High-reflectivity target identification method and device and high-reflectivity object calibration method

Abstract

The invention discloses a high-reflectivity target identification method and device and a high-reflectivity object calibration method, relates to the technical field of laser radar calibration, and mainly aims to solve the problem that the marking accuracy of a high-reflectivity target is reduced due to the fact that the high-reflectivity target and a pseudo high-reflectivity target cannot be accurately distinguished in the prior art. Comprising the following steps: determining a first reflectivity parameter of a target object according to echo energy data and distance data; if the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold value, determining a distance attenuation factor of a high-reflectivity target matched with the distance data according to the distance data of the target object; adjusting the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter; and if the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, marking the target object as a high-reflectivity target.

Description

Technical Field

[0001] The present application relates to the technical field of lidar calibration, and particularly to a method and device for identifying high-reflectivity targets and a method for calibrating high-reflectivity objects. Background Art

[0002] Due to its good object recognition ability, lidar is widely used in fields such as security monitoring, autonomous driving, and intelligent transportation. Its object recognition ability mainly depends on the reflection characteristics of the object surface to laser pulses. Since the reflectivity of high-reflectivity targets is strong and the echo energy is strong, on the point cloud image, a high-reflectivity expansion phenomenon will occur, resulting in a blurred contour of the high-reflectivity target and the surrounding information being masked. Therefore, it is necessary to first mark the high-reflectivity target and filter out the corresponding point cloud to avoid affecting the object recognition ability of the lidar.

[0003] Currently, the existing method for marking high-reflectivity targets is to calibrate the reflectivity and mark the targets with a reflectivity greater than a preset reflectivity threshold as high-reflectivity targets.

[0004] However, in the actual marking process, due to the surface material of some pseudo-high-reflectivity targets, the direction and energy of the reflected light are relatively concentrated, and the difference in echo energy from real high-reflectivity targets is not obvious. Therefore, both will be marked as high-reflectivity targets, resulting in a decrease in the marking accuracy of high-reflectivity targets. Summary of the Invention

[0005] In view of this, the present application provides a method and device for identifying high-reflectivity targets and a method for calibrating high-reflectivity objects, mainly aiming at the problem that the existing method cannot accurately distinguish high-reflectivity targets from pseudo-high-reflectivity targets, resulting in a decrease in the marking accuracy of high-reflectivity targets.

[0006] According to one aspect of the present application, a method for marking high-reflectivity targets of a lidar is provided, including:

[0007] Determine a first reflectivity parameter of a target object according to echo energy data and distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model;

[0008] If the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, determine a distance attenuation factor of a high-reflectivity target matching the distance data according to the distance data of the target object, where the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model;

[0009] Adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter;

[0010] If the second reflectivity parameter is greater than or equal to the second preset reflectivity threshold, the target object is marked as a high-reflectivity target.

[0011] Preferably, the method further includes:

[0012] Collecting echo energy data of a non-high-reflectivity target board at different distance conditions, where the non-high-reflectivity target board includes multiple objects with different reflectivities;

[0013] Fitting the echo energy-distance-reflectivity model according to the reflectivities, distance data, and echo energy data of multiple objects of the non-high-reflectivity target board.

[0014] Preferably, the step of fitting the echo energy-distance-reflectivity model according to the reflectivities, distance data, and echo energy data of multiple objects of the non-high-reflectivity target board includes:

[0015] For each object of the non-high-reflectivity target board, fitting a first echo energy-distance-reflectivity model corresponding to multiple non-high-reflectivity target boards according to the reflectivity, distance data, and echo energy data of the object;

[0016] Performing weighted processing on the first echo energy-distance-reflectivity models corresponding to multiple non-high-reflectivity target boards to obtain the echo energy-distance-reflectivity model.

[0017] Preferably, the distance attenuation factor k is determined according to the following formula:

[0018] k = (Reflectivity1_Hr - ReflectThre) / (A - ReflectThre)

[0019] where Reflectivity1_Hr represents the first reflectivity parameter of a true high-reflectivity target, ReflectThre represents the first preset reflectivity threshold, and A represents the reflectivity limit value collected by the radar;

[0020] Then, the step of adjusting the first reflectivity parameter according to the distance attenuation factor k of the high-reflectivity target to obtain the second reflectivity parameter includes:

[0021] Taking the sum of the quotient obtained by dividing the difference between the first reflectivity parameter and the first preset reflectivity threshold by the distance attenuation factor of the high-reflectivity target and the first preset reflectivity threshold as the second reflectivity parameter.

[0022] Preferably, the method further includes:

[0023] If the second reflectivity parameter is greater than the first preset reflectivity threshold and less than the second preset reflectivity threshold, mark the target object as a pseudo-high-reflectivity target;

[0024] And / or, if the first reflectivity parameter is less than the first preset reflectivity threshold, mark the target object as a non-high-reflectivity target.

[0025] According to another aspect of the present application, a calibration method for high-reflectivity objects is provided, including:

[0026] Use a lidar to collect echo energy data of target plates with different reflectivities at various distances, and obtain a dataset of the echo energy of multiple target plates changing with distance. Among them, the target plates with different reflectivities include a high-reflectivity target plate and at least one non-high-reflectivity target plate;

[0027] According to the echo energy data and distance data of at least one non-high-reflectivity target plate, fit an echo energy-distance-reflectivity model;

[0028] Use the echo energy-distance-reflectivity model to process the echo energy data corresponding to the high-reflectivity target plate, and obtain a calibration result of the high-reflectivity target reflectivity corresponding to the high-reflectivity target plate changing with distance.

[0029] Preferably, before using the lidar to be tested to collect echo energy data of target plates with different reflectivities at various distances and obtain a dataset of the echo energy of multiple target plates changing with distance, the method further includes:

[0030] Construct a standard target plate calibration system to collect echo energy data and distance data. The standard target plate calibration system includes at least one non-high-reflectivity target plate, a high-reflectivity target plate, a slide rail, a transmission shaft, and a lidar;

[0031] Among them, the at least one non-high-reflectivity target plate and the high-reflectivity target plate together form the vertical surfaces of a prism, and each vertical surface is a kind of sample;

[0032] The transmission shaft connects the prism to the slide rail and is used to rotate the prism to switch samples;

[0033] The transmission shaft can slide on the slide rail and is used to adjust the distance between the prism and the lidar.

[0034] According to yet another aspect of the present application, a high-reflectivity target recognition device is provided, including:

[0035] The first reflectivity parameter calculation module is used to determine the first reflectivity parameter of the target object according to the echo energy data and the distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model;

[0036] The first judgment module is used to, if the first reflectivity parameter of the target object is greater than or equal to the first preset reflectivity threshold, determine the distance attenuation factor of the high-reflectivity target that matches the distance data according to the distance data of the target object, where the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model;

[0037] The second reflectivity parameter calculation module is used to adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain the second reflectivity parameter;

[0038] The second judgment module is used to, if the second reflectivity parameter is greater than or equal to the second preset reflectivity threshold, mark the target object as a high-reflectivity target.

[0039] Preferably, the device further includes a fitting module, which is used for:

[0040] Using a lidar to collect echo energy data of non-high-reflectivity target plates under different distance conditions, where the non-high-reflectivity target plates include multiple target plates with different reflectivities;

[0041] According to the reflectivities, distance data, and echo energy data of multiple non-high-reflectivity target plates, fitting to obtain the echo energy-distance-reflectivity model.

[0042] Preferably, the fitting module is further used for:

[0043] For each non-high-reflectivity target plate, according to the reflectivity, distance data, and echo energy data of the target plate, fitting a first echo energy-distance-reflectivity model corresponding one-to-one to multiple non-high-reflectivity target plates;

[0044] Performing weighted processing on the first echo energy-distance-reflectivity models corresponding one-to-one to multiple non-high-reflectivity target plates to obtain the echo energy-distance-reflectivity model.

[0045] Preferably, the distance attenuation factor k is determined according to the following formula:

[0046] k = (Reflectivity1_Hr - ReflectThre) / (A - ReflectThre)

[0047] Among them, Reflectivity 1_Hr represents the first reflectivity parameter of the true high-reflection target, ReflectThre represents the first preset reflectivity threshold, and A represents the reflectivity limit value collected by the radar;

[0048] Then, the second reflectivity parameter calculation module is used for:

[0049] The quotient obtained by dividing the difference between the first reflectivity parameter and the first preset reflectivity threshold by the distance attenuation factor of the high-reflection target, and the sum of the quotient and the first preset reflectivity threshold is used as the second reflectivity parameter.

[0050] Preferably, the device further includes a marking module for:

[0051] If the second reflectivity parameter is greater than the first preset reflectivity threshold and less than the second preset reflectivity threshold, the target object is marked as a pseudo high-reflection target;

[0052] And / or, if the first reflectivity parameter is less than the first preset reflectivity threshold, the target object is marked as a non-high-reflection target.

[0053] According to another aspect of the present application, a storage medium is provided. At least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned method for marking high-reflection targets of lidar and the operations corresponding to the method for calibrating high-reflection objects.

[0054] According to still another aspect of the present application, a terminal is provided, including: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus;

[0055] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned method for marking high-reflection targets of lidar and the operations corresponding to the method for calibrating high-reflection objects.

[0056] By means of the above technical solutions, the technical solutions provided by the embodiments of the present application have at least the following advantages:

[0057] The present application provides a method and device for identifying high-reflectivity targets and a method for calibrating high-reflectivity objects. First, a first reflectivity parameter of a target object is determined based on echo energy data and distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model; if the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, a distance attenuation factor of a high-reflectivity target matching the distance data is determined according to the distance data of the target object, where the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model; the first reflectivity parameter is adjusted according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter; if the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, the target object is marked as a high-reflectivity target.

[0058] Compared with the prior art, in the embodiments of the present application, according to a preset distance decoupling method, a data set of the echo energy of target plates with different reflectivities changing with distance is processed to obtain a calibration result of the reflectivity of a high-reflectivity target plate changing with distance corresponding to the high-reflectivity target plate, that is, the distance attenuation factor corresponding to the high-reflectivity target plate at different distances. During actual marking, first, according to the echo energy-distance-reflectivity model, the first reflectivity parameter of the target object is calculated. When the first reflectivity parameter is greater than the threshold, the second reflectivity parameter is calculated using the matching distance attenuation factor to increase the value of its reflectivity parameter, and a secondary judgment is performed to distinguish the high-reflectivity target from the pseudo-high-reflectivity target, so as to improve the marking accuracy of the high-reflectivity target.

[0059] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specific embodiments of the present application are specifically exemplified. Description of the Drawings

[0060] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0061] Figure 1 A flowchart of a method for identifying a high-reflectivity target provided by an embodiment of the present application is shown;

[0062] Figure 2 A curve graph of the change of echo energy with distance provided by an embodiment of the present application is shown;

[0063] Figure 3 Shows the curve graph of the reflectivity varying with distance provided by the embodiment of the present application;

[0064] Figure 4 Shows the flowchart of a calibration method for a high-reflectivity object provided by the embodiment of the present application;

[0065] Figure 5 Shows the schematic diagram of a calibration system for standard target plates with different reflectivities provided by the embodiment of the present application;

[0066] Figure 6 Shows the block diagram of a high-reflectivity target recognition device provided by the embodiment of the present application;

[0067] Figure 7 Shows the schematic diagram of the structure of a terminal provided by the embodiment of the present application. Detailed implementation manners

[0068] Hereinafter, the exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0069] Meanwhile, it should be understood that, for the sake of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0070] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way limits the present application and its application or use.

[0071] The techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said techniques, methods and devices should be regarded as part of the description.

[0072] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0073] Embodiments of the present application can be applied to a computer system / server, which can operate together with many other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0074] The computer system / server can be described in the general context of computer system-executable instructions, such as program modules, executed by the computer system. Generally, program modules can include routines, programs, target programs, components, logic, data structures, and so on, which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0075] Since high-reflectivity objects will produce the phenomenon of high-reflectivity expansion in the radar point cloud, the contours of high-reflectivity targets are blurred and the surrounding information is masked. Therefore, generally before processing radar point cloud data, the algorithm is set to first automatically filter out data points with too high reflectivity and then transfer them to the backend for processing to improve processing efficiency. However, this method will produce misjudgments. For example, some targets also have a relatively high reflectivity, but they do not produce the phenomenon of high-reflectivity expansion. The above objects are called "pseudo-high-reflectivity" targets. Different from the diffuse reflection form of true high-reflectivity targets, such targets are often due to special surface texture structures and other reasons, resulting in the direction and energy of the reflected light being more concentrated, so the received echo energy is also more concentrated, and therefore the reflectivity detected by the radar will also be relatively high. However, since the pseudo-high-reflectivity target itself does not produce the phenomenon of high-reflectivity expansion and is still admissible data, the traditional method will wrongly filter out this type of data.

[0076] The present application proposes a method that can further confirm whether the object belongs to a true high-reflectivity target or a pseudo-high-reflectivity target when the reflectivity of the object is detected to exceed the judgment threshold, and does not filter out the pseudo-high-reflectivity target, but only filters out the true high-reflectivity target, thereby improving the utilization rate and accuracy of radar point cloud data.

[0077] Embodiments of the present application first provide a calibration method for high-reflectivity objects, as Figure 4 shown, the method includes:

[0078] 201. Use a lidar to collect the echo energy data of target plates with different reflectivities at various distances, and obtain a data set of the echo energy of multiple target plates varying with distance. Among them, the target plates with different reflectivities include a high-reflectivity target plate and at least one non-high-reflectivity target plate.

[0079] In the embodiments of the present application, step 201 is completed by using a pre-constructed reflectivity standard target plate calibration system. Specifically, the system may include: The standard target plate calibration system includes at least one non-high-reflectivity target plate, a high-reflectivity target plate, a slide rail, a transmission shaft, and a lidar; among them, at least one non-high-reflectivity target plate and the high-reflectivity target plate respectively serve as one facade of a prism; the transmission shaft connects the prism to the slide rail and is used to rotate the prism to switch the target plate; the transmission shaft can slide on the slide rail to adjust the distance between the prism and the lidar.

[0080] As Figure 5 shown, a different reflectivity standard target plate calibration system includes multiple non-high-reflectivity target plates (101, 102, 103) with different reflectivities, a high-reflectivity target plate (104), a slide rail (301), a transmission shaft (302), and a lidar (200); the multiple non-high-reflectivity target plates and the high-reflectivity target plate jointly form the facades of a prism, and each facade is a kind of sample; the transmission shaft connects the prism to the slide rail and is used to rotate the prism to switch the sample; the transmission shaft can slide on the slide rail to adjust the distance between the prism and the lidar.

[0081] Among them, the non-high-reflectivity target plates (101, 102, 103) can respectively use target plates with reflectivities of 90%, 40%, and 10%, and the high-reflectivity target plate (104) can use a target plate made of a true high-reflectivity material. The number of non-high-reflectivity target plates is at least one. Of course, in this case, the non-high-reflectivity target plate selects a value within the normal range and a relatively high value for the reflectivity, such as 90%, because it is closer to the characteristics of the high-reflectivity target plate.

[0082] 202. Fit an echo energy-distance-reflectivity model according to the echo energy data and distance data of at least one non-high-reflectivity target plate.

[0083] According to Figure 5 the system, move the transmission shaft 302 to change the distance between the radar and the target plate, rotate the four faces of the prism, and collect the echo energy data of each target plate at multiple distances. The echo energy data shows that the echo energy of the non-high-reflectivity target plates (101, 102, 103) varies with distance, and the greater the distance, the lower the echo energy. Due to its too high reflectivity, the echo energy of the high-reflectivity target plate (104) approaches saturation at different distances, that is, the limit value that the radar can detect. Therefore, the echo energy of the high-reflectivity target presents a straight line at different distances. As Figure 2 shown, Figure 2The uppermost straight line corresponds to the high-reflectivity target plate 104, and the three curves slanting downward to the lower right below respectively correspond to the echo energy and distance data of the three non-high-reflectivity target plates (101, 102, 103). Among them, the abscissa represents the distance data, and the ordinate represents the echo energy data.

[0084] In practice, since the reflectivity of an object is only related to the material and surface parameters of the object, the reflectivity of the object should be a constant parameter. However, the distance between the object and the radar will also affect the amount of echo energy received by the radar. The greater the distance, the higher the dissipation and loss of energy. Therefore, from the measured data, the greater the distance between the radar and the object, the lower the echo energy of the object detected by the radar, and the lower the reflectivity. Therefore, the echo data corresponding to the non-high-reflectivity target plates will show a downward trend from the upper left to the lower right. As Figure 2 shown, the three curves slanting downward to the lower right below the straight line respectively correspond to the measured data of the three non-high-reflectivity target plates.

[0085] That is to say, the reflectivity of the object detected by the radar is not only related to the material of the object itself, but also related to the distance. Therefore, for the echo energy data of the three non-high-reflectivity target plates collected above, it is necessary to eliminate the influence factor of the distance on the reduction of the reflectivity, that is, decouple the reflectivity and the distance, so that the reflectivity of the object detected by the radar shows a trend that does not change with the distance, which is closer to the actual situation (since the reflectivity of the high-reflectivity target plate does not change with the distance, the data of the high-reflectivity target plate is not used in the decoupling process).

[0086] Specifically, for the non-high-reflectivity target plates (101, 102, 103), as Figure 2 shown, using the above echo energy data, the corresponding distance data, and the reflectivity for fitting processing, the first echo energy-distance-reflectivity model of the non-high-reflectivity object is obtained as follows:

[0087]

[0088] Among them, E received represents the echo energy data, r represents the distance data, α represents the model parameter, and ρ represents the true reflectivity of the target plate.

[0089] When fitting the first echo energy-distance-reflectivity model corresponding to any non-high-reflectivity target plate, the reflectivity ρ is known, and the echo energy data can be actually collected (due to the influence of the detection environment and conditions, the echo energy data may fluctuate, such as Figure 2Among them, at each distance, the curve or straight line corresponds to multiple points. When fitting, the lowest echo energy corresponding to each distance can be taken). r represents the distance data, which is also a known quantity. The only parameter to be fitted in the formula is α. That is to say, the obtained model parameter α can make the reflectivity ρ remain constant under different distances and echo energy conditions. Therefore, the process of obtaining α can be regarded as a process of decoupling the reflectivity of the object from the distance, so that the reflectivity of non-high-reflectivity objects does not change with the change of distance.

[0090] α can be fitted by choosing a polynomial. For example, a quadratic or cubic polynomial can be chosen, expressed as α = ar 2 + br + c. Exemplarily, for three non-high-reflectivity target plates (101, 102, 103) with reflectivities ρ = 90%, ρ = 40%, and ρ = 10% respectively, the corresponding α are expressed as α(ρ = 90%) = a1r 2 + b1r + c1, α(ρ = 40%) = a2r 2 + b2r + c2, α(ρ = 10%) = a3r 2 + b3r + c3.

[0091] Exemplarily, for α(ρ = 90%) = a1r 2 + b1r + c1, substituting the echo energy data and distance data with ρ = 90%, a1, b1, and c1 are obtained by fitting, and then α(ρ = 90%) and the corresponding first echo energy-distance-reflectivity model are obtained:

[0092]

[0093] Similarly, α(ρ = 40%) and α(ρ = 10%) and their corresponding first echo energy-distance-reflectivity models can be obtained. The decoupling results can be seen Figure 3 in the three lines closer to the horizontal coordinate system at the lower part in [reference], where the abscissa represents the distance data and the ordinate represents the reflectivity. It can be seen that at medium and long distances, the reflectivity no longer changes with the distance (this law is not followed at short distances because the short-distance scenario is relatively special, and there will be special treatment measures for this scenario later).

[0094] Finally, according to the first echo energy-distance-reflectivity models of each non-high-reflectivity object, the echo energy-distance-reflectivity model for this lidar is obtained. For example, the model parameters of multiple first echo energy-distance-reflectivity models are weighted. Specifically, in the model parameter α = ar 2 + br + c of the echo energy-distance-reflectivity model of this lidar, each coefficient is Thus, the wave energy-distance-reflectivity model of this lidar is obtained by fitting.

[0095] Among them, the value of the weighting coefficient is related to the reflectivity. When the reflectivity is higher, it is closer to the reflection situation of a highly reflective object. Therefore, the higher the reflectivity, the higher the weight value is set. In this embodiment, the weights of three non-highly reflective objects with ρ = 90%, ρ = 40%, and ρ = 10% can be set to Of course, other values can also be adopted for the weights.

[0096] Among them, the number of non-highly reflective target plates and the reflectivity values can be different from those in the embodiment. The more the number of highly reflective target plates and the more the reflectivity values cover the three levels of high, medium, and low, the higher the fitting accuracy, and the more comprehensive the radar considers objects with multiple different reflectivities. For example, when six non-highly reflective target plates with reflectivities of 90%, 70%, 50%, 30%, 10%, and 5% are used for fitting, at this time, the weights also need to be adjusted adaptively.

[0097] 203. Use the echo energy-distance-reflectivity model to process the echo energy data corresponding to the highly reflective target plate, and obtain the calibration result of the reflectivity of the highly reflective target corresponding to the highly reflective target plate changing with distance.

[0098] It should be noted that although the echo energy-distance-reflectivity model of the lidar is fitted according to non-highly reflective target plates, since the echo data of highly reflective target plates and non-highly reflective target plates are collected under the same test conditions, the distance decoupling law reflected by the echo energy-distance-reflectivity model also affects the detection process of the lidar for highly reflective targets. That is, substitute the echo energy data, distance data of the highly reflective target plate 104, and the model parameters α = ar 2 +br + c into the echo energy-distance-reflectivity model to obtain the change trend of the reflectivity of the highly reflective target plate with distance, such as Figure 3 the curve extending upward to the upper right at the top (hereinafter referred to as the highly reflective decoupling curve).

[0099] According to Figure 3 it can be seen that even if the reflectivity of the highly reflective object itself is fixed, after distance decoupling processing, the reflectivity of the highly reflective object detected by the radar changes with distance. Figure 3 The highly reflective decoupling curve in

[0100] In the actual application process, for a certain target to be measured, the measured echo energy and distance r are substituted into the pre-fitted echo energy-distance-reflectivity model of the lidar, and the reflectivity (referred to as the first reflectivity parameter) ρ of the target to be measured can be obtained. Then, it is compared with the value of the high-reflectivity decoupling curve at the same distance r. When the first reflectivity parameter is greater than the latter, the target to be measured is considered a high-reflectivity object.

[0101] Therefore, there is a difference between the method proposed in this application and the traditional method. The traditional method believes that regardless of the distance, as long as the reflectivity of the target to be measured is greater than a fixed, artificially set high-reflectivity threshold, it will be identified as a high-reflectivity target. In this application, it is considered that the determination of a high-reflectivity target should first exclude the influence of distance, and different determination thresholds should be adopted at different distances to avoid misjudging a pseudo-high-reflectivity target as a high-reflectivity target.

[0102] Accordingly, this application further proposes a method for identifying high-reflectivity targets, which is applied to a lidar that is performing a target detection task, such as Figure 1 shown, the method includes:

[0103] 101. Determine the first reflectivity parameter of the target object according to the echo energy data and distance data.

[0104] During the lidar detection process, the lidar emits laser light to any target object in the environment, such as a vehicle, a person, a static building, etc., and receives the echo energy data reflected by the target object, and generates corresponding point cloud information according to the echo energy signal. Among them, the point cloud information includes the distance data of the target object relative to the lidar.

[0105] Among them, the first reflectivity parameter is calculated according to the distance data of the target object, the echo energy data of the target object, and the pre-fitted echo energy-distance-reflectivity model. For the fitting process of the echo energy-distance-reflectivity model, refer to the above embodiment, which is expressed as the following formula:

[0106]

[0107] Among them, E received represents the echo energy data, r represents the distance data, α represents the model parameter, and ρ represents the first reflectivity parameter.

[0108] 102. If the first reflectivity parameter of the target object is greater than or equal to the first preset reflectivity threshold, then determine the distance attenuation factor of the high-reflectivity target that matches the distance data according to the distance data of the target object.

[0109] Among them, the first preset reflectivity threshold can be preset in advance. In this embodiment, it can be set to be more than half of the limit value of the reflectivity that the radar can detect; the distance attenuation factor of the high-reflection target is related to the distance and is obtained by decoupling the reflectivity of the high-reflection target using the echo energy-distance-reflectivity model.

[0110] 103. Adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflection target to obtain the second reflectivity parameter.

[0111] In the embodiment of the present application, when the first reflectivity parameter is greater than or equal to the first preset reflectivity threshold, the target object can be first marked as a suspected high-reflection target. At this time, the first reflectivity parameter can be adjusted according to the distance attenuation factor of the high-reflection target that matches the distance data to obtain the second reflectivity parameter for secondary judgment.

[0112] It should be noted that the second reflectivity parameter is generally greater than the first reflectivity parameter, and the second preset reflectivity threshold is generally also greater than the first preset reflectivity threshold. Further, according to the second preset reflectivity threshold, it is judged whether it is a true high-reflection target, so as to distinguish the high-reflection target from the pseudo-high-reflection target, effectively improving the marking accuracy of the high-reflection target.

[0113] 104. If the second reflectivity parameter is greater than or equal to the second preset reflectivity threshold, mark the target object as a high-reflection target.

[0114] In the embodiment of the present application, when the second reflectivity parameter is greater than or equal to the second preset reflectivity threshold, it can be determined that the target object is a true high-reflection target. At this time, it can be marked as a high-reflection target. In a specific application scenario, the second reflectivity threshold can take the limit value of the reflectivity that the radar can detect.

[0115] Compared with the prior art, in the embodiment of the present application, first, according to the echo energy-distance-reflectivity model, the first reflectivity parameter of the target object is calculated. When the first reflectivity parameter is greater than the threshold, the second reflectivity parameter is calculated using the matching distance attenuation factor and secondary judgment is performed, so as to distinguish the high-reflection target from the pseudo-high-reflection target and improve the marking accuracy of the high-reflection target.

[0116] In an embodiment of the present application, the distance attenuation factor is determined according to the following relationship:

[0117] k = (Reflectivity1_Hr - ReflectThre) / (A - ReflectThre)

[0118] Among them, k represents the distance attenuation factor, Reflectivity 1_Hr represents the points on the above-mentioned high-reflectivity decoupling curve, that is, the first reflectivity parameter corresponding to the true high-reflectivity target. At different distances, the value of Reflectivity 1_Hr is different. ReflectThre represents the first preset reflectivity threshold, and A represents the radar acquisition threshold, that is, the limit value of the reflectivity that the radar can detect.

[0119] That is to say, because Reflectivity 1_Hr changes with distance, k is also a parameter that changes with distance.

[0120] In an embodiment of the present application, for further limitation and explanation, step 103 of the embodiment adjusts the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter, including: taking the sum of the quotient obtained by dividing the difference between the first reflectivity parameter and the first preset reflectivity threshold by the distance attenuation factor of the high-reflectivity target and the first preset reflectivity threshold as the second reflectivity parameter.

[0121] Specifically, the calculation formula of the second reflectivity parameter is expressed as the following formula

[0122] Reflectivity2 = (Reflectivity1 - ReflectThre) / k + ReflectThre

[0123] Among them, Reflectivity2 represents the second reflectivity parameter, and Reflectivity1 represents the first reflectivity parameter of the target object. The second reflectivity threshold generally corresponds to the limit value of the reflectivity detected by the radar, that is, A. If the reflectivity that the radar can detect is mapped between 0 and 255, then A takes 255, and ReflectThre can take 100.

[0124] In an embodiment of the present application, for further limitation and explanation, the embodiment method further includes: if the second reflectivity parameter is greater than the first preset reflectivity threshold and less than the second preset reflectivity threshold, then mark the target object as a pseudo high-reflectivity target.

[0125] In an embodiment of the present application, for further limitation and explanation, the embodiment method further includes: if the first reflectivity parameter is less than the first preset reflectivity threshold, then mark the target object as a non-high-reflectivity target.

[0126] It should be noted that the application scenarios of the above embodiments do not have good effects at all detection distances. For example Figure 3Among them, the echo data of the decoupled non-high-reflectivity target board presents a standard straight line at medium and long distances, but the effect at close range is not satisfactory. This is because when the distance between the target object and the lidar is relatively close, due to the strong echo energy of the true high-reflectivity target, multiple reflection phenomena will occur, resulting in distorted fitting results. Therefore, the distance range of the application effect of the above embodiments is at medium and long distances, that is, greater than 5 meters or greater than 10 meters, and the effect of using the high-reflectivity decoupling curve or the distance attenuation factor to identify high-reflectivity objects is better.

[0127] At short distances, due to the obvious ghost noise in the point cloud data of the high-reflectivity target at short distances, therefore, the ghost noise characteristics in the point cloud dimension can be used to identify the high-reflectivity target, and then directly filter it. No specific limitation is made in this application.

[0128] This application provides a method for identifying high-reflectivity targets. First, determine the first reflectivity parameter of the target object according to the echo energy data and the distance data. Among them, the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model; if the first reflectivity parameter of the target object is greater than or equal to the first preset reflectivity threshold, then according to the distance data of the target object, determine the distance attenuation factor of the high-reflectivity target that matches the distance data. Among them, the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target using the echo energy-distance-reflectivity model; adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter; if the second reflectivity parameter is greater than or equal to the second preset reflectivity threshold, then mark the target object as a high-reflectivity target.

[0129] Compared with the prior art, the embodiment of this application obtains the calibration result of the change of the reflectivity of the high-reflectivity target with distance according to the preset distance decoupling method, that is, the distance attenuation factor corresponding to the high-reflectivity target at different distances, and uses the matching distance attenuation factor to adjust the target reflectivity, so as to distinguish the high-reflectivity target from the pseudo-high-reflectivity target and improve the marking accuracy of the high-reflectivity target.

[0130] In the embodiment of this application, the specific fitting process and the specific calibration process have been described in detail in the above embodiments, and will not be repeated here.

[0131] The present application provides a calibration method for highly reflective objects. By using a lidar to collect echo energy data of target plates with different reflectivities at various distances, a data set of the echo energy of multiple target plates varying with distance is obtained. Among them, the target plates with different reflectivities include a highly reflective target plate and at least one non-highly reflective target plate. According to the echo energy data and distance data of at least one non-highly reflective target plate, an echo energy-distance-reflectivity model is fitted. Using the echo energy-distance-reflectivity model, the echo energy data corresponding to the highly reflective target plate is processed to obtain a calibration result of the highly reflective target reflectivity varying with distance corresponding to the highly reflective target plate.

[0132] Compared with the prior art, in the embodiment of the present application, according to a preset distance decoupling method, a data set of the echo energy of target plates with different reflectivities varying with distance is processed to obtain a calibration result of the highly reflective target reflectivity varying with distance corresponding to the highly reflective target plate, that is, a highly reflective decoupling curve. The highly reflective target and the pseudo-highly reflective target are distinguished according to the highly reflective decoupling curve to improve the marking accuracy of the highly reflective target.

[0133] Further, as an implementation of the method shown above Figure 1 In the embodiment of the present application, a highly reflective target recognition device is provided, as Figure 6 shown. The device includes:

[0134] A first reflectivity parameter calculation module 31, a first judgment module 32, a second reflectivity parameter calculation module 33, and a second judgment module 34;

[0135] The first reflectivity parameter calculation module 31 is used to determine the first reflectivity parameter of the target object according to the echo energy data and distance data. Among them, the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model.

[0136] The first judgment module 32 is used to, if the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, determine the distance attenuation factor of the highly reflective target matching the distance data according to the distance data of the target object. Among them, the distance attenuation factor of the highly reflective target is obtained by performing distance decoupling on the reflectivity of the highly reflective target using the echo energy-distance-reflectivity model.

[0137] The second reflectivity parameter calculation module 33 is used to adjust the first reflectivity parameter according to the distance attenuation factor of the highly reflective target to obtain a second reflectivity parameter.

[0138] The second judgment module 34 is used to, if the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, mark the target object as a highly reflective target.

[0139] Preferably, the device further includes a fitting module for:

[0140] Collecting echo energy data of a non-high-reflectivity target board at different distances by using a lidar, where the non-high-reflectivity target board includes multiple target boards with different reflectivities;

[0141] Fitting the echo energy-distance-reflectivity model according to the reflectivities, distance data, and echo energy data of multiple non-high-reflectivity target boards.

[0142] Preferably, the fitting module is further used for:

[0143] For each non-high-reflectivity target board, fitting a first echo energy-distance-reflectivity model corresponding one-to-one to multiple non-high-reflectivity target boards according to the reflectivity, distance data, and echo energy data of the target board;

[0144] Performing a weighting process on the first echo energy-distance-reflectivity models corresponding one-to-one to multiple non-high-reflectivity target boards to obtain the echo energy-distance-reflectivity model.

[0145] Preferably, the distance attenuation factor k is determined according to the following formula:

[0146] k = (Reflectivity1_Hr - ReflectThre) / (A - ReflectThre)

[0147] where Reflectivity1_Hr represents the first reflectivity parameter of a true high-reflectivity target, ReflectThre represents the first preset reflectivity threshold, and A represents the reflectivity limit value collected by the radar;

[0148] Then, the second reflectivity parameter calculation module is used for:

[0149] Taking the sum of the quotient obtained by dividing the difference between the first reflectivity parameter and the first preset reflectivity threshold by the distance attenuation factor of the high-reflectivity target and the first preset reflectivity threshold as the second reflectivity parameter.

[0150] Preferably, the device further includes a marking module for:

[0151] If the second reflectivity parameter is greater than the first preset reflectivity threshold and less than the second preset reflectivity threshold, then marking the target object as a pseudo-high-reflectivity target;

[0152] and / or, if the first reflectivity parameter is less than the first preset reflectivity threshold, then marking the target object as a non-high-reflectivity target.

[0153] The present application provides a high-reflectivity target recognition device. First, a first reflectivity parameter of a target object is determined according to echo energy data and distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model. If the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, a distance attenuation factor of a high-reflectivity target matching the distance data is determined according to the distance data of the target object, where the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model. The first reflectivity parameter is adjusted according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter. If the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, the target object is marked as a high-reflectivity target. Compared with the prior art, in the embodiment of the present application, according to a preset distance decoupling method, a data set of the echo energy of target plates with different reflectivities changing with distance is processed to obtain a calibration result of the reflectivity of the high-reflectivity target corresponding to the high-reflectivity target plate changing with distance, that is, the distance attenuation factor corresponding to the high-reflectivity target plate at different distances. During actual marking, first, according to the echo energy-distance-reflectivity model, the first reflectivity parameter of the target object is calculated. When the first reflectivity parameter is greater than the threshold, the second reflectivity parameter is calculated using the matching distance attenuation factor to increase its reflectivity parameter value, and a secondary judgment is performed to distinguish the high-reflectivity target from the pseudo-high-reflectivity target, so as to improve the marking accuracy of the high-reflectivity target.

[0154] According to an embodiment of the present application, there is provided a storage medium storing at least one executable instruction, and the computer executable instruction can execute the high-reflectivity target recognition method and the calibration method of a high-reflectivity object in any of the above method embodiments.

[0155] Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0156] Figure 7 FIG. shows a schematic structural diagram of a terminal according to an embodiment of the present application. The specific implementation of the terminal is not limited in the specific embodiments of the present application.

[0157] As Figure 7As shown in the figure, the terminal may include: a processor 402, a communications interface 404, a memory 406, and a communication bus 408.

[0158] Among them: the processor 402, the communication interface 404, and the memory 406 communicate with each other through the communication bus 408.

[0159] The communication interface 404 is used to communicate with network elements of other devices such as clients or other servers.

[0160] The processor 402 is used to execute the program 410, and specifically can execute the relevant steps in the above-mentioned embodiments of the high-back target recognition method and the calibration method of high-back objects.

[0161] Specifically, the program 410 may include program code, and the program code includes computer operation instructions.

[0162] The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the computer device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0163] The memory 406 is used to store the program 410. The memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0164] The program 410 is specifically used to cause the processor 402 to perform the following operations:

[0165] Determine the first reflectivity parameter of the target object according to the echo energy data and the distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model;

[0166] If the first reflectivity parameter of the target object is greater than or equal to the first preset reflectivity threshold, then determine the distance attenuation factor of the high-back target matching the distance data according to the distance data of the target object, where the distance attenuation factor of the high-back target is obtained by performing distance decoupling on the reflectivity of the high-back target using the echo energy-distance-reflectivity model;

[0167] Adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflection target to obtain a second reflectivity parameter;

[0168] If the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, mark the target object as a high-reflection target.

[0169] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the entity device hardware and software resources of the above high-reflection target recognition method and the calibration method of the high-reflection object, supporting the operation of the information processing program and other software and / or programs. The network communication module is used to implement the communication between the components inside the storage medium, as well as the communication with other hardware and software in the information processing entity device.

[0170] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is the difference from other embodiments. For the same or similar parts between the embodiments, reference can be made to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the description of the method embodiment.

[0171] The methods and systems of the present application can be implemented in many ways. For example, the methods and systems of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the method is only for illustration. The steps of the method of the present application are not limited to the above specific described order, unless otherwise specifically stated. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0172] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.

[0173] The above are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for identifying high-reflectivity targets, characterized in that, Including: Determine a first reflectivity parameter of a target object according to echo energy data and distance data, where the first reflectivity parameter is calculated according to the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model; If the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, determine a distance attenuation factor of a high-reflectivity target that matches the distance data according to the distance data of the target object, where the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model; Adjust the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter; If the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, mark the target object as a high-reflectivity target.

2. The method according to claim 1, wherein The method further includes: Collect echo energy data of a non-high-reflectivity target board under different distance conditions using a lidar, where the non-high-reflectivity target board includes multiple target boards with different reflectivities; Fit the echo energy-distance-reflectivity model according to the reflectivities, distance data, and echo energy data of multiple non-high-reflectivity target boards.

3. The method according to claim 2, wherein The step of fitting the echo energy-distance-reflectivity model according to the reflectivities, distance data, and echo energy data of multiple non-high-reflectivity target boards includes: For each non-high-reflectivity target board, fit a first echo energy-distance-reflectivity model corresponding one-to-one to multiple non-high-reflectivity target boards according to the reflectivity, distance data, and echo energy data; Perform a weighted processing on the first echo energy-distance-reflectivity models corresponding one-to-one to multiple non-high-reflectivity target boards to obtain the echo energy-distance-reflectivity model.

4. The method according to claim 2, characterized in that, The distance attenuation factor k is determined according to the following formula: k = (Reflectivity1_Hr - ReflectThre) / (A - ReflectThre) where Reflectivity1_Hr represents the first reflectivity parameter of a true high-reflectivity target, ReflectThre represents the first preset reflectivity threshold, and A represents the maximum reflectivity value collected by the radar; Then, the step of adjusting the first reflectivity parameter according to the distance attenuation factor k of the high-reflectivity target to obtain a second reflectivity parameter includes: Use the sum of the quotient obtained by dividing the difference between the first reflectivity parameter and the first preset reflectivity threshold by the distance attenuation factor of the high-reflectivity target and the first preset reflectivity threshold as the second reflectivity parameter.

5. The method according to claim 1, wherein The method further includes: If the second reflectivity parameter is greater than the first preset reflectivity threshold and less than the second preset reflectivity threshold, mark the target object as a pseudo high-reflectivity target; and / or, if the first reflectivity parameter is less than the first preset reflectivity threshold, mark the target object as a non-high-reflectivity target.

6. A calibration method for high-reflectivity objects, characterized in that, Including: Collect the echo energy data of target plates with different reflectivities at various distances using a lidar, and obtain a data set of the echo energy of multiple target plates varying with distance. Among them, the target plates with different reflectivities include a high-reflectivity target plate and at least one non-high-reflectivity target plate; Based on the echo energy data and distance data of at least one non-high-reflectivity target plate, fit an echo energy-distance-reflectivity model; Use the echo energy-distance-reflectivity model to process the echo energy data corresponding to the high-reflectivity target plate, and obtain a calibration result of the high-reflectivity target reflectivity varying with distance.

7. The method according to claim 6, wherein Before collecting the echo energy data of target plates with different reflectivities at various distances using the lidar to be measured and obtaining a data set of the echo energy of multiple target plates varying with distance, the method further includes: Construct a standard target plate calibration system for collecting echo energy data and distance data. The standard target plate calibration system includes at least one non-high-reflectivity target plate, a high-reflectivity target plate, a slide rail, a transmission shaft, and a lidar; Among them, the at least one non-high-reflectivity target plate and the high-reflectivity target plate together form the vertical surfaces of a prism, and each vertical surface is a kind of sample; The transmission shaft connects the prism to the slide rail and is used to rotate the prism to switch samples; The transmission shaft can slide on the slide rail and is used to adjust the distance between the prism and the lidar.

8. A high-backscattering target recognition device, characterized in that, Including: A first reflectivity parameter calculation module for determining a first reflectivity parameter of a target object according to echo energy data and distance data. Among them, the first reflectivity parameter is calculated based on the distance data, the echo energy data of the target object, and a pre-fitted echo energy-distance-reflectivity model; A first judgment module for, if the first reflectivity parameter of the target object is greater than or equal to a first preset reflectivity threshold, determining a distance attenuation factor of a high-reflectivity target that matches the distance data according to the distance data of the target object. Among them, the distance attenuation factor of the high-reflectivity target is obtained by decoupling the reflectivity of the high-reflectivity target with respect to distance using the echo energy-distance-reflectivity model; A second reflectivity parameter calculation module for adjusting the first reflectivity parameter according to the distance attenuation factor of the high-reflectivity target to obtain a second reflectivity parameter; A second judgment module for, if the second reflectivity parameter is greater than or equal to a second preset reflectivity threshold, marking the target object as a high-reflectivity target.

9. A storage medium, wherein at least one executable instruction is stored in the storage medium, characterized in that, The executable instructions cause the processor to perform the operations corresponding to the high-reflectivity target recognition method described in any one of claims 1-5, and / or the operations corresponding to the calibration method of the high-reflectivity object described in any one of claims 6 or 7.

10. A terminal, comprising: A processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used for storing at least one executable instruction, characterized in that the executable instruction causes the processor to perform operations corresponding to the high-reflectivity target recognition method described in any one of claims 1-5, and / or operations corresponding to the calibration method of the high-reflectivity object described in any one of claims 6 or 7.

Images