Electronic fence acquisition system, method and device and storage medium

Abstract

The embodiment of the invention provides an electronic fence acquisition system, method and device and a storage medium, the system comprises a positioning unit, a camera shooting unit, a motion unit and a control unit, the positioning unit and the camera shooting unit are carried on the motion unit, and the motion unit moves the positioning unit and the camera shooting unit to a target area; the positioning unit is configured to obtain positioning data of a target point; the camera unit is configured to collect a fence image and a target point image of a target area; the movement unit is configured to move to a target point based on the movement control instruction; the control unit is configured to determine a movement control instruction based on the fence image; determining whether the motion unit moves to the target point based on the target point image; in response to the movement unit moving to the target point, controlling the positioning unit to obtain positioning data of the target point; and determining coordinate information of the electronic fence based on the positioning data of the target point.

Description

Technical Field

[0001] This specification relates to the field of mobile control, and in particular to an electronic fence collection system, method, device and storage medium. Background Art

[0002] The emergence of shared vehicles (such as motorcycles, bicycles, and electric vehicles) has brought significant convenience to people's daily lives. Standardized parking is a fundamental requirement for shared vehicle management. For example, when parking a shared two-wheeled vehicle, it must be parked in a white parking frame on the roadside, known as a parking fence. The vehicle's position is compared to the nearest electronic fence. If it is within the electronic fence, the parking fence is successful; if not, the user is prompted to park properly.

[0003] Currently, geo-fence coordinate collection typically relies on personnel using high-precision coordinate collection equipment to capture the positions of the four corners of a white frame on the road surface and manually upload the data to a server. Multiple acquisitions are time-consuming and inefficient, while differences in standing habits can lead to errors. Furthermore, varying standards for determining the stability of the collection equipment make it difficult to ensure data consistency.

[0004] Therefore, it is necessary to provide an electronic fence collection system, method, device and storage medium that can form a complete automated electronic fence collection system, reduce data collection errors caused by human factors, and improve the collection efficiency of the electronic fence and the consistency of the collected data. Summary of the Invention

[0005] One or more embodiments of the present specification provide an electronic fence acquisition system, the system comprising: a positioning unit, a camera unit, a motion unit and a control unit, wherein the positioning unit and the camera unit are mounted on the motion unit, and the motion unit moves the positioning unit and the camera unit to a target area; the positioning unit is configured to obtain positioning data of a target point; the camera unit is configured to collect a fence image and a target point image of the target area; the motion unit is configured to move to the target point based on a movement control instruction; the control unit is configured to: determine the movement control instruction based on the fence image; determine whether the motion unit moves to the target point based on the target point image; control the positioning unit to obtain the positioning data of the target point in response to the motion unit moving to the target point; and determine the coordinate information of the electronic fence based on the positioning data of the target point.

[0006] One or more embodiments of the present specification provide an electronic fence acquisition method, the method comprising: acquiring a fence image of a target area; determining a movement control instruction based on the fence image; moving to the target point based on the movement control instruction; acquiring an image of the target point; determining whether to move to the target point based on the target point image; in response to moving to the target point, acquiring the positioning data of the target point; and determining the coordinate information of the electronic fence based on the positioning data of the target point.

[0007] One or more embodiments of this specification provide an electronic fence collection device, characterized in that the device includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement the electronic fence collection method.

[0008] One or more embodiments of this specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions, the computer executes the electronic fence collection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0010] Figure 1 is an exemplary module diagram of an electronic fence data collection system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of an electronic fence collection method according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart for determining positioning data of a target point according to some embodiments of this specification;

[0013] Figure 4 is an exemplary flow chart of collecting coordinate information of an electronic fence according to some embodiments of this specification;

[0014] Figure 5 is an exemplary schematic diagram of determining the working time of a cleaning component according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0017] Unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0018] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 is an exemplary module diagram of an electronic fence collection system according to some embodiments of this specification. In some embodiments, Figure 1 As shown, the electronic fence acquisition system 100 may include a positioning unit 110 , a camera unit 120 , a motion unit 130 and a control unit 140 .

[0020] The positioning unit 110 refers to a device with a high-precision positioning function, such as a high-precision GPS locator. In some embodiments, the positioning unit 110 can be configured to obtain positioning data of a target point.

[0021] The imaging unit 120 refers to a device having an image acquisition function, such as a camera. In some embodiments, the imaging unit 120 can be configured to acquire fence images and target point images of a target area.

[0022] The motion unit 130 refers to a device with a mobile function, such as a small unmanned vehicle, a drone, etc. In some embodiments, the motion unit 130 can be configured to move to a target point based on a mobile control instruction.

[0023] In some embodiments, the positioning unit and the camera unit are mounted on a motion unit, and the motion unit moves the positioning unit and the camera unit to a target area.

[0024] The control unit 140 is a device with computing capabilities that can receive, process, and respond to instructions. The control unit 140 can be used to manage resources and process data and / or information from at least one component of the system or an external data source (e.g., a cloud data center).

[0025] In some embodiments, the control unit 140 may include a processor. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core processing device). By way of example only, the processor may include a central processing unit (CPU), a microcontroller unit (MCU), a digital signal processor (DSP), or any combination thereof.

[0026] In some embodiments, the control unit 140 may further include a storage device. In some embodiments, the storage device may store data and / or information processed by the control unit 140. For example, the storage device may store positioning data, coordinate information, fence images, etc. In some embodiments, the storage device may include random access memory (RAM), read-only memory (ROM), mass storage, removable memory, volatile read-write memory, etc., or any combination thereof.

[0027] In some embodiments, the control unit 140 may be mounted on the motion unit 130 or integrated on a remote server.

[0028] In some embodiments, the control unit 140 can be configured to determine a movement control instruction based on the fence image; determine whether the motion unit moves to the target point based on the target point image; control the positioning unit to obtain the positioning data of the target point in response to the motion unit moving to the target point; and determine the coordinate information of the electronic fence based on the positioning data of the target point.

[0029] In some embodiments, the control unit 140 can be further configured to control the positioning unit to obtain first positioning data of the target point; determine whether the first positioning data meets the preset accuracy condition; and in response to the first positioning data meeting the preset accuracy condition, determine the first positioning data as positioning data.

[0030] In some embodiments, the control unit 140 can be further configured to, in response to the first positioning data not satisfying the preset accuracy condition, determine whether the data collection time corresponding to the target point satisfies the preset time condition; in response to the data collection time satisfying the preset time condition, select the first positioning data that satisfies the preset selection condition from the acquired first positioning data as the positioning data; in response to the data collection time not satisfying the preset time condition, control the positioning unit to re-acquire the first positioning data of the target point, and repeat the judgment process until the positioning data is determined.

[0031] In some embodiments, the control unit 140 may be further configured to control the positioning unit to obtain a positioning data sequence of the target point; and determine the positioning data based on the positioning accuracy of the second positioning data in the positioning data sequence.

[0032] In some embodiments, the control unit 140 can be further configured to determine candidate fence information based on the candidate fence image captured by the camera unit; determine whether the candidate fence information meets the preset fence conditions; and determine that the candidate fence image is a fence image in response to the candidate fence information meeting the preset fence conditions.

[0033] In some embodiments, the electronic fence acquisition system 100 may further include a communication component 150 .

[0034] The communication component 150 refers to a component used for data transmission and information exchange, such as a cable network, an optical fiber network, the Internet, a wireless local area network (WLAN), near field communication (NFC), an internal line of a device, etc., or any combination thereof.

[0035] In some embodiments, the motion unit 130 may include a first motion unit and a second motion unit.

[0036] The first motion unit refers to a motion unit that moves on the ground, for example, a small unmanned vehicle. The second motion unit refers to a motion unit that moves in the air, for example, a drone.

[0037] In some embodiments, the second motion unit has a higher working height than the first motion unit. The working height refers to the height of the motion unit from the horizontal plane when the motion unit is operating. For example, the working height of the first motion unit may be 0 meters, and the working height of the second motion unit may be 3 meters, 5 meters, etc.

[0038] In some embodiments, the first positioning unit and the first camera unit may be mounted on the first motion unit, and the second positioning unit and the second camera unit may be mounted on the second motion unit. For example, the first positioning unit and the first camera unit may be respectively a high-precision GPS locator and a camera mounted on the first motion unit, and the second positioning unit and the second camera unit may be respectively a high-precision GPS locator and a camera mounted on the second motion unit.

[0039] In some embodiments, the second camera unit may be configured to acquire a second fence image.

[0040] In some embodiments, the control unit 140 is communicatively connected to the first motion unit, the first positioning unit, the first camera unit, the second motion unit, the second positioning unit, and the second camera unit through the communication component 150 .

[0041] In some embodiments, the control unit 140 may be further configured to determine a first motion parameter of the first motion unit based on the second fence image; and determine a movement control instruction of the first motion unit based on the first motion parameter. For more information on this part, please refer to Figure 2 Related description.

[0042] In some embodiments, the first camera unit may be configured to acquire a first fence image.

[0043] In some embodiments, the electronic fence acquisition system 100 may further include a cleaning component 160 .

[0044] The cleaning component 160 refers to a device with a cleaning function, such as a cleaning brush. In some embodiments, the cleaning component can be used to clean debris on the ground, such as leaves, garbage, dust, snow, etc. covering the fence area.

[0045] In some embodiments, the control unit 140 may be further configured to determine whether to turn on the cleaning component and the working time of the cleaning component based on the first fence image.

[0046] For more information about the positioning unit 110, the camera unit 120, the motion unit 130, the control unit 140, the communication component 150 and the cleaning component 160, see Figure 2-Figure 5 and its related descriptions.

[0047] It should be noted that the above description of the electronic fence collection system 100 and its modules is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principle of the device, may arbitrarily combine the modules or form sub-devices connected to other modules without deviating from the principle. In some embodiments, Figure 1The positioning unit 110, camera unit 120, motion unit 130, control unit 140, communication component 150, and cleaning component 160 disclosed herein may be different modules within a single system, or a single module may implement the functions of two or more of the aforementioned modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0048] Figure 2 is an exemplary flow chart of the electronic fence collection method according to some embodiments of this specification. In some embodiments, process 200 can be executed by the electronic fence collection system 100. Figure 2 As shown, the process 200 includes the following steps.

[0049] Step 210 , obtaining a fence image of the target area. In some embodiments, step 210 may be performed by the control unit 140 .

[0050] The target area is the area where the geo-fence coordinates are to be collected. For example, an area with a parking frame for a shared two-wheeled vehicle drawn on the ground.

[0051] The electronic fence refers to a virtual parking frame for shared vehicles. If the shared vehicle is within the electronic fence, parking is successful. If the shared vehicle is not within the electronic fence, parking is unsuccessful. In some embodiments, depending on the situation, the electronic fence can include various shapes and sizes. For example, a rectangle of 1.5m*10m, a circle with a radius of 5m, or irregular shapes of various sizes. In this specification, the electronic fence refers to a virtual parking frame for shared two-wheeled vehicles, so the electronic fence is described as a rectangular frame.

[0052] The fence image refers to the image containing the ground parking frame in the target area.

[0053] In some embodiments, the fence image can be obtained in a variety of ways. For example, a worker places the motion unit in a parking frame, a camera unit captures the fence image, and the control unit obtains the fence image of the target area from the camera unit via a communication component.

[0054] In some embodiments, the control unit can determine candidate fence information based on the candidate fence image captured by the camera unit; determine whether the candidate fence information meets the preset fence conditions; and determine that the candidate fence image is a fence image in response to the candidate fence information meeting the preset fence conditions.

[0055] The candidate fence image refers to a candidate image used to determine the fence image. In some embodiments, the candidate fence image can be all initial images captured by the camera unit.

[0056] Candidate fence information refers to fence-related information in the candidate fence image. For example, candidate fence information may include fence shape, fence color, fence size, etc. The fence refers to the shared two-wheeled vehicle parking frame drawn on the ground by government staff.

[0057] In some embodiments, the control unit may determine the candidate fence information based on the candidate fence image through various methods, such as image recognition technology (e.g., image recognition model), feature extraction (e.g., edge detection algorithm), etc. For example, the control unit may output the candidate fence information based on the candidate fence image through an image recognition model.

[0058] The preset fence conditions refer to the conditions that must be met by the candidate fence information for determining whether the candidate fence image is a fence image. In some embodiments, the preset fence conditions can be manually preset or set by the system default. For example, the preset fence conditions may include a fence shape of a rectangle, a fence area of 15m 2 ~30m 2 , the fence color is white, etc.

[0059] In some embodiments, the control unit can determine whether the candidate fence information satisfies a preset fence condition. In response to the candidate fence information satisfying the preset fence condition, the control unit can determine the candidate fence image as a fence image in a variety of ways. For example, all candidate fence images whose candidate fence information satisfies the preset fence condition are determined as fence images. For another example, from the candidate fence images whose candidate fence information satisfies the preset fence condition, the fence image with the fence area closest to the preset value (e.g., 20m2) is selected. 2 ) are fence images. The value of N is preset manually or by the system (e.g., N≤3).

[0060] In some embodiments of the present specification, candidate fence information is determined based on candidate fence images, and a fence image is determined from the candidate fence images based on whether the candidate fence information meets preset fence conditions. This can avoid erroneous collection of fence images (for example, misjudging a car parking space as a parking frame corresponding to an electronic fence), which is conducive to ensuring the effective implementation of electronic fence coordinate collection.

[0061] Step 220 : Determine a movement control instruction based on the fence image. In some embodiments, step 220 may be performed by the control unit 140 .

[0062] A movement control instruction is an instruction used to control the movement of a motion unit. A movement control instruction can be expressed as a sentence, a prompt word, or a paragraph. For example, a movement control instruction could be "Please move 5 meters southeast at a speed of 0.1 m / s."

[0063] In some embodiments, the control unit can determine the movement control instruction based on the fence image through various methods. For example, the control unit can search a first historical database to obtain the historical fence image with the highest image similarity to the fence image, and determine the historical movement control instruction corresponding to the historical fence image as the movement control instruction. The first historical database can be constructed based on a large number of historical fence images and corresponding historical movement control instructions. In some embodiments, the control unit can determine image similarity through various methods, such as the Structural Similarity algorithm (SSIM) and the Perceptual Hash algorithm (PHash).

[0064] In some embodiments, the control unit may determine a first motion parameter of the first motion unit based on the second fence image; and determine a movement control instruction of the first motion unit based on the first motion parameter.

[0065] The second fence image refers to a fence image captured by a second camera unit, for example, a fence image captured by a camera mounted on a drone.

[0066] The first motion parameter refers to parameters related to the movement of the first motion unit. For example, the movement speed, movement direction, and movement distance of the first motion unit, and the image acquisition frequency of the first motion unit (first camera unit). The image acquisition frequency refers to the frequency at which the first camera unit captures images, for example, once per second.

[0067] In some embodiments, the control unit can determine the first motion parameter based on the second fence image using various methods. For example, the control unit can determine the first motion parameter based on the second fence image using existing line-following technology (a process including: HSV data conversion - binarization - edge contour processing - perspective transformation - frame line processing - frame line following).

[0068] In some embodiments, the control unit may determine a capture difficulty of the fence area based on the second fence image; and adjust the first motion parameter based on the capture difficulty.

[0069] A fenced area refers to an area that includes a partial fence. In some embodiments, the fenced area can be divided by a control unit or technician based on preset rules. For example, the preset rule can be that different fenced areas include different frame lines and corner points (vertices) of the parking frame. For example, the fenced area corresponding to a rectangular parking frame can be an area that includes four corner points, and the frame lines included in the four fenced areas can constitute the entire parking frame.

[0070] The difficulty of acquisition refers to the degree of difficulty in performing the acquisition work. In some embodiments, the difficulty of acquisition can be represented by the difficulty of identifying the parking frame. Due to problems such as the parking frame line color becoming faded, part of the frame line being missing, and the frame line being covered by debris, the motion unit may have different degrees of acquisition difficulty when performing line acquisition in different fenced areas. In some embodiments, the acquisition difficulty can be represented by a numerical value (e.g., a numerical value in the range of 0-10). The larger the numerical value, the greater the acquisition difficulty.

[0071] In some embodiments, the control unit can determine the acquisition difficulty of the fenced area based on the second fence image using various methods. For example, the control unit can use a no-reference image quality assessment method (e.g., a blind / referenceless image spatial quality evaluator (BRISQUE)) based on the second fence image to determine the image quality of images corresponding to different fenced areas and determine the acquisition difficulty based on the image quality. The lower the image quality, the greater the acquisition difficulty.

[0072] In some embodiments, the control unit may determine the contrast of the fence area based on the second fence image through a contrast evaluation layer of a duration model; and determine the acquisition difficulty based on the contrast.

[0073] Contrast refers to the degree of blurriness of the parking frame within the fenced area. In some embodiments, contrast can refer to the degree of similarity between the parking frame within the fenced area and a standard parking frame. A standard parking frame refers to a complete and clear parking frame. In some embodiments, contrast can be expressed as a percentage, such as 50% or 80%. The lower the contrast, the lower the degree of similarity and the higher the blurriness.

[0074] In some embodiments, the control unit can input the second fence image and the second standard image into the contrast evaluation layer of the duration model and output the contrast of the fence area. For more information about the duration model, see Figure 5 Related description.

[0075] In some embodiments, the control unit may determine the acquisition difficulty by searching a preset relationship table including a correspondence between contrast and acquisition difficulty. The preset relationship table may be pre-constructed by a technician based on experience. The correspondence may be such that the lower the contrast, the greater the acquisition difficulty.

[0076] In some embodiments of the present specification, based on the second fence image, the model can quickly and accurately determine the contrast of the fence area, and then accurately determine the acquisition difficulty of the fence area, which is conducive to the subsequent targeted and reasonable adjustment of the motion parameters of the motion unit.

[0077] In some embodiments, the control unit can adjust the first motion parameter in a variety of ways based on the acquisition difficulty. For example, the control unit can cluster the historical acquisition difficulty and the historical first motion parameter (including the historical movement speed and the historical image acquisition frequency) in the historical data to determine multiple cluster centers. A cluster center may include a center acquisition difficulty, a center movement speed, and a center image acquisition frequency. The control unit can calculate the similarity between the current acquisition difficulty and each center acquisition difficulty, and adjust the first motion parameter according to the center acquisition difficulty with the highest similarity, the corresponding center movement speed, and the center image acquisition frequency.

[0078] Clustering methods include, but are not limited to, K-means clustering and mean-shift clustering. Similarity calculation methods include, but are not limited to, Euclidean distance and cosine similarity. The highest similarity is achieved when the Euclidean distance is the smallest and the cosine similarity is the largest.

[0079] In some embodiments of the present specification, based on the second fence image, the difficulty of collecting data in different fence areas is evaluated, and full consideration is given to the differences in the difficulty of line patrol and collection work of the motion unit due to differences in different fence areas (differences in wireframe color depth, integrity, debris coverage, etc.). Further, according to different collection difficulties, the first motion parameters are appropriately adjusted to make the first motion parameters more reasonable, which is conducive to improving the accuracy of line patrol and ensuring the smooth progress of subsequent coordinate collection work.

[0080] In some embodiments, the control unit may determine a plurality of fences based on the second fence image; and determine a first motion parameter of the first motion unit based on the rough position coordinates of the plurality of fences.

[0081] In some embodiments, the control unit may determine the presence of multiple fences within the target area based on the second fence image using various methods. For example, the control unit may determine the presence of multiple fences based on the second fence image using an image recognition algorithm.

[0082] Coarse position coordinates are coordinates that can represent the approximate positions of the corner points of the fence. In some embodiments, the coarse position coordinates can be represented by coordinates in a camera coordinate system or an image coordinate system. For example, an image coordinate system is established with the center of the second fence image as the origin and any two mutually perpendicular rays as the X-axis and Y-axis. The coordinates in this image coordinate system are the coarse position coordinates.

[0083] In some embodiments, the control unit may determine the corner points of the first motion unit and the plurality of fences based on the second fence image through an image recognition algorithm, and further determine the rough position coordinates in the image coordinate system.

[0084] In some embodiments, the control unit can determine the two closest corner points (marked as feature points) between two adjacent fences based on the rough position coordinates of each corner point of the multiple fences, select the fence closest to the first motion unit as the starting fence, use the feature point of the starting fence as the last corner point collected in the starting fence, use the feature point of the second fence adjacent to the starting fence as the first corner point collected in the second fence, and continue in this order until all corner points of the multiple fences are traversed. The control unit can determine the first motion parameters (including movement distance and movement direction) of the first motion unit based on the rough position coordinates of the first motion unit and each corner point, as well as the traversal path of the corner points.

[0085] In some embodiments of the present specification, when it is determined that there are multiple fences in the target area based on the second fence image, the first motion parameter of the first motion unit can be completely determined based on the rough position coordinates of the multiple fences, which is conducive to the continuous coordinate acquisition of multiple electronic fences, making the applicability of the acquisition system more comprehensive.

[0086] In some embodiments, the control unit can input the first motion parameter into the instruction template to automatically generate a movement control instruction. The instruction template can be preset in advance by a technician. For example, the instruction template can be "Please move forward at A (moving speed) to B (moving direction) by C (moving distance), and capture images at a frequency of D (image acquisition frequency)". Then, when the first motion parameter includes a moving speed of 0.1m / s, a moving direction of straight ahead, a moving distance of 2 meters, and an image acquisition frequency of once per second, the movement control instruction is "Please move forward 2 meters straight ahead at a speed of 0.1m / s, and capture images at a frequency of once per second".

[0087] In some embodiments of the present specification, combining ground and aerial acquisition devices makes the acquired data more comprehensive, which is beneficial to improving the adaptability of the acquisition system; based on the global second fence image, the first motion parameters of the first motion unit can be quickly determined; according to the first motion parameters, the movement control instructions of the first motion unit can be accurately determined to ensure the line patrol accuracy of the first motion unit, which is beneficial to realize automated coordinate acquisition.

[0088] In step 230 , the device moves to the target point based on the movement control instruction. In some embodiments, step 230 may be performed by the movement unit 130 .

[0089] The target point refers to the point where coordinate collection is required. In some embodiments, the target point can refer to the corner point of a fence, i.e., the corner point of a rectangular parking frame.

[0090] In some embodiments, the motion unit may move based on a motion control instruction and move to a target point to collect coordinates of the target point.

[0091] Step 240 , acquiring a target point image. In some embodiments, step 240 may be performed by the imaging unit 120 .

[0092] The target point image refers to the image captured by the camera unit when the motion unit moves to the target point.

[0093] In step 250 , based on the target point image, determine whether to move to the target point. In some embodiments, step 250 may be performed by the control unit 140 .

[0094] In some embodiments, the control unit may acquire the target point image from the camera unit through the communication component.

[0095] In some embodiments, the control unit can determine whether the motion unit has moved to the target point based on the target point image in a variety of ways. For example, the control unit can use image recognition technology to determine whether the target point image contains an intersecting line. If an intersecting line is contained and the angle of the intersecting line is a preset angle (e.g., 90°), the motion unit has moved to the target point. For another example, the control unit can use the distance measurement principle to determine the distance between the second motion unit and the target point based on the target point image. If the distance is equal to the working height of the second motion unit (the flight height of the drone), it is determined that the second motion unit has moved to the target point.

[0096] Step 260 : In response to moving to the target point, obtaining positioning data of the target point. In some embodiments, step 260 may be performed by the control unit 140 .

[0097] Positioning data refers to the final positioning information that can accurately represent the position of the target point. For example, the relatively accurate position coordinates of the target point in the world coordinate system determined after screening and judgment. Among them, the world coordinate system refers to an absolute coordinate system that is fixed and unchanged after being specified. In some embodiments, the world coordinate system can be a three-dimensional coordinate system and / or a plane coordinate system. For example, the world coordinate system can be a Universal Transverse Mercator (UTM) coordinate system, a geocentric inertial coordinate system, a World Geodetic System-84 (WGS-84), etc.

[0098] In some embodiments, the control unit can obtain positioning data of the target point in a variety of ways in response to the motion unit moving to the target point. For example, the control unit can determine the average value (e.g., average coordinates) of two consecutive positioning data obtained, where the difference in positioning data does not exceed a fluctuation threshold, as the positioning data. The difference in positioning data refers to the absolute value of the difference between two consecutive positioning data obtained. For example, the coordinate distance between two position coordinates. The fluctuation threshold can be pre-set by a technician or set by the system by default. For example, 0.5 meters, etc.

[0099] For example, the first three acquired positioning data are X1, X2, and X3, respectively, where the difference between X1 and X2, and the difference between X2 and X3 both exceed the fluctuation threshold. The fourth acquired positioning data is X4, and the difference between X3 and X4 does not exceed the fluctuation threshold. The positioning data is the average value of X3 and X4.

[0100] In some embodiments, the control unit can control the positioning unit to obtain the first positioning data of the target point, and determine the first positioning data that meets the preset accuracy condition as the positioning data. For more information about this part, please refer to Figure 3 Related description.

[0101] In some embodiments, the control unit may control the positioning unit to obtain a positioning data sequence of the target point; and determine the positioning data based on the positioning accuracy of the second positioning data in the positioning data sequence. For more information on this part, please refer to the relevant description below.

[0102] Step 270 : Determine the coordinate information of the electronic fence based on the positioning data of the target point. In some embodiments, step 270 may be performed by the control unit 140 .

[0103] Coordinate information refers to information related to the coordinates of the location of the electronic fence. In some embodiments, the coordinate information of the electronic fence can be represented by a combination of positioning data of multiple target points. For example, [W1, W2, W3, W4], where W1, W2, W3, and W4 represent four target points (i.e., the four corner points of the fence).

[0104] In some embodiments, the control unit can determine the coordinate information of the electronic fence in a variety of ways based on the positioning data of the target points. For example, the control unit can control the positioning unit to obtain the positioning data of all target points, and determine the combination of the positioning data of all target points in a parking frame as the coordinate information of the electronic fence corresponding to the parking frame. For another example, the control unit can control the positioning unit to obtain the positioning data of some target points (such as the positioning data of 3 target points in a parking frame), calculate the positioning data of the remaining target points (such as, based on the rectangular structure, infer the positioning data of the remaining 1 target point), and determine the combination of the positioning data as the coordinate information.

[0105] In some embodiments of the present specification, by acquiring a fence image of the target area, determining a movement control instruction, and controlling the motion unit to move to the target point, and then acquiring an image of the target point, determining whether the motion unit has moved to the target point, and when it moves to the target point, acquiring the positioning data of the target point, and then determining the coordinate information of the electronic fence, the above method is used to realize automated coordinate collection, which can save manpower and material resources, improve collection efficiency, and avoid collection errors caused by human factors (such as differences in data collection accuracy due to personal standing habits and heights, and differences in consistency of collected data due to different standards for personal judgment of whether the positioning of the collection equipment is stable), thereby improving the accuracy and consistency of the collected data.

[0106] It should be noted that the above description of process 200 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and variations to process 200 under the guidance of this specification. However, such modifications and variations are still within the scope of this specification.

[0107] Figure 3 FIG. 1 is an exemplary flow chart of determining the positioning data of a target point according to some embodiments of this specification. Figure 3 As shown, process 300 may include the following steps. In some embodiments, Figure 3 The process 300 shown may be executed by the control unit 140 .

[0108] Step 310: Control the positioning unit to obtain first positioning data of the target point.

[0109] First positioning data refers to positioning information acquired by a positioning unit in a single instance that can preliminarily characterize the location of a target point. In some embodiments, the control unit can control the positioning unit to acquire the first positioning data of the target point. For example, the first positioning data can be location coordinates directly acquired by a high-precision GPS locator.

[0110] Step 320: Determine whether the first positioning data meets a preset accuracy condition.

[0111] The preset accuracy condition refers to a condition regarding positioning accuracy for determining the first positioning data as positioning data. In some embodiments, the preset accuracy condition is that the positioning accuracy of the first positioning data reaches a standard accuracy.

[0112] Positioning accuracy refers to the accuracy with which a positioning system measures spatial position. The positioning accuracy of the first positioning data can represent the difference between the first positioning data obtained by the positioning unit and the actual position (theoretical position). The higher the positioning accuracy, the smaller the difference.

[0113] In some embodiments, the positioning accuracy can be represented by a numerical value (e.g., an integer value from 0 to 5). Each numerical value represents a different range of difference. For example, a positioning accuracy of 0, 1, 2, 3, 4, or 5 can respectively represent that the difference between the first positioning data and the true position is greater than 10 meters, the difference is 5 to 10 meters, the difference is 3 to 5 meters, the difference is 1 to 3 meters, the difference is 0.5 to 1 meter, and the difference is less than 0.5 meters. The larger the numerical value, the higher the corresponding positioning accuracy, and the closer the first positioning data is to the true position.

[0114] In some embodiments, the control unit may determine the positioning accuracy of the first positioning data in a variety of ways. For example, the positioning accuracy of the first positioning data may be determined using an existing algorithm (e.g., a GNSS (Global Navigation Satellite System) accuracy measurement method). Another example is evaluating the positioning accuracy using a self-designed machine learning algorithm.

[0115] Standard accuracy refers to a relatively high, ideal positioning accuracy. In some embodiments, the standard accuracy can be pre-set by a technician based on needs or experience, or set by the system by default. For example, the standard accuracy can be 5 (corresponding to a difference of less than 0.5 meters between the first positioning data and the actual position).

[0116] In some embodiments, the control unit may determine whether the first positioning data meets the preset accuracy condition in a variety of ways. For example, the positioning accuracy of the first positioning data may be compared with a standard accuracy. If the positioning accuracy of the first positioning data meets the standard accuracy (e.g., the positioning accuracy is equal to 5), the first positioning data meets the preset accuracy condition; if the positioning accuracy does not meet the standard accuracy (e.g., the positioning accuracy is less than 5), the first positioning data does not meet the preset accuracy condition.

[0117] Step 330: Determine the first positioning data as positioning data.

[0118] In some embodiments, in response to the first positioning data satisfying a preset accuracy condition, the control unit may execute step 330 .

[0119] In some embodiments of the present specification, by obtaining the first positioning data of the target point and determining whether the first positioning data meets the preset accuracy conditions, the first positioning data that meets the preset accuracy conditions is determined as the positioning data, giving priority to the positioning accuracy issue, which is conducive to ensuring the high precision requirements of the positioning data and making the determination of the coordinate information of the electronic fence more accurate.

[0120] In some embodiments, in response to the first positioning data not meeting the preset accuracy condition, the control unit may determine the positioning data in a variety of ways. For example, the control unit may repeatedly acquire the first positioning data of the target point until the first positioning data meets the preset accuracy condition, and determine the first positioning data as the positioning data. For another example, the control unit may repeatedly acquire the first positioning data of the target point until the number of repetitions reaches a preset threshold (e.g., 10 times), and determine the average of the first positioning data acquired multiple times as the positioning data.

[0121] Step 340: Determine whether the data collection time corresponding to the target point meets the preset time condition.

[0122] In some embodiments, in response to the first positioning data not meeting the preset accuracy condition, the control unit may execute step 340 .

[0123] The data collection time refers to the time it takes to collect data at a target point. In some embodiments, the data collection time can be represented by the time from the moment when the initial collection starts at the current target point to the current moment.

[0124] The preset time condition refers to a preset condition regarding the data collection time. In some embodiments, the preset time condition is that the data collection time reaches a standard time.

[0125] The standard time refers to the maximum duration for which data can be collected at a target point. In some embodiments, the standard time can be pre-set by a technician based on actual conditions or experience, or set by the system by default. For example, 1 minute, 2 minutes, etc.

[0126] In some embodiments, the data collection time reaching the standard time may mean that the data collection time has reached a maximum value, that is, data collection is no longer continued at the target point.

[0127] In some embodiments, the control unit can determine whether the data collection time corresponding to the target point meets the preset time condition in various ways. For example, the data collection time corresponding to the target point can be compared with the standard time. If the data collection time reaches the standard time, the data collection time meets the preset time condition.

[0128] Step 350 : Selecting first positioning data that meets a preset selection condition from the acquired first positioning data as positioning data.

[0129] In some embodiments, in response to the data collection time meeting a preset time condition, the control unit may execute step 350 .

[0130] In some embodiments, when a target point is first collected, the first positioning data obtained can refer to the first positioning data of the target point obtained by the positioning unit for the first time; when a target point has been collected multiple times, the first positioning data obtained can refer to all the first positioning data of the target point obtained multiple times by the positioning unit.

[0131] The preset selection condition refers to a preset condition for filtering the acquired first positioning data. In some embodiments, the preset selection condition can be pre-set by a technician. For example, the preset selection condition can be that the first positioning data with the highest positioning accuracy is the positioning data. For another example, the preset selection condition can be that the average of the M first positioning data with the highest positioning accuracy is the positioning data. The value of M can be manually preset or set by system default. For example, M = 2.

[0132] Step 360: Control the positioning unit to reacquire the first positioning data of the target point and repeat the determination process until the positioning data is determined.

[0133] In some embodiments, in response to the data collection time not meeting the preset time condition, the control unit may execute step 360 .

[0134] In some embodiments, the determination process may include determining whether the first positioning data meets a preset accuracy condition and determining whether the data collection time corresponding to the target point meets a preset time condition.

[0135] In some embodiments, repeating the determination process may refer to repeatedly executing steps 320 - 350 based on the newly acquired first positioning data.

[0136] In some embodiments, steps 320-350 are repeatedly performed multiple times until the first positioning data meets the preset accuracy condition, and the first positioning data is determined as the positioning data; or when the first positioning data does not meet the preset accuracy condition, the data collection time corresponding to the target point has met the preset time condition, then the first positioning data that meets the preset selection condition is selected as the positioning data from the multiple first positioning data corresponding to the multiple repeated acquisitions.

[0137] In some embodiments of the present specification, when the first positioning data does not meet the preset accuracy conditions, the first positioning data is determined based on whether the data collection time corresponding to the target point meets the preset time conditions. By comprehensively considering both positioning accuracy and collection time, low collection efficiency caused by excessively long collection time can be avoided, and multiple repeated collections are performed within a specified time range to ensure collection efficiency while obtaining positioning data with higher positioning accuracy as much as possible.

[0138] It should be noted that the above description of process 300 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and alterations to process 300 under the guidance of this specification. However, such modifications and alterations are still within the scope of this specification.

[0139] In some embodiments, the control unit may control the positioning unit to obtain a positioning data sequence of the target point; and determine the positioning data based on the positioning accuracy of the second positioning data in the positioning data sequence.

[0140] The positioning data sequence refers to a sequence consisting of a plurality of second positioning data. In some embodiments, the positioning data sequence includes the second positioning data of the target point acquired within a standard time.

[0141] Secondary positioning data refers to positioning information continuously acquired by the positioning unit that can initially characterize the location of the target point. In some embodiments, the control unit can control the positioning unit to continuously acquire multiple secondary positioning data of the target point. For example, the secondary positioning data can be location coordinates directly acquired by a high-precision GPS locator.

[0142] In some embodiments, the control unit may determine the positioning data in various ways based on the positioning accuracy of the second positioning data in the positioning data sequence. For example, the second positioning data with the highest positioning accuracy in the positioning data sequence may be selected as the positioning data. In another example, the average of the R second positioning data with the highest positioning accuracy in the positioning data sequence may be selected as the positioning data. The value of R may be manually preset or set by system default. For example, R = 3.

[0143] In some embodiments of the present specification, by controlling the positioning unit to obtain a positioning data sequence of the target point, the positioning data is determined according to the positioning accuracy based on the second positioning data, providing another method for quickly determining the positioning data, which is conducive to improving the efficiency of coordinate acquisition.

[0144] In some embodiments, the first motion unit may further include a tilt sensor.

[0145] A tilt sensor is a sensing device capable of detecting tilt angles, such as a solid-state pendulum tilt sensor. In some embodiments, the tilt sensor can be configured to acquire a tilt data sequence, where the tilt data sequence includes a plurality of tilt data points generated during the movement of the first motion unit into the fenced area.

[0146] The inclination data refers to the angle data of the first motion unit deviating from the horizontal position. In some embodiments, the inclination data can represent the slope of the road surface where the first motion unit is located. For example, the inclination data can be 0°, 10°, -3°, etc. Among them, 0° represents that the slope of the road surface where the first motion unit is located is 0 (i.e., a horizontal plane), 10° represents that the road surface where the first motion unit is located is an uphill section (the head of the first motion unit is tilted upward), and the road surface slope is 10° (the inclination angle of the first motion unit to the horizontal plane is 10°), and -3° represents that the road surface where the first motion unit is located is a downhill section (the head of the first motion unit is tilted downward), and the road surface slope is 3° (the inclination angle of the first motion unit to the horizontal plane is -3°).

[0147] A tilt angle data sequence is a sequence of multiple tilt angle data. For example, the tilt angle data sequence is (10, 10, 11, 12, 13, 11, 11), which means that the tilt angle data generated when the first motion unit moves to the fence area are 10°, 10°, 11°, 12°, 13°, 11°, and 11°, respectively.

[0148] The preset inclination condition refers to a preset condition regarding the inclination data sequence used to determine whether the fence ground is flat. In some embodiments, the preset inclination condition can be pre-set by a technician. For example, the preset inclination condition can be that the fluctuation amplitude of the inclination data is less than a preset amplitude threshold.

[0149] The inclination data fluctuation amplitude refers to the variation amplitude of multiple inclination data in the inclination data sequence. In some embodiments, the inclination data fluctuation amplitude can be represented by the range of multiple inclination data in the inclination data sequence. For example, if the inclination data sequence is (10, 10, 11, 12, 13, 11, 11), the corresponding inclination data fluctuation amplitude is 3°. For another example, if the inclination data sequence is (0, -3, -8, 5, 8, 9, 3), the corresponding inclination data fluctuation amplitude is 17°.

[0150] The preset amplitude threshold refers to the maximum fluctuation amplitude of the inclination data corresponding to a flat fence ground. In some embodiments, the preset amplitude threshold can be manually preset based on experience or set by system default. For example, 5°, etc.

[0151] In some embodiments, the control unit may cause the second positioning unit to collect coordinate information of the electronic fence in response to the inclination data sequence of the first motion unit not meeting a preset inclination condition.

[0152] For example, the inclination data sequence of the first motion unit is (0, -3, -8, 5, 8, 9, 3), the corresponding inclination data fluctuation amplitude is 17°, and the preset amplitude threshold is 5°. The inclination data fluctuation amplitude is greater than the preset amplitude threshold, that is, the inclination data sequence does not meet the preset inclination condition, indicating that the fence ground is uneven, and the coordinate information of the electronic fence is collected by the second positioning unit.

[0153] In some embodiments, the control unit can collect the coordinate information of the electronic fence through the second positioning unit in various ways. For example, the control unit can control the second positioning unit to obtain the positioning data of the target point; based on the positioning data of the target point, the coordinate information of the electronic fence is determined. For more information about this part, please refer to Figure 2 and Figure 3 Related description.

[0154] In some embodiments of the present specification, the flatness of the fence ground can be accurately characterized by the inclination data sequence of the first motion unit. When the inclination data sequence does not meet the preset inclination condition, it means that the fence ground is uneven, and the positioning by the first positioning unit is more difficult and the accuracy is poor. Therefore, it is determined that the coordinate information of the electronic fence is collected by the second positioning unit, which is conducive to ensuring collection efficiency and data accuracy.

[0155] Figure 4 This is an exemplary flow chart of collecting coordinate information of an electronic fence according to some embodiments of this specification. Figure 4 As shown, process 400 may include the following steps. In some embodiments, Figure 4 The process 400 shown may be executed by the control unit 140 .

[0156] The preset image condition refers to a preset condition for determining whether the second fence image can be used to determine the first motion parameter. In some embodiments, the preset image condition can be pre-set by a technician. For example, the preset image condition can be that the second fence image can identify the fence (parking frame).

[0157] In some embodiments, the control unit may determine whether the second fence image meets the preset image condition in various ways. For example, if a fence can be identified in the second fence image using image recognition technology, then the second fence image meets the preset image condition.

[0158] In some embodiments, in response to the second fence image meeting the preset image condition, the control unit may determine the first motion parameter of the first motion unit based on the second fence image. For more information about this part, please refer to Figure 2 Related description.

[0159] In some embodiments, in response to the second fence image not satisfying the preset image condition, the control unit may execute step 411 and step 412 .

[0160] Step 411: Determine a first motion parameter based on the first fence image.

[0161] The first fence image refers to a fence image captured by the first camera unit, for example, a fence image captured by a camera mounted on a small unmanned vehicle.

[0162] In some embodiments, the control unit may determine the first motion parameter based on the first fence image using a variety of methods. For example, the control unit may determine the first motion parameter based on the first fence image using existing line-following technology.

[0163] Step 412: The first positioning unit collects coordinate information of the electronic fence.

[0164] In some embodiments, the control unit can collect the coordinate information of the electronic fence from the first positioning unit in various ways. For example, the control unit can control the first positioning unit to obtain the positioning data of the target point; based on the positioning data of the target point, the coordinate information of the electronic fence is determined. For more information about this part, please refer to Figure 2 and Figure 3 Related description.

[0165] Step 420: In response to the inclination data sequence of the first motion unit not satisfying the preset inclination condition, the coordinate information collected by the first positioning unit is checked.

[0166] In some embodiments, when the first positioning unit collects coordinate information of the electronic fence, if the inclination data sequence of the first motion unit does not meet the preset inclination conditions, the control unit can verify the coordinate information collected by the first positioning unit in various ways. For example, the control unit can transmit the coordinate information collected by the first positioning unit to a server or user terminal via a communication component, display the coordinate information collected by the first positioning unit to a technician, and manually verify the coordinate information by the technician. The user terminal can include a mobile device, a tablet computer, a laptop computer, other devices with input and / or output functions, or any combination thereof.

[0167] In some embodiments of this specification, when the second fence image does not meet a preset image condition, a first motion parameter is determined based on the first fence image, and the first positioning unit collects coordinate information of the electronic fence. Furthermore, if the inclination data sequence of the first motion unit does not meet the preset inclination condition, the coordinate information collected by the first positioning unit is verified. This comprehensive consideration of various possible scenarios and the implementation of corresponding solutions make the acquisition system more adaptable and suitable for acquisition in a variety of complex environments, while ensuring acquisition accuracy while improving efficiency and saving costs.

[0168] It should be noted that the above description of process 400 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and variations to process 400 under the guidance of this specification. However, such modifications and variations are still within the scope of this specification.

[0169] In some embodiments, the electronic fence acquisition system further includes a cleaning component, and the control unit can determine whether to turn on the cleaning component and the working time of the cleaning component based on the first fence image.

[0170] In some embodiments, the control unit can determine whether to activate the cleaning component based on the first fence image in a variety of ways. For example, based on the first fence image, image recognition technology (such as neural network, etc.) can be used to determine whether the fence is blocked by debris. If so, the cleaning component is activated; if not, the cleaning component is not activated. For more information about the cleaning component, please refer to Figure 1 Related description.

[0171] Working time refers to the duration of time a cleaning component performs debris removal. In some embodiments, the control unit can determine the working time of the cleaning component based on the first fence image using various methods. For example, the control unit can search a second historical database to obtain the historical first fence image with the highest image similarity to the first fence image, and determine the historical working time corresponding to the historical first fence image as the working time. The second historical database can be constructed based on a large number of historical first fence images and their corresponding historical working times.

[0172] In some embodiments of the present specification, based on the first fence image, the opening of the cleaning component can be accurately controlled and the reasonable working time of the cleaning component can be determined, which is conducive to ensuring that the cleaning level meets the requirements (for example, the parking frame can be recognized) and avoiding excessive cleaning that causes waste of time and resources.

[0173] Figure 5 is an exemplary schematic diagram of determining the working time of a cleaning component according to some embodiments of the present specification.

[0174] In some embodiments, the control unit can determine the contrast 550 and the contrast type 540 based on the first fence image 510 and the first standard image 520 through the contrast evaluation layer 530-1 of the duration model 530; based on the contrast 550 and the candidate working time 560, determine the corrected contrast 570 corresponding to the candidate working time 560 through the time estimation layer 530-2 of the duration model 530; and determine the working time 580 of the cleaning component based on the corrected contrast 570.

[0175] The first standard image 520 is a standard image (ideal image) of the first fence image. For example, it may be a clear and complete historical image of various parking frames and their corners. In some embodiments, the first standard image may be pre-uploaded to a server by a technician and stored in a storage device. The control unit may retrieve the image from the storage device via a communication component.

[0176] The contrast type 540 refers to the type of cause that causes the parking frame in the fenced area to be obscured. In some embodiments, the contrast type may refer to the type of debris. For example, the contrast type may include leaves, garbage, dust, snow, etc.

[0177] Duration model 530 is a model used to determine the operating time of the cleaning component. In some embodiments, the duration model is a machine learning model. For example, a machine learning model with a custom structure described below, other neural network models (e.g., a convolutional neural network (CNN)), etc.

[0178] In some embodiments, the duration model 530 may include a contrast evaluation layer 530 - 1 and a time estimation layer 530 - 2 .

[0179] The contrast assessment layer refers to a model that determines contrast and contrast type. In some embodiments, the contrast assessment layer can be a machine learning model with image recognition capabilities, such as a convolutional neural network.

[0180] In some embodiments, the input of the contrast evaluation layer 530 - 1 may include the first fence image 510 and the first standard image 520 , and the output may be a contrast 550 and a contrast type 540 .

[0181] More information on first fence images and contrast can be found in Figure 2 Related description.

[0182] In some embodiments, the contrast assessment layer can be obtained by training a large number of first training samples. The first training samples for training the contrast assessment layer include a sample first fence image and a sample first standard image. The first label is the actual contrast and actual contrast type corresponding to the first training sample.

[0183] In some embodiments, the first training sample can be obtained based on experimental data. For example, the first training sample can be an experimental first fence image and an experimental first standard image, or a historical first fence image and a historical first standard image. In some embodiments, the control unit can select a large number of historical first standard images as experimental first standard images, perform blurring on a randomly selected portion of the experimental first standard images (e.g., blurring to simulate the color of leaves or dust), and use the blurred portion of the experimental first standard images and the historical first fence images as the experimental first fence images. The first label can be manually annotated. For example, the contrast ratio of the blurred historical first fence image (or the blurred experimental first standard image) and the historical first standard image (or the experimental first standard image) in the parking frame can be labeled as 0, and the contrast type can be labeled with a specific contrast type (leaves, garbage, dust, snow, etc.). The contrast ratio of the identical or similar historical first fence image and the historical first standard image (or the experimental first fence image and the experimental first standard image) can be labeled as 1, and the contrast type can be labeled as 0.

[0184] In some embodiments, the control unit may input a first training sample with a first label into the contrast assessment layer, construct a first loss function using the output contrast and contrast type and the first label, and iteratively update parameters of the contrast assessment layer based on the plurality of first training samples so that the first loss function satisfies a preset condition. For example, the first loss function converges, or the value of the first loss function is less than a preset value. When the first loss function satisfies the preset condition, training is completed, and a trained contrast assessment layer is obtained.

[0185] The time estimation layer 530-2 is a model used to determine the corrected contrast. In some embodiments, the time estimation layer can be a machine learning model. For example, the time estimation layer can be a neural network (NN).

[0186] In some embodiments, the input of the time estimation layer 530 - 2 includes contrast 550 and candidate working time 560 , and the output may be a modified contrast 570 corresponding to the candidate working time 560 .

[0187] The candidate working time refers to a candidate working time, for example, 30 seconds, 40 seconds, 1 minute, 2 minutes, etc. In some embodiments, the candidate working time can be pre-set by a technician based on experience and stored in a storage device.

[0188] The corrected contrast refers to the contrast after cleaning by the cleaning component. In some embodiments, different candidate working times of the cleaning component may correspond to different corrected contrasts.

[0189] In some embodiments, the time estimation layer can be obtained by training a large number of second training samples. The second training samples for training the time estimation layer include sample contrast and sample candidate working time. The second label is the actual corrected contrast corresponding to the second training sample.

[0190] In some embodiments, the second training sample can be obtained based on historical data and / or experimental data. The second label can be manually labeled. For example, multiple candidate working times are manually preset as sample candidate working times, and multiple historical contrasts are used as sample contrasts. For one sample contrast, the corresponding corrected contrast of the multiple sample candidate working times is determined to be greater than or equal to the contrast threshold. Among the sample candidate working times, the corrected contrast corresponding to the shortest K sample candidate working times is marked as 1, and the rest are marked as 0.

[0191] The contrast threshold is the minimum contrast value required to meet positioning requirements (parking area recognition, i.e., coordinate acquisition). A corrected contrast greater than or equal to the contrast value indicates that after cleaning for the candidate working time, the contrast meets positioning requirements. The contrast threshold and K value can be manually preset or set by system default. For example, a contrast threshold of 80% and K = 3 are acceptable.

[0192] In some embodiments, the training process of the time estimation layer is similar to the training process of the contrast assessment layer, and reference may be made to the above related description, which will not be repeated here.

[0193] In some embodiments, a trained duration model may be obtained by separately obtaining a contrast evaluation layer and a time estimation layer.

[0194] In some embodiments, the control unit may determine the operating time of the cleaning component based on the corrected contrast in a variety of ways. For example, the control unit may determine the shortest candidate operating time among the candidate operating times whose corrected contrast is greater than or equal to the contrast threshold as the operating time of the cleaning component.

[0195] In some embodiments, in response to the inclination data sequence of the first motion unit not meeting the preset inclination condition, the control unit can start the cleaning component for cleaning; in response to the inclination data sequence still not meeting the preset inclination condition after the cleaning component has cleaned for a working time, the control unit can collect the coordinate information of the electronic fence by the second positioning unit.

[0196] In some embodiments of the present specification, based on the first fence image and the first standard image, a machine learning model can be used to accurately and quickly determine the contrast and contrast type. According to the contrast and the candidate working time, the model can be used to determine the corrected contrast corresponding to the candidate working time. Based on the corrected contrast, the working time of the cleaning component that can meet the positioning requirements and has the shortest time can be accurately determined, which can save time and improve efficiency while ensuring the smooth progress of the collection work.

[0197] One or more embodiments of this specification provide an electronic fence collection device, which includes at least one memory and at least one processor, wherein the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement an electronic fence collection method.

[0198] One or more embodiments of this specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the electronic fence collection method.

[0199] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0200] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0201] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0202] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0203] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values are as accurate as possible within the feasible range.

[0204] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0205] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. An electronic fence collection system, characterized in that: The system includes a positioning unit, a camera unit, a motion unit, and a control unit. The positioning unit and the camera unit are mounted on the motion unit, and the motion unit moves the positioning unit and the camera unit to a target area. The positioning unit is configured to obtain positioning data of the target point; The camera unit is configured to capture a fence image and a target point image of the target area; The motion unit is configured to move to the target point based on a movement control instruction; The control unit is configured to: determining the movement control instruction based on the fence image; determining, based on the target point image, whether the motion unit has moved to the target point; In response to the motion unit moving to the target point, controlling the positioning unit to obtain the positioning data of the target point; Based on the positioning data of the target point, coordinate information of the electronic fence is determined.

2. The system according to claim 1, wherein The control unit is further configured to: Controlling the positioning unit to obtain first positioning data of the target point; Determining whether the first positioning data meets a preset accuracy condition, where the preset accuracy condition is that the positioning accuracy of the first positioning data reaches a standard accuracy; In response to the first positioning data satisfying the preset accuracy condition, the first positioning data is determined as the positioning data.

3. The system according to claim 2, wherein: The control unit is further configured to: In response to the first positioning data not meeting the preset accuracy condition, determining whether the data collection time corresponding to the target point meets a preset time condition, the preset time condition being that the data collection time reaches a standard time; In response to the data collection time satisfying the preset time condition, selecting the first positioning data satisfying a preset selection condition from the acquired first positioning data as the positioning data; In response to the data collection time not meeting the preset time condition, the positioning unit is controlled to reacquire the first positioning data of the target point, and the judgment process is repeated until the positioning data is determined, the judgment process including judging whether the first positioning data meets the preset accuracy condition and judging whether the data collection time corresponding to the target point meets the preset time condition.

4. The system according to claim 1, wherein: The control unit is further configured to: controlling the positioning unit to obtain a positioning data sequence of the target point, wherein the positioning data sequence includes second positioning data of the target point obtained within the standard time; The positioning data is determined based on the positioning accuracy of the second positioning data in the positioning data sequence.

5. The system according to claim 1, wherein: The control unit is further configured to: Determining candidate fence information based on the candidate fence image captured by the camera unit; Determining whether the candidate fence information meets a preset fence condition; In response to the candidate fence information satisfying the preset fence condition, the candidate fence image is determined to be the fence image.

6. The system according to claim 1, wherein: The system further includes a communication component, the motion unit includes a first motion unit and a second motion unit, the first positioning unit and the first camera unit are mounted on the first motion unit, and the second positioning unit and the second camera unit are mounted on the second motion unit; The control unit is communicatively connected with the first motion unit, the first positioning unit, the first camera unit, the second motion unit, the second positioning unit and the second camera unit respectively through the communication component; The working height of the second motion unit is higher than the working height of the first motion unit; The second camera unit is configured to acquire a second fence image; The control unit is further configured to: determining a first motion parameter of the first motion unit based on the second fence image; The movement control instruction of the first motion unit is determined based on the first motion parameter.

7. The system according to claim 6, wherein: The first camera unit is configured to acquire a first fence image, and the system further includes a cleaning component mounted on the first motion unit; The control unit is further configured to: Based on the first fence image, whether to turn on the cleaning component and the working time of the cleaning component are determined.

8. An electronic fence collection method, characterized in that: The method comprises: Obtain a fence image of the target area; determining a movement control instruction based on the fence image; Moving to the target point based on the movement control instruction; Acquire target point image; determining whether to move to the target point based on the target point image; In response to moving to the target point, acquiring the positioning data of the target point; Based on the positioning data of the target point, coordinate information of the electronic fence is determined.

9. An electronic fence collection device, characterized in that: The device includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement the electronic fence collection method described in claim 8.

10. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions, the computer executes the electronic fence collection method according to claim 8.

Images