Method and device for determining region boundaries
By combining the RTK base station with the GNSS positioning system of the smart terminal, using video and IMU data, intelligently identify the working area boundaries of outdoor intelligent robots, solving the problem of long time and low accuracy in the existing technology, and achieving more efficient and accurate boundary construction.
Patent Information
- Application Number
- CN202411052897.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-02
AI Technical Summary
When determining the boundaries of the working area, the traditional buried method is time-consuming and inaccurate. The artificial remote control method is limited by the robot's freedom of movement, making it difficult to complete arc movement quickly and efficiently, resulting in a long time to determine the boundary and accuracy. Low.
The GNSS positioning system of the smart terminal is combined with the GNSS positioning system. Through the mobile smart terminal, the location and attitude information are collected, keyframes and points of interest in the video are calculated, and the boundary position information is calculated to achieve more efficient and accurate boundary determination.
It shortens the boundary construction time, improves the accuracy and operation flexibility of boundary, reduces the difficulty and time of boundary determination, and improves the effect of tasks such as mowing.
Smart Images

Figure CN118608772B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of outdoor intelligent robots, and in particular to a method and device for determining area boundaries. Background Art
[0002] For outdoor intelligent robots, such as lawn mowers, determining their working area is a prerequisite for the mower to achieve autonomous mowing. The existing solutions are divided into the enclosure method and the manual remote control boundary determination method. In the traditional enclosure method, the mower needs to arrange wires at the boundary of the working area to determine the boundary of the mowing area. This method buries the wires underground according to the predetermined line, and the change of the wires requires digging out the wires and reburying them, which requires a lot of manpower. In the manual remote control boundary determination method, the new intelligent lawn mower is equipped with a GNSS (Global Navigation Satellite System) chip and uses RTK (Real-time kinematic) technology to locate the lawn mower. Before the lawn mower starts working, the lawn mower is manually controlled to determine the boundary of the working area based on the trajectory of the lawn mower.
[0003] The manual remote control method of determining boundaries is much more efficient than the traditional wire-laying solution. However, due to the chassis structure of the lawn mower, the lawn mower has limited freedom of movement. When controlled remotely, it can only perform a combination of linear motion and on-the-spot turning movements, and cannot complete arc motion. Therefore, it still takes a lot of time to manually determine the boundaries of the working area of the lawn mower, and it is difficult to obtain a more accurate boundary, which may result in mowing beyond the boundary or inability to level the working area, thus affecting the mowing effect. Summary of the invention
[0004] In view of the problems existing in the prior art, this application provides a solution for determining the regional boundary, which uses the GNSS positioning system of the RTK base station and the GNSS positioning system of the smart terminal to establish RTK between the smart terminal and the RTK base station, thereby converting the manual remote control of the outdoor smart robot (such as a lawn mower) to determine the working area boundary to the mobile smart terminal to establish the regional boundary. The solution of this application can shorten the time of constructing the regional boundary and improve the accuracy of constructing the regional boundary.
[0005] According to a first aspect of the present application, a method for determining a region boundary is provided, characterized by comprising:
[0006] Determining the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval;
[0007] Determine key frames in the video of the region boundary collected by the smart terminal;
[0008] When there is an interest point in the key frame, calculating the position information of the interest point in the key frame according to the position information and posture information of the smart terminal; and
[0009] The location information of the area boundary is determined according to the location information of the point of interest and / or the location information of the smart terminal.
[0010] According to a second aspect of the present application, a device for determining a region boundary is provided, characterized in that it includes:
[0011] A first determination module is used to determine the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval;
[0012] A second determination module is used to determine the key frame in the video of the area boundary collected by the smart terminal;
[0013] a calculation module, configured to calculate the position information of the point of interest in the key frame according to the position information and posture information of the smart terminal when there is a point of interest in the key frame; and
[0014] The third determination module is used to determine the location information of the area boundary according to the location information of the point of interest and / or the location information of the smart terminal.
[0015] According to a third aspect of the present application, there is provided an electronic device, comprising:
[0016] Processor; and
[0017] The memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program in the memory.
[0018] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.
[0019] According to the method and device for determining the regional boundary provided by the present application, the GNSS positioning system of the intelligent terminal is used to replace the GNSS positioning system carried by the outdoor intelligent robot itself, so as to achieve more efficient and flexible generation of the regional boundary, and the IMU data of the intelligent terminal and the video collected by the video acquisition device are integrated to intelligently identify the working area boundary of the outdoor intelligent robot, so that the final boundary is more accurate. In this way, the time for constructing the regional boundary can be shortened, the difficulty of constructing the regional boundary can be reduced, and the accuracy of constructing the regional boundary can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without exceeding the scope of protection required by the present application.
[0021] Figure 1 is a flowchart of a method for determining a region boundary according to an embodiment of the present application.
[0022] Figure 2 is a flowchart of a method for determining a region boundary according to another embodiment of the present application.
[0023] Figure 3 is a flowchart of a method for determining a region boundary according to yet another embodiment of the present application.
[0024] Figure 4 is a schematic diagram of a device for determining a region boundary according to an embodiment of the present application.
[0025] Figure 5 is a schematic diagram of a device for determining a region boundary according to another embodiment of the present application.
[0026] Figure 6 is a schematic diagram of a device for determining a region boundary according to yet another embodiment of the present application.
[0027] Figure 7 It is a structural diagram of an electronic device provided by this application. DETAILED DESCRIPTION
[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0029] Figure 1 FIG. 1 is a flow chart of a method for determining a region boundary according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps.
[0030] Step S101, determining the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval;
[0031] Step S102, determining a key frame in the video of the region boundary collected by the smart terminal;
[0032] Step S103, when there is an interest point in the key frame, calculating the position information of the interest point in the key frame according to the position information and posture information of the smart terminal; and
[0033] Step S104: determining the location information of the area boundary according to the location information of the point of interest and / or the location information of the smart terminal.
[0034] In the present application, the determined area boundary may be any outdoor boundary. For ease of understanding, the boundary of the working area of a lawn mower is taken as an example for explanation. Figure 1 The system used in the method shown includes a lawn mower base station, or RTK base station, and an intelligent terminal. The intelligent terminal can be any mobile or portable intelligent terminal, such as a smart phone, a tablet computer, etc. For ease of explanation, a smart phone is used as an example below.
[0035] According to some embodiments, in order to determine the location information and attitude information of a smartphone, the GNSS positioning system of the lawn mower base station, combined with the GNSS positioning system of the smartphone, establishes RTK between the smartphone and the lawn mower base station, thereby determining the location information of the smartphone; at the same time, combined with the IMU (Inertial Measurement Unit) of the smartphone, the attitude information of the smartphone is determined.
[0036] Specifically, first choose an open, unobstructed area without large mirror reflections to build an RTK base station. Use the antenna center of the RTK base station as the origin to establish an ENU (for example, the east direction is the positive direction of the X axis, the north direction is the positive direction of the Y axis, and the opposite direction of gravity is the positive direction of the Z axis) station center horizontal coordinate system. Then connect the smartphone to the RTK base station to obtain the GNSS observation values (including correction information) of the RTK base station, so as to achieve relative positioning between the smartphone and the RTK base station, thereby determining the position of the smartphone. Assume that the position coordinate sequence obtained when the handheld smartphone moves along the boundary of the working area is X i(i=0,1,2,… ), the coordinate sequence can be obtained according to the set sampling time interval, and the sampling time interval determines the density of the coordinate sequence. At the same time, the IMU measurement value is obtained to solve the mobile phone posture information when the handheld smartphone moves along the boundary of the working area. Assume that the posture sequence (including the roll angle, pitch angle and heading angle of the mobile phone) obtained when the handheld smartphone moves along the boundary of the working area is Ф j (j=0,1,2,… ).
[0037] Thus, step S101 specifically includes:
[0038] Determine the position information of the smart terminal by receiving correction information from an RTK base station communicating with the smart terminal; and
[0039] The posture information of the smart terminal is determined according to the measurement value of the IMU of the smart terminal.
[0040] According to some embodiments, when a smartphone moves along the boundary of a work area, the recording function of the smartphone is turned on, and the camera is aimed at the precise boundary of the work area, for example, the intersection of a fence and a lawn, the intersection of a road and a lawn, the intersection of a flower bed and a lawn, etc., to obtain a video related to the boundary of the area, and determine the key frame of the boundary of the work area in the video. In the process of determining the key frame, it is usually necessary to determine the feature points. Feature points refer to points in an image that have significant characteristics and are easy to detect and identify. They contain important information about the structure of the image and can be used to support various advanced visual tasks, such as image matching, target recognition, 3D reconstruction, motion tracking, etc.
[0041] The characteristics of feature points are:
[0042] Discrimination: Feature points should be highly discriminative so that they can be uniquely identified in different images, which is usually achieved by analyzing the intensity of pixels around the feature points.
[0043] Stability / repeatability: The same feature points should be detected stably under different image conditions (e.g. different viewing angles, lighting conditions, sizes, etc.).
[0044] Invariance: Ideal feature points have properties such as scale invariance, rotation invariance, and brightness change invariance, which means that these points can be accurately detected and matched no matter how the image is transformed (scaled, rotated, brightness adjusted, etc.).
[0045] Locality: Feature points usually represent local areas in an image, which makes them effective even when other parts of the image are occluded or deformed.
[0046] Based on the above characteristics, SIFT (Scale-invariant feature transform), SUFT, ORB and other computer vision technologies can be used to extract feature points of each frame in the video. Feature points are important indicators for selecting key frames. Extracting key frames can greatly reduce the workload of subsequent lawn edge point calculations.
[0047] After determining the feature points of each frame in the video, whether the current frame is a key frame can be determined based on whether the feature points in the current frame meet preset conditions. For example, when the distance and angle change between the position of the smartphone corresponding to the current frame and the previous key frame in the video reaches a first preset value (e.g., a minimum preset value), the number of feature points tracked by the current frame reaches a threshold and / or the number of feature points tracked by the current frame in the previous key frame is less than a set value (e.g., 90%), the current frame is determined to be a key frame.
[0048] Thus, step S102 may include:
[0049] Determine the feature points of each frame in the video by computer vision technology; and
[0050] In response to a feature point in a current frame satisfying a preset condition, the current frame is determined as a key frame associated with the region boundary.
[0051] In the process of making the above judgment based on the feature points of each frame in the video, a key frame may not be determined for a considerable period of time. In this regard, the present application sets a second preset value (e.g., a maximum preset value), and when the distance and angle change between the position of the smartphone corresponding to the current frame and the previous key frame in the video reaches the second preset value, the current frame is determined as a key frame related to the boundary of the area. The first preset value and the second preset value can be set as needed, and the present application does not impose any limitation on this.
[0052] Thus, step S102 may include:
[0053] In response to the distance and angle changes between the position of the smart terminal corresponding to the current frame and the previous key frame in the video reaching a preset value, the current frame is determined as a key frame.
[0054] After determining the keyframe, the next step is to determine the points of interest in the keyframe. Among them, the points of interest are points related to the edge of the area boundary. For the working boundary area of the lawn mower, the points of interest are the edge points of the lawn. Therefore, it is necessary to further extract the lawn edge points of interest from the keyframe, and the first thing is to find the boundary between the lawn and the non-lawn.
[0055] According to one embodiment, the present application adopts a color segmentation method to extract the boundary between lawn and non-lawn. First, the image of the video frame is converted from the RGB color space to the HSV color space which is more suitable for color segmentation. Then, in the HSV color space, the green area is extracted by adjusting the thresholds of hue (H) and saturation (S) to obtain a green boundary line. The pixel distance between all points of interest in the image and the edge of the lawn is evaluated, and those less than a certain threshold are classified as points of interest at the edge of the lawn, and their coordinates in the video frame image are recorded.
[0056] Then, the smartphone pose P (X i , Ф j ), if the pose of the smartphone cannot be found at the corresponding shooting time, the required pose can be obtained by interpolating the two adjacent poses.
[0057] After obtaining the image coordinates of the interest point and the corresponding smartphone pose at the time of shooting, the coordinates of the interest point can be calculated. For example, the coordinates of the boundary points of the working area can be calculated by multi-frame triangulation. In this way, the coordinates of the interest point in each key frame are calculated in turn to obtain the coordinates of multiple interest points, and the coordinate sequence S of the interest point is generated. k (k=0,1,2,…).
[0058] Thus, step S103 may include:
[0059] Determining the position coordinates and posture coordinates corresponding to the key frame in time from the position coordinate sequence and posture sequence of the smart terminal; and
[0060] The position coordinates of the interest point in the key frame are calculated according to the position coordinates and the posture coordinates.
[0061] After determining the location information and the location information of the point of interest obtained when the smartphone moves along the boundary of the working area, the location information of the smartphone or the point of interest is selected according to the specific situation, or the location information of the smartphone and the point of interest are fused to determine the location information of the boundary point of the area.
[0062] According to some embodiments, the determined key frame may or may not contain a point of interest (for example, when the boundary of the lawn is not clear). In the case where there is a point of interest in the key frame, if the difference between the position of the smartphone corresponding to the key frame in time and the position of the point of interest is greater than a set threshold, for example, the smartphone moves along the fence beside the lawn, and the smartphone and the boundary between the fence and the lawn are at a certain distance. In this case, the position of the smartphone is usually different from the actual edge of the lawn, then the position information of the region boundary is determined according to the position information of the point of interest. If the difference between the position of the smartphone corresponding to the key frame in time and the position of the point of interest is not greater than a set threshold, for example, the smartphone moves along the curb beside the lawn, and the smartphone and the fence can move on the curb. In this case, the position of the smartphone is usually not much different from the actual edge of the lawn, then the position information of the smartphone corresponding to the key frame in time and the position information of the point of interest are fused to determine the position information of the region boundary. According to some embodiments, various methods can be used to determine the position information of the region boundary. For example, the least squares method can be used to fit a straight line to the position information of the smartphone and the position information of the point of interest, and the points that meet the straight line fitting are selected as the region boundary position information. The threshold value may be set according to actual needs, and this application does not impose any limitation on this.
[0063] Thus, step S104 may include:
[0064] When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is greater than a set threshold, determining the position information of the region boundary according to the position information of the point of interest;
[0065] When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is less than or equal to the set threshold, the position information of the smart terminal corresponding to the key frame in time and the position information of the point of interest are fused to determine the position information of the area boundary.
[0066] The present application also provides a method for determining the region boundary, such as Figure 2 As shown. Figure 1 compared to, Figure 2 Step S201 and step S202 are Figure 1 Step S101 and step S102 are the same and will not be described in detail. The difference is that: Figure 2 The method shown also includes:
[0067] Step S203: when there is no point of interest in the key frame, determine the position information of the area boundary according to the position information of the smart terminal corresponding to the key frame in time.
[0068] According to some embodiments, the determined key frame may or may not contain a point of interest (for example, when the boundary of the lawn is not clear). When a point of interest exists in the key frame, the position information of the region boundary is determined in the above manner, and when a point of interest does not exist in the key frame, since there is no position information of the point of interest, the position information of the region boundary can only be determined by using the position information of the smartphone corresponding to the key frame in time.
[0069] The present application also provides a method for determining the region boundary, such as Figure 3 As shown. Figure 1 compared to, Figure 3 Steps S301 to S304 are Figure 1 Steps S101 to S104 are the same and will not be described in detail. The difference is that: Figure 3 The method shown also includes:
[0070] Step S305: Connect multiple position coordinates of the area boundary to generate the area boundary.
[0071] According to some embodiments, in the process of determining the location information of the region boundary based on the location information of the smartphone and / or the location information of the point of interest, since the location information of the smartphone and the location information of the point of interest are both coordinate sequences with certain intervals, the determined location information of the region boundary is also a coordinate sequence with certain intervals. In order to further determine the outline of the region boundary, the coordinate sequences of the region boundary are connected to generate a continuous region boundary.
[0072] According to another aspect of the present application, a device for determining a region boundary is provided. Figure 4 As shown, the device includes: a first determination module 401, a second determination module 402, a calculation module 403 and a third determination module 404, wherein the first determination module 401 is used to determine the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval; the second determination module 402 is used to determine the key frames in the video of the area boundary collected by the smart terminal; the calculation module 403 is used to determine the position information of the interest point in the key frame according to the position information and posture information of the smart terminal when there is an interest point in the key frame; the third determination module 404 is used to determine the position information of the area boundary according to the position information of the interest point and / or the position information of the smart terminal.
[0073] According to one embodiment, the first determining module 401 may be specifically configured to:
[0074] Determine the position information of the smart terminal by receiving correction information from an RTK base station communicating with the smart terminal; and
[0075] The posture information of the smart terminal is determined according to the measurement value of the IMU of the smart terminal.
[0076] According to one embodiment, the second determining module 402 may be specifically configured to:
[0077] Determine the feature points of each frame in the video by computer vision technology; and
[0078] In response to a feature point in the current frame satisfying a preset condition, the current frame is determined as a key frame associated with the region boundary.
[0079] According to another embodiment, the second determining module 402 may also be specifically configured to:
[0080] In response to the distance and angle changes between the position of the smart terminal corresponding to the current frame and the previous key frame in the video reaching a preset value, the current frame is determined as a key frame.
[0081] According to one embodiment, the calculation module 403 may be specifically configured to:
[0082] Determining the position coordinates and posture coordinates corresponding to the key frame in time from the position coordinate sequence and posture sequence of the smart terminal; and
[0083] The position coordinates of the interest point in the key frame are calculated according to the position coordinates and the posture coordinates.
[0084] According to one embodiment, the third determining module 404 may be specifically configured to:
[0085] When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is greater than a set threshold, determining the position information of the region boundary according to the position information of the point of interest;
[0086] When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is less than or equal to the set threshold, the position information of the smart terminal corresponding to the key frame in time and the position information of the point of interest are fused to determine the position information of the area boundary.
[0087] The present application also provides another device for determining the region boundary, such as Figure 5 As shown. Figure 4 compared to, Figure 5 Module 501 and module 502 are Figure 4 Module 401 and module 402 are the same and will not be described in detail. The difference is that: Figure 5 The device shown also includes:
[0088] The fourth determination module 503 is configured to determine the position information of the area boundary according to the position information of the smart terminal corresponding to the key frame in time when there is no point of interest in the key frame.
[0089] The present application also provides another device for determining the region boundary, such as Figure 6 As shown. Figure 4 compared to, Figure 6 Modules 601 to 604 and Figure 4 Modules 401 to 404 are the same and will not be described in detail. The difference is that: Figure 6 The device shown also includes:
[0090] The generating module 605 is used to connect the multiple position coordinates of the area boundary to generate the area boundary.
[0091] According to the method and device for determining the regional boundary provided by the present application, the GNSS positioning system of the intelligent terminal is used to replace the GNSS positioning system carried by the outdoor intelligent robot itself, so as to achieve more efficient and flexible generation of the regional boundary, and the IMU data of the intelligent terminal and the video collected by the video acquisition device are integrated to intelligently identify the working area boundary of the outdoor intelligent robot, so that the final boundary is more accurate. In this way, the time for constructing the regional boundary can be shortened, the difficulty of constructing the regional boundary can be reduced, and the accuracy of constructing the regional boundary can be improved.
[0092] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0093] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.
[0094] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical connection or other forms.
[0095] See also Figure 7 , Figure 7 An electronic device is provided, comprising a processor and a memory. The memory stores computer instructions, and when the computer instructions are executed by the processor, the processor executes the computer instructions to achieve the following Figures 1 to 3 The method and refinement scheme shown.
[0096] It should be understood that the above device embodiments are only illustrative, and the device disclosed in the present invention can also be implemented in other ways. For example, the division of units / modules described in the above embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.
[0097] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present invention may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.
[0098] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor or chip may be any appropriate hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the on-chip cache, off-chip memory, and storage may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory RRAM (Resistive Random Access Memory), dynamic random access memory DRAM (Dynamic Random Access Memory), static random access memory SRAM (Static Random-Access Memory), enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), high-bandwidth memory HBM (High-Bandwidth Memory), hybrid memory cube HMC (Hybrid Memory Cube), etc.
[0099] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer electronic device (which can be a personal computer, a server or a network electronic device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., various media that can store program codes.
[0100] The present application also provides a non-transitory computer storage medium storing a computer program. When the computer program is executed by a plurality of processors, the processors execute the following Figures 1 to 3 The method and refinement scheme shown.
[0101] The embodiments of the present application are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. At the same time, changes or deformations made by those skilled in the art based on the ideas of the present application, the specific implementation methods and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as a limitation on the present application.
Claims
1. A method for determining a region boundary, characterized in that: include: Determine the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval; Determine key frames in the video of the region boundary collected by the smart terminal; In the case where there is an interest point in the key frame, calculating the position information of the interest point in the key frame according to the position information and posture information of the smart terminal, wherein the interest point is a point related to the edge of the region boundary; Determining the location information of the area boundary according to the location information of the point of interest and / or the location information of the smart terminal; and In the case where there is no point of interest in the key frame, determining the position information of the region boundary according to the position information of the smart terminal corresponding to the key frame in time; Wherein, determining the location information of the area boundary according to the location of the point of interest and / or the location of the smart terminal includes: When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is greater than a set threshold, determining the position information of the region boundary according to the position information of the point of interest; When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is less than or equal to the set threshold, the position information of the smart terminal corresponding to the key frame in time and the position information of the point of interest are fused to determine the position information of the area boundary.
2. The method according to claim 1, characterized in that The determining of the location information and posture information of the intelligent terminal includes: Determine the position information of the smart terminal by receiving correction information from an RTK base station communicating with the smart terminal; and The posture information of the smart terminal is determined according to the measurement value of the IMU of the smart terminal.
3. The method according to claim 1, characterized in that The calculating the position information of the point of interest in the key frame according to the position information and posture information of the smart terminal includes: Determining the position coordinates and posture coordinates corresponding to the key frame in time from the position coordinate sequence and posture sequence of the smart terminal; and The position coordinates of the interest point in the key frame are calculated according to the position coordinates and the posture coordinates.
4. The method according to claim 1, characterized in that The determining of the key frame in the video of the area boundary collected by the smart terminal includes: Determine the feature points of each frame in the video by computer vision technology; and In response to a feature point in the current frame satisfying a preset condition, the current frame is determined as a key frame associated with the region boundary.
5. The method according to claim 1, characterized in that The determining of the key frame in the video of the area boundary collected by the smart terminal includes: In response to the distance and angle changes between the position of the smart terminal corresponding to the current frame and the previous key frame in the video reaching a preset value, the current frame is determined as a key frame.
6. The method according to any one of claims 1 to 5, characterized in that: The location information of the area boundary includes a plurality of location coordinates of the area boundary, and the method further includes: The plurality of position coordinates of the region boundary are connected to generate the region boundary.
7. A device for determining a region boundary, characterized in that: include: A first determination module is used to determine the position information and posture information of the smart terminal, wherein the smart terminal moves along the boundary of the area, and the position information and posture information of the smart terminal respectively include a position coordinate sequence and a posture sequence collected according to a set sampling time interval; A second determination module is used to determine the key frame in the video of the area boundary collected by the smart terminal; A calculation module, configured to calculate the position information of the point of interest in the key frame according to the position information and posture information of the smart terminal when there is a point of interest in the key frame, wherein the point of interest is a point related to the edge of the region boundary; A third determination module is used to determine the location information of the area boundary according to the location information of the point of interest and / or the location information of the smart terminal; and A fourth determination module, configured to determine the position information of the area boundary according to the position information of the smart terminal corresponding to the key frame in time when there is no point of interest in the key frame; Wherein, the third determination module is used for: When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is greater than a set threshold, determining the position information of the region boundary according to the position information of the point of interest; When the distance between the position of the smart terminal corresponding to the key frame in time and the position of the point of interest is less than or equal to the set threshold, the position information of the smart terminal corresponding to the key frame in time and the position information of the point of interest are fused to determine the position information of the area boundary.
8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program in the memory.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
