KR102589483B1 - System and method for inspecting road facilities using artificial intelligence - Google Patents

Abstract

The present invention relates to a rover-based 3D scanning mobile mapping system and method for supporting construction infrastructure scanning work, which includes a GPS sensor for acquiring location sensing data, an IMU sensor for acquiring motion sensing data, and 3D scanning of a construction site in real time. It may include a scanner that acquires scanning data for each viewpoint, and a mobile mapping module that fuses location sensing data, motion sensing data, and scanning data for each viewpoint, and performs real-time PCD registration by applying the SLAM algorithm.

Description

Rover-based 3D scanning mobile mapping system and method for supporting construction infrastructure scanning operations {System and method for inspecting road facilities using artificial intelligence}

The present invention relates to a rover-based 3D scanning mobile mapping system and method. More specifically, construction infrastructure scanning work that can increase scanning productivity by utilizing mobile mapping capable of real-time data matching and ground rover technology. It relates to a support rover-based 3D scanning mobile mapping system and method.

Recently, the need for smart construction technology has been increasing in the construction industry. In order for smart construction technology to be implemented, construction site data collection is essential.

Construction site data can be acquired using various sensors suitable for the purpose. Among the acquired construction site data, 3D scan data can be used for various purposes compared to other sensor data.

3D scan data reproduces the site situation in 3D, so after data collection, the exact location, size, and volume of construction facilities can be obtained from the 3D digital model whenever necessary without the need for workers to visit and investigate the site each time.

In particular, 3D scan data contains useful data and is used in various applications such as precision construction, unmanned autonomous vehicles, robotics, and 3D map creation.

There are two types of scan data acquisition: fixed LiDAR (Light Detection and Ranging) technology and mobile LiDAR technology. Fixed LiDAR technology has higher accuracy and density than mobile LiDAR, but it takes a long time for workers to reinstall heavy sensor equipment every time they scan, and to post-process and match data after scanning.

Therefore, in the field of building management, which requires relatively high accuracy, there is a need for technology that can scan space while freely moving and match the scanning results to provide spatial information.

Domestic Public Patent No. 10-2019-0045006

In order to solve the above-mentioned problems, the technical problem that the present invention aims to achieve is a rover-based 3D scanning mobile mapping system (R) that can increase scanning productivity by utilizing mobile mapping capable of real-time data matching and ground-type rover technology. -To present MMS (Rover-based Mobile Mapping System) and method.

The problems of the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

As a means to solve the above-described technical problem, a rover-based 3D scan data mobile mapping device according to an embodiment of the present invention includes a GPS sensor for acquiring location sensing data; IMU sensor (Inertial Measurement Unit) that acquires motion sensing data; A scanner that 3D scans the construction site in real time to obtain scanning data at each point in time; and a mobile mapping module that fuses location sensing data, motion sensing data, and scanning data for each viewpoint, and performs real-time PCD matching by applying the SLAM algorithm. It includes the GPS sensor, IMU sensor, scanner, and mobile mapping. The module can be mounted on a rover that moves around the construction site.

The mobile mapping module includes a filtering unit that filters the location sensing data, motion sensing data, and scanning data for each viewpoint; An SDF (Sensor Data Fusion) unit that generates a scan data set by synchronizing and fusing data acquisition points of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint; A SLAM unit that performs real-time PCD registration by applying a SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and a data management unit that stores and manages the scan data set generated in the SDF unit in a DB.

In order to synchronize the data acquisition time, the SDF unit may synchronize the filtered position sensing data and motion sensing data based on the filtered scanning data for each time point.

Meanwhile, a rover-based 3D scan data mobile mapping method according to another embodiment of the present invention includes the steps of: (A) a GPS sensor acquiring location sensing data while the rover moves around the construction site along a scan movement path; (B) a step in which an IMU sensor (Inertial Measurement Unit) acquires motion sensing data; (C) obtaining scanning data for each viewpoint by using a scanner to 3D scan the construction site in real time; and (D) the mobile mapping module fusing the location sensing data, motion sensing data, and scanning data for each viewpoint, and performing real-time PCD matching by applying a SLAM algorithm.

The step (D) includes (D1) filtering the location sensing data, motion sensing data, and scanning data for each viewpoint; (D2) synchronizing the data acquisition time points of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint and fusing them to create a scan data set; (D3) performing real-time PCD registration by applying the SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and (D4) storing and managing the scan data set generated in step (D2) in a DB.

In step (D2), in order to synchronize the data acquisition time, the filtered location sensing data and the motion sensing data may be synchronized based on the filtered scanning data for each time point.

Meanwhile, a rover-based 3D scan data mobile mapping system according to another embodiment of the present invention includes a rover that moves around a construction site along a scanned path; And the rover's position sensing data, motion sensing data, and scanning data for each viewpoint acquired by 3D scanning the construction site in real time are fused, and a SLAM algorithm is applied to the scanning data for each viewpoint acquired while the scanner moves. It may include a mobile mapping device that performs real-time PCD matching.

The mobile mapping device includes a GPS sensor that acquires the location sensing data; An IMU sensor (Inertial Measurement Unit) that acquires the motion sensing data; A scanner that 3D scans the construction site in real time to obtain scanning data for each viewpoint; And a mobile mapping module that fuses the location sensing data, motion sensing data, and scanning data for each viewpoint, and performs real-time PCD matching by applying the SLAM algorithm; including, the GPS sensor, IMU sensor, scanner, and mobile The mapping module can be mounted on a rover moving around a construction site.

The mobile mapping module includes a filtering unit that filters the location sensing data, motion sensing data, and scanning data for each viewpoint; An SDF (Sensor Data Fusion) unit that generates a scan data set by synchronizing and fusing data acquisition points of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint; A SLAM unit that performs real-time PCD registration by applying a SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and a data management unit that stores and manages the scan data set generated in the SDF unit in a DB.

In order to synchronize the data acquisition time, the SDF unit may synchronize the filtered position sensing data and motion sensing data based on the filtered scanning data for each time point.

According to the present invention, the site is scanned in real time while moving around the site using a rover, the PCD, GPS sensing data, and IMU sensing data obtained through scanning are fused in real time, and then SLAM is matched to enable confirmation at low cost. Spatial information can also be provided in real time.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram illustrating a rover-based 3D scan data mobile mapping system according to an embodiment of the present invention;
2 is a block diagram showing the mobile mapping device 300 according to an embodiment of the present invention, where 1 shown in FIG. 1 is a block diagram.
3 is a block diagram detailing the processor 384;
Figure 4 is a diagram for explaining the SDF algorithm by which the SDF unit 384b synchronizes sensing data;
Figure 5 is an example of the R-MMS DB architecture designed in UML (Unified Modeling Language).
Figure 6 is a diagram defining the data sets that are exchanged, processed, and managed between each component in R-MMS, and
Figure 7 is a flowchart showing a mobile mapping method according to an embodiment of the present invention.

Before explaining the specific details for practicing the present invention, the terms and words used in the specification and claims may be used by the inventor to appropriately define the concept of the term in order to explain the invention in the best way. It should be interpreted as meaning and concept consistent with the technical details of the present invention based on the principle that it is.

Additionally, it should be noted that if a detailed description of a known function related to the present invention and its configuration is judged to unnecessarily obscure the gist of the present invention, the detailed description has been omitted.

If any element, component, device, or system is said to contain a component consisting of a program or software, even if explicitly stated, that element, component, device, or system is not intended to allow that program or software to run or operate. It should be understood as including hardware (e.g., memory, CPU, etc.) or other programs or software (e.g., operating system or drivers required to run the hardware) required to run the computer.

In addition, unless specifically stated in the implementation of an element (or component), it should be understood that the element (or component) may be implemented in any form of software, hardware, or software and hardware.

Additionally, in this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the module may mean a logical unit of a predetermined code and hardware resources for executing the predetermined code, and does not necessarily mean a physically connected code or one type of hardware. It can be easily inferred by an average expert in the technical field.

Hereinafter, specific technical details to be implemented in the present invention will be described in detail with reference to the accompanying drawings.

Each configuration of the devices shown in FIGS. 1 to 3 indicates that each configuration can be separated functionally and/or logically, and does not necessarily mean that each configuration is divided into a separate physical device or generated with separate code. An average expert in the technical field of the present invention will be able to easily deduce.

Figure 1 is a diagram illustrating a rover-based 3D scan data mobile mapping system according to an embodiment of the present invention.

Referring to FIG. 1, a rover-based 3D scan data mobile mapping system according to an embodiment of the present invention may include a rover 100, a remote monitoring device 200, and a mobile mapping device 300.

The rover 100 can automatically move around the construction site along the scanned movement path.

The rover 100 is a device capable of autonomous driving using wheels, and can drive in various directions including forward, backward, left turn, and right turn according to the control of the mobile mapping device 300 or the user's remote control. there is. In addition, the rover 100 moves at an accurate distance and can move forward, backward, left and right and change direction depending on the rotation angle.

The remote monitoring device 200 receives and displays the status and movement of the rover 100, such as the moving distance, direction of movement, and rotation amount of the rover 100, through the mobile mapping device 300 or directly from the rover 100. , the 3D scanned image scanned from the mobile mapping device 300 can be displayed to allow the user to remotely monitor the rover 100 and the construction site scan results in real time.

In addition, the remote monitoring device 200 sends a remote control signal for controlling the driving of the rover 100 and a remote control signal for controlling the sensing operation of the mobile mapping device 300 to the rover 100 or the mobile mapping device 300. ) can also be sent.

The mobile mapping device 300 is detachably mounted on the rover 100, and includes location sensing data for sensing the position of the rover 100, motion sensing data for sensing the movement of the rover 100, and movement of the rover 100. During this process, scanning data for each viewpoint (or scene) obtained by 3D scanning the construction site in real time can be fused and real-time PCD registration can be performed by applying the SLAM algorithm.

FIG. 2 is a block diagram showing a mobile mapping device 300 according to an embodiment of the present invention shown in FIG. 1.

Referring to FIG. 2, the mobile mapping device 300 according to an embodiment of the present invention includes a power supply unit 310, a rover driver 320, a user interface unit 330, a communication interface unit 340, and a Global Positioning System (GPS). ) It may include a sensor 350, an IMU (Inertial Measurement Unit) sensor 360, a scanner 370, and a mobile mapping module 380.

The power supply unit 310 supplies power to each component 310 to 170 of the mobile mapping device 300 or the rover 100, and may be a battery, for example.

The rover driver 320 can drive the rover 100 and control its movement.

For example, the power supply unit 310 and the rover driving unit 320 may be implemented as a motor driver and a battery system supporting 70 Kg payload, but this is an example and may not be limited thereto.

The user interface unit 330 includes circuitry that provides an interfacing path between the user and the mobile mapping device 300. The user interface unit 330 receives commands from the user to operate the functions provided by the mobile mapping device 300, such as starting scanning, stopping scanning, recording various sensing data, and displaying various sensing data, and provides the mobile mapping device. It can be delivered to (300).

The communication interface unit 340 may transmit data sensed by the GPS sensor 350, IMU sensor 360, or scanner 370 to the remote monitoring device 200 through a wired or wireless communication network. Additionally, the communication interface unit 340 may receive a remote control signal from the remote monitoring device 200 and transmit it to the mobile mapping module 380.

The GPS sensor 350 is mounted on the rover 100 and can sense the current location and transmit the location sensing data to the mobile mapping device 300.

The IMU sensor 360 may be mounted on the rover 100 to acquire motion sensing data of the rover 100 and transmit the obtained motion sensing data to the mobile mapping device 300. The motion sensing data acquired by the IMU sensor 360 is IMU sensor sensing data that includes location information and posture information of the mobile mapping device 300, and can be used during SALM matching to increase matching accuracy.

The scanner 370 can acquire scanning data for each viewpoint (or scene) by 3D scanning the construction site in real time. The scanner 370 may use a mobile 3D LiDAR (Light Detection And Ranging) sensor.

The mobile mapping module 380 fuses the location sensing data of the GPS sensor 350, the movement sensing data of the IMU sensor 360, and the scanning data for each viewpoint of the scanner 370, and performs SLAM (Simultaneous Localization and Mapping) Real-time PCD matching can be performed by applying the algorithm.

The mobile mapping module 380 can perform real-time PCD registration by applying the SLAM algorithm to scanning data acquired while the scanner 370 moves, acquired at the same location with a time difference, or acquired by changing the scanning angle at the same location. there is.

In addition, the mobile mapping module 380 can communicate with terminal sensors and devices to exchange data between each component and exchange messages for function calls. Communication status must be able to be monitored, and if a problem occurs when exchanging data and messages, it must be recorded and diagnosed. Considering this, ROS (Robot Operating System) can be used in the present invention.

Mobile mapping module 380 may include memory 382 and processor 384.

Memory 382 may include volatile memory and/or non-volatile memory. The memory 382 includes, for example, instructions or data related to components, one or more programs, and/or to implement and/or provide operations, functions, etc. provided by the mobile mapping device 300 or the rover 100. Alternatively, software, operating system, etc. may be stored.

The programs stored in the memory 382 are an SDF program for implementing the SDF algorithm for fusion of various types of sensing data, a SLAM program for implementing the SLAM algorithm, and a CGL (Computational Geometry Library) that supports numerical analysis and computational geometry of the SLAM algorithm. ), a Robot Operating System (ROS) and an Embedded Operating System (OS) responsible for exchanging data between the GPS sensor 350, the IMU sensor 360 and the scanner 370 and the processor 384. can do.

The processor 384 controls the overall operation of the mobile mapping device 300 by executing one or more programs stored in the memory 382.

For example, the processor 384 executes the SDF program stored in the memory 382 to collect location sensing data from the GPS sensor 350, motion sensing data from the IMU sensor 360, and scanning data for each viewpoint from the scanner 370. After synchronization, they can be fused. In addition, the processor 384 executes the SLAM program to calculate feature points present in the 3D scan data for each scene, compares the feature points calculated for each scene, performs point cloud matching in real time, and provides spatial information of the facility. You can create and manage scan datasets.

Additionally, if the mobile mapping device 300 is further equipped with a camera (not shown), the processor 384 processes the camera image to be transmitted to the remote monitoring device 200, and the user displays it on the remote monitoring device 200. The rover 100 can be remotely controlled through the camera image.

In addition, the processor 384 can communicate with each component to exchange data and exchange messages for function calls between each component, monitors the communication status, and reports to the memory 382 if a problem occurs during data and message exchange. It can also be recorded and diagnosed.

Figure 3 is a block diagram showing the processor 384 in detail.

Referring to FIG. 3, the processor 384 may include a filtering unit 384a, an SDF unit 384b, a SLAM unit 384c, and a data management unit 384d.

The filtering unit 384a may perform filtering such as noise removal to process the acquired location sensing data, motion sensing data, and scanning data for each viewpoint. Filtered position sensing data, motion sensing data, and scanning data can be input into the SDF algorithm to obtain data required for data matching.

Meanwhile, the Hz cycle at which the GPS sensor 350, IMU sensor 360, and scanner 370 sense data are different. For example, if the scanner 370 operates at 10Hz and the GPS sensor 350 and IMU sensor 360 operate at 100Hz, the timing of data acquisition is different, so each sensing data must be synchronized based on the scanning data. do.

To this end, the SDF unit 384b may input the position sensing data, motion sensing data, and scanning data filtered by the filtering unit 384a into the SDF algorithm to obtain a scan data set necessary for data matching.

The SDF unit 384b can generate a scan data set by synchronizing and then fusing the data acquisition times of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint using the SDF algorithm.

In detail, the SDF unit 384b adds a time stamp to the filtered scanning data in order to synchronize the data acquisition time of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint, and scans the data to which the time stamp has been added. Position sensing data and motion sensing data filtered based on the data can be synchronized. The time stamp may be the point in time when the scanning data is sensed or the time point in which the scanning data is filtered. In the embodiment of the present invention, the sensed point in time is used as an example.

The SDF unit 384b checks the time of the time stamp added to the scanning data, and if there is no position sensing data sensed at the confirmed time, the position sensing data sensed before the confirmed time and the position sensing data sensed after the confirmed time. Using , position sensing data corresponding to the confirmed time can be generated by linear interpolation.

Figure 4 is a diagram for explaining the SDF algorithm by which the SDF unit 384b synchronizes sensing data.

Referring to FIG. 4, the scanning data includes a timestamp (time stamp_LIDAR), and the SDF unit 384b can store the filtered location sensing data (sensor_data_GPS) and motion sensing data (sensor_data_IMU) in a queue (not shown). There is (queue.push(sensor_data)).

The timing of each data sensing may be different for position sensing data, motion sensing data, and 3D scanning data. Therefore, when the SDF unit 384b needs position sensing data and motion sensing data corresponding to the time stamp (time_stamp_LIDAR) of the 3D scanning data, that is, generated (or sensed) at the same time point (time_stamp_LIDAR) as the scanning data. When fusion of position sensing data and motion sensing data is required, based on the time of the time stamp (time_stamp_LIDAR), the position sensing data sensed immediately before and the position sensing data sensed immediately after are read from the queue and processed for linear interpolation. Location sensing data corresponding to the time stamp (time_stamp_LIDAR) can be predicted.

The SDF unit 384b can apply the same synchronization method to motion sensing data to predict motion sensing data corresponding to the timestamp (time_stamp_LIDAR).

In Figure 4, sensor_data is position sensing data and motion sensing data predicted and generated by linear interpolation, P is position sensing data and motion sensing data previously sensed based on the time of the timestamp (time_stamp_LIDAR), and N is later. C is the sensed position sensing data and motion sensing data, and C is the position sensing data and motion sensing data predicted and generated by linear interpolation.

The SDF unit 384b may generate a scan data set (scan_dataset) by fusing data-synchronized position sensing data, motion sensing data, and scanning data. The generated scan data set may be transmitted to the data management unit 384d.

The SLAM unit 384c can perform real-time PCD (Point Cloud Data) matching by applying the SLAM algorithm to scanning data for each viewpoint acquired while the scanner 370 moves. The SLAM unit 384c can perform PCD matching using PCD-type scanning data, position sensing data, and motion sensing data acquired in real time, and the SLAM algorithm. The dataset (registered_dataset) generated by PCT matching may be transmitted to the data management unit 384d.

SLAM technology is a map generation technology developed in the field of robotics that uses a distance measurement sensor or IMU to recognize the current location and create spatial information about facilities.

The data management unit 384d may store and manage the fused scan data set (scan_dataset) and the registered data set (registered_dataset) in a DB (not shown). The data management unit 384d can sense data in real time as the mobile mapping system moves around the field and fuse the sensing data at the time of mapping, thereby storing and managing the fused data set in a time series database structure.

The DB (not shown) may be provided in addition to the system shown in FIG. 1 or may be installed in a remote location, and in the latter case, it can receive and store data through a wired or wireless network.

Figure 5 is an example diagram of the R-MMS DB architecture designed in UML (Unified Modeling Language), and Figure 6 is a diagram defining data sets that are exchanged, processed, and managed between each component in R-MMS. R-MMS stands for robo-based mobile mapping system.

Referring to Figures 5 and 6, scan is a plurality of scan data sets (scan_dataset), and the scan data sets include sequence ID, timestamp, PCD (scanning data), IMU (motion sensing data), and GPS (position sensing data). Includes. Multiple fused scan datasets (scan) and the registered dataset (registered_dataset) are input and managed by the data management unit (MMS_database_management) 384d. Each data set as shown in FIG. 6 may be included in a message when exchanging data between components.

Figure 7 is a flowchart showing a mobile mapping method according to an embodiment of the present invention.

Referring to FIG. 7, while the rover 100 moves around the construction site along the scanning path, the GPS sensor 350 acquires location sensing data, and the acquired location sensing data is stored in a queue (not shown). (S710).

While the rover 100 moves around the construction site along the scanning path, the IMU sensor 360 acquires motion sensing data, and the obtained motion sensing data may be stored in a queue (not shown) (S720).

In addition, while the rover 100 moves the construction site along the scanning path, the scanner 370 acquires scanning data for each viewpoint by 3D scanning the construction site in real time, and the acquired scanning data is stored in a queue (not shown). ) or may be stored in the memory 382 (S730).

The mobile mapping module 380 fuses the location sensing data, motion sensing data, and scanning data for each viewpoint, and applies the SLAM algorithm to perform real-time PCD registration to create a scan data set (scan_dataset) and a registered data set (registered_dataset). ) can be created.

In detail, the mobile mapping module 380 may remove noise by filtering the location sensing data, motion sensing data, and scanning data for each viewpoint obtained in steps S710 to S730 (S740).

The mobile mapping module 380 can generate a scan data set (scan_dataset) by synchronizing and fusing the data acquisition points of the filtered location sensing data, motion sensing data, and scanning data for each viewpoint based on the timestamp of the scanning data. (S750). In step S750, the mobile mapping module 380 can linearly interpolate the location sensing data and the motion sensing data to predict data at a point in time that is not sensed.

In addition, the mobile mapping module 380 can perform real-time PCD matching by applying the SLAM algorithm to scanning data, location sensing data, and motion sensing data synchronized for each viewpoint (S760).

The mobile mapping module 380 stores and manages the scan data set (scan_dataset) created in step S750 and the registered data set (registered_dataset) created in step S760 in the DB (S770).

According to the above-described embodiment of the present invention, R-MMS, a rover-based 3D scanning mobile mapping system that can increase the productivity of scanning work at construction sites, is proposed, and a prototype developed based on the designed R-MMS framework is utilized. After scanning outdoor infrastructure facilities, the results were analyzed. Based on this, considerations for developing mobile scanning equipment that can be used for infrastructure facility management were derived.

R-MMS is lower than fixed LiDAR in terms of accuracy and density. As a result of the test, it was possible to use it in areas that require GSA's Level 2 LoD (Level Of Detail).

R-MMS has high work productivity because one worker checks and scans the FPV within the remote control range. Additionally, since R-MMS itself operates unmanned, there is little risk of safety issues occurring during field work. In this regard, when using unmanned equipment such as R-MMS, it may be necessary to develop guidelines to ensure a certain level of quality of work. If data quality using deep learning technology improves, it will be possible to apply the mobile mapping system in a variety of environments.

In the above, even though all the components constituting the embodiment of the present invention have been described as being combined or operated in combination, the present invention is not necessarily limited to this embodiment. That is, as long as it is within the scope of the purpose of the present invention, all of the components may be operated by selectively combining one or more of them. In addition, although all of the components may be implemented as a single independent hardware, a program module in which some or all of the components are selectively combined to perform some or all of the functions of one or more pieces of hardware. It may also be implemented as a computer program with . The codes and code segments that make up the computer program can be easily deduced by a person skilled in the art of the present invention. Such a computer program can be stored in a computer-readable storage medium and read and executed by a computer, thereby implementing embodiments of the present invention.

Meanwhile, although the preferred embodiments have been described and illustrated to illustrate the technical idea of the present invention, the present invention is not limited to the configuration and operation as shown and described, and does not deviate from the scope of the technical idea. Without limitation, those skilled in the art will understand that many changes and modifications can be made to the present invention. Accordingly, all such appropriate changes, modifications and equivalents should be considered to fall within the scope of the present invention. Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the attached registration claims.

100: Rover
200: remote monitor device
300: mobile mapping device
310: power unit
320: Rover driving unit
330: User interface unit
340: Communication interface unit
350: GPS sensor
360: IMU sensor
370: scanner
380: Mobile mapping module

Claims (10)

GPS sensor that acquires location sensing data;
IMU sensor that acquires motion sensing data;
A scanner that 3D scans the construction site in real time to obtain scanning data at each point in time; and
A mobile mapping module that fuses location sensing data, motion sensing data, and scanning data for each viewpoint, performs real-time PCD registration by applying the SLAM algorithm, and stores and manages the scan data set and registration data set in the database;
Including,
The GPS sensor, IMU sensor, scanner, and mobile mapping module are removably mounted on a rover moving around the construction site.
The mobile mapping module is,
a filtering unit that filters the location sensing data, motion sensing data, and scanning data for each viewpoint;
An SDF (Sensor Data Fusion) unit that generates a scan data set by synchronizing and fusing data acquisition points of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint;
A SLAM unit that performs real-time PCD registration by applying a SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and
A data management unit that stores and manages the scan data set generated in the SDF unit in a DB;
Including,
The SDF department
A timestamp is added to the filtered data to synchronize the acquisition time of location sensing data, motion sensing data, and scanning data for each viewpoint.
The process of synchronizing filtered sensing data and motion sensing data based on scanning data with a timestamp added.
If there is no location data sensed at the confirmed time, position sensing data corresponding to the confirmed time is generated through linear interpolation using the position sensing data sensed before the confirmed time and the position sensing data sensed after the confirmed time. process
A rover-based 3D scan data mobile mapping device for supporting construction infrastructure scanning operations, including further.
delete delete (A) A GPS sensor acquires location sensing data while the rover moves around the construction site along a scanning path;
(B) IMU sensor acquiring motion sensing data;
(C) obtaining scanning data for each viewpoint by using a scanner to 3D scan the construction site in real time; and
(D) a mobile mapping module fusing the location sensing data, motion sensing data, and scanning data for each viewpoint, and performing real-time PCD matching by applying a SLAM algorithm;
Including,
In step (D),
(D1) filtering the location sensing data, motion sensing data, and scanning data for each viewpoint;
(D2) synchronizing the data acquisition time points of the filtered position sensing data, motion sensing data, and scanning data for each viewpoint and fusing them to create a scan data set;
In the step of adding the timestamp of step (D3)
If there is no location data sensed at the confirmed time, position sensing data corresponding to the confirmed time is generated through linear interpolation using the position sensing data sensed before the confirmed time and the position sensing data sensed after the confirmed time. step;
(D4) performing real-time PCD registration by applying the SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and
(D5) storing and managing the scan data set generated in step (D2) in a DB;
A rover-based 3D scan data mobile mapping method for supporting construction infrastructure scanning tasks, comprising:
delete delete A rover moving around a construction site following a scanned path; and
The rover's position sensing data, motion sensing data, and scanning data for each viewpoint acquired by real-time 3D scanning of the construction site are fused, and the SLAM algorithm is applied to the scanning data for each viewpoint acquired as the scanner moves to perform real-time PCD matching. A mobile mapping device that performs;
Including
The mobile mapping device,
A GPS sensor 350 that acquires the location sensing data;
An IMU sensor (Inertial Measurement Unit) that acquires the motion sensing data;
A scanner that 3D scans the construction site in real time to obtain scanning data for each viewpoint;
a filtering unit that filters the location sensing data, motion sensing data, and scanning data for each viewpoint;
The data acquisition time of the filtered location sensing data, motion sensing data, and scanning data for each time point are synchronized and then fused to create a scan data set. If there is no location data sensed at the confirmed time, sensing is performed before the confirmed time. An SDF (Sensor Data Fusion) unit that generates position sensing data corresponding to the confirmed time through linear interpolation using the confirmed position sensing data and the later sensed position sensing data;
A SLAM unit that performs real-time PCD registration by applying a SLAM algorithm to scanning data for each viewpoint acquired while the scanner moves; and
It includes a data management unit that stores and manages the scan data set generated in the SDF unit in the DB,
The GPS sensor, IMU sensor, scanner, and mobile mapping module are removably mounted on a rover moving around a construction site. A rover-based 3D scan data mobile mapping system for supporting construction infrastructure scanning work.

delete delete delete

Images