LiDAR-based methods, devices, and electronic equipment for identifying specular reflective objects.

Abstract

This invention discloses a method, device, and electronic device for identifying specularly reflective objects based on lidar, belonging to the field of intelligent hardware technology. The method includes: acquiring reflected laser signals received by lidar; determining the distance between the target object and the lidar, and the light intensity data of the reflected laser signal, based on the reflected laser signal; determining whether the target object is a specularly reflective object based on the light intensity data; if the target object is a specularly reflective object, filtering out light intensity point cloud data that conforms to the light intensity mode; fitting the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain fitting function parameters; and determining the category of the specularly reflective object based on the fitting function parameters. The lidar-based specularly reflective object identification method disclosed in this invention can not only identify specularly reflective objects but also identify the refined category to which the specularly reflective object belongs.

Description

Technical Field

[0001] This invention relates to the field of smart hardware technology, and in particular to a method and device for identifying specular reflective objects based on lidar, and an electronic device. Background Technology

[0002] LiDAR measures distance by receiving pulsed laser light emitted by the robot. However, in current robotic applications, objects with transmissive and specular reflection properties, such as glass, smooth metal surfaces, and mirrors, severely interfere with the robot's mapping, localization, and navigation. Glass transmits light, making it impossible for LiDAR to effectively perceive and model transparent environmental structures like glass doors and walls during robot mapping and navigation. Furthermore, other smooth, mirror-like objects, such as mirrors, smooth metal, and tiles, reflect the laser light specularly, causing it to hit other obstacles. When the mirror object has high reflectivity, the reflected light returns along the optical path and is received by the LiDAR; when the reflectivity is low, the reflected light cannot be detected by the LiDAR. All these phenomena lead to incorrect laser measurement values ​​from the LiDAR, ultimately affecting mapping quality and consequently impacting the robot's localization and navigation. Therefore, identifying specularly reflective objects has become a critical problem that urgently needs to be solved in the field of robotics.

[0003] In existing technologies, the following methods are commonly used to identify specular reflective objects: Method 1: Using ultrasonic sensors to detect obstacles such as glass that optical sensors cannot detect; Method 2: Fusing data from multiple ultrasonic ranging sensors and laser ranging sensors to detect glass and create maps in multi-glass scenarios. It is evident that existing technologies all require ultrasonic ranging sensors for glass detection, which has the following drawbacks: First, it requires installing more sensors, increasing costs; second, ultrasonic sensors have low accuracy and stability, resulting in poor reliability of detection results. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, and electronic device for identifying specular reflective objects based on lidar, which can solve the problems of high cost and poor reliability of detection results in existing specular reflective object identification schemes.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] This invention provides a method for identifying specular reflective objects based on lidar, wherein the method includes: acquiring a reflected laser signal received by the lidar, wherein the reflected laser signal is a signal reflected back when a laser pulse signal emitted by the lidar encounters a target object;

[0007] Based on the reflected laser signal, the distance between the target object and the lidar, as well as the light intensity data of the reflected laser signal, are determined.

[0008] Based on the light intensity data, determine whether the target object is a specular reflective object;

[0009] When the target object is a specular reflective object, select the light intensity point cloud data that matches the light intensity mode;

[0010] The light intensity data and distance of the light intensity point cloud data are fitted by a Gaussian mixture model to obtain the fitting function parameters;

[0011] Based on the parameters of the fitting function, the category of the specular reflective object is determined.

[0012] Optionally, the step of determining whether the target object is a specularly reflective object based on the light intensity data includes:

[0013] Filter out the target light intensity data whose distance is less than the first preset distance from the light intensity data;

[0014] Based on the target light intensity data, determine whether the target object is a specular reflective object.

[0015] Optionally, the step of determining whether the target object is a specular reflective object based on the target light intensity data includes:

[0016] Determine whether there is a light intensity mode in the target light intensity data; wherein, the light intensity mode is a shape in which the difference between the light intensity value of a preset number of intermediate points and the light intensity value of the surrounding points is greater than a first preset value;

[0017] If it exists, the target object is determined to be a specular reflective object;

[0018] If it does not exist, the target object is determined to be a non-specular reflective object.

[0019] Optionally, the step of determining the category of the specularly reflecting object based on the fitting function parameters includes:

[0020] Based on the parameters of the fitting function, the specular reflection characteristics are determined;

[0021] Based on the specular reflection characteristics, the category of the specularly reflecting object is determined.

[0022] Optionally, the step of determining the category of the specularly reflecting object based on the fitting function parameters includes:

[0023] Based on the fitting function parameters, the light intensity distribution on the surface of the specularly reflective object is determined;

[0024] The category of the specularly reflective object is determined based on the light intensity distribution on its surface.

[0025] This invention provides a specular reflective object identification device based on lidar, wherein the device includes:

[0026] The acquisition module is used to acquire the reflected laser signal received by the lidar, wherein the reflected laser signal is the signal reflected back when the laser pulse signal emitted by the lidar encounters the target object;

[0027] The first determining module is used to determine the distance between the target object and the lidar and the light intensity data of the reflected laser signal based on the reflected laser signal.

[0028] The judgment module is used to determine whether the target object is a specular reflective object based on the light intensity data;

[0029] The filtering module is used to filter out light intensity point cloud data that conform to the light intensity mode when the target object is a specular reflective object.

[0030] The fitting module is used to fit the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain the fitting function parameters.

[0031] The second determining module is used to determine the category of the specular reflection object based on the fitting function parameters.

[0032] Optionally, the determination module includes:

[0033] The first submodule is used to filter out target light intensity data whose corresponding distance is less than a first preset distance from the light intensity data;

[0034] The second submodule is used to determine whether the target object is a specular reflective object based on the target light intensity data.

[0035] Optionally, the second submodule is specifically used for:

[0036] Determine whether there is a light intensity mode in the target light intensity data; wherein, the light intensity mode is a shape in which the difference between the light intensity value of a preset number of intermediate points and the light intensity value of the surrounding points is greater than a first preset value;

[0037] If it exists, the target object is determined to be a specular reflective object;

[0038] If it does not exist, the target object is determined to be a non-specular reflective object.

[0039] Optionally, the fitting module includes:

[0040] The third submodule is used to determine the specular reflection characteristics based on the fitting function parameters;

[0041] The fourth submodule is used to determine the category of the specularly reflecting object based on the specular reflection characteristics.

[0042] Optionally, the fitting module includes:

[0043] The fifth submodule is used to determine the light intensity distribution on the surface of the specular reflective object based on the fitting function parameters;

[0044] The sixth submodule is used to determine the category of the specular reflective object based on the light intensity distribution on the surface of the specular reflective object.

[0045] This invention provides an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of any of the above-described laser radar-based specular reflection object recognition methods.

[0046] This invention provides a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of any of the above-described laser radar-based specular reflection object recognition methods.

[0047] The specular reflection object identification scheme based on lidar provided in this invention acquires the reflected laser signal received by the lidar; based on the acquired reflected laser signal, it determines the distance between the target object and the lidar, as well as the light intensity data of the reflected laser signal; based on the light intensity data, it determines whether the target object is a specular reflection object, thus accurately identifying specular reflection objects. Furthermore, when the target object is a specular reflection object, it filters out light intensity point cloud data that conforms to the light intensity mode; it fits the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain fitting function parameters; based on the fitting function parameters, it can identify the refined category to which the specular reflection object belongs. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the steps of a method for identifying specular reflective objects based on LiDAR according to an embodiment of this application;

[0049] Figure 2 This is a schematic diagram illustrating the optical path of a lidar mirror reflection.

[0050] Figure 3 This is a schematic diagram illustrating the refraction and reflection of light by glass;

[0051] Figure 4 This is a schematic diagram illustrating the reflection of light on the surface of a smooth object;

[0052] Figure 5 This is a schematic diagram illustrating the diffuse reflection of light on the surface of a rough object;

[0053] Figure 6 This is a schematic diagram showing the distribution of light intensity values ​​on the glass surface by a lidar.

[0054] Figure 7 This is a schematic diagram showing the distribution of light intensity values ​​of lidar on a smooth stone surface;

[0055] Figure 8 This is a schematic diagram showing the distribution of reflected light intensity values ​​from a lidar sensor on a smooth metal surface.

[0056] Figure 9 This is a structural block diagram illustrating a specular reflective object identification device based on LiDAR according to an embodiment of this application;

[0057] Figure 10 This is a structural block diagram illustrating an embodiment of an electronic device according to this application. Detailed Implementation

[0058] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0059] The following description, in conjunction with the accompanying drawings, details the laser radar-based specular reflection object recognition scheme provided in this application through specific embodiments and application scenarios.

[0060] As attached Figure 1 As shown, the specular reflective object recognition method based on lidar in this application includes the following steps:

[0061] Step 101: Obtain the reflected laser signal received by the lidar.

[0062] Among them, the reflected laser signal is the signal reflected back when the laser pulse signal emitted by the lidar encounters the target object.

[0063] like Figure 2As shown in the schematic diagram of the mirror reflection optical path of a LiDAR, the LiDAR measures distance by receiving the pulsed laser light emitted by the LiDAR. In current robot applications, objects with both transmissive and specular reflection properties, such as glass, smooth metal surfaces, and mirrors, severely interfere with the robot's mapping, localization, and navigation. Glass transmits light, making it impossible for the LiDAR to effectively perceive and model transparent environmental structures such as glass doors and walls during robot mapping and navigation. Simultaneously, other smooth mirror objects, such as mirrors, smooth metal, and tiles, reflect the laser light specularly, causing it to hit other obstacles. When the mirror object has high reflectivity, the reflected light returns along the optical path and is received by the LiDAR; when the reflectivity is low, the reflected light cannot be detected by the LiDAR. All these phenomena lead to incorrect laser measurement values ​​collected by the LiDAR, ultimately affecting the mapping quality and consequently the robot's localization and navigation.

[0064] The specular reflective object identification method for lidar provided in this application embodiment can effectively identify whether a target object is a specular reflective object, and when the target object is a specular reflective object, it can further determine the specular reflective object category to which the target object belongs.

[0065] Among them, the categories of mirror reflective materials include, but are not limited to: glass, mirrors, smooth metals, and smooth stone.

[0066] The specular reflective object recognition method based on LiDAR in this application is applied to the main control module of an electronic device or robot. The electronic device can be a server, computer, or other device with analysis capabilities. The storage medium in the electronic device or robot stores a specular reflective object recognition program for LiDAR. The processor of the electronic device or the main control module of the robot runs the program in the storage medium to execute the specular reflective object recognition process.

[0067] Step 102: Determine the distance between the target object and the lidar, as well as the intensity data of the reflected laser signal, based on the reflected laser signal.

[0068] Figure 2 This is a schematic diagram of the optical path of a lidar mirror reflection. Figure 3 This is a schematic diagram of the refraction and reflection of light by glass. Figure 4 This is a schematic diagram of light reflection on a smooth surface. Figure 5 This is a schematic diagram of diffuse reflection of light on a rough surface. Figure 2-5Visually, light undergoes primarily diffuse reflection on rough surfaces and primarily specular reflection on smooth surfaces. Both theory and practical experiments show that the reflectivity of laser light reflected by a specular surface at a certain angle is greater than that of diffuse reflection. In reality, light undergoes primarily transmission, refraction, and partial specular reflection on glass; primarily specular reflection and partial diffuse reflection on smooth metals, stone, and tiles; primarily specular reflection on mirrors; and primarily diffuse reflection on rough surfaces such as walls. Therefore, by comparing specular reflection and diffuse reflection characteristics, we can distinguish between rough and smooth surface obstacles, and by comparing different specular reflection characteristics, we can differentiate the materials of different smooth surface obstacles.

[0069] In this embodiment, the reflective physical phenomenon of the target object is determined mainly by the reflected laser signal received by the lidar after the laser reaches the target object, thereby further identifying the specular reflective object category to which the target object belongs.

[0070] Step 103: Determine whether the target object is a specular reflective object based on the light intensity data.

[0071] An optional method for determining whether a target object is a specular reflective object based on light intensity data is as follows: First, filter out target light intensity data with a corresponding distance less than a first preset distance from the light intensity data; determine whether the target object is a specular reflective object based on the target light intensity data.

[0072] In actual implementation, the first preset distance can be flexibly determined by those skilled in the art, and this application embodiment does not impose specific restrictions on it. For example, the first preset distance can be set to 1.5m, 2m, or 3m, etc. Preferably, the first preset distance is set to 2m.

[0073] This is because the point cloud is denser in the near part of the lidar's field of view and sparser in the far part. Therefore, objects that are too far away from the lidar cannot form effective features. Thus, analyzing lidar data within a first preset distance, such as 2m, can improve the accuracy of the final judgment result.

[0074] A feasible method for determining whether a target object is a specular reflective object based on target light intensity data is as follows:

[0075] First, determine whether there is a light intensity mode in the target light intensity data;

[0076] The light intensity mode is defined as a pattern in which the difference between the light intensity values ​​of a predetermined number of intermediate points and the light intensity values ​​of surrounding points is greater than a first predetermined value. That is, if the light intensity values ​​of several intermediate points are much higher than the light intensity values ​​of surrounding points, it proves that a matching light intensity mode has appeared in the light intensity data.

[0077] Secondly, if it exists, the target object is determined to be a specular reflective object; if it does not exist, the target object is determined to be a non-spectral reflective object.

[0078] It should be noted that if the target object is determined to be a non-specular reflective object, the LiDAR-based specular reflective object recognition process terminates. When the next target object is detected, step 101 is executed again to restart the LiDAR-based specular reflective object recognition process.

[0079] Step 104: If the target object is a specular reflective object, filter out the light intensity point cloud data that matches the light intensity mode.

[0080] A light intensity mode is a form, and this form is a manifestation of the overall light intensity of multiple point clouds. Therefore, one light intensity mode corresponds to multiple light intensity point cloud data. In this step, the light intensity point cloud data corresponding to the light intensity mode is selected, and the category to which the target object belongs is subsequently determined based on the selected light intensity point cloud data.

[0081] Step 105: Fit the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain the fitting function parameters.

[0082] Step 106: Determine the category of the mirror-reflecting object based on the fitting function parameters.

[0083] An alternative way to determine the category of a specularly reflecting object based on the fitting function parameters is as follows: determine the specular reflection characteristics based on the fitting function parameters; determine the category of the specularly reflecting object based on the specular reflection characteristics.

[0084] In practical implementation, when determining the category of a specularly reflecting object based on its specular reflection characteristics, the object can be classified as non-glass if the specular reflectivity is greater than the diffuse reflectivity; and as glass if the refractive index is greater than the reflectivity.

[0085] Another alternative way to determine the category of a specularly reflecting object based on the parameters of the fitted function is as follows:

[0086] Based on the parameters of the fitted function, determine the light intensity distribution on the surface of the specularly reflecting object; based on the light intensity distribution on the surface of the specularly reflecting object, determine the category of the specularly reflecting object.

[0087] Figure 6 This is a schematic diagram of the light intensity distribution of a lidar on a glass surface. Figure 7 This is a schematic diagram showing the distribution of light intensity values ​​of a lidar on a smooth stone surface. Figure 8 This is a schematic diagram showing the distribution of reflected light intensity from a lidar sensor on a smooth metal surface. Figures 6-8As shown, the light intensity distributions corresponding to different specular reflective object surfaces are different. Therefore, the category of specular reflective object can be determined based on the fitted light intensity distribution.

[0088] The specular reflection object identification method based on lidar provided in this application acquires the reflected laser signal received by the lidar; based on the acquired reflected laser signal, it determines the distance between the target object and the lidar, as well as the light intensity data of the reflected laser signal; based on the light intensity data, it determines whether the target object is a specular reflection object, thus accurately identifying specular reflection objects. Furthermore, when the target object is a specular reflection object, it filters out light intensity point cloud data that matches the light intensity mode; it fits the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain fitting function parameters; based on the fitting function parameters, it can identify the refined category to which the specular reflection object belongs.

[0089] Figure 9 The structural block diagram of a specular reflective object identification device based on lidar according to an embodiment of this application is shown.

[0090] The specular reflective object recognition device based on LiDAR provided in this application embodiment can be applied to robots. The device includes the following functional modules:

[0091] The acquisition module 901 is used to acquire the reflected laser signal received by the lidar, wherein the reflected laser signal is the signal reflected back when the laser pulse signal emitted by the lidar encounters the target object;

[0092] The first determining module 902 is used to determine the distance between the target object and the lidar and the light intensity data of the reflected laser signal based on the reflected laser signal.

[0093] The judgment module 903 is used to determine whether the target object is a specular reflective object based on the light intensity data;

[0094] The filtering module 904 is used to filter out light intensity point cloud data that conform to the light intensity mode when the target object is a specular reflective object.

[0095] The fitting module 905 is used to fit the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain the fitting function parameters.

[0096] The second determining module 906 is used to determine the category of the specular reflection object based on the fitting function parameters.

[0097] Optionally, the determination module includes:

[0098] The first submodule is used to filter out target light intensity data whose corresponding distance is less than a first preset distance from the light intensity data;

[0099] The second submodule is used to determine whether the target object is a specular reflective object based on the target light intensity data.

[0100] Optionally, the second submodule is specifically used for:

[0101] Determine whether there is a light intensity mode in the target light intensity data; wherein, the light intensity mode is a shape in which the difference between the light intensity value of a preset number of intermediate points and the light intensity value of the surrounding points is greater than a first preset value;

[0102] If it exists, the target object is determined to be a specular reflective object;

[0103] If it does not exist, the target object is determined to be a non-specular reflective object.

[0104] Optionally, the fitting module includes:

[0105] The third submodule is used to determine the specular reflection characteristics based on the fitting function parameters;

[0106] The fourth submodule is used to determine the category of the specularly reflecting object based on the specular reflection characteristics.

[0107] Optionally, the fitting module includes:

[0108] The fifth submodule is used to determine the light intensity distribution on the surface of the specular reflective object based on the fitting function parameters;

[0109] The sixth submodule is used to determine the category of the specular reflective object based on the light intensity distribution on the surface of the specular reflective object.

[0110] The specular reflective object identification device based on lidar provided in this application acquires the reflected laser signal received by the lidar; based on the acquired reflected laser signal, it determines the distance between the target object and the lidar, as well as the light intensity data of the reflected laser signal; based on the light intensity data, it determines whether the target object is a specular reflective object, thus accurately identifying specular reflective objects. Furthermore, when the target object is a specular reflective object, it filters out light intensity point cloud data that matches the light intensity mode; it fits the light intensity data and distance of the light intensity point cloud data using a Gaussian mixture model to obtain fitting function parameters; based on the fitting function parameters, it can identify the refined category to which the specular reflective object belongs.

[0111] In the embodiments of this application Figure 9 The LiDAR-based specular reflective object identification device shown can be a physical device, or it can be a component, integrated circuit, or chip in a server. (This is from an embodiment of the present application.) Figure 9 The LiDAR-based specular reflector identification device shown can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application does not specifically limit its implementation.

[0112] The embodiments provided in this application Figure 9 The laser radar-based specular reflector recognition device shown can achieve Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0113] Optionally, such as Figure 10 As shown, this application embodiment also provides an electronic device 1000, including a processor 1001, a memory 1002, and a program or instructions stored in the memory 1002 and executable on the processor 1001. When the program or instructions are executed by the processor 1001, they implement the various processes of the above-described embodiment of the laser radar-based specular reflection object recognition method and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0114] It should be noted that the electronic device in this application embodiment includes the server described above.

[0115] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the laser radar-based specular reflective object recognition method and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0116] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0117] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described embodiment of the specular reflection object recognition method based on lidar, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0118] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0119] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0120] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for laser radar-based identification of a specular reflector, characterized by The method comprises: acquiring a reflected laser signal received by a laser radar, wherein the reflected laser signal is a signal reflected back when a laser pulse signal emitted by the laser radar encounters a target object; determining, according to the reflected laser signal, a distance between the target object and the laser radar and light intensity data of the reflected laser signal; judging, based on the light intensity data, whether the target object is a specular reflection object; in the case where the target object is a specular reflection object, screening out light intensity point cloud data conforming to a light intensity mode; wherein the light intensity mode is a mode in which a difference between a light intensity value of a middle preset number of points and light intensity values of surrounding points is greater than a first preset value; fitting, by a mixture Gaussian model, light intensity data and distances of the light intensity point cloud data to obtain fitting function parameters; determining, according to the fitting function parameters, a category of the specular reflection object.

2. The method of claim 1, wherein, The step of judging, based on the light intensity data, whether the target object is a specular reflection object comprises: screening, from the light intensity data, target light intensity data corresponding to a distance less than a first preset distance; judging, according to the target light intensity data, whether the target object is a specular reflection object.

3. The method of claim 2, wherein, The step of judging, according to the target light intensity data, whether the target object is a specular reflection object comprises: judging whether there is a light intensity mode in the target light intensity data; if there is, determining that the target object is a specular reflection object; if there is not, determining that the target object is a non-specular reflection object.

4. The method of claim 1, wherein, The step of determining, according to the fitting function parameters, a category of the specular reflection object comprises: determining, according to the fitting function parameters, a specular reflection feature; determining, according to the specular reflection feature, the category of the specular reflection object.

5. The method of claim 1, wherein, The step of determining, according to the fitting function parameters, a category of the specular reflection object comprises: determining, according to the fitting function parameters, a light intensity value distribution of a surface of the specular reflection object; determining, according to the light intensity value distribution of the surface of the specular reflection object, the category of the specular reflection object.

6. A laser radar-based glint object recognition device, characterized by The device comprises: an acquisition module, configured to acquire a reflected laser signal received by a laser radar, wherein the reflected laser signal is a signal reflected back when a laser pulse signal emitted by the laser radar encounters a target object; a first determination module, configured to determine, according to the reflected laser signal, a distance between the target object and the laser radar and light intensity data of the reflected laser signal; a judgment module, configured to judge, based on the light intensity data, whether the target object is a specular reflection object; a screening module, configured to, in the case where the target object is a specular reflection object, screen out light intensity point cloud data conforming to a light intensity mode; wherein the light intensity mode is a mode in which a difference between a light intensity value of a middle preset number of points and light intensity values of surrounding points is greater than a first preset value; a fitting module, configured to fit, by a mixture Gaussian model, light intensity data and distances of the light intensity point cloud data to obtain fitting function parameters; a second determination module, configured to determine, according to the fitting function parameters, a category of the specular reflection object.

7. The apparatus of claim 6, wherein, The judgment module comprises: The first sub-module is configured to filter out target light intensity data corresponding to a distance less than a first preset distance from the light intensity data. The second sub-module is configured to determine whether the target object is a specular reflection object according to the target light intensity data.

8. The apparatus of claim 7, wherein, The second sub-module is specifically configured to: determine whether there is a light intensity mode in the target light intensity data; if yes, determine that the target object is a specular reflection object; if no, determine that the target object is a non-specular reflection object.

9. The apparatus of claim 6, wherein, The fitting module comprises: a third sub-module configured to determine a specular reflection feature according to the fitting function parameters; a fourth sub-module configured to determine a category of the specular reflection object according to the specular reflection feature. 10.An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method for identifying a specular reflection object based on a laser radar according to any one of claims 1-5.

Images