Ultrasonic obstacle height detection method, system and equipment based on dynamic geometric modeling and medium

Abstract

The invention relates to an ultrasonic obstacle height detection method, system and device based on dynamic geometric modeling and a medium. The method comprises the following steps: acquiring an obstacle distance sequence and a vehicle odometer coordinate sequence of an ultrasonic radar at continuous time sequence points, combining an installation height fixed value of the ultrasonic radar, constructing a planar triangular model, calculating an included angle cosine value by utilizing a cosine law, converting a vertical height difference, and finally calculating the actual height of an obstacle reflection point. According to the method, through dynamic geometric modeling, the obstacle height detection precision of the ultrasonic radar in the dynamic driving process of the vehicle is improved, the recognition capability on low obstacles and complex scenes is enhanced, meanwhile, the system cost and complexity are reduced, and the system reliability is improved. And the application value and the popularization feasibility of the ultrasonic radar in middle and low-end vehicles and low-cost perception scenes are improved.

Description

Technical Field

[0001] This invention belongs to the field of vehicle safety perception technology, and in particular relates to a method, system, device and medium for ultrasonic obstacle height detection based on dynamic geometric modeling. Background Technology

[0002] Ultrasonic radar, due to its low cost, strong resistance to environmental interference, and high short-range detection accuracy, has been widely used in obstacle detection in autonomous driving and assisted driving systems. Existing ultrasonic radar-based detection solutions can typically acquire basic information such as obstacle distance and orientation, providing data support for vehicle obstacle avoidance and parking functions. However, existing obstacle height detection technologies still have significant shortcomings in meeting the critical requirement of obstacle height detection. For example, most solutions rely on ultrasonic detection data from a single time point, combined with the fixed installation angle of the ultrasonic radar, to estimate the height. This type of method does not fully consider the impact of displacement changes during vehicle dynamics on the detection distance. When the vehicle is moving, single-moment detection data cannot establish a stable spatial geometric relationship between the obstacle and the radar, easily leading to low height detection accuracy due to perspective shifts and distance measurement deviations, making it difficult to meet the precise identification requirements for special scenarios such as low-lying obstacles and protruding obstacles. In addition, another part of the high-precision height detection solution relies on multi-sensor fusion technology of lidar, visual sensors and ultrasonic radar. Although it can improve detection accuracy, it significantly increases the system hardware cost and data processing complexity, which is not conducive to its promotion and application in low-end and mid-range vehicles and low-cost perception scenarios. Summary of the Invention

[0003] Therefore, it is necessary to provide ultrasonic obstacle height detection methods, systems, devices, and media based on dynamic geometric modeling to address the aforementioned technical problems. The aim is to improve the accuracy of obstacle height detection, enhance the recognition capability in dynamic driving scenarios and special obstacle scenarios, reduce system hardware costs and data processing complexity, and improve the application value and feasibility of ultrasonic radar in low-end vehicles and low-cost perception scenarios.

[0004] In a first aspect, this application provides a method for detecting the height of ultrasonic obstacles based on dynamic geometric modeling, including:

[0005] S1: Collect the obstacle distance sequence detected by ultrasonic radar at continuous time points; based on the vehicle positioning system, synchronously collect the vehicle odometer coordinate sequence at the corresponding time points of the continuous time points, and call the pre-stored fixed value of ultrasonic radar installation height.

[0006] S2: Based on the vehicle odometer coordinate sequence, select any two consecutive time points as the first time point and the second time point, perform difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement.

[0007] S3: Extract the first obstacle distance value corresponding to the first time step and the second obstacle distance value corresponding to the second time step from the obstacle distance sequence; construct a planar triangle model based on the vehicle displacement, the first obstacle distance value, and the second obstacle distance value, where the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value, and the length of the second side is the second obstacle distance value;

[0008] S4: Based on the planar triangle model, the cosine value of the included angle is calculated using the law of cosines to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle at the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane.

[0009] S5: Based on the fixed installation height of the ultrasonic radar and the vertical height difference, the actual height is calculated to obtain the actual height of the obstacle reflection point from the ground.

[0010] In one embodiment, a planar triangle model is constructed based on the vehicle displacement, the distance value of a first obstacle, and the distance value of a second obstacle, including:

[0011] The radar position at the first moment is defined as the first vertex, the radar position at the second moment is defined as the second vertex, and the obstacle reflection point is defined as the third vertex.

[0012] The vehicle displacement is assigned the side length between the first and second vertices, the first obstacle distance is assigned the side length between the first and third vertices, and the second obstacle distance is assigned the side length between the second and third vertices, thus constructing a planar triangle model.

[0013] In one embodiment, based on a planar triangle model, the cosine value of the included angle is calculated using the law of cosines to obtain the cosine value of the included angle between the first side and the base of the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle at the first moment, a vertical height difference conversion is performed to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane, including:

[0014] Extract the base length, first side length, and second side length from the planar triangle model;

[0015] Based on the lengths of the base, the first side, and the second side, the cosine of the angle between the first side and the base is calculated using the Law of Cosines. The cosine of the angle is obtained using the following formula:

[0016]

[0017] in, for The angle between the first side and the bottom side at any given moment. This is the length of the base, which is the length of the side between the first vertex A and the second vertex B. This refers to the length of the first side, which is the side length between the first vertex A and the third vertex C. This is the length of the second side, that is, the side length between the second vertex B and the third vertex C;

[0018] Based on the cosine of the included angle and the distance to the first obstacle, the vertical height difference is calculated to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane; the vertical height difference is calculated using the following formula:

[0019]

[0020] in, This represents the vertical height difference.

[0021] In one embodiment, the actual height is calculated using the following formula:

[0022]

[0023] in, This is the actual height. The installation height of the ultrasonic radar is fixed.

[0024] In one embodiment, the method further includes:

[0025] Take the next time point of the adjacent second time point in the continuous time series as the new second time point, and take the second time point as the new first time point to form a new time series detection group;

[0026] Based on the vehicle odometer coordinates and obstacle distance sequence corresponding to the new time-series detection group, repeat steps S2 to S5 to obtain the new actual height of the obstacle reflection point from the ground.

[0027] The new actual height and the actual height are integrated in chronological order to generate a dynamic update sequence of obstacle height.

[0028] Secondly, this application also provides an ultrasonic obstacle height detection system based on dynamic geometric modeling, including:

[0029] The data acquisition and initialization module is used to acquire the obstacle distance sequence detected by the ultrasonic radar at continuous time points; based on the vehicle positioning system, it synchronously acquires the vehicle odometer coordinate sequence at corresponding times of continuous time points, and calls the pre-stored fixed value of ultrasonic radar installation height.

[0030] The vehicle displacement calculation module is used to select any two consecutive time points as the first time point and the second time point based on the vehicle odometer coordinate sequence, and perform difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement.

[0031] The triangle model construction module is used to extract the first obstacle distance value corresponding to the first time step and the second obstacle distance value corresponding to the second time step from the obstacle distance sequence; based on the vehicle displacement, the first obstacle distance value, and the second obstacle distance value, a planar triangle model is constructed, wherein the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value, and the length of the second side is the second obstacle distance value;

[0032] The height difference calculation module is used to calculate the cosine value of the included angle based on the planar triangle model using the law of cosines, so as to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle at the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane.

[0033] The obstacle actual height calculation module is used to calculate the actual height of the obstacle reflection point from the ground based on the fixed value of the ultrasonic radar installation height and the vertical height difference.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the first aspect.

[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the first aspect.

[0036] The aforementioned ultrasonic obstacle height detection method, system, equipment, and medium based on dynamic geometric modeling first lays the data foundation for subsequent geometric modeling and height calculation by collecting continuous time-series distance sequences from ultrasonic radar, synchronizing vehicle odometer coordinate sequences, and calling fixed values ​​for radar installation height. Secondly, by calculating vehicle displacement at consecutive time intervals and combining this with the obstacle distance values ​​at corresponding times, a planar triangle model is constructed. This avoids the shortcomings of existing obstacle height detection methods that rely on single-moment data and cannot adapt to dynamic vehicle driving scenarios, establishing a stable spatial geometric relationship between the obstacle and the radar to improve the scenario adaptability of detection. Furthermore, based on the triangle model, the cosine value of the included angle is calculated using the law of cosines, then converted into the vertical height difference and the actual height is calculated. This eliminates the need for multi-sensor fusion, solving the problems of high hardware cost and high processing complexity of existing high-precision solutions, and ensuring detection accuracy at a low cost. This method, through the combination of dynamic time-series data and geometric modeling, achieves real-time and accurate detection of obstacle height during dynamic vehicle driving, effectively improving safety perception capabilities in low-cost perception scenarios. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart of an ultrasonic obstacle height detection method based on dynamic geometric modeling, provided as an exemplary embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a planar triangular model structure is provided for an exemplary embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of an ultrasonic obstacle height detection system based on dynamic geometric modeling, provided as an exemplary embodiment of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0042] In one embodiment, such as Figure 1As shown, an ultrasonic obstacle height detection method based on dynamic geometric modeling is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0043] S101: Collect obstacle distance sequences detected by ultrasonic radar at continuous time points; based on the vehicle positioning system, synchronously collect vehicle odometer coordinate sequences at corresponding times of continuous time points, and call the pre-stored fixed value of ultrasonic radar installation height.

[0044] Specifically, the hardware operating environment of this embodiment may include an onboard main control unit, an ultrasonic radar module, a photoelectric vehicle odometer, and a temperature sensor (for ultrasonic propagation speed compensation), etc. Each module can communicate with the main control unit via a CAN bus. Illustratively, the main control unit can send a start command to the ultrasonic radar module via the CAN bus, controlling the radar to continuously detect obstacles ahead at a sampling frequency of 10Hz. The radar module can achieve ranging based on the time-of-flight (ToF) principle, that is, by emitting amplitude-modulated pulses, receiving the echo signal reflected by the obstacle, first removing electromagnetic interference through bandpass filtering, and then converting the analog signal into a digital signal through low-noise amplifier and 16-bit ADC sampling. Simultaneously, it can also read real-time data from the temperature sensor, such as an ambient temperature of 25℃, and calculate the ultrasonic propagation speed v according to the formula, which can be:

[0045]

[0046] in Substituting 25℃ into the ambient temperature, we get v = 346 m / s. Finally, the distance measurement result is calculated using the flight time. ,in The ultrasonic radar takes the time to travel to and from the sound wave, and it can add a timestamp to each ranging data point before transmitting it to the main control unit, forming a sequence of obstacle distances. For example, during vehicle movement, the ultrasonic radar transmits data at preset frequencies at consecutive time points. , , ,…, It emits ultrasonic signals and receives reflected signals to obtain obstacle distance sequences. , , ,…, Simultaneously, based on vehicle positioning systems such as photoelectric odometers or inertial navigation systems, the vehicle odometer coordinate sequences corresponding to these time points are collected synchronously. , , ,…, If a photoelectric odometer is used, it can calculate the vehicle's real-time position based on wheel speed signals and steering angle, output coordinate values ​​in a Cartesian coordinate system, and add a timestamp of the same format to form a corresponding vehicle odometer coordinate sequence. The main control unit can then synchronize radar distance data and odometer coordinate data through timestamp comparison, ensuring a one-to-one correspondence between the two types of data at the same time point. Furthermore, it can retrieve the pre-stored fixed value h of the ultrasonic radar installation height from the non-volatile storage module of the onboard ultrasonic radar ECU.

[0047] S102: Based on the vehicle odometer coordinate sequence, select any two consecutive time points as the first time point and the second time point, perform difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement.

[0048] Specifically, during vehicle operation, the ultrasonic radar moves synchronously with the vehicle body. The relative displacement of the radar position at two different moments is a key parameter for constructing the base of the planar triangular model. By selecting consecutive time points, the calculation error of the displacement can be minimized, ensuring the rationality of the model's side length ratio. For example, the main control unit can arbitrarily select two adjacent time points from the synchronized odometer coordinate sequence. , This serves as the first and second time points. Since the vehicle displacement is relatively small at adjacent time points, typically within the range of 0.1-1.0m, selecting adjacent points meets the requirements of close-range ultrasonic radar detection and reduces the extreme cases of obtuse or acute angles in the triangle model, thus improving the accuracy of the cosine theorem calculation. Subsequently, a coordinate difference calculation algorithm can be used to calculate the coordinates at the two time points to obtain the vehicle displacement.

[0049] S103: Extract the first obstacle distance value corresponding to the first time step and the second obstacle distance value corresponding to the second time step from the obstacle distance sequence; construct a planar triangle model based on the vehicle displacement, the first obstacle distance value and the second obstacle distance value, wherein the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value and the length of the second side is the second obstacle distance value.

[0050] Specifically, by constructing a triangle based on the spatial relationship between the radar's two time points and the obstacle's reflection point, the dynamic obstacle detection problem can be transformed into a static geometric calculation problem. For example, the main control unit can extract the first time point from the obstacle distance sequence based on timestamp matching rules. The corresponding first obstacle distance value Second moment The corresponding second obstacle distance value This ensures that the distance value strictly corresponds to the odometer coordinate timing selected in this step. Furthermore, it can be based on the first moment. Second moment Corresponding vehicle odometer coordinates and The vehicle displacement is obtained by performing difference calculation. Then, the length of the base of the triangle model can be set as the vehicle displacement. Set the length of the first side as the distance value to the first obstacle. Set the length of the second side as the distance value to the second obstacle. A planar triangle model was constructed.

[0051] S104: Based on the planar triangle model, the cosine value of the included angle is calculated using the cosine theorem to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle corresponding to the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane.

[0052] Specifically, according to the law of cosines, the square of any side of a planar triangle is equal to the sum of the squares of the other two sides minus twice the product of those two sides and the cosine of the included angle. Therefore, based on the planar triangle model constructed using S103, the cosine of the angle between its first side and base can be calculated. Furthermore, since the first side represents the straight-line distance from the radar to the obstacle reflection point at the first moment, the projected length of this distance in the direction perpendicular to the radar mounting plane is the vertical height difference between the obstacle reflection point and the radar mounting plane. Therefore, based on the projection principle of trigonometric functions, and using the cosine of the included angle and the first obstacle distance value corresponding to the first moment, the cosine of the angle can be calculated. The vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane is calculated.

[0053] S105: Based on the fixed installation height of the ultrasonic radar and the vertical height difference, the actual height is calculated to obtain the actual height of the obstacle reflection point from the ground.

[0054] Specifically, the fixed installation height of the ultrasonic radar can be used to convert the relative height difference obtained in S104 into an absolute height value. For example, the main control unit retrieves the pre-stored fixed installation height value h of the ultrasonic radar from the storage module. This value is the vertical distance between the center of the radar emitting surface and the ground surface on which the vehicle is driving. This value is calibrated by a laser rangefinder and written into the ECU before the vehicle leaves the factory, with the standard driving ground surface under no-load conditions as the reference plane during calibration. Since the vertical height difference obtained in S104 is the vertical downward projection height from the ultrasonic radar emitting surface to the obstacle reflection point, that is, the reflection point is located below the radar installation plane (facing the ground), this height difference is calculated from the cosine of the spatial angle between the radar and the obstacle reflection point and the ranging value, reflecting the vertical orientation relationship of the reflection point relative to the radar installation plane. Therefore, the final height above the ground of the obstacle reflection point can be obtained by subtracting the vertical downward projection height of the radar to the reflection point from the radar installation height h (i.e., the total vertical height above the ground).

[0055] The above method first collects obstacle distance sequences and vehicle odometer coordinate sequences from ultrasonic radar at continuous time points, and uses a fixed installation height value for the ultrasonic radar, thus solving the problem that single-moment data cannot construct stable spatial geometric relationships during dynamic vehicle operation. Second, a planar triangle model is constructed based on the vehicle displacement and obstacle distance values. The cosine value of the included angle is calculated using the law of cosines, and the vertical height difference is converted, solving the problem of low height detection accuracy caused by viewpoint offset and distance deviation in existing technologies, and enhancing the ability to identify low obstacles and complex scenes. Finally, the actual height of the obstacle reflection point above the ground can be obtained through actual height calculation.

[0056] In one embodiment, a planar triangle model is constructed based on the vehicle displacement, the distance to a first obstacle, and the distance to a second obstacle, including:

[0057] The radar position at the first moment is defined as the first vertex, the radar position at the second moment is defined as the second vertex, and the obstacle reflection point is defined as the third vertex.

[0058] The vehicle displacement is assigned the side length between the first and second vertices, the first obstacle distance is assigned the side length between the first and third vertices, and the second obstacle distance is assigned the side length between the second and third vertices, thus constructing a planar triangle model.

[0059] Specifically, such as Figure 2 As shown, at the first moment The corresponding radar position is the first vertex A, and the second time step... The corresponding radar position is the second vertex B, and the ultrasonic wave reflection point on the obstacle surface is the third vertex C. Subsequently, the main control unit can obtain the vehicle displacement between consecutive time points from the vehicle's odometer. Let the length be AB, which is the side length between the first vertex A and the second vertex B. The first moment obtained from ultrasonic radar The corresponding first obstacle distance value Assign it the length AC of the side between the first vertex A and the third vertex C, denoted as The second moment obtained from ultrasonic radar Corresponding obstacle distance value Let BC be the length of the side between the second vertex B and the third vertex C, denoted as BC. .and Figure 2 In this context, 'h' represents the fixed installation height of the ultrasonic radar. The underlying principle is that the installation height 'h' remains constant during vehicle operation. Therefore, by defining the vertices and assigning side lengths as described above, a planar triangle model ABC can be constructed.

[0060] Furthermore, when calculating the cosine of the angle between the first side and the base based on the planar triangle model ABC, the main control unit first extracts the side length parameters from the triangle model. , , Then, the built-in mathematical operation module is invoked to perform calculations based on the cosine theorem formula to obtain the first side. With the bottom edge The cosine of the included angle, which is... - First side of the moment With the bottom edge The angle between them is denoted as The corresponding calculation formula is:

[0061]

[0062] Based on the above formula, the angle can be calculated. cosine value of the included angle Subsequently, based on the cosine value of the included angle and the first moment... The corresponding first obstacle distance value To perform vertical height difference calculation, the main control unit can use the principle of trigonometric function projection to calculate the side length between the first vertex A and the third vertex C. Projecting the image onto a direction perpendicular to the radar mounting plane, we obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane, denoted as . The calculation formula is as follows:

[0063]

[0064] in, That is, the distance value to the first obstacle. .

[0065] When finally calculating the actual height, the main control unit can call up the pre-stored fixed value h of the ultrasonic radar installation height, and combine it with the calculated vertical height difference. The actual height of the obstacle's reflection point from the ground is obtained through spatial positional calculations. The calculation formula is as follows:

[0066]

[0067] in, This refers to the actual height.

[0068] In one embodiment, the method further includes:

[0069] Take the next time point of the adjacent second time point in the continuous time series as the new second time point, and take the second time point as the new first time point to form a new time series detection group;

[0070] Based on the vehicle odometer coordinates and obstacle distance sequence corresponding to the new time-series detection group, repeat steps S2 to S5 to obtain the new actual height of the obstacle reflection point from the ground.

[0071] The new actual height and the actual height are integrated in chronological order to generate a dynamic update sequence of obstacle height.

[0072] Specifically, based on the single obstacle height calculation, the main control unit's built-in timing management module and data integration module can further enable dynamic and continuous obstacle height detection to adapt to scenarios where the relative positions of obstacles and radar continuously change during vehicle movement. For example, the main control unit's timing management module maintains a continuous timing point queue, storing currently acquired continuous detection timing points (the timing point interval is consistent with the ultrasonic radar's sampling frequency). After completing the height calculation for a set of timing points (denoted as time i and time i+1), the timing management module can use the timing point corresponding to the original time i+1 as the new first time, and simultaneously select the next timing point immediately adjacent to time i+1 from the real-time acquired timing stream as the new second time, forming a new timing detection group. Furthermore, the timing management module can discard the historical data corresponding to the completed calculation at time i, retaining only the relevant data for the new first and second times, thereby reducing the computational and storage load on the main control unit.

[0073] Furthermore, when calculating the height based on the new time-series detection group, the main control unit can call the pre-loaded displacement calculation module, planar triangle modeling module, included angle cosine value calculation module, and height calculation module. The displacement calculation module calculates the new vehicle displacement based on the new vehicle odometer coordinates corresponding to the first and second time points. The planar triangle modeling module constructs a new planar triangle model based on this displacement, the obstacle distance value corresponding to the new first time point, and the obstacle distance value corresponding to the new second time point. Subsequently, the included angle cosine value calculation module and the height calculation module are called sequentially to calculate the included angle cosine value and vertical height difference based on the new triangle model parameters, ultimately obtaining the actual height of the obstacle reflection point from the ground. After completing the calculation of the new actual height, the main control unit's data integration module can extract the timestamp corresponding to each calculation result, sort and integrate the new actual height with the previously obtained actual heights according to the chronological order of the timestamps, and generate a dynamic update sequence for obstacle height. The sequence is stored in the cache module of the main control unit in real time, and can also be output to the vehicle's driver assistance system via the CAN bus to provide continuous obstacle height data support for the vehicle's real-time obstacle avoidance, path planning and other functions.

[0074] Based on the same inventive concept, this application also provides an ultrasonic obstacle height detection system based on dynamic geometric modeling for implementing the ultrasonic obstacle height detection method based on dynamic geometric modeling described above. The solution provided by this system is similar to the implementation described in the above method. Therefore, the specific limitations of one or more embodiments of the ultrasonic obstacle height detection system based on dynamic geometric modeling provided below can be found in the limitations of the ultrasonic obstacle height detection method based on dynamic geometric modeling described above, and will not be repeated here.

[0075] In one exemplary embodiment, such as Figure 3 As shown, an ultrasonic obstacle height detection system 300 based on dynamic geometric modeling is provided, including:

[0076] The data acquisition and initialization module 301 is used to acquire the obstacle distance sequence detected by the ultrasonic radar at continuous time points; based on the vehicle positioning system, it synchronously acquires the vehicle odometer coordinate sequence at the corresponding time points of the continuous time points, and calls the pre-stored fixed value of the ultrasonic radar installation height.

[0077] The vehicle displacement calculation module 302 is used to select any two consecutive time points as the first time point and the second time point based on the vehicle odometer coordinate sequence, and perform difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement.

[0078] The triangle model construction module 303 is used to extract the first obstacle distance value corresponding to the first time moment and the second obstacle distance value corresponding to the second time moment from the obstacle distance sequence; and to construct a planar triangle model based on the vehicle displacement, the first obstacle distance value and the second obstacle distance value, wherein the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value and the length of the second side is the second obstacle distance value.

[0079] The height difference calculation module 304 is used to calculate the cosine value of the included angle based on the planar triangle model by using the law of cosines, so as to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle at the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane.

[0080] The obstacle actual height calculation module 305 is used to calculate the actual height based on the fixed value of the ultrasonic radar installation height and the vertical height difference, so as to obtain the actual height of the obstacle reflection point from the ground.

[0081] In one exemplary embodiment, the present invention also provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the ultrasonic obstacle height detection method based on dynamic geometric modeling of this application. A multi-core processor is preferred to improve the system's parallel processing capability. The memory provides sufficient temporary storage space to support program execution and data processing. The memory capacity should be large enough to accommodate large amounts of data and computational tasks.

[0082] In one exemplary embodiment, the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the ultrasonic obstacle height detection method based on dynamic geometric modeling of this application. The computer-readable storage medium may include: a read-only memory, a random access memory (RAM), a solid-state drive (SSD), or an optical disc, etc.

[0083] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for detecting the height of ultrasonic obstacles based on dynamic geometric modeling, characterized in that, The method includes: S1: Collect the obstacle distance sequence detected by the ultrasonic radar at continuous time points; based on the vehicle positioning system, synchronously collect the vehicle odometer coordinate sequence at the corresponding time points of the continuous time points, and call the pre-stored fixed value of the ultrasonic radar installation height. S2: Based on the vehicle odometer coordinate sequence, select any two consecutive time points as the first time point and the second time point, and perform a difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement. S3: Extract the first obstacle distance value corresponding to the first time moment and the second obstacle distance value corresponding to the second time moment from the obstacle distance sequence; construct a planar triangle model based on the vehicle displacement, the first obstacle distance value and the second obstacle distance value, wherein the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value and the length of the second side is the second obstacle distance value; S4: Based on the planar triangle model, the cosine value of the included angle is calculated using the law of cosines to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle corresponding to the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane. S5: Based on the fixed installation height of the ultrasonic radar and the vertical height difference, the actual height is calculated to obtain the actual height of the obstacle reflection point from the ground.

2. The method according to claim 1, characterized in that, The step of constructing a planar triangle model based on the vehicle displacement, the distance value of the first obstacle, and the distance value of the second obstacle includes: The radar position at the first moment is defined as the first vertex, the radar position at the second moment is defined as the second vertex, and the obstacle reflection point is defined as the third vertex. The vehicle displacement is assigned the side length between the first vertex and the second vertex, the first obstacle distance is assigned the side length between the first vertex and the third vertex, and the second obstacle distance is assigned the side length between the second vertex and the third vertex, thus constructing the planar triangle model.

3. The method according to claim 2, characterized in that, Based on the planar triangle model, the cosine value of the included angle is calculated using the law of cosines to obtain the cosine value of the included angle between the first side and the base in the planar triangle model. Based on the cosine value of the included angle and the distance value of the first obstacle at the first moment, a vertical height difference calculation is performed to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane, including: Extract the base length, the first side length, and the second side length from the planar triangle model; Based on the lengths of the base, the first side, and the second side, the cosine of the angle between the first side and the base is obtained using the law of cosines. The cosine of the angle is calculated using the following formula: in, for The angle between the first side and the bottom side at any given moment. The base length is the side length between the first vertex A and the second vertex B. The length of the first side is the side length between the first vertex A and the third vertex C. The length of the second side is the side length between the second vertex B and the third vertex C; Based on the cosine of the included angle and the distance to the first obstacle, a vertical height difference is calculated to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar mounting plane; the vertical height difference is calculated using the following formula: in, The vertical height difference is mentioned.

4. The method according to claim 3, characterized in that, The actual height is calculated using the following formula: in, The actual height, The ultrasonic radar is installed at a fixed height.

5. The method according to claim 1, characterized in that, The method further includes: The next time point adjacent to the second time point in the continuous time series is taken as the new second time point, and the second time point is taken as the new first time point to form a new time series detection group; Based on the vehicle odometer coordinates and obstacle distance sequence corresponding to the new time-series detection group, repeat steps S2 to S5 to obtain the new actual height of the obstacle reflection point from the ground. The new actual height and the actual height are integrated in chronological order to generate a dynamic update sequence of obstacle height.

6. An ultrasonic obstacle height detection system based on dynamic geometric modeling, characterized in that, The system includes: The data acquisition and initialization module is used to acquire the obstacle distance sequence detected by the ultrasonic radar at continuous time points; based on the vehicle positioning system, it synchronously acquires the vehicle odometer coordinate sequence at the corresponding time of the continuous time points, and calls the pre-stored fixed value of the ultrasonic radar installation height. The vehicle displacement calculation module is used to select any two consecutive time points as the first time point and the second time point based on the vehicle odometer coordinate sequence, and perform a difference calculation on the vehicle odometer coordinates at the first time point and the vehicle odometer coordinates at the second time point to obtain the vehicle displacement. A triangle model construction module is used to extract the first obstacle distance value corresponding to the first time moment and the second obstacle distance value corresponding to the second time moment from the obstacle distance sequence; and to construct a planar triangle model based on the vehicle displacement, the first obstacle distance value and the second obstacle distance value, wherein the length of the base of the triangle model is the vehicle displacement, the length of the first side is the first obstacle distance value and the length of the second side is the second obstacle distance value; The height difference calculation module is used to calculate the cosine value of the included angle based on the planar triangle model using the law of cosines, to obtain the cosine value of the included angle between the first side and the bottom side in the planar triangle model; based on the cosine value of the included angle and the distance value of the first obstacle corresponding to the first moment, the vertical height difference is converted to obtain the vertical height difference between the obstacle reflection point and the ultrasonic radar installation plane. The obstacle actual height calculation module is used to calculate the actual height based on the fixed value of the ultrasonic radar installation height and the vertical height difference, so as to obtain the actual height of the obstacle reflection point from the ground.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images