A road surface marking point cloud recognition method, device, medium and electronic equipment

Abstract

The present disclosure provides a road surface mark point cloud recognition method, device, medium and electronic equipment. The method comprises: acquiring a reflection intensity value of a global point cloud on a road surface; cutting the global point cloud to obtain a plurality of sheet-shaped point data; determining a reflection intensity value range of a road surface mark on the road surface based on the reflection intensity value of each point data in the global point cloud; identifying the reflection intensity value of each point data in each sheet-shaped point cloud based on the reflection intensity value range, determining each reflection intensity value related to the road surface mark in each sheet-shaped point cloud, and the point data corresponding to each reflection intensity value respectively. The present disclosure does not use other physical characteristics of the collection device, nor does it need to establish a complex mathematical model for the road surface mark. It reduces the excessive dependence on the collection device, avoids complex data processing, makes the application more convenient, and processes data faster. The method has higher robustness.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of surveying and mapping, in particular to a road surface marking point cloud identification method, device, medium and electronic equipment. BACKGROUND

[0002] There are various styles of road surface markings on highways, such as white solid lines, white dashed lines, straight arrows, turning arrows, bus lanes, and speed limit numbers, etc. These road surface markings are essential information in high-precision digital maps. For tens of thousands of kilometers of highways nationwide, it is an extremely difficult, heavy and delicate task to manually add three-dimensional vector information of these road surface markings.

[0003] Currently, the main way to add road surface markings to digital maps is to collect road surface point clouds through vehicle-mounted laser radars, and automatically extract and add road surface markings through reflection intensity, laser incidence angle, coordinate information, etc. in the point cloud. However, this method has slow processing speed and great scene limitations, and can only extract flat and clear road markings.

[0004] Therefore, the present disclosure provides a road surface marking point cloud identification method to solve one of the above technical problems. SUMMARY

[0005] The purpose of the present disclosure is to provide a road surface marking point cloud identification method, device, medium and electronic equipment, which can solve at least one of the above technical problems. The specific scheme is as follows:

[0006] According to the specific embodiment of the present disclosure, in a first aspect, the present disclosure provides a road surface marking point cloud identification method, comprising:

[0007] Obtaining a reflection intensity value of a global point cloud on a road surface, wherein the global point cloud comprises a plurality of point data, and each point data comprises at least a reflection intensity value;

[0008] Cutting the global point cloud to obtain a plurality of sheet-shaped point clouds;

[0009] Determining a reflection intensity value range of road surface markings on the road surface based on the reflection intensity values of the point data in the global point cloud;

[0010] Identifying the reflection intensity values of the point data in each sheet-shaped point cloud based on the reflection intensity value range, determining the reflection intensity values related to the road surface markings in each sheet-shaped point cloud, and the point data corresponding to each reflection intensity value, respectively.

[0011] According to the specific embodiment of the present disclosure, in a second aspect, the present disclosure provides a road surface marking point cloud identification device, comprising:

[0012] an acquisition unit, configured to acquire a reflection intensity value of a global point cloud on a road surface, wherein the global point cloud includes a plurality of point data, and each point data includes at least a reflection intensity value;

[0013] A cutting unit, configured to cut the global point cloud to obtain a plurality of sheet point clouds;

[0014] a first determining unit, configured to determine a reflection intensity value range of a road surface marking on the road surface based on the reflection intensity value of each point data in the global point cloud;

[0015] The second determination unit is used to identify the reflection intensity value of each point data in each sheet point cloud based on the reflection intensity value range, determine each reflection intensity value related to the road surface marking in each sheet point cloud, and point data corresponding to each reflection intensity value.

[0016] According to a specific embodiment of the present disclosure, in a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for recognizing a road surface marking point cloud as described in any one of the above items.

[0017] According to the specific implementation of the present disclosure, in a fourth aspect, the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method for recognizing road marking point clouds as described in any one of the above items.

[0018] Compared with the prior art, the above solution of the embodiment of the present disclosure has at least the following beneficial effects:

[0019] This disclosure provides a method, device, medium, and electronic device for identifying road marking point clouds. This method directly utilizes the reflection intensity value of each point in a global point cloud for road marking identification, without utilizing other physical properties of the acquisition equipment or establishing complex mathematical models for the road markings. This reduces over-reliance on acquisition equipment and avoids complex data processing, making the application more convenient and data processing faster, resulting in a more robust method. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a method for recognizing a road surface marking point cloud according to an embodiment of the present disclosure is shown;

[0021] Figure 2 shows a histogram of a global point cloud according to an embodiment of the present disclosure;

[0022] Figure 3 shows a histogram of a sheet of point cloud according to an embodiment of the present disclosure;

[0023] Figure 4 A unit block diagram of a device for recognizing a road surface marking point cloud according to an embodiment of the present disclosure is shown;

[0024] Figure 5 A schematic diagram of a connection structure of an electronic device provided according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the present disclosure more clear, the present disclosure will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only a portion of the embodiments of the present disclosure, rather than all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present disclosure without creative effort are intended to fall within the scope of protection of the present disclosure.

[0026] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure. The singular forms "a," "an," "the," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0027] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0028] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present disclosure, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, the first can also be referred to as the second, and similarly, the second can also be referred to as the first without departing from the scope of the embodiments of the present disclosure.

[0029] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0030] It is also important to note that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0031] In particular, it is to be noted that signs and / or numbers present in the description, if not marked in the description of the figures, are not figure references.

[0032] Optional embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0033] Embodiment 1

[0034] The embodiments provided by the present disclosure are embodiments of a road surface marking point cloud recognition method.

[0035] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Figure 1 The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0036] Step S101, obtaining a reflection intensity value of a global point cloud on a road surface.

[0037] Point cloud (English full name point cloud data) refers to a collection of massive point information representing the characteristics of the target surface in a three-dimensional coordinate system, and each point information includes a set of vectors. The point cloud in the embodiments of the present disclosure is mainly used to detect road markings on the road surface. The global point cloud refers to a collection of point data of the surrounding environment detected on the road surface. The global point cloud includes a plurality of point data, and each point data refers to point information detected at a certain time point. Each point data at least includes a reflection intensity value, and also includes a distance value, an azimuth value and a height value. The present disclosure only uses the reflection intensity value of the point data to determine the road markings on the road surface.

[0038] The reflection intensity value refers to the intensity value of light intensity or electromagnetic wave reflection. In the embodiments of the present disclosure, the road surface can be the front road surface, the rear road surface, the left road surface and / or the right road surface, which is not limited by the embodiments of the present disclosure. The reflection intensity value is automatically obtained by a device, which can be a handheld device or a vehicle-mounted device, which is not limited by the embodiments of the present disclosure.

[0039] In some specific embodiments, the step of obtaining the reflection intensity value of the global point cloud on the road surface includes the following steps:

[0040] Step S101a, obtaining the reflection intensity value of the global point cloud on the road surface by the radar mounted on the vehicle.

[0041] Radar (radio detection and ranging), short for "radio detection and ranging," uses radio to detect targets and determine their spatial positions. For this reason, radar is also called "radio positioning." Radar is an electronic device that uses electromagnetic waves to detect targets. Radar emits electromagnetic waves to illuminate a target and receives the echoes, thereby obtaining information such as the distance from the target to the point of emission, the rate of change of distance (radial velocity), azimuth, and altitude. For example, a lidar shines a laser onto the surface of a target object. The laser reflected by the target carries information such as azimuth and distance. If a vehicle-mounted lidar scans the road point by point along a predetermined trajectory, it records a global point cloud as it scans. During scanning, the smaller the distance between two adjacent scanning points, the larger the number of global point clouds obtained. Vehicle-mounted radar can quickly acquire large amounts of point data, with high speed and efficiency.

[0042] The vehicle-mounted radar can not only obtain the reflection intensity value of each point data, but also the distance value, azimuth value and altitude value of each point data.

[0043] In some other specific embodiments, obtaining the reflection intensity value of the global point cloud on the road surface includes the following steps:

[0044] Step S101b-1: Acquire a global image of the road surface through a vehicle-mounted camera.

[0045] Specifically, the detection vehicle is equipped with one or more cameras, at least one of which is used to capture video of the road surface while the vehicle is traveling. The global image refers to the video image captured within the road surface video. To obtain the distance value of a target on the road surface, at least two cameras are positioned in the direction of capture, forming a binocular camera. Using the video images captured simultaneously by the binocular cameras, triangulation calculations are performed on the target, thereby obtaining the distance value of the target's point data. The process of obtaining distance values ​​using the binocular cameras is not described in detail in this embodiment; however, reference can be made to various implementation methods in the prior art for implementation.

[0046] Step S101b-2: performing reflection intensity analysis on the pixel value of each pixel in the global image to obtain the reflection intensity value of each pixel.

[0047] The reflection intensity value of each pixel represents the reflection intensity value of each point data in the global point cloud.

[0048] The pixel value of the pixel is also the RGB value of the pixel. In this specific embodiment, a corresponding relationship model is established for the pixel value and the reflection intensity value of the image pixel. Through this corresponding relationship model, the reflection intensity value of the pixel can be obtained by knowing the pixel value of the pixel.

[0049] The global image is obtained through an ordinary camera, and then the reflection intensity value of the global point cloud is obtained through the global image, which greatly reduces the use cost.

[0050] The on-board binocular camera can not only obtain the reflection intensity value of each point data, but also the distance value, azimuth value and altitude value of each point data.

[0051] Step S102 : cutting the global point cloud to obtain a plurality of sheet point clouds.

[0052] The disclosed embodiment cuts the global point cloud into multiple sheet point clouds and performs recognition on the sheet point clouds, which reduces the amount of information, reduces interference information, and effectively improves the recognition accuracy. The slice specifications of each sheet point cloud can be different.

[0053] In some specific embodiments, the step of cutting the global point cloud to obtain a plurality of sheet point clouds includes the following steps:

[0054] Step S102a: cutting the global point cloud based on a preset segmentation specification to obtain a plurality of sheet point clouds.

[0055] For example, the preset slicing specification is 50 meters × 50 meters; if the final slicing is less than 50 meters × 50 meters, it is cut according to the specifications of one side. For example, if there is only 120 meters × 20 meters of uncut point cloud left, and the long side can be cut according to the specifications of 50 meters, it is cut according to the slicing specifications of 50 meters × 20 meters, and the specifications of the last piece of point cloud are 20 meters × 20 meters.

[0056] Step S103 : determining a reflection intensity value range of the road surface marking on the road surface based on the reflection intensity value of each point data in the global point cloud.

[0057] The reflection intensity value range is used to identify reflection intensity values ​​related to road markings in the sheet point cloud.

[0058] In some specific embodiments, determining the reflection intensity value range of the road surface marking on the road surface based on the reflection intensity value of each point data in the global point cloud includes the following steps:

[0059] Step S103 - 1 : performing classification statistics on the reflection intensity value of each point data in the global point cloud based on a plurality of preset intensity value classification regions, and obtaining a first statistical value of each preset intensity value classification region.

[0060] The preset intensity value classification area is a type of area divided by the reflection intensity value based on experience. The preset intensity value classification area is represented by the range of reflection intensity values. For example, 5 consecutive preset intensity value classification areas are preset as follows: A1, A2, A3, A4 and A5. The number of reflection intensity values ​​of the global point cloud in each preset intensity value classification area is the first statistical value, such as Figure 2 As shown, the first statistical value is represented in the form of a histogram, wherein the first statistical value of the preset intensity value classification area A1 is n1; the first statistical value of the preset intensity value classification area A2 is n2; the first statistical value of the preset intensity value classification area A3 is n3; the first statistical value of the preset intensity value classification area A4 is n4; and the first statistical value of the preset intensity value classification area A5 is n5.

[0061] The multiple preset intensity value classification areas can be continuous or discontinuous, and the present disclosure does not impose any limitation thereto. The widths of the preset intensity value classification areas can be the same or different, and the present disclosure does not impose any limitation thereto. For example, the width of the preset intensity value classification area A4 can be 200, while the width of the preset intensity value classification area A5 can be 150; or, the width of the preset intensity value classification area A4 can be 200, and the width of the preset intensity value classification area A5 can also be 200.

[0062] Step S103 - 2 : determining the reflection intensity value range of the road sign based on the first statistical value of each preset intensity value classification area.

[0063] Specifically, the method includes the following steps:

[0064] Step S103-2-1: determining the largest first statistical value and the second largest first statistical value based on the first statistical values ​​of each preset intensity value classification area.

[0065] For example, Figure 2 As shown, the largest first statistical value is n4=90, and the second largest first statistical value is n5=45.

[0066] Step S103-2-2: determining a first median based on the preset intensity value classification area corresponding to the largest first statistical value, and determining a second median based on the preset intensity value classification area corresponding to the second largest first statistical value.

[0067] In the embodiment of the present disclosure, the median value refers to the average value of the maximum reflection intensity value and the minimum reflection intensity value in the preset intensity value classification area.

[0068] For example, continuing with the above example, the largest first statistical value n4 corresponds to the preset intensity value classification area A4 (2000, 2200], and the first median of the preset intensity value classification area A4 is 2100; the second largest first statistical value n5 corresponds to the preset intensity value classification area A5 (2200, 2400], and the first median of the preset intensity value classification area A5 is 2300.

[0069] Step S103-2-3: determine the reflection intensity value range of the road surface marking based on the first median and the second median.

[0070] When driving on an asphalt road, the point cloud formed by the asphalt has the largest number of reflection intensity values ​​in the histogram statistics, that is, the largest first statistical value. Therefore, the first median value of the preset intensity value classification area corresponding to this first statistical value, and all points below this first median value, belong to the asphalt road surface. Meanwhile, the point cloud formed by road markings has the second largest number of reflection intensity values ​​in the histogram statistics, that is, the second largest first statistical value. Therefore, the first median value of the preset intensity value classification area corresponding to this first statistical value, and all points above this first median value, belong to road markings. Based on this, a reflection intensity value range for road markings is generated. For example, continuing with the above example, if the first median value of preset intensity value classification area A4 is 2100 and the first median value of preset intensity value classification area A5 is 2300, then the reflection intensity value range for road markings is [2100, 2300].

[0071] Step S104 : identifying the reflection intensity value of each point data in each sheet point cloud based on the reflection intensity value range, and determining each reflection intensity value related to the road surface marking in each sheet point cloud, and point data corresponding to each reflection intensity value.

[0072] In any point cloud, if the reflection intensity value of a point data point is determined to be associated with a road marking, then the point data can also be determined to be associated with the road marking. Based on this, the corresponding road marking can be generated in digital form in the 3D coordinate system of the high-precision digital map using other information (such as distance, direction, and altitude) contained in all the point data points associated with the road marking.

[0073] In some specific embodiments, identifying the reflection intensity value of each point data in each sheet point cloud based on the reflection intensity value range, determining each reflection intensity value associated with the road surface marking in each sheet point cloud, and the point data corresponding to each reflection intensity value, includes the following steps:

[0074] Step S104 - 1 : performing classification statistics on the reflection intensity values ​​of each point data in each sheet point cloud based on the multiple preset intensity value classification areas, and obtaining a second statistical value of each sheet point cloud in each preset intensity value classification area.

[0075] For each sheet point cloud, it uses the same preset intensity value classification area as the global point cloud. The statistical method is the same as the global point cloud, which will not be repeated here. Please refer to the statistical method of the global point cloud. For example, the same as the global point cloud, 5 consecutive preset intensity value classification areas are pre-set: A1, A2, A3, A4 and A5. The number of reflection intensity values ​​of the global point cloud in each preset intensity value classification area is the second statistical value, such as Figure 3 As shown, the second statistical value is represented in the form of a histogram, wherein the second statistical value of the preset intensity value classification area A1 is m1; the second statistical value of the preset intensity value classification area A2 is m2; the second statistical value of the preset intensity value classification area A3 is m3; the second statistical value of the preset intensity value classification area A4 is m4; and the second statistical value of the preset intensity value classification area A5 is m5.

[0076] Step S104 - 2 , excluding the largest second statistical value in each sheet point cloud, and obtaining the remaining second statistical values ​​in each sheet point cloud.

[0077] In each sheet point cloud, the reflection intensity values ​​within the preset intensity value classification area corresponding to the largest second statistical value all represent the reflection intensity values ​​of asphalt on the road surface. Therefore, this specific embodiment excludes the reflection intensity values ​​belonging to asphalt from the recognition. Instead, the recognition process starts from the remaining second statistical values ​​in each sheet point cloud. For example, Figure 3 As shown, the second statistical value m4 of the preset intensity value classification area A4 of the sheet point cloud is the largest second statistical value in the sheet point cloud. Therefore, the reflection intensity value in the preset intensity value classification area A4 is excluded from the recognition range, and the reflection intensity values ​​in the preset intensity value classification areas A1, A2, A3 and A5 are recognized.

[0078] Step S104 - 3 : obtaining a third median value corresponding to the preset intensity value classification area based on the preset intensity value classification areas corresponding to the remaining second statistical values.

[0079] For example, in the preset intensity value classification area A1 (1400, 1600], the third median of the preset intensity value classification area A1 is 1500; in the preset intensity value classification area A2 (1600, 1800], the third median of the preset intensity value classification area A2 is 1700; in the preset intensity value classification area A3 (1800, 2000], the third median of the preset intensity value classification area A3 is 1900; in the preset intensity value classification area A5 (2200, 2400], the third median of the preset intensity value classification area A5 is 2300.

[0080] Step S104 - 4 : performing similarity matching on the reflection intensity value range and each third median value in each sheet point cloud to obtain a corresponding similarity matching result.

[0081] The similarity matching result includes a matching difference and / or a matching degree.

[0082] The matching difference refers to a first distance between the third median and the reflection intensity value range. The first distance refers to an absolute value of a difference between the third median and the nearest value in the reflection intensity value range. For example, continuing the above example, the reflection intensity value range obtained by the global point cloud is [2100, 2300]; since the third median value 1500 of the preset intensity value classification area A1 is less than the minimum value 2100 in the reflection intensity value range, the first distance value is |1500-2100|=600; since the third median value 1700 of the preset intensity value classification area A2 is less than the minimum value 2100 in the reflection intensity value range, the first distance value is |1700-2100|=400; since the third median value 1900 of the preset intensity value classification area A3 is less than the minimum value 2100 in the reflection intensity value range, the first distance value is |1900-2100|=200; since the third median value 2300 of the preset intensity value classification area A5 is equal to the maximum value 2300 in the reflection intensity value range, the first distance value is |2300-2300|=0.

[0083] The matching degree is the ratio of the second distance value between the first distance value and the fourth median value of the reflection intensity value range, and the second distance value to the fourth median value. The second distance value refers to the absolute value of the difference between the first distance value and the fourth median value. For example, continuing with the above example, the fourth median value of the reflection intensity value range [2100, 2300] is 2200; the matching degree of the third median value 1500 of the preset intensity value classification area A1 is |600-2200| / 2200=72.73%; the matching degree of the third median value 1700 of the preset intensity value classification area A2 is |400-2200| / 2200=81.82%; the matching degree of the third median value 1900 of the preset intensity value classification area A3 is |200-2200| / 2200=90.91%; and the matching degree of the third median value 2300 of the preset intensity value classification area A5 is |0-2200| / 2200=100%.

[0084] Step S104 - 5 : determining the fourth median of the corresponding sheet point cloud from the third medians of each sheet point cloud.

[0085] Wherein, the similarity matching result of the fourth median meets a preset similarity condition.

[0086] For example, continuing with the above example, for similarity matching results that are matching differences, the preset similarity condition is the minimum value. For example, the matching difference of the preset intensity value classification area A5 is 0, which is the minimum value. Therefore, the median 2300 of the preset intensity value classification area A5 is determined to be the fourth median. For similarity matching results that are matching degrees, the preset similarity condition is the maximum value. For example, the matching degree of the preset intensity value classification area A5 is 100%, which is the maximum value. Therefore, the median 2300 of the preset intensity value classification area A5 is determined to be the fourth median. The third medians of other preset intensity value classification areas are considered to be abnormal values.

[0087] Step S104-6: In each sheet point cloud, determine whether each reflection intensity value within the preset intensity value classification area corresponding to the fourth median value is related to the road surface marking, and determine point data corresponding to each reflection intensity value.

[0088] Having determined the reflection intensity value associated with the road marking, it is determined that the point data recording this reflection intensity value is also associated with the road marking. For example, continuing with the above example, the fourth median value 2300 corresponds to the preset intensity value classification region A5 (2200, 2400). Each reflection intensity value within this preset intensity value classification region A5 in the sheet point cloud is associated with the road marking, and therefore the point data associated with each reflection intensity value is also associated with the road marking.

[0089] Since point data includes not only reflection intensity values ​​but also distance, azimuth, and altitude values, once the point data related to road markings is determined, the corresponding road markings can be generated in digital form in the three-dimensional coordinate system of the high-precision digital map.

[0090] This disclosed embodiment directly uses the reflection intensity value of each point in the global point cloud to identify road markings, without relying on other physical properties of the acquisition equipment or building complex mathematical models for the road markings. This reduces over-reliance on acquisition equipment and avoids complex data processing, making the application more convenient and data processing faster, resulting in a more robust method.

[0091] Example 2

[0092] The present disclosure also provides an apparatus embodiment that is consistent with the above embodiment, and is used to implement the method steps described in the above embodiment. The interpretation based on the same name meaning is the same as that of the above embodiment, and has the same technical effect as the above embodiment, and will not be repeated here.

[0093] like Figure 4 As shown, the present disclosure provides a road surface marking point cloud recognition device 400, comprising:

[0094] The acquisition unit 401 is configured to acquire a reflection intensity value of a global point cloud on a road surface, wherein the global point cloud comprises a plurality of point data, and each point data comprises at least a reflection intensity value;

[0095] The cutting unit 402 is configured to cut the global point cloud to obtain a plurality of sheet-shaped point clouds;

[0096] The first determination unit 403 is configured to determine a reflection intensity value range of a road surface mark on the road surface based on the reflection intensity value of each point data in the global point cloud;

[0097] The second determination unit 404 is configured to identify the reflection intensity value of each point data in each sheet-shaped point cloud based on the reflection intensity value range, determine each reflection intensity value related to the road surface mark in each sheet-shaped point cloud, and point data corresponding to each reflection intensity value.

[0098] Optionally, the first determination unit 403 comprises:

[0099] The first statistical subunit is configured to statistically classify the reflection intensity value of each point data in the global point cloud based on a plurality of preset intensity value classification regions to obtain a first statistical value of each preset intensity value classification region;

[0100] The first determination subunit is configured to determine the reflection intensity value range of the road surface mark based on the first statistical value of each preset intensity value classification region.

[0101] Optionally, the first determination subunit comprises:

[0102] The second determination subunit is configured to determine a maximum first statistical value and a second maximum first statistical value based on the first statistical value of each preset intensity value classification region;

[0103] The second determination subunit is configured to determine a first median value based on the preset intensity value classification region corresponding to the maximum first statistical value, and determine a second median value based on the preset intensity value classification region corresponding to the second maximum first statistical value;

[0104] The third determination subunit is configured to determine the reflection intensity value range of the road surface mark based on the first median value and the second median value.

[0105] Optionally, the second determination unit 404 comprises:

[0106] The first acquisition subunit is configured to statistically classify the reflection intensity value of each point data in each sheet-shaped point cloud based on the plurality of preset intensity value classification regions to obtain a second statistical value of each sheet-shaped point cloud in each preset intensity value classification region;

[0107] an exclusion subunit, configured to exclude the largest second statistical value in each sheet point cloud and obtain the remaining second statistical values ​​in each sheet point cloud;

[0108] a second acquiring subunit, configured to acquire a third median value of a corresponding preset intensity value classification region based on the preset intensity value classification regions corresponding to the remaining second statistical values;

[0109] a matching subunit, configured to perform similarity matching on the reflection intensity value range and each third median value in each sheet point cloud, respectively, to obtain a corresponding similarity matching result;

[0110] a fourth determining subunit, configured to determine a fourth median of the corresponding sheet point cloud from the third medians of each sheet point cloud, wherein a similarity matching result of the fourth median satisfies a preset similarity condition;

[0111] The fifth determining subunit is configured to determine, in each sheet point cloud, whether each reflection intensity value within the preset intensity value classification area corresponding to the fourth median value is related to the road surface marking, and determine point data corresponding to each reflection intensity value.

[0112] Optionally, the similarity matching result includes a matching difference and / or a matching degree;

[0113] The matching difference refers to the first distance value between the third median value and the reflection intensity value range;

[0114] The matching degree is a ratio of the second distance value between the first distance value and the fourth median value of the reflection intensity value range, and the second distance value to the fourth median value.

[0115] Optionally, the cutting unit 402 includes:

[0116] The cutting subunit is used to cut the global point cloud based on a preset segmentation specification to obtain multiple sheet point clouds.

[0117] Optionally, the acquiring unit 401 includes:

[0118] The third acquisition subunit is used to obtain the reflection intensity value of the global point cloud on the road surface through the vehicle-mounted radar.

[0119] The disclosed embodiments directly utilize the reflection intensity values ​​of each point in a global point cloud for road sign recognition, without relying on other physical properties of the acquisition device or building complex mathematical models for the road signs. This reduces over-reliance on acquisition devices and avoids complex data processing, making the application more convenient and data processing faster, resulting in a more robust method.

[0120] Example 3

[0121] like Figure 5 As shown, this embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method steps described in the above embodiment.

[0122] Example 4

[0123] An embodiment of the present disclosure provides a non-volatile computer storage medium, wherein the computer storage medium stores computer-executable instructions, and the computer-executable instructions can execute the method steps described in the above embodiment.

[0124] Example 5

[0125] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0126] like Figure 5 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0127] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 505 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0128] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0129] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0130] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0131] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

Claims

1. A method for identifying road marking point clouds, characterized in that: include: Obtaining a reflection intensity value of a global point cloud on a road surface, wherein the global point cloud includes a plurality of point clouds, and each point cloud includes at least a reflection intensity value; Cutting the global point cloud to obtain multiple sheet point clouds; Determining a reflection intensity value range of a road surface marking on the road surface based on the reflection intensity value of each point cloud in the global point cloud; Identifying the reflection intensity values ​​of each point cloud in each sheet point cloud based on the reflection intensity value range, and determining each reflection intensity value associated with the road marking in each sheet point cloud, and the point clouds corresponding to each reflection intensity value; The determining of the reflection intensity value range of the road surface marking on the road surface based on the reflection intensity value of each point cloud in the global point cloud includes: performing classification statistics on the reflection intensity value of each point cloud in the global point cloud based on a plurality of preset intensity value classification regions, and obtaining a first statistical value of each preset intensity value classification region; Determining a reflection intensity value range of the road marking based on first statistical values ​​of each preset intensity value classification area; The step of identifying the reflection intensity values ​​of each point cloud in each sheet point cloud based on the reflection intensity value range, and determining each reflection intensity value associated with the road surface marking in each sheet point cloud, and the point clouds corresponding to each reflection intensity value, includes: performing classified statistics on the reflection intensity values ​​of each point cloud in each sheet point cloud based on the multiple preset intensity value classification areas, and obtaining a second statistical value of each sheet point cloud in each preset intensity value classification area; Excluding the largest second statistical value in each sheet point cloud, and obtaining the remaining second statistical values ​​in each sheet point cloud; Obtaining a third median value of the corresponding preset intensity value classification area based on the preset intensity value classification areas respectively corresponding to the remaining second statistical values; Performing similarity matching based on the reflection intensity value range and each third median value in each sheet point cloud to obtain corresponding similarity matching results; Determining a fourth median of the corresponding sheet point cloud from each third median of each sheet point cloud, wherein a similarity matching result of the fourth median satisfies a preset similarity condition; In each sheet point cloud, determining that each reflection intensity value within the preset intensity value classification area corresponding to the fourth median value is related to the road surface marking, and determining point clouds corresponding to each of the reflection intensity values; The similarity matching result includes a matching difference and / or a matching degree; The matching difference refers to the first distance value between the third median value and the reflection intensity value range; The matching degree is a ratio of the second distance value between the first distance value and the fourth median value of the reflection intensity value range, and the second distance value to the fourth median value.

2. The method according to claim 1, characterized in that The determining of the reflection intensity value range of the road sign based on the first statistical value of each preset intensity value classification area includes: determining a maximum first statistical value and a second maximum first statistical value based on the first statistical values ​​of the respective preset intensity value classification regions; Determine a first median value based on the preset intensity value classification area corresponding to the largest first statistical value, and determine a second median value based on the preset intensity value classification area corresponding to the second largest first statistical value; A reflection intensity value range of the road surface marking is determined based on the first median value and the second median value.

3. The method according to claim 1, characterized in that The step of cutting the global point cloud to obtain a plurality of sheet point clouds includes: The global point cloud is cut based on a preset segmentation specification to obtain a plurality of sheet point clouds.

4. The method according to claim 1, wherein The obtaining of the reflection intensity value of the global point cloud on the road surface includes: The reflection intensity value of the global point cloud on the road surface is obtained through the vehicle-mounted radar.

5. A road marking point cloud recognition device, characterized in that: include: an acquisition unit, configured to acquire a reflection intensity value of a global point cloud on a road surface, wherein the global point cloud includes a plurality of point clouds, and each point cloud includes at least a reflection intensity value; A cutting unit, configured to cut the global point cloud to obtain a plurality of sheet point clouds; a first determining unit, configured to determine a reflection intensity value range of a road surface marking on the road surface based on the reflection intensity value of each point cloud in the global point cloud; a second determining unit, configured to identify the reflection intensity values ​​of each point cloud in each sheet point cloud based on the reflection intensity value range, and determine each reflection intensity value associated with the road surface marking in each sheet point cloud, and point clouds corresponding to each reflection intensity value; The identifying of the reflection intensity values ​​of each point cloud in each sheet point cloud based on the reflection intensity value range, determining each reflection intensity value associated with the road surface marking in each sheet point cloud, and the point clouds corresponding to each reflection intensity value, includes: classifying and counting the reflection intensity values ​​of each point cloud in each sheet point cloud based on the multiple preset intensity value classification areas, obtaining a second statistical value of each sheet point cloud in each preset intensity value classification area; excluding the largest second statistical value in each sheet point cloud, obtaining the remaining second statistical values ​​in each sheet point cloud; and obtaining a third median value of the corresponding preset intensity value classification area based on the preset intensity value classification areas corresponding to the remaining second statistical values. Performing similarity matching based on the reflection intensity value range and each third median value in each sheet point cloud to obtain corresponding similarity matching results; Determining a fourth median of the corresponding sheet point cloud from each third median of each sheet point cloud, wherein a similarity matching result of the fourth median satisfies a preset similarity condition; In each sheet point cloud, determining that each reflection intensity value within the preset intensity value classification area corresponding to the fourth median value is related to the road surface marking, and determining point clouds corresponding to each of the reflection intensity values; The similarity matching result includes a matching difference and / or a matching degree; the matching difference refers to the first distance value between the third median and the reflection intensity value range; the matching degree is the second distance value between the first distance value and the fourth median of the reflection intensity value range, and the ratio of the second distance value to the fourth median.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

Images