Target positioning method, computer program product, electronic equipment and storage medium

Abstract

The invention provides a target positioning method, a computer program product, electronic equipment and a storage medium, and the method comprises the steps: obtaining the elevation positioning data of a target point; obtaining calibration positioning data of the target point based on laser positioning and / or manual calibration; and determining a positioning result of the target point based on the calibration positioning data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of target positioning, in particular to a target positioning method, a computer program product, an electronic device and a storage medium. BACKGROUND

[0002] With the deepening of the construction of smart cities, the application of photoelectric equipment in complex observation scenes in cities is increasingly expanding, such as the illegal snapping of city management departments, abnormal target tracking in emergency response, and real-time alarm of invasions in key areas of security systems. These scenes usually involve high-density building shielding, multi-source interference (such as dynamic light and shadow, rain and fog, and glass curtain wall reflection), and frequent changes in terrain (such as newly built viaducts and deep foundation pits), which pose strict requirements on the target identification and accurate positioning of photoelectric equipment: on the premise of not sacrificing the convenience of deployment, reliable meter-level precision positioning is realized to support rapid response and precise intervention.

[0003] At present, the existing positioning technology has the problem that: it mainly adopts a static and open-loop positioning framework, cannot dynamically extract effective calibration samples from daily observation data, has large system errors, and especially in high-frequency use areas, the cumulative effect of system errors is significant. SUMMARY

[0004] To solve the existing technical problems, the present application provides a target positioning method, a computer program product, an electronic device and a storage medium which can effectively reduce positioning errors.

[0005] In a first aspect, an embodiment of the present application provides a target positioning method, comprising: obtaining elevation positioning data of a target point; obtaining calibration positioning data of the target point based on laser positioning and / or manual calibration; and determining a positioning result of the target point based on the calibration positioning data.

[0006] In a second aspect, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the target positioning method according to any embodiment of the present application.

[0007] In a third aspect, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the target positioning method according to any embodiment of the present application.

[0008] In a fourth aspect, a storage medium is provided, comprising a computer program stored thereon, wherein the computer program, when executed by a processor, implements the target positioning method according to any embodiment of the present application.

[0009] In the target positioning method provided in the above embodiments, after the height positioning data of the target point is acquired, the calibration positioning data is formed based on the laser positioning and / or manual calibration with higher accuracy, and then the positioning result of the target point is determined based on the calibration positioning data. In this way, the calibration of the height positioning data can be effectively performed according to the height positioning data and the laser positioning / manual calibration data with higher accuracy and reliability, the error existing in the height measurement can be avoided, especially in the complex observation positioning scene such as a city, the system error can be effectively reduced, and the accurate positioning of the target point can be realized.

[0010] The computer program product, the electronic device and the storage medium provided in the above embodiments belong to the same concept as the corresponding target positioning method embodiments, and thus have the same technical effects as the corresponding target positioning method embodiments, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 FIG. 1 is a flowchart of a target positioning method according to an embodiment of the present application; Figure 2 FIG. 2 is a flowchart of a target positioning method according to another embodiment of the present application; Figure 3 FIG. 3 is a flowchart of step S2 in the target positioning method according to an embodiment of the present application; Figure 4 FIG. 4 is a flowchart of step S3 in the target positioning method according to an embodiment of the present application; Figure 5 FIG. 5 is a flowchart of step S4 in the target positioning method according to an embodiment of the present application; Figure 6 FIG. 6 is a flowchart of step S5 in the target positioning method according to an embodiment of the present application; Figure 7 FIG. 7 is a schematic diagram of a system architecture corresponding to the target positioning method according to an embodiment of the present application; Figure 8 FIG. 8 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] The technical solutions of the present application will be further described in detail below in combination with the accompanying drawings and specific embodiments.

[0013] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the accompanying drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by a person of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0014] In the following description, the expression "some embodiments" refers to a subset of all possible embodiments, and it is to be understood that "some embodiments" can be the same subset or different subsets as each other and can be combined with each other as long as there is no conflict.

[0015] In the following description, the terms "first", "second", "third" are merely used to distinguish similar objects, and do not represent a specific order of the objects. Understandably, "first", "second", "third" can be interchanged in a specific order or sequence as long as it is allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other as long as there is no conflict.

[0016] As shown in Figure 1 An embodiment of the present application provides a target positioning method, comprising: S10: obtaining elevation positioning data of a target point; S20: obtaining calibration positioning data of the target point based on laser positioning and / or manual calibration; S30: determining a positioning result of the target point based on the calibration positioning data.

[0017] In one embodiment, the target positioning method can be applied to an observation device, such as an intelligent ball machine, a cylinder machine, a cloud platform, an optoelectronic observation device, etc. The target point can be a point that needs to be observed and positioned. The elevation positioning data is positioning data representing the position of the target point determined based on a digital elevation model (DEM), for example, the elevation positioning data can be an elevation positioning coordinate, etc.

[0018] In one embodiment, laser positioning can refer to determining laser positioning data of the target point based on laser measurement, for example, the laser positioning data can be a laser positioning coordinate, etc. Manual calibration can refer to positioning data of the target point input by a user, such as coordinate data, etc. Wherein, in the case that the observation device does not have laser positioning function, or the laser positioning is invalid, or the laser positioning data is invalid, the calibration positioning data can be obtained through manual calibration.

[0019] In one embodiment, the calibration positioning data of the target point can also refer to calibration positioning data used for calibrating the elevation positioning data, that is, the error compensation amount corresponding to the region can be determined through the calibration positioning data, so as to compensate and calibrate the elevation positioning data.

[0020] In one embodiment, when only the laser positioning data of the target point or the positioning data input by manual calibration (i.e. manual calibration data) exists, the laser positioning data or the positioning data input by manual calibration is taken as the calibration positioning data. When the laser positioning data of the target point and the positioning data input by manual calibration exist simultaneously, the positioning data input by manual calibration can be taken as the calibration positioning data, or whether a preset selection operation is detected based on the positioning data input by manual calibration can be used to determine which data is taken as the calibration positioning data.

[0021] For example, if the preset selection operation is detected, the positioning data input by manual calibration is taken as the calibration positioning data, and if the preset selection operation is not detected, the laser positioning data is taken as the calibration positioning data. The preset selection operation can be an operation of selecting the positioning data input by manual calibration as the calibration positioning data.

[0022] In one embodiment, the laser positioning data can be calculated based on the laser ranging value determined based on laser ranging, the height positioning data, and the device position data of the observation device. The laser positioning data can be calculated by forward intersection triangulation.

[0023] In this way, the height positioning data can be effectively calibrated based on multiple sets of height positioning data and laser positioning data or manual calibration data with higher accuracy and reliability, so as to avoid errors in height measurement, especially in complex observation positioning scenarios such as cities, so as to effectively reduce systematic errors and achieve accurate positioning of the target point.

[0024] In some embodiments, the step S30 can include: storing the calibration positioning data, the height positioning data, and the preset region where the target point is located in association; determining an error compensation amount corresponding to the preset region based on multiple sets of calibration positioning data and height positioning data corresponding to the preset region; compensating the height positioning data based on the error compensation amount to obtain a positioning result of the target point.

[0025] In one embodiment, storing the calibration positioning data, the height positioning data, and the preset region where the target point is located in association can include storing the calibration positioning data, the height positioning data, and device sensor data corresponding to the height positioning data in association with the preset region where the target point is located. The device sensor data corresponding to the height positioning data can include at least one of horizontal angle data, pitch angle data, pointing angle data, observation distance data, device position data, focal length, timestamp, and image capture data.

[0026] In an embodiment, the determining the error compensation quantity corresponding to the preset region based on the plurality of sets of the calibration positioning data and the height positioning data corresponding to the preset region can comprise: training a preset error model based on the plurality of sets of the calibration positioning data and the height positioning data corresponding to the preset region; and determining the error compensation quantity corresponding to the preset region based on the preset error model.

[0027] In an embodiment, the training the preset error model based on the plurality of sets of the calibration positioning data and the height positioning data corresponding to the preset region can comprise: determining whether a quantity of the height positioning data stored corresponding to the preset region reaches a preset threshold; and in response to the quantity reaching the preset threshold, training the preset error model based on all of the calibration positioning data and the height positioning data corresponding to the preset region.

[0028] The quantity of the height positioning data can refer to a quantity of height positioning data having corresponding calibration positioning data, or can refer to a quantity of initial data sets each containing a set of calibration positioning data and height positioning data. Each height positioning data corresponds to a target point, that is, each initial data set corresponds to a target point, and each initial data set contains a set of calibration positioning data and height positioning data.

[0029] In an embodiment, the training the preset error model based on the plurality of sets of the calibration positioning data and the height positioning data corresponding to the preset region can comprise: taking the plurality of sets of the calibration positioning data, the height positioning data, and at least one item of device sensor data corresponding to the height positioning data as input, and outputting a target being an error between the height positioning data and an expected positioning result (which is also equal to the error compensation quantity). Here, the error can be a position vector error.

[0030] In this way, the error compensation quantity corresponding to the region, that is, the required error compensation quantity, can be determined based on the plurality of sets of the height positioning data and the laser positioning / artificial calibration data with higher accuracy and reliability, so that the initially obtained height positioning data can be compensated based on the error compensation quantity corresponding to the region in the positioning calculation for the target point, and in particular, in a complex observation positioning scene such as a city, system error can be effectively reduced, and accurate positioning of the target point can be achieved.

[0031] In some embodiments, the storing the calibration positioning data, the height positioning data, and the preset region where the target point is located in association can comprise: obtaining device sensor data corresponding to the height positioning data; the device sensor data at least comprising one of the following: pointing angle data, observation distance data, device position data, focal length, and time stamp; An initial dataset is constructed based on the calibration positioning data, the elevation positioning data, and the corresponding device sensor data. The initial dataset is associated with and stored in the preset area where the target point is located; The step of determining the error compensation amount corresponding to the preset area based on multiple sets of calibration positioning data and elevation positioning data corresponding to the preset area includes: The error compensation amount corresponding to the preset region is determined based on multiple initial datasets corresponding to the preset region.

[0032] In one embodiment, device sensor data refers to the sensor data of the observation device during the acquisition of elevation positioning data. Pointing angle data can be data representing the observation direction determined based on the horizontal and pitch angle data of the observation device during the acquisition of elevation positioning data. Observation distance data can be data representing the distance between the target point and the observation device. Device position data can be the position data of the observation device itself during the acquisition of elevation positioning data, such as coordinate data, which can be Global Navigation Satellite System (GNSS) coordinates, etc. Focal length can be the focal length of the observation device during the acquisition of elevation positioning data, and the timestamp can be the timestamp corresponding to the acquisition of elevation positioning data.

[0033] In one embodiment, constructing an initial dataset based on the calibration positioning data, the elevation positioning data, and the corresponding device sensor data may include: associating and packaging the calibration positioning data, elevation positioning data, and corresponding device sensor data corresponding to the target point to form an initial dataset.

[0034] In one embodiment, the preset area where the target point is located can refer to the area where the observation device is currently located, or it can refer to the area where the target point is located based on the elevation positioning data and / or calibration positioning data of the target point.

[0035] In one embodiment, determining the error compensation amount corresponding to the preset region based on multiple initial datasets corresponding to the preset region may include: determining the error compensation amount corresponding to the preset region based on all the initial datasets corresponding to the preset region. For example, it may include determining the error compensation amount corresponding to the preset region based on all the initial datasets corresponding to the preset region when the number of initial datasets stored corresponding to the preset region reaches a preset threshold.

[0036] In one embodiment, all the initial datasets corresponding to the preset area may include at least one of the following: all the initial datasets corresponding to the preset area acquired within a predetermined time period before the current time, all the initial datasets acquired within a preset range near the observation device in the preset area, and all the initial datasets acquired within a preset range near the target point in the preset area. The preset range near the target point may be a nearby preset range determined based on the target point's elevation positioning data and / or calibration positioning data.

[0037] In this way, based on the sensor data of the equipment corresponding to the collected elevation positioning data, the observation attitude and position of the observation equipment can be characterized. This data, together with the elevation positioning data and calibration positioning data, can be used to determine the dynamic error change relationship between each elevation positioning data and the required positioning result, thereby improving the matching accuracy between the error compensation amount and the actual positioning result and further reducing the system error.

[0038] In some embodiments, determining the error compensation amount corresponding to the preset region based on multiple initial datasets corresponding to the preset region includes: Determine whether the number of initial datasets stored in the preset region reaches a preset threshold; In response to the quantity reaching a preset threshold, all the initial datasets corresponding to the preset region are obtained; Based on the device sensor data, calibration positioning data, and elevation positioning data in all the initial datasets corresponding to the preset region, the error compensation amount corresponding to the preset region is determined.

[0039] In one embodiment, the number of initial datasets can be equal to the number of elevation positioning data; that is, an initial dataset is formed by the process of acquiring elevation positioning data for a target point once.

[0040] In one embodiment, the preset threshold can be a fixed value, such as 3, 5, 10, etc., or it can be a value adjusted based on the size of the preset region. For example, the larger the range of the preset region, the larger the preset threshold, thereby avoiding insufficient initial datasets that could lead to inaccurate error compensation calculations.

[0041] In one embodiment, all the initial datasets corresponding to the preset area may include at least one of the following: all the initial datasets corresponding to the preset area acquired within a predetermined time period before the current time, all the initial datasets acquired within a preset range near the observation device in the preset area, and all the initial datasets acquired within a preset range near the target point in the preset area.

[0042] In one embodiment, the device sensor data may include at least one of pointing angle data, observation distance data, and device location data.

[0043] In one embodiment, determining the error compensation amount corresponding to the preset region based on the device sensor data, calibration positioning data, and elevation positioning data in all the initial datasets corresponding to the preset region may include: using the device sensor data, calibration positioning data, and elevation positioning data in all the initial datasets corresponding to the preset region as multiple sets of inputs, and determining the error compensation amount corresponding to the preset region through a preset error model. Each set of inputs includes the device sensor data, calibration positioning data, and elevation positioning data from one initial dataset.

[0044] Thus, when the number of initial datasets stored in the preset area reaches a certain amount, the error offset of the area is calculated based on all the initial datasets. This avoids the situation where the amount of data is too small to fully represent the system error of the positioning in the area. At the same time, by combining all the initial datasets, the error situation of all datasets can be aggregated, thereby accurately calculating the optimal error compensation amount in the area and further reducing the system error.

[0045] In some embodiments, the step of compensating the elevation positioning data based on the error compensation amount to obtain the positioning result of the target point includes: The error compensation amount is added to the elevation positioning data to obtain the positioning result of the target point.

[0046] In one embodiment, the elevation positioning data can be elevation coordinate data, including three parameters: longitude, latitude, and elevation. Adding the error compensation amount to the elevation positioning data can mean adding the error compensation amount to the longitude, latitude, and elevation values ​​in the elevation positioning data separately.

[0047] For example, the error compensation amount can include longitude error compensation amount, latitude error compensation amount, and elevation error compensation amount. Adding the error compensation amount to the elevation positioning data can include: adding the longitude error compensation amount to the longitude value in the elevation positioning data to obtain the target longitude value in the target point positioning result; adding the latitude error compensation amount to the latitude value in the elevation positioning data to obtain the target latitude value in the target point positioning result; and adding the elevation error compensation amount to the elevation value in the elevation positioning data to obtain the target elevation value in the target point positioning result.

[0048] In one embodiment, the longitude error compensation, latitude error compensation, and elevation error compensation in the error compensation amount can all be positive or negative, or they can be 0.

[0049] In one embodiment, after obtaining the location result of the target point, the method further includes: The positioning result and its calibration information are displayed and output; wherein the source information includes at least one of laser calibration, manual calibration, and error compensation-based calibration.

[0050] For example, positioning results and calibration information can be output on the display interface by following the target point. Laser calibration refers to using laser positioning data as calibration positioning data, manual calibration refers to using manually calibrated data as calibration positioning data, and error compensation-based calibration refers to the positioning result obtained by compensating for the aforementioned error compensation amounts.

[0051] Thus, by adding the error compensation calculated based on all datasets within the region to the elevation positioning data, the systematic errors observed by the observation equipment within the region can be offset, thereby obtaining a more accurate positioning result.

[0052] In some embodiments, the device sensor data corresponding to the elevation positioning data may include pointing angle data. When the device sensor angle includes pointing angle data, obtaining the device sensor data corresponding to the elevation positioning data may include: Obtain the current horizontal angle data and the current pitch angle data; The pointing angle data is determined based on the current horizontal angle data and the current pitch angle data.

[0053] In one embodiment, the current horizontal angle data and the current pitch angle data can also refer to the current horizontal angle data and the current pitch angle data at the time of acquiring the elevation positioning data. For example, acquiring elevation positioning data can be done by obtaining the elevation positioning data through a DEM model based on the current horizontal angle data and the current pitch angle data.

[0054] In one embodiment, the pointing angle data represents the observation angle at which the observation device locates the target point.

[0055] In one embodiment, before acquiring the elevation positioning data of the target point, the method further includes: Determine the pointing angle offset based on the reference point coordinates and the current coordinates of the device; Rotate the device horizontally one full turn and collect multiple sets of horizontal and pitch angle data; Based on the collected sets of horizontal angle data and pitch angle data, a compensation model is fitted to generate the pitch angle data as it changes with the horizontal angle data. The process of determining the pointing angle data based on the current horizontal angle data and the current pitch angle data includes: Based on the current horizontal angle data and the compensation model, the current pitch angle data is corrected; Based on the current horizontal angle data, the corrected current pitch angle data, and the pointing angle offset, the pointing angle data is determined.

[0056] In one embodiment, the reference point coordinates can be preset by the personnel installing the observation equipment. Determining the pointing angle offset based on the reference point coordinates and the current coordinates of the equipment may include: aligning the observation direction of the observation equipment with the reference point, and determining the pointing angle offset based on the reference point coordinates and the current coordinates of the equipment.

[0057] In one embodiment, "device" refers to an observation device used to observe a target point. Determining the pointing angle offset based on the reference point coordinates and the device's current coordinates can refer to calculating the target angle using spherical trigonometry based on the device's reference point coordinates and current coordinates; determining the pointing angle offset based on the target angle and the device's original gimbal angle. The original gimbal angle may include the device's current horizontal and vertical angle data.

[0058] The target angle refers to the theoretical true horizontal angle and the theoretical true pitch angle. The pointing angle offset can include the horizontal angle offset and the pitch angle offset. The horizontal angle offset is equal to the difference between the current horizontal angle data and the theoretical true horizontal angle, and the pitch angle offset is equal to the difference between the current pitch angle data and the theoretical true pitch angle.

[0059] In one embodiment, the correction relationship between the original gimbal angle and the actual position can be obtained based on the pointing angle offset.

[0060] In one embodiment, rotating the device horizontally one revolution and collecting multiple sets of horizontal angle data and pitch angle data may include: controlling the device to rotate uniformly one revolution in the horizontal direction when the pitch angle is 0; and collecting a set of horizontal angle data and pitch angle data at preset angular intervals (e.g., 10°) using a built-in gyroscope.

[0061] In one embodiment, based on the collected sets of horizontal angle data and pitch angle data, a compensation model is fitted to generate a pitch angle data that varies with the horizontal angle data. This can refer to fitting a dynamic compensation curve or lookup table (i.e., compensation model) of pitch angle variation with horizontal angle based on the collected sets of data.

[0062] In one embodiment, determining the pointing angle data based on the current horizontal angle data, the corrected current pitch angle data, and the pointing angle offset may include: determining the pointing angle data based on the correction relationship corresponding to the current horizontal angle data, the corrected current pitch angle data, and the pointing angle offset.

[0063] In one embodiment, after correcting the current pitch angle data, the method further includes: displaying the corrected current pitch angle data.

[0064] For example, the corrected current pitch angle data can be displayed together with the original pitch angle data.

[0065] Thus, before locating the target point, single-point benchmark calibration is performed based on the pointing angle offset to establish the correction value of the relationship between the original gimbal angle and the actual position. Furthermore, dynamic calibration of pitch consistency is performed based on the compensation model, establishing the transformation relationship between the observation equipment angle and the geographic coordinate system, and correcting the zero-point error of the gimbal and the error caused by the tilt angle of the installation platform.

[0066] In some embodiments, obtaining calibration positioning data of the target point based on laser positioning and / or manual calibration includes: The system displays a prompt indicating whether laser positioning is enabled. In response to detecting a confirmation operation based on the prompt information, laser positioning data is acquired based on the laser positioning. The calibration positioning data of the target point is determined based on the laser positioning data.

[0067] For example, the prompt message can be used to prompt the user to confirm whether to activate laser positioning. The confirmation operation based on the prompt message can refer to clicking the confirmation option on the display interface, tapping or long-pressing a designated button, or confirming via voice input, etc.

[0068] In one embodiment, determining the calibration positioning data of the target point based on the laser positioning data includes: Laser positioning data is acquired based on laser positioning. Determine whether the laser positioning data is valid; If the laser positioning data is valid, the laser positioning data will be used as the calibration positioning data for the target point; If the laser positioning data is invalid, check if the user has entered manual calibration data; In response to the detection of the artificial calibration data, the artificial calibration data is used as the calibration positioning data of the target point.

[0069] In one embodiment, when the device includes a laser rangefinder, laser positioning data can be collected by the laser rangefinder within the device. Determining the validity of the laser positioning data may include determining whether the laser positioning data is missing or whether the difference between the laser positioning data and the elevation positioning data exceeds a preset range.

[0070] In one embodiment, if laser positioning data is lost, and / or the difference between laser positioning data and elevation positioning data exceeds a preset range, the laser positioning data is determined to be invalid.

[0071] In one embodiment, inputting manual calibration data can refer to the positioning data input by manual calibration.

[0072] In one embodiment, if the laser positioning data is invalid, detecting whether the user has entered manual calibration data may include: if the laser positioning data is invalid, in response to detecting a viewing operation of the elevation positioning data, displaying the elevation positioning data and the corresponding device sensor data; and detecting whether the user has entered manual calibration data.

[0073] In one embodiment, using the laser positioning data as calibration positioning data for the target point includes: If the laser positioning data is valid, the laser positioning data will be displayed and output. Within a preset time period, detect whether the user has input manual calibration data for the laser positioning data; In response to the absence of detected manual calibration data, the laser positioning data is used as the calibration positioning data for the target point.

[0074] In one embodiment, outputting the laser positioning data may include outputting the laser positioning data through a display device. The preset duration can be 10s, 30s, or 60s, etc. Detecting whether the user calibrates the currently detected laser positioning data within the preset duration can avoid excessive waiting time.

[0075] In one embodiment, inputting manual calibration data can refer to inputting positioning data as manual calibration data. When the user inputs manual calibration data, the source of the calibration positioning data is manual calibration; when the user does not input manual calibration data, the source of the calibration positioning data is laser positioning calibration.

[0076] Thus, by introducing the logic of selective manual calibration, users can be provided with more accurate coordinate data as calibration data, which can provide a more accurate calculation basis in the subsequent compensation process and further reduce errors.

[0077] In some embodiments, obtaining calibration positioning data of the target point based on laser positioning and / or manual calibration includes: In response to detecting a viewing operation of the elevation positioning data, the elevation positioning data and the corresponding device sensor data are displayed and output. Detect whether the user has entered manual calibration data; In response to detecting user-inputted manual calibration data, the manual calibration data is used as the calibration positioning data for the target point.

[0078] In one embodiment, the operation of viewing the elevation positioning data can refer to clicking on the elevation positioning data, or, for example, selecting and viewing the data in the positioning log interface.

[0079] In one embodiment, displaying the elevation positioning data and the corresponding device sensor data may include: displaying target positioning information, target positioning time, latitude, longitude and altitude, horizontal pitch angle of the gimbal, relative position azimuth and distance of the device, as well as image capture information and a log list indicating whether corrections have been made.

[0080] Here, in the absence of laser positioning capabilities, based on the user's viewing of elevation positioning data and corresponding equipment sensor data, manual calibration data can be input and thus used as calibration positioning data.

[0081] As one possible implementation, a target localization method for an observation device is provided, such as... Figure 2 As shown, it may specifically include: S1: System Initialization and Basic Calibration 1. Implementation conditions / means: Equipment (i.e., observation equipment): A fixed intelligent PTZ camera, which includes readable horizontal and vertical angles of the pan-tilt unit, an integrated gyroscope, and basic GNSS positioning capabilities; Data: One reference point with known precise coordinates (used as a baseline).

[0082] 2. Specific Implementation: S1.1 Single-point reference calibration At the installation location, control the pan-tilt unit to be aimed at a reference point with known coordinates (which can be preset by the installer). Record the original gimbal angle (Az) raw El raw ); Based on the equipment's own coordinates and the coordinates of the reference point, the theoretical true horizontal angle (Az) is calculated using the spherical trigonometry formula. true ) and pitch angle (El true ) Calculate the pointing angle offset (△Az=Az) raw -Az true , △El=El raw -El true And store it to establish the correction relationship between the original gimbal angle and the actual position.

[0083] S1.2 Pitch Consistency Dynamic Calibration When the pitch value is 0, the control unit rotates one full revolution at a constant speed in the horizontal direction. Using a built-in gyroscope, a set of data (horizontal angle Az) is collected at preset angular intervals (e.g., 10°). i gyroscope pitch value RT i ); Based on the collected data, a dynamic compensation curve or lookup table (i.e., compensation model) is generated by fitting the pitch angle as it changes with the horizontal angle. Subsequently, the pitch angle read by the equipment at any horizontal angle must be corrected by this compensation model to correct the angle difference caused by the actual tilt angle of the installation platform.

[0084] After the above basic calibration, the transformation relationship between the ball head angle and the geographic coordinate system was established, and the zero-point error of the ball head and the error caused by the tilt angle of the mounting platform were corrected.

[0085] S2: As Figure 3 As shown, real-time target localization and automatic dataset construction 1. Implementation conditions / means: Basic calibration parameters have been loaded, positioning function has been enabled, and tracking positioning module has been triggered; 2. Specific Implementation: S2.1 Target Positioning When target localization is triggered, the current horizontal and vertical angle data of the gimbal are read, and the correction parameters and compensation model generated in step S1 are used to correct them in real time to obtain the pointing angle data (Az). corrected El corrected ); Laser measurement of distance yields slant range D. laser ; Combining the slant range and DEM data from laser ranging with the device's own GNSS coordinates (London... device Lat device Alt device Using forward intersection triangulation, the laser positioning data (London laser coordinates) of the targeted point are obtained. laser Lat laser Alt laser ) and elevation positioning data (Lon DEM Lat DEM Alt DEM ); Since laser ranging accuracy is an order of magnitude higher than that of elevation maps and angles, laser positioning data is labeled as "high confidence samples" and the target laser coordinate data can be considered as calibration data points of elevation coordinate data.

[0086] S2.2 Storing Datasets Record the location information calculated from the DEM and the sensor correlation data (Az) corrected El corrected (Focus length, timestamp, and captured image data) serve as a standard initial dataset; sensor-related data refers to device sensor data.

[0087] If the current laser positioning data is valid, associate the positioning result of this "true value" with the original elevation positioning data and use it as a labeled calibration value, with the calibration source being laser. For raw positioning data packets that did not use lasers or whose lasers failed (i.e., unlabeled data packets), manual calibration is supported in step S3.

[0088] S3: As Figure 4 As shown, the review and data calibration 1. Implementation conditions / means: Users have access to more accurate target coordinate information (RTK measurement, map point selection, etc.).

[0089] 2. Specific Implementation: View the original positioning dataset on the backend management platform to see the gimbal angle value during positioning, the calculated positioning coordinate value, and the captured image information, etc. The user selects a location record and enters the target's actual coordinates, i.e., the manually calibrated data (Lon). truth Lat truth Alt truth ); By correlating the initial dataset, high-confidence calibration data points are obtained, with the calibration source being manual.

[0090] S4: As Figure 5 As shown, the partitioning error model is constructed. 1. Implementation conditions / means: The cumulative number of calibration data points within the region reaches a threshold (e.g., 5). 2. Specific Implementation: S4.1 Region Optimization Trigger: The system detects that the initial dataset number, i.e. the number of samples, is periodically checked within a preset region during operation. When the number of samples reaches the threshold N, the region optimization calculation process is automatically triggered. S4.2 Dataset Construction: The initial dataset consists of all high-confidence samples within the region. The input features for each sample are device sensor data (observation angle, observation point location, distance, etc.), and the output target is the "high-confidence ground truth" (London). truth Lat truth Alt truth ) and "original solution value (Lon raw Latraw Alt raw "" refers to the position vector error (△Lon, △Lat, △Alt) between elevation positioning data.

[0091] S4.3 Calculate the optimal angle offset: Perform error learning on the initial dataset to calculate the optimal parameter offset of the region, i.e., the error compensation amount. Aggregate the error correction vector of the subset and generate a global offset mapping function to compensate for systematic deviations.

[0092] S5: As Figure 6 As shown, real-time positioning compensation output 1. Implementation conditions / means: The optimal parameter offset calculation for the region is ready.

[0093] 2. Specific Implementation: The calculated optimal offset parameters are integrated into the target positioning calculation process for optoelectronic devices, based on the input angle parameters (Az). corrected El corrected ), matching the preset area; Obtain the error prediction value (△Lon) for the current positioning scene. predict , △Lat predict , △Alt predict The optimal parameter offset (error compensation) is added to the original positioning result to obtain the optimized positioning coordinates (Lon). adjust Lat adjust Alt adjust The results of this location analysis will be output, displayed, and recorded.

[0094] Based on the above method, the following beneficial effects were achieved: 1. Improved accuracy: Reduced system error accumulation through closed-loop compensation (especially in high-frequency use areas), reduced positioning failure rate in complex scenarios (such as rain, fog, glass reflection), and supported rapid response and precise intervention (such as violation capture and intrusion alarm). 2. Enhanced robustness: The dynamic self-learning mechanism adapts to terrain changes and disturbances, accumulates calibration samples (laser + manual) to update the regional error model, and reduces dependence on old DEMs or external benchmarks; the pitch compensation curve corrects tilt deviations and ensures consistency of multi-angle observations; 3. Economic and convenient deployment: Moderate hardware cost (single-person deployment, no need for dual-machine baseline measurement), reducing on-site manual calculation expenses (laser provides real-time high-confidence samples); autonomous optimization reduces maintenance frequency, suitable for high-density smart city applications, and improves overall system availability.

[0095] In one embodiment, S1 is typically executed once during system installation or periodic maintenance. S2 to S5 form a continuous closed loop: S2 and S5 are executed every time a location is established; S3 is a manually triggered, non-continuous process; and S4 is automatically triggered by the results of S3 (accumulation of error samples).

[0096] In one embodiment, S1 is the foundation of the entire method. The high-precision angle data it provides not only directly improves the accuracy of the original positioning results in S2, but also ensures the "quality" and "credibility" of the error samples generated in S3, so that the model trained in S4 can learn the real error patterns.

[0097] In one embodiment, the above method can be implemented on a smart PTZ camera integrating GNSS, a high-precision pan-tilt encoder, a gyroscope, and a laser rangefinder. While the laser rangefinder is not strictly necessary, it can provide high-confidence values ​​for real-time optimization of detection accuracy in frequently used areas, reducing the cost for users to calculate geographical locations on-site.

[0098] In one embodiment, the above method can form as follows: Figure 7 The system architecture diagram shown below indicates that the system has the following modules: Calibration module: used to perform single-point calibration and pitch consistency dynamic calibration; Positioning calculation module: used to calculate the original coordinates of the target based on calibrated sensor data and the selected positioning algorithm (elevation / laser / fusion); Input verification module: Provides a manual verification interface to receive the coordinates of the truth value input by the user; Error Calculation and Database Module: Calculates errors and stores error samples; Dataset training module: Periodically trains the error prediction model based on the calibration database to obtain the optimal compensation parameters; Real-time compensation module: Uses the recorded optimal compensation parameters for each partition to compensate the output of the positioning solution module in real time.

[0099] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the target localization method as described in any embodiment of this application.

[0100] This application also provides an electronic device, which can be an observation device with observation and positioning functions, such as an intelligent PTZ camera or other photoelectric observation device. Figure 8 This is a structural diagram of an electronic device according to an embodiment of this application, such as... Figure 8As shown, the electronic device includes a processor 41, a communication interface 42, a memory 43, and a communication bus 44. The processor 41, the communication interface 42, and the memory 43 communicate with each other through the communication bus 44. The memory 43 is used to store computer programs. When the processor 41 executes the program stored in the memory 43, it implements the steps of the method described in any one or more of the foregoing method embodiments.

[0101] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0102] The communication interface is used for communication between the aforementioned terminal and other devices.

[0103] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0104] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0105] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the method described in any of the above embodiments.

[0106] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0108] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A target localization method, characterized in that, include: Obtain the elevation positioning data of the target point; Based on laser positioning and / or manual calibration, obtain calibration positioning data for the target point; The positioning result of the target point is determined based on the calibration positioning data.

2. The target localization method according to claim 1, characterized in that, The step of determining the positioning result of the target point based on the calibration positioning data includes: The calibration positioning data and the elevation positioning data are associated and stored with the preset area where the target point is located; Based on multiple sets of calibration positioning data and elevation positioning data corresponding to the preset area, the error compensation amount corresponding to the preset area is determined. The elevation positioning data is compensated based on the error compensation amount to obtain the positioning result of the target point.

3. The target localization method according to claim 2, characterized in that, The step of associating and storing the calibration positioning data, the elevation positioning data, and the preset area where the target point is located includes: Obtain the device sensor data corresponding to the elevation positioning data; the device sensor data includes at least one of the following: pointing angle data, observation distance data, device position data, focal length, and timestamp; An initial dataset is constructed based on the calibration positioning data, the elevation positioning data, and the corresponding device sensor data. The initial dataset is associated with and stored in the preset area where the target point is located; The step of determining the error compensation amount corresponding to the preset area based on multiple sets of calibration positioning data and elevation positioning data corresponding to the preset area includes: The error compensation amount corresponding to the preset region is determined based on multiple initial datasets corresponding to the preset region.

4. The target localization method according to claim 3, characterized in that, The step of determining the error compensation amount corresponding to the preset region based on multiple initial datasets corresponding to the preset region includes: Determine whether the number of initial datasets stored in the preset region reaches a preset threshold; In response to the quantity reaching a preset threshold, all the initial datasets corresponding to the preset region are obtained; Based on the device sensor data, calibration positioning data, and elevation positioning data in all the initial datasets corresponding to the preset region, the error compensation amount corresponding to the preset region is determined.

5. The target localization method according to claim 4, characterized in that, The step of compensating the elevation positioning data based on the error compensation amount to obtain the positioning result of the target point includes: The error compensation amount is added to the elevation positioning data to obtain the positioning result of the target point.

6. The target localization method according to claim 3, characterized in that, The acquisition of the device sensor data corresponding to the elevation positioning data includes: Obtain the current horizontal angle data and the current pitch angle data; The pointing angle data is determined based on the current horizontal angle data and the current pitch angle data.

7. The target localization method according to claim 6, characterized in that, Before acquiring the elevation positioning data of the target point, the method further includes: Determine the pointing angle offset based on the reference point coordinates and the current coordinates of the device; Rotate the device horizontally one full turn and collect multiple sets of horizontal and pitch angle data; Based on the collected sets of horizontal angle data and pitch angle data, a compensation model is fitted to generate the pitch angle data as it changes with the horizontal angle data. The process of determining the pointing angle data based on the current horizontal angle data and the current pitch angle data includes: Based on the current horizontal angle data and the compensation model, the current pitch angle data is corrected; Based on the current horizontal angle data, the corrected current pitch angle data, and the pointing angle offset, the pointing angle data is determined.

8. The target localization method according to claim 1, characterized in that, The step of obtaining calibration and positioning data for the target point based on laser positioning and / or manual calibration includes: Laser positioning data is acquired based on laser positioning. Determine whether the laser positioning data is valid; If the laser positioning data is valid, the laser positioning data will be used as the calibration positioning data for the target point; If the laser positioning data is invalid, check if the user has entered manual calibration data; In response to the detection of the artificial calibration data, the artificial calibration data is used as the calibration positioning data of the target point.

9. The target localization method according to claim 8, characterized in that, The step of using the laser positioning data as the calibration positioning data for the target point includes: If the laser positioning data is valid, output the laser positioning data; Within a preset time period, detect whether the user has input manual calibration data for the laser positioning data; In response to the absence of detected manual calibration data, the laser positioning data is used as the calibration positioning data for the target point.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the target localization method as described in any one of claims 1 to 9.

11. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the target localization method as described in any one of claims 1 to 9.

12. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the target localization method as described in any one of claims 1 to 9.

Images