CN118618426A

CN118618426A - Vehicle escape route matching method, vehicle control system and storage medium

Info

Publication number: CN118618426A
Application number: CN202410690056.8A
Authority: CN
Inventors: 黄彬; 吴智宽; 李剑平
Original assignee: Huizhou Desay SV Automotive Co Ltd
Current assignee: Huizhou Desay SV Automotive Co Ltd
Priority date: 2024-05-30
Filing date: 2024-05-30
Publication date: 2024-09-10

Abstract

The application provides a vehicle escape route matching method, a vehicle control system and a storage medium; the vehicle escape route matching method comprises the following steps: extracting first characteristic information and corresponding first position information based on real-time surrounding environment in advance so as to memorize an escape route; and then after receiving the escape instruction, matching the second characteristic information of the current environment of the identified target vehicle and the corresponding second position information with the escape route so as to determine that the escape route is successfully matched when the overlapping degree of the matching area is greater than or equal to a preset threshold value. The application can comprehensively sense surrounding conditions, ensure more accurate escape route matching, quickly determine escape routes under emergency conditions and improve vehicle escape efficiency and success rate; the target vehicle can be driven away from the dangerous area in time by matching the escape route, so that property loss is reduced.

Description

Vehicle escape route matching method, vehicle control system and storage medium

Technical Field

The application relates to the technical field of vehicle safety, in particular to a vehicle escape route matching method, a vehicle control system and a storage medium.

Background

In summer, many cities face severe weather such as storm and typhoon, at this time, underground garages and low-lying residential areas are always submerged by rainwater due to geographical positions, and vehicles in the underground garages and the low-lying residential areas are also always submerged by rainwater, so that the water-immersed vehicles are formed, and the water-immersed vehicles are greatly devaluated even if the water-immersed vehicles are maintained at a high price, so that great property loss of people is caused.

Under severe weather, a vehicle owner can not immediately travel to the place where the vehicle is located to leave the vehicle, and can not travel the vehicle away from an underground garage or a low-lying residential area and other easily submerged areas in the early period of flooding, so that after flooding is caused to a certain extent, the vehicle can not be ignited and started to travel away from the flooding area, and property loss of the vehicle owner is caused.

Disclosure of Invention

The application provides a vehicle escape route matching method, a vehicle control system and a storage medium for solving the technical problems.

Specifically, the application provides a vehicle escape route matching method, which comprises the following steps:

s100: first characteristic information of the surrounding environment of the target vehicle is extracted in real time, and first position information corresponding to each first characteristic information is recorded so as to memorize the escape route.

S200: responding to the escape instruction, identifying second characteristic information and corresponding second position information of the current environment of the target vehicle, and matching with the escape route to determine the overlapping degree of the matching area; and when the overlapping degree is greater than or equal to a preset threshold value, determining that the escape route is successfully matched.

In the technical scheme, the vehicle can comprehensively sense the surrounding situation by extracting the characteristic information of the surrounding environment and recording the position information, so that more accurate escape route matching is ensured; by recording the escape route in advance, the escape route can be rapidly determined in emergency, and the escape efficiency and the success rate of the vehicle are improved; the target vehicle can be driven away from a dangerous area, such as a flooded area, in time by matching with the escape route, so that property loss is reduced.

Further, the step S100 includes:

And determining a memory starting point coordinate, acquiring a first initial image of the surrounding environment of the target vehicle in real time, and sequentially carrying out graying treatment and normalization treatment on the first initial image to acquire the target image.

In the technical scheme, the system can accurately memorize the starting position of the escape route by determining and memorizing the starting point coordinates and acquiring the first initial image of the surrounding environment of the target vehicle in real time, so as to provide a reliable reference basis for the subsequent escape route; through the graying treatment and the normalization treatment of the first initial image, the characteristic information can be better extracted, so that the comparability and the matching accuracy of the target image are improved, and the accuracy of the escape route is ensured.

Further, after the target image is acquired, the step S100 further includes:

And calculating the gradient direction and the gradient amplitude between pixels of the target image, and dividing the target image into pixel units with preset sizes.

And forming a gradient histogram based on the gradient direction and the gradient amplitude corresponding to the pixel unit, so as to serve as initial characteristic information of the pixel unit.

In the technical scheme, by calculating the gradient direction and the gradient amplitude, the system can analyze the characteristics in the image more carefully and divide the image into pixel units with preset sizes, thereby being beneficial to extracting more detailed and accurate characteristic information; the gradient histogram is formed as the initial characteristic information of the pixel unit, so that the characteristic distribution condition of the image can be better represented, the accuracy and the precision of image matching are improved, the accurate escape route matching is facilitated, and the reliability and the accuracy of the escape route matching method are enhanced.

Further, after the initial feature information is obtained, the step S100 further includes:

And combining each first preset adjacent pixel unit into a pixel module, and acquiring target characteristic information based on the initial characteristic information of each pixel unit in the pixel module. For example, every 5 (i.e., the first preset) adjacent pixel units are combined into a pixel module, and a combined histogram, i.e., the target feature information, is obtained based on the gradient histogram statistics of each pixel unit, which may also be represented as HOG features.

And further combining the second preset target characteristic information to acquire the first characteristic information.

In the technical scheme, the adjacent pixel units are combined into the pixel module, so that the system can better capture the relevance and local characteristics among the pixels, the expression capacity of the characteristic information is improved, and the image characteristics can be described more accurately; the pixel module is formed by combining the pixel units, so that the data dimension can be reduced, the characteristic information processing process is simplified, the calculation complexity and the storage requirement are reduced, and the efficiency and the performance of the system are improved; acquiring target feature information based on initial feature information of each pixel unit in the pixel module, so as to be beneficial to averaging the difference of local features, increase the stability and consistency of image features and improve the reliability of feature information; and combining the target characteristic information to acquire the first characteristic information, thereby being beneficial to integrating the characteristic information, optimizing the extraction and matching processes of the characteristics and improving the matching precision and accuracy of the escape route.

Further, the step S100 further includes, while recording the first location information:

And acquiring wheel speed pulse data and IMU data of the target vehicle in real time, and fusing the wheel speed pulse data and the IMU data to acquire DR information.

The DR (dead reckoning ) information is information of the target vehicle position and direction obtained by wheel speed pulse data and IMU data reckoning.

In the technical scheme, the DR information can provide more accurate vehicle position and direction information by fusing the wheel speed pulse data and the IMU data, so that the accuracy and stability of an escape route are enhanced; the DR information is acquired independent of external signals, such as satellite signals, so that reliable positioning information can be acquired without GPS signals or with weak signals.

Further, after obtaining the DR information, the step S100 further includes:

And determining a memory end point coordinate, generating an escape route according to the memory start point coordinate, the memory end point coordinate, the first characteristic information, the first position information and the DR information, and storing the escape route.

Wherein a plurality of HOG features (target feature information) constitute feature sets (i.e., the first feature information) of different specific elements (pillars, pipes, gates, landmarks, buildings, etc.); and storing the feature sets, and simultaneously recording the corresponding position (namely the first position information) of the feature sets of the specific elements of each frame.

In the technical scheme, by determining the memory starting point and the memory end point coordinates and combining the first characteristic information, the position information and the DR information, the system can generate a more accurate escape route, so that the system can plan a safe escape route more accurately, and a vehicle owner can be helped to drive a target vehicle out of a flooding area rapidly and safely in an emergency.

Further, before executing step S200, the method includes:

responding to the water logging early warning reported by the water logging sensor of the target vehicle, and sending a message to inform the vehicle owner by combining the ignition state of the target vehicle so as to send out an escape instruction.

According to the technical scheme, the water immersion sensor and the vehicle ignition state are combined, the system can monitor the vehicle condition in real time, and once water immersion early warning is found, a message notification is sent to the vehicle owner immediately, so that the vehicle owner is helped to take countermeasures in time, and property loss and personal safety risks are reduced; the vehicle owner sends out the escape instruction, so that the active participation and control right of the user are increased, the user can actively start the escape procedure when necessary, and the initiative and the flexibility in the escape process are enhanced.

Further, after the escape route matching in step S200 is determined to be successful, the method further includes:

and recording the current coordinates of the target vehicle to acquire the relative vector coordinates of the current coordinates based on the memory starting point coordinates as escape starting point coordinates.

In the technical scheme, the escape starting point position can be more accurately determined by acquiring the relative vector coordinates of the current coordinates based on the memory starting point coordinates, and the accuracy and operability of the escape route are enhanced by considering the relative positions of the current position of the vehicle and the escape route; the relative vector coordinates are recorded, so that the escape starting point coordinates can be flexibly adjusted according to the current position of the vehicle, the escape requirements under different conditions are met, and the adaptability and the practicability of the system are improved.

Based on the same conception, the present application also provides a vehicle control system including:

the matching module is used for matching the escape route of the target vehicle through the vehicle escape route matching method, and acquiring the escape starting point coordinates and the memory ending point coordinates.

The planning module is used for planning the vehicle escape route based on the escape starting point coordinates, the memory ending point coordinates and the escape route.

And the control module is used for controlling the vehicle to travel to the memory terminal point coordinate according to the planning result of the planning module.

According to the technical scheme, the escape route of the target vehicle is accurately matched through the vehicle escape route matching method, so that the vehicle can escape according to the optimal route, and the efficiency and the success rate of the escape process are improved; based on the escape starting point coordinates, the memory ending point coordinates and the escape route, the escape route of the vehicle is intelligently planned, and the vehicle can safely and quickly reach the destination by taking road conditions and other factors into consideration; the whole system can rapidly respond to the escape requirement of the vehicle, and the rapid escape and safety of the vehicle under emergency conditions are ensured through intelligent path planning and automatic control.

Based on the same idea, the present application also provides a storage medium having stored therein a computer program, wherein the computer program is arranged to execute the vehicle escape route matching method when run.

Compared with the prior art, the application has the beneficial effects that:

the application needs to extract the first characteristic information and the corresponding first position information based on the real-time surrounding environment in advance so as to memorize the escape route; and then, when an escape instruction is received, matching the second characteristic information of the current environment of the identified target vehicle and the corresponding second position information with the escape route, so as to determine that the escape route is successfully matched when the overlapping degree of the matching area is greater than or equal to a preset threshold value.

The application can comprehensively sense the surrounding situation and ensure more accurate escape route matching; by recording the escape route in advance, the escape route can be rapidly determined in emergency, and the escape efficiency and the success rate of the vehicle are improved; the target vehicle can be driven away from the dangerous area in time by matching the escape route, so that property loss is reduced.

Drawings

Fig. 1 is a flowchart of a vehicle escape route matching method according to an embodiment.

Fig. 2 is a frame diagram of a vehicle control system according to a second embodiment.

Detailed Description

The following describes a vehicle escape route matching method, a vehicle control system and a storage medium according to the present application in further detail with reference to specific embodiments and drawings.

Embodiment one:

referring to fig. 1, the application provides a vehicle escape route matching method, which comprises the following steps:

Further, the step S100 includes:

In this embodiment, the driver needs to start the escape route memorizing function in advance, confirm the memorizing starting point through the vehicle software to obtain the corresponding memorizing starting point coordinate, and then manually drive to the preset escape destination.

In the process of driving from a determined memory starting point to a preset escape destination, a target vehicle can be combined with a camera and an ultrasonic radar to extract information on a driving route in real time; in this embodiment, a HOG (Histogram of Oriented Gradient, gradient direction histogram, which is a feature expression method based on the local gradient direction of the image) feature extraction algorithm is mainly used.

Specifically, first, image data of the surrounding environment of the target vehicle (i.e., the first initial image) is acquired in real time by, for example, front, rear, left and right 4 cameras.

It should be noted that, the collection by the 4-way camera is only an example, and when the vehicle further includes other cameras, the image data of the cameras may be obtained for further feature extraction, which is not limited thereto.

Further, the first initial image is subjected to graying processing, and the image can be regarded as a three-dimensional image of x, y and z (gray scale); and then, carrying out color space normalization processing on the first initial image after the graying processing by adopting a Gamma correction method, adjusting the contrast of the image, reducing the influence of local illumination and shadow, and further obtaining the target image.

The Gamma correction method is a method for adjusting the brightness and contrast of an image; in digital image processing, nonlinear Gamma correction is typically used to adjust the brightness of an image; the Gamma correction is based on the principle that the display effect of the image in the dark and light portions is improved by performing nonlinear transformation on the pixel values of the image.

The Gamma correction formula is: v_corr=v≡gamma, where v_corr is the corrected pixel value, V is the original pixel value, gamma is a constant greater than 0, called gamma value; when the gamma value is less than 1, the contrast of the image is increased and the details of dark parts are enhanced; when the gamma value is greater than 1, the contrast of the image is reduced and the bright details are enhanced.

Further, after the target image is acquired, the step S100 further includes:

In the present embodiment, gradient magnitudes in the horizontal direction and the vertical direction of the target image are calculated using the difference, and the gradient direction and the gradient magnitude are obtained based on the gradient magnitudes.

Then dividing the target image into pixel units (n×n pixels) with preset sizes.

It should be noted that, a person skilled in the art may select a suitable size according to actual application requirements, and the size of the pixel units is not limited herein, and only the sizes of the pixel units are required to be uniform.

In the present embodiment, the gradient of each pixel inside each pixel unit forms a gradient histogram of the unit as initial characteristic information of this pixel unit.

And combining each first preset adjacent pixel unit into a pixel module, and acquiring target characteristic information based on the initial characteristic information of each pixel unit in the pixel module.

In this embodiment, a plurality of adjacent pixel units are combined into a pixel module, and initial feature information of all pixel units in each pixel module is combined, so that the HOG feature (i.e. the target feature information) of the pixel module is obtained.

It should be noted that, a person skilled in the art may select a suitable number of pixel units according to practical application requirements, which is not limited herein.

And combining the second preset target characteristic information to acquire the first characteristic information.

In this embodiment, the plurality of HOG features constitute feature sets (i.e., the first feature information) of different specific elements (pillars, pipes, gates, landmarks, buildings, etc.); and storing the feature sets, and simultaneously recording the corresponding position (namely the first position information) of the feature sets of the specific elements of each frame.

In this embodiment, the acquired DR information is also recorded.

Further, after obtaining the DR information, the step S100 further includes:

In this embodiment, after reaching a preset escape destination, determining an end point by using vehicle software, acquiring corresponding memory end point coordinates, and acquiring an escape route in the whole process by combining the memory start point coordinates, the memory end point coordinates, the first characteristic information, the first position information and the DR information, and storing the escape route in an EMMC.

The memory starting point is confirmed in advance, so that the current position of the target vehicle is combined with the area where the memory starting point is located for matching when the escape route is matched later.

Further, before executing step S200, the method includes:

In the present embodiment, the contact-type water sensor and the noncontact-type water sensor device can be freely selected.

If the vehicle is in the ignition state, the vehicle can send out a message to inform the vehicle owner, and the vehicle owner further sends out an escape instruction.

If the vehicle is in a non-contact type water logging sensor, the vehicle can be arranged at any position where the vehicle can downwards detect, when the non-contact type water logging sensor recognizes that the water level is a certain distance away from the non-contact type water logging sensor, the vehicle-mounted network reports the mobile phone application, the mobile phone application is combined with the current ignition state of the vehicle to judge whether to send a message to inform the vehicle owner, and the vehicle owner further sends an escape instruction.

In the embodiment, a VSLAM (Visual Simultaneous Localization AND MAPPING ) technology is mainly adopted; the basic principle is that an environment image is captured by using a camera, and the position of a target vehicle in the environment is positioned in real time through algorithms such as a visual odometer, feature point matching and the like.

Acquiring second characteristic information and second position information by adopting an HOG characteristic extraction algorithm in the step S100, matching the second characteristic information and the stored escape route, and further determining the matching degree by comparing the similarity between a target area marked in an image to be matched and the escape route of the target vehicle; common similarity measures such as difference measures or correlation measures.

And (3) evaluating the matching result by calculating an overlapping degree (IoU) index of the matching area, wherein the target feature of more than 50% (variable) is successfully matched, and judging that the current position is successfully positioned.

If the matching is unsuccessful, the matching is carried out again, and when the matching is supposed to fail for 3 times, an escape failure early warning is sent to the vehicle owner.

It should be noted that, for the preset threshold value of 50% and the number of matching failures, those skilled in the art can adaptively adjust according to the actual application requirements, and are not limited thereto.

The memory starting point coordinates can be coordinates of fixed parking spaces or coordinates of any point of a garage, and the actual parking position when flooding occurs can be on the parking spaces on two sides of a path for creating an escape path by manual driving, so that the escape path can be successfully matched.

The coordinate system of the whole escape route is the origin point (0, 0) corresponding to the position of the automobile when the memory function of the escape route is started by clicking, the direction of the head of the automobile is the positive direction of the Y axis, the direction of the vertical head of the automobile is the positive direction of the X axis, and the position of the current escape position in the coordinate system of the escape route can be determined after the image matching of the escape starting point is successful.

Assuming that the escape route is successfully matched, the position (i.e. the memory starting point coordinates) of the target vehicle corresponding to the image in the stage of memorizing the escape route is x1, y1 and theta1, and after the matching is successful, the position (i.e. the current coordinates of the target vehicle are recorded) of the target vehicle corresponding to the image in the stage of positioning is x2, y2 and theta2.

The rotation angle theta2 can be estimated by comparing the gradient directions of the images in the two stages, and the rotation angle is calculated by the difference between the recorded gradient direction information of the escape route and the gradient direction of the current positioning stage.

The transformation is converted into x2', y2', theta2' (namely relative vector coordinates) under a relative coordinate system of the escape route memorizing stage through translation and rotation. This transformation may use the formulas for translation and rotation:

x2′＝x2*cos(theta1)-y2*sin(theta1)+x1

y2′＝x2*sin(theta1)+y2*cos(theta1)+y1

it should be noted that, the coordinate mode of converting the coordinate after the feature set matching to the escape route coordinate system is only one mode, and the application should not be limited to a certain conversion formula, nor to the feature matching algorithm in the description.

Embodiment two:

Referring to fig. 2, the present application further provides a vehicle control system, including:

The matching module is used for matching the escape route of the target vehicle through the vehicle escape route matching method according to the first embodiment, and obtaining the escape starting point coordinates and the memory ending point coordinates.

In this embodiment, it is necessary to store escape routes in advance, including:

First characteristic information of the surrounding environment of the target vehicle is extracted in real time, and first position information corresponding to each first characteristic information is recorded so as to memorize the escape route.

Further, responding to the water logging early warning reported by the water logging sensor of the target vehicle, and sending a message to inform the vehicle owner by combining the ignition state of the target vehicle so as to send an escape instruction; and responding to the escape instruction, identifying second characteristic information and corresponding second position information of the current environment of the target vehicle, and matching with the escape route to determine the overlapping degree of the matching area.

And when the overlapping degree is greater than or equal to a preset threshold value, determining that the escape route is successfully matched.

In this embodiment, the path planning may be any one of the current vehicle planning algorithms, such as global path planning, and a global path (i.e. a vehicle escape path) is generated according to the determined escape start point coordinates and memory end point coordinates and in combination with feature information in the escape route.

It should be noted that, a person skilled in the art may select any suitable vehicle planning algorithm according to the actual application requirement, and the application of the vehicle planning algorithm is not limited herein.

Embodiment III:

the present application also provides a storage medium having a computer program stored therein, wherein the computer program is configured to execute the vehicle escape route matching method according to embodiment one of the present application when executed.

In this embodiment, the storage medium stores a plurality of computer programs for causing a matching module to execute all or part of the steps of the method according to the embodiment of the present application.

The storage medium may include a usb disk, a removable hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc. various media capable of storing program codes.

In summary, the present application provides a vehicle escape route matching method, a vehicle control system and a storage medium; extracting first characteristic information and corresponding first position information based on real-time surrounding environment in advance so as to memorize an escape route; and then, when an escape instruction is received, matching the second characteristic information of the current environment of the identified target vehicle and the corresponding second position information with the escape route, so as to determine that the escape route is successfully matched when the overlapping degree of the matching area is greater than or equal to a preset threshold value. The application can comprehensively sense the surrounding situation and ensure more accurate escape route matching; by recording the escape route in advance, the escape route can be rapidly determined in emergency, and the escape efficiency and the success rate of the vehicle are improved; the target vehicle can be driven away from the dangerous area in time by matching the escape route, so that property loss is reduced.

Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above illustrative embodiments are merely exemplary and are not intended to limit the scope of the present application thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the application. All such changes and modifications are intended to be included within the scope of the present application as set forth in the appended claims.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another device, or some features may be omitted or not performed.

Various component embodiments of the application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some of the modules according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application can also be implemented as an apparatus program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

While the application has been described in conjunction with the specific embodiments above, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art in light of the foregoing description. Accordingly, all such alternatives, modifications, and variations are included within the spirit and scope of the following claims.

Claims

1. The vehicle escape route matching method is characterized by comprising the following steps of:

s100: extracting first characteristic information of the surrounding environment of the target vehicle in real time, and recording first position information corresponding to each first characteristic information so as to memorize an escape route;

s200: responding to the escape instruction, identifying second characteristic information and corresponding second position information of the current environment of the target vehicle, and matching with the escape route to determine the overlapping degree of the matching area;

2. The vehicle escape route matching method according to claim 1, wherein said step S100 includes:

3. The vehicle escape route matching method according to claim 2, wherein after the target image is acquired, the step S100 further includes:

calculating the gradient direction and the gradient amplitude between pixels of the target image, and dividing the target image into pixel units with preset sizes;

4. The vehicle escape route matching method according to claim 3, wherein after the initial characteristic information is acquired, the step S100 further comprises:

Combining each first preset adjacent pixel unit into a pixel module, and acquiring target characteristic information based on initial characteristic information of each pixel unit in the pixel module;

5. The vehicle escape route matching method according to claim 4, wherein said step S100 further comprises, while recording the first position information:

6. The vehicle escape route matching method according to claim 5, wherein after obtaining DR information, said step S100 further comprises:

7. The vehicle escape route matching method according to claim 1, characterized by comprising, before performing step S200: responding to the water logging early warning reported by the water logging sensor of the target vehicle, and sending a message to inform the vehicle owner by combining the ignition state of the target vehicle so as to send out an escape instruction.

8. The vehicle escape route matching method according to claim 1, wherein after the escape route matching determined in step S200 is successful, further comprising:

9. A vehicle control system, characterized by comprising:

A matching module for matching an escape route of a target vehicle by the vehicle escape route matching method according to any one of claims 1 to 8, and obtaining escape start point coordinates and memory end point coordinates;

the planning module is used for planning a vehicle escape path based on the escape starting point coordinates, the memory terminal point coordinates and the escape route;

10. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the vehicle escape route matching method according to any one of claims 1-8 when run.