Ground fault cliff identification method and device, electronic equipment and readable storage medium

Abstract

The application discloses a ground cliff identification method and device, electronic equipment and a readable storage medium. The ground cliff identification method comprises the following steps: acquiring point cloud data collected by a depth camera, and dividing the point cloud data into positive point cloud, ground point cloud and negative point cloud; setting a first detection range based on the internal parameters of the depth camera; in response to the absence of positive point cloud in the first detection range, extracting target ground point cloud from the ground point cloud by using a random sampling method; acquiring the target ground point cloud in a second detection range, and acquiring a calibration value based on the target ground point cloud in the second detection range; the second detection range is set based on the first detection range, and the second detection range contains the first detection range; and in response to the calibration value being less than a first preset threshold value, it is judged that there is a ground cliff in front of the depth camera. The point cloud data is divided into positive, ground and negative point cloud, and the ground point cloud is extracted and judged for multiple times, so that whether the ground cliff exists can be accurately judged.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical measurement, in particular to a ground cliff identification method and device, an electronic device and a readable storage medium. BACKGROUND

[0002] In the field of robot control, especially the movement control of mobile robots, when there are ground cliff scenes such as pits and stairs in the running environment of the robot, a distance sensor such as a depth camera or millimeter wave radar is generally installed on the robot to identify pits and stairs by allowing the sensor to image below the ground, thereby achieving the function of fall prevention. However, when the pit or stair is relatively deep, the sensor cannot image below the ground at a relatively deep depth, which will cause the fall prevention algorithm to fail and cause the robot to fall and be damaged. Therefore, accurate identification of ground cliffs of different depths during the operation of the robot is very important. SUMMARY

[0003] The present application provides a ground cliff identification method and device, an electronic device and a readable storage medium for accurately identifying ground cliffs of different depths.

[0004] The first aspect of the present application provides a ground cliff identification method, which comprises:

[0005] Obtaining point cloud data collected by a depth camera, and segmenting the point cloud data into positive point cloud, ground point cloud and negative point cloud;

[0006] Setting a first detection range based on the intrinsic parameters of the depth camera;

[0007] In response to the absence of positive point cloud in the first detection range, extracting target ground point cloud from the ground point cloud using a random sampling method;

[0008] Obtaining target ground point cloud in a second detection range, and obtaining a calibration value based on the target ground point cloud in the second detection range; the second detection range is set based on the first detection range, and the second detection range contains the first detection range;

[0009] In response to the calibration value being less than a first preset threshold, it is determined that there is a ground cliff in front of the depth camera.

[0010] Optionally, the step of segmenting the point cloud data into positive point cloud, ground point cloud and negative point cloud comprises:

[0011] Obtaining a world coordinate system; wherein the world coordinate system comprises a positive height plane and a negative height plane;

[0012] Calculating the height of the point cloud data under the world coordinate system;

[0013] In response to the height of the point cloud data being greater than the positive height plane, the point cloud data is defined as a positive point cloud;

[0014] In response to the height of the point cloud data being less than the negative height plane, the point cloud data is defined as a negative point cloud;

[0015] In response to the height of the point cloud data being less than or equal to the positive height plane and greater than or equal to the negative height plane, the point cloud data is defined as a ground point cloud.

[0016] Optionally, the step of extracting the target ground point cloud from the ground point cloud by using a random sampling method comprises:

[0017] Plane fitting is performed on the ground point cloud to obtain the target ground point cloud with the discrete point cloud removed.

[0018] Optionally, before the step of obtaining the target ground point cloud in the second detection range, the method further comprises:

[0019] In response to the number of target ground point clouds being greater than the second preset threshold, the second detection range is set based on the first detection range, so that the lateral length of the second detection range is equal to the lateral length of the first detection range, and the longitudinal length of the second detection range is greater than the longitudinal length of the first detection range;

[0020] In response to the number of target ground point clouds being less than or equal to the second preset threshold, it is determined that there is a ground cliff in front of the depth camera.

[0021] Optionally, the step of obtaining the calibration value based on the target ground point cloud in the second detection range comprises:

[0022] The number of target ground point clouds in the second detection range is obtained, and the number is defined as the calibration value; wherein the first preset threshold is a number threshold.

[0023] Optionally, the step of obtaining the calibration value based on the target ground point cloud in the second detection range comprises:

[0024] The outer bounding box of the target ground point cloud in the second detection range is calculated;

[0025] The difference between the maximum value and the minimum value of the outer bounding box is obtained, and the difference is defined as the calibration value; wherein the first preset threshold is a distance threshold.

[0026] Optionally, the ground cliff identification method further comprises:

[0027] In response to the presence of a positive point cloud in the first detection range, it is determined that there is no cliff in front of the depth camera;

[0028] Alternatively, in response to the calibration value being greater than or equal to the first preset threshold, it is determined that there is no ground cliff in front of the depth camera.

[0029] The second aspect of the present application provides a ground cliff recognition device, which comprises:

[0030] An acquisition module is configured to acquire point cloud data collected by a depth camera, and divide the point cloud data into positive point cloud, ground point cloud and negative point cloud, and extract target ground point cloud from the ground point cloud by using a random sampling method;

[0031] The acquisition module is further configured to set a first detection range based on intrinsic parameters of the depth camera, and set a second detection range based on the first detection range; wherein the second detection range contains the first detection range;

[0032] A calculation module is configured to detect whether there is positive point cloud in the first detection range;

[0033] The calculation module is further configured to acquire target ground point cloud in the second detection range, and acquire a calibration value based on the target ground point cloud in the second detection range;

[0034] The calculation module is further configured to determine that there is a ground cliff in front of the depth camera in response to the calibration value being less than a first preset threshold.

[0035] The third aspect of the present application provides an electronic device, which comprises a memory and a processor coupled with each other, and the processor is configured to execute program instructions stored in the memory to implement the ground cliff recognition method as described above.

[0036] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program can be executed by a processor to implement the ground cliff recognition method as described above.

[0037] The beneficial effects of the present application are as follows: different from the prior art, the present application divides the point cloud data collected by the depth camera into positive point cloud, ground point cloud and negative point cloud, and sets a first detection range based on the intrinsic parameters of the depth camera; it is determined whether there is positive point cloud in the first detection range, and in response to there being no positive point cloud in the first detection range, target ground point cloud is further extracted from the ground point cloud by using a random sampling method; a second detection range is set based on the first detection range, and target ground point cloud in the second detection range is further acquired, a calibration value is acquired based on the target ground point cloud in the second detection range, and a ground cliff is determined according to the calibration value; in response to the calibration value being less than a first preset threshold, it is determined that there is a ground cliff in front of the depth camera.

[0038] The application identifies the possible cliff through the positive point cloud and the ground point cloud, does not need to process and judge the negative point cloud, that is, does not identify the cliff through obtaining the imaging below the ground, and can be suitable for cliff detection of various depths; and the application sets the first detection range and the second detection range, can realize multiple extraction of the target ground point cloud, and improves the accuracy of ground cliff identification.

[0039] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, rather than limiting the application. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0041] Figure 1 is a flowchart of an embodiment of the ground cliff identification method of the application;

[0042] Figure 2 is a specific flowchart of step S11 in Figure 1

[0043] Figure 3 is a specific flowchart of step S14 in Figure 1

[0044] Figure 4 is a structural diagram of an embodiment of the ground cliff identification device of the application;

[0045] Figure 5 is a framework diagram of an embodiment of the electronic device of the application;

[0046] Figure 6 is a framework diagram of an embodiment of the computer readable storage medium of the application. DETAILED DESCRIPTION

[0047] In order to make those skilled in the art better understand the technical solutions of the application, the ground cliff identification method, device, electronic device and readable storage medium provided by the application will be further described in detail below in combination with the drawings and specific embodiments. It can be understood that the described embodiments are only some of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0048] ​​The terms "first", "second", etc. in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to these processes, methods, products or devices.

[0049] The application provides a ground cliff identification method to accurately identify cliffs of different depths on the ground. Figure 1 , Figure 1 is a flowchart of an embodiment of the ground cliff identification method of the application.

[0050] The execution subject of the ground cliff identification method of the application can be a ground cliff identification device, for example, the ground cliff identification method can be executed by a terminal device or a server or other processing device, wherein the ground cliff identification device can include a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a wireless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the ground cliff identification method can be realized by a processor calling computer readable instructions stored in a memory.

[0051] Specifically, the execution of the ground cliff identification method of the embodiment is a mobile robot, and a depth camera is arranged on the mobile robot to obtain a depth image on the moving path of the mobile robot, to determine whether there is an obstacle in front of the mobile robot, or whether there is a pit, a stair or a step, etc. Ground cliff condition, and then control the movement of the mobile robot.

[0052] Specifically, the ground cliff identification method of the embodiment of the present disclosure can include the following steps:

[0053] Step S11: Obtain point cloud data collected by the depth camera, and divide the point cloud data into positive point cloud, ground point cloud and negative point cloud.

[0054] The mobile robot shoots a depth image in front of its path through the depth camera, and converts the shot depth image into point cloud data.

[0055] Specifically, the conversion of the depth map to the point cloud data is actually a coordinate system conversion, specifically from an image coordinate system to a camera coordinate system, and the constraint condition of the coordinate system conversion is the intrinsic parameters of the depth camera. Alternatively, the coordinates in the camera coordinate system can be calculated through the intrinsic parameters of the depth camera and the coordinates in the image coordinate system, wherein the intrinsic parameters of the depth camera usually include principal point coordinates, focal lengths, and coordinate axis tilt parameters; relative to the imaging plane, the principal point coordinates are x0 and y0, the focal lengths can include the focal lengths fx and fy along the x-axis and the y-axis, and in general cases, fx and fy are equal; in an ideal case, the coordinate axis tilt parameter is 0.

[0056] Alternatively, the process of specifically segmenting the point cloud data into the positive point cloud, the ground point cloud, and the negative point cloud can be continued to refer to Figure 2 , Figure 2 is Figure 1 the specific flowchart of step S11 in

[0057] Step S111: Obtain a world coordinate system.

[0058] The world coordinate system is also obtained based on the coordinate system conversion of the image coordinate system, and the constraint condition of the coordinate system conversion is the intrinsic parameters and the extrinsic parameters of the depth camera.

[0059] Specifically, the image coordinate system is converted into the camera coordinate system based on the intrinsic parameters of the depth camera, and the camera coordinate system is further converted into the world coordinate system based on the extrinsic parameters of the depth camera. The extrinsic parameters of the depth camera can include a rotation matrix and a translation matrix, the rotation matrix is used to describe the direction of the coordinate axis of the world coordinate system relative to the camera coordinate system, and the translation matrix is used to describe the position of the space origin in the camera coordinate system.

[0060] Step S112: Calculate the height of the point cloud data in the world coordinate system.

[0061] Based on the obtained point cloud data and the world coordinate system, the specific coordinates of all the point cloud data in the world coordinate system are calculated, wherein the height of the point cloud data in the world coordinate system is the coordinate value of the z-axis of the world coordinate system.

[0062] Specifically, the world coordinate system includes a positive height plane and a negative height plane, wherein the positive height plane is a coordinate plane with a z-axis coordinate value equal to m, and the negative height plane is a coordinate plane with a z-axis coordinate value equal to n. Alternatively, in general, m is equal to -n.

[0063] Optionally, the height of all point cloud data in the world coordinate system is calculated, and the height of all point cloud data is compared with the z-axis coordinate value of the positive height plane and the negative height plane, to determine whether the height of the point cloud data is greater than the z-axis coordinate value of the positive height plane, or whether the height of the point cloud data is less than the z-axis coordinate value of the negative height plane, or whether the height of the point cloud data is less than or equal to the z-axis coordinate value of the positive height plane and greater than or equal to the z-axis coordinate value of the negative height plane, and any one of steps S113-S115 is executed in response to the determination result.

[0064] Step S113: In response to the height of the point cloud data being greater than the positive height plane, the point cloud data is defined as positive point cloud.

[0065] wherein, when it is determined that the height of the point cloud data is greater than the z-axis coordinate value of the positive height plane, the point cloud data is defined as positive point cloud.

[0066] Step S114: In response to the height of the point cloud data being less than the negative height plane, the point cloud data is defined as negative point cloud.

[0067] wherein, when it is determined that the height of the point cloud data is less than the z-axis coordinate value of the negative height plane, the point cloud data is defined as negative point cloud.

[0068] Step S115: In response to the height of the point cloud data being less than or equal to the positive height plane and greater than or equal to the negative height plane, the point cloud data is defined as ground point cloud.

[0069] wherein, when it is determined that the height of the point cloud data is less than or equal to the z-axis coordinate value of the positive height plane and greater than or equal to the z-axis coordinate value of the negative height plane, the point cloud data is defined as ground point cloud.

[0070] Optionally, according to different working environments of the mobile robot, the depth map captured by the depth camera is different, and the number of positive point cloud, negative point cloud and ground point cloud included in the point cloud data converted from the depth map is different. For example, only positive point cloud, or only negative point cloud, or only ground point cloud, or positive point cloud and negative point cloud, or positive point cloud and ground point cloud, or negative point cloud and ground point cloud, or positive point cloud, negative point cloud and ground point cloud, etc. can be included.

[0071] Step S12: Set the first detection range based on the intrinsic parameters of the depth camera.

[0072] In the embodiment, the first detection range is set based on the internal parameters of the depth camera. Specifically, the first detection range is set based on the display distance of the depth camera, and the display distance of the depth camera is related to the focal length, wherein the minimum distance and the maximum distance of the display distance of the depth camera are the minimum value and the maximum value of the first detection range.

[0073] Specifically, when it is determined that the forward point cloud exists in the first detection range, step S16 is performed; and when it is determined that the forward point cloud does not exist in the first detection range, step S13 is performed.

[0074] Step S16: In response to the existence of the forward point cloud in the first detection range, it is determined that there is no cliff in front of the depth camera.

[0075] In the embodiment, the forward point cloud is generally formed by a forward object, i.e., an obstacle, and the obstacle is usually arranged on a plane according to the working environment of the mobile robot, and will not be arranged in a pit, a step or a staircase, etc. Therefore, when it is determined that the forward point cloud exists in the first detection range, it is determined that there is no cliff in front of the depth camera, i.e., there is no cliff in front of the moving path of the mobile robot, and the mobile robot can continue to move along the current moving path without the need to control the mobile robot to stop moving or turn.

[0076] Step S13: In response to the non-existence of the forward point cloud in the first detection range, a target ground point cloud is extracted from the ground point cloud by using a random sampling method.

[0077] In the embodiment, when it is determined that the forward point cloud does not exist in the first detection range, it is determined that there may be a cliff in front of the depth camera. If the mobile robot continues to move along the current moving path, the mobile robot may fall, and the mobile robot needs to be controlled to stop moving or turn.

[0078] In addition, since the embodiment needs to perform image shooting, coordinate system conversion, image transmission and other operations, image noise may be generated due to random signal interference. Therefore, the ground point cloud obtained by classification needs to be denoised. Specifically, the target ground point cloud is extracted from the ground point cloud by using a random sampling method.

[0079] Optionally, the process of extracting the target ground point cloud from the ground point cloud by using the random sampling method can also be shown in the following step S131. Specifically, the process includes the following steps.

[0080] Step S131: Plane fitting is performed on the ground point cloud to obtain the target ground point cloud from which the discrete point cloud is removed.

[0081] In the embodiment, the random sampling method is specifically plane fitting, and the target ground point cloud from which the discrete point cloud is removed is obtained by performing plane fitting on the ground point cloud.

[0082] Optionally, the embodiment is further provided with a second detection range, when it is judged that the number of the target ground point cloud in the first detection range is greater than a second preset threshold, then step S22 is further executed; when it is judged that the number of the target ground point cloud in the first detection range is less than or equal to the second preset threshold, then step S21 is executed.

[0083] Step S21: in response to the number of the target ground point cloud being less than or equal to the second preset threshold, it is judged that there is a ground cliff in front of the depth camera.

[0084] Wherein, when it is judged that the number of the target ground point cloud is less than or equal to the second preset threshold, it is proved that the planar area in front of the moving robot moving path is small, and the non-planar area is large, that is, it is judged that there is a ground cliff in front of the depth camera (or the moving robot).

[0085] Step S22: setting a second detection range based on the first detection range.

[0086] Wherein, in response to the number of the target ground point cloud being greater than the second preset threshold, the second detection range is set based on the first detection range.

[0087] Specifically, the second detection range contains the first detection range. Wherein, the lateral length of the second detection range is equal to the lateral length of the first detection range, and the longitudinal length of the second detection range is greater than the longitudinal length of the first detection range, wherein the lateral length is the width direction of the view angle of the depth camera, and the longitudinal length is the direction of the distance far and near of the depth camera.

[0088] Optionally, the longitudinal length of the first detection range is usually set to 0.3m-2m, which can be adjusted according to the engineering debugging experience. The longitudinal length of the second detection range can be 0.2m-0.3m longer than the longitudinal length of the first detection range.

[0089] After setting the second detection range, the target ground point cloud is further screened to obtain the target ground point cloud in the second detection range, so as to obtain the calibration value based on the target ground point cloud in the second detection range, that is, step S14 is further executed.

[0090] Wherein, the embodiment further compares the number of the target ground point cloud in the first detection range with the second preset threshold before executing step S14, that is, step S21 or step S22 is executed, which can prevent misjudgment of the ground cliff.

[0091] Step S14: obtaining the target ground point cloud in the second detection range, and obtaining the calibration value based on the target ground point cloud in the second detection range.

[0092] After obtaining the denoised target ground point cloud through step S13, it is necessary to further determine whether the target ground point cloud exists within the second detection range, and obtain a calibration value based on the target ground point cloud within the second detection range to determine whether a ground cliff exists.

[0093] Furthermore, when the number of target ground point clouds is sufficiently large, it indicates the presence of a large flat area in front of the mobile robot. Even small potholes will not cause the robot to fall or tip over. Therefore, this embodiment sets a second preset threshold. By determining whether the number of target ground point clouds exceeds the second preset threshold, it distinguishes between negligible ground cliffs and ground cliffs requiring movement control of the mobile robot. Optionally, the second preset threshold can be set based on the size parameters of the mobile robot.

[0094] Optionally, please refer to the following for details on the process of obtaining calibration values ​​based on the target ground point cloud within the second detection range. Figure 3 , Figure 3 yes Figure 1 A detailed flowchart of step S14 is provided. Specifically, it includes the following steps:

[0095] Step S141: Obtain the number of target ground point clouds within the second detection range and define the number as a calibration value.

[0096] In this embodiment, the number of target ground point clouds within the second detection range is obtained and defined as a calibration value.

[0097] And / or,

[0098] Step S142: Calculate the bounding box of the target ground point cloud within the second detection range.

[0099] In this embodiment, the bounding box of the target ground point cloud within the second detection range is calculated using a preset fitting formula, wherein the number of bounding boxes is at least two. Optionally, this embodiment can use axis-aligned bounding boxes (AABBs) to fit the target ground point cloud within the second detection range.

[0100] Step S143: Obtain the difference between the maximum and minimum values ​​of the outer bounding box, and define the difference as the calibration value.

[0101] In this embodiment, the maximum and minimum values ​​of the multiple bounding boxes calculated in step S142 are further obtained, and the difference between the maximum and minimum values ​​is calculated and defined as a calibration value. Specifically, in this embodiment, the difference is used to represent the longitudinal span of the ground.

[0102] Optionally, the embodiment compares the calibrated value obtained based on step S141 or step S143 with a first preset threshold. Specifically, when the calibrated value is a quantity, the first preset threshold is a quantity threshold; when the calibrated value is a difference, the first preset threshold is a distance threshold.

[0103] Specifically, when it is determined that the calibrated value is less than the first preset threshold, step S15 is performed; when it is determined that the calibrated value is greater than or equal to the first preset threshold, step S17 is performed.

[0104] Step S15: In response to the calibrated value being less than the first preset threshold, it is determined that there is a ground cliff in front of the depth camera.

[0105] When it is determined that the calibrated value is less than the first preset threshold, it is proved that the planar region in front of the movement path of the mobile robot is small, and the non-planar region is large, that is, it is determined that there is a ground cliff in front of the depth camera (or the mobile robot). Alternatively, it is proved that the span of the non-planar region in front of the movement path of the mobile robot is large, that is, it is determined that there is a ground cliff in front of the depth camera (or the mobile robot).

[0106] Step S17: In response to the calibrated value being greater than or equal to the first preset threshold, it is determined that there is no ground cliff in front of the depth camera.

[0107] When it is determined that the calibrated value is greater than or equal to the first preset threshold, it is proved that the planar region in front of the movement path is large, or the span of the non-planar region in front of the movement path of the mobile robot is small, so it can be determined that there is no ground cliff in front of the depth camera (or the mobile robot).

[0108] The application converts the depth map photographed by the depth camera into point cloud data, and further classifies the point cloud data, to identify the possible cliff through the positive point cloud and the ground point cloud, without the need to process and determine the negative point cloud, that is, without identifying the cliff through the imaging below the ground, and can be suitable for cliff detection of various depths. In addition, the application sets the first detection range and the second detection range, can extract the target ground point cloud multiple times, and improves the accuracy of ground cliff identification.

[0109] The application also provides a ground cliff identification device, please refer to Figure 4 , Figure 4 is a structural schematic diagram of an embodiment of the ground cliff identification device of the application. As Figure 4 shown, the ground cliff identification device 40 comprises an acquisition module 41 and a calculation module 42 connected with each other. Optionally, the embodiment of the ground cliff identification device 40 can be arranged on the mobile robot, and the mobile robot is provided with a depth camera for photographing the depth map of the movement path of the mobile robot.

[0110] Specifically, the acquisition module 41 is configured to acquire point cloud data collected by the depth camera, and divide the point cloud data into positive point cloud data, ground point cloud data and negative point cloud data, and configured to extract target ground point cloud data from the ground point cloud data by using a random sampling method.

[0111] The acquisition module 41 is further configured to set a first detection range based on an intrinsic parameter of the depth camera, and set a second detection range based on the first detection range, wherein the second detection range contains the first detection range.

[0112] The calculation module 42 is configured to detect whether the positive point cloud data exists in the first detection range, and further configured to acquire the target ground point cloud data in the second detection range, and acquire a calibration value based on the target ground point cloud data in the second detection range, and further configured to determine that the ground cliff exists in front of the depth camera in response to the calibration value being less than a first preset threshold.

[0113] The present application also provides an electronic device, please refer to Figure 5 , Figure 5 is a framework schematic diagram of an embodiment of the electronic device of the present application. The electronic device 50 comprises a memory 51 and a processor 52 coupled with each other, and the processor 52 is configured to execute program instructions stored in the memory 51 to implement the steps in any of the above ground cliff identification method embodiments. In a specific implementation scenario, the electronic device 50 can include but is not limited to: a microcomputer, a server, in addition, the electronic device 50 can also include a notebook computer, a tablet computer and other mobile devices, which are not limited here.

[0114] Specifically, the processor 52 is configured to control itself and the memory 51 to implement the steps in any of the above ground cliff identification method embodiments. The processor 52 can also be called CPU (Central Processing Unit, central processing unit). The processor 52 can be an integrated circuit chip with signal processing capability. The processor 52 can also be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The general processor can be a microprocessor or the processor can also be any conventional processor. In addition, the processor 52 can be realized by integrated circuit chips together.

[0115] The present application also provides a computer readable storage medium, please refer to Figure 6 , Figure 6FIG. 1 is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of the present application. The computer-readable storage medium 60 stores a computer program 61 capable of being executed by a processor, and the computer program 61 is used to implement the steps in any of the above ground fault scarp identification method embodiments.

[0116] In some embodiments, the apparatus provided by the embodiments of the present disclosure has functions or includes modules that can be used to perform the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, details are not repeated here.

[0117] The above description of various embodiments tends to emphasize the differences between various embodiments, and the same or similar parts can be mutually referred to. For brevity, details are not repeated here.

[0118] In several embodiments provided in the present application, it should be understood that the disclosed methods and apparatuses can be implemented in other ways. For example, the above-described apparatus implementation is only schematic. For example, the division of modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a unit or component can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual elements can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0119] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0120] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solutions of the present application essentially or in other words, the part that makes a contribution to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0121] The above merely provides the examples of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made according to the content of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for identifying ground cliffs, characterized in that, include: Acquire point cloud data collected by a depth camera, and segment the point cloud data into positive point cloud, ground point cloud, and negative point cloud; A first detection range is set based on the intrinsic parameters of the depth camera; In response to the absence of the positive point cloud within the first detection range, a target ground point cloud is extracted from the ground point cloud using a random sampling method; Obtain the target ground point cloud within the second detection range, and obtain calibration values ​​based on the target ground point cloud within the second detection range; the second detection range is set based on the first detection range, and the second detection range includes the first detection range; If the calibration value is less than a first preset threshold, it is determined that there is a ground cliff in front of the depth camera.

2. The method for identifying ground cliffs according to claim 1, characterized in that, The step of segmenting the point cloud data into positive point cloud, ground point cloud, and negative point cloud includes: Obtain the world coordinate system; wherein the world coordinate system includes a positive height plane and a negative height plane; Calculate the height of the point cloud data in the world coordinate system; If the height of the point cloud data is greater than the forward height plane, then the point cloud data is defined as the forward point cloud; If the height of the point cloud data is less than the negative height plane, then the point cloud data is defined as the negative point cloud; If the height of the point cloud data is less than or equal to the positive height plane and greater than or equal to the negative height plane, then the point cloud data is defined as the ground point cloud.

3. The method for identifying ground cliffs according to claim 1, characterized in that, The step of extracting the target ground point cloud from the ground point cloud using a random sampling method includes: Planar fitting is performed on the ground point cloud to obtain the target ground point cloud after removing the discrete point cloud.

4. The method for identifying ground cliffs according to claim 1, characterized in that, Before the step of acquiring the target ground point cloud within the second detection range, the method further includes: In response to the number of target ground point clouds being greater than a second preset threshold, a second detection range is set based on the first detection range, such that the horizontal length of the second detection range is equal to the horizontal length of the first detection range, and the vertical length of the second detection range is greater than the vertical length of the first detection range. If the number of target ground point clouds is less than or equal to the second preset threshold, it is determined that there is a ground cliff in front of the depth camera.

5. The method for identifying ground cliffs according to claim 1, characterized in that, The step of obtaining calibration values ​​based on the target ground point cloud within the second detection range includes: The number of target ground point clouds within the second detection range is obtained, and the number is defined as the calibration value; the first preset threshold is the number threshold.

6. The method for identifying ground cliffs according to claim 1, characterized in that, The step of obtaining calibration values ​​based on the target ground point cloud within the second detection range includes: Calculate the bounding box of the target ground point cloud within the second detection range; Obtain the difference between the maximum and minimum values ​​of the bounding box, and define the difference as the calibration value; the first preset threshold is a distance threshold.

7. The method for identifying ground cliffs according to claim 1, characterized in that, The ground cliff identification method also includes: In response to the presence of the positive point cloud within the first detection range, it is determined that there is no cliff in front of the depth camera; Alternatively, in response to the calibration value being greater than or equal to the first preset threshold, it is determined that there is no ground cliff in front of the depth camera.

8. A ground cliff identification device, characterized in that, include: The acquisition module is used to acquire point cloud data collected by the depth camera, and to segment the point cloud data into positive point cloud, ground point cloud and negative point cloud, and to extract target ground point cloud from the ground point cloud using a random sampling method. The acquisition module is further configured to set a first detection range based on the intrinsic parameters of the depth camera, and set a second detection range based on the first detection range; wherein the second detection range includes the first detection range; The calculation module is used to detect whether the positive point cloud exists within the first detection range; The calculation module is also used to obtain the target ground point cloud within the second detection range, and to obtain a calibration value based on the target ground point cloud within the second detection range; The calculation module is also used to determine that there is a ground cliff in front of the depth camera in response to the calibration value being less than a first preset threshold.

9. An electronic device, characterized in that, It includes a memory and a processor coupled to each other, the processor being used to execute program instructions stored in the memory to implement the ground cliff identification method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the ground cliff identification method as described in any one of claims 1-7.

Images