Parameter determination method and device of dual-sensor device, electronic device, and storage medium

Abstract

The application provides a parameter determination method and device of a double-sensor device, electronic equipment and a storage medium. The vertical height information of a vehicle chassis relative to the double-sensor device, the inherent vertical field of view angle of a first sensor and a second sensor and the horizontal distance between the first sensor and the second sensor are obtained. Based on a preset double-sensor vehicle bottom blind area coverage geometric constraint model, the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor are calculated based on the vertical height information, the inherent vertical field of view angle and the horizontal distance. The effective value range is output for a user to determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor, so that the quantitative and calculable configuration of the sensor installation tilt angle is realized. The reasonable installation tilt angle can be quickly determined without relying on manual installation experience and multiple trial adjustments, and the vehicle bottom detection blind area coverage is ensured.

Description

Technical Field

[0001] This application belongs to the field of dual-sensor device technology, and particularly relates to a parameter determination method, apparatus, electronic device and storage medium for a dual-sensor device. Background Technology

[0002] Current parking space monitoring and under-vehicle detection technologies have many shortcomings: single-matrix infrared sensors have a limited field of view, and the coverage length at conventional installation heights is much smaller than the standard vehicle body size, resulting in large blind spots under vehicle monitoring; scanning detection relies on moving parts such as motors and guide rails, which are costly and prone to mechanical failures, resulting in poor reliability; therefore, existing technologies use dual-sensor devices for detection, but current dual-sensor deployments only provide qualitative tilting installation suggestions, lacking quantitative parameter configuration basis, requiring repeated debugging during installation, and cannot stably achieve blind-spot-free coverage under the vehicle. Summary of the Invention

[0003] In view of this, embodiments of this application provide a parameter determination method, apparatus, electronic device and storage medium for a dual-sensor device, which can quantitatively calculate and output the effective range of tilt angles of the two sensors by acquiring key parameters such as the vertical height of the vehicle underside, the inherent vertical field of view of the sensors and the horizontal distance between the two sensors, based on a preset dual-sensor vehicle underside blind-spot coverage geometric constraint model.

[0004] In a first aspect, embodiments of this application provide a method for determining parameters of a dual-sensor device. The dual-sensor device is used to be installed on the ground of a parking space and to detect the chassis of a vehicle upwards. The dual-sensor device includes a first sensor and a second sensor, wherein the detection optical axes of the first sensor and the second sensor are set in opposite directions. The method includes: The vertical height information of the vehicle chassis relative to the dual-sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor are obtained. Based on the preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combined with the vertical height information, the inherent vertical field of view angle and the horizontal distance, the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor are calculated. The valid value range is output so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

[0005] In some embodiments, the calculation of the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor, based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model and in conjunction with the vertical height information, the inherent vertical field of view, and the horizontal distance, includes: The vertical height information, the inherent vertical field of view, and the horizontal distance are input into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor. The dual-sensor under-vehicle blind-spot coverage geometric constraint model includes: a first geometric constraint model for enabling the first sensor to cover the front area of ​​the vehicle, a second geometric constraint model for enabling the second sensor to cover the rear area of ​​the vehicle, a third geometric constraint model for enabling the lower viewing angles of the first and second sensors to meet the effective conditions, and a fourth geometric constraint model for enabling the distance between the upper viewing angle coverage areas of the first sensor and the upper viewing angle coverage areas of the second sensor in the overlapping area at the middle of the under-vehicle to be greater than the horizontal distance.

[0006] In some embodiments, the first sensor and the second sensor are symmetrically arranged, and the first sensor and the second sensor have the same tilt angle. The step of inputting the vertical height information, the inherent vertical field of view, and the horizontal distance into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor includes: The inherent vertical field of view is input into the first geometric constraint model to obtain the first effective range of values ​​for the tilt angle of the first sensor; The inherent vertical field of view is input into the third geometric constraint model to obtain the second effective range of values ​​for the tilt angle of the first sensor; The inherent vertical field of view and the horizontal height are input into the fourth geometric constraint model to obtain the third effective range of values ​​for the tilt angle of the first sensor; The effective range of the tilt angle of the first sensor is determined based on the first effective range, the second effective range, and the third effective range.

[0007] In some embodiments, determining the effective range of the tilt angle of the first sensor based on the first effective range, the second effective range, and the third effective range includes: Extract the upper limit values ​​of the angles corresponding to the first effective value range, the second effective value range, and the third effective value range. Select the smallest upper limit value of the angle as the maximum critical value of the tilt angle. Combine the lower limit values ​​of the angles of the first effective value range, the second effective value range, and the third effective value range to form a continuous effective angle interval that satisfies all constraints, and obtain the effective value range of the tilt angle of the first sensor.

[0008] In some embodiments, the first geometric constraint model is: α < θ / 2, the second geometric constraint model includes: β < θ / 2, the third geometric constraint model includes: α + θ / 2 ≤ 90°, β + θ / 2 ≤ 90°, and the fourth geometric constraint model includes: H×tan(θ / 2-α)+H×tan(θ / 2-β)>D, where θ is the inherent vertical field of view, α is the tilt angle of the first sensor, β is the tilt angle of the second sensor, H is the vertical height information, and D is the horizontal distance.

[0009] In some embodiments, the method further includes: Establish the geometric coverage model of the first sensor and the coverage geometric model of the second sensor; The dual-sensor under-vehicle blind-spot-free coverage geometric constraint model is established based on the coverage geometric model of the first sensor and the coverage geometric model of the second sensor.

[0010] In some embodiments, the method further includes: Obtain the tilt angle of the first sensor and the tilt angle of the second sensor selected by the user; The tilt angle of the first sensor and the tilt angle, vertical height information and inherent vertical field of view of the second sensor are input into the dual-sensor vehicle under-blind-spot coverage geometric constraint model to obtain the verification results, and the verification results are output.

[0011] Secondly, embodiments of this application provide a parameter determination device for a dual-sensor device. The dual-sensor device is used to be installed on the ground of a parking space and to detect the vehicle chassis upwards. The dual-sensor device includes a first sensor and a second sensor, wherein the detection optical axes of the first sensor and the second sensor are arranged in opposite directions. The acquisition module is used to acquire the vertical height information of the vehicle chassis relative to the dual sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor; The calculation module is used to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, combined with the vertical height information, the inherent vertical field of view and the horizontal distance. The output module is used to output the effective value range so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

[0012] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the methods described above.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the methods described above.

[0014] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes an electronic device to execute any of the methods described above.

[0015] This application provides a parameter determination method for a dual-sensor device. By acquiring the vertical height information of the vehicle chassis relative to the dual-sensor device, the inherent vertical field of view of the first and second sensors, and the horizontal distance between the first and second sensors; based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combining the vertical height information, the inherent vertical field of view, and the horizontal distance, the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor are calculated; the effective value range is output so that the user can determine and configure the installation tilt angle of the first and second sensors, achieving quantitative and calculable configuration of the sensor installation tilt angle; without relying on manual installation experience and multiple trial adjustments, a reasonable installation tilt angle can be quickly determined, ensuring blind-spot-free coverage of the under-vehicle detection. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0017] Figure 1 A schematic diagram illustrating the implementation process of a parameter determination method for a dual-sensor device provided in an embodiment of this application; Figure 2 This application provides a schematic diagram of the implementation process of step S1021 in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of a parameter determination device for a dual-sensor device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0019] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0020] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0021] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected," or "in response to detection."

[0022] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0024] To address the problems in related technologies, this application provides a parameter determination method for a dual-sensor device that can be applied to electronic devices, including mobile phones, computers, and other similar devices. The method provided in this application can be implemented using the processor of the electronic device.

[0025] In this embodiment, the dual-sensor device is installed on the ground of the parking space and probes the vehicle chassis upwards. The dual-sensor device includes a first sensor and a second sensor, with the detection optical axes of the first and second sensors arranged in opposite directions. The first and second sensors can be temperature sensors.

[0026] In this embodiment, the dual-sensor device is an integrated detection unit composed of a first and a second detection sensor. It is installed on the ground of the parking space and is specifically designed to collect detection signals from the vehicle chassis area, enabling the perception of parking space occupancy and vehicle undercarriage status. The device is laid flat and fixed to the parking space surface, with the detection direction pointing upwards towards the vehicle chassis, unlike lateral or suspended installation methods, and is suitable for standard parking lot layouts. The first and second sensors are two independent detection units constituting the detection device, employing the same type of detection device and possessing a fixed vertical field of view. The detection coverage area can be changed by tilting the installation. The detection optical axes are reversed, with the central detection axes of the two sensors arranged in opposite directions, one biased towards the front of the vehicle and the other towards the rear, forming a two-way coverage layout that provides a structural basis for full-length, blind-spot-free detection under the vehicle.

[0027] Figure 1 This is a schematic diagram illustrating the implementation process of a parameter determination method for a dual-sensor device provided in an embodiment of this application, as shown below. Figure 1 As shown, the parameter determination method for a dual-sensor device includes: Step S101: Obtain the vertical height information of the vehicle chassis relative to the dual sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor.

[0028] In this embodiment, the vertical height information of the vehicle chassis relative to the dual-sensor device refers to the vertical distance H from the lowest point of the vehicle chassis to the mounting surface of the ground sensor in the parking space. This is a key fixed parameter determined by the vehicle model and the ground clearance of the chassis, and is used for geometric optical path trigonometric function calculations. The inherent vertical field of view sensor has a fixed and unchangeable vertical in-plane detection angle θ, which is an inherent hardware parameter of the sensor and determines the vertical detection field of view of a single sensor. The horizontal distance between the first and second sensors is the horizontal center-to-center distance D between the two sensors on the ground mounting surface. This is a structural dimension of the device and a core structural parameter for controlling whether a blind spot occurs in the middle of the vehicle undercarriage.

[0029] In this embodiment, vertical height information can be obtained by inputting vehicle model parameters, on-site measurement and calibration, and reading from a preset standard vehicle model universal height library; the inherent vertical field of view can be obtained by directly reading the sensor's factory specifications; and the horizontal distance can be obtained by reading the fixed dimensions of the equipment structure or by measuring the horizontal distance after on-site installation.

[0030] In some embodiments, a user interface may be provided, through which a user can input vertical height information, inherent vertical field of view, and horizontal distance.

[0031] Step S102: Based on the preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combined with vertical height information, inherent vertical field of view angle and horizontal distance, calculate the effective range of tilt angle of the first sensor and the effective range of tilt angle of the second sensor.

[0032] In this embodiment, the dual-sensor underbody blind-spot coverage geometric constraint model is a mathematical model pre-established using geometric optical paths and trigonometric functions. It incorporates multi-dimensional geometric constraints, relating four main parameters: chassis height, field of view, horizontal spacing, and sensor tilt angle. This allows for the quantitative calculation of the tilt angle range that satisfies full underbody coverage. The effective range of tilt angle values ​​refers to the range of sensor installation tilt angles that satisfy all geometric constraints and achieve blind-spot-free underbody coverage. Exceeding this range will result in insufficient coverage at the front or rear of the vehicle, or a blind spot in the middle of the underbody.

[0033] In this embodiment, the dual-sensor geometric constraint model and the corresponding trigonometric function constraint formula can be pre-fixed in the algorithm / program; the acquired vertical height information, inherent vertical field of view angle and horizontal distance are input into the dual-sensor vehicle under-blind-spot coverage geometric constraint model, the model automatically sets multiple sets of geometric inequality constraints, and through interval solving operations, the tilt angle intervals in which the first and second sensors can be legally installed are calculated respectively.

[0034] Step S103: Output the valid value range so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

[0035] In this embodiment of the application, the effective range of the obtained tilt angle can be displayed on the interface as a numerical range or a recommended angle value, output as a message, or exported as a document; the installer can directly select any angle within the range based on the output angle range for fixed installation and angle adjustment.

[0036] The method provided in this application acquires the vertical height information of the vehicle chassis relative to the dual-sensor device, the inherent vertical field of view of the first and second sensors, and the horizontal distance between the first and second sensors. Based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combined with the vertical height information, inherent vertical field of view, and horizontal distance, the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor are calculated. The effective range of values ​​is output so that the user can determine and configure the installation tilt angle of the first and second sensors, thereby realizing the quantitative and calculable configuration of the sensor installation tilt angle. It can quickly determine a reasonable installation tilt angle without relying on manual installation experience and multiple trial adjustments, ensuring blind-spot coverage of the under-vehicle detection.

[0037] In some embodiments, step S102 can be implemented by the following steps: Step S1021: Input the vertical height information, inherent vertical field of view, and horizontal distance into the dual-sensor vehicle under-blind-spot coverage geometric constraint model, and calculate the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor. The dual-sensor vehicle under-blind-spot coverage geometric constraint model includes: a first geometric constraint model for enabling the first sensor to cover the front area of ​​the vehicle, a second geometric constraint model for enabling the second sensor to cover the rear area of ​​the vehicle, a third geometric constraint model for enabling the lower viewing angles of the first and second sensors to meet the effective conditions, and a fourth geometric constraint model for enabling the distance between the upper viewing angle coverage areas of the first sensor and the upper viewing angle coverage areas of the second sensor in the overlapping area in the middle of the vehicle under-blind spot to be greater than the horizontal distance.

[0038] In this embodiment, the first geometric constraint model is a geometric determination rule specifically designed for the first sensor. By limiting the angular relationship between the tilt angle and the field of view of the first sensor, it ensures that its upper viewing angle can extend forward to cover the front area of ​​the vehicle, avoiding detection blind spots at the front of the vehicle. The second geometric constraint model is a geometric determination rule specifically designed for the second sensor. By limiting the angular relationship between the tilt angle and the field of view of the second sensor, it ensures that its upper viewing angle can extend backward to cover the rear area of ​​the vehicle, avoiding detection blind spots at the rear of the vehicle. The third geometric constraint model is a lower viewing angle optical path effectiveness constraint rule, which limits the sum of the sensor tilt angle and the half field of view to no more than 90°, preventing the detection light from shifting upward and the horizontal coverage distance from becoming invalid, ensuring that the lower viewing angle ground coverage distance has physical meaning and is computationally valid. The fourth geometric constraint model is a blind spot-free overlap constraint rule for the middle of the vehicle bottom. It uses the sum of the backward and forward coverage lengths of the upper viewing angles of the two sensors and the horizontal distance between the two sensors to determine the magnitude; that is, the coverage ranges of the upper viewing angles on both sides must overlap to ensure that there are no discontinuous detection blind spots in the middle of the vehicle bottom. The upper viewing angle coverage area is the near-field ground coverage zone corresponding to the half-field of view centered on the optical axis of the sensor, mainly responsible for covering the middle of the vehicle's underside, the inner side of the front of the vehicle, and the inner side of the rear of the vehicle. The lower viewing angle is the far-field ground coverage zone corresponding to the half-field of view centered on the optical axis of the sensor, mainly responsible for extending coverage to the outer areas of the front and rear of the vehicle. The distance of the overlapping area is the sum of the rearward upper viewing angle coverage length of the first sensor and the forward upper viewing angle coverage length of the second sensor; if this sum is greater than the horizontal distance between the two sensors, it means that the middle area completely overlaps without gaps or blind spots.

[0039] In this embodiment, the three core known parameters collected—the vertical height of the vehicle chassis, the inherent vertical field of view of the sensor, and the horizontal distance between the two sensors—are imported in batches into a pre-set geometric constraint model. The model has pre-fixed the angle and trigonometric operation logic of four types of constraints, eliminating the need for manual calculation.

[0040] In this embodiment, the model performs four constraint checks in parallel: First, it calls the first geometric constraint model to verify whether the tilt angle of the first sensor meets the front-end coverage angle condition, filtering out angle ranges that meet the front-end coverage. Second, it calls the second geometric constraint model to verify whether the tilt angle of the second sensor meets the rear-end coverage angle condition, filtering out angle ranges that meet the rear-end coverage. Third, it calls the third geometric constraint model to verify whether the lower-view optical path of each sensor is valid, eliminating angles exceeding 90° that are invalid. Fourth, it calls the fourth geometric constraint model to calculate the upper-view coverage length on both sides using trigonometric functions, verifying whether the cumulative length is greater than the horizontal distance of the sensors, filtering out angle ranges with no blind spots in the middle of the vehicle's underside. Then, it performs an intersection operation on the valid angle ranges output by each of the four constraints, retaining only the angle ranges that simultaneously meet all conditions: front-end coverage, rear-end coverage, valid optical path, and middle overlap. Finally, it outputs the valid tilt angle ranges of the first and second sensors that can be directly used for installation and configuration.

[0041] The method provided in this application separates the constraints into four independent areas: the front of the vehicle, the rear of the vehicle, the effectiveness of the optical path, and the middle of the vehicle's undercarriage. It then implements targeted control over the detection boundary, the rationality of the optical path, and the blind spot in the middle, achieving blind-spot-free closed-loop coverage across the entire area from the front of the vehicle to the rear and the middle of the vehicle's undercarriage. Instead of relying on manual on-site adjustments, it uses four preset rigid geometric constraints for quantitative verification, ensuring no blind spots from the underlying optical path geometry, thus avoiding insufficient coverage and localized missed detections caused by experience-based installation. The model uses a parametric input method; when changing the chassis height, sensor field of view, or sensor installation spacing, only the parameters need to be re-entered to automatically recalculate the tilt angle range. This method is highly versatile and adaptable to various parking space monitoring scenarios.

[0042] In some embodiments, the first sensor and the second sensor are symmetrically arranged, and the first sensor and the second sensor have the same tilt angle. In this embodiment, symmetrical arrangement refers to the first sensor and the second sensor being centrally symmetrical and positioned opposite each other on the same mounting base, with completely symmetrical structural dimensions and installation posture. This is a standardized assembly structure for dual-sensor devices. Under the premise of symmetrical installation with the same tilt angle, the tilt angles of the first sensor's optical axis and the vertical direction, and the tilt angles of the second sensor's optical axis and the vertical direction are equal, i.e., α=β. This eliminates the need to adjust the two angles separately, simplifying parameter variables.

[0043] In the embodiments of this application, Figure 2 This application provides a schematic diagram of the implementation process of step S1021, which can be implemented through the following steps: Step S1: Input the inherent vertical field of view into the first geometric constraint model to obtain the first effective range of values ​​for the tilt angle of the first sensor.

[0044] In this embodiment, the first effective value range is calculated by the first geometric constraint model (vehicle front coverage constraint) and only satisfies the allowable range of sensor tilt angle that fully covers the vehicle front area. If the range is exceeded, the vehicle front detection coverage is insufficient and a blind spot is generated.

[0045] In this embodiment, the fixed inherent parameter of the sensor, the vertical field of view angle θ, is substituted into the vehicle front coverage constraint α<θ / 2; the model uses angle inequality calculations to select all tilt angle intervals that can guarantee the upper viewing angle covers the vehicle front area as the first effective value range.

[0046] Step S2: Input the inherent vertical field of view into the third geometric constraint model to obtain the second effective range of values ​​for the tilt angle of the first sensor.

[0047] In this embodiment of the application, the second effective value range is calculated by the third geometric constraint model (effective constraint of the lower view optical path) and only satisfies the allowable range of tilt angles that are physically effective for the lower view optical path. If the value exceeds this range, the detection optical path is upward, the ground coverage distance has no physical meaning, and the calculation fails.

[0048] In this embodiment, the vertical field of view θ is also input, and the third geometric constraint model α+θ / 2≤90° is substituted into it. The model eliminates invalid angles that would cause the probe beam to have an excessive elevation angle and lose ground coverage capability, and outputs the tilt angle range that satisfies the physical rationality of the optical path as the second valid value range.

[0049] Step S3: Input the inherent vertical field of view and horizontal height into the fourth geometric constraint model to obtain the third effective range of the tilt angle of the first sensor.

[0050] In this embodiment, the third effective value range is calculated by the fourth geometric constraint model (overlapping constraint at the center of the vehicle bottom) and only satisfies the allowable range of tilt angles that cover the overlap at the center of the vehicle bottom without blind spots. If the range is exceeded, the viewing angles of the two sensors cannot overlap, and a detection hole appears in the middle of the vehicle bottom.

[0051] In this embodiment of the application, the fourth geometric constraint model includes: Since H×tan(θ / 2-α)+H×tan(θ / 2-β)>D, we can substitute H and D into the model. Since α=β, we can solve for α.

[0052] Step S4: Determine the effective range of the tilt angle of the first sensor based on the first effective range, the second effective range, and the third effective range.

[0053] In this embodiment, the angle intervals corresponding to the first three sets of independent constraints are logically intersected and filtered to obtain a unique legal tilt angle interval that simultaneously satisfies the requirements of front-end coverage, effective optical path, and central overlap; since the tilt angles of the two sensors are equal, this interval is also applicable to the second sensor.

[0054] The method provided in this application simplifies the complex calculation of solving two tilt angles separately by limiting the symmetry and tilt angle of the two sensors to solving only one tilt angle, reducing the computational complexity of the model and facilitating the implementation of embedded algorithms and low-cost controllers. The three constraints of vehicle front coverage, optical path effectiveness, and center overlap are calculated independently for their respective angle ranges, and then the intersection is unified for filtering. This provides a clear troubleshooting logic, facilitating later fault location, parameter modification, and algorithm iteration. The symmetrical structure and symmetry configuration allow for standardized factory production of the dual-sensor device, eliminating the need for separate angle adjustments for each sensor, significantly reducing assembly difficulty on the production line and on-site installation and debugging workload. By sequentially filtering through the three layers of constraints—vehicle front coverage, optical path effectiveness, and center overlap—the final angle range naturally and simultaneously satisfies all blind-zone-free conditions, avoiding localized missed detections caused by a single constraint and improving the completeness and stability of parking space and under-vehicle detection.

[0055] In some embodiments, step S4 can be implemented through the following steps: Extract the upper limit values ​​of the angles corresponding to the first, second, and third effective value ranges, select the smallest upper limit value of the angle as the maximum critical value of the tilt angle, and combine the lower limit values ​​of the angles of the first, second, and third effective value ranges to form a continuous effective angle interval that satisfies all constraints, thus obtaining the effective value range of the tilt angle of the first sensor.

[0056] In this embodiment, the upper limit of the angle is the maximum allowable tilt angle within each valid range. Exceeding this upper limit will violate the corresponding geometric constraints, resulting in blind spots or optical path failures. The lower limit of the angle is the minimum allowable tilt angle within each valid range. Values ​​below the lower limit also fail to meet the coverage conditions. The minimum upper limit of the angle is determined by comparing the upper limits of the three constraints and selecting the smallest value. The maximum critical value of the tilt angle is the final determined limit angle that cannot be exceeded; it is a hard upper limit resulting from the superposition of all constraints. A continuous valid angle interval that simultaneously satisfies the three geometric constraints, has no breaks, and is a legally installable tilt angle interval that can be directly selected, in the form of: lower limit of angle ~ maximum critical value.

[0057] The method provided in this application adopts a simplified logic of "extracting the upper limit → taking the minimum upper limit → synthesizing the interval," which does not require complex interval intersection operations. It is easy to implement directly in embedded programs and low-end controllers, with low computational load and high execution efficiency. It automatically follows the most stringent constraints, ensuring no blind spots from the root. By selecting the minimum angle upper limit, it automatically uses the strongest geometric constraints as the control boundary, naturally satisfying the three requirements of front-end coverage, effective optical path, and central overlap simultaneously, without any situation where one requirement is neglected.

[0058] In some embodiments, the first geometric constraint model is: α < θ / 2, the second geometric constraint model includes: β < θ / 2, the third geometric constraint model includes: α + θ / 2 ≤ 90°, β + θ / 2 ≤ 90°, and the fourth geometric constraint model includes: H×tan(θ / 2-α)+H×tan(θ / 2-β)>D, where θ is the inherent vertical field of view, α is the tilt angle of the first sensor, β is the tilt angle of the second sensor, H is the vertical height information, and D is the horizontal distance.

[0059] In some embodiments, before step S102, the method further includes: establishing a geometric coverage model of the first sensor and a coverage geometric model of the second sensor; and establishing a dual-sensor blind-spot-free coverage geometric constraint model of the vehicle underside based on the coverage geometric model of the first sensor and the coverage geometric model of the second sensor.

[0060] In this embodiment, the geometric coverage model of the first sensor is a mathematical model constructed using a single first sensor as the object, based on the sensor's vertical field of view, installation tilt angle, and vehicle chassis vertical height, through trigonometric functions and geometric optical path relationships. It is used to characterize the horizontal coverage distance and detection boundary range of the upper and lower viewing angles on the ground at different tilt angles of the sensor, and can quantitatively calculate the forward and backward detection coverage length of a single sensor. The geometric coverage model of the second sensor is completely consistent in principle and structure with the first sensor's geometric coverage model, and is a separate optical path geometric mathematical model established specifically for the second sensor. It is used to independently characterize the forward and backward detection coverage range and boundary position of the second sensor at different tilt angles.

[0061] In this embodiment, a two-dimensional vertical detection geometric coordinate system can be established with the parking space ground as the reference and the vertical direction as the reference; geometric variables such as sensor optical axis, vertical field of view half angle, tilt angle, and chassis vertical height are defined; based on the optical path principle of symmetrical distribution of optical axis deflection angle + field of view angle, the calculation formulas for the upper and lower viewing angle coverage distances of a single sensor are derived using tangent trigonometric functions; independent optical path-coverage distance mathematical relationships are solidified for the first sensor and the second sensor respectively, forming their own exclusive single-sensor geometric coverage models; a single model can independently input tilt angle, field of view angle, and chassis height, and output the corresponding front and rear coverage lengths and detection boundaries.

[0062] In this embodiment, two independent geometric coverage models, the first sensor and the second sensor, can be spatially correlated, and the horizontal distance between the two sensors can be introduced as a structural constraint. Combined with actual under-vehicle detection requirements, four types of constraint rules are superimposed: Constraint 1: The first sensor covers the front area of ​​the vehicle; Constraint 2: The second sensor covers the rear area of ​​the vehicle; Constraint 3: The downward viewing angles of the two sensors are legal and valid; Constraint 4: The upward viewing coverage areas of the two sensors overlap in the middle of the under-vehicle area without detection gaps. The above spatial relationships, coverage distance formulas, and four types of geometric constraint inequalities are combined and integrated to form a complete, calculable, and solvable tilt angle range dual-sensor under-vehicle blind-spot-free coverage geometric constraint model. After the model is built, it can be pre-set and fixed in the algorithm program, and subsequent calculations only require inputting parameters to automatically calculate the effective tilt angle range, eliminating the need for re-modeling and derivation each time.

[0063] For example, the coverage types of the first sensor include: lower-view coverage and upper-view coverage, wherein the coverage geometry model of the lower-view coverage is: L1_front = H × tan(α + θ / 2), with the constraint: α + θ / 2 ≤ 90°, and the coverage geometry model of the upper-view coverage is: L1_back = H × tan(θ / 2 - α), with the constraint: α < θ / 2. The coverage types of the second sensor include: lower-view coverage and upper-view coverage, wherein the coverage geometry model of the lower-view coverage is: L2_back = H × tan(β + θ / 2), and the coverage geometry model of the upper-view coverage is: L2_front = H × tan(β - θ / 2) β), where the angle between the sensor's optical axis and the vertical direction is the tilt angle, the field of view is symmetrically distributed around the optical axis, the half-field of view is θ / 2, the angle between the farthest ray of the lower viewing angle and the vertical direction is = tilt angle + θ / 2, and the angle between the farthest ray of the upper viewing angle and the vertical direction is = θ / 2 - tilt angle. Here, H is the vertical distance between the vehicle chassis and the sensor, θ is the inherent vertical field of view, and D is the distance between the two sensors.

[0064] To achieve full coverage of the vehicle's undercarriage, the following three constraints must be met: Constraint 1: Top view coverage condition (ensure the front and rear of the vehicle are covered); The first sensor needs to cover the front area of ​​the vehicle: α < θ / 2; The second sensor needs to cover the rear area of ​​the vehicle: β < θ / 2; Constraint 2: Valid conditions for the lower viewpoint (to ensure that the coverage distance calculation is valid); The angle between the downward-facing ray and the vertical direction must not exceed 90°. α + θ / 2 ≤ 90°; β + θ / 2 ≤ 90°; Constraint 3: Overlap condition (ensure there is no blind spot in the middle of the vehicle undercarriage); The downward-view coverage areas of the two sensors overlap in the middle of the vehicle's underside: L2_front + L1_back > D; Substitute into the formula: H × tan(θ / 2-α) + H × tan(θ / 2-β)>D; In this embodiment of the application, the parameter combinations that satisfy all inequalities can be solved based on the above inequalities and the above constraints.

[0065] In some embodiments, when symmetrically mounted, α = β, and the model can be simplified to: The constraints for top view coverage are: α < θ / 2; the effective condition for bottom view coverage is α ≤ 90° - θ / 2; the overlap condition is: α < θ / 2 - arctan(D / (2H)); Combined constraints: 0<α <min(θ / 2,90°-θ / 2,θ / 2-arctan(D / (2H))); Given H, D, and θ, calculate the range of values ​​for α, and select an appropriate value for α within that range.

[0066] The method provided in this application first performs single-sensor micro-vision path coverage modeling, and then couples spatial location with full coverage constraints to generate a dual-sensor overall constraint model.

[0067] In some embodiments, after step S103, the method further includes: Step S104: Obtain the tilt angle of the first sensor and the tilt angle of the second sensor selected by the user.

[0068] In this embodiment, the tilt angles of the first and second sensors selected by the user are the actual installation tilt angles of the two sensors, which are manually selected or set on-site according to actual installation requirements. These are the actual configuration angle values ​​to be verified.

[0069] In this embodiment, the actual installation tilt angles of two sensors selected by the user can be collected through a human-computer interaction interface, parameter input port, on-site debugging and configuration, etc.; the actual tilt angles are used as parameters to be verified and transmitted to the background verification process.

[0070] Step S105: Input the tilt angle of the first sensor and the tilt angle of the second sensor, the vertical height information and the inherent vertical field of view into the dual-sensor vehicle under-blind-spot coverage geometric constraint model to obtain the verification results, and output the verification results.

[0071] In this embodiment of the application, the verification result is the judgment conclusion output by the model after performing full constraint verification on the tilt angle selected by the user, including: whether it meets the requirement of no blind spot coverage, whether it exceeds the effective angle of the optical path, whether there is a blind spot in the middle of the vehicle bottom, and whether the tilt angle is compliant, etc.

[0072] In this embodiment, four key parameters—the tilt angle of the first sensor selected by the user, the tilt angle of the second sensor, the vertical height of the chassis, and the inherent vertical field of view of the sensor—can be imported into a pre-set dual-sensor vehicle under-blind-spot coverage geometric constraint model. The model internally calls the preset geometric constraint formulas and judgment conditions to perform compliance verification item by item.

[0073] In this embodiment, the model sequentially verifies: whether it satisfies the effective coverage of the front and rear of the vehicle; whether the optical path angle of the sensor's lower view is legal and valid; whether the coverage area of ​​the upper view of the two sensors in the middle of the vehicle's underside meets the condition of overlapping without blind spots; and generates a structured verification conclusion by comprehensively considering all constraint verification results. The verification results are then output to the user through interface display, data messages, text prompts, etc., so that the user can determine whether the currently selected tilt angle is usable.

[0074] The method provided in this application can automatically verify the compliance of any tilt angle selected by the user, eliminating the need for manual on-site inspection of blind spots after actual installation. It pre-determines whether the configuration is qualified, avoiding invalid installation and rework. Full-coverage multi-dimensional constraint verification ensures accurate and reliable results. Based on a built-in complete geometric constraint model, it simultaneously verifies front and rear coverage, optical path effectiveness, and central overlap, avoiding omissions caused by single-dimensional judgments. The verification standards are unified, and the results are objective. It lowers the professional threshold for installation and commissioning. Users do not need to master complex geometric principles and calculation formulas; they only need to input their selected installation angle to automatically obtain verification results regarding whether there are no blind spots. Ordinary construction personnel can also quickly complete parameter self-checks.

[0075] Exemplarily, the chassis height H = 20 cm, the sensor field of view angle θ = 110°, and the distance between two sensors D = 5 cm. The calculation process is as follows: θ / 2 = 55°; 90° - θ / 2 = 35°; D / (2H) = 5 / 40 = 0.125; arctan(0.125) ≈ 7.125°; α_min = 55° - 7.125° = 47.875°; The value range of α: 0 < α < min(55°, 35°, 47.875°) = 35°; Recommended value: α = 30°; For the coverage distance calculation, taking α = β = 30°, then L1_front (lower view angle forward) = H × tan(α + θ / 2) = 20 × tan(85°) = 20 × 11.43 = 228.6 cm; L1_back (upper view angle backward) = H × tan(θ / 2 - α) = 20 × tan(25°) = 20 × 0.466 = 9.3 cm; L2_back (lower view angle backward) = H × tan(β + θ / 2) = 20 × tan(85°) = 228.6 cm, L2_front (upper view angle forward) = H × tan(θ / 2 - β) = 20 × tan(25°) = 9.3 cm. Overlap verification: L1_back + L2_front = 9.3 + 9.3 = 18.6 cm > 5 cm; then the overlap is established. Coverage integrity: Near the front of the vehicle: L1_front = 228.6 cm (covered by the lower view angle of sensor A forward); Near the rear of the vehicle: L2_back = 228.6 cm (covered by the lower view angle of sensor B backward); In the middle of the vehicle bottom: The upper view angle overlap is 18.6 cm - D = 13.6 cm.

[0076] In some embodiments, the method further includes: After calculating the effective value range of the tilt angle, a preset angular safety margin is reserved inside the effective value range, and the edge angle interval close to the critical upper limit is removed to obtain the final installation tilt angle interval after fault tolerance optimization; the angular safety margin is used to compensate for mechanical installation deviation, assembly tolerance, and device consistency error, so that even if there is a small deviation in the actual installation angle, the full coverage of the vehicle bottom without blind spots can still be satisfied.

[0077] In some embodiments, the angular safety margin is set according to the classification of the parking space application scenarios. The scenarios include indoor standard parking spaces, outdoor open parking spaces, and simple temporary parking spaces; different sizes of angular safety margins are matched according to the installation vibration amplitude, temperature environment, and construction accuracy corresponding to different scenarios to achieve hierarchical fault tolerance adaptation, taking into account the reliability of no blind spots and the installation adaptability.

[0078] In some embodiments, the method further includes a coverage margin classification determination step: the overlap margin in the middle of the vehicle bottom is calculated based on the fourth geometric constraint model, and the overlap margin is divided into three levels: critical qualified, standard qualified, and excellent; the optimal tilt angle is matched according to the margin level to avoid the problem that the overlap margin is too small and will easily produce blind spots, or the margin is too large and will result in insufficient detection coverage distance at both ends, so as to achieve the optimal configuration of coverage performance.

[0079] In some embodiments, the method further includes: Obtain the vehicle body length parameters suitable for the current parking space, and match the corresponding minimum front-end coverage distance and minimum rear-end coverage distance based on the vehicle body length parameters; combine the dual-sensor under-vehicle blind-spot coverage geometric constraint model, dynamically correct the effective range of tilt angle values, so that different vehicle length models can meet the full coverage detection of the front, rear and middle of the under-vehicle.

[0080] In some embodiments, the method further includes: The system collects real-time chassis vertical height data for different vehicles, iteratively inputs the real-time chassis height parameters into a dual-sensor underbody blind-spot coverage geometric constraint model, dynamically updates the effective range of sensor tilt angle values, and adapts to the detection needs of different vehicle models with varying chassis ground clearance.

[0081] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0082] According to the foregoing embodiments, this application provides a parameter determination device for a dual-sensor device. The various modules and units included in the device can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0083] This application provides a parameter determination device for a dual-sensor device. Figure 3 This is a schematic diagram of the structure of a parameter determination device for a dual-sensor device provided in an embodiment of this application, as shown below. Figure 3 As shown, the parameter determination device 300 for the dual-sensor device includes: The acquisition module 301 is used to acquire the vertical height information of the vehicle chassis relative to the dual sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor. The calculation module 302 is used to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor based on the preset dual-sensor vehicle bottom blind-spot coverage geometric constraint model, combined with vertical height information, inherent vertical field of view and horizontal distance. The output module 303 is used to output the valid value range so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

[0084] In some embodiments, based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combining information based on vertical height, inherent vertical field of view, and horizontal distance, the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor are calculated, including: Vertical height information, inherent vertical field of view, and horizontal distance are input into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor. The dual-sensor under-vehicle blind-spot coverage geometric constraint model includes: a first geometric constraint model for enabling the first sensor to cover the front area of ​​the vehicle, a second geometric constraint model for enabling the second sensor to cover the rear area of ​​the vehicle, a third geometric constraint model for ensuring that the downward viewing angles of the first and second sensors meet the effective conditions, and a fourth geometric constraint model for ensuring that the distance between the overlapping area of ​​the upper viewing angle coverage areas of the first and second sensors in the middle of the under-vehicle is greater than the horizontal distance.

[0085] In some embodiments, the first sensor and the second sensor are symmetrically arranged, and the first sensor and the second sensor have the same tilt angle. Vertical height information, inherent vertical field of view, and horizontal distance are input into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor, including: By inputting the inherent vertical field of view into the first geometric constraint model, the first effective range of values ​​for the tilt angle of the first sensor is obtained. The inherent vertical field of view is input into the third geometric constraint model to obtain the second effective range of values ​​for the tilt angle of the first sensor; By inputting the inherent vertical field of view and horizontal height into the fourth geometric constraint model, the third effective range of values ​​for the tilt angle of the first sensor is obtained. The effective range of the tilt angle of the first sensor is determined based on the first effective range, the second effective range, and the third effective range.

[0086] In some embodiments, determining the effective range of the tilt angle of the first sensor based on a first effective range, a second effective range, and a third effective range includes: Extract the upper limit values ​​of the angles corresponding to the first, second, and third effective value ranges, select the smallest upper limit value of the angle as the maximum critical value of the tilt angle, and combine the lower limit values ​​of the angles of the first, second, and third effective value ranges to form a continuous effective angle interval that satisfies all constraints, thus obtaining the effective value range of the tilt angle of the first sensor.

[0087] In some embodiments, the first geometric constraint model is: α < θ / 2, the second geometric constraint model includes: β < θ / 2, the third geometric constraint model includes: α + θ / 2 ≤ 90°, β + θ / 2 ≤ 90°, and the fourth geometric constraint model includes: H×tan(θ / 2-α)+H×tan(θ / 2-β)>D, where θ is the inherent vertical field of view, α is the tilt angle of the first sensor, β is the tilt angle of the second sensor, H is the vertical height information, and D is the horizontal distance.

[0088] In some embodiments, the parameter determination device 300 for the dual-sensor device further includes: The first establishment module is used to establish the geometric coverage model of the first sensor and the coverage geometric model of the second sensor; The second module is used to establish a blind-spot-free coverage geometric constraint model for the undercarriage of a dual-sensor vehicle based on the coverage geometric model of the first sensor and the coverage geometric model of the second sensor.

[0089] In some embodiments, the parameter determination device 300 for the dual-sensor device further includes: The acquisition module is used to acquire the tilt angle of the first sensor and the tilt angle of the second sensor selected by the user. The verification module is used to input the tilt angle of the first sensor and the tilt angle of the second sensor, the vertical height information and the inherent vertical field of view into the dual-sensor vehicle under-blind-spot coverage geometric constraint model to obtain the verification results and output the verification results.

[0090] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0091] In addition, the parameter determination device of the dual-sensor device described above can be a software unit, a hardware unit, or a combination of software and hardware. It can also be integrated into electronic devices as an independent component, or exist as an independent terminal device.

[0092] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0093] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device of this embodiment may include: at least one processor 30 ( Figure 4 Only one processor 30, memory 31, and computer program 32 stored in memory 31 and executable on at least one processor 30 are shown. When the processor 30 executes the computer program 32, it implements the steps in any of the above method embodiments, or the processor 30 executes the computer program 32 to implement the functions of each module / unit in the above device or system embodiments.

[0094] For example, computer program 32 may be divided into one or more modules / units, one or more of which are stored in memory 31 and executed by processor 30 to complete this application. One or more modules / units may be a series of computer program 32 instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in an electronic device.

[0095] This application also provides a computer-readable storage medium storing a computer program 32, which, when executed by a processor 30, implements the steps described in the above-described method embodiments.

[0096] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0097] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program 32 instructing related hardware. The computer program 32 can be stored in a computer-readable storage medium, and when executed by the processor 30, it can implement the steps of the various method embodiments described above. The computer program 32 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a terminal, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), electrical carrier information, telecommunication information, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0098] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0099] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0100] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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 this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining parameters of a dual-sensor device, characterized in that, The dual-sensor device is used to be installed on the ground of a parking space and to detect the vehicle chassis upwards. The dual-sensor device includes a first sensor and a second sensor, wherein the detection optical axes of the first sensor and the second sensor are set in opposite directions. The method includes: The vertical height information of the vehicle chassis relative to the dual-sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor are obtained. Based on the preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, and combined with the vertical height information, the inherent vertical field of view angle and the horizontal distance, the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor are calculated. The valid value range is output so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

2. The method according to claim 1, characterized in that, The pre-defined dual-sensor under-vehicle blind-spot coverage geometric constraint model, combined with the vertical height information, the inherent vertical field of view, and the horizontal distance, calculates the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor, including: The vertical height information, the inherent vertical field of view, and the horizontal distance are input into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor. The dual-sensor under-vehicle blind-spot coverage geometric constraint model includes: a first geometric constraint model for enabling the first sensor to cover the front area of ​​the vehicle, a second geometric constraint model for enabling the second sensor to cover the rear area of ​​the vehicle, a third geometric constraint model for enabling the lower viewing angles of the first and second sensors to meet the effective conditions, and a fourth geometric constraint model for enabling the distance between the upper viewing angle coverage areas of the first sensor and the upper viewing angle coverage areas of the second sensor in the overlapping area at the middle of the under-vehicle to be greater than the horizontal distance.

3. The method according to claim 2, characterized in that, The first sensor and the second sensor are symmetrically arranged, and the first sensor and the second sensor have the same tilt angle. The vertical height information, the inherent vertical field of view, and the horizontal distance are input into the dual-sensor under-vehicle blind-spot coverage geometric constraint model to calculate the effective value range of the tilt angle of the first sensor and the effective value range of the tilt angle of the second sensor, including: The inherent vertical field of view is input into the first geometric constraint model to obtain the first effective range of values ​​for the tilt angle of the first sensor; The inherent vertical field of view is input into the third geometric constraint model to obtain the second effective range of values ​​for the tilt angle of the first sensor; The inherent vertical field of view and the horizontal height are input into the fourth geometric constraint model to obtain the third effective range of values ​​for the tilt angle of the first sensor; The effective range of the tilt angle of the first sensor is determined based on the first effective range, the second effective range, and the third effective range.

4. The method according to claim 3, characterized in that, Determining the effective range of the tilt angle of the first sensor based on the first effective range, the second effective range, and the third effective range includes: Extract the upper limit values ​​of the angles corresponding to the first effective value range, the second effective value range, and the third effective value range. Select the smallest upper limit value of the angle as the maximum critical value of the tilt angle. Combine the lower limit values ​​of the angles of the first effective value range, the second effective value range, and the third effective value range to form a continuous effective angle interval that satisfies all constraints, and obtain the effective value range of the tilt angle of the first sensor.

5. The method according to claim 2, characterized in that, The first geometric constraint model is: α < θ / 2; the second geometric constraint model includes: β < θ / 2; the third geometric constraint model includes: α + θ / 2 ≤ 90°, β + θ / 2 ≤ 90°; and the fourth geometric constraint model includes: H×tan(θ / 2-α)+H×tan(θ / 2-β)>D, where θ is the inherent vertical field of view, α is the tilt angle of the first sensor, β is the tilt angle of the second sensor, H is the vertical height information, and D is the horizontal distance.

6. The method according to claim 2, characterized in that, The method further includes: Establish the geometric coverage model of the first sensor and the coverage geometric model of the second sensor; The dual-sensor under-vehicle blind-spot-free coverage geometric constraint model is established based on the coverage geometric model of the first sensor and the coverage geometric model of the second sensor.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the tilt angle of the first sensor and the tilt angle of the second sensor selected by the user; The tilt angle of the first sensor and the tilt angle, vertical height information and inherent vertical field of view of the second sensor are input into the dual-sensor vehicle under-blind-spot coverage geometric constraint model to obtain the verification results, and the verification results are output.

8. A parameter determination device for a dual-sensor device, characterized in that, The dual-sensor device is used to be installed on the ground of the parking space and to detect the vehicle chassis upwards. The dual-sensor device includes a first sensor and a second sensor, and the detection optical axes of the first sensor and the second sensor are set in opposite directions. The acquisition module is used to acquire the vertical height information of the vehicle chassis relative to the dual sensor device, the inherent vertical field of view of the first sensor and the second sensor, and the horizontal distance between the first sensor and the second sensor; The calculation module is used to calculate the effective range of the tilt angle of the first sensor and the effective range of the tilt angle of the second sensor based on a preset dual-sensor under-vehicle blind-spot coverage geometric constraint model, combined with the vertical height information, the inherent vertical field of view and the horizontal distance. The output module is used to output the effective value range so that the user can determine and configure the installation tilt angle of the first sensor and the installation tilt angle of the second sensor.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images