Obstacle position information determination method and device and vehicle

Abstract

The embodiment of the invention discloses an obstacle position information determination method and device and a vehicle. The method comprises the following steps: acquiring a first detection result of an ultrasonic sensor of a vehicle for an obstacle and a second detection result of a visual sensor of the vehicle for the obstacle; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold value, acquiring a moving trend of an obstacle relative to the vehicle; and adjusting the second detection result according to the moving trend to obtain position information of the obstacle. According to the method, under the condition that different detection results of the same obstacle are greatly different, the moving trend of the obstacle is obtained, the adjustment mode of the obstacle detection result is determined according to the moving trend of the obstacle, the more accurate obstacle position can be derived, the driving space of the vehicle is increased, and the driving efficiency of the vehicle is improved. And the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle parking, and more specifically, to a method and device for determining position information of an obstacle, and a vehicle. Background Art

[0002] As autonomous driving technology matures, more and more vehicles are equipped with autonomous driving functions, which can realize automatic parking and memory parking. In the process of automatic parking and memory parking, ultrasonic radar sensors and visual cameras play an important role to help vehicles avoid obstacles and avoid collisions with obstacles and emergency braking. However, during the system control of the vehicle, there are many obstacles that intrude into the vehicle's running trajectory due to inaccurate obstacle detection, resulting in emergency braking of the vehicle, which seriously affects the user experience. Summary of the invention

[0003] In view of the above problems, the present application proposes a method, device and vehicle for determining the location information of an obstacle to improve the above problems.

[0004] In a first aspect, the present application provides a method for determining the location information of an obstacle, the method comprising: obtaining a first detection result of a vehicle's ultrasonic sensor for the obstacle and a second detection result of the vehicle's visual sensor for the obstacle, the first detection result and the second detection result respectively including the obstacle location information detected by the ultrasonic sensor and the obstacle location information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtaining a movement trend of the obstacle relative to the vehicle; adjusting the second detection result according to the movement trend to obtain the location information of the obstacle.

[0005] In a second aspect, the present application provides a device for determining the position information of an obstacle, the device comprising: an obstacle detection module, used to obtain a first detection result of a vehicle's ultrasonic sensor for an obstacle and a second detection result of a vehicle's visual sensor for the obstacle, the first detection result and the second detection result respectively including the obstacle position information detected by the ultrasonic sensor and the obstacle position information detected by the visual sensor; an obstacle detection error acquisition module, used to obtain an error parameter between the first detection result and the second detection result; a movement trend acquisition module, used to obtain the movement trend of the obstacle relative to the vehicle if the error parameter is greater than or equal to a preset threshold; an obstacle position information determination module, used to adjust the second detection result according to the movement trend to obtain the position information of the obstacle.

[0006] In a third aspect, the present application provides a vehicle comprising one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above-mentioned method.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, in which program code is stored, wherein the above method is executed when the program code is run.

[0008] In a fifth aspect, the present application provides a computer program product, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0009] The present application provides a method, device, vehicle and storage medium for determining the location information of an obstacle. The method obtains a first detection result of the vehicle's ultrasonic sensor for the obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include the obstacle location information detected by the ultrasonic sensor and the obstacle location information detected by the visual sensor; then obtains the error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtains the movement trend of the obstacle relative to the vehicle; then adjusts the second detection result according to the movement trend to obtain the location information of the obstacle. In the case where there are large differences in different detection results for the same obstacle, the method can derive a more accurate obstacle location by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the vehicle's drivable space and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flow chart of a method for determining location information of an obstacle proposed in an embodiment of the present application is shown.

[0012] Figure 2 An example diagram of detection results of a first detection frame and a second detection frame provided in an embodiment of the present application is shown.

[0013] Figure 3A flow chart of a method for determining location information of an obstacle proposed in another embodiment of the present application is shown.

[0014] Figure 4 An example diagram of a process for correcting the position of a first detection frame provided in an embodiment of the present application is shown.

[0015] Figure 5 Another example diagram of a process for correcting the position of a first detection frame provided in an embodiment of the present application is shown.

[0016] Figure 6 A flow chart of a method for determining location information of an obstacle proposed in yet another embodiment of the present application is shown.

[0017] Figure 7 A structural block diagram of a device for determining location information of an obstacle proposed in an embodiment of the present application is shown.

[0018] Figure 8 A structural block diagram of a vehicle proposed in this application is shown. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] In an embodiment of the present application, the inventor proposes a method, device and vehicle for determining the location information of an obstacle, by obtaining a first detection result of the vehicle's ultrasonic sensor for the obstacle and a second detection result of the vehicle's visual sensor for the obstacle, the first detection result and the second detection result respectively including the obstacle location information detected by the ultrasonic sensor and the obstacle location information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtaining the movement trend of the obstacle relative to the vehicle; adjusting the second detection result according to the movement trend to obtain the location information of the obstacle. In the case where there are large differences in different detection results for the same obstacle, this method can deduce a more accurate obstacle location by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the vehicle's drivable space and improving the user experience.

[0021] See also Figure 1, a method for determining the position information of an obstacle provided in an embodiment of the present application, the method for determining the position information of the obstacle can be applied to the intelligent parking scene of the vehicle, specifically, it can be used in the automatic parking and memory parking perception links of the vehicle. The method includes:

[0022] Step S110: Obtain a first detection result of the vehicle's ultrasonic sensor for an obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor.

[0023] In the implementation manner of the present application, a vehicle in a parking scenario can synchronously collect obstacle location information through an ultrasonic radar sensor and a visual camera installed in the vehicle, and then jointly plan the vehicle's parking path based on the obstacle location information respectively collected by the two, so as to improve the accuracy of parking path planning.

[0024] For ease of description, as an implementation, the detection result of the vehicle's ultrasonic (radar) sensor for an obstacle can be used as the first detection result, and the detection result of the vehicle's visual sensor (visual camera) for the obstacle can be used as the second detection result. The first detection result includes the obstacle position information detected by the ultrasonic sensor, and the second detection result includes the obstacle position information detected by the visual sensor. It should be noted that the first detection result and the second detection result in this implementation are obtained by detecting the same obstacle.

[0025] Optionally, ultrasonic radar sensors can be arranged on the left and right sides of the vehicle, and visual cameras (visual sensors) can be arranged on the front and rear sides of the vehicle; or ultrasonic radar sensors can be arranged on the front and rear sides of the vehicle, and visual cameras can be arranged on the left and right sides of the vehicle; or ultrasonic radar sensors and visual cameras can be arranged on the front and rear sides and on the left and right sides of the vehicle. The specific number and arrangement positions of ultrasonic radar sensors, as well as the specific number and arrangement positions of visual cameras can be set according to actual needs and are not limited here.

[0026] In the implementation manner of the present application, the first detection result includes a first detection frame representing the obstacle, and the second detection result includes a second detection frame representing the obstacle.

[0027] Optionally, the shapes of the first detection frame and the second detection frame may not be limited. In some embodiments, the shape of the first detection frame may be the same as the shape of the second detection frame, for example, the first detection frame and the second detection frame may both be "trapezoidal" in shape. In some other embodiments, the shape of the first detection frame may be different from the shape of the second detection frame. It is understandable that since there are multiple visual cameras, the second detection frame is a synthesis (or splicing) of the shooting results of multiple visual cameras, resulting in the shape of the second detection frame may be irregular, thereby making the shape of the second detection frame different from the shape of the first detection frame.

[0028] It is worth noting that, when the shape of the first detection frame is the same as the shape of the second detection frame, the shape of the first detection frame and the shape of the second detection frame may not be completely the same, but may be substantially the same. For example, when the similarity between the shape of the first detection frame and the shape of the second detection frame is greater than a specified threshold, it can be considered that the shape of the first detection frame is the same as the shape of the second detection frame. At this time, the specific value of the specified threshold may not be limited, for example, the specified threshold may be 90%, 95%, or other values.

[0029] As an implementation mode, when it is detected that the vehicle enters automatic parking or parking task, the first detection result of the vehicle's ultrasonic sensor for the obstacle and the second detection result of the vehicle's visual sensor for the obstacle can be obtained, so as to timely adjust the parking path according to the location information of the obstacle to improve the accuracy and reliability of parking.

[0030] Step S120: Obtain an error parameter between the first detection result and the second detection result.

[0031] During the vehicle parking process, since the detection accuracy of the ultrasonic radar sensor is different from that of the visual camera, the detection range of the ultrasonic radar sensor is different from that of the visual camera, and both the ultrasonic radar sensor and the visual camera inevitably have detection blind spots, there is inevitably a detection error between the second detection result obtained by the visual camera and the first detection result obtained by the ultrasonic radar sensor. In order to be able to more accurately control the vehicle parking later, the error parameter between the first detection result and the second detection result can be obtained at this time to correct the obstacle position detection result according to the error parameter.

[0032] In a specific application scenario, see Figure 2 , shows an example diagram of the first detection result and the second detection result provided by the embodiment of the present application. Figure 2As shown, the rectangle represents the outline of the vehicle, the x-axis is the direction of vehicle movement, L_v2s represents the second detection result, L_u2s represents the first detection result, and the maximum angle between the first detection result and the second detection result is FOV. In this way, the error parameter (D) between the first detection result and the second detection result can be expressed as:

[0033] D=|L_u2s-L_v2s|

[0034] Step S130: If the error parameter is greater than or equal to a preset threshold, the movement trend of the obstacle relative to the vehicle is obtained.

[0035] As an implementation mode, if the error parameter is greater than or equal to the preset threshold, it means that the error between the first detection frame and the second detection frame is large. In order to accurately determine the parking path of the vehicle, the movement trend of the obstacle relative to the vehicle can be obtained, so as to determine the deviation correction method for the position of the obstacle according to the movement trend. Different movement trends correspond to different obstacle position deviation correction methods. Among them, the specific value of the preset threshold can be set or adjusted according to actual needs and is not limited here.

[0036] Step S140: adjusting the second detection result according to the movement trend to obtain the position information of the obstacle.

[0037] In the process of detecting the position of the obstacle, since there are multiple visual cameras and the second detection result is spliced ​​by the detection results of multiple visual cameras, specifically, the visual camera will output a frame with a shape similar to track (trace, trajectory) according to the detection results of multiple cameras (the frame can be regarded as the second detection result), and the coordinates of the track sometimes have a certain offset, while the detection results of the ultrasonic radar sensor are relatively calibrated. Therefore, the detection result of the ultrasonic radar sensor (i.e., the first detection result) can be retained, and the detection result of the visual camera (i.e., the second detection result) can be corrected.

[0038] Therefore, as an implementation method, when the movement trend of the obstacle relative to the vehicle is determined, the second detection result can be directly adjusted according to the movement trend of the obstacle relative to the vehicle to obtain the position information of the obstacle. By adjusting the second detection result, the drivable space of the vehicle can be increased.

[0039] The present embodiment provides a method for determining the location information of an obstacle, by obtaining a first detection result of the vehicle's ultrasonic sensor for the obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include the obstacle location information detected by the ultrasonic sensor and the obstacle location information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtaining the movement trend of the obstacle relative to the vehicle; adjusting the second detection result according to the movement trend to obtain the location information of the obstacle. In the case where there are large differences in different detection results for the same obstacle, this method can derive a more accurate obstacle location by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the vehicle's drivable space and improving the user experience.

[0040] See also Figure 3 , is a method for determining the location information of an obstacle provided by another embodiment of the present application, the method comprising:

[0041] Step S210: Obtain a first detection result of the vehicle's ultrasonic sensor for an obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor.

[0042] The specific implementation of step S210 may refer to the relevant description of step S110 in the aforementioned embodiment, which will not be repeated here.

[0043] Step S220: Obtain an error parameter between the first detection result and the second detection result.

[0044] The specific implementation of step S220 may refer to the relevant description of step S120 in the aforementioned embodiment, which will not be repeated here.

[0045] Step S230: If the error parameter is greater than or equal to a preset threshold, the movement trend of the obstacle relative to the vehicle is obtained.

[0046] The specific implementation of step S230 may refer to the relevant description of step S130 in the aforementioned embodiment, which will not be repeated here.

[0047] Step S241: If the moving trend is stationary, move the obstacle position in the second detection result to the position where the obstacle is located in the first detection result.

[0048] In the implementation manner of the present application, the movement trend of the obstacle relative to the vehicle includes stationary and moving. Here, stationary can be understood as the obstacle being stationary relative to the vehicle, and moving can be understood as the obstacle having a movement trend relative to the vehicle.

[0049] As an implementation method, if the obstacle is stationary relative to the movement trend of the vehicle, the obstacle position in the second detection result can be moved to the position of the obstacle in the first detection result to correct the second detection result. Specifically, the second detection frame can be directly moved to the position of the first detection frame to correct the position of the second detection frame.

[0050] As a specific implementation, please refer to Figure 4 , shows an example diagram of the process of correcting the position of the second detection frame provided by an embodiment of the present application. Figure 4 As shown on the left, it shows an example of the location of the original obstacle (i.e., the second detection frame). Figure 4 The position of the obstacle after extrapolation shown in the right figure represents the position of the first detection frame. In the process of correcting the position of the second detection frame, the second detection frame can be directly changed from Figure 4 The original obstacle position shown on the left is extrapolated to Figure 4 The right side of the figure shows the location of the obstacle after extrapolation. In this case, the extrapolated distance is equal to the distance between the first detection frame and the second detection frame, that is, Figure 4 The spacing between the two "trapezoides" shown on the right.

[0051] Optional, Figure 4 The black dot shown on the left of the figure represents the aiming point of the obstacle (i.e., the second detection frame). The direction of the Uss distance represents the direction from the sensor of the vehicle body to the aiming point of the obstacle. When the second detection frame is extrapolated, it can be extrapolated in the direction of the Uss distance.

[0052] Step S242: If the movement trend is movement and the error parameter is less than a first threshold, a reference vector is obtained based on the movement direction of the obstacle and the distance vector between the first detection result and the second detection result, and the second detection result is adjusted according to the reference vector, and the first threshold is greater than a preset threshold.

[0053] As another implementation, if the obstacle tends to move relative to the vehicle and the error parameter is less than a first threshold, a reference vector can be obtained based on the moving direction of the obstacle and the distance vector between the first detection result and the second detection result, and the second detection result can be adjusted according to the reference vector, wherein the first threshold is greater than a preset threshold.

[0054] Among them, obtaining a reference vector based on the moving direction of the obstacle and the distance vector between the first detection result and the second detection result can specifically include: obtaining the moving time, moving speed and moving direction of the obstacle; determining the moving vector based on the moving time, moving speed and moving direction of the obstacle; determining the reference vector based on the moving vector and the distance vector between the first detection result and the second detection result.

[0055] It can be understood that the moving direction, moving speed and moving time of the obstacle can all be detected, and thus the moving vector of the obstacle can be obtained based on these parameters, and each identical position point will include a first detection result and a second detection result, and thus the distance and direction between the two can be determined based on the first detection result and the second detection result, and the distance vector between the first detection result and the second detection result can be obtained. In this way, the moving vector of the obstacle and the distance vector between (the first detection result and the second detection result) can be vector synthesized according to mathematical rules to obtain a reference vector.

[0056] In this implementation, the reference vector includes a reference direction and a reference distance. In combination with the description of the foregoing embodiment, the second detection result includes a second detection frame representing an obstacle, and in the process of adjusting the second detection result according to the reference vector, the second detection frame can be controlled to move the reference distance along the reference direction to control the obstacle to leave the drivable space where the vehicle is located, thereby increasing the drivable space of the vehicle.

[0057] In a specific application scenario, see Figure 5 , shows an example diagram of the process of correcting the position of the second detection frame provided in an embodiment of the present application. Figure 5 The "trapezoid" shown on the left of the figure represents the second detection frame. Figure 5 The left trapezoid shown in the right figure represents the second detection frame. Figure 5 The right trapezoid in the figure shows the second detection frame after position correction. Figure 5 As shown in the figure above, the motion (movement) vector (v) of the obstacle and the distance vector between the two detection frames can be used to perform vector synthesis to obtain a reference vector, and then the second detection frame can be controlled to move a corresponding distance in the direction of the reference vector, thereby correcting the position of the second detection frame.

[0058] In the implementation mode of the present application, if the error parameter between the first detection result and the second detection result is less than the preset threshold, it indicates that the difference between the first detection result and the second detection result is small, and the first detection result can overlap with the second detection result. Then, as a way, the position information of the obstacle can be determined as the first detection result or the second detection result. In this way, the position error of the obstacle can be ignored and the normal parking process can continue.

[0059] The present embodiment provides a method for determining the position information of an obstacle, by obtaining a first detection result of an ultrasonic sensor of a vehicle for an obstacle and a second detection result of a visual sensor of the vehicle for the obstacle, wherein the first detection result and the second detection result respectively include the obstacle position information detected by the ultrasonic sensor and the obstacle position information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtaining the movement trend of the obstacle relative to the vehicle; if the movement trend is stationary, moving the obstacle position in the second detection result to the position of the obstacle in the first detection result; if the movement trend is moving, obtaining a reference vector based on the movement direction of the obstacle and the distance vector between the first detection result and the second detection result, and adjusting the second detection result according to the reference vector. In the case where there are large differences in different detection results for the same obstacle, the present method can derive a more accurate obstacle position by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the drivable space of the vehicle and improving the user experience.

[0060] At the same time, by distinguishing the movement trend of the obstacle relative to the vehicle and then making targeted position corrections to the second detection result, the accuracy of obstacle position detection can be further ensured, thereby improving the accuracy and reliability of parking control and optimizing driving smoothness.

[0061] See also Figure 6 , is a method for determining the location information of an obstacle provided by another embodiment of the present application, the method comprising:

[0062] Step S310: Obtain a first detection result of the vehicle's ultrasonic sensor for an obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor.

[0063] The specific implementation of step S310 may refer to the relevant description of step S110 in the aforementioned embodiment, which will not be repeated here.

[0064] Step S320: Obtain an error parameter between the first detection result and the second detection result.

[0065] The specific implementation of step S320 may refer to the relevant description of step S120 in the aforementioned embodiment, which will not be repeated here.

[0066] Step S331: If the error parameter is less than a preset threshold, determine that the location information of the obstacle is the first detection result or the second detection result.

[0067] The specific implementation of step S331 may refer to the relevant description of step S242 in the aforementioned embodiment, which will not be repeated here.

[0068] Step S332: If the error parameter is greater than or equal to a preset threshold, the movement trend of the obstacle relative to the vehicle is obtained.

[0069] The specific implementation of step S332 may refer to the relevant description of step S130 in the aforementioned embodiment, which will not be repeated here.

[0070] Step S341: If the moving trend is stationary, move the obstacle position in the second detection result to the position where the obstacle is located in the first detection result.

[0071] The specific implementation of step S341 may refer to the relevant description of step S241 in the aforementioned embodiment, which will not be repeated here.

[0072] Step S342: If the movement trend is movement and the error parameter is greater than a second threshold, the second detection frame is moved along the rear axis of the vehicle body in a direction away from the vehicle, and the second threshold is greater than the first threshold.

[0073] In an embodiment of the present application, if the error parameter between the first detection result and the second detection result is greater than or equal to a preset threshold value, in order to more accurately correct the position of the obstacle, the numerical value of the error parameter can be distinguished, and the numerical value can characterize the degree of difference between the first detection result and the second detection result. The larger the numerical value, the greater the difference between the two, and the smaller the numerical value, the smaller the difference between the two. Different degrees of correction can be determined according to different numerical values.

[0074] As a method, if the movement trend is movement and the error parameter is less than a first threshold (the first threshold is greater than a preset threshold), the reference vector can be directly obtained based on the movement direction of the obstacle and the distance vector between the first detection result and the second detection result as described in the above embodiment, and the second detection result can be adjusted according to the reference vector; and if the movement trend is movement and the error parameter is greater than the second threshold (the second threshold is greater than the first threshold, assuming that the value of the second threshold is greater than or much greater than the first threshold), the second detection frame can be directly controlled to move along the rear axis of the vehicle body in the direction away from the vehicle. The moving distance can be unlimited and can be a specific value or a range of values ​​to maximize the vehicle's drivable space.

[0075] Among them, the degree of correction of the second detection frame when the error parameter is greater than the second threshold is greater than the degree of correction of the second detection frame when the error parameter is less than the first threshold.

[0076] The present embodiment provides a method for determining the position information of an obstacle, by obtaining a first detection result of an ultrasonic sensor of a vehicle for an obstacle and a second detection result of a visual sensor of the vehicle for the obstacle, wherein the first detection result and the second detection result respectively include the obstacle position information detected by the ultrasonic sensor and the obstacle position information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is less than a preset threshold, determining that the position information of the obstacle is the first detection result or the second detection result; if the error parameter is greater than or equal to the preset threshold, obtaining the movement trend of the obstacle relative to the vehicle; if the movement trend is stationary, moving the obstacle position in the second detection result to the position of the obstacle in the first detection result; if the movement trend is moving and the error parameter is greater than a second threshold, moving the second detection frame away from the vehicle along the rear axis of the vehicle body, and the second threshold is greater than the first threshold. In the case where there are large differences in different detection results for the same obstacle, the method can derive a more accurate obstacle position by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the drivable space of the vehicle and improving the user experience.

[0077] By determining the degree of correction for the position of the second detection frame based on the numerical value of the error parameter between the first detection result and the second detection result, a more flexible and intelligent correction of the position of the obstacle can be achieved to avoid vehicle stalling during parking, thereby enhancing the user's physical sensation.

[0078] See also Figure 7The present application provides an obstacle location information determination device 400, the obstacle location information determination device 400 comprising:

[0079] The obstacle detection module 410 is used to obtain a first detection result of the vehicle's ultrasonic sensor for an obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor.

[0080] The obstacle detection error acquisition module 420 is used to obtain an error parameter between the first detection result and the second detection result.

[0081] The movement trend acquisition module 430 is used to acquire the movement trend of the obstacle relative to the vehicle if the error parameter is greater than or equal to a preset threshold.

[0082] The obstacle position information determination module 440 is used to adjust the second detection result according to the movement trend to obtain the position information of the obstacle.

[0083] The movement trend in the implementation manner of the present application includes stationary and moving. The obstacle position information determination module 440 can be specifically used to move the obstacle position in the second detection result to the position of the obstacle in the first detection result if the movement trend is stationary; if the movement trend is moving and the error parameter is less than a first threshold, obtain a reference vector based on the moving direction of the obstacle and the distance vector between the first detection result and the second detection result, and adjust the second detection result according to the reference vector, and the first threshold is greater than a preset threshold.

[0084] Among them, obtaining the reference vector based on the moving direction of the obstacle and the distance vector between the first detection result and the second detection result may include: obtaining the moving time, moving speed and moving direction of the obstacle; determining the moving vector based on the moving time, moving speed and moving direction of the obstacle; determining the reference vector based on the moving vector and the distance vector between the first detection result and the second detection result.

[0085] The reference vector may include a reference direction and a reference distance, and the second detection result may include a second detection frame representing the obstacle. As an implementation, adjusting the second detection result according to the reference vector may include: moving the second detection frame along the reference direction by the reference distance.

[0086] As an embodiment, the obstacle position information determination module 440 can also be specifically used to move the second detection frame along the rear axis of the vehicle body away from the vehicle if the moving trend is moving and the error parameter is greater than a second threshold, and the second threshold is greater than the first threshold.

[0087] In the implementation manner of the present application, if the error parameter is less than a preset threshold, the first detection result may coincide with the second detection result, and at this time the location information of the obstacle may be directly determined as the first detection result or the second detection result.

[0088] The following will be combined Figure 8 A vehicle provided in the present application is described.

[0089] See also Figure 8 Based on the above-mentioned method and device for determining the position information of an obstacle, the embodiment of the present application also provides another vehicle 100 that can execute the above-mentioned method for determining the position information of an obstacle. The vehicle 100 includes one or more (only one is shown in the figure) processors 102, a memory 104, and a data acquisition module 106 that are coupled to each other. Among them, the memory 104 stores a program that can execute the content of the above-mentioned embodiment, and the processor 102 can execute the program stored in the memory 104.

[0090] Among them, the processor 102 may include one or more processing cores. The processor 102 uses various interfaces and lines to connect various parts in the entire vehicle 100, and executes various functions and processes data of the vehicle 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 104, and calling data stored in the memory 104. Optionally, the processor 102 can be implemented in at least one hardware form of a network processor (Neural network Processing Unit, NPU), a digital signal processing (Digital Signal Processing, DSP), a field programmable gate array (Field-Programmable Gate Array, FPGA), and a programmable logic array (Programmable Logic Array, PLA). The processor 102 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a network processor (Neural network Processing Unit, NPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; the NPU is responsible for processing multimedia data such as video and images; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 102, but may be implemented separately through a communication chip.

[0091] The memory 104 may include a random access memory (RAM) or a read-only memory (ROM). The memory 104 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 104 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created by the vehicle 100 during use (such as a phone book, audio and video data, chat record data), etc.

[0092] The data acquisition module 106 can be used to obtain the driving status information of the vehicle 100. The data acquisition module 106 can be a laser radar, a camera, a sensor, a GPS (Global Positioning System) navigation, etc.

[0093] An embodiment of the present application provides a computer-readable storage medium in which a program code is stored, and the program code can be called by a processor to execute the method described in the above method embodiment.

[0094] The computer readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium includes a non-transitory computer-readable storage medium. The computer readable storage medium has storage space for program codes that execute any of the method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code can be compressed, for example, in an appropriate form.

[0095] In summary, the present application provides a method, device and vehicle for determining the location information of an obstacle, by obtaining a first detection result of the vehicle's ultrasonic sensor for the obstacle and a second detection result of the vehicle's visual sensor for the obstacle, wherein the first detection result and the second detection result respectively include the obstacle location information detected by the ultrasonic sensor and the obstacle location information detected by the visual sensor; obtaining an error parameter between the first detection result and the second detection result; if the error parameter is greater than or equal to a preset threshold, obtaining the movement trend of the obstacle relative to the vehicle; adjusting the second detection result according to the movement trend to obtain the location information of the obstacle. In the case where there are large differences in different detection results for the same obstacle, this method can derive a more accurate obstacle location by obtaining the movement trend of the obstacle and determining the adjustment method for the obstacle detection result according to the movement trend of the obstacle, thereby increasing the vehicle's drivable space and improving the user experience.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining the position information of an obstacle, characterized in that: The method comprises: Obtaining a first detection result of an ultrasonic sensor of the vehicle for an obstacle and a second detection result of a visual sensor of the vehicle for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor; Obtaining an error parameter between the first detection result and the second detection result; If the error parameter is greater than or equal to a preset threshold, obtaining a movement trend of the obstacle relative to the vehicle; The second detection result is adjusted according to the movement trend to obtain the position information of the obstacle.

2. The method according to claim 1, characterized in that: The movement trend includes stationary and moving, and the adjusting the second detection result according to the movement trend includes: If the movement trend is stationary, move the obstacle position in the second detection result to the position where the obstacle is located in the first detection result; If the movement trend is movement and the error parameter is less than a first threshold, a reference vector is obtained based on the movement direction of the obstacle and the distance vector between the first detection result and the second detection result, and the second detection result is adjusted according to the reference vector, and the first threshold is greater than a preset threshold.

3. The method according to claim 2, characterized in that The acquiring a reference vector based on the moving direction of the obstacle and the distance vector between the first detection result and the second detection result includes: Obtaining the moving time, moving speed and moving direction of the obstacle; Determine a movement vector based on the movement time, movement speed and movement direction of the obstacle; A reference vector is determined based on the movement vector and a distance vector between the first detection result and the second detection result.

4. The method according to claim 2, characterized in that: The reference vector includes a reference direction and a reference distance, the second detection result includes a second detection frame representing the obstacle, and the adjusting the second detection result according to the reference vector includes: The second detection frame is moved along the reference direction by the reference distance.

5. The method according to claim 2, characterized in that: The second detection result includes a second detection frame representing the obstacle, and the method further includes: If the movement trend is movement and the error parameter is greater than a second threshold, the second detection frame is moved along the rear axis of the vehicle body in a direction away from the vehicle, and the second threshold is greater than the first threshold.

6. The method according to claim 1, characterized in that The method further comprises: If the error parameter is less than a preset threshold, the position information of the obstacle is determined to be the first detection result or the second detection result.

7. A device for determining the position information of an obstacle, characterized in that: The device comprises: An obstacle detection module, used to obtain a first detection result of an ultrasonic sensor of a vehicle for an obstacle and a second detection result of a visual sensor of the vehicle for the obstacle, wherein the first detection result and the second detection result respectively include obstacle position information detected by the ultrasonic sensor and obstacle position information detected by the visual sensor; An obstacle detection error acquisition module, used to obtain an error parameter between the first detection result and the second detection result; A movement trend acquisition module, configured to acquire a movement trend of the obstacle relative to the vehicle if the error parameter is greater than or equal to a preset threshold; The obstacle position information determination module is used to adjust the second detection result according to the movement trend to obtain the position information of the obstacle.

8. A vehicle, characterized in that: including one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, wherein when the program code is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of any method described in claims 1-6 are implemented.

Images