measurement mean values corresponding to the two position measurement devices.
[0112] In step S303, at least one first position measurement device is determined from a plurality of position measurement devices according to the trusted distance set, including:
[0113] Obtain target membership function;
[0114] At least one first position measurement device is determined from a plurality of position measurement devices according to the target membership function and the trustworthy distance set.
[0115] After obtaining the position measurement mean, the credible distance between the two position measurement devices can be determined using the following formula, as follows:
[0116]
[0117] In the above formula, d mn represents the credible distance, x m represents the initial position measurement value corresponding to a position measurement device, x n represents the initial position measurement value corresponding to another position measurement device, x a Represents the mean of the location measurements.
[0118] Specifically, the obtained trusted distance set is actually a trusted distance matrix. The target membership function is a function that determines the support between two position measurement devices based on the trusted distance and the trusted distance threshold. The trusted distance threshold can be set according to actual needs. The specific value of the trusted distance threshold is not limited in this embodiment. Similarly, the specific form of the target membership function is not limited in this embodiment, and the specific form of the target membership function can be selected according to actual needs. After obtaining the target membership function, each trusted distance in the trusted distance set can be compared with the trusted distance threshold in the target membership function to obtain the support between every two position measurement devices, and then according to all the obtained supports, the position measurement devices that are not supported by each position measurement device are screened out from multiple position measurement devices, so that the remaining position measurement devices are determined as the first position measurement device. Among them, the position measurement device that is not supported by each position measurement device is an abnormal position measurement device, and the first position measurement device is a normal position measurement device.
[0119] In this embodiment, after executing step S302 to obtain a credible distance set, a vehicle early warning method provided by this embodiment further includes the following steps:
[0120] When a second position measurement device is determined from a plurality of position measurement devices according to the trusted distance set, a target number of times that the second position measurement device continuously becomes abnormal is determined, and the second position measurement device is an abnormal position measurement device;
[0121] When the target number reaches a preset number threshold, target prompt information corresponding to the second position measurement device is generated, and the preset number threshold represents an upper limit value of the target number corresponding to the failure of the second position measurement device;
[0122] Push the target prompt information.
[0123] Among them, when an abnormal position measurement device is determined from multiple position measurement devices, it may be an abnormality caused by environmental interference. In order to avoid misjudgment, the target number of times that the abnormal position measurement device continuously appears abnormal is counted. If the target number reaches the preset number threshold, the position measurement device that represents the abnormality may have a fault, and a fault alarm is required at this time. When a fault alarm is performed, corresponding target prompt information is generated for the abnormal position measurement device, and the target prompt information is pushed to the corresponding staff. The specific form of the target prompt information can be set according to actual needs, and the specific form of the target prompt information is not limited in this embodiment. If the target number does not reach the preset number threshold, the position measurement device that represents the abnormality may not have a fault, and further judgment is required. This embodiment improves the reliability of vehicle operation in the above manner.
[0124] It should be noted that the preset number of times threshold can be set according to actual needs, and the specific value of the preset number of times threshold is not limited in this embodiment.
[0125] S305: Processing the first position measurement value and the first position estimation value using a Kalman filter algorithm to determine a second position estimation value corresponding to the target obstacle at the current moment.
[0126] S306: Perform weighted averaging processing on the first position estimation value and the second position estimation value to obtain the target position corresponding to the target obstacle at the current moment.
[0127] S307: Issue a warning to the vehicle based on the target location.
[0128] Regarding the above-mentioned steps S305 to S307, step S305 is consistent with the above-mentioned step S102, step S306 is consistent with the above-mentioned step S103, and step S307 is consistent with the above-mentioned step S104. For details, please refer to the above-mentioned steps S102 to S104, and this embodiment will not be repeated here.
[0129] The present embodiment provides a vehicle warning method. When the vehicle stops and obstacles around the vehicle need to be detected, a first position measurement value corresponding to the target obstacle detected at the current moment and a first position estimate value corresponding to the target obstacle detected at the previous moment are obtained, and the first position measurement value and the first position estimate value are processed by a Kalman filter algorithm to obtain a second position estimate value corresponding to the target obstacle at the current moment, and then the first position estimate value and the second position estimate value are processed by a weighted average algorithm to obtain the final target position of the target obstacle at the current moment, and then the target position is used to warn the vehicle. In this way, the present application jointly eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filter algorithm and the weighted average algorithm, and obtains a more accurate target position of the target obstacle at the current moment, thereby improving the accuracy of warning the vehicle according to the obstacles around the vehicle.
[0130] refer to Figure 5 , Figure 5 A schematic diagram of the structure of a vehicle warning device provided in an embodiment of the present application. A vehicle warning device provided in an embodiment of the present application includes: an acquisition module 10, a processing module 20 and an early warning module 30. Among them, the acquisition module 10 is used to acquire the first position measurement value corresponding to the target obstacle detected at the current moment and the first position estimation value corresponding to the target obstacle detected at the previous moment of the current moment when the vehicle is in the target mode, and the target mode is used to characterize the detection of surrounding obstacles by the vehicle when it stops; the processing module 20 is used to process the first position measurement value and the first position estimation value using the Kalman filter algorithm to determine the second position estimation value corresponding to the target obstacle at the current moment; the processing module 20 is also used to perform weighted average processing on the first position estimation value and the second position estimation value to obtain the target position corresponding to the target obstacle at the current moment; the early warning module 30 is used to warn the vehicle according to the target position.
[0131] In this embodiment, the acquisition module 10 is further used for:
[0132] If the target obstacle is detected to exist around the vehicle, a corresponding image frame set around the vehicle is acquired, wherein all image frames in the image frame set are continuous in time and the number of all image frames is a preset number;
[0133] When all the image frames in the image frame set contain the target obstacle, determining a first image frame from the image frame set, the time corresponding to the first image frame being the latest time among the times corresponding to all the image frames in the image frame set;
[0134] Starting from the moment corresponding to the first image frame, a first position measurement value corresponding to the target obstacle detected at the current moment is obtained, and a first position estimation value corresponding to the target obstacle detected at a moment before the current moment is obtained.
[0135] In this embodiment, the acquisition module 10 is further used for:
[0136] When all the image frames in the image frame set contain the target obstacle, determining, for each of the image frames in the image frame set, a first distance between the target obstacle in the image frame and the vehicle to obtain a first distance set;
[0137] When all the first distances in the first distance set gradually decrease in order from small to large in time, a first image frame is determined from the image frame set.
[0138] In this embodiment, the acquisition module 10 is further used for:
[0139] If it is detected that the target obstacle exists around the vehicle, determining a second distance between the current target obstacle and the vehicle;
[0140] When the second distance is less than or equal to a first distance threshold, a set of image frames corresponding to the surroundings of the vehicle is acquired, wherein the first distance threshold represents an upper limit value of the second distance corresponding to the obstacle detection around the vehicle.
[0141] In this embodiment, a plurality of position measuring devices are arranged in the vehicle.
[0142] In this embodiment, the acquisition module 10 is further used for:
[0143] Acquire a plurality of initial position measurement values corresponding to the target obstacle detected at the current moment, the initial position measurement values being acquired by the position measurement device, and the initial position measurement values corresponding to the position measurement device one-to-one;
[0144] For each two position measurement devices in the vehicle, determining a credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices, so as to obtain a credible distance set corresponding to the vehicle;
[0145] Determine at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set, wherein the first position measurement device is a normal position measurement device;
[0146] A first position measurement value corresponding to the target obstacle detected at a current moment is determined according to the initial position measurement value corresponding to at least one of the first position measurement devices.
[0147] In this embodiment, the acquisition module 10 is further used for:
[0148] determining an average value between a plurality of said initial position measurements to obtain a position measurement mean;
[0149] Determining a credible distance between the two position measurement devices according to the initial position measurement values and the position measurement mean values corresponding to the two position measurement devices;
[0150] The step of determining at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set comprises:
[0151] Acquire a target membership function, where the target membership function is a function for determining the support between the two position measurement devices based on the credible distance and a credible distance threshold;
[0152] At least one first position measurement device is determined from the plurality of position measurement devices according to the target membership function and the trusted distance set.
[0153] The vehicle early warning device provided in this embodiment further includes a push module, which is used to:
[0154] When a second position measurement device is determined from the plurality of position measurement devices according to the trusted distance set, a target number of times that the second position measurement device continuously becomes abnormal is determined, and the second position measurement device is the abnormal position measurement device;
[0155] When the target number reaches a preset number threshold, generating target prompt information corresponding to the second position measurement device, wherein the preset number threshold represents an upper limit value of the target number corresponding to the failure of the second position measurement device;
[0156] The target prompt information is pushed.
[0157] The present embodiment provides a vehicle warning device, which, when the vehicle stops and obstacles around the vehicle need to be detected, obtains a first position measurement value corresponding to the target obstacle detected at the current moment and a first position estimate value corresponding to the target obstacle detected at the previous moment before the current moment, so as to process the first position measurement value and the first position estimate value using a Kalman filter algorithm to obtain a second position estimate value corresponding to the target obstacle at the current moment, and then processes the first position estimate value and the second position estimate value using a weighted average algorithm to obtain the final target position of the target obstacle at the current moment, and then uses the target position to warn the vehicle. In this way, the present application jointly eliminates the noise in the first position measurement value corresponding to the target obstacle measured at the current moment through the Kalman filter algorithm and the weighted average algorithm, obtains a more accurate target position of the target obstacle at the current moment, and improves the accuracy of warning the vehicle according to the obstacles around the vehicle.
[0158] refer to Figure 6 As shown, Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle 600 in this embodiment may include: at least one processor 601, a vehicle memory 602, at least one network interface 604 and other user interfaces 603. The various components in the vehicle 600 are coupled together via a bus system 605. It can be understood that the bus system 605 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 605 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, various buses are labeled as bus system 605.
[0159] The user interface 603 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).
[0160] It can be understood that the memory 602 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 602 described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0161] In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 6021 and an application program 6022 .
[0162] The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 6022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application can be included in the application 6022.
[0163] In the embodiment of the present application, by calling the program or instruction stored in the memory 602, specifically, the program or instruction stored in the application 6022, the processor 601 is used to execute the method provided by each method embodiment.
[0164] The method disclosed in the above embodiment of the present application can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the above method in combination with its hardware.
[0165] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or at least one application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing vehicle (DSPDevice, DSPD), programmable logic vehicle (PLD), field programmable gate array (FPGA), general purpose processor, controller, microcontroller, microprocessor, other electronic unit for performing the functions described in the present application, or a combination thereof.
[0166] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.
[0167] The embodiment of the present application also provides a storage medium (computer-readable storage medium). The storage medium here stores one or at least one program. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.
[0168] When one or at least one program in the storage medium can be executed by one or at least one processor. When the storage medium is applied to a vehicle, the above-mentioned method executed in the vehicle can be implemented. The processor is used to execute the vehicle program stored in the memory to implement the above-mentioned method executed in the vehicle.
[0169] The professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0170] It should be noted that the phrases "one implementation", "an embodiment", "an exemplary embodiment", "some embodiments", etc. mentioned in the specification indicate that the described embodiments may include certain features, structures or characteristics, but not every embodiment may include the certain features, structures or characteristics. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when describing certain features, structures or characteristics in conjunction with an embodiment, it is within the knowledge of those skilled in the art to implement such features, structures or characteristics in conjunction with other embodiments, whether explicitly or not explicitly described.
[0171] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method or article including a series of elements may include not only those elements, but also other elements not explicitly listed, or may also include elements inherent to such process, method, article or vehicle. In the absence of more limitations, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or vehicle including the elements.
[0172] The above embodiments are only preferred embodiments for fully illustrating the present application, and the protection scope of the present application is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present application is within the protection scope of the present application.
Claims
1. A vehicle early warning method, characterized in that: include: When the vehicle is in a target mode, obtaining a first position measurement value corresponding to a target obstacle detected at a current moment and obtaining a first position estimation value corresponding to the target obstacle detected at a moment before the current moment, wherein the target mode is used to indicate that the vehicle detects surrounding obstacles when it is stopped; Processing the first position measurement value and the first position estimate value by using a Kalman filter algorithm to determine a second position estimate value corresponding to the target obstacle at the current moment; Performing weighted averaging processing on the first position estimation value and the second position estimation value to obtain a target position corresponding to the target obstacle at the current moment; According to the target position, the vehicle is warned.
2. The vehicle early warning method according to claim 1, characterized in that: The obtaining of a first position measurement value corresponding to a target obstacle detected at a current moment and obtaining a first position estimation value corresponding to the target obstacle detected at a moment before the current moment include: If the target obstacle is detected to exist around the vehicle, a corresponding image frame set around the vehicle is acquired, wherein all image frames in the image frame set are continuous in time and the number of all image frames is a preset number; When all the image frames in the image frame set contain the target obstacle, determining a first image frame from the image frame set, the time corresponding to the first image frame being the latest time among the times corresponding to all the image frames in the image frame set; Starting from the moment corresponding to the first image frame, a first position measurement value corresponding to the target obstacle detected at the current moment is obtained, and a first position estimation value corresponding to the target obstacle detected at a moment before the current moment is obtained.
3. The vehicle early warning method according to claim 2, characterized in that: When all the image frames in the image frame set contain the target obstacle, determining a first image frame from the image frame set includes: When all the image frames in the image frame set contain the target obstacle, determining, for each of the image frames in the image frame set, a first distance between the target obstacle in the image frame and the vehicle to obtain a first distance set; When all the first distances in the first distance set gradually decrease in order from small to large in time, a first image frame is determined from the image frame set.
4. The vehicle warning method according to claim 2, characterized in that: If the target obstacle is detected to exist around the vehicle, obtaining a corresponding image frame set around the vehicle includes: If it is detected that the target obstacle exists around the vehicle, determining a second distance between the current target obstacle and the vehicle; When the second distance is less than or equal to a first distance threshold, a set of image frames corresponding to the surroundings of the vehicle is acquired, wherein the first distance threshold represents an upper limit value of the second distance corresponding to the obstacle detection around the vehicle.
5. The vehicle warning method according to claim 1, characterized in that: A plurality of position measuring devices are provided in the vehicle; The obtaining of a first position measurement value corresponding to the target obstacle detected at the current moment includes: Acquire a plurality of initial position measurement values corresponding to the target obstacle detected at the current moment, the initial position measurement values being acquired by the position measurement device, and the initial position measurement values corresponding to the position measurement device one-to-one; For each two position measurement devices in the vehicle, determining a credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices, so as to obtain a credible distance set corresponding to the vehicle; Determine at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set, wherein the first position measurement device is a normal position measurement device; A first position measurement value corresponding to the target obstacle detected at a current moment is determined according to the initial position measurement value corresponding to at least one of the first position measurement devices.
6. The vehicle warning method according to claim 5, characterized in that: Determining the credible distance between the two position measurement devices according to the initial position measurement values corresponding to the two position measurement devices includes: determining an average value between a plurality of said initial position measurements to obtain a position measurement mean; Determining a credible distance between the two position measurement devices according to the initial position measurement values and the position measurement mean values corresponding to the two position measurement devices; The step of determining at least one first position measurement device from the plurality of position measurement devices according to the trusted distance set comprises: Acquire a target membership function, where the target membership function is a function for determining the support between the two position measurement devices based on the credible distance and a credible distance threshold; At least one first position measurement device is determined from the plurality of position measurement devices according to the target membership function and the trusted distance set.
7. The vehicle warning method according to claim 5, characterized in that: After obtaining the credible distance set, the method further includes: When a second position measurement device is determined from the plurality of position measurement devices according to the trusted distance set, a target number of times that the second position measurement device continuously becomes abnormal is determined, and the second position measurement device is the abnormal position measurement device; When the target number reaches a preset number threshold, generating target prompt information corresponding to the second position measurement device, wherein the preset number threshold represents an upper limit value of the target number corresponding to the failure of the second position measurement device; The target prompt information is pushed.
8. A vehicle warning device, characterized in that: include: an acquisition module, used for acquiring a first position measurement value corresponding to a target obstacle detected at a current moment and acquiring a first position estimation value corresponding to the target obstacle detected at a previous moment before the current moment when the vehicle is in a target mode, wherein the target mode is used to indicate that the vehicle detects surrounding obstacles when it is stopped; a processing module, configured to process the first position measurement value and the first position estimation value by using a Kalman filter algorithm to determine a second position estimation value corresponding to the target obstacle at the current moment; The processing module is further used to perform weighted average processing on the first position estimation value and the second position estimation value to obtain the target position corresponding to the target obstacle at the current moment; The early warning module is used to issue an early warning to the vehicle according to the target position.
9. A vehicle, characterized in that: include: A processor and a memory, wherein the processor is used to execute a vehicle warning program stored in the memory to implement the vehicle warning method of any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the vehicle warning method of any one of claims 1 to 7.