Method and computer equipment for detecting light-transmitting materials

Abstract

The present application relates to a method and computer device for detecting transparent materials. The method comprises: obtaining a laser point cloud through a laser ranging sensor; determining a target point cloud from the laser point cloud; performing clustering processing on the target point cloud to obtain a transparent material point cluster; fitting a target transparent material line segment corresponding to each transparent material point cluster; the target transparent material line segment represents a transparent material object corresponding to the transparent material point cluster; and determining a target transparent material object in the environment where the laser ranging sensor is located based on each target transparent material line segment. The present method can accurately detect transparent materials.

Description

Technical Field

[0001] The present application relates to the field of mobile robot perception technology, and in particular to a method and computer device for detecting light-transmitting materials. Background Art

[0002] With the development of artificial intelligence technology and robotics technology, various mobile computer devices have emerged, such as sweeping robots, driverless vehicles, automatic food delivery vehicles, etc. These computer devices can move automatically to complete corresponding tasks.

[0003] When computer equipment is moving, it usually uses laser rangefinders to scan the environment to avoid obstacles. Laser rangefinders emit lasers into the surrounding environment. After being reflected by objects in the environment, the lasers scatter in all directions. Some of the scattered light returns to the receiver of the laser rangefinder, which records and processes the time from the laser emission to the return reception to obtain the distance to the objects in the environment. The laser scans the objects in the environment to obtain a data set of reflection points, namely the laser point cloud. Each laser point cloud contains coordinates and laser reflection intensity, and obstacles are then determined based on the laser point cloud. However, as an optical sensor, most lasers of laser rangefinders will pass through transparent materials to scan obstacles behind the transparent materials. There is only a small point cloud in the direction perpendicular to the transparent material, and there is a problem that the transparent material cannot be accurately detected. Summary of the invention

[0004] Based on this, it is necessary to provide a detection method, device, computer equipment, computer-readable storage medium and computer program product that can accurately detect translucent materials in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting a light-transmitting material, comprising:

[0006] Acquire laser point cloud through laser ranging sensor;

[0007] Determining a target point cloud from the laser point cloud;

[0008] Performing clustering processing on the target point cloud to obtain light-transmitting material point clusters;

[0009] For each of the light-transmitting material point clusters, a target light-transmitting material line segment corresponding to the light-transmitting material point cluster is fitted; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0010] Based on each of the target light-transmitting material line segments, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined.

[0011] In one embodiment, for each of the light-transmitting material point clusters, fitting a target light-transmitting material line segment corresponding to the light-transmitting material point cluster includes:

[0012] For each of the light-transmitting material point clusters, fitting a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster;

[0013] Determine a candidate light-transmitting material line segment from the candidate light-transmitting material straight lines;

[0014] If the candidate translucent material line segment satisfies both the first constraint and the second constraint, the candidate translucent material line segment is used as the target translucent material line segment corresponding to the translucent material point cluster; the first constraint includes that the length of the candidate translucent material line segment is greater than a preset length threshold, the second constraint includes that the number of first target point clouds in the translucent material point cluster is greater than a preset number threshold, and the distance between the first target point cloud and the candidate translucent material straight line is less than a preset distance threshold.

[0015] In one embodiment, determining a candidate light-transmitting material line segment from the candidate light-transmitting material straight lines comprises:

[0016] Based on each target point cloud in the light-transmitting material point cluster, determining a coordinate maximum value point and a coordinate minimum value point;

[0017] Determine a first endpoint of the candidate light-transmitting material straight line according to the coordinate maximum value point and the candidate light-transmitting material straight line, and determine a second endpoint of the candidate light-transmitting material straight line according to the coordinate minimum value point and the candidate light-transmitting material straight line;

[0018] Based on the first endpoint and the second endpoint, a candidate light-transmitting material line segment corresponding to the light-transmitting material point cluster is determined.

[0019] In one embodiment, determining the coordinate maximum value point and the coordinate minimum value point based on each target point cloud in the light-transmitting material point cluster includes:

[0020] In the world coordinate system to which the target point cloud belongs, determining the maximum x-coordinate value and the minimum x-coordinate value in the x-axis direction from each target point cloud of the light-transmitting material point cluster, and determining the maximum y-coordinate value and the minimum y-coordinate value in the y-axis direction from each target point cloud in the light-transmitting material point cluster;

[0021] Determine a coordinate maximum point based on the x-coordinate maximum value and the y-coordinate maximum value;

[0022] Based on the minimum x-coordinate value and the minimum y-coordinate value, a coordinate minimum point is determined.

[0023] In one embodiment, the step of determining a first endpoint of the candidate light-transmitting material straight line according to the coordinate maximum point and the candidate light-transmitting material straight line, and determining a second endpoint of the candidate light-transmitting material straight line according to the coordinate minimum point and the candidate light-transmitting material straight line, comprises:

[0024] Determine the foot of a first perpendicular between the coordinate maximum point and the candidate light-transmitting material straight line, and use the first foot of the perpendicular as the first endpoint of the candidate light-transmitting material straight line;

[0025] Determine the second foot of a perpendicular between the coordinate minimum point and the candidate light-transmitting material straight line, and use the second foot of a perpendicular as the second endpoint of the candidate light-transmitting material straight line.

[0026] In one embodiment, the method further comprises:

[0027] If the candidate light-transmitting material line segment does not satisfy the first constraint condition or the second constraint condition, determining a second target point cloud related to the candidate light-transmitting material line segment from the light-transmitting material point cluster;

[0028] The second target point cloud in the light-transmitting material point cluster is removed to obtain a new light-transmitting material point cluster, and based on the new light-transmitting material point cluster, the step of fitting a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster is returned to be executed.

[0029] In one embodiment, determining a target point cloud from the laser point cloud comprises:

[0030] For each of the laser point clouds, obtaining position information and intensity information of the laser point cloud;

[0031] Based on the position information and intensity information of each of the laser point clouds, a target point cloud is determined.

[0032] In one embodiment, the position information includes an angle between the laser ranging sensor and the position of the laser point cloud, and a distance between the laser ranging sensor and the position of the laser point cloud; and determining the target point cloud based on the position information and intensity information of each of the laser point clouds includes:

[0033] Based on the angles and distances corresponding to each of the laser point clouds, determining whether the laser point cloud meets a position condition; the position condition includes the existence of adjacent laser point clouds, and the distances corresponding to each of the adjacent laser point clouds are within a preset distance range;

[0034] Based on the intensity information corresponding to each of the laser point clouds, determining whether the laser point cloud meets an intensity condition; the intensity condition includes that the intensity information of each of the laser point clouds has a gradient change and the intensity information of the laser point cloud is higher than a preset intensity threshold;

[0035] If the laser point cloud satisfies both the position condition and the intensity condition, the laser point cloud is determined as a target point cloud.

[0036] In one embodiment, determining the target light-transmitting material object in the environment where the laser ranging sensor is located based on each of the target light-transmitting material line segments includes:

[0037] Matching each of the target light-transmitting material line segments, and merging at least two target light-transmitting material line segments that match each other to obtain a new target light-transmitting material line segment;

[0038] The new target light-transmitting material line segment is used to update each of the target light-transmitting material line segments, and each updated target light-transmitting material line segment is mapped to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0039] In a second aspect, the present application also provides a light-transmitting material detection device, comprising:

[0040] A laser point cloud acquisition module is used to acquire laser point clouds through a laser ranging sensor;

[0041] A target point cloud acquisition module is used to determine the target point cloud from the laser point cloud;

[0042] A clustering processing module, used for performing clustering processing on the target point cloud to obtain a light-transmitting material point cluster;

[0043] A line segment fitting module is used to fit a target light-transmitting material line segment corresponding to each light-transmitting material point cluster; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0044] The target light-transmitting material object determining module is used to determine the target light-transmitting material object in the environment where the laser ranging sensor is located based on each of the target light-transmitting material line segments.

[0045] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0046] Acquire laser point cloud through laser ranging sensor;

[0047] Determining a target point cloud from the laser point cloud;

[0048] Performing clustering processing on the target point cloud to obtain light-transmitting material point clusters;

[0049] For each of the light-transmitting material point clusters, a target light-transmitting material line segment corresponding to the light-transmitting material point cluster is fitted; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0050] Based on each of the target light-transmitting material line segments, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0052] Acquire laser point cloud through laser ranging sensor;

[0053] Determining a target point cloud from the laser point cloud;

[0054] Performing clustering processing on the target point cloud to obtain light-transmitting material point clusters;

[0055] For each of the light-transmitting material point clusters, a target light-transmitting material line segment corresponding to the light-transmitting material point cluster is fitted; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0056] Based on each of the target light-transmitting material line segments, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined.

[0057] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0058] Acquire laser point cloud through laser ranging sensor;

[0059] Determining a target point cloud from the laser point cloud;

[0060] Performing clustering processing on the target point cloud to obtain light-transmitting material point clusters;

[0061] For each of the light-transmitting material point clusters, a target light-transmitting material line segment corresponding to the light-transmitting material point cluster is fitted; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0062] Based on each of the target light-transmitting material line segments, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined.

[0063] The above-mentioned translucent material detection method, device, computer equipment, computer-readable storage medium and computer program product obtain a laser point cloud through a laser ranging sensor, and determine a target point cloud from the laser point cloud; cluster the target point cloud to obtain a translucent material point cluster; for each translucent material point cluster, fit a target translucent material line segment corresponding to the translucent material point cluster, and the target translucent material line segment represents the translucent material object corresponding to the translucent material point cluster. Then, based on each target translucent material line segment, the target translucent material object in the environment where the laser ranging sensor is located can be accurately determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 Schematic diagram of a process of detecting a light-transmitting material in one embodiment;

[0066] Figure 2 A schematic diagram of a laser ranging sensor scanning a light-transmitting material in one embodiment;

[0067] Figure 3 is a visualization diagram of a laser point cloud in one embodiment;

[0068] Figure 4 A schematic diagram of data expression of a laser point cloud in a polar coordinate system in one embodiment;

[0069] Figure 5 A schematic diagram of determining a candidate light-transmitting material line segment in one embodiment;

[0070] Figure 6 A schematic diagram of fitting a candidate light-transmitting material straight line in one embodiment;

[0071] Figure 7 It is a schematic diagram of fitting a candidate light-transmitting material straight line in another embodiment;

[0072] Figure 8 is a schematic flow chart of a method for detecting light-transmitting materials in another embodiment;

[0073] Fig. 9 is a structural block diagram of a light-transmitting material detection device in one embodiment;

[0074] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0076] In one embodiment, Figure 1 As shown, a method for detecting light-transmitting materials is provided. This embodiment uses the method applied to a computer device as an example for illustration. The computer device can be a terminal or a server. It can be understood that the method can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various robots, unmanned vehicles, automatic food delivery vehicles, personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The robot can be a cleaning robot, a distribution robot, a logistics robot, an inspection robot and a disinfection robot, etc. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart car-mounted device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0077] In this embodiment, the light-transmitting material detection method includes the following steps:

[0078] Step S102, obtaining a laser point cloud through a laser ranging sensor.

[0079] Among them, the laser ranging sensor is a system that detects characteristic quantities such as target position and speed by emitting laser beams. ‌‌Optionally, the laser ranging sensor can be a line laser sensor, a laser radar, etc., wherein the laser radar can be a single-line laser radar or a multi-line laser radar, etc. A single-line laser radar is a laser radar that emits one laser beam, and a multi-line laser radar is a laser radar that emits multiple laser beams.

[0080] Laser point cloud is the data of coordinate points in three-dimensional space obtained by scanning with a laser ranging sensor. Laser point cloud can include the location information of the coordinate point and the intensity information of the laser reflected from the coordinate point.

[0081] Optionally, a laser ranging sensor is provided on the computer device, and the laser ranging sensor is used to scan the surrounding environment to obtain at least two laser point clouds.

[0082] Step S104, determining the target point cloud from the laser point cloud.

[0083] The target point cloud is a laser point cloud of a light-transmitting material object, which may be glass, a transparent plastic plate, a light-transmitting plastic film, or a transparent bag, but is not limited thereto.

[0084] Optionally, the computer device obtains a selection instruction from the user and selects a target point cloud from the laser point cloud.

[0085] Optionally, determining the target point cloud from the laser point cloud includes: acquiring position information and intensity information of the laser point cloud for each laser point cloud; and determining the target point cloud based on the position information and intensity information of each laser point cloud.

[0086] The intensity information of the laser point cloud is used to characterize the intensity of the laser reflected from the coordinate point where the laser point cloud is located.

[0087] Optionally, the computer device determines whether the laser point cloud satisfies the constraint condition based on the position information and intensity information of each laser point cloud, and if the laser point cloud satisfies the constraint condition, the laser point cloud is used as the target point cloud. The constraint condition can be set as needed, such as the constraint condition can include a first constraint condition related to the position information and a second constraint condition related to the intensity information.

[0088] Optionally, the position information includes the angle between the laser ranging sensor and the laser point cloud, and the distance between the laser ranging sensor and the laser point cloud; based on the position information and intensity information of each laser point cloud, determining the target point cloud, including: determining whether the laser point cloud meets the position condition based on the angle and distance corresponding to each laser point cloud; the position condition includes the existence of adjacent laser point clouds, and the distances corresponding to each adjacent laser point cloud are all within a preset distance range; based on the intensity information corresponding to each laser point cloud, determining whether the laser point cloud meets the intensity condition; the intensity condition includes that the intensity information of each laser point cloud has a preset change and the intensity information of the laser point cloud is higher than a preset intensity threshold; if the laser point cloud meets both the position condition and the intensity condition, the laser point cloud is determined as the target point cloud.

[0089] Among them, the preset distance range and the preset intensity threshold can be set as needed. The preset distance range and the preset intensity threshold can be adaptively set according to the physical properties of different light-transmitting materials and the ranging principle of the laser ranging sensor. For example, different light-transmitting materials can be detected multiple times, and the collected data can be statistically analyzed. According to the statistical analysis results, the preset distance range and the preset intensity threshold are adaptively set for the type of light-transmitting material in the computer device operation scene. The intensity information of each laser point cloud has preset changes, which can be gradient changes or fluctuation changes, for example, the intensity of each laser point cloud first increases and then decreases. The preset changes can also be other types of changes. The change law of the intensity information of the laser point cloud can be determined based on the physical properties of the light-transmitting material and the ranging principle of the laser ranging sensor, and no specific restrictions are made here.

[0090] The computer device matches the angle and distance corresponding to each laser point cloud with the position condition. If there are adjacent laser point clouds and the distances corresponding to each adjacent laser point cloud are within a preset distance range, the laser point cloud meets the position condition; the computer device matches the intensity information corresponding to each laser point cloud with the intensity condition. If there is a preset change in the intensity information of each adjacent laser point cloud and the intensity information of each laser point cloud is higher than a preset intensity threshold, the laser point cloud meets the intensity condition.

[0091] like Figure 2 As shown in the figure, if there is a transparent material in the environment where the laser ranging sensor is located, the laser ranging sensor will emit a laser beam (straight line with arrow) when facing a piece of transparent material, and the obtained laser point cloud is as follows Figure 3 As shown. Figure 3 In the polar coordinate system to which the laser distance sensor belongs, the laser distance sensor is at the center of the circle, and the laser point cloud shows the distance between the position and the laser distance sensor. The data expression of each laser point cloud in the polar coordinate system can be referred to Figure 4 As shown, draw a perpendicular line through point M to the axis Ox, and the foot of the perpendicular M' is called the polar coordinate projection point of point M, denoted by . Vector It is called vector The polar coordinate projection vector of In the polar coordinate system Ox, establish the plane Rt coordinate system xOy with O as the origin and Ox as the positive direction of the x-axis. The vector ,So , ,then The rectangular coordinates are In this way, the position information of the laser point cloud in the polar coordinate system to which the laser ranging sensor belongs can be obtained.

[0092] In an exemplary embodiment, the light-transmitting material is glass, and the laser ranging sensor is a laser radar; the laser ranging sensor acquires a number of laser point clouds, such as Figure 3 As shown, Figure 3 The 329 in the figure indicates that the distance between the laser point cloud and the laser ranging sensor is 329 mm, the 659 indicates that the distance between the laser point cloud and the laser ranging sensor is 659 mm, and the 359 indicates that the distance between the laser point cloud and the laser ranging sensor is 359 mm. Figure 3 It also includes point clouds of other obstacles, such as Figure 3 The white continuous laser point cloud clusters formed in the lower left and lower right may correspond to obstacles such as laser point clouds formed by human feet or seats.

[0093] As shown in Table 1, the computer device obtains laser point clouds with ID numbers 2-17. Each laser point cloud carries position information and intensity information. The position information includes the angle between the laser ranging sensor and the position of the laser point cloud, and the distance between the laser ranging sensor and the position of the laser point cloud. Based on the angle and distance corresponding to each laser point cloud, the computer device can determine that the laser point clouds with ID numbers 7-12 meet the position condition, that is, the laser point clouds with ID numbers 7-12 have adjacent laser point clouds (the distances of the laser point clouds are close), and the adjacent The distances corresponding to each laser point cloud are within the preset distance range (the distance fluctuates up and down by 5mm); based on the intensity information corresponding to each laser point cloud, it can be determined that the laser point clouds with ID numbers 7-12 meet the intensity condition, that is, the intensity information of the laser point clouds with ID numbers 7-12 has a preset change (gradient change) and the intensity information of the laser point cloud is higher than the preset intensity threshold (for example, 150); therefore, it can be determined that the laser point clouds with ID numbers 7-12 meet the position condition and the intensity condition, and the laser point clouds with ID numbers 7-12 are determined as the target point clouds, that is, Figure 2 The laser point cloud selected in the middle box is the target point cloud.

[0094] Table 1:

[0095]

[0096] The distance of the laser point cloud that does not receive laser reflection or exceeds the maximum detection distance is usually displayed as 0.

[0097] Step S106, clustering the target point cloud to obtain light-transmitting material point clusters.

[0098] The light-transmitting material point cluster is a data cluster obtained by clustering at least two target point clouds.

[0099] Optionally, the computer device performs Euclidean clustering on the target point cloud to obtain a transparent material point cluster. The Euclidean clustering can represent the close target point cloud as a point cluster, that is, it is ensured that each target point cloud in the transparent material point cluster can find at least one point whose distance is less than a certain value.

[0100] Optionally, the computer may also use other clustering algorithms to perform clustering processing on the target point cloud, such as a k-means algorithm, a Gaussian mixture clustering algorithm, or a hierarchical clustering algorithm, but is not limited thereto.

[0101] Optionally, the computer device constructs a target point cloud set, the target point cloud set includes at least two target point clouds; clustering is performed on the target point cloud set to obtain at least one light-transmitting material point cluster.

[0102] The computer can update the target point cloud set to obtain a new target point cloud set, and perform clustering on the new target point cloud set to obtain at least one light-transmitting material point cluster. Optionally, if the number of target point clouds in the target point cloud set is greater than a preset number threshold or the range formed by the positions of the target point clouds in the target point cloud set is greater than a preset range, the target point clouds that were first added to the target point cloud set are removed until the number of target point clouds in the target point cloud set is less than or equal to the preset number threshold, and a new target point cloud set is obtained, so that the unlimited expansion of the target point cloud set can be avoided.

[0103] Step S108 , for each transparent material point cluster, a target transparent material line segment corresponding to the transparent material point cluster is fitted; the target transparent material line segment represents the transparent material object corresponding to the transparent material point cluster.

[0104] The target transparent material line segment is a line segment fitted by the transparent material point cluster in the world coordinate system, and is used to represent the transparent material object corresponding to the transparent material point cluster. The length of the target transparent material line segment represents the length of the transparent material object corresponding to the transparent material point cluster.

[0105] Optionally, for each transparent material point cluster, a candidate transparent material line corresponding to the transparent material point cluster is fitted; and a target transparent material line segment corresponding to the transparent material point cluster is determined from the candidate transparent material line. The candidate transparent material line is a line fitted by the transparent material point cluster.

[0106] The computer device may intercept a partial line segment from the candidate light-transmitting material straight line as a target light-transmitting material line segment corresponding to the light-transmitting material point cluster.

[0107] Step S110 , determining a target light-transmitting material object in the environment where the laser ranging sensor is located based on each target light-transmitting material line segment.

[0108] The target light-transmitting material object is a light-transmitting material in the environment where the laser ranging sensor is located. The target light-transmitting material object can be determined as an obstacle to prevent the computer device from colliding with the light-transmitting material during movement.

[0109] Optionally, the computer device maps each target light-transmitting material line segment to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0110] Optionally, based on each target light-transmitting material line segment, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined, including: matching each target light-transmitting material line segment, and merging at least two target light-transmitting material line segments that match each other to obtain a new target light-transmitting material line segment; updating each target light-transmitting material line segment with the new target light-transmitting material line segment, and mapping each updated target light-transmitting material line segment to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0111] The computer device matches each target light-transmitting material line segment. If there are not at least two target light-transmitting material line segments that match each other, each target light-transmitting material line segment is mapped to the environment where the laser ranging sensor is located to determine the target light-transmitting material object; if there are at least two target light-transmitting material line segments that match each other, the at least two target light-transmitting material line segments that match each other are merged to obtain a new target light-transmitting material line segment, and the new target light-transmitting material line segment replaces the corresponding at least two target light-transmitting material line segments that match each other to obtain each updated target light-transmitting material line segment, and each updated target light-transmitting material line segment is mapped to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0112] It can be understood that, among each target light-transmitting material line segment, there may be only at least two target light-transmitting material line segments that match each other, or there may be both at least two target light-transmitting material line segments that match each other and target light-transmitting material line segments that do not match each other. The computer device merges at least two target light-transmitting material line segments that match each other among each target light-transmitting material line segment to obtain a new target light-transmitting material line segment, and replaces the corresponding at least two target light-transmitting material line segments that match each other with the new target light-transmitting material line segment, so as to obtain an accurate merged target light-transmitting material line segment.

[0113] Optionally, for every two target translucent material segments, including a first target translucent material segment and a second target translucent material segment, the computer device matches the endpoints of the first target translucent material segment with the endpoints of the second target translucent material segment; if the distances between the endpoints of the first target translucent material segment and the corresponding endpoints of the second target translucent material segment are both less than a specified distance threshold, then the first target translucent material segment and the second target translucent material segment match each other.

[0114] The computer device determines the distances between the first endpoint and the second endpoint of the first target light-transmitting material line segment and the first endpoint and the second endpoint of the second target light-transmitting material line segment, respectively. If the distance between the first endpoint of the first target light-transmitting material line segment and the first endpoint of the second target light-transmitting material line segment is less than a specified distance threshold, and the distance between the second endpoint of the first target light-transmitting material line segment and the second endpoint of the second target light-transmitting material line segment is less than the specified distance threshold, then the first target light-transmitting material line segment and the second target light-transmitting material line segment match each other.

[0115] Exemplarily, the first target light-transmitting material line segment A is composed of a first endpoint a and a second endpoint b, and the second target light-transmitting material line segment B is composed of a first endpoint c and a second endpoint d. The distances between a and c, and d are calculated respectively. If the distance between a and c is very short, that is, the distance between a and c is less than a specified distance threshold, then the distances between b and c, and d are calculated respectively. If the distance between b and d is very short, that is, the distance between b and d is less than the specified distance threshold, then it can be determined that the first target light-transmitting material line segment A and the second target light-transmitting material line segment B match each other, and the first target light-transmitting material line segment A and the second target light-transmitting material line segment B are similar.

[0116] The above-mentioned method for detecting translucent materials obtains a laser point cloud through a laser ranging sensor, and determines a target point cloud from the laser point cloud; clusters the target point cloud to obtain a translucent material point cluster; for each translucent material point cluster, fits a target translucent material line segment corresponding to the translucent material point cluster, and the target translucent material line segment represents the translucent material object corresponding to the translucent material point cluster. Then, based on each target translucent material line segment, the target translucent material object in the environment where the laser ranging sensor is located can be accurately determined.

[0117] In one embodiment, for each transparent material point cluster, a target transparent material line segment corresponding to the transparent material point cluster is fitted, including: for each transparent material point cluster, a candidate transparent material straight line corresponding to the transparent material point cluster is fitted; a candidate transparent material line segment is determined from the candidate transparent material straight lines; if the candidate transparent material line segment satisfies a first constraint condition and a second constraint condition, the candidate transparent material line segment is used as the target transparent material line segment corresponding to the transparent material point cluster; the first constraint condition includes that the length of the candidate transparent material line segment is greater than a preset length threshold, and the second constraint condition includes that the number of first target point clouds in the transparent material point cluster is greater than a preset number threshold, and the distance between the first target point cloud and the candidate transparent material straight line is less than a preset distance threshold.

[0118] Among them, both the preset length threshold and the preset distance threshold can be set as needed. The preset length threshold is, for example, 0.05m. Since in actual scenes, objects of translucent materials have a certain length, if the translucent material detected by the laser ranging sensor is very short, that is, less than the preset length threshold, it is likely that the laser ranging sensor misdetects, therefore, setting the preset length threshold can reduce the probability of processing the laser ranging sensor misdetected data. The preset distance threshold is used to constrain the quality of the candidate translucent material line segment to avoid the first target point cloud used to fit the candidate translucent material line segment being too discrete. When the distance between the first target point cloud and the candidate translucent material line segment is less than the preset distance threshold, it means that the first target point cloud is relatively concentrated, and the quality of the fitted candidate translucent material line segment is high, so that the quality of the target translucent material line segment determined by the candidate translucent material line segment is higher and more accurate. It can be understood that when the laser ranging sensor is set on a computer device, due to the movement of the computer device itself, the laser ranging sensor will observe the surrounding environment from multiple angles and generate multiple detection data, and the detected translucent material should be composed of multiple target point clouds. Therefore, setting the number of the first target point cloud in the transparent material point cluster to be greater than a preset number threshold can increase the credibility of the first target point cloud and improve the quality of the candidate transparent material line segments, thereby improving the credibility of the target transparent material line segments.

[0119] Optionally, for each light-transmitting material point cluster, the computer device uses a Ransac random sampling consistency algorithm to fit a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster.

[0120] For each translucent material point cluster, the computer device obtains the coordinates of the target point cloud in the polar coordinate system, which can be converted into coordinates in the Cartesian coordinate system through a calculation formula, and then the candidate translucent material straight line corresponding to the translucent material point cluster is fitted based on the coordinates in the Cartesian coordinate system.

[0121] For example, assuming that the coordinates of the target point cloud in the polar coordinate system are (r, θ, h), where r is the distance from the origin to the point, θ is the azimuth on the XY plane (usually in radians), and h is the height of the point on the Z axis; the computer device can use the following calculation formula to convert the coordinates of the target point cloud in the polar coordinate system into the coordinates in the Cartesian coordinate system: , , , the coordinates of the target point cloud in the Cartesian coordinate system are (x, y, z).

[0122] Optionally, if the transparent material point cluster cannot fit a candidate transparent material line, the transparent material point cluster is re-added to the target point cloud set, and the step of clustering the target point cloud is re-executed. The target point cloud set is a set of target point clouds.

[0123] Optionally, determining a candidate translucent material line segment from the candidate translucent material straight lines includes: determining a coordinate maximum point and a coordinate minimum point based on each target point cloud in the translucent material point cluster; determining a first endpoint in the candidate translucent material straight line based on the coordinate maximum point and the candidate translucent material straight line, and determining a second endpoint in the candidate translucent material straight line based on the coordinate minimum point and the candidate translucent material straight line; determining the candidate translucent material line segment corresponding to the translucent material point cluster based on the first endpoint and the second endpoint.

[0124] Among them, the maximum coordinate point is the point corresponding to the maximum coordinate of the target point cloud, and the minimum coordinate point is the point corresponding to the minimum coordinate of the target point cloud.

[0125] It can be understood that the computer device can accurately determine the first endpoint and the second endpoint in the candidate transparent material straight line based on the coordinate maximum point and the coordinate minimum point determined in the transparent material point cluster, and then accurately determine the candidate transparent material line segment from the candidate transparent material straight line.

[0126] Optionally, based on each target point cloud in the transparent material point cluster, determine the coordinate maximum value point and the coordinate minimum value point, including: in the world coordinate system to which the target point cloud belongs, determine the x-coordinate maximum value and the x-coordinate minimum value in the x-axis direction from each target point cloud in the transparent material point cluster, and determine the y-coordinate maximum value and the y-coordinate minimum value in the y-axis direction from each target point cloud in the transparent material point cluster; determine the coordinate maximum value point based on the x-coordinate maximum value and the y-coordinate maximum value; determine the coordinate minimum value point based on the x-coordinate minimum value and the y-coordinate minimum value.

[0127] Optionally, the computer device combines the maximum x-coordinate value and the maximum y-coordinate value into a coordinate maximum point, and combines the minimum x-coordinate value and the minimum y-coordinate value into a coordinate minimum point.

[0128] It is understandable that the computer device determines the maximum and minimum coordinates in the x-axis direction and the y-axis direction in the world coordinate system to which the target point cloud belongs, respectively, and can more accurately determine the maximum and minimum coordinate points.

[0129] Optionally, the first endpoint in the candidate light-transmitting material straight line is determined based on the coordinate maximum point and the candidate light-transmitting material straight line, and the second endpoint in the candidate light-transmitting material straight line is determined based on the coordinate minimum point and the candidate light-transmitting material straight line, including: determining the first perpendicular foot between the coordinate maximum point and the candidate light-transmitting material straight line, and using the first perpendicular foot as the first endpoint in the candidate light-transmitting material straight line; determining the second perpendicular foot between the coordinate minimum point and the candidate light-transmitting material straight line, and using the second perpendicular foot as the second endpoint in the candidate light-transmitting material straight line.

[0130] Optionally, the computer device intercepts a segment between the first endpoint and the second endpoint from the candidate light-transmitting material straight line as a candidate light-transmitting material line segment corresponding to the light-transmitting material point cluster.

[0131] like Figure 5 As shown, for a translucent material point cluster, the computer device fits a corresponding candidate translucent material straight line based on each target point cloud in the translucent material point cluster, and in the world coordinate system to which the target point cloud belongs, determines the maximum x-coordinate value (x_max) and the minimum x-coordinate value (x_min) in the x-axis direction from each target point cloud in the translucent material point cluster, and determines the maximum y-coordinate value (y_max) and the minimum y-coordinate value (y_min) in the y-axis direction from each target point cloud in the translucent material point cluster, determines the coordinate maximum point (x_max, y_max) and the coordinate minimum point (x_min, y_min), determines the first perpendicular foot F_max between the coordinate maximum point (x_max, y_max) and the candidate translucent material straight line as the first endpoint, and determines the second perpendicular foot F_min between the coordinate minimum point (x_min, y_min) and the candidate translucent material straight line as the second endpoint, and determines the line segment between the first endpoint and the second endpoint from the candidate translucent material straight line as the candidate translucent material line segment.

[0132] Reference Figure 6 and Figure 7 , the computer equipment fits the corresponding candidate transparent material straight line for the transparent material point cluster, Figure 6 The number of the first target point cloud (the gray points between the two dashed lines) is small, while Figure 7 The number of the first target point cloud (the gray dots between the two dotted lines) is large, and the distance between the first target point cloud and the candidate transparent material line is less than the preset distance threshold δ. The more the number of the first target point cloud corresponding to the fitted candidate transparent material line is, the higher the quality of the candidate transparent material line is. Figure 7The quality of the fitted candidate transparent material straight line is higher and better satisfies the second constraint.

[0133] It can be understood that the computer device determines the feet of perpendiculars between the maximum coordinate point and the minimum coordinate point to the candidate light-transmitting material straight line respectively, so as to more accurately determine the first endpoint and the second endpoint of the candidate light-transmitting material straight line.

[0134] Optionally, the computer device matches the candidate light-transmitting material line segment with the first constraint and the second constraint respectively to determine whether the candidate light-transmitting material line segment satisfies the first constraint and whether the candidate light-transmitting material line segment satisfies the second constraint.

[0135] It is understandable that the length of the transparent material in the real scene will not be too short, so the first constraint condition includes that the length of the candidate transparent material line segment is greater than the preset length threshold, which can avoid the misdetection caused by the short length of the target transparent material line segment. Although there are only a few target point clouds in a frame of laser point cloud, after the movement of the computer device itself (multiple angle observations) and the accumulation of multiple frames of laser point clouds, the detected candidate transparent material straight line is composed of multiple target point clouds. The quality of the fitted candidate transparent material straight line can be judged according to the number of target point clouds. The second constraint condition includes that the number of first target point clouds in the transparent material point cluster is greater than the preset number threshold, and the distance between the first target point cloud and the candidate transparent material line segment is less than the preset distance threshold, that is, there are more first target point clouds near the fitted candidate transparent material line segment, and the quality of the fitted candidate transparent material line segment is higher.

[0136] Optionally, the above method also includes: if the candidate transparent material line segment does not satisfy the first constraint condition or the second constraint condition, determining a second target point cloud related to the candidate transparent material line segment from the transparent material point cluster; removing the second target point cloud in the transparent material point cluster to obtain a new transparent material point cluster, and returning to execute the step of fitting the candidate transparent material straight line corresponding to the transparent material point cluster based on the new transparent material point cluster.

[0137] Optionally, the distance between the second target point cloud and the candidate light-transmitting material line segment is less than a preset distance threshold.

[0138] Optionally, the computer device updates the fitting parameters, and uses the updated fitting parameters to fit the candidate transparent material straight line corresponding to the new transparent material point cluster.

[0139] Optionally, if the candidate light-transmitting material line segment does not satisfy the first constraint condition or the second constraint condition, the candidate light-transmitting material straight line and the candidate light-transmitting material line segment are discarded.

[0140] It can be understood that if the candidate transparent material line segment does not meet the first constraint condition or the second constraint condition, it means that the second target point cloud related to the candidate transparent material line segment is unreliable, then the second target point cloud related to the candidate transparent material line segment in the transparent material point cluster is removed to obtain a new transparent material point cluster, and new candidate transparent material straight lines and candidate transparent material line segments can be obtained based on the new transparent material point cluster to prevent the re-fitting of the same candidate transparent material straight lines and candidate transparent material line segments that do not meet the conditions, and thus the candidate transparent material straight lines can be accurately re-fitted.

[0141] In an optional embodiment, if Figure 8 As shown, a laser point cloud is obtained by a laser ranging sensor, and features are extracted from the laser point cloud. A target point cloud is determined from the laser point cloud, and each target point cloud is formed into a target point cloud set. A clustering algorithm is used to cluster the target point cloud in the target point cloud set to obtain transparent material point clusters A to N. For each transparent material point cluster, if a straight line cannot be fitted, the target point cloud in the transparent material point cluster is re-added to the target point cloud set. If a candidate transparent material straight line corresponding to the transparent material point cluster is fitted, a candidate transparent material line segment is determined from the candidate transparent material straight line. If the candidate transparent material line segment satisfies both the first constraint condition and the second constraint condition, the candidate transparent material line segment is used as the target transparent material line segment (target transparent material line segment A) corresponding to the transparent material point cluster. If the candidate transparent material line segment does not satisfy the first constraint condition or the second constraint condition, the fitting parameters are updated and the candidate transparent material line is re-fitted. Based on each target transparent material line segment, the transparent material obstacle in the environment where the laser ranging sensor is located is determined.

[0142] In this embodiment, a candidate transparent material straight line is fitted for each transparent material point cluster, and a candidate transparent material line segment is determined from the candidate transparent material straight line. Then, if the candidate transparent material line segment satisfies the first constraint condition and the second constraint condition, the candidate transparent material line segment can be used as the target transparent material line segment corresponding to the transparent material point cluster, that is, a target transparent material line segment with a longer length and higher quality is obtained, and the transparent material obstacle is accurately determined.

[0143] In one embodiment, another light-transmitting material detection method is provided, which is applied to a computer device. The light-transmitting material detection method includes the following steps:

[0144] Step A1, obtaining laser point cloud through a laser ranging sensor.

[0145] Step A2, for each laser point cloud, obtain the position information and intensity information of the laser point cloud; the position information includes the angle between the laser ranging sensor and the position of the laser point cloud, and the distance between the laser ranging sensor and the position of the laser point cloud.

[0146] Step A3, based on the angle and distance corresponding to each laser point cloud, determine whether the laser point cloud meets the position condition; the position condition includes the existence of adjacent laser point clouds, and the distances corresponding to each adjacent laser point cloud are within a preset distance range; based on the intensity information corresponding to each laser point cloud, determine whether the laser point cloud meets the intensity condition; the intensity condition includes that the intensity information of each laser point cloud has a gradient change and the intensity information of the laser point cloud is higher than a preset intensity threshold.

[0147] Step A4: If the laser point cloud satisfies both the position condition and the intensity condition, the laser point cloud is determined as the target point cloud.

[0148] Step A5: clustering the target point cloud to obtain light-transmitting material point clusters.

[0149] Step A6: for each light-transmitting material point cluster, a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster is fitted.

[0150] Step A7, in the world coordinate system to which the target point cloud belongs, determine the maximum x-coordinate and the minimum x-coordinate in the x-axis direction from each target point cloud in the transparent material point cluster, and determine the maximum y-coordinate and the minimum y-coordinate in the y-axis direction from each target point cloud in the transparent material point cluster; determine the maximum coordinate point based on the maximum x-coordinate and the maximum y-coordinate; determine the minimum coordinate point based on the minimum x-coordinate and the minimum y-coordinate.

[0151] Step A8, determine the first perpendicular foot between the coordinate maximum point and the candidate light-transmitting material straight line, and use the first perpendicular foot as the first endpoint of the candidate light-transmitting material straight line; determine the second perpendicular foot between the coordinate minimum point and the candidate light-transmitting material straight line, and use the second perpendicular foot as the second endpoint of the candidate light-transmitting material straight line.

[0152] Step A9, based on the first endpoint and the second endpoint, determine the candidate transparent material line segment corresponding to the transparent material point cluster; if the candidate transparent material line segments all satisfy the first constraint and the second constraint, execute step A10, if the candidate transparent material line segment does not satisfy the first constraint or the second constraint, execute step A11; the first constraint includes that the length of the candidate transparent material line segment is greater than a preset length threshold, and the second constraint includes that the number of first target point clouds in the transparent material point cluster is greater than a preset number threshold, and the distance between the first target point cloud and the candidate transparent material straight line is less than a preset distance threshold.

[0153] Step A10, taking the candidate light-transmitting material line segment as the target light-transmitting material line segment corresponding to the light-transmitting material point cluster; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster;

[0154] Step A11, determine the second target point cloud related to the candidate transparent material line segment from the transparent material point cluster; remove the second target point cloud in the transparent material point cluster to obtain a new transparent material point cluster, and return to execute step A6 based on the new transparent material point cluster.

[0155] Step A12, match each target light-transmitting material line segment, and merge at least two target light-transmitting material line segments that match each other to obtain a new target light-transmitting material line segment; update each target light-transmitting material line segment with the new target light-transmitting material line segment, and map each updated target light-transmitting material line segment to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0156] In this embodiment, a laser point cloud is obtained by a laser ranging sensor, and for each laser point cloud, position information and intensity information of the laser point cloud are obtained, the position information includes the angle between the laser ranging sensor and the position of the laser point cloud, and the distance between the laser ranging sensor and the position of the laser point cloud. Then, based on the angle and distance corresponding to each laser point cloud, it can be determined whether the laser point cloud meets the position condition, and based on the intensity information corresponding to each laser point cloud, it can be determined whether the laser point cloud meets the intensity condition. If the laser point cloud meets both the position condition and the intensity condition, the laser point cloud can be accurately determined as the target point cloud.

[0157] The target point cloud is clustered to obtain a transparent material point cluster. For each transparent material point cluster, a candidate transparent material straight line corresponding to the transparent material point cluster is fitted. In the world coordinate system to which the target point cloud belongs, the coordinate maximum point and the coordinate minimum point can be accurately determined from each target point cloud of the transparent material point cluster, and then the perpendiculars between the coordinate maximum point and the coordinate minimum point to the candidate transparent material straight line are determined respectively to determine the first endpoint and the second endpoint in the candidate transparent material straight line. Then, based on the first endpoint and the second endpoint, the candidate transparent material line segment corresponding to the transparent material point cluster can be accurately determined.

[0158] Furthermore, if the candidate transparent material line segments satisfy both the first constraint and the second constraint, the candidate transparent material line segments are used as the target transparent material line segments corresponding to the transparent material point cluster; if the candidate transparent material line segments do not satisfy the first constraint or the second constraint, the second target point cloud related to the candidate transparent material line segment is determined from the transparent material point cluster, the second target point cloud in the transparent material point cluster is removed to obtain a new transparent material point cluster, and based on the new transparent material point cluster, the candidate transparent material straight line corresponding to the transparent material point cluster is re-fitted, so that the target transparent material line segment can be accurately fitted.

[0159] Each target light-transmitting material line segment is matched, and at least two target light-transmitting material line segments that match each other are merged to obtain an accurate new target light-transmitting material line segment after the merger. The new target light-transmitting material line segment after the merger is used to update each target light-transmitting material line segment, and each updated target light-transmitting material line segment is mapped to the environment where the laser ranging sensor is located, so that the target light-transmitting material object can be accurately determined.

[0160] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0161] Based on the same inventive concept, the embodiment of the present application also provides a light-transmitting material detection device for implementing the light-transmitting material detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more light-transmitting material detection devices provided below can refer to the limitations of the light-transmitting material detection method above, and will not be repeated here.

[0162] In an exemplary embodiment, Fig. 9 As shown, a light-transmitting material detection device is provided, comprising: a laser point cloud acquisition module 902, a target point cloud acquisition module 904, a clustering processing module 906, a line segment fitting module 908 and a target light-transmitting material object determination module 910, wherein:

[0163] The laser point cloud acquisition module 902 is used to acquire the laser point cloud through a laser ranging sensor.

[0164] The target point cloud acquisition module 904 is used to determine the target point cloud from the laser point cloud.

[0165] The clustering processing module 906 is used to perform clustering processing on the target point cloud to obtain light-transmitting material point clusters.

[0166] The line segment fitting module 908 is used to fit a target light-transmitting material line segment corresponding to each light-transmitting material point cluster; the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster.

[0167] The target light-transmitting material object determining module 910 is used to determine the target light-transmitting material object in the environment where the laser ranging sensor is located based on each target light-transmitting material line segment.

[0168] The above-mentioned translucent material detection device obtains a laser point cloud through a laser ranging sensor, and determines a target point cloud from the laser point cloud; clusters the target point cloud to obtain a translucent material point cluster; for each translucent material point cluster, fits a target translucent material line segment corresponding to the translucent material point cluster, and the target translucent material line segment represents the translucent material object corresponding to the translucent material point cluster. Then, based on each target translucent material line segment, the target translucent material object in the environment where the laser ranging sensor is located can be accurately determined.

[0169] In one embodiment, the above-mentioned line segment fitting module 908 is also used to fit a candidate transparent material straight line corresponding to the transparent material point cluster for each transparent material point cluster; determine a candidate transparent material line segment from the candidate transparent material straight line; if the candidate transparent material line segment satisfies both the first constraint condition and the second constraint condition, then the candidate transparent material line segment is used as the target transparent material line segment corresponding to the transparent material point cluster; the first constraint condition includes that the length of the candidate transparent material line segment is greater than a preset length threshold, and the second constraint condition includes that the number of the first target point cloud in the transparent material point cluster is greater than a preset number threshold, and the distance between the first target point cloud and the candidate transparent material straight line is less than a preset distance threshold.

[0170] In one embodiment, the above-mentioned line segment fitting module 908 is also used to determine the coordinate maximum point and the coordinate minimum point based on each target point cloud in the transparent material point cluster; determine the first endpoint in the candidate transparent material straight line according to the coordinate maximum point and the candidate transparent material straight line, and determine the second endpoint in the candidate transparent material straight line according to the coordinate minimum point and the candidate transparent material straight line; based on the first endpoint and the second endpoint, determine the candidate transparent material line segment corresponding to the transparent material point cluster.

[0171] In one embodiment, the above-mentioned line segment fitting module 908 is also used to determine the maximum x-coordinate value and the minimum x-coordinate value in the x-axis direction from each target point cloud in the transparent material point cluster in the world coordinate system to which the target point cloud belongs, and to determine the maximum y-coordinate value and the minimum y-coordinate value in the y-axis direction from each target point cloud in the transparent material point cluster; determine the maximum coordinate point based on the maximum x-coordinate value and the maximum y-coordinate value; determine the minimum coordinate point based on the minimum x-coordinate value and the minimum y-coordinate value.

[0172] In one embodiment, the above-mentioned line segment fitting module 908 is also used to determine the first perpendicular foot between the coordinate maximum value point and the candidate light-transmitting material straight line, and use the first perpendicular foot as the first endpoint in the candidate light-transmitting material straight line; determine the second perpendicular foot between the coordinate minimum value point and the candidate light-transmitting material straight line, and use the second perpendicular foot as the second endpoint in the candidate light-transmitting material straight line.

[0173] In one embodiment, the above-mentioned line segment fitting module 908 is also used to determine the second target point cloud related to the candidate transparent material line segment from the transparent material point cluster if the candidate transparent material line segment does not meet the first constraint condition or the second constraint condition; remove the second target point cloud in the transparent material point cluster to obtain a new transparent material point cluster, and fit the candidate transparent material straight line corresponding to the transparent material point cluster based on the new transparent material point cluster.

[0174] In one embodiment, the target point cloud acquisition module 904 is further used to acquire the position information and intensity information of each laser point cloud; and determine the target point cloud based on the position information and intensity information of each laser point cloud.

[0175] In one embodiment, the position information includes the angle between the laser ranging sensor and the position of the laser point cloud, and the distance between the laser ranging sensor and the position of the laser point cloud; the target point cloud acquisition module 904 is also used to determine whether the laser point cloud meets the position condition based on the angle and distance corresponding to each laser point cloud; the position condition includes the existence of adjacent laser point clouds, and the distances corresponding to each adjacent laser point cloud are all within a preset distance range; based on the intensity information corresponding to each laser point cloud, determine whether the laser point cloud meets the intensity condition; the intensity condition includes that the intensity information of each laser point cloud has a gradient change and the intensity information of the laser point cloud is higher than a preset intensity threshold; if the laser point cloud meets both the position condition and the intensity condition, the laser point cloud is determined as the target point cloud.

[0176] In one embodiment, the target light-transmitting material object determination module 910 is also used to match each target light-transmitting material line segment, and merge at least two target light-transmitting material line segments that match each other to obtain a new target light-transmitting material line segment; update each target light-transmitting material line segment with the new target light-transmitting material line segment, and map each updated target light-transmitting material line segment to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

[0177] Each module in the above-mentioned light-transmitting material detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0178] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for detecting a light-transmitting material is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0179] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0180] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0181] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0182] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0183] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0184] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0185] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0186] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting light-transmitting materials, characterized in that: The method comprises: Acquire laser point cloud through laser ranging sensor; Determining a target point cloud from the laser point cloud; Performing clustering processing on the target point cloud to obtain light-transmitting material point clusters; For each of the light-transmitting material point clusters, fitting a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster; Determine a candidate light-transmitting material line segment from the candidate light-transmitting material straight lines; If the candidate light-transmitting material line segment satisfies both the first constraint and the second constraint, the candidate light-transmitting material line segment is used as the target light-transmitting material line segment corresponding to the light-transmitting material point cluster; the first constraint includes that the length of the candidate light-transmitting material line segment is greater than a preset length threshold, the second constraint includes that the number of first target point clouds in the light-transmitting material point cluster is greater than a preset number threshold, the distance between the first target point cloud and the candidate light-transmitting material straight line is less than a preset distance threshold, and the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster; Based on each of the target light-transmitting material line segments, a target light-transmitting material object in the environment where the laser ranging sensor is located is determined.

2. The method according to claim 1, characterized in that The determining of a candidate light-transmitting material line segment from the candidate light-transmitting material straight lines comprises: Based on each target point cloud in the light-transmitting material point cluster, determining a coordinate maximum value point and a coordinate minimum value point; Determine a first endpoint of the candidate light-transmitting material straight line according to the coordinate maximum value point and the candidate light-transmitting material straight line, and determine a second endpoint of the candidate light-transmitting material straight line according to the coordinate minimum value point and the candidate light-transmitting material straight line; Based on the first endpoint and the second endpoint, a candidate light-transmitting material line segment corresponding to the light-transmitting material point cluster is determined.

3. The method according to claim 2, characterized in that The step of determining the maximum coordinate point and the minimum coordinate point based on each target point cloud in the light-transmitting material point cluster includes: In the world coordinate system to which the target point cloud belongs, determining the maximum x-coordinate value and the minimum x-coordinate value in the x-axis direction from each target point cloud of the light-transmitting material point cluster, and determining the maximum y-coordinate value and the minimum y-coordinate value in the y-axis direction from each target point cloud in the light-transmitting material point cluster; Determine a coordinate maximum point based on the x-coordinate maximum value and the y-coordinate maximum value; Based on the minimum x-coordinate value and the minimum y-coordinate value, a coordinate minimum point is determined.

4. The method according to claim 2, characterized in that: The step of determining a first endpoint of the candidate light-transmitting material straight line according to the coordinate maximum value point and the candidate light-transmitting material straight line, and determining a second endpoint of the candidate light-transmitting material straight line according to the coordinate minimum value point and the candidate light-transmitting material straight line, comprises: Determine the foot of a first perpendicular between the coordinate maximum point and the candidate light-transmitting material straight line, and use the first foot of the perpendicular as the first endpoint of the candidate light-transmitting material straight line; Determine the second foot of a perpendicular between the coordinate minimum point and the candidate light-transmitting material straight line, and use the second foot of a perpendicular as the second endpoint of the candidate light-transmitting material straight line.

5. The method according to claim 1, characterized in that: The method further comprises: If the candidate light-transmitting material line segment does not satisfy the first constraint condition or the second constraint condition, determining a second target point cloud related to the candidate light-transmitting material line segment from the light-transmitting material point cluster; The second target point cloud in the light-transmitting material point cluster is removed to obtain a new light-transmitting material point cluster, and based on the new light-transmitting material point cluster, the step of fitting a candidate light-transmitting material straight line corresponding to the light-transmitting material point cluster is returned to be executed.

6. The method according to claim 1, characterized in that Determining a target point cloud from the laser point cloud comprises: For each of the laser point clouds, obtaining position information and intensity information of the laser point cloud; Based on the position information and intensity information of each of the laser point clouds, a target point cloud is determined.

7. The method according to claim 6, characterized in that The position information includes an angle between the laser ranging sensor and the position of the laser point cloud, and a distance between the laser ranging sensor and the position of the laser point cloud; and determining the target point cloud based on the position information and intensity information of each of the laser point clouds includes: Based on the angles and distances corresponding to each of the laser point clouds, determining whether the laser point cloud meets a position condition; the position condition includes the existence of adjacent laser point clouds, and the distances corresponding to each of the adjacent laser point clouds are within a preset distance range; Based on the intensity information corresponding to each of the laser point clouds, determining whether the laser point cloud meets an intensity condition; the intensity condition includes that the intensity information of each of the laser point clouds has a gradient change and the intensity information of the laser point cloud is higher than a preset intensity threshold; If the laser point cloud satisfies both the position condition and the intensity condition, the laser point cloud is determined as a target point cloud.

8. The method according to claim 1, characterized in that The step of determining the target light-transmitting material object in the environment where the laser ranging sensor is located based on each of the target light-transmitting material line segments includes: Matching each of the target light-transmitting material line segments, and merging at least two target light-transmitting material line segments that match each other to obtain a new target light-transmitting material line segment; The new target light-transmitting material line segment is used to update each of the target light-transmitting material line segments, and each updated target light-transmitting material line segment is mapped to the environment where the laser ranging sensor is located to determine the target light-transmitting material object.

9. A light-transmitting material detection device, characterized in that: include: A laser point cloud acquisition module is used to acquire laser point clouds through a laser ranging sensor; A target point cloud acquisition module is used to determine the target point cloud from the laser point cloud; A clustering processing module, used for performing clustering processing on the target point cloud to obtain a light-transmitting material point cluster; A line segment fitting module is used to fit a candidate light-transmitting material straight line corresponding to each light-transmitting material point cluster; determine a candidate light-transmitting material line segment from the candidate light-transmitting material straight lines; if the candidate light-transmitting material line segments satisfy both a first constraint and a second constraint, use the candidate light-transmitting material line segment as a target light-transmitting material line segment corresponding to the light-transmitting material point cluster; the first constraint condition includes that the length of the candidate light-transmitting material line segment is greater than a preset length threshold, the second constraint condition includes that the number of first target point clouds in the light-transmitting material point cluster is greater than a preset number threshold, the distance between the first target point cloud and the candidate light-transmitting material straight line is less than a preset distance threshold, and the target light-transmitting material line segment represents the light-transmitting material object corresponding to the light-transmitting material point cluster; The target light-transmitting material object determining module is used to determine the target light-transmitting material object in the environment where the laser ranging sensor is located based on each of the target light-transmitting material line segments.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images