A mapping method, cleaning robot and computer storage medium

Abstract

Embodiments of the present application disclose a mapping method, which is applied to a cleaning robot and includes: controlling the cleaning robot to rotate at a preset first interval angle, capturing at least two interval pictures at rotation intervals of the first interval angle by a camera of the cleaning robot, controlling the cleaning robot to rotate at a preset second interval angle, performing vertical scanning on an object image of the interval picture by a laser ranging sensor of the cleaning robot at rotation intervals of the second interval angle, obtaining depth images of the at least two interval pictures, and splicing the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures to obtain 3D pictures of the at least two interval pictures. Embodiments of the present application also disclose a cleaning robot and a computer storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of three-dimensional (3D) mapping with a cleaning robot, and in particular to a mapping method, a cleaning robot and a computer storage medium. BACKGROUND

[0002] At present, a cleaning robot usually adopts a depth camera or a 3D laser radar to perform 3D mapping. However, the method has high calculation complexity, resulting in slow 3D mapping speed.

[0003] It can be seen that the existing cleaning robot has the technical problem of slow mapping speed in 3D mapping.

[0004] SUMMARY

[0005] Embodiments of the present application aim to provide a mapping method, a cleaning robot and a computer storage medium to solve the technical problem of slow mapping speed in 3D mapping of a cleaning robot in the related art.

[0006] The technical solution of the present application is implemented as follows:

[0007] A mapping method, applied to a cleaning robot, comprises the following steps:

[0008] controlling the cleaning robot to rotate at a preset first interval angle, and capturing at least two interval pictures through a camera of the cleaning robot at a rotation interval of the first interval angle;

[0009] controlling the cleaning robot to rotate at a preset second interval angle, and performing vertical scanning on an object image of the at least two interval pictures through a laser ranging sensor of the cleaning robot at a rotation interval of the second interval angle to obtain a depth image of the at least two interval pictures;

[0010] splicing the at least two interval pictures according to the at least two interval pictures and the depth image of the at least two interval pictures to obtain a 3D picture of the at least two interval pictures.

[0011] A cleaning robot comprises:

[0012] a capturing module configured to control the cleaning robot to rotate at a preset first interval angle, and capture at least two interval pictures through a camera of the cleaning robot at a rotation interval of the first interval angle;

[0013] The scanning module is configured to control the cleaning robot to rotate at a preset second interval angle, and to perform vertical scanning on the at least two interval pictures at the rotation interval of the second interval angle by the laser ranging sensor of the cleaning robot, to obtain a depth image of the at least two interval pictures.

[0014] The mapping module is configured to stitch the at least two interval pictures according to the at least two interval pictures and the depth image of the at least two interval pictures, to obtain a 3D picture of the at least two interval pictures.

[0015] A cleaning robot comprises:

[0016] A processor and a storage medium storing instructions executable by the processor, the storage medium being dependent on the processor to perform operations, when the instructions are executed by the processor, the mapping method described in one or more embodiments is executed.

[0017] A computer storage medium storing executable instructions, when the executable instructions are executed by one or more processors, the processor executes the mapping method as described in one or more embodiments.

[0018] The mapping method, the cleaning robot and the computer storage medium provided in the embodiments of the present application control the cleaning robot to rotate at a preset first interval angle, capture at least two interval pictures at the rotation interval of the first interval angle by the camera of the cleaning robot, control the cleaning robot to rotate at a preset second interval angle, and perform vertical scanning on the object image of the at least two interval pictures at the rotation interval of the second interval angle by the laser ranging sensor of the cleaning robot, to obtain a depth image of the at least two interval pictures, and stitch the at least two interval pictures according to the at least two interval pictures and the depth image of the at least two interval pictures, to obtain a 3D picture of the at least two interval pictures; that is, in the embodiments of the present application, the pictures at the rotation interval of the first interval angle are captured by the camera of the cleaning robot, and the object image of the pictures at the rotation interval of the second interval angle is scanned by the laser ranging sensor to obtain the depth image of the pictures, so that the pictures and the depth images of the pictures can be obtained by the camera and the laser ranging sensor, and finally, the pictures are stitched by using the pictures and the depth images of the pictures to obtain a 3D picture, in this way, by controlling the rotation of the cleaning robot, and using the camera and the laser ranging sensor to collect the pictures and the depth information of the pictures, and using the picture stitching technology, 3D mapping can be realized, compared with the existing method, only an ordinary camera and an ordinary laser ranging sensor are needed to obtain the pictures and the depth images, and the 3D mapping can be realized by using the image stitching technology, thereby reducing the computational complexity and improving the speed of 3D mapping. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 An optional mapping method provided for an embodiment of the present application has a flowchart as shown in the figure;

[0020] Figure 2 An optional structure of a cleaning robot provided for an embodiment of the present application has a schematic diagram as shown in the figure;

[0021] Figure 3 Another optional structure of a cleaning robot provided for an embodiment of the present application has a schematic diagram as shown in the figure. DETAILED DESCRIPTION

[0022] In order to better understand the purpose, structure and function of the present application, a mapping method and a cleaning robot of the present application are further described in detail below in combination with the drawings.

[0023] An embodiment of the present application provides a mapping method, which is applied to a cleaning robot, Figure 1 An optional mapping method provided for an embodiment of the present application has a flowchart as shown in the figure, which is described in detail as follows. Figure 1 The mapping method can include the following steps.

[0024] S101: Control the cleaning robot to rotate at a preset first interval angle, and capture at least two interval pictures through the camera of the cleaning robot at each rotation interval of the first interval angle.

[0025] At present, for the cleaning robot, either a depth image is set in the cleaning robot to realize 3D mapping, or a laser radar is set in the cleaning robot to realize 3D mapping. This method can realize 3D mapping by using a relatively complex calculation method, and the 3D mapping speed is slow due to the high calculation complexity.

[0026] In order to improve the speed of 3D mapping, an embodiment of the present application provides a mapping method, which is applied to a cleaning robot, and a camera for capturing a pixel image is arranged in the cleaning robot, the camera is arranged at the front of the forward direction of the cleaning robot, in addition, a laser ranging sensor is also arranged in the cleaning robot, and the laser ranging sensor is also arranged at the front of the forward direction of the cleaning robot, and the distance between the camera and the laser ranging sensor is within a preset threshold.

[0027] Firstly, the cleaning robot is controlled to rotate at a preset first interval angle. Specifically, when the cleaning robot rotates, the rotation angle can be measured by a gyroscope sensor in the cleaning robot, and at each rotation interval of the first interval angle, a picture is captured through the camera to obtain at least two interval pictures.

[0028] The camera can be a red green blue (RGB) camera or a luminance chrominance chroma (YUV) camera, and the embodiments of the present application do not make a specific limitation here.

[0029] S102: The cleaning robot is controlled to rotate at a preset second interval angle, and a laser ranging sensor of the cleaning robot is used to perform vertical scanning on the object image of the at least two interval pictures at the rotation interval of the second interval angle, to obtain a depth image of the at least two interval pictures.

[0030] Specifically, each interval picture can be obtained when the cleaning robot is controlled to rotate at the first interval angle. After each interval picture is obtained, the cleaning robot is controlled to rotate at a preset second interval angle, and the laser ranging sensor is used to perform vertical scanning on the object image of each interval picture at the rotation interval of the second interval angle, so that a depth image of each interval picture can be obtained.

[0031] Here, it should be noted that the vertical scanning of the object image of each interval picture by the laser ranging sensor at the rotation interval of the second interval angle can obtain a distance curve of the object image of each interval picture from the camera, and the cleaning robot can obtain the depth image of each interval picture by setting different sampling frequencies.

[0032] In addition, the first interval angle and the second interval angle can be set by an actual environment, and the first interval angle is greater than the second interval angle. For example, the first interval angle is 60 degrees, and the second interval angle is 5 degrees.

[0033] S103: The at least two interval pictures are spliced according to the at least two interval pictures and the depth images of the at least two interval pictures, to obtain a 3D picture of the at least two interval pictures.

[0034] Specifically, after the at least two interval pictures and the depth images of the at least two interval pictures are obtained, in order to obtain a 3D picture, the at least two interval pictures need to be spliced. Here, the pose of the camera and the rotation angle of the gyroscope sensor can be used to calculate an affine transformation matrix, to realize the splicing of the at least two interval pictures. Alternatively, a feature point matching method can be used to realize the splicing of the at least two interval pictures, and the embodiments of the present application do not make a specific limitation here.

[0035] In order to further obtain the depth images of the at least two interval pictures, in an optional embodiment, the method further includes:

[0036] segmenting each of the at least two interval pictures according to a preset pixel size to obtain sub-pictures of each of the at least two interval pictures;

[0037] re-determining depth images of the sub-pictures of each of the at least two interval pictures according to the depth images of each of the at least two interval pictures to obtain the depth images of the at least two interval pictures.

[0038] Specifically, in order to re-determine the depth images of the at least two interval pictures, first, each of the at least two interval pictures is segmented by using a fixed size window, and the fixed size window can be a preset pixel size. For example, if the interval picture is a picture of 1600x800, the preset pixel size can be 100x200, so that the interval picture can be segmented into a plurality of sub-pictures.

[0039] Finally, the depth images of the sub-pictures of each of the at least two interval pictures are re-determined according to the depth images of each of the at least two interval pictures, and the depth images of the at least two interval pictures are obtained after the depth images of the sub-pictures of each of the at least two interval pictures are determined.

[0040] It should be noted that the embodiments of the present application can directly use the depth images of each of the interval pictures for picture stitching, or can use the depth images of each of the interval pictures determined based on the re-determined depth images of the sub-pictures of each of the interval pictures for picture stitching, and the embodiments of the present application do not make specific limitations here.

[0041] In addition to using the depth images corresponding to the sub-pictures in each of the interval pictures, the depth images of the sub-pictures of each of the interval pictures can also be re-determined. In an optional embodiment, in order to re-determine the depth images of the sub-pictures of each of the interval pictures, re-determining the depth images of the sub-pictures of each of the at least two interval pictures according to the depth images of each of the at least two interval pictures to obtain the depth images of the at least two interval pictures can include:

[0042] determining the depth images corresponding to the sub-pictures in each of the interval pictures from the depth images of each of the interval pictures;

[0043] re-determining the depth images of the sub-pictures of each of the at least two interval pictures according to the depth images corresponding to the sub-pictures in each of the interval pictures to obtain the depth images of the at least two interval pictures.

[0044] That is, first, the depth images corresponding to the sub-pictures in each of the interval pictures can be selected from the depth images of each of the interval pictures, and then the depth images of the sub-pictures of each of the interval pictures are re-determined based on the depth images corresponding to the sub-pictures in each of the interval pictures.

[0045] Here, the average value of all distance values in the depth image corresponding to the sub-picture in each interval picture can be taken as the distance value in the depth image of the sub-picture of each interval picture, of course, the standard deviation of all distance values in the depth image corresponding to the sub-picture in each interval picture can be taken as the distance value in the depth image of the sub-picture of each interval picture, and the variance of all distance values in the depth image corresponding to the sub-picture in each interval picture can be taken as the distance value in the depth image of the sub-picture of each interval picture. Here, embodiments of the present application do not make specific limitations.

[0046] Further, in order to re-determine the depth image of the sub-picture of each interval picture, after knowing the depth image corresponding to the sub-picture in each interval picture, in an optional embodiment, the depth image of the sub-picture of each interval picture is re-determined according to the depth image corresponding to the sub-picture in each interval picture to obtain the depth image of at least two interval pictures, which can include:

[0047] determining the mode of all distance values in the depth image corresponding to the sub-picture in each interval picture;

[0048] re-determining the depth image of the sub-picture of each interval picture according to the mode to obtain the depth image of at least two interval pictures.

[0049] Here, all distance values in the depth image corresponding to the sub-picture in each interval picture are first selected, then all distance values are counted, the mode of all distance values is counted, and the depth image of the sub-picture of each interval picture is re-determined according to the counted mode to obtain the depth image of at least two interval pictures.

[0050] For the mode of all distance values, there can be only one mode, or there can be multiple modes. For the case of only one mode, in an optional embodiment, the depth image of the sub-picture of each interval picture is re-determined according to the mode to obtain the depth image of at least two interval pictures, which includes:

[0051] When the mode is one, the mode is determined as the distance value in the depth image of the sub-picture of each interval picture to obtain the depth image of at least two interval pictures.

[0052] Specifically, for the case of only one mode, the mode is taken as the distance value of the depth image of the sub-picture of each interval picture, that is, for each sub-picture, the mode of all distance values in the depth image corresponding to the sub-picture is taken as the distance value, to form the depth image of each sub-picture. In this way, the depth image of each sub-picture takes one value to represent the distance between the camera and the object image, which can reduce the complexity of 3D mapping and is beneficial to the cleaning robot to avoid obstacles when sweeping the ground.

[0053] For the case of having multiple modes, in an optional embodiment, the depth image of the sub-picture of each interval picture is re-determined according to the mode, to obtain the depth image of at least two interval pictures, including:

[0054] When the mode is at least two, the minimum value in the mode is determined as the distance value in the depth image of the sub-picture of the interval picture, to obtain the depth image of at least two interval pictures.

[0055] Specifically, for the case of having multiple modes, the minimum value in the mode is taken as the distance value of the depth image of the sub-picture of each interval picture, that is, for each sub-picture, the minimum value of the mode of all distance values in the depth image corresponding to the sub-picture is taken as the distance value, to form the depth image of each sub-picture. In this way, the depth image of each sub-picture takes one value to represent the distance between the camera and the object image, which can reduce the complexity of 3D mapping and is beneficial to the cleaning robot to avoid obstacles when sweeping the ground.

[0056] In order to realize the splicing of the interval pictures, in an optional embodiment, S103 can include:

[0057] From the at least two interval pictures, two interval pictures at adjacent rotation intervals of a first interval angle are selected;

[0058] When there is an overlapping area between the two interval pictures, feature point matching processing is performed on the overlapping area to obtain a target relative displacement between the two interval pictures;

[0059] The two interval pictures are spliced using the target relative displacement to obtain a spliced picture;

[0060] The depth image of the spliced picture is determined according to the depth images of the two interval pictures;

[0061] A 3D picture is obtained according to the spliced picture and the depth image of the spliced picture.

[0062] Specifically, for the obtained at least two interval pictures, first, two interval pictures at adjacent rotation intervals of a first interval angle are obtained, for example, after obtaining a first interval picture, the cleaning robot is controlled to rotate 60 degrees, a second interval picture is obtained, and the two interval pictures are processed by intersection to obtain an overlapping region of the two interval pictures.

[0063] Then, the overlapping region is processed by feature point matching, the feature points and feature descriptors of the overlapping region of the two interval pictures can be extracted respectively, and the matching feature points are obtained by matching the feature points and feature descriptors of the two interval pictures. Finally, the target relative displacement of the two interval pictures is obtained by using the relative displacement between each pair of matching feature points.

[0064] The target relative displacement includes a target vertical relative displacement and a target horizontal relative displacement. When splicing the pictures, the first interval picture can be used as a reference image, and the second interval picture can be used as a moving image. The moving image is translated in the vertical direction by the target vertical relative displacement and in the horizontal direction by the target horizontal relative displacement. Of course, the moving image can be first translated in the horizontal direction by the target horizontal relative displacement, and then translated in the vertical direction by the target vertical relative displacement. Here, the embodiments of the present application do not make specific limitations.

[0065] The above translation can complete the splicing of the two interval pictures. Of course, for the two interval pictures without an overlapping region, the pose of the camera and the rotation angle of the gyroscope sensor can be used to calculate an affine transformation matrix, and then the splicing of the at least two interval pictures can be realized.

[0066] After obtaining the spliced picture, the depth image of the spliced picture can be determined by using the depth images of the two interval pictures, and thus the 3D picture can be determined.

[0067] The mapping method according to one or more embodiments described above will be described below by taking examples.

[0068] First, a 200 million RGB pixel camera is installed in front of the cleaning robot in the forward direction, and a tiltable single-point laser ranging sensor is installed in front of the cleaning robot in the forward direction. In order to ensure that the tiltable single-point laser ranging sensor can scan all the images captured by the camera, the distance between the camera and the tiltable single-point laser ranging sensor is less than a preset distance. In addition, a gyroscope sensor is installed inside the robot.

[0069] When the cleaning robot enters the 3D mapping mode, it first stops to collect a picture, the gyro sensor records the rotation angle of the cleaning robot at this time, the position of the fixed camera and the tiltable single-point laser ranging sensor is fixed, the tiltable single-point laser ranging sensor starts to scan from the left edge of the picture, the cleaning robot rotates right by 5 degrees each time, the tiltable single-point laser ranging sensor scans once, until it scans to the right edge of the picture, the distance between the camera and the corresponding image of the picture can be obtained through scanning, so that the sparse point depth image of the picture can be obtained.

[0070] Then, the picture is profiled and segmented, a fixed size window is used to scan different profiles, the depth image of the picture in the window is the mode of all distance values in the depth image in the window, so that a picture with a depth image is obtained, the cleaning robot obtains such a picture every 60 degrees of rotation, so that multiple pictures and depth images of the pictures can be obtained.

[0071] Finally, the rotation matrix between adjacent pictures can be calculated through the installation pose of the camera and the rotation angle of the robot, panoramic stitching is performed using adjacent pictures and depth images of the pictures to realize 3D mapping.

[0072] The mapping method provided in the embodiments of the application controls the cleaning robot to rotate according to a preset first interval angle, captures at least two interval pictures at the rotation interval of the first interval angle through the camera of the cleaning robot, controls the cleaning robot to rotate according to a preset second interval angle, performs vertical scanning on the images of the at least two interval pictures through the laser ranging sensor of the cleaning robot at the rotation interval of the second interval angle, obtains depth images of the at least two interval pictures, and splices the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures to obtain 3D pictures of the at least two interval pictures; that is, in the embodiments of the application, the cleaning robot captures the pictures at the rotation interval of the first interval angle through the camera of the cleaning robot, and obtains the depth images of the pictures by scanning the images of the pictures at the rotation interval of the second interval angle using the laser ranging sensor, so that the pictures and the depth images of the pictures can be obtained through the camera and the laser ranging sensor, finally, the pictures are spliced using the pictures and the depth images of the pictures to obtain 3D pictures, in this way, the rotation of the cleaning robot is controlled, the pictures and the depth information of the pictures are collected using the camera and the laser ranging sensor, and the 3D mapping is realized using the picture splicing technology, compared with the existing method, only an ordinary camera and an ordinary laser ranging sensor are needed to obtain the pictures and the depth images, the 3D mapping is realized using the image splicing technology, so that the calculation complexity is reduced, and the speed of 3D mapping is improved.

[0073] Embodiment two

[0074] Based on the same inventive concept, the embodiments of the present application provide a cleaning robot, Figure 2 An optional structural schematic diagram of a cleaning robot is provided for the embodiments of the present application, referring to Figure 2 As shown in the figure, the cleaning robot can include:

[0075] A capturing module 21 is configured to control the cleaning robot to rotate at a preset first interval angle, and capture at least two interval pictures through a camera of the cleaning robot at a rotation interval of the first interval angle.

[0076] A scanning module 22 is configured to control the cleaning robot to rotate at a preset second interval angle, and perform vertical scanning on an object image of the at least two interval pictures through a laser ranging sensor of the cleaning robot at a rotation interval of the second interval angle, to obtain a depth image of the at least two interval pictures.

[0077] A mapping module 23 is configured to splice the at least two interval pictures according to the depth image of the at least two interval pictures, to obtain a 3D picture of the at least two interval pictures.

[0078] In other embodiments of the present application, the cleaning robot is further configured to:

[0079] divide each interval picture of the at least two interval pictures according to a preset pixel size, to obtain a sub-picture of each interval picture;

[0080] re-determine a depth image of the sub-picture of each interval picture according to the depth image of each interval picture of the at least two interval pictures, to obtain a depth image of the at least two interval pictures.

[0081] In other embodiments of the present application, the cleaning robot re-determines a depth image of the sub-picture of each interval picture according to the depth image of each interval picture of the at least two interval pictures, to obtain a depth image of the at least two interval pictures, including:

[0082] determining a depth image corresponding to the sub-picture in each interval picture from the depth image of each interval picture;

[0083] re-determining a depth image of the sub-picture of each interval picture according to the depth image corresponding to the sub-picture in each interval picture, to obtain a depth image of the at least two interval pictures.

[0084] In other embodiments of the present application, the cleaning robot re-determines a depth image of the sub-picture of each interval picture according to the depth image corresponding to the sub-picture in each interval picture, to obtain a depth image of the at least two interval pictures, including:

[0085] determine the mode of all distance values in the depth image corresponding to the sub-picture in each interval picture;

[0086] re-determine the depth image of the sub-picture of each interval picture according to the mode, to obtain the depth images of the at least two interval pictures.

[0087] In other embodiments of the present application, the cleaning robot re-determines the depth image of the sub-picture of each interval picture according to the mode, to obtain the depth images of the at least two interval pictures, including:

[0088] When the mode is one, the mode is determined as the distance value in the depth image of the sub-picture of each interval picture, to obtain the depth images of the at least two interval pictures.

[0089] In other embodiments of the present application, the cleaning robot re-determines the depth image of the sub-picture of each interval picture according to the mode, to obtain the depth images of the at least two interval pictures, including:

[0090] When the mode is at least two, the minimum value in the mode is determined as the distance value in the depth image of the sub-picture of the interval picture, to obtain the depth images of the at least two interval pictures.

[0091] In other embodiments of the present application, the cleaning robot splices the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures, to obtain the 3D picture of the interval picture, including:

[0092] Select two interval pictures at adjacent rotation intervals of a first interval angle from the at least two interval pictures;

[0093] When there is an overlapping area between the two interval pictures, perform feature point matching processing on the overlapping area to obtain a target relative displacement between the two interval pictures;

[0094] Splice the two interval pictures using the target relative displacement to obtain a spliced picture;

[0095] Determine the depth image of the spliced picture according to the depth images of the two interval pictures;

[0096] Obtain the 3D picture according to the spliced picture and the depth image of the spliced picture.

[0097] In practical applications, the above-mentioned capturing module 21, scanning module 22 and mapping module 23 can be implemented by a processor on the cleaning robot, specifically, a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA) and the like.

[0098] Based on the foregoing embodiments, the embodiments of the present application provide a cleaning robot, Figure 3 As shown in FIG. 6, the embodiments of the present application provide a cleaning robot 300, which comprises: Figure 3

[0099] The processor 31 and the storage medium 32 storing executable instructions of the processor 31, the storage medium 32 performs operations in dependence on the processor 31 through the communication bus 33, when the instructions are executed by the processor 31, the mapping method in one or more of the foregoing embodiments is executed.

[0100] It should be noted that in practical applications, various components in the terminal are coupled together through the communication bus 33. It can be understood that the communication bus 33 is used to realize the connection and communication between the components. The communication bus 33 includes not only a data bus, but also a power bus, a control bus and a state signal bus. However, in order to clearly illustrate, all kinds of buses are marked as communication bus 33 in Figure 3 .

[0101] Based on the foregoing embodiments, the embodiments of the present application provide a computer storage medium, which stores one or more programs, the one or more programs can be executed by one or more processors to execute the mapping method provided by the embodiments of the present application.

[0102] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a hardware embodiment, a software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage and optical storage and the like) containing computer usable program code.

[0103] ​The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0104] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0105] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0106] The above merely provides a preferred embodiment of the present application, but not for limiting the present application.

Claims

1. A mapping method characterized by, The method is applied to a cleaning robot, and comprises: controlling the cleaning robot to rotate at a preset first interval angle, and capturing at least two interval pictures at rotation intervals of the first interval angle by a camera of the cleaning robot; controlling the cleaning robot to rotate at a preset second interval angle, and performing vertical scanning on an object image of the at least two interval pictures by a laser ranging sensor of the cleaning robot at rotation intervals of the second interval angle to obtain depth images of the at least two interval pictures; stitching the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures to obtain a 3D picture of the at least two interval pictures. The method further comprises: segmenting each interval picture of the at least two interval pictures according to a preset pixel size to obtain a sub-picture of each interval picture; redetermining depth images of the sub-pictures of each interval picture according to the depth images of each interval picture of the at least two interval pictures to obtain the depth images of the at least two interval pictures.

2. The method of claim 1, wherein, The redetermining of the depth images of the sub-pictures of each interval picture according to the depth images of each interval picture of the at least two interval pictures to obtain the depth images of the at least two interval pictures comprises: determining the depth images corresponding to the sub-pictures in each interval picture from the depth images of each interval picture; redetermining the depth images of the sub-pictures of each interval picture according to the depth images corresponding to the sub-pictures in each interval picture to obtain the depth images of the at least two interval pictures.

3. The method of claim 2, wherein, The redetermining of the depth images of the sub-pictures of each interval picture according to the depth images corresponding to the sub-pictures in each interval picture to obtain the depth images of the at least two interval pictures comprises: determining the mode of all distance values in the depth images corresponding to the sub-pictures in each interval picture; redetermining the depth images of the sub-pictures of each interval picture according to the mode to obtain the depth images of the at least two interval pictures.

4. The method of claim 3, wherein, The redetermining of the depth images of the sub-pictures of each interval picture according to the mode to obtain the depth images of the at least two interval pictures comprises: when the mode is one, determining the mode as a distance value in the depth images of the sub-pictures of each interval picture to obtain the depth images of the at least two interval pictures.

5. The method of claim 3, wherein, The redetermining of the depth images of the sub-pictures of each interval picture according to the mode to obtain the depth images of the at least two interval pictures comprises: when the mode is at least two, determining the minimum value in the mode as a distance value in the depth images of the sub-pictures of each interval picture to obtain the depth images of the at least two interval pictures.

6. The method of claim 1, wherein, The stitching of the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures to obtain a 3D picture of the interval pictures comprises: selecting two interval pictures at adjacent rotation intervals of the first interval angle from the at least two interval pictures; when there is an overlapping area between the two interval pictures, performing feature point matching processing on the overlapping area to obtain a target relative displacement between the two interval pictures; stitching the two interval pictures using the target relative displacement to obtain a stitched picture; determining a depth image of the stitched picture according to the depth images of the two interval pictures; obtaining the 3D picture according to the stitched picture and the depth image of the stitched picture.

7. A cleaning robot, characterized in that, comprising: a capturing module configured to control the cleaning robot to rotate at a preset first interval angle, and capture at least two interval pictures at rotation intervals of the first interval angle by a camera of the cleaning robot; a scanning module configured to control the cleaning robot to rotate at a preset second interval angle, and perform vertical scanning on an object image of the at least two interval pictures by a laser ranging sensor of the cleaning robot at rotation intervals of the second interval angle to obtain depth images of the at least two interval pictures; a mapping module configured to stitch the at least two interval pictures according to the at least two interval pictures and the depth images of the at least two interval pictures to obtain a 3D picture of the at least two interval pictures. The cleaning robot is further configured to: divide each interval picture of the at least two interval pictures according to a preset pixel size to obtain a sub-picture of each interval picture; re-determine the depth image of the sub-picture of each interval picture according to the depth image of each interval picture of the at least two interval pictures to obtain the depth images of the at least two interval pictures.

8. A cleaning robot, characterized in that, comprising: a processor and a storage medium having instructions executable by the processor, the storage medium performing operations in dependence on the processor via a communication bus, when the instructions are executed by the processor, performing the mapping method of any one of claims 1 to 6.

9. A computer storage medium, characterized in that a storage medium having executable instructions, when the executable instructions are executed by one or more processors, the processor performing the mapping method of any one of claims 1 to 6.

Images