Regional point cloud data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a regional point cloud data processing method and device, a storage medium and electronic equipment. The method comprises the following steps: determining an advancing route for collecting a target area, and setting a plurality of targets along the advancing route; the first collection device is controlled to collect the target area along the advancing route, first area point cloud data are obtained, and the first area point cloud data comprise target point cloud data corresponding to the multiple targets; controlling a second collection device to collect a predetermined device in the target area to obtain first device point cloud data; and determining target area point cloud data of the target area based on the first area point cloud data, the first equipment point cloud data and the target point cloud data corresponding to the plurality of targets. The technical problem that the regional point cloud data generation efficiency is not ideal in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional surveying, and in particular to a method, device, storage medium and electronic equipment for processing regional point cloud data. Background Art

[0002] At present, when the oil and gas field station is being renovated and expanded on the ground, it is necessary to conduct detailed measurement and drawing of the objects, equipment, and pipelines in the station for later design and modification. The relevant technology partly relies on station-type scanning equipment, using total stations or GNSS RTK (Global Navigation Satellite System Real-Time Kinematic) for measurement, and using the form of single-point measurement, which cannot meet the requirements of fine and detailed description of surrounding objects. Due to the acquisition characteristics of station-type scanning equipment, it is necessary to move the station frequently, resulting in cumbersome data processing, unsatisfactory efficiency of 3D point cloud modeling, and point cloud fusion is prone to inaccuracy.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, storage medium and electronic device for processing regional point cloud data, so as to at least solve the technical problem of unsatisfactory efficiency in generating regional point cloud data existing in the related art.

[0005] According to one aspect of an embodiment of the present invention, a method for processing regional point cloud data is provided, comprising: determining a travel route for collecting data on a target area, wherein a plurality of targets are arranged along the travel route; controlling a first collection device to collect data on the target area along the travel route to obtain first regional point cloud data, wherein the first regional point cloud data includes target point cloud data corresponding to the plurality of targets respectively; controlling a second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein a collection speed of the first collection device is greater than a collection speed of the second collection device, and a collection accuracy of the first collection device is less than a collection accuracy of the second collection device; determining target regional point cloud data of the target area based on the first regional point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets respectively.

[0006] Optionally, determining the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the multiple targets respectively, includes: determining a reference coordinate system; determining the target poses of the target point cloud data corresponding to the multiple targets respectively in the reference coordinate system; performing a coordinate system conversion on the first area point cloud data based on the target poses corresponding to the multiple targets respectively, to obtain second area point cloud data in the reference coordinate system; performing a coordinate system conversion on the first device point cloud data based on the target poses corresponding to the multiple targets respectively, to obtain second device point cloud data in the reference coordinate system; and fusing the second area point cloud data and the second device point cloud data to obtain the target area point cloud data.

[0007] Optionally, the fusing of the second area point cloud data and the second device point cloud data to obtain the target area point cloud data includes: determining predetermined features of the predetermined device; based on the predetermined features, performing feature extraction on the second area point cloud data to obtain first feature point data; based on the predetermined features, performing feature extraction on the second device point cloud data to obtain second feature point data; based on the first feature point cloud data and the second feature point cloud data, registering the second area point cloud data and the second device point cloud data to obtain the target area point cloud data.

[0008] Optionally, there are multiple predetermined devices, and the multiple predetermined devices are adjacent and in a predetermined order, and the coordinate system conversion is performed on the first device point cloud data based on the target postures corresponding to the multiple targets respectively, to obtain the second device point cloud data in the reference coordinate system, including: based on the target postures corresponding to the multiple targets respectively, the coordinate system conversion is performed on the first device point cloud data corresponding to the multiple predetermined devices respectively, to obtain the third device point cloud data corresponding to the multiple predetermined devices in the reference coordinate system; according to a predetermined overlap, the third device point cloud data corresponding to the multiple predetermined devices respectively are filtered out to obtain the second device point cloud data corresponding to the multiple predetermined devices respectively, wherein the data volume of the second device point cloud data is less than the data volume of the third device point cloud data.

[0009] Optionally, there are multiple predetermined devices, and the multiple predetermined devices are adjacent and in a predetermined order, and controlling the second acquisition device to acquire data from the predetermined devices in the target area to obtain first device point cloud data includes: controlling the second acquisition device to acquire data from the multiple predetermined devices respectively according to the predetermined order and predetermined overlap, to obtain first device point cloud data respectively corresponding to the multiple predetermined devices, wherein the first device point cloud data respectively corresponding to adjacent predetermined devices among the multiple predetermined devices overlap with the predetermined overlap.

[0010] Optionally, the first acquisition device is a first mobile device carrying a synchronous positioning and map building device, the second acquisition device is a second mobile device carrying a station-type scanning device, and the first mobile device and the second mobile device are any one of the following: a ground robot, a drone, and an autonomous driving vehicle.

[0011] Optionally, determining a route for collecting data on a target area comprises: acquiring a plurality of collection points in the target area; determining a candidate route that passes through at least the plurality of collection points; when there are a plurality of candidate routes, determining repeated collection distances corresponding to the plurality of candidate routes respectively; and determining the route with the shortest repeated collection distance among the plurality of candidate routes as the route.

[0012] According to another aspect of an embodiment of the present invention, a regional point cloud data processing device is provided, comprising: a determination module, for determining a travel route for collecting data on a target area, wherein a plurality of targets are arranged along the travel route; a first control module, for controlling a first collection device to collect data on the target area along the travel route to obtain first regional point cloud data, wherein the first regional point cloud data includes target point cloud data corresponding to the plurality of targets respectively; a second control module, for controlling a second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein a collection speed of the first collection device is greater than a collection speed of the second collection device, and a collection accuracy of the first collection device is less than a collection accuracy of the second collection device; and a fusion module, for determining the target regional point cloud data of the target area based on the first regional point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets respectively.

[0013] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing any one of the regional point cloud data processing methods.

[0014] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the regional point cloud data processing methods.

[0015] In an embodiment of the present invention, a travel route for collecting data on a target area is determined, wherein a plurality of targets are arranged along the travel route; a first collection device is controlled to collect data on the target area along the travel route to obtain first area point cloud data, wherein the first area point cloud data includes target point cloud data corresponding to the plurality of targets respectively; a second collection device is controlled to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein the collection speed of the first collection device is greater than the collection speed of the second collection device, and the collection accuracy of the first collection device is less than the collection accuracy of the second collection device; based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets respectively, the target area point cloud data of the target area is determined. The purpose of generating area point cloud by combining different collection devices is achieved, and the technical effect of improving the processing efficiency of area point cloud data is realized, thereby solving the technical problem of unsatisfactory efficiency of generating area point cloud data existing in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flowchart of an optional regional point cloud data processing method provided according to an embodiment of the present invention;

[0018] Figure 2 is a target schematic diagram of an optional regional point cloud data processing method provided in an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a first acquisition device of an optional regional point cloud data processing method provided by an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of a second acquisition device of an optional regional point cloud data processing method provided by an embodiment of the present invention;

[0021] Figure 5 is a schematic diagram of a target area of ​​an optional regional point cloud data processing method provided in an embodiment of the present invention;

[0022] Figure 6 It is a schematic diagram of an optional regional point cloud data processing device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0026] SLAM (Simultaneous Localization and Mapping) is a mobile scanning technology. SLAM technology is a technology that uses sensor data to simultaneously achieve the positioning and mapping of robots or unmanned vehicles. SLAM devices use various sensors (such as cameras, lidar, and inertial measurement units) to perceive the environment and use algorithms to estimate the device's position in the environment and build a map of the environment.

[0027] The ICP (Iterative Closest Point) algorithm is an iterative closest point algorithm used to align one point cloud to another point cloud. It is commonly used in point cloud registration, 3D reconstruction, point cloud matching and other fields.

[0028] RTK (Real-Time Kinematic) is a global navigation satellite system (GNSS) positioning technology that can provide high-precision position measurement by using differential data between a base station and a mobile device. RTK technology measures the delay and error of satellite signal propagation to correct the positioning data of the receiving device, thereby achieving centimeter-level or sub-centimeter-level accurate measurement.

[0029] According to an embodiment of the present invention, a method embodiment of regional point cloud data processing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a method for processing regional point cloud data according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step S102, determining a route for collecting data of the target area, wherein a plurality of targets are arranged along the route;

[0032] It can be understood that the multiple targets set along the route are used for point cloud positioning, so as to improve the registration efficiency during point cloud fusion and determine the route for collection in the target area.

[0033] Optionally, the above target can be set as follows Figure 2 The black and white cross pattern shown.

[0034] In an optional embodiment, determining a travel route for collecting data in a target area includes: acquiring multiple collection points in the target area; determining a candidate route that passes through at least multiple collection points; in the case of multiple candidate routes, determining repeated collection distances corresponding to the multiple candidate routes respectively; and determining the route with the smallest repeated collection distance among the multiple candidate routes as the travel route.

[0035] It can be understood that the multiple collection points set in the target area represent at least the points that need to be passed through. In order to reduce the amount of collected data, it is expected that the repeated collection distance in the candidate path is relatively small. Among multiple candidate routes, the one with the smallest repeated collection distance is determined as the route for executing collection.

[0036] Step S104, controlling the first acquisition device to acquire the target area along the travel route to obtain first area point cloud data, wherein the first area point cloud data includes target point cloud data corresponding to the plurality of targets respectively;

[0037] It can be understood that the first acquisition device is controlled to collect data on the target area along the travel route. Since the first acquisition device can collect data on multiple targets set along the travel route, the target point cloud data corresponding to the multiple targets can be obtained.

[0038] Optionally, the first acquisition device is to fix the SLAM device on the robot, and collect data along the travel route at a normal rate. At this time, the collected data includes not only buildings, roads, and large equipment but also targets.

[0039] Step S106, controlling the second acquisition device to acquire the predetermined device in the target area to obtain the point cloud data of the first device, wherein the acquisition speed of the first acquisition device is greater than the acquisition speed of the second acquisition device, and the acquisition accuracy of the first acquisition device is less than the acquisition accuracy of the second acquisition device;

[0040] It can be understood that since different acquisition devices have different acquisition characteristics, the characteristics of different devices can be combined for acquisition, thereby improving data acquisition efficiency. The acquisition speed of the first acquisition device is greater than the acquisition speed of the second acquisition device, and the acquisition accuracy of the first acquisition device is less than the acquisition accuracy of the second acquisition device. The second acquisition device is controlled to collect data from the predetermined device in the target area, and data with higher accuracy can be collected from the predetermined device at a fixed point according to demand.

[0041] Optionally, the predetermined equipment may be of multiple types, such as equipment, pipe networks, valves, flanges and other objects with high precision requirements.

[0042] In an optional embodiment, the first collection device is a first mobile device carrying a synchronous positioning and map building device, the second collection device is a second mobile device carrying a station-type scanning device, and the first mobile device and the second mobile device are any one of the following: a ground robot, a drone, and an autonomous driving vehicle.

[0043] It can be understood that the first mobile device and the second mobile device to be selected are determined according to the specific terrain and collection conditions of the target area.

[0044] Optionally, the first acquisition device may be a mobile SLAM device such as Figure 3 As shown, the mobile scanning device (RTK function) can be fixed on a movable device. Based on SLAM technology, the device can continuously collect data on a robot or scanning dog. It has the characteristics of fast collection speed and no need for subsequent data splicing. The collection distance is effective (less than 80m), the data accuracy is low (within 1cm), and the collection density is low.

[0045] Optionally, the second acquisition device may be a station-type scanning device such as Figure 4 As shown, the station-type equipment can be fixed on a movable device. The device emits laser light to the object through the instrument, and after reflection, the instrument records and measures the three-dimensional coordinates and reflectivity of the measured object. The advantages of this instrument are high data acquisition accuracy (millimeter level), long acquisition distance (greater than 100m), and high point cloud density. Due to the frequent station setting and the cumbersome and time-consuming data splicing in the later stage, it is generally widely used for three-dimensional scanning of high-precision equipment, devices and other objects.

[0046] In an optional embodiment, there are multiple predetermined devices, and the multiple predetermined devices are adjacent and in a predetermined order. The second acquisition device is controlled to acquire data from the predetermined devices in the target area to obtain first device point cloud data, including: controlling the second acquisition device to acquire data from the multiple predetermined devices respectively according to the predetermined order and predetermined overlap degree to obtain first device point cloud data respectively corresponding to the multiple predetermined devices, wherein the first device point cloud data respectively corresponding to adjacent predetermined devices among the multiple predetermined devices overlap with a predetermined overlap degree.

[0047] It can be understood that in order to ensure the integrity of the collected data and reduce the complexity of data source sorting, when the second collection device is controlled to collect data from the predetermined device, its corresponding first device point cloud data can be obtained, and there is a predetermined degree of overlap between the first device point cloud data of multiple adjacent predetermined devices.

[0048] It should be noted that when performing station-based data collection, maintaining a certain degree of overlap has the following effects: by increasing the overlapping part, the possible missing or error in data collection can be compensated, thereby improving the integrity and accuracy of the data. The overlapping part can provide multiple observation values. By measuring the overlapping area multiple times, the consistency and reliability of the data can be checked and verified, thereby improving the quality of the data. The existence of the overlapping part can provide multiple perspectives and observation angles, thereby increasing the availability of the data. This is very important for subsequent data processing, analysis and modeling. The overlapping part can provide redundant data, thereby simplifying the data processing process. In data registration, splicing and fusion, the overlapping part can provide additional information, which can more accurately match and align data. Data from multiple perspectives can also be used in the map generation process, thereby improving the accuracy and precision of the map. The overlapping part can provide more feature points and matching points, which helps to improve the density and detail expression ability of the map. Therefore, maintaining a certain degree of overlap can improve the integrity, quality and availability of the data, reduce the complexity of data processing, and improve the accuracy of map generation. Therefore, when performing station-based data collection, it is preferred to maintain an overlap of more than 60%.

[0049] Step S108, determining the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets.

[0050] In an optional embodiment, based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to multiple targets, the target area point cloud data of the target area is determined, including: determining a reference coordinate system; determining the target poses of the target point cloud data corresponding to the multiple targets in the reference coordinate system; based on the target poses corresponding to the multiple targets, performing a coordinate system conversion on the first area point cloud data to obtain the second area point cloud data in the reference coordinate system; based on the target poses corresponding to the multiple targets, performing a coordinate system conversion on the first device point cloud data to obtain the second device point cloud data in the reference coordinate system; and fusing the second area point cloud data and the second device point cloud data to obtain the target area point cloud data.

[0051] It can be understood that in order to fuse the collected data, it is necessary to unify the coordinate system. In order to ensure that the point cloud fusion will not be inaccurate, the target point cloud data is used for positioning. The target point cloud data corresponding to multiple targets can determine the target pose in the reference coordinate system. By obtaining the target poses corresponding to multiple targets, the coordinate system of the first area point cloud data domain is transformed into the second area point cloud data in the reference coordinate system. And the coordinate system of the first device point cloud data is transformed, which can be converted into the second device point cloud data in the reference coordinate system. The second area point cloud data and the second device point cloud data are fused to obtain the target area point cloud data.

[0052] Optionally, the reference coordinate system may be a world coordinate system, or a predetermined coordinate system set according to specific requirements.

[0053] In an optional embodiment, the second area point cloud data and the second device point cloud data are fused to obtain the target area point cloud data, including: determining predetermined features of the predetermined device; based on the predetermined features, performing feature extraction on the second area point cloud data to obtain first feature point data; based on the predetermined features, performing feature extraction on the second device point cloud data to obtain second feature point data; based on the first feature point cloud data and the second feature point cloud data, registering the second area point cloud data and the second device point cloud data to obtain the target area point cloud data.

[0054] It can be understood that the second device point cloud data supplements the second area point cloud data in a refined processing method. In order to obtain detailed data of the predetermined device of focus in the area, the above two point cloud data need to be fused. In the fusion process, it is necessary to match based on the predetermined features, and use the first feature point data and the second feature point data to perform registration processing on the second area point cloud data and the second device point cloud data, so as to obtain the target area point cloud data with higher accuracy.

[0055] Optionally, there are many ways to align the second area point cloud data and the second device point cloud data, such as: performing data preprocessing, preprocessing the above two point cloud data, including noise removal, filtering, coordinate system conversion, etc., for subsequent splicing operations. Since the two point cloud data are already in the same coordinate system, feature extraction and matching can be used, such as using feature descriptors (such as SIFT, SURF, etc.) to extract the first feature point data and the second feature point cloud data. SIFT is Scale-Invariant Feature Transform, and its full name in Chinese is scale-invariant feature transform, which is used to detect and describe local features in images. SURF, Speeded Up Robust Features, is an improved algorithm based on scale-invariant feature transform, which can stably detect and match feature points under different scales, rotations and lighting conditions. Then use a feature matching algorithm, such as the nearest neighbor algorithm or RANSAC (RANdom SAmpleConsensus, random sampling consistency) algorithm, to match the first feature point data and the second feature point cloud data. Based on the matched feature points, the rigid body transformation relationship between the second area point cloud data and the second device point cloud data is estimated. For example, the ICP (Iterative Closest Point) algorithm is used for rigid body transformation estimation. The basic idea of ​​the ICP algorithm is to find an optimal rigid body transformation (rotation and translation) through continuous iteration to align one point cloud to another point cloud. According to the rigid body transformation relationship, the coordinates of the second device point cloud data are transformed, and then fused with the second area point cloud data to obtain the final target area point cloud data. Since there may be some discontinuous or non-smooth areas in the target area point cloud, further point cloud processing may be required, such as surface reconstruction or point cloud smoothing.

[0056] Optionally, since the ICP algorithm is sensitive to the initial estimate, some preprocessing methods, such as coarse matching or global registration, can be used to provide a better initial estimate. In addition, the ICP algorithm may be time-consuming when processing large-scale point cloud data. Some acceleration techniques, such as kd-tree (k-dimensional tree) or octree (octree), can be used to improve the efficiency of the algorithm.

[0057] In an optional embodiment, there are multiple predetermined devices, and the multiple predetermined devices are adjacent and in a predetermined order. Based on the target postures corresponding to the multiple targets, the coordinate system transformation is performed on the first device point cloud data to obtain the second device point cloud data in the reference coordinate system, including: based on the target postures corresponding to the multiple targets, the coordinate system transformation is performed on the first device point cloud data corresponding to the multiple predetermined devices to obtain the third device point cloud data corresponding to the multiple predetermined devices in the reference coordinate system; according to a predetermined overlap, the third device point cloud data corresponding to the multiple predetermined devices are filtered out to obtain the second device point cloud data corresponding to the multiple predetermined devices, wherein the data volume of the second device point cloud data is less than the data volume of the third device point cloud data.

[0058] It can be understood that there may be multiple predetermined devices in the target area, which are arranged adjacent to each other in a predetermined order on the route. In order to ensure data integrity and facilitate positioning, there is a predetermined overlap and coincidence. After the coordinate system conversion, it is necessary to filter out the overlapping parts according to the predetermined overlap to obtain the second device point cloud data corresponding to the multiple predetermined devices. In this way, the amount of data can be effectively reduced and the efficiency of subsequent point cloud data processing can be improved.

[0059] Through the above step S102, the travel route for collecting data on the target area is determined, wherein multiple targets are set along the travel route; step S104, control the first collection device to collect data on the target area along the travel route to obtain first area point cloud data, wherein the first area point cloud data includes target point cloud data corresponding to multiple targets respectively; step S106, control the second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein the collection speed of the first collection device is greater than the collection speed of the second collection device, and the collection accuracy of the first collection device is less than the collection accuracy of the second collection device; step S108, based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to multiple targets respectively, determine the target area point cloud data of the target area. The purpose of generating regional point clouds by combining different collection devices can be achieved, and the technical effect of improving the processing efficiency of regional point cloud data is achieved, thereby solving the technical problem of unsatisfactory efficiency of generating regional point cloud data existing in the related art.

[0060] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method, which is mainly applied to oil and gas field stations, and the above oil and gas stations are taken as target areas (stations include equipment, pipe networks, valves and other predetermined precision equipment, and houses, roads and other facilities with low precision requirements). Figure 5As shown in the figure, a schematic diagram of some areas is provided, and it can be seen that the main components with high acquisition accuracy requirements are equipment pipelines, valves, etc. Of course, this method is not limited to the above-mentioned oil and gas field stations, but can also be applied to cadastral surveying, ordinary building surveying, etc.

[0061] Determine the route of the SLAM (equipped with GNSS-RTK) equipment in the oil and gas field station. In order to quickly complete the data collection of the collected objects in the station, the determined route needs to reduce the route overlap during the collection process and reduce the data collection volume of the SLAM equipment. Targets with black and white cross patterns are set along the route to facilitate the collection and registration of point cloud data.

[0062] The SLAM device is fixed on the ground robot (i.e., the first acquisition device) and data is collected along the above-mentioned route at a normal rate. At this time, the collected data includes not only buildings, roads, and large equipment, but also targets. After the first area point cloud data is collected, it includes target point cloud data corresponding to multiple targets.

[0063] The station uses a station-type scanner set on a ground robot (i.e., the second acquisition device) to collect the precision equipment, facilities, valves, etc. in the station. During the acquisition, the two adjacent stations maintain an overlap of more than 60% to obtain the point cloud data of the first equipment. According to the effective scanning distance of the mobile scanning device of 60%, the threshold is set to automatically filter out the redundant point cloud data to reduce data redundancy.

[0064] Since the clearly identifiable targets along the line are collected, the coordinates of the target points can be output in batches, and the target points with the same name can be found in the same reference coordinate system for positioning and matching. It is also possible to select a predetermined number of target points, adopt the 7-parameter principle, perform coordinate conversion, and convert the first area point cloud data and the first device point cloud data to the reference coordinate system, so that the above two types of data have coordinate attributes, and obtain the second area point cloud data and the second device point cloud data.

[0065] By fusing and registering the second area point cloud data and the second device point cloud data and filtering out the overlapping data, data collection of all elements within the oil and gas station can be efficiently realized.

[0066] The optional implementation method described above can achieve at least one of the following effects: data collection efficiency is increased by 40%. Mobile scanning equipment does not require single station scanning and subsequent data splicing, and the operation efficiency is increased by 40% compared with the station scanning efficiency, and the data processing efficiency is increased by more than 15%. After the above method is used, the station scanning uses visual overlap for automatic splicing, and the efficiency is increased by more than 15% compared with manual splicing.

[0067] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0068] In this embodiment, a regional point cloud data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0069] According to an embodiment of the present invention, a device embodiment for implementing a method for processing regional point cloud data is also provided. Figure 6 is a schematic diagram of a regional point cloud data processing device according to an embodiment of the present invention. Figure 6 As shown, the above-mentioned regional point cloud data processing device includes a determination module 602, a first control module 604, a second control module 606, and a fusion module 608. The device is described below.

[0070] A determination module 602 is used to determine a travel route for collecting data from a target area, wherein a plurality of targets are arranged along the travel route;

[0071] The first control module 604 is connected to the determination module 602 and is used to control the first acquisition device to acquire the target area along the travel route to obtain the first area point cloud data, wherein the first area point cloud data includes the target point cloud data corresponding to the multiple targets respectively;

[0072] The second control module 606 is connected to the first control module 604 and is used to control the second acquisition device to acquire the predetermined device in the target area to obtain the point cloud data of the first device, wherein the acquisition speed of the first acquisition device is greater than the acquisition speed of the second acquisition device, and the acquisition accuracy of the first acquisition device is less than the acquisition accuracy of the second acquisition device;

[0073] The fusion module 608 is connected to the second control module 606, and is used to determine the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the multiple targets.

[0074] In a regional point cloud data processing device provided by an embodiment of the present invention, a determination module 602 is used to determine a travel route for collecting data on a target area, wherein a plurality of targets are arranged along the travel route; a first control module 604 is connected to the determination module 602, and is used to control a first collection device to collect data on the target area along the travel route to obtain first regional point cloud data, wherein the first regional point cloud data includes target point cloud data corresponding to a plurality of targets respectively; a second control module 606 is connected to the first control module 604, and is used to control a second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein a collection speed of the first collection device is greater than a collection speed of the second collection device, and a collection accuracy of the first collection device is less than a collection accuracy of the second collection device; a fusion module 608 is connected to the second control module 606, and is used to determine the target regional point cloud data of the target area based on the first regional point cloud data, the first device point cloud data, and the target point cloud data corresponding to a plurality of targets respectively. The purpose of combining different acquisition devices to generate regional point clouds is achieved, the technical effect of improving the efficiency of regional point cloud data processing is achieved, and the technical problem of unsatisfactory regional point cloud data generation efficiency existing in related technologies is solved.

[0075] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0076] It should be noted that the determination module 602, the first control module 604, the second control module 606, and the fusion module 608 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the modules as part of the device can be run in a computer terminal.

[0077] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0078] The above-mentioned regional point cloud data processing device may also include a processor and a memory. The determination module 602, the first control module 604, the second control module 606, the fusion module 608, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0079] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0080] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a method for processing regional point cloud data is implemented.

[0081] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: determining a travel route for collecting data on a target area, wherein a plurality of targets are arranged along the travel route; controlling a first collection device to collect data on the target area along the travel route to obtain first area point cloud data, wherein the first area point cloud data includes target point cloud data corresponding to a plurality of targets; controlling a second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein the collection speed of the first collection device is greater than the collection speed of the second collection device, and the collection accuracy of the first collection device is less than the collection accuracy of the second collection device; determining the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to a plurality of targets. The device in this article may be a server, a PC, etc.

[0082] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: determining a travel route for collecting data on a target area, wherein a plurality of targets are arranged along the travel route; controlling a first collection device to collect data on the target area along the travel route to obtain first area point cloud data, wherein the first area point cloud data includes target point cloud data corresponding to the plurality of targets respectively; controlling a second collection device to collect data on a predetermined device in the target area to obtain first device point cloud data, wherein a collection speed of the first collection device is greater than a collection speed of the second collection device, and a collection accuracy of the first collection device is less than a collection accuracy of the second collection device; and determining the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets respectively.

[0083] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0089] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0091] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0092] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for processing regional point cloud data, characterized in that: include: Determining a travel route for collecting data from a target area, wherein a plurality of targets are arranged along the travel route; Controlling a first acquisition device to acquire point cloud data of the target area along the travel route to obtain point cloud data of the first area, wherein the point cloud data of the first area includes target point cloud data corresponding to the multiple targets respectively; Controlling the second acquisition device to acquire the predetermined device in the target area to obtain the point cloud data of the first device, wherein the acquisition speed of the first acquisition device is greater than the acquisition speed of the second acquisition device, and the acquisition accuracy of the first acquisition device is less than the acquisition accuracy of the second acquisition device; Based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the multiple targets respectively, the target area point cloud data of the target area is determined.

2. The method according to claim 1, characterized in that The determining the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the plurality of targets respectively includes: Determine the reference coordinate system; Determine the target positions and poses of the target point cloud data respectively corresponding to the multiple targets in the reference coordinate system; Based on the target poses respectively corresponding to the multiple targets, coordinate system conversion is performed on the first area point cloud data to obtain the second area point cloud data in the reference coordinate system; Based on the target poses respectively corresponding to the multiple targets, coordinate system conversion is performed on the first device point cloud data to obtain the second device point cloud data in the reference coordinate system; The second area point cloud data and the second device point cloud data are fused to obtain the target area point cloud data.

3. The method according to claim 2, characterized in that The fusing the second area point cloud data and the second device point cloud data to obtain the target area point cloud data includes: determining a predetermined characteristic of the predetermined device; Based on the predetermined feature, feature extraction is performed on the second area point cloud data to obtain first feature point data; Based on the predetermined feature, extracting features from the second device point cloud data to obtain second feature point data; Based on the first feature point cloud data and the second feature point cloud data, the second area point cloud data and the second device point cloud data are registered to obtain the target area point cloud data.

4. The method according to claim 2, characterized in that: The predetermined devices are multiple, the multiple predetermined devices are adjacent and in a predetermined order, and the coordinate system conversion is performed on the first device point cloud data based on the target poses corresponding to the multiple targets respectively to obtain the second device point cloud data in the reference coordinate system, including: Based on the target poses respectively corresponding to the multiple targets, coordinate system conversion is performed on the first device point cloud data respectively corresponding to the multiple predetermined devices to obtain the third device point cloud data respectively corresponding to the multiple predetermined devices in the reference coordinate system; According to a predetermined degree of overlap, the third device point cloud data corresponding to the plurality of predetermined devices are filtered out to obtain the second device point cloud data corresponding to the plurality of predetermined devices, wherein the amount of data of the second device point cloud data is smaller than the amount of data of the third device point cloud data.

5. The method according to claim 1, characterized in that The predetermined devices are multiple, the multiple predetermined devices are adjacent and in a predetermined order, and the controlling the second acquisition device to acquire the predetermined devices in the target area to obtain the first device point cloud data includes: According to the predetermined order and the predetermined overlap, the second acquisition device is controlled to respectively acquire data from the multiple predetermined devices to obtain first device point cloud data respectively corresponding to the multiple predetermined devices, wherein the first device point cloud data respectively corresponding to adjacent predetermined devices among the multiple predetermined devices overlap with the predetermined overlap.

6. The method according to claim 1, characterized in that The first acquisition device is a first mobile device carrying a synchronous positioning and map building device, the second acquisition device is a second mobile device carrying a station-type scanning device, and the first mobile device and the second mobile device are any one of the following: a ground robot, a drone, and an autonomous driving vehicle.

7. The method according to any one of claims 1 to 6, characterized in that: The step of determining a route for collecting data from a target area includes: Acquire multiple acquisition points in the target area; Determine a candidate route that passes through at least the plurality of collection points; In the case where there are multiple candidate routes, determining the repeated collection distances respectively corresponding to the multiple candidate routes; Among the multiple candidate routes, a route with the smallest repeated collection distance is determined as the travel route.

8. A regional point cloud data processing device, characterized in that: include: A determination module, used to determine a travel route for collecting data from a target area, wherein a plurality of targets are arranged along the travel route; A first control module is used to control a first acquisition device to acquire point cloud data of the target area along the travel route to obtain point cloud data of the first area, wherein the point cloud data of the first area includes target point cloud data corresponding to the multiple targets respectively; A second control module is used to control a second acquisition device to acquire the predetermined device in the target area to obtain the point cloud data of the first device, wherein the acquisition speed of the first acquisition device is greater than the acquisition speed of the second acquisition device, and the acquisition accuracy of the first acquisition device is less than the acquisition accuracy of the second acquisition device; A fusion module is used to determine the target area point cloud data of the target area based on the first area point cloud data, the first device point cloud data, and the target point cloud data corresponding to the multiple targets.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the regional point cloud data processing method described in any one of claims 1 to 6.

10. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the regional point cloud data processing method described in any one of claims 1 to 6.

Images