Transparent object recognition method and device and computing equipment

Abstract

The invention discloses a transparent object recognition method and device and computing equipment, and relates to the field of computers. The transparent object identification method comprises the following steps: acquiring an obstacle in a scanning range, processing an included angle formed by a light beam emitted by equipment and a tangent plane of a reference point on the obstacle, and receiving a detection result of the obstacle in a process of changing from a first included angle to a second included angle. And determining a transparent object from the obstacles according to the detection result of the obstacles. Wherein the first included angle is different from the second included angle, and the reference point is an intersection of the light beams on the obstacle.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a transparent object recognition method, device and computing equipment. Background Art

[0002] Transparent object detection refers to identifying transparent objects in the environment. Due to the high light transmittance of transparent objects and the refraction and reflection of light in transparent objects, transparent objects are difficult to be captured by sensors.

[0003] Usually, a deep learning model is used to identify transparent objects in the environment. For example, when using a deep learning model, it is necessary to collect a large number of pictures containing transparent objects (such as glass), and train the model after manual annotation to obtain a trained model, which can identify the glass in the picture. However, the use of a deep learning model requires a large amount of manual annotation of the pictures, and the constructed deep learning model is relatively complex, resulting in low efficiency in identifying transparent objects using a deep learning model. Summary of the invention

[0004] The present application provides a transparent object recognition method, apparatus and computing device, which solve the problem of low efficiency in identifying transparent objects in an environment.

[0005] In a first aspect, the present application provides a transparent object recognition method, which can be applied to a computer system or to a processing device that supports the computer system to implement the transparent object recognition method. For example, the processing device can be an autonomous vehicle, a robot, or a drone. The transparent object recognition method may include: obtaining obstacles within a scanning range, a light beam emitted by the processing device and a tangent plane of a reference point on the obstacle form an angle, and receiving the detection result of the obstacle during the process of changing from a first angle to a second angle. According to the detection result of the obstacle, a transparent object is determined from the obstacle. The first angle is different from the second angle, and the reference point is the intersection point of the light beam on the obstacle.

[0006] In the present application, the process of the angle changing from the first angle to the second angle is the process in which the position of the processing device relative to the obstacle is constantly changing. At different positions, detection results of different angles are obtained, and the detection results of different angles indicate the optical properties of the obstacle. Therefore, transparent objects in the obstacle can be determined based on the optical properties of the obstacle, thereby improving the recognition accuracy. In addition, transparent objects in the obstacle can be determined by only obtaining detection results of different angles at different positions, thereby improving the efficiency of identifying transparent objects.

[0007] Exemplarily, the light beam emitted by the above-mentioned processing device is a laser beam emitted by a laser radar in the processing device.

[0008] In a possible implementation, obtaining obstacles within the scanning range includes: a processing device sends a light beam to all directions, and receives a reflection result of the light beam by an obstacle to obtain a detection result. The detection result is compared with a target threshold range. When the detection result is outside the target range, it is determined that there are obstacles in the scanning area.

[0009] In a possible implementation, the detection result indicates: a point cloud intensity set at multiple different angles. The point cloud intensity set includes multiple point cloud intensities, and any one of the multiple point cloud intensities is used to indicate: the reflection intensity of the reference point of the obstacle to the light beam at an angle between the first angle and the second angle.

[0010] In the present application, the processing device obtains the point cloud intensity of the same reference point on the obstacle at different angles, and can fully obtain the optical properties of the obstacle. Based on the optical properties of the obstacle, it can accurately determine whether the obstacle is a transparent object, thereby improving the accuracy of transparent object recognition.

[0011] In a possible implementation, the above-mentioned obstacle detection result includes: the processing device moves according to the movement strategy and reaches multiple target positions in sequence. At each target position, the laser radar emits a light beam to illuminate a reference point on the transparent object, receives the light beam reflected by the reference point on the transparent object, and obtains the point cloud intensity at the angle between the light beam emitted by the processing device and the reference point on the transparent object at each target position.

[0012] The determination of the target position during the movement according to the movement strategy may be determined according to the granularity set by the user, or the target position may be pre-set on the movement track indicated by the movement strategy.

[0013] Two possible examples are provided below for the above movement strategy.

[0014] Example 1: The processing device moves around an obstacle. During the process of the processing device moving around the obstacle, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from a first angle to a second angle.

[0015] Exemplarily, the processing device moving around the obstacle includes: the processing device moving clockwise around the obstacle, or the processing device moving counterclockwise around the obstacle.

[0016] In the present application, the processing device moves around the obstacle to obtain the point cloud intensity at the reference point on the obstacle at different positions, that is, to obtain the point cloud intensity of the reference point at different angles, so as to fully determine the optical properties of the obstacle. The processing device determines the transparent object in the obstacle based on the optical properties, which can improve the accuracy of identifying transparent objects. And it is only necessary to obtain the detection results of different angles at different positions to determine the transparent object in the obstacle, which improves the efficiency of identifying transparent objects.

[0017] Example 2: The processing device moves along a straight line. During the process of the processing device moving along a straight line, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from a first angle to a second angle. That is, during the process of moving along a straight line, the moving direction of the straight line does not intersect with the obstacle.

[0018] In the present application, the processing device moves in a straight line, and the direction of the straight line movement does not intersect with the obstacle to obtain the point cloud intensity of the reference point at different angles. This can reduce the energy consumption of the processing device in obtaining the point cloud intensity of the reference point at different angles, and the processing device can improve the accuracy and efficiency of determining transparent objects in obstacles based on the point cloud intensity at different angles.

[0019] In one possible implementation, transparent objects are determined from obstacles based on the detection results of obstacles, including: obtaining the similarity between the point cloud intensity set of the obstacle and the point cloud intensity set of the non-transparent object, and determining the obstacles with similarity less than or equal to a first threshold as transparent objects.

[0020] In the present application, the processing device determines the transparent objects in the obstacles based on the similarity between the point cloud intensity set of the obstacles and the point cloud intensity of the non-transparent objects, and distinguishes between transparent objects and non-transparent objects based on the different optical properties between the materials, thereby improving the accuracy of identifying transparent objects.

[0021] In a possible implementation, a set of point cloud intensities at multiple different angles is a point cloud intensity curve, and the point cloud intensity curve is used to indicate: a corresponding relationship between point cloud intensities and angles.

[0022] In this application, the similarity between point cloud intensity sets is converted into the similarity between point cloud intensity curves. Since the curve is insensitive to small changes, determining the similarity based on the point cloud intensity curve has better robustness and can produce consistent results even when the data changes slightly, thereby improving the accuracy of identifying transparent objects.

[0023] In a possible implementation, the similarity of the point cloud intensity set is used to indicate: the similarity of the properties of the point cloud intensity curve; the properties of the point cloud intensity curve include: one or more of: peak value, average width, average gradient. The average width is used to indicate: the difference between the horizontal coordinates of two points in the point cloud intensity curve whose vertical coordinates are half of the peak value, the vertical coordinate is used to indicate the point cloud intensity, and the horizontal coordinate is used to indicate the angle. The average gradient is used to indicate: the average value of the gradients of multiple points in the point cloud intensity curve.

[0024] In the present application, the peak value, average width, and average gradient features of the point cloud intensity curve characterize the shape and structure of the entire curve. Therefore, when similarity calculation is performed based on the attributes of the point cloud intensity curve, it will be more robust when dealing with noise or local interference, making the results more consistent and improving the stability and accuracy of identifying transparent objects.

[0025] In a possible implementation, the transparent object recognition method further includes: receiving a point cloud intensity set of multiple transparent materials input by a user. For the point cloud intensity sets of the multiple transparent materials, obtaining the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material. The transparent material with a plurality of similarities greater than or equal to a second threshold is used as the material of the transparent object.

[0026] In the present application, since the point cloud intensity set of the transparent object at different incident angles is similar to the point cloud intensity set of one of the multiple transparent materials at different angles, that is, the optical properties (point cloud intensity at different incident angles) of the transparent object and the transparent material are relatively consistent. Then, it is determined that the material of the transparent object is consistent with the transparent material, and the material of the transparent object is determined using prior data (the point cloud intensity set of multiple transparent materials at different angles). While improving the accuracy of transparent object recognition, it also improves the processing efficiency of transparent object recognition. In addition, compared to the use of deep learning models that can only identify transparent objects, the present application can also determine the material of transparent objects based on prior data, thereby providing data support for obstacle avoidance processing equipment and improving the success rate of obstacle avoidance.

[0027] Exemplarily, the point cloud intensity set of the transparent object is clustered with the point cloud intensity sets of the multiple transparent materials, and the transparent material corresponding to the point cloud intensity set in the same cluster as the point cloud intensity set of the transparent object is used as the material of the transparent object. The similarity of the point cloud intensity sets in the same cluster is greater than or equal to the second threshold.

[0028] In a possible implementation, the transparent object recognition method further includes: obtaining point cloud distance distribution data, generating an occupied grid map based on the point cloud distance distribution data, and merging the occupied grid map with the transparent object map to obtain a semantic map. The point cloud distance distribution data is used to indicate the distance between any two positions within the scanning range, and the occupied grid map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles, and one grid corresponds to one or more pixels. The transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by transparent objects; the semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles and / or transparent objects, and the grid mark is used to indicate the material of the transparent object.

[0029] In this application, since the processing device can accurately identify transparent objects and the materials of transparent objects in the scanning area, the semantic map constructed based on the transparent objects and the materials of transparent objects in the scanning area has a high accuracy. Furthermore, when the processing device navigates according to the semantic map, it can bypass transparent objects and non-transparent objects, thereby improving the safety of the processing device during movement.

[0030] In a possible implementation, the transparent object recognition method further includes: navigating using a navigation strategy according to the semantic map. The navigation strategy is used to instruct: circumventing occupied grids in the semantic map.

[0031] In the present application, since the semantic map records the location of transparent objects, navigation based on the semantic map can accurately avoid transparent objects in the scanning area, thereby improving the safety of the processing equipment during movement.

[0032] For example, since the semantic map also indicates the materials of different transparent objects, corresponding detour strategies can be adopted for different transparent object materials to further ensure the safety of the processing equipment during movement.

[0033] In a possible implementation manner, the transparent object recognition method further includes: displaying a semantic map.

[0034] In this application, for the user, the user can adjust the processing device to meet the user's needs based on the visualized semantic map, which is conducive to more accurate recognition of transparent objects or mapping process of the processing device.

[0035] In the second aspect, the present application also provides a transparent object recognition device, which is applied to a processing device, and the transparent object recognition device includes various modules for executing the transparent object recognition method in the first aspect or any optional method of the first aspect. By way of example, the transparent object recognition device includes: a first acquisition module, a receiving module and a first determination module. The first acquisition module is used to acquire obstacles within the scanning range. The receiving module is used to process the light beam emitted by the device and the tangent plane of the reference point on the obstacle to form an angle, and receive the detection result of the obstacle during the process of changing from the first angle to the second angle; the first angle is different from the second angle, and the reference point is the intersection point of the light beam on the obstacle. The first determination module is used to determine the transparent object from the obstacle based on the detection result of the obstacle.

[0036] In one possible implementation, a light beam emitted by the processing device forms an angle with a tangent plane of a reference point on the obstacle, and the change from a first angle to a second angle is used to indicate that during the process of the processing device moving around the obstacle, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

[0037] In a possible implementation manner, the processing device moving around the obstacle includes: the processing device moving clockwise around the obstacle, or the processing device moving counterclockwise around the obstacle.

[0038] In one possible implementation, a light beam emitted by the processing device forms an angle with a tangent plane of a reference point on the obstacle, and the change from a first angle to a second angle is used to indicate that during the movement of the processing device along a straight line, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

[0039] In a possible implementation, the detection result is used to indicate: a point cloud intensity set at multiple different angles. The point cloud intensity set includes multiple point cloud intensities, and any point cloud intensity of the multiple point cloud intensities is used to indicate: the reflection intensity of the reference point of the obstacle to the light beam at an angle between the first angle and the second angle.

[0040] In a possible implementation, the first determination module is specifically configured to obtain a similarity between a point cloud intensity set of an obstacle and a point cloud intensity set of a non-transparent object, and determine an obstacle with a similarity less than or equal to a first threshold as a transparent object.

[0041] In a possible implementation, a set of point cloud intensities at multiple different angles is a point cloud intensity curve, and the point cloud intensity curve is used to indicate: a corresponding relationship between point cloud intensities and angles.

[0042] In a possible implementation, the similarity of the point cloud intensity set is used to indicate: the similarity of the attributes of the point cloud intensity curve. The attributes of the point cloud intensity curve include: one or more of: peak value, average width and average gradient. The average width is used to indicate: the difference between the horizontal coordinates of two points in the point cloud intensity curve whose vertical coordinates are half of the peak value, the vertical coordinate is used to indicate the point cloud intensity, and the horizontal coordinate is used to indicate the angle. The average gradient is used to indicate: the average value of the gradients of multiple points in the point cloud intensity curve.

[0043] In a possible implementation, the transparent object recognition device further includes: a similarity acquisition module and a second determination module. The similarity acquisition module is used to indicate the point cloud intensity sets for multiple transparent materials and obtain the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material. The second determination module is used to use the transparent material with a plurality of similarities greater than or equal to a second threshold as the material of the transparent object.

[0044] In a possible implementation, the transparent object recognition device further includes: a second acquisition module, a generation module and a merging module. The second acquisition module is used to acquire point cloud distance distribution data, and the point cloud distance distribution data is used to indicate the distance between any two positions within the scanning range. The generation module is used to generate an occupied grid map according to the point cloud distance distribution data; the occupied grid map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles, and one grid corresponds to one or more pixels. The merging module is used to merge the occupied grid map with the transparent object map to obtain a semantic map. The transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by transparent objects; the semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles and / or transparent objects, and the grid mark is used to indicate the material of the transparent object.

[0045] In a possible implementation, the transparent object recognition device further includes: a navigation module. The navigation module is used to navigate according to the semantic map using a navigation strategy; the navigation strategy is used to instruct: to detour the occupied grids in the semantic map.

[0046] In a possible implementation, the transparent object recognition device further includes: a display module. The display module is used to display the semantic map.

[0047] In a third aspect, the present application also provides a chip, comprising: an interface circuit and a power supply circuit; the interface circuit is used to acquire obstacles within a scanning range, and the control circuit is used to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0048] In a fourth aspect, the present application provides a computing device. The computing device includes a memory and a processor, the memory is used to store computer instructions; when the processor executes the computer instructions, the method in the first aspect or any possible implementation of the first aspect is implemented. The computing device may refer to an autonomous vehicle, a robot, or a drone, etc.

[0049] In one possible implementation, the computing device also includes a laser radar and a motion component.

[0050] In a fifth aspect, the present application further provides a computer-readable storage medium, wherein a computer program or instruction is stored in the storage medium, and when the computer program or instruction is executed by a computing device, the method in the first aspect or any optional implementation of the first aspect is implemented.

[0051] In a sixth aspect, the present application further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a computing device, the method in the first aspect or any optional implementation of the first aspect is implemented.

[0052] The beneficial effects of the second to sixth aspects above can be referred to the description of the first aspect or any implementation method of the first aspect, and will not be elaborated here.

[0053] Based on the implementations provided in the above aspects, the present application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of the real picture and the labeled mask;

[0055] Figure 2 It is a structural diagram of a deep learning network model;

[0056] Figure 3 Schematic diagram of laser radar identifying transparent objects;

[0057] Figure 4 Application scenario of a computer system provided for this application Figure 1 ;

[0058] Figure 5 Application scenario of a computer system provided for this application Figure 2 ;

[0059] Figure 6 A schematic diagram of a transparent object recognition method provided in this application;

[0060] Figure 7 Schematic diagram of the location of obstacles and handling equipment provided for this application;

[0061] Figure 8 A schematic diagram of the movement trajectory of the processing equipment provided in this application;

[0062] Fig. 9 A schematic diagram of the point cloud intensity curve of obstacles provided for this application;

[0063] Fig.10 A schematic diagram of the process of the mapping method provided in this application;

[0064] Fig.11 A schematic diagram of a transparent object recognition device provided in this application Figure 1 ;

[0065] Fig.12 A schematic diagram of a transparent object recognition device provided in this application Figure 2 ;

[0066] Fig.13 A schematic diagram of the structure of a computing device provided in this application. DETAILED DESCRIPTION

[0067] To facilitate understanding, the technical terms involved in this application are first introduced.

[0068] Point cloud intensity, also known as radar intensity, refers to a measurement indicator of the laser radar pulse echo intensity at a certain point. This value can reflect the reflection intensity (reflectivity) or echo intensity of the object (a certain point or point cloud) scanned by the laser radar pulse. Among them, the aforementioned point cloud is a three-dimensional spatial data set composed of a large number of discrete points. Each point has its coordinate information in three-dimensional space, and the position information between each point in the point cloud can be determined.

[0069] Gmapping and Cartographer are both lidar mapping and positioning algorithms that enable the device to locate and build maps in the environment in real time to ultimately obtain a map.

[0070] Due to the high light transmittance of transparent objects, as well as the refraction and reflection of light in transparent objects, optical sensors (cameras, radars) have limited field of view for sensing transparent objects, that is, it is difficult to identify transparent objects in the environment. As a result, in scenes of autonomous driving and robot operation, there may be a large number of transparent objects (supermarkets, office areas, etc.), which may lead to accidents and collisions, causing serious safety hazards.

[0071] To identify transparent objects in the environment, two possible processing solutions are provided below.

[0072] Solution 1: Camera glass detection solution based on deep learning.

[0073] First, users need to collect a large number of images containing glass and manually mark the glass masks. Figure 1 As shown, Figure 1 Schematic diagram of the real picture and the labeled mask. Figure 1 Figure a shows various types of real pictures (glass pictures) in a supermarket scene. Figure 1 Figure b shows the masks corresponding to various types of glass images. The white area in the mask represents glass, and the black area represents other objects outside the glass.

[0074] Furthermore, the deep learning model is trained using the above-mentioned pictures containing glass and the corresponding masks, so that the model has the ability to recognize and segment glass.

[0075] like Figure 2 As shown, Figure 2 A structural diagram of a deep learning network model. Figure 2 is a GDNet (glass detection dataset and design a glass detection network), the structure of which includes: a multi-level feature extractor, a large contextual feature integration (LCFI) module, a convolutional layer, a normalization layer, an activation function layer for activation processing, a spatially separable convolutional layer, etc. Input a picture with glass into Figure 2 In the GDNet shown, the area where the glass in the image is located can be obtained.

[0076] However, when constructing the training set (including glass images and corresponding masks), a large number of images need to be manually obtained for construction, which is costly and inefficient. Figure 2 The GDNet shown has a complex structure, high construction cost, and low efficiency.

[0077] Solution 2: Glass detection solution based on LiDAR.

[0078] 1) If Figure 3 As shown, Figure 3 This is a schematic diagram of laser radar identifying transparent objects. When the laser radar is vertically directed at the glass, the intensity of the point cloud obtained is the largest. Then, when the device moves horizontally along the glass, the intensity of the point cloud remains at the maximum (that is, the device moves from R t Moving to R t+1 , the corresponding device emits a beam of light that illuminates the point on the object from O t ` , move to O t+1 `). When the above situation occurs, the object is considered to be glass.

[0079] Since the above devices cannot determine the orientation of the object, it is necessary to manually control the movement of the device to identify whether the object is glass, etc. Also, if there is a dynamically moving object in the scene (such as an electric door covered with advertisements at the entrance of a supermarket), the object will move continuously with the movement of the device and will therefore be mistaken for a transparent object.

[0080] 2) Multiple lidar parameters of a single laser beam irradiated by the lidar to a transparent object are input into a deep learning model to determine whether the transparent object is glass.

[0081] For example, the rotation angle, pitch angle, length and intensity of the laser beam are input into the glass recognition deep neural network to identify the probability of whether the radar point is glass. Also, in the spatial voxel map containing the glass probability and the glass normal vector, the ray casting method is used to simulate the rotation angle and pitch angle of the laser beam emitted by the lidar when the robot is in the initial posture, and input into the optical property deep neural network to obtain the probability of laser beam transmission. The radar points generated by the reflected laser beam are added to the point cloud to generate a simulated point cloud set. Based on the real three-dimensional radar data and the simulated point cloud set, the normal distribution transformation is used to calculate the absolute posture of the robot in the spatial voxel map with glass probability and glass direction information.

[0082] Since only the parameters of a single laser beam are input into the deep neural network, there are limitations in determining whether an object is glass, resulting in low recognition accuracy. In addition, the use of deep neural networks requires the collection of a large amount of training data, and the network structure is complex, resulting in high cost and low efficiency in training deep neural networks.

[0083] In summary, the above processing scheme has low overall efficiency when identifying transparent objects, and has low accuracy in judging the material of transparent objects.

[0084] Based on this, the present application provides a transparent object recognition method. The transparent object recognition method is applied to a processing device, and the transparent object recognition method includes: obtaining obstacles within a scanning range, a light beam emitted by the processing device and a tangent plane of a reference point on the obstacle form an angle, and receiving the detection result of the obstacle during the process of changing from a first angle to a second angle. According to the detection result of the obstacle, a transparent object is determined from the obstacle. Among them, the first angle is different from the second angle, and the reference point is the intersection point of the light beam on the obstacle.

[0085] In the present application, the process of the angle changing from the first angle to the second angle means that the position of the processing device relative to the obstacle is constantly changing. At different positions, detection results of different angles are obtained, and the detection results of different angles indicate the optical properties of the obstacle. Therefore, transparent objects in the obstacle can be determined based on the optical properties of the obstacle, thereby improving the recognition accuracy. In addition, transparent objects in the obstacle can be determined by only obtaining detection results of different angles at different positions, thereby improving the efficiency of identifying transparent objects.

[0086] Next, the transparent object recognition method provided by the present application is described in detail with reference to the accompanying drawings. The transparent object recognition method provided by the present application can be applied to Figure 4 or Figure 5 The scene shown.

[0087] In the first scenario, if Figure 4 As shown, Figure 4 Application scenario of a computer system provided for this application Figure 1 The computing device 410 can scan objects within an area, which can be referred to as a scanning range. After the computing device 410 identifies the obstacle 420 within its scanning range, the computing device 410 can move around the obstacle 420, thereby obtaining detection results at different angles between the light beam emitted by the computing device 410 and the tangent plane of the reference point on the obstacle 420. Then, based on the detection results at different angles, the transparent object in the obstacle 420 is determined.

[0088] The reference point may be a position selected arbitrarily by the computing device 410 from the obstacle 420, or a position specified by the user on the obstacle 420. Furthermore, the computing device 410 continuously emits a light beam during the movement, so that the light beam is directed to the reference point on the obstacle 420. Alternatively, the computing device 410 emits a light beam every time it reaches the target position during the movement, so that the light beam is directed to the reference point on the obstacle 420. In other words, after the reference point on the obstacle 420 is determined, the reference point is the intersection point of the light beams emitted by the computing device 410 on the obstacle.

[0089] For example, a user may specify a position in a display interface output by the computing device 410, and the display interface indicates obstacles in the scanning area. The user may perform a trigger operation on the display interface, and the computing device 410 determines the position specified by the user on the obstacle according to the user's trigger operation. The trigger operation may be a click operation or a slide operation, etc. The light beam emitted by the computing device 410 may be a laser beam emitted by a laser radar deployed in the computing device 410.

[0090] The tangent plane of the reference point on the obstacle means that if there are tangent lines to the curve passing through the reference point on the obstacle surface, then these tangent lines are in the same plane, and this plane is the tangent plane of the reference point on the obstacle. The tangent line is a straight line that just touches the reference point on the curve, that is, when the tangent line passes through the reference point on the curve, the direction of the tangent line is the same as the direction of the reference point on the curve.

[0091] In a possible example, the tangent plane may also be called a tangent plane or a local plane. The tangent plane or the local plane may represent a curve passing through a reference point on the obstacle surface, and if there is a tangent, the plane where the tangent is located.

[0092] In one possible scenario, computing device 410 may move clockwise around obstacle 420 .

[0093] Exemplarily, the computing device 410 moves clockwise, that is, passes through point ① and point ② in sequence, and obtains the detection result of the computing device 410 between point ① and point ② at the angle between the light beam emitted by the computing device 410 and the tangent plane of the reference point on the obstacle 420.

[0094] In another possible scenario, computing device 410 may move counterclockwise around obstacle 420 .

[0095] Exemplarily, the computing device 410 moves counterclockwise, that is, passes through point ② and point ① in sequence, and obtains the detection result between point ② and point ① at the angle between the light beam emitted by the computing device 410 and the tangent plane of the reference point on the obstacle 420.

[0096] It is worth noting that Figure 4 As shown, if the reference point of the obstacle 420 is located on the right side of the cube-shaped obstacle 420, the tangent plane of the reference point is the right side. The movement of the computing device 410 around the obstacle 420 can be: the computing device 410 moves around the center of the obstacle 420, or the computing device 410 moves around the reference point. When the computing device 410 rotates around the obstacle 420, it only needs to rotate 180° around the tangent plane of the reference point, and the application does not limit the rotation angle. In other embodiments of the present application, the rotation angle may be 90° or 120°, etc. The size of the scanning range is determined according to the processing power of the computing device 410, specifically, according to the power, receiving sensitivity, etc. of the laser radar in the computing device 410.

[0097] In this scenario, the computing device 410 may also build a map based on obstacles 420 within the scanning range, and navigate based on the obtained map.

[0098] In the second scenario, if Figure 5 As shown, Figure 5Application scenario of a computer system provided for this application Figure 2 After the computing device 410 identifies the obstacle 420 within its scanning range, the computing device 410 moves in a straight line, and the direction of the straight line movement does not intersect the reference point on the obstacle 420 or the obstacle 420, so that the detection results of the light beam emitted by the computing device 410 and the tangent plane of the reference point on the obstacle 420 at different angles can be obtained. Then, according to the detection results at different angles, the transparent object in the obstacle 420 is determined.

[0099] like Figure 5 As shown, the computing device 410 can move from point ① to point ② along a straight line, or from point ② to point ① along a straight line. During the movement of the computing device 410, the angle between the emitted light beam and the tangent plane of the reference point on the obstacle 420 changes continuously, thereby obtaining the detection results of the obstacle 420 at different angles.

[0100] The present application provides a transparent object recognition method, which can be applied to Figure 4 or Figure 5 The following transparent object recognition method is applied in the application scenario shown in Figure 4 The application scenario shown in the figure is used as an example to illustrate. Figure 6 As shown, Figure 6 The flowchart of a transparent object recognition method provided by the present application is shown in FIG. 6 , which can be executed by a processing device 610. The processing device 610 may include Figure 4 The computing device 410 shown in FIG. 4 is provided with a laser radar in the processing device 610. Figure 6 As shown, the transparent object recognition method may include the following steps S610 to S630.

[0101] S610: The processing device 610 obtains obstacles 420 within a scanning range.

[0102] In a possible implementation, the processing device 610 acquires the obstacle 420 within the scanning range, including: the processing device 610 emits a light beam to acquire a detection result of an object within the scanning range, and determines the obstacle 420 within the scanning range according to the detection result of the object.

[0103] In a possible example, the processing device 610 continuously emits light beams around the processing device 610 during normal movement. If there is an object within the scanning range, the processing device 610 will receive the reflection result of the light beam by the object, that is, the detection result. The processing device 610 compares the detection result with the target threshold range. If the detection result is outside the target threshold range, the object is determined to be an obstacle 420 (suspected transparent object). If the detection result is within the target threshold range, the object is determined to be a non-transparent object.

[0104] If the detection result is at two end values ​​of the target threshold range, the object is determined to be a suspected transparent object or a non-transparent object, which is not limited in this application.

[0105] It is worth noting that Figure 6 The scanning range shown in the figure is only a part of the complete scanning range of the processing device 610. In practice, the complete scanning range of the processing device 610 is an area radiating from the position of the processing device 610 to the surrounding areas. The range of this area is determined by the power of the laser radar in the processing device 610, the shielding conditions of the surrounding obstacles, etc.

[0106] like Figure 7 As shown, Figure 7 Schematic diagram of the locations of obstacles and handling equipment provided for this application. Figure 7 In a, when the processing device 610 is at a position, the light beam emitted by the processing device 610 has multiple angles with the surface of the object, and the detection intensity corresponding to the multiple angles is the detection intensity of the object. The processing device 610 sequentially judges the detection intensity corresponding to the multiple angles with the target threshold range to determine whether the object is an obstacle.

[0107] In a possible scenario, the processing device 610 may determine the detection strength of the object at multiple positions, and determine whether the object is an obstacle based on the detection strength at the multiple positions.

[0108] Exemplarily, the light beam emitted by the processing device 610 is a laser beam, and the detection intensity is the point cloud intensity.

[0109] In the process of identifying obstacles within the scanning range, the processing device 610 will also determine the relative position between the obstacle and the processing device 610 according to the point cloud intensity of the obstacle. The relative position may be the distance and angle between the obstacle and the processing device 610.

[0110] Since the point cloud intensity indicates the coordinate position of each point in the point cloud, which is determined based on the processing device 610, the processing device 610 can determine the relative position of the obstacle and the processing device 610 according to the coordinate position of each point.

[0111] Exemplarily, the coordinates of each point in the point cloud are determined with the processing device 610 that emits the light beam as the origin.

[0112] S620: The light beam emitted by the processing device 610 forms an angle with the tangent plane of the reference point on the obstacle 420. In the process of changing from the first angle to the second angle, the detection result of the obstacle 420 is received.

[0113] The first angle is different from the second angle, and the reference point is the intersection point of the light beams on the obstacle.

[0114] The difference between the first angle and the second angle may be 180°. In other embodiments of the present application, the difference may be 90° or 120°, which is not limited in the present application. The reference point on the obstacle may be any point on the outer surface of the obstacle where the light beam emitted by the processing device 610 irradiates, or the reference point may be a position specified by the user on the outer surface of the obstacle.

[0115] In one possible implementation, the processing device 610 moves according to the relative position of the processing device 610 and the obstacle 420, and the moving direction does not intersect with the obstacle 420, so that the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 changes from the first angle to the second angle, and the detection result of the obstacle 420 is received.

[0116] like Figure 6 As shown, the processing device 610 moves from point a, through point b, to point c. In the process of moving from point a to point c, the angle between the light beam emitted by the processing device and the tangent plane of the reference point on the obstacle 420 changes continuously, that is, in the process of changing from the first angle to the second angle, the processing device 610 continues to receive the detection results of the obstacle 420.

[0117] Similarly, if Figure 7 As shown in b, the obstacle 420 is a regular cubic structure, so the tangent plane of the reference point on the obstacle is the plane where the reference point is located. The processing device 610 passes through multiple points in sequence. In the process of passing through multiple points, the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 is constantly changing. For example, it changes from angle a to angle b, and as the processing device 610 continues to move, the angle continues to increase.

[0118] like Figure 7 As shown in c, the obstacle 420 is an arc-shaped structure, and the tangent plane of the reference point on the obstacle 420 is determined according to the reference point on the obstacle 420. When the processing device 610 moves around the obstacle 420, the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 changes continuously. For example, the angle changes continuously starting from angle c.

[0119] It is worth noting that due to Figure 7 The obstacle 420 shown in c is an arc-shaped structure, so the tangent plane of the reference point on the obstacle 420 is perpendicular to the line connecting the center of the arc-shaped structure and the reference point.

[0120] The detection result indicates: a point cloud intensity set at multiple different angles. The point cloud intensity set includes multiple point cloud intensities, any one of which is used to indicate: the reflection intensity of the reference point of the obstacle 420 to the light beam at an angle between the first angle and the second angle.

[0121] For example, during the movement of the processing device 610, when the angle continuously changes from the first angle to the second angle, the processing device 610 continuously emits a light beam, and at each angle, the point cloud intensity at the reference point on the obstacle 420 is obtained. That is, the point cloud intensity set includes multiple sets of angle and point cloud intensity data, such as (20°, 60°).

[0122] In the present application, the processing device 610 obtains the point cloud intensity of the same reference point on the obstacle 420 at different angles, and can fully obtain the optical properties of the obstacle 420. Based on the optical properties of the obstacle 420, it can accurately determine whether the obstacle 420 is a transparent object, thereby improving the accuracy of transparent object recognition.

[0123] When the processing device is at the starting position (point a), the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 is the first angle. When the processing device is at the ending position (point b), the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 is the second angle. The aforementioned starting position and ending position are relative to one obstacle. The starting position and ending position corresponding to different obstacles may be different.

[0124] In a possible example, the processing device 610 moves according to the movement strategy and reaches multiple target positions in sequence. At each target position, the processing device 610 emits a light beam to illuminate a reference point on the obstacle 420, receives a light beam reflected by the reference point on the obstacle 420, and obtains the point cloud intensity of the light beam emitted by the processing device 610 at the reference point under the obstacle 420 at each target position.

[0125] The determination of the target position during the movement of the processing device 610 according to the movement strategy can be determined according to the granularity set by the user. For example, the position reached by the processing device 610 every 10 cm according to the movement strategy is the target position. Alternatively, the target position is pre-set on the movement trajectory indicated by the movement strategy, which is not limited in this application.

[0126] In one possible scenario, the plane in which the processing device 610 forms a trajectory according to the movement strategy may be parallel to the horizontal plane, or may be at a certain angle to the horizontal plane (for example, when the obstacle is on a slope, the processing device 610 may move up and down with the slope, and thus the movement trajectory of the processing device 610 may be at a certain angle to the horizontal plane).

[0127] With respect to the above-mentioned mobile strategy, a possible implementation example is provided as follows.

[0128] In a possible embodiment, when the processing device 610 moves around the obstacle 420, the angle formed by the light beam emitted by the processing device 610 and the tangent plane of the reference point changes from a first angle to a second angle.

[0129] like Figure 4 As shown, the processing device 610 moves in a manner of surrounding the obstacle 420. Every time the processing device 610 moves a certain distance, the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 will change. When the processing device 610 moves from point ① to point ②, the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point changes from the first angle to the second angle.

[0130] In a possible scenario, the processing device 610 may move around the obstacle 420 in a clockwise direction or in a counterclockwise direction, which is not limited in the present application.

[0131] For example, the shape of the trajectory of the processing device 610 moving around the obstacle 420 may be a curve or a polyline, wherein the opening of the curve or the polyline faces the obstacle 420 .

[0132] like Figure 8 As shown, Figure 8 A schematic diagram of the movement trajectory of the processing device provided in this application. Figure 8 The track 1 in the figure is an arc, that is, a curve, the track 2 is an irregular curve, and the track 3 is a multi-fold line. The openings of the track 1, the track 2, and the track 3 are all facing the obstacle 420.

[0133] In the present application, the processing device 610 moves around the obstacle 420 to obtain the point cloud intensity at the reference point on the obstacle 420 at different positions, that is, to obtain the point cloud intensity of the reference point at different angles, so as to fully determine the optical properties of the obstacle 420. The processing device 610 determines the transparent object in the obstacle 420 according to the optical properties, which can improve the accuracy of identifying the transparent object.

[0134] S630 : The processing device 610 determines a transparent object from the obstacles 420 according to the detection result of the obstacles 420 .

[0135] In a possible implementation, the processing device 610 determines the transparent object from the obstacle 420 according to the detection result of the obstacle 420, including: obtaining the similarity between the point cloud intensity set of the obstacle 420 and the point cloud intensity set of the non-transparent object. Obstacles 420 with a similarity less than or equal to a first threshold are determined as transparent objects.

[0136] For example, the processing device 610 may use Euclidean distance, Manhattan distance, Chebyshev distance, etc. to determine the similarity of the point cloud intensity sets.

[0137] The processing device 610 uses Euclidean distance, Manhattan distance, and Chebyshev distance to determine the distance between data, and uses the distance to measure the similarity between data.

[0138] Taking the Euclidean distance among the Euclidean distance, Manhattan distance, and Chebyshev distance used by the processing device 610 as an example, the processing device 610 uses the Euclidean distance to calculate the distance between the point cloud intensity set of the obstacle 420 and the point cloud intensity set of the non-transparent object at the same angle, and then obtains the similarity of the point cloud intensity at the same angle based on the distance. The processing device 610 performs a weighted summation of the similarity of the corresponding intensity at each angle to obtain the similarity between the point cloud intensity sets.

[0139] In the present application, the processing device 610 determines the transparent objects in the obstacle 420 based on the similarity between the point cloud intensity set of the obstacle 420 and the point cloud intensity of the non-transparent object, thereby distinguishing between transparent objects and non-transparent objects based on the different optical properties between the materials, thereby improving the accuracy of identifying transparent objects.

[0140] In another embodiment of the present application, the transparent object recognition method is applied to Figure 5 The application scenario shown in the figure is used as an example to illustrate. Figure 6 The content shown is different only in that the movement strategy adopted by the processing device 610 in this embodiment is linear movement.

[0141] In a possible implementation, when the processing device 610 moves along a straight line, the angle formed by the light beam emitted by the processing device and the tangent plane of the reference point changes from a first angle to a second angle.

[0142] like Figure 5 As shown, the processing device 610 moves in a straight line, and the direction of the straight line movement does not intersect the obstacle 420, so that the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point on the obstacle 420 changes every time the processing device 610 moves a certain distance. When the processing device 610 moves from point ① to point ②, the angle between the light beam emitted by the processing device 610 and the tangent plane of the reference point changes from the first angle to the second angle.

[0143] In a possible scenario, when the processing device 610 moves in a straight line, the direction of the straight line movement does not intersect with the reference point on the obstacle 420 .

[0144] In the present application, the processing device 610 moves in a straight line, and the direction of the straight line movement does not intersect with the obstacle 420 to obtain the point cloud intensity of the reference point at different angles. This can reduce the energy consumption of the processing device 610 in obtaining the point cloud intensity of the reference point at different angles, and the processing device 610 can improve the accuracy of determining transparent objects in the obstacle 420 based on the point cloud intensity at different angles.

[0145] In a possible embodiment, the point cloud intensity set under different angles is a point cloud intensity curve. The point cloud intensity curve is used to indicate the corresponding relationship between the point cloud intensity and the angle.

[0146] When the processing device 610 determines the transparent object from the obstacles 420 according to the detection result of the obstacles 420 , the similarity between the point cloud intensity curve of the obstacles 420 and the point cloud intensity curve of the non-transparent object may be used.

[0147] like Fig. 9 As shown, Fig. 9 A schematic diagram of the point cloud intensity curve of an obstacle provided in this application. Fig. 9 The point cloud intensity curve of a transparent object and the point cloud intensity curve of a non-transparent object are shown in a figure a. The point cloud intensity of a transparent object changes parabolically with the change of the angle. When the tangent plane of the light beam of the processing device 610 and the reference point is 90°, the point cloud intensity reaches a peak value. The point cloud intensity of a non-transparent object does not fluctuate much with the change of the angle, and fluctuates within a certain range.

[0148] The processing device 610 may use Fréchet distance, dynamic time warping (DTW), etc. to determine the similarity between the point cloud intensity curve of the obstacle 420 and the point cloud intensity curve of the non-transparent object.

[0149] The Fréchet distance is defined as the maximum value of the following process: select a point on one curve and a point on the other curve, and then connect the two points to form a connecting line segment. The position and length of the connecting line segment are restricted by the order of the points on the two curves. The Fréchet distance is the maximum value that makes the connecting line segment of this process the shortest. The smaller the Fréchet distance, the more similar the two curves are.

[0150] The basic idea of ​​DTW is to align two time series (curves) to minimize the distance between them while satisfying a strict monotonicity and smoothness restriction. Specifically, DTW calculates the distance matrix between the two sequences and uses dynamic programming to find the optimal path, that is, to provide a measure of the similarity between the two sequences.

[0151] In the present application, the processing device 610 converts the similarity between point cloud intensity sets into the similarity between point cloud intensity curves. Since the curve is more sensitive to slight changes, determining the similarity based on the point cloud intensity curve has better robustness and can produce consistent results even when the data changes slightly, thereby improving the accuracy of identifying transparent objects.

[0152] In a possible implementation, the similarity of the point cloud intensity set is used to indicate: the similarity of the properties of the point cloud intensity curve. The properties of the point cloud intensity curve include: one or more of a peak value, an average width, and an average gradient.

[0153] The average width is used to indicate: the difference between the horizontal coordinates of two points whose vertical coordinates are half of the peak value in the point cloud intensity curve. The vertical coordinate is used to indicate the point cloud intensity, and the horizontal coordinate is used to indicate the angle. The average gradient is used to indicate: the average value of the gradients of multiple points in the point cloud intensity curve.

[0154] Fig. 9 Figure b shows three properties of the point cloud intensity curve (peak value, average width, average gradient). The processing device 610 determines the average gradient of the point cloud intensity curve, and can select multiple points from the point cloud intensity curve according to the sampling granularity determined by the user, and then determine the average value of the gradients of the multiple points. For example, the sampling granularity can be sampling every 1°, which is not limited in this application. In other embodiments of the present application, the sampling granularity can also be sampling every 2°.

[0155] Exemplarily, the processing device 610 compares the attributes of the point cloud intensity curve of the obstacle 420 with the attributes of the point cloud intensity curve of the non-transparent object one by one to determine the similarity.

[0156] For example, the processing device 610 compares the peak value a in the attribute of the point cloud intensity curve of the obstacle 420 with the peak value b in the attribute of the point cloud intensity curve of the non-transparent object. If the peak value a satisfies the condition that it is greater than or equal to the peak value b plus the first value, it is determined that the similarity between the peak value a and the peak value b is less than or equal to the threshold. The first value may be 10, and the first value may be set according to user needs, and is not limited in this application.

[0157] The processing device 610 compares the average width a in the attribute of the point cloud intensity curve of the obstacle 420 with the average width b in the attribute of the point cloud intensity curve of the non-transparent object. If the average width a is less than or equal to the average width b minus the second value, it is determined that the similarity between the average width a and the average width b is less than or equal to the threshold. The second value may be 5, and the second value may be set according to user needs, and is not limited in this application.

[0158] The processing device 610 compares the average gradient a in the attribute of the point cloud intensity curve of the obstacle 420 with the average gradient b in the attribute of the point cloud intensity curve of the non-transparent object. If the average gradient a satisfies the condition that it is greater than or equal to the average gradient b plus a third value, it is determined that the similarity between the average gradient a and the average gradient b is less than or equal to a threshold. The third value may be 1, and the third value may be set according to user needs, and is not limited in this application.

[0159] In summary, the processing device 610 performs weighted summation according to the similarities among the peak values, average widths, and average gradients to obtain the similarity between the point cloud intensity set of the obstacle 420 and the point cloud intensity set of the non-transparent object.

[0160] Exemplarily, if the similarity between the peak value a and the peak value b is less than or equal to the threshold, the processing device 610 assigns a value of 0 to the peak value of the point cloud curve of the obstacle. If the similarity between the average width a and the average width b is less than or equal to the threshold, the processing device 610 assigns a value of 0 to the average width of the point cloud curve of the obstacle. If the similarity between the average gradient a and the average gradient b is less than or equal to the threshold, the processing device 610 assigns a value of 0 to the average gradient of the point cloud curve of the obstacle. The processing device 610 determines that the similarity between the attributes of the point cloud intensity curve of the obstacle and the attributes of the point cloud intensity curve of the non-transparent object is 0 based on the weights of the peak value, the average width, and the average gradient (0.4 / 0.2 / 0.4), and when the similarity between the aforementioned attributes is less than or equal to a fourth value, it is determined that the obstacle is a non-transparent object or a transparent object. The fourth value may be 0.2, and the fourth value may be set according to user requirements, and is not limited in this application.

[0161] In the present application, the peak value, average width, and average gradient features of the point cloud intensity curve characterize the shape and structure of the entire curve. Therefore, when the processing device 610 performs similarity calculations based on the attributes of the point cloud intensity curve, it will be more robust when processing noise or local interference, making the results more consistent and improving the stability and accuracy of identifying transparent objects.

[0162] In order to solve the problem that the above neural network model can only identify transparent objects but cannot confirm the material of the transparent objects, a possible embodiment is provided below to identify the material of the transparent objects.

[0163] The processing device 610 obtains the point cloud intensity sets of multiple transparent materials input by the user. The processing device 610 obtains the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material for the point cloud intensity sets of the multiple transparent materials, and uses the transparent material with a plurality of similarities greater than or equal to the second threshold as the material of the transparent object.

[0164] In a possible scenario, the point cloud intensity set of the plurality of transparent materials input by the user obtained by the processing device 610 may be a point cloud intensity curve or an attribute of the point cloud intensity curve.

[0165] In a possible example, the processing device 610 may determine the similarity by using a neural network model, DTW, etc. The neural network model may be a recurrent neural network (RNN), a temporal convolutional neural network (TCN), etc.

[0166] The material of the transparent object can be transparent plastic, glass, frosted glass, water tank, etc.

[0167] In the present application, since the point cloud intensity set of the transparent object at different incident angles is similar to the point cloud intensity set of one of the multiple transparent materials at different angles, that is, the optical properties (point cloud intensity at different incident angles) of the transparent object and the transparent material are relatively consistent. Then, it is determined that the material of the transparent object is consistent with the transparent material, and the material of the transparent object is determined using prior data (the point cloud intensity set of multiple transparent materials at different angles). While improving the accuracy of transparent object recognition, it also improves the processing efficiency of transparent object recognition. In addition, compared to the use of deep learning models that can only identify transparent objects, the present application can also determine the material of transparent objects based on prior data, thereby providing data support for obstacle avoidance processing equipment and improving the success rate of obstacle avoidance.

[0168] With respect to the content of determining the similarity in the above embodiment, two possible implementation methods are provided below.

[0169] In a first possible implementation manner, the processing device 610 calculates the similarity between the point cloud intensity curve of the transparent object and the point cloud intensity curve of each transparent material.

[0170] Exemplarily, the processing device 610 may use the above-mentioned neural network model to determine the similarity between the point cloud intensity curve of the transparent object and the point cloud intensity curve of each material.

[0171] In a second possible implementation manner, the processing device 610 calculates the similarity between the attributes of the point cloud intensity curve of the transparent object and the attributes of the point cloud intensity curve of each material.

[0172] Exemplarily, the processing device 610 may cluster the attributes of the point cloud intensity curve of the transparent object with the attributes of the point cloud intensity curves of multiple transparent materials to obtain a clustering result. The clustering result is obtained based on the similarity between the attributes of the point cloud intensity curve of the transparent object and the attributes of the point cloud intensity curves of multiple transparent materials, and the similarity of the attributes of the point cloud intensity curves in the same cluster in the clustering result is greater than or equal to a threshold.

[0173] For example, the processing device 610 uses the peak value, average width, and average gradient of the point cloud intensity curve to represent the characteristics of the point cloud intensity curve, showing the three-dimensional properties of the curve. The processing device 610 performs aggregation according to the characteristics of the point cloud intensity curve, which can improve the accuracy of the clustering results.

[0174] The processing device 610 may use K-means, hierarchical clustering, or density clustering algorithms to cluster the attributes of the above point cloud intensity curves.

[0175] In a possible embodiment, the present application builds a map based on the transparent objects and the materials of the transparent objects identified by the processing device 610 from the scanning area. Fig.10 As shown, Fig.10 The flowchart of the mapping method provided by the present application is shown in FIG. The mapping method may be executed by the processing device 610 , and the mapping method may include the following steps S1010 to S1030 .

[0176] S1010 , the processing device 610 obtains point cloud distance distribution data.

[0177] The point cloud distance distribution data is used to indicate: the distance between any two positions within the scanning range.

[0178] Exemplarily, the processing device 610 can obtain point cloud distance distribution data within the scanning range during normal movement, movement around the obstacle 420, or movement along a straight line.

[0179] The description of the point cloud distance distribution data obtained by the processing device 610 within the scanning range can refer to the content of the processing device 610 obtaining the detection result of the object in the above S610, which will not be repeated here.

[0180] In a possible example, the processing device 610 emits a light beam to illuminate an object while moving, receives the light beam reflected by the object, and obtains point cloud distance distribution data while obtaining detection results.

[0181] S1020. The processing device 610 generates an occupancy grid map according to the point cloud distance distribution data.

[0182] The occupied grid map is used to indicate whether a grid in the map corresponding to the scanning range is occupied by an obstacle 420 , and one grid corresponds to one or more pixel points.

[0183] In one possible implementation, the processing device 610 determines the area occupied by a grid in the grid map, and then converts the point cloud in the point cloud distance distribution data into a point in the grid map according to the area of ​​the grid, and calculates the distribution of the point cloud distance in each grid. The processing device 610 generates an occupied grid map according to the distribution of the point cloud distance in each grid.

[0184] Exemplarily, the processing device 610 determines how many small squares (grids) the scan area is divided into, that is, determines the area occupied by a grid. If the area occupied by the grid is small, the obtained occupied grid map will have better accuracy, and if the area occupied by the grid is large, the occupied grid map will be obtained faster. A small square can correspond to one or more pixels, and the area occupied by the small square corresponds to the area in the real environment.

[0185] The processing device 610 can convert the distance between each point in the point cloud distance distribution data into the distance between points in the coordinate system of the grid map by using a transformation matrix. For each grid, the distance values ​​of all points falling in the grid are counted, and the distribution of the distance values ​​is calculated. The processing device 610 can determine whether the grid is occupied by an object or the grid is idle based on the threshold of the distance value.

[0186] Generally, grids with distance values ​​less than the threshold are considered to be occupied by objects, and grids with distance values ​​greater than the threshold are considered to be idle areas.

[0187] The above-mentioned occupied grid may use a binary identifier, wherein 1 indicates that the grid is an area occupied by an object, and 0 indicates that the grid is an idle area.

[0188] To visualize the occupancy grid map, different colors can be used to represent occupied areas or free areas. For example, black indicates that the grid is occupied by objects, and white indicates that the grid is free.

[0189] In a possible implementation, the processing device 610 may use Gmapping and Cartographer to generate an occupancy grid map.

[0190] S1030: The processing device 610 merges the occupancy grid map with the transparent object map to obtain a semantic map.

[0191] The transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by transparent objects. The semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles and / or transparent objects.

[0192] Exemplarily, the marks in the grid are used to indicate the material of the transparent object.

[0193] The processing device 610 constructs a transparent object map according to the transparent objects in the scanning range and the point cloud intensity distribution data. The grid marks in the transparent object map are used to indicate the material of the transparent object, that is, different marks are used to indicate different materials.

[0194] The processing device 610 may fill the grid with different colors to indicate the material of the object occupying the grid. For example, red represents glass and blue represents frosted glass. The material represented by the color is only an example and should not be construed as limiting the present application. In other embodiments of the present application, red may also represent transparent plastic.

[0195] For the content of constructing the transparent object map by the processing device 610, reference may be made to the description of constructing the occupancy grid map in S1020, which will not be described in detail here.

[0196] In a possible implementation, the processing device 610 merges the occupied grid map with the transparent object map to obtain a semantic map, including: the processing device 610 merges the grids in the occupied grid map with the corresponding grids in the transparent object map to obtain a semantic map.

[0197] Exemplarily, the processing device 610 merges the grids at corresponding positions in the grid map and the transparent object map to obtain a semantic map.

[0198] For example, if a grid in the occupied grid map is an area occupied by an object, and the grid at the corresponding position in the transparent object map is an area occupied by glass, the processing device 610 determines that the grid at that position in the semantic map is an area occupied by glass.

[0199] If a grid in the occupied grid map is black and the grid at the corresponding position in the transparent object map is red, the processing device 610 determines that the grid at that position in the semantic map is red, indicating that the grid is occupied by glass.

[0200] In the present application, since the processing device 610 can accurately identify transparent objects and the materials of transparent objects in the scanning area, the semantic map constructed based on the transparent objects and the materials of transparent objects in the scanning area has a high accuracy. Then, when the processing device 610 navigates according to the semantic map, it can bypass transparent objects and non-transparent objects, thereby improving the safety of the processing device 610 during movement.

[0201] In one possible embodiment, the processing device 610 may visualize the semantic map.

[0202] In a possible implementation, the processing device 610 displays the semantic map on the front end, where the front end may refer to a display connected to the processing device 610 or a display screen provided by the processing device 610, etc., which is not limited in this application.

[0203] In the present application, for the user, the user adjusts the processing device 610 to meet the user's needs based on the visualized semantic map, which is conducive to more accurate recognition of transparent objects or mapping by the processing device 610.

[0204] In one possible embodiment, the processing device 610 performs navigation according to an occupancy grid map or a semantic map.

[0205] For example, the processing device 610 may use a navigation strategy to perform navigation according to the occupancy of grids in the occupancy grid map or the semantic map.

[0206] The navigation strategy is used to indicate: detour around occupied cells in the semantic map.

[0207] In one possible scenario, the processing device 610 has different detour methods according to the material of the transparent object indicated by the occupied grid in the semantic map.

[0208] For example, since glass has a high risk factor, the expansion coefficient of glass is set to be large, that is, the occupation range of the grid corresponding to glass in the semantic map is expanded by a multiple of the expansion coefficient, so that the processing device 610 will go further when passing through the glass. Since plastic has a low risk factor, the expansion coefficient of transparent plastic is set to be small, that is, the occupation range of the grid corresponding to transparent plastic in the semantic map is expanded by a multiple of the expansion coefficient, so that the processing device 610 can move close to the transparent plastic when passing through it.

[0209] In the present application, since the semantic map records the location of transparent objects, the processing device 610 navigates according to the semantic map and can accurately avoid transparent objects in the scanning area, thereby improving the safety of the processing device 610 during movement. In addition, the semantic map also indicates the material of the transparent object, and the processing device 610 can adopt corresponding detour strategies for different transparent object materials to further ensure the safety of the processing device 610 during movement.

[0210] In a possible example, the processing device 610 may also display the moving path of the processing device 610 on the front end. For example, the moving path of the processing device 610 is additionally displayed on the semantic map. This facilitates the user to adjust the processing device 610 in accordance with the user's needs, so that the moving path of the processing device 610 better meets the user's needs.

[0211] It is understandable that in order to implement the functions in the above embodiments, the computing device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and method steps of each example described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0212] Combined with the above Figure 4-Figure 10 The transparent object recognition method provided by this embodiment is described in detail. Fig.11 , describing the transparent object recognition device provided according to this embodiment.

[0213] Fig.11 A schematic diagram of a transparent object recognition device provided in this application Figure 1 The transparent object recognition device can be used to implement the functions of the computing device in the above method embodiment, and thus can also achieve the beneficial effects of the above method embodiment. In this embodiment, the transparent object recognition device can be a module (such as a chip) of the computing device.

[0214] like Fig.11 As shown, the transparent object recognition device 1100 includes a first acquisition module 1101, a receiving module 1102 and a first determination module 1103. The transparent object recognition device 1100 is used to implement the above Figures 4 to 10 The functions in the method embodiments shown in .

[0215] The first acquisition module 1101 is used to acquire obstacles within the scanning range.

[0216] The receiving module 1102 is used to process the angle formed by the light beam emitted by the device and the tangent plane of the reference point on the obstacle, and receive the detection result of the obstacle during the process of changing from the first angle to the second angle. The first angle is different from the second angle, and the reference point is the intersection point of the light beam on the obstacle.

[0217] The first determination module 1103 is used to determine the transparent object from the obstacles according to the detection result of the obstacles.

[0218] To further achieve the above Figures 4 to 10 The present application also provides a transparent object recognition device, such as Fig.12 As shown, Fig.12 A schematic diagram of a transparent object recognition device provided in this application Figure 2The transparent object recognition device 1100 also includes: a similarity acquisition module 1104, a second determination module 1105, a second acquisition module 1106, a generation module 1107, a merging module 1108, a navigation module 1109, and a display module 1110.

[0219] The similarity acquisition module 1104 is used to acquire the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material with respect to the point cloud intensity sets of multiple transparent materials.

[0220] The second determining module 1105 is configured to use the transparent materials with a similarity greater than or equal to a second threshold among the plurality of similarities as the material of the transparent object.

[0221] The second acquisition module 1106 is used to acquire point cloud distance distribution data, where the point cloud distance distribution data is used to indicate the distance between any two positions within the scanning range.

[0222] The generation module 1107 is used to generate an occupied grid map according to the point cloud distance distribution data. The occupied grid map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles. One grid corresponds to one or more pixel points.

[0223] The merging module 1108 is used to merge the occupied grid map with the transparent object map to obtain a semantic map. The transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by transparent objects. The semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by obstacles and / or transparent objects, and the mark of the grid is used to indicate the material of the transparent object.

[0224] The navigation module 1109 is used for navigating according to the semantic map using a navigation strategy; the navigation strategy is used to indicate: detouring the occupied grids in the semantic map.

[0225] The display module 1110 is used to display the semantic map.

[0226] It is worth noting that the processing device 610 of the aforementioned embodiment may correspond to the transparent object recognition device 1100, and may correspond to executing the method according to the embodiment of the present application. Figure 4-Figure 10 The corresponding corresponding body, and the operation and / or function of each module in the transparent object recognition device 1100 are respectively to achieve Figure 4-Figure 10 For the sake of brevity, the corresponding processes of each method in the corresponding embodiments are not repeated here.

[0227] in addition, Fig.11 and Fig.12The apparatus shown may also be implemented by a communication device, where the communication device may refer to the computing device in the aforementioned embodiment, or, when the communication device is a chip or a chip system applied to a computing device, the apparatus may also be implemented by the chip or the chip system.

[0228] When the transparent object recognition device is implemented by hardware, the hardware can be implemented by a processor or a chip. The hardware is described below by taking a chip as an example. The chip includes a processor for implementing the function of the processing device 610 in the above method. In a possible design, the chip also includes a power supply circuit for powering the processor. The chip can be directly composed of a chip, or it can include a chip and other discrete devices.

[0229] The present application provides a computing device, such as Fig.13 As shown, Fig.13 A schematic diagram of the structure of a computing device provided in this application. The computing device can be applied to Figure 1 In the computer system shown.

[0230] The computing device 1300 can specifically be a mobile phone, a tablet computer, a television (also known as a smart TV, a smart screen or a large-screen device), a laptop computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device (for example: a smart watch, a smart bracelet, smart glasses), a vehicle-mounted device, a virtual reality device, a server and other electronic devices with computing capabilities, as well as automobiles, robots, drones and other simultaneous localization and mapping (SLAM) devices.

[0231] like Fig.13 As shown, the computing device 1300 includes: a bus 1302, a processor 1304, a memory 1306, and a communication interface 1308. The processor 1304, the memory 1306, and the communication interface 1308 communicate with each other through the bus 1302. The computing device 1300 can be a server or a terminal device. It is worth noting that the present application does not limit the number of processors and memories in the processing device.

[0232] The bus 1302 may be, but is not limited to: a peripheral component interconnect express (PCIe) bus, a universal serial bus (USB), or an inter-integrated circuit (I2C), an extended industry standard architecture (EISA) bus, a unified bus (Ubus or UB), a compute express link (CXL), a cache coherent interconnect for accelerators (CCIX), a controller area network (CAN), etc. The bus 1302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.13 The bus 1302 may include a path for transmitting information between various components of the computing device 1300 (eg, the memory 1306, the processor 1304, and the communication interface 1308).

[0233] The processor 1304 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0234] The memory 1306 may include a volatile memory, such as a random access memory (RAM). The memory 1306 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0235] The memory 1306 stores executable program codes, and the processor 1304 executes the executable program codes to respectively implement the functions of the first acquisition module, the receiving module, and the first determination module, thereby implementing the transparent object recognition method. That is, the memory 1306 stores instructions for executing the transparent object recognition method.

[0236] The communication interface 1308 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1300 and other devices or communication networks.

[0237] In a possible embodiment, the computing device 1300 may further include a laser radar or a motion component. The processor 1304 , the memory 1306 , the communication interface 1308 , the laser radar, and the motion component are connected via a bus 1302 .

[0238] LiDAR is a sensor used to measure and sense the distance and geometry of the surrounding environment. LiDARs may include: Rotating LiDAR: Rotating LiDAR obtains point cloud data of the environment by rotating scanning. Rotating LiDAR usually consists of a rotating laser beam and a receiver, which can achieve panoramic scanning in the horizontal direction. Rotating LiDAR has a large coverage range and high-density point cloud output, which is suitable for tasks such as 3D reconstruction, map construction and obstacle detection.

[0239] Solid-state LiDAR: Solid-state LiDAR uses solid-state optoelectronic devices (such as solid-state lasers and solid-state receivers) for laser emission and reception. Compared with rotating LiDAR, solid-state LiDAR does not require mechanical rotation and has a smaller size, higher reliability and lower power consumption. However, due to the limited emission and reception angles of solid-state LiDAR, its data collection range is relatively small.

[0240] 3D TOF LiDAR (time-of-flight LiDAR): 3D TOF LiDAR uses the round-trip time of light pulses to measure the distance between an object and the radar. It measures the distance by sending a short pulse beam and measuring the time it takes for the beam to return to the radar. 3D TOF LiDAR has the characteristics of high-speed ranging and high precision, and is suitable for applications in fast perception and dynamic environments.

[0241] Modulated continuous wave LiDAR: Modulated continuous wave LiDAR uses a modulated continuous wave beam for ranging. Modulated continuous wave LiDAR encodes distance information by changing the frequency or amplitude of light, and decodes it through the receiver to achieve measurement. Modulated continuous wave LiDAR is suitable for long-distance measurement and detection of high-speed moving objects.

[0242] The motion component may include a motor, a wheel set, or a track, etc., to enable the computing device 1300 to move.

[0243] The embodiment of the present application also provides a computer program product including instructions. The computer program product may be a software or program product including instructions that can be run on a processing device or stored in any available medium. When the computer program product is run on at least one processing device, the at least one processing device executes the above-mentioned transparent object recognition method.

[0244] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by the processing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the processing device to perform the transparent object recognition method.

[0245] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, a tape; it may also be an optical medium, for example, a digital video disc (DVD); it may also be a semiconductor medium, for example, a solid state drive (SSD).

[0246] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A transparent object recognition method, characterized in that: The method is applied to a processing device, and the method comprises: Obtain obstacles within the scanning range; The light beam emitted by the processing device forms an angle with a tangent plane of a reference point on the obstacle, and during the process of changing from a first angle to a second angle, receiving a detection result of the obstacle, the first angle is different from the second angle, and the reference point is an intersection point of the light beam on the obstacle; According to the detection result of the obstacle, a transparent object is determined from the obstacles.

2. The method according to claim 1, characterized in that The light beam emitted by the processing device forms an angle with the tangent plane of the reference point on the obstacle, and the change from the first angle to the second angle is used to indicate that: during the process of the processing device moving around the obstacle, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

3. The method according to claim 2, characterized in that The processing device moving around the obstacle includes: the processing device moving clockwise around the obstacle, or the processing device moving counterclockwise around the obstacle.

4. The method according to claim 1, characterized in that The light beam emitted by the processing device forms an angle with the tangent plane of the reference point on the obstacle, and the change from the first angle to the second angle is used to indicate that: during the process of the processing device moving along a straight line, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

5. The method according to any one of claims 1 to 4, characterized in that The detection result is used to indicate: a point cloud intensity set at multiple different angles; The point cloud intensity set includes multiple point cloud intensities, and any one of the multiple point cloud intensities is used to indicate: the reflection intensity of the light beam at an angle at the reference point of the obstacle, and the angle is between the first angle and the second angle.

6. The method according to claim 5, characterized in that The step of determining the transparent object from the obstacles according to the detection result of the obstacles comprises: Obtaining the similarity between the point cloud intensity set of the obstacle and the point cloud intensity set of the non-transparent object; Obstacles with a similarity less than or equal to a first threshold are determined as the transparent objects.

7. The method according to claim 5 or 6, characterized in that: The point cloud intensity set under the multiple different angles is a point cloud intensity curve, and the point cloud intensity curve is used to indicate: the corresponding relationship between the point cloud intensity and the angle.

8. The method according to claim 7, characterized in that The similarity of the point cloud intensity set is used to indicate: the similarity of the attributes of the point cloud intensity curve; The attributes of the point cloud intensity curve include: one or more of a peak value, an average width, and an average gradient; The average width is used to indicate: the difference between the horizontal coordinates of two points in the point cloud intensity curve whose vertical coordinates are half of the peak value, the vertical coordinate is used to indicate the point cloud intensity, and the horizontal coordinate is used to indicate the angle; The average gradient is used to indicate: an average value of gradients of multiple points in the point cloud intensity curve.

9. The method according to any one of claims 5 to 8, characterized in that The method further comprises: For point cloud intensity sets of multiple transparent materials, obtaining the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material; The transparent materials with a plurality of similarities greater than or equal to a second threshold are used as the material of the transparent object.

10. The method according to claim 9, characterized in that The method further comprises: Acquire point cloud distance distribution data; the point cloud distance distribution data is used to indicate the distance between any two positions within the scanning range; Generate an occupied grid map according to the point cloud distance distribution data, wherein the occupied grid map is used to indicate whether a grid in the map corresponding to the scanning range is occupied by an obstacle, and one grid corresponds to one or more pixel points; The occupied grid map is merged with the transparent object map to obtain a semantic map, wherein the transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by the transparent object; the semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by the obstacle and / or the transparent object, and the mark of the grid is used to indicate the material of the transparent object.

11. The method according to claim 10, characterized in that The method further comprises: Navigation is performed using a navigation strategy according to the semantic map; the navigation strategy is used to instruct: circumventing occupied grids in the semantic map.

12. The method according to claim 10, characterized in that The method further comprises: The semantic map is displayed.

13. A transparent object recognition device, characterized in that: The device is applied to a processing device, and comprises: a first acquisition module, a receiving module and a first determination module; A first acquisition module is used to acquire obstacles within the scanning range; a receiving module, configured to receive a detection result of the obstacle when an angle is formed between the light beam emitted by the processing device and a tangent plane of a reference point on the obstacle, and when the angle changes from a first angle to a second angle, the first angle is different from the second angle, and the reference point is an intersection point of the light beam on the obstacle; The first determination module is used to determine the transparent object from the obstacles according to the detection result of the obstacles.

14. The device according to claim 13, characterized in that The light beam emitted by the processing device forms an angle with the tangent plane of the reference point on the obstacle, and the change from the first angle to the second angle is used to indicate that: during the process of the processing device moving around the obstacle, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

15. The device according to claim 14, characterized in that The processing device moving around the obstacle includes: the processing device moving clockwise around the obstacle, or the processing device moving counterclockwise around the obstacle.

16. The device according to claim 13, characterized in that The light beam emitted by the processing device forms an angle with the tangent plane of the reference point on the obstacle, and the change from the first angle to the second angle is used to indicate that: during the process of the processing device moving along a straight line, the angle between the light beam emitted by the processing device and the tangent plane of the reference point changes from the first angle to the second angle.

17. The device according to any one of claims 13 to 16, characterized in that The detection result is used to indicate: a set of point cloud intensities at multiple different angles; the point cloud intensity set includes multiple point cloud intensities, and any one of the multiple point cloud intensities is used to indicate: the reflection intensity of the reference point of the obstacle to a light beam at an angle, and the angle is between the first angle and the second angle.

18. The device according to claim 17, characterized in that The first determination module is specifically used to obtain the similarity between the point cloud intensity set of the obstacle and the point cloud intensity set of the non-transparent object, and determine the obstacle with a similarity less than or equal to a first threshold as the transparent object.

19. The device according to claim 17 or 18, characterized in that The point cloud intensity set under the multiple different angles is a point cloud intensity curve, and the point cloud intensity curve is used to indicate: the corresponding relationship between the point cloud intensity and the angle.

20. The device according to claim 19, characterized in that The similarity of the point cloud intensity set is used to indicate: the similarity of the attributes of the point cloud intensity curve; The attributes of the point cloud intensity curve include: one or more of a peak value, an average width, and an average gradient; The average width is used to indicate: the difference between the horizontal coordinates of two points in the point cloud intensity curve whose vertical coordinates are half of the peak value, the vertical coordinate is used to indicate the point cloud intensity, and the horizontal coordinate is used to indicate the angle; The average gradient is used to indicate: an average value of gradients of multiple points in the point cloud intensity curve.

21. The device according to any one of claims 17 to 20, characterized in that The transparent object recognition device further includes: a similarity acquisition module and a second determination module; The similarity acquisition module is used to indicate the point cloud intensity sets for multiple transparent materials, and to acquire the similarity between the point cloud intensity set of the transparent object and the point cloud intensity set of each transparent material; The second determination module is used to use the transparent materials with a similarity greater than or equal to a second threshold among the multiple similarities as the material of the transparent object.

22. The device according to claim 21, characterized in that The transparent object recognition device further includes: a second acquisition module, a generation module and a merging module; The second acquisition module is used to acquire point cloud distance distribution data; the point cloud distance distribution data is used to indicate the distance between any two positions within the scanning range; The generating module is used to generate an occupied grid map according to the point cloud distance distribution data, wherein the occupied grid map is used to indicate whether a grid in the map corresponding to the scanning range is occupied by an obstacle, and one grid corresponds to one or more pixel points; The merging module is used to merge the occupied grid map with the transparent object map to obtain a semantic map, wherein the transparent object map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by the transparent object; the semantic map is used to indicate whether the grid in the map corresponding to the scanning range is occupied by the obstacle and / or the transparent object, and the mark of the grid is used to indicate the material of the transparent object.

23. The device according to claim 22, characterized in that The transparent object recognition device further includes: a navigation module; The navigation module is used to navigate according to the semantic map using a navigation strategy; the navigation strategy is used to instruct: to detour the occupied grids in the semantic map.

24. The device according to claim 22, characterized in that The transparent object recognition device further includes: a display module; The display module is used to display the semantic map.

25. A computing device, characterized in that including a processor and a memory; The processor is configured to execute instructions stored in the memory so that the computing device performs the method according to any one of claims 1 to 12.

Images