Construction management system and construction management method

The construction management system uses image and terrain data to track the three-dimensional positions of individuals at a construction site, improving efficiency and safety by accurately locating workers.

JP7739161B2Active Publication Date: 2025-09-16KOMATSU LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2021201058
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-12-10
Publication Date
2025-09-16
Estimated Expiration
2041-12-10

AI Technical Summary

Technical Problem

There is a need to confirm the positions of people at a construction site to prevent a decrease in construction efficiency.

Method used

A construction management system comprising an image data acquisition unit, terrain data storage unit, person identification unit, two-dimensional position identification unit, and three-dimensional position identification unit to track the location of individuals at a construction site using a combination of image data from a camera and terrain data from a three-dimensional sensor.

Benefits of technology

Enables accurate confirmation of the three-dimensional positions of individuals at a construction site, enhancing work efficiency and safety by providing real-time tracking and analysis of worker movements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007739161000001
    Figure 0007739161000001
  • Figure 0007739161000002
    Figure 0007739161000002
  • Figure 0007739161000003
    Figure 0007739161000003
Patent Text Reader

Abstract

To confirm a position of a person at a construction site.SOLUTION: A construction management system includes: an image data acquisition unit configured to acquire image data indicating an image of a construction site where a work machine operates; a topographical data storage unit configured to store topographical data indicating the three-dimensional shape of topography of the construction site; a person identification unit configured to identify a person in the image; a two-dimensional position identification unit configured to identify a two-dimensional position of the person in the image; and a three-dimensional position identification unit configured to identify a three-dimensional position of the person at the construction site based on the two-dimensional position and the topographical data.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present disclosure relates to a construction management system and a construction management method. [Background technology]

[0002] BACKGROUND ART In the technical field related to construction management systems, a construction management system such as that disclosed in Patent Document 1 is known. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 012993 Summary of the Invention [Problem to be solved by the invention]

[0004] There are cases where people are present at a construction site. In order to prevent a decrease in construction efficiency at the construction site, it is preferable to be able to confirm the positions of people.

[0005] The present disclosure aims to confirm the location of people at a construction site. [Means for solving the problem]

[0006] According to the present disclosure, there is provided a construction management system comprising an image data acquisition unit that acquires image data showing an image of a construction site where a work machine is operating, a terrain data storage unit that stores terrain data showing the three-dimensional shape of the terrain of the construction site, a person identification unit that identifies a person in the image, a two-dimensional position identification unit that identifies the two-dimensional position of the person in the image, and a three-dimensional position identification unit that identifies the three-dimensional position of the person at the construction site based on the two-dimensional position and the terrain data. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to confirm the location of people at a construction site. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram showing a construction management system according to an embodiment. [Figure 2] FIG. 2 is a diagram showing an aircraft according to the embodiment. [Figure 3] FIG. 3 is a functional block diagram showing the construction management system according to the embodiment. [Figure 4] FIG. 4 is a flowchart showing the construction management method according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating a method for identifying a person according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating a method for identifying a three-dimensional position of a person according to the embodiment. [Figure 7] FIG. 7 is a diagram showing a usage pattern of the three-dimensional position of a person according to the embodiment. [Figure 8] FIG. 8 is a block diagram illustrating a computer system according to an embodiment. [Figure 9] FIG. 9 is a diagram showing a method for identifying a three-dimensional position of a person according to another embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings, but the present disclosure is not limited to the embodiments. The components of the embodiments described below can be combined as appropriate. In addition, some components may not be used.

[0010] [Construction management system] FIG. 1 is a schematic diagram showing a construction management system 1 according to an embodiment. The construction management system 1 manages construction at a construction site 2. A plurality of work machines 20 operate at the construction site 2. In the embodiment, the work machines 20 include a hydraulic excavator 21, a bulldozer 22, and a crawler dump truck 23. A human WM is present at the construction site 2. An example of the human WM is a worker working at the construction site 2. The human WM may be a supervisor who manages the construction. The human WM may also be an observer.

[0011] As shown in FIG. 1, the construction management system 1 includes a management device 3, a server 4, an information terminal 5, and an aircraft 8.

[0012] The management device 3 includes a computer system that is placed at the construction site 2. The management device 3 is supported by a traveling device 6. The management device 3 can travel at the construction site 2 by means of the traveling device 6. Examples of the traveling device 6 include aerial work vehicles, trucks, and traveling robots.

[0013] The server 4 includes a computer system. The server 4 may be located at the construction site 2 or may be located at a remote location from the construction site 2.

[0014] The information terminal 5 is a computer system located in a remote location 9 of the construction site 2. Examples of the information terminal 5 include a personal computer and a smartphone.

[0015] The management device 3, the server 4, and the information terminal 5 communicate with each other via a communication system 10. Examples of the communication system 10 include the Internet, a local area network (LAN), a mobile phone communication network, and a satellite communication network.

[0016] The aircraft 8 flies over the construction site 2. An example of the aircraft 8 is an unmanned aerial vehicle (UAV) such as a drone. In the embodiment, the aircraft 8 and the management device 3 are connected by a cable 7. The management device 3 includes a power source or a generator. The management device 3 can supply power to the aircraft 8 via the cable 7.

[0017] [Flying object] 2 is a diagram showing an aircraft 8 according to an embodiment. The aircraft 8 is equipped with a three-dimensional sensor 11, a camera 12, a position sensor 14, and an attitude sensor 15.

[0018] The three-dimensional sensor 11 detects the construction site 2. The three-dimensional sensor 11 acquires three-dimensional data indicating the three-dimensional shape of the topography of the construction site 2. The detection data of the three-dimensional sensor 11 includes three-dimensional data of the construction site 2. The three-dimensional sensor 11 is placed on the flying object 8. The three-dimensional sensor 11 detects the construction site 2 from above the construction site 2. An example of the three-dimensional sensor 11 is a laser sensor (LIDAR: Light Detection and Ranging) that detects the detection target by emitting laser light. The three-dimensional sensor 11 may also be an infrared sensor that detects objects by emitting infrared light or a radar sensor (RADAR: Radio Detection and Ranging) that detects objects by emitting radio waves. The three-dimensional sensor 11 may also be a three-dimensional camera such as a stereo camera.

[0019] The camera 12 captures an image of the construction site 2. The camera 12 acquires image data showing an image of the construction site 2. The image data of the camera 12 includes image data of the construction site 2. The camera 12 is placed on the flying vehicle 8. The camera 12 captures an image of the construction site 2 from above the construction site 2. The camera 12 is a two-dimensional camera such as a monocular camera. The camera 12 may be a visible light camera or an infrared camera. The image data acquired by the camera 12 may be video data or still image data. Furthermore, if the three-dimensional sensor 11 is a stereo camera, the stereo camera may be used as the camera 12.

[0020] The position sensor 14 detects the position of the air vehicle 8. The position sensor 14 detects the position of the air vehicle 8 using a global navigation satellite system (GNSS). The position sensor 14 includes a GNSS receiver (GNSS sensor) and detects the position of the air vehicle 8 in a global coordinate system. The three-dimensional sensor 11 and the camera 12 are each fixed to the air vehicle 8. The position sensor 14 can detect the position of the three-dimensional sensor 11 and the camera 12 by detecting the position of the air vehicle 8. The detection data of the position sensor 14 includes position data of the three-dimensional sensor 11 and the camera 12.

[0021] The attitude sensor 15 detects the attitude of the flying object 8. The attitude includes, for example, a roll angle, a pitch angle, and a yaw angle. An example of the attitude sensor 15 is an inertial measurement unit (IMU). The three-dimensional sensor 11 and the camera 12 are each fixed to the flying object 8. The attitude sensor 15 can detect the attitude of the three-dimensional sensor 11 and the attitude of the camera 12 by detecting the attitude of the flying object 8. The detection data of the attitude sensor 15 includes attitude data of the three-dimensional sensor 11 and the attitude data of the camera 12.

[0022] The detection data of the three-dimensional sensor 11, the imaging data of the camera 12, the detection data of the position sensor 14, and the detection data of the orientation sensor 15 are each transmitted to the management device 3 via the cable 7. The detection data of the three-dimensional sensor 11, the imaging data of the camera 12, the detection data of the position sensor 14, and the detection data of the orientation sensor 15 received by the management device 3 are each transmitted to the server 4 via the communication system 10.

[0023] [server] 3 is a functional block diagram showing a construction management system 1 according to an embodiment. As shown in FIG. 3, the construction management system 1 includes an aircraft 8, a management device 3 disposed at a construction site 2, a server 4, and an information terminal 5 disposed at a remote location 9 of the construction site 2.

[0024] The flying object 8 has a three-dimensional sensor 11 , a camera 12 , a position sensor 14 , and an attitude sensor 15 .

[0025] The information terminal 5 includes a display control unit 51 and a display device 52 .

[0026] The display device 52 displays the display data. The administrator at the remote location 9 can check the display data displayed on the display device 52. Examples of the display device 52 include a flat panel display such as a liquid crystal display (LCD) or an organic electroluminescence display (OLED).

[0027] The server 4 has a three-dimensional data acquisition unit 41, a topographical data calculation unit 42, a topographical data storage unit 43, an image data acquisition unit 44, a person identification unit 45, a two-dimensional position identification unit 46, a three-dimensional position identification unit 47, and an output unit 48.

[0028] The three-dimensional data acquisition unit 41 acquires detection data from the three-dimensional sensor 11. That is, the three-dimensional data acquisition unit 41 acquires three-dimensional data of the construction site 2 from the three-dimensional sensor 11.

[0029] The topographical data calculation unit 42 calculates topographical data indicating the three-dimensional shape of the topography of the construction site 2 based on the three-dimensional data of the construction site 2 acquired by the three-dimensional data acquisition unit 41. The topographical data calculation unit 42 acquires from the position sensor 14 the position of the three-dimensional sensor 11 when the three-dimensional sensor 11 detected the construction site 2, and acquires from the attitude sensor 15 the attitude of the three-dimensional sensor 11 when the three-dimensional sensor 11 detected the construction site 2. The three-dimensional data of the construction site 2 includes point cloud data consisting of a plurality of detection points. The three-dimensional data of the construction site 2 includes the relative distance and relative position between the three-dimensional sensor 11 and each of a plurality of detection points defined in the detection target. The topographical data calculation unit 42 can calculate topographical data in, for example, a local coordinate system defined for the construction site 2 based on the three-dimensional data of the construction site 2 acquired by the three-dimensional data acquisition unit 41, the position of the three-dimensional sensor 11 detected by the position sensor 14, and the attitude of the three-dimensional sensor 11 detected by the attitude sensor 15.

[0030] The topographical data storage unit 43 stores topographical data that indicates the three-dimensional shape of the topography of the construction site 2 calculated by the topographical data calculation unit 42.

[0031] The image data acquisition unit 44 acquires imaging data of the camera 12. That is, the image data acquisition unit 44 acquires image data showing an image of the construction site 2 from the camera 12. The image acquired from the camera 12 is a two-dimensional image of the construction site 2.

[0032] The person identification unit 45 identifies the person WM in the image of the construction site 2 acquired by the image data acquisition unit 44. The person identification unit 45 identifies the person WM using artificial intelligence (AI) that analyzes input data using an algorithm and outputs output data. The person identification unit 45 identifies the person WM using, for example, a neural network.

[0033] The two-dimensional position specifying unit 46 specifies the two-dimensional position of the person WM in the image of the construction site 2 acquired by the image data acquiring unit 44.

[0034] The three-dimensional position identification unit 47 identifies the three-dimensional position of the person WM at the construction site 2 based on the two-dimensional position of the person WM in the image of the construction site 2 identified by the two-dimensional position identification unit 46 and the topographical data of the construction site 2 stored in the topographical data storage unit 43. In the embodiment, the three-dimensional position identification unit 47 identifies the three-dimensional position of the person WM at the construction site 2 based on the position of the camera 12 detected by the position sensor 14, the two-dimensional position of the person WM in the image of the construction site 2 identified by the two-dimensional position identification unit 46, and the topographical data of the construction site 2 stored in the topographical data storage unit 43.

[0035] The output unit 48 outputs the three-dimensional position of the person WM at the construction site 2 identified by the three-dimensional position identification unit 47 to the information terminal 5. The output unit 48 transmits the three-dimensional position of the person WM at the construction site 2 to the information terminal 5 via the communication system 10.

[0036] The output unit 48 transmits a control command to the display control unit 51 to cause the display device 52 to display the three-dimensional position of the person WM at the construction site 2. Based on the control command transmitted from the output unit 48, the display control unit 51 controls the display device 52 so that the three-dimensional position of the person WM at the construction site 2 is displayed on the display device 52.

[0037] [Construction management method] 4 is a flowchart showing a construction management method according to an embodiment. In the embodiment, the detection range of the three-dimensional sensor 11 and the imaging range of the camera 12 at least partially overlap. Furthermore, the detection process of the construction site 2 by the three-dimensional sensor 11 and the imaging process of the construction site 2 by the camera 12 are carried out simultaneously. The three-dimensional sensor 11 and the camera 12 are fixed to the flying object 8. Before the detection process by the three-dimensional sensor 11 and the imaging process by the camera 12 are carried out, a calibration process is carried out to determine the relative position between the three-dimensional sensor 11 and the camera 12 and the relative attitude between the three-dimensional sensor 11 and the camera 12.

[0038] When the flying object 8 starts flying in the sky above the construction site 2, the detection process of the construction site 2 by the three-dimensional sensor 11 and the image capturing process of the construction site 2 by the camera 12 are started.

[0039] The three-dimensional data acquisition unit 41 acquires three-dimensional data of the construction site 2 from the three-dimensional sensor 11 (step S1).

[0040] The topographical data calculation unit 42 calculates topographical data indicating the three-dimensional shape of the topography of the construction site 2 based on the three-dimensional data of the construction site 2 acquired in step S1 (step S2).

[0041] The topographical data calculation unit 42 calculates topographical data, for example, in a local coordinate system defined for the construction site 2, based on the three-dimensional data of the construction site 2, the position of the three-dimensional sensor 11 detected by the position sensor 14, and the attitude of the three-dimensional sensor 11 detected by the attitude sensor 15.

[0042] The topographical data storage unit 43 stores the topographical data indicating the three-dimensional shape of the topography of the construction site 2 calculated in step S2 (step S3).

[0043] The image data acquisition unit 44 acquires image data showing an image of the construction site 2 from the camera 12. The image acquired by the image data acquisition unit 44 is a two-dimensional image of the construction site 2 (step S4).

[0044] The person identification unit 45 identifies the person WM in the image of the construction site 2 acquired in step S4. The person identification unit 45 identifies the person WM by using artificial intelligence (AI) (step S5).

[0045] FIG. 5 is a diagram showing a method for identifying a person WM according to an embodiment. The person identification unit 45 holds a learning model generated by learning the feature amounts of an object. The person identification unit 45 identifies the person WM from a two-dimensional image based on the learning model. The person identification unit 45 generates a learning model that inputs the feature amounts of an object and outputs a person (presence or absence of a person) by performing machine learning using, for example, learning images including images of people as training data. The person identification unit 45 inputs the feature amounts of an object extracted from the image data showing the image of the construction site 2 acquired in step S4 into the learning model, and identifies the person WM in the two-dimensional image.

[0046] After the person WM is identified in step S5, the two-dimensional position identifying unit 46 identifies the two-dimensional position of the person WM in the two-dimensional image. In the embodiment, the two-dimensional position identifying unit 46 identifies the two-dimensional position of the feet of the person WM (step S6).

[0047] The three-dimensional position identification unit 47 identifies the three-dimensional position of the person WM at the construction site 2 based on the two-dimensional position of the person WM in the two-dimensional image of the construction site 2 identified in step S6 and the topographical data of the construction site 2 stored in the topographical data memory unit 43 (step S7).

[0048] FIG. 6 is a diagram illustrating a method for identifying the three-dimensional position of the person WM according to an embodiment. The three-dimensional position of the person WM is, for example, a three-dimensional position in the topographical data of the construction site 2. As shown in FIG. 6, a perspective projection plane is defined between the optical center of the camera 12 and the person WM. The relative position between the three-dimensional sensor 11 and the camera 12 and the relative orientation between the three-dimensional sensor 11 and the camera 12 are known through the calibration process described above. The perspective projection surface is an image plane virtually defined based on a perspective projection model. The three-dimensional position identification unit 47 identifies the three-dimensional position of the person WM at the construction site 2 based on the intersection of a vector connecting the optical center of the camera 12 and the person WM on the perspective projection plane with the topographical data. The topographical data of the construction site 2 includes point cloud data consisting of multiple detection points. The three-dimensional position identification unit 47 identifies the detection point from the multiple detection points that maximizes the dot product with the vector as the three-dimensional position of the person WM. The vector is set to pass through the feet of the person WM on the perspective projection plane. The three-dimensional position specifying unit 47 specifies the three-dimensional position of the feet of the person WM as the three-dimensional position of the person WM.

[0049] The output unit 48 transmits the three-dimensional position of the person WM identified in step S7 to the information terminal 5 via the communication system 10. The output unit 48 transmits a control command to the display control unit 51 to display the three-dimensional position of the person WM at the construction site 2 on the display device 52. Based on the control command transmitted from the output unit 48, the display control unit 51 displays the three-dimensional position of the person WM at the construction site 2 on the display device 52 (step S8).

[0050] [How people's 3D positions are used] FIG. 7 is a diagram showing how the three-dimensional position of the person WM is used in accordance with an embodiment. The information terminal 5 can recognize the situation at the construction site 2 based on the three-dimensional position of the person WM. The information terminal 5 can analyze the movement of the worker based on the three-dimensional position of the person WM, thereby improving work efficiency, for example. The information terminal 5 can suggest a work procedure with high work efficiency based on the three-dimensional position of the person WM. The information terminal 5 can notify a warning to the person WM based on the three-dimensional position of the person WM. The information terminal 5 can notify a warning to an information terminal carried by a worker based on the three-dimensional position of the person WM, for example, to ensure the safety of the worker.

[0051] [Computer System] FIG. 8 is a block diagram showing a computer system 1000 according to an embodiment. The server 4 described above includes the computer system 1000. The computer system 1000 includes a processor 1001 such as a central processing unit (CPU), a main memory 1002 including a nonvolatile memory such as a read-only memory (ROM) and a volatile memory such as a random access memory (RAM), a storage 1003, and an interface 1004 including an input / output circuit. The functions of the server 4 described above are stored in the storage 1003 as a computer program. The processor 1001 reads the computer program from the storage 1003, loads it into the main memory 1002, and executes the above-described processing in accordance with the program. The computer program may be distributed to the computer system 1000 via a network.

[0052] According to the above-described embodiment, the computer program or computer system 1000 can acquire image data showing an image of the construction site 2 where the work machine 20 is operating, store terrain data showing the three-dimensional shape of the terrain of the construction site 2, identify a person WM in the image, identify the two-dimensional position of the person WM in the image, and identify the three-dimensional position of the person WM at the construction site 2 based on the two-dimensional position and the terrain data.

[0053] [effect] As described above, according to the embodiment, the server 4 can identify the three-dimensional position of the person WM at the construction site 2. This allows, for example, a manager to confirm the three-dimensional position of the person WM at the construction site 2.

[0054] It may be difficult to identify the person WM from only the detection data of the three-dimensional sensor 11. However, it is possible to identify the person WM with a high degree of accuracy from the two-dimensional image acquired by the camera 12. In the embodiment, the three-dimensional position of the person WM is identified with a high degree of accuracy by combining the topography of the construction site 2 calculated from the detection data of the three-dimensional sensor 11 with the two-dimensional position of the person WM identified from the imaging data of the camera 12.

[0055] The three-dimensional position identification unit 47 can identify the three-dimensional position of the person WM based on the position of the camera 12 detected by the position sensor 14, the two-dimensional position of the person WM in the two-dimensional image, and the topographical data of the construction site 2.

[0056] By defining the perspective projection plane, the three-dimensional position determination unit 47 can determine the three-dimensional position of the person WM based on the intersection of the vector connecting the optical center of the camera 12 and the person WM on the perspective projection plane with the terrain.

[0057] By identifying the position of the feet of the person WM, the relationship between the person WM and the terrain can be identified with high accuracy.

[0058] The camera 12 is arranged on the flying object 8, which is a mobile body, so that the construction site 2 is imaged over a wide range. The three-dimensional sensor 11 is arranged on the flying object 8, which is a mobile body, so that the topography of the construction site 2 is detected over a wide range.

[0059] The person identification unit 45 can identify the person WM from the two-dimensional image with high accuracy by using artificial intelligence.

[0060] By displaying the three-dimensional position of the identified person WM on the display device 52, as explained with reference to Figure 7, it is possible to prevent a decline in work efficiency and a deterioration in the working environment at the construction site 2.

[0061] [Other embodiments] In the above embodiment, the flying object 8 is a wired flying object connected to the cable 7. The flying object 8 may be a wireless flying object that is not connected to the cable 7.

[0062] In the above-described embodiment, the two-dimensional position specifying unit 46 specifies the two-dimensional position of the feet of the person WM. The two-dimensional position specifying unit 46 may specify the two-dimensional position of the head of the person WM, may specify the two-dimensional position of any part of the person WM, or may specify the two-dimensional position of an article worn by the person WM.

[0063] In the above-described embodiment, the position sensor 14 is used to detect the position of the aircraft 8, and the attitude sensor 15 is used to detect the attitude of the aircraft 8. The position and attitude of the aircraft 8 may also be detected using SLAM (Simultaneous Localization and Mapping). The position and attitude of the aircraft 8 may also be detected using geomagnetism or a barometer.

[0064] In the above-described embodiment, the person identification unit 45 may identify the person WM based on, for example, a pattern matching method without using artificial intelligence. The person identification unit 45 can identify the person WM by comparing a template representing the person WM with image data of the construction site 2. The person identification unit 45 may also identify the person WM based on the heat quantity of the person WM detected by an infrared camera.

[0065] In the above-described embodiment, the management device 3 is supported by the traveling device 6 and can travel within the construction site 2. The management device 3 may be mounted on the work machine 20, or may be installed at a predetermined position within the construction site 2.

[0066] In the above-described embodiment, the information terminal 5 does not have to be located in the remote location 9 of the construction site 2. The information terminal 5 may be mounted on the work machine 20, for example.

[0067] In the above-described embodiment, the functions of the server 4 may be provided in the management device 3, the information terminal 5, or a computer system mounted on the aircraft 8. For example, at least one function of the three-dimensional data acquisition unit 41, the topographical data calculation unit 42, the topographical data storage unit 43, the image data acquisition unit 44, the person identification unit 45, the two-dimensional position identification unit 46, the three-dimensional position identification unit 47, and the output unit 48 may be provided in the management device 3, the information terminal 5, or a computer system mounted on the aircraft 8.

[0068] In the above-described embodiment, each of the three-dimensional data acquisition unit 41, the topographical data calculation unit 42, the topographical data storage unit 43, the image data acquisition unit 44, the person identification unit 45, the two-dimensional position identification unit 46, the three-dimensional position identification unit 47, and the output unit 48 may be configured as separate hardware.

[0069] In the above-described embodiment, at least one of the three-dimensional sensor 11 and the camera 12 does not have to be disposed on the air vehicle 8. At least one of the three-dimensional sensor 11 and the camera 12 may be disposed on the work machine 20, for example.

[0070] Figure 9 is a diagram showing a method for identifying the three-dimensional position of person WM according to another embodiment. As shown in Figure 9, the camera 12 is mounted on a work machine 20. The three-dimensional position identification unit 47 may identify the three-dimensional position of person WM at the construction site 2 based on the intersection of a vector connecting the optical center of the camera 12 mounted on the work machine 20 and person WM on the perspective projection plane with the terrain.

[0071] Furthermore, at least one of the 3D sensor 11 and the camera 12 may be disposed on a moving body separate from the flying vehicle 8 and the work machine 20. Furthermore, at least one of the 3D sensor 11 and the camera 12 may be disposed on a structure present at the construction site 2. Furthermore, multiple 3D sensors 11 may be installed at the construction site 2, and the topography of the construction site 2 may be detected over a wide area. Multiple cameras 12 may be installed at the construction site 2, and images of the construction site 2 may be taken over a wide area.

[0072] In the above-described embodiment, the detection process by the three-dimensional sensor 11 and the imaging process by the camera 12 are carried out simultaneously. After the detection process by the three-dimensional sensor 11 is carried out and the topographical data of the construction site 2 is stored in the topographical data storage unit 43, the imaging process of the construction site 2 by the camera 12 may be carried out. By detecting the position and attitude of the three-dimensional sensor 11 when detecting the construction site 2 and detecting the position and attitude of the camera 12 when imaging the construction site 2, the three-dimensional position identification unit 47 can identify the three-dimensional position of the person WM at the construction site 2 based on the two-dimensional position of the person WM and the topographical data.

[0073] In the above-described embodiments, the work machine 20 may be a work machine other than the hydraulic excavator 21, the bulldozer 22, and the crawler dump truck 23. The work machine 20 may include, for example, a wheel loader. [Explanation of symbols]

[0074] 1...construction management system, 2...construction site, 3...management device, 4...server (data processing device), 5...information terminal, 6...traveling device, 7...cable, 8...aircraft vehicle, 9...remote location, 10...communication system, 11...3D sensor, 12...camera, 14...position sensor, 15...attitude sensor, 20...work machine, 21...hydraulic excavator, 22...bulldozer, 23...crawler dump, 41...3D data acquisition unit, 42...terrain data calculation unit, 43...terrain data storage unit, 44...image data acquisition unit, 45...person identification unit, 46...2D position identification unit, 47...3D position identification unit, 48...output unit, 51...display control unit, 52...display device, 1000...computer system, 1001...processor, 1002...main memory, 1003...storage, 1004...interface, WM...person

Claims

1. an image data acquisition unit that acquires image data showing an image of a construction site where the work machine is operating; a topographical data storage unit that stores topographical data indicating a three-dimensional shape of the topography of the construction site; a person identification unit that identifies a person in the image; a two-dimensional position specifying unit that specifies a two-dimensional position of the person in the image; a three-dimensional position specifying unit that specifies a three-dimensional position of the person at the construction site based on the two-dimensional position and the topographical data, The image data acquisition unit acquires image data from a camera that captures an image of the construction site, a perspective projection plane is defined between the optical center of the camera and the person; the three-dimensional position specifying unit specifies the three-dimensional position based on an intersection of a vector connecting the optical center and the person on the perspective projection plane with the terrain. Construction management system.

2. the vector is set to pass through a part of the person on the perspective projection plane; The construction management system according to claim 1 .

3. The part of the person is the person's feet. The construction management system according to claim 2 .

4. The camera is disposed on a moving object. The construction management system according to any one of claims 1 to 3.

5. The moving object includes at least one of an aircraft and a work machine. The construction management system according to claim 4.

6. the person identification unit identifies the person based on a learning model that takes a feature amount of an object as an input and a person as an output. The construction management system according to any one of claims 1 to 5.

7. a display control unit that displays the three-dimensional position on a display device; The construction management system according to any one of claims 1 to 6.

8. A computer comprising: acquiring image data representing an image of a construction site where a work machine is operating; storing topographical data indicating a three-dimensional shape of the topography of the construction site; identifying people in the image; identifying a two-dimensional position of the person in the image; and determining a three-dimensional position of the person at the construction site based on the two-dimensional position and the topographical data; The computer The image data is acquired from a camera that captures an image of the construction site, defining a perspective projection plane between the optical center of the camera and the person; The three-dimensional position is identified based on an intersection point between a vector connecting the optical center and the person on the perspective projection plane and the terrain. Construction management method.

9. The computer sets the vector so that it passes through a part of the person on the perspective projection plane. The construction management method according to claim 8.

10. The part of the person is the person's feet. The construction management method according to claim 9.

11. The camera is disposed on a moving object. The construction management method according to any one of claims 8 to 10.

12. The moving object includes at least one of an aircraft and a work machine. The construction management method according to claim 11.

13. The computer identifies the person based on a learning model that takes object features as input and people as output. The construction management method according to any one of claims 8 to 12.

14. The computer executes displaying the three-dimensional position on a display device. The construction management method according to any one of claims 8 to 13.

Citation Information

Patent Citations

  • Three-dimensional site information creating system

    JP2003329448A

  • Operation support apparatus

    JP2005250990A

  • Safety management support device, safety management support program, and storage medium

    JP2017033047A

  • Unmanned aerial vehicle (UAV)-assisted worksite data acquisition

    US20190114847A1

  • Topographic information transmission device, construction management system, and topographic information transmission method

    WO2019012988A1