Fastening Work Analysis Device, Analysis Method, and Program

Abstract

To more accurately analyze than before concrete compaction work by workers.SOLUTION: In a system 1 according to this embodiment, first, imaging devices 10a,10b capture images of a worker who holds a vibrator and performs compaction work, and a compaction work analysis device 30 performs image analysis of the worker and the vibrator in the image data. Next, in a unique coordinate system (called an image device system of coordinates) in the imaging range of the imaging devices 10a, 10b, a location where concrete is being compacted (an imaging device coordinate value) is identified. And then, the coordinate values of the imaging devices are converted into coordinate values (3-dimensional absolute coordinate values) in a system of absolute coordinates (called 3-dimensional system of absolute coordinates) in the 3-dimensional space where compaction is performed, and based on the 3D absolute coordinate values, the location where compaction is performed in the concrete is estimated.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a technique for analyzing the compaction work of concrete placed by workers.

Background Art

[0002] The work of applying vibration to the concrete placed in the formwork to spread the concrete and prevent voids from occurring in the formwork is called compaction. For example, in Patent Document 1, recognition bodies i1 to i3 are attached to the vibrating part 21 of the vibrator 2 for compaction, three-dimensional coordinate values of the recognition bodies i1 to i3 are obtained from the captured image of the compaction work, and further, based on the relationship between the coordinate values on the concrete surface and the coordinate values of the tip F of the vibrator 2, the insertion depth and insertion period of the vibrator 2 are calculated.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to accurately estimate the position where the concrete is compacted by the compaction work of the worker.

Means for Solving the Problems

[0005] To solve the above problems, the present invention includes an acquisition unit that acquires image data obtained by imaging the space where a worker performs compaction work on concrete with a vibrator from a plurality of imaging devices, and from the plurality of acquired image data, a worker image object corresponding to the worker, and, an extraction unit that extracts a vibrator image object corresponding to the vibrator, and for each of the worker image objects or the vibrator image objects extracted from the plurality of the image data, a specific unit that specifies imaging device coordinate values in an imaging device coordinate system, which is a unique coordinate system of the imaging device, a conversion unit that converts the specified imaging device coordinate values into three-dimensional absolute coordinate values, and an estimation unit that estimates a location where tamping is being performed in the concrete based on the converted three-dimensional absolute coordinate values comprises, wherein the extraction unit extracts at least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator, and a marker image object corresponding to a marker provided on a cord extending from the vibrator, as the vibrator image object, extracts a hand image object corresponding to the hand of the operator as the operator image object, and in the extraction of the hand image object, uses skeleton estimation to extract, as the hand image object, an image of the hand determined to be gripping the vibrator and / or the cord among both hands of the operator , and It is a tamping work analysis device.

[0008] The marker may be composed of a single color or a combination of a plurality of single colors so as to have different color schemes before and after at a predetermined interval in the extending direction of the code.

[0009] The estimation unit may estimate a location where tamping is being performed by preferentially using the three-dimensional absolute coordinate values of the image object closest to the vibrator among the vibrator image object, the marker image object, and the hand image object.

[0010] The specific unit may specify the imaging device coordinate values for each of the worker image objects or the vibrator image objects extracted from the plurality of the image data based on the focal length of each of the imaging devices and the planar coordinate values in the image sensors of each of the imaging devices.

[0011] The extraction unit extracts a plurality of worker image objects corresponding to a plurality of the workers working simultaneously from the image data, and a plurality of vibrator image objects corresponding to a plurality of the vibrators, and the estimation unit may estimate a plurality of locations where tamping is being performed simultaneously in the concrete.

[0012] Further, the present invention includes steps of: acquiring, from a plurality of imaging devices, image data obtained by imaging a space where an operator performs a concrete compacting operation with a vibrator; from the plurality of acquired image data, an operator image object corresponding to the operator, comprises, and in the step of extraction, extracts at least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator, and a marker image object corresponding to a marker provided on a cord extending from the vibrator, as the vibrator image object, extracts a hand image object corresponding to the hand of the operator as the operator image object, and in the extraction of the hand image object, uses skeleton estimation to extract, as the hand image object, an image of the hand determined to be gripping the vibrator and / or the cord among both hands of the operator extracting a vibrator image object corresponding to the vibrator; specifying, for the operator image object or the vibrator image object respectively extracted from the plurality of image data, imaging device coordinate values in an imaging device coordinate system which is a unique coordinate system of the imaging device; converting the specified imaging device coordinate values into three-dimensional absolute coordinate values; and estimating a location where compacting is being performed in the concrete based on the converted three-dimensional absolute coordinate values and This is a compacting operation analysis method.

[0013] Further, the present invention causes a computer to perform steps of: acquiring, from a plurality of imaging devices, image data obtained by imaging a space where an operator performs a concrete compacting operation with a vibrator; from the plurality of acquired image data, an operator image object corresponding to the operator, wherein at least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator, and a marker image object corresponding to a marker provided on a cord extending from the vibrator, is extracted as the vibrator image object, a hand image object corresponding to the hand of the operator is extracted as the operator image object, and in the extraction of the hand image object, an image of the hand determined to be gripping the vibrator and / or the cord among both hands of the operator is extracted as the hand image object using skeleton estimation step extracting a vibrator image object corresponding to the vibrator

Figure 1

Advantages of the Invention

[0014] According to the present invention, it is possible to accurately estimate the position where the concrete has been compacted by the compacting operation of the worker.

Brief Description of the Drawings

[0015]

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

[0016] An example of an embodiment for carrying out the present invention will be described. [Configuration] FIG. 1 is a block diagram showing an example of the overall configuration of a system 1 according to an embodiment of the present invention. As shown in FIG. 1, this system 1 includes a plurality of imaging devices 10a and 10b, a network 20 including a wireless communication network or a wired communication network, and a tightening work analysis device 30. The imaging devices 10a and 10b are installed at the site where concrete is placed and are connected to the network 20 by wire or wirelessly. In FIG. 1, two imaging devices 10a and 10b are illustrated as a plurality of imaging devices installed at the concrete placement site, but these may be three or more.

[0017] The operator inserts a vibrator into the concrete placed in the formwork at predetermined intervals for a predetermined period, and gives appropriate vibration to the concrete to compact the concrete. As a result, the voids in the formwork where the concrete is not filled disappear, and the quality of the concrete structure becomes good. In this embodiment, the vibrator is a general term for a vibrating body and a cord extending from the vibrating body.

[0018] In the system 1 according to this embodiment, first, an imaging device 10a, 10b images the state in which an operator performs a compaction operation with a vibrator, and a compaction operation analysis device 30 analyzes the operator and the vibrator in the image data. Next, the position (imaging device coordinate value) where compaction is performed on the concrete in the imaging device coordinate system, which is the unique coordinate system of each imaging device in the imaging range of the imaging devices 10a, 10b, is specified. Then, the imaging device coordinate value is converted into a coordinate value (3D absolute coordinate value) in an absolute coordinate system (referred to as a 3D absolute coordinate system) in the three-dimensional space where compaction is performed, and based on this 3D absolute coordinate value, the location where compaction is performed in the concrete is estimated.

[0019] FIG. 2 is a diagram showing the hardware configuration of the compaction operation analysis device 30. Physically, the compaction operation analysis device 30 is configured as a computer device including a processor 3001, a memory 3002, a storage 3003, a communication device 3004, an input device 3005, an output device 3006, and a bus connecting these. Each of these devices operates with power supplied from a power source (not shown). In the following description, the term "device" can be read as a circuit, a device, a unit, etc. The hardware configuration of the compaction operation analysis device 30 may be configured to include one or more of the devices shown in FIG. 2, or may be configured without including some of the devices.

[0020] Each function in the tightening operation analysis device 30 is realized by causing a processor 3001 to perform calculations, control communication by a communication device 3004, acquire data transmitted from other devices, or control at least one of reading and writing data in a memory 3002 and a storage 3003, by loading a predetermined software (program) onto hardware such as the processor 3001 and a memory 3002.

[0021] The processor 3001 controls the entire computer by operating, for example, an operating system. The processor 3001 may be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like.

[0022] The processor 3001 reads a program (program code), a software module, data, etc. from at least one of the storage 3003 and the communication device 3004 into the memory 3002, and executes various processes according to these. As the program, a program for causing a computer to execute at least a part of the operations described later is used. The function blocks of the tightening operation analysis device 30 may be stored in the memory 3002 and realized by a control program operating in the processor 3001. Various processes may be executed by one processor 3001, or may be executed simultaneously or sequentially by two or more processors 3001. The processor 3001 may be mounted by one or more chips. Note that the program may be transmitted to the tightening operation analysis device 30 via a telecommunication line from another device on the cloud, or may be installed in the memory 3002 or the storage 3003.

[0023] Memory 3002 is a computer-readable recording medium and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 3002 may be referred to as a register, a cache, a main memory (main storage device), etc. Memory 3002 can store a program (program code), a software module, etc. executable for implementing the method according to the present embodiment.

[0024] Storage 3003 is a computer-readable recording medium and may be constituted by at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a solid state drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 3003 may be referred to as an auxiliary storage device.

[0025] Communication device 3004 is hardware (a transceiver device) for performing communication between computers via at least one of wired or wireless, and communicates with imaging devices 10a and 10b via network 20. Also, when a mobile terminal or the like is used as output device 3006 separately from tightening work analysis device 30, communication between the computer and output device 3006 is also performed via network 20.

[0026] The input device 3005 is an input device that receives external input (for example, a keyboard, a mouse, a microphone, a switch, a button, etc.). The output device 3006 is an output device that performs output to the outside (for example, a mobile terminal, smart glasses, a display, a speaker, an LED lamp, etc.). Note that the input device 3005 and the output device 3006 may have an integrated configuration (for example, a touch panel).

[0027] The tightening operation analysis device 30 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 3001 may be implemented using at least one of these hardware components.

[0028] FIG. 3 is a diagram showing an example of the functional configuration of the tightening operation analysis device 30. Each function realized by the tightening operation analysis device 30 is realized by causing the processor 3001 to perform calculations by loading a predetermined software (program) onto hardware such as the processor 3001 and the memory 3002, controlling communication by the communication device 3004, or controlling at least one of reading and writing data in the memory 3002 and the storage 3003.

[0029] In FIG. 3, acquisition unit 31 acquires various data from outside the tightening work analysis device 30. For example, acquisition unit 31 acquires, via network 20 from imaging devices 10a and 10b, image data representing a plurality of images captured by the imaging devices 10a and 10b, such as an image in which an operator, a vibrator, and a space where the operator performs the concrete tightening work with the vibrator are imaged. This image data may be, for example, time-continuous video data, or may be a set of still image data captured at a predetermined time interval (for example, 1 second) by the time plus function.

[0030] Extraction unit 32 extracts an image object corresponding to the operator (hereinafter referred to as the operator image object) and an image object corresponding to the vibrator (hereinafter referred to as the vibrator image object) by using a shape recognition algorithm such as pattern matching on the above image data. Further, extraction unit 32 analyzes this operator image object and vibrator image object. Specifically, extraction unit 32 performs skeleton estimation on the operator image object and the vibrator image object to analyze the position, posture, or movement of the operator image object and the vibrator image object. Skeleton estimation is a technique of recognizing the positions of a plurality of parts s such as joints of the human body H and parts (eyes, nose, ears, etc.) constituting the face, and estimating the skeleton of the human body H from the positional relationship of these parts s. Skeleton estimation for the human body can be realized in a state where no so-called marker is provided on the human body (markerless). Thereby, extraction unit 32 can extract, as the operator image object, for example, a hand image object corresponding to the hand of the operator. Specifically, extraction unit 32 extracts, as the hand image object, an image of the hand determined to be holding the vibrator body and / or the cord among both hands of the operator by using skeleton estimation.

[0031] On the other hand, when applying skeleton estimation to the vibrator, as illustrated in FIG. 5, for example, a plurality of markers m of different colors are attached to each part of the vibrator VR. By recognizing the positions of the respective markers m attached to the vibrator VR, the extraction unit 32 can estimate the position, posture, or movement of the vibrator V provided at the tip of the vibrator VR and the cord C extending from the vibrator V.

[0032] Here, FIG. 6 is a diagram illustrating the color schemes of the plurality of markers m provided on the vibrator VR. As illustrated in FIG. 6, markers m are provided such that they have different colors every 50 cm from the base of the vibrator V provided at the tip of the cord C. The red marker provided at the position 0 cm from the tip of the cord C is realized, for example, by sticking a red tape around the cord. Also, the red and yellow markers m provided at the position 300 cm from the tip of the cord C are realized, for example, by sticking a red tape and a yellow tape in a proximate state around the cord. That is, these markers m are configured as a single color or a combination of a plurality of single colors so as to have different color schemes before and after with a predetermined interval in the extension direction of the cord C. By performing image recognition on such markers m, the extraction unit 32 can extract at least one of a vibrator image object corresponding to the vibrator V provided at the tip of the vibrator VR or a marker image object corresponding to the marker m attached to the cord C extending from the vibrator V as a vibrator image object.

[0033] The specifying unit 33 specifies the imaging device coordinate values in the imaging device coordinate systems of the imaging devices 10a and 10b for the operator image objects or the vibrator image objects respectively extracted from a plurality of pieces of image data. For example, in the configuration illustrated in FIG. 7, the specifying unit 33 specifies the imaging device coordinate values in the (10a) imaging device coordinate system, which is the unique coordinate system of the imaging device 10a, for the operator image object or the vibrator image object extracted from the image data acquired from the imaging device 10a in imaging with the azimuth angle θa. Similarly, the specifying unit 33 specifies the imaging device coordinate values in the (10b) imaging device coordinate system, which is the unique coordinate system of the imaging device 10b, for the operator image object or the vibrator image object extracted from the image data acquired from the imaging device 10b in imaging with the azimuth angle θb.

[0034] The imaging device coordinate values in the (10a) imaging device coordinate system and the (10b) imaging device coordinate system, which are the respective unique coordinate systems of the imaging devices 10a and 10b, are specified as follows. As shown in FIG. 8, the specifying unit 33 specifies the imaging device coordinate values (X, Y, Z) in the XYZ coordinates of the (10a) imaging device coordinate system and the (10b) imaging device coordinate system, which are the respective unique coordinate systems of the imaging devices 10a and 10b, for the operator image object or the vibrator image object respectively extracted from the respective pieces of image data based on the focal length f = z of each of the imaging devices 10a and 10b and the planar coordinate values (x, y) in the planar coordinate system (xy coordinate system) of the imaging elements of each of the imaging devices 10a and 10b.

[0035] Thereby, as shown in FIG. 9, for the operator image object or the vibrator image object P included in the image data acquired from the imaging device 10b, the imaging device coordinate values (X, Y, Z) in the imaging device coordinate system LC1 of the imaging device 10b are specified, and for the operator image object or the vibrator image object P included in the image data acquired from the imaging device 10a, the imaging device coordinate values (X, Y, Z) in the imaging device coordinate system LC2 of the imaging device 10a are specified.

[0036] The conversion unit 34 converts at least one of the imaging device coordinate values in the imaging device coordinate systems LC2 and LC1, which are the respective coordinate systems of the imaging devices 10a and 10b, into the three-dimensional absolute coordinate values (x, y, z) of the operator image object or the vibrator image object P in the three-dimensional absolute coordinate system WC.

[0037] When there are a plurality of imaging devices, the conversion from the imaging device coordinate values in one of them to the three-dimensional absolute coordinate values is calculated by the mathematical formula shown in FIG. 10. In this mathematical formula, M X (-φ j ), M Y (-α j ) and M Z (-θ j ) are rotation matrices around the X, Y, and Z axes, respectively. j O x * , j O y * , j O z *, φ j , α j , θ j , B j are parameters that can be measured in advance for each imaging device. The subscript j represents each imaging device. Therefore, when imaging is performed with k imaging devices, for one image object, the number of unknowns is x i , y i , z i , j Y j * (k + 3) in number, and since there are 3k mathematical formulas shown in FIG. 10, (k + 3) of them can be used to obtain the three-dimensional absolute coordinate values (x i , y i , z i ).

[0038] The estimation unit 35 estimates the location where the concrete is being compacted based on the converted three-dimensional absolute coordinate values. At this time, the estimation unit 35 estimates the location where the compaction is being performed by preferentially using the coordinate values of the image object closest to the vibrator among the vibrator image object, the marker image object, and the hand image object. Specifically, when the vibrator image object is extracted, the estimation unit 35 estimates the location where the compaction is being performed based on the three-dimensional absolute coordinate values (x, y, z) of the vibrator image object. In this case, the three-dimensional absolute coordinate values (x, y, z) of the vibrator image object become the coordinate values of the location where the compaction is being performed.

[0039] On the other hand, when the vibrator image object is not extracted, if a marker image object is extracted at a position closer to the vibrator V than the hand image object, the estimation unit 35 estimates the location where the compaction is being performed based on the three-dimensional absolute coordinate values (x, y, z) of the extracted marker image object. Specifically, as illustrated in FIG. 6, since each marker image object can be distinguished from the vibrator V by its color, the estimation unit 35 determines which marker image object is closest to the vibrator V among the plurality of extracted marker image objects by its color. Thus, when a marker image object located closer to the vibrator V than the hand image object is extracted, since that marker image object corresponds to the image object closest to the vibrator V, the estimation unit 35 estimates the location where the compaction is being performed based on the three-dimensional absolute coordinate values (x, y, z) of that marker image object. In this case, the x and y coordinate values of the three-dimensional absolute coordinate values (x, y, z) of the marker image object closest to the vibrator V become the x and y coordinate values of the location where the compaction is being performed. Also, with respect to the z coordinate value of the three-dimensional absolute coordinate values (x, y, z) of the marker image object closest to the vibrator V, the value obtained by subtracting the distance from the code tip of that marker image object (see FIG. 6) becomes the z coordinate value of the location where the compaction is being performed.

[0040] On the other hand, when no marker image object closer to the vibrating body V than the hand image object is extracted, since the hand image object corresponds to the image object closest to the vibrating body V, the estimation unit 35 estimates the location where tightening is being performed based on the three-dimensional absolute coordinate values (x, y, z) of the hand image object. In this case, the x and y coordinate values of the three-dimensional absolute coordinate values (x, y, z) of the hand image object are regarded as the x and y coordinate values of the location where tightening is being performed. Also, with respect to the z coordinate value of the three-dimensional absolute coordinate values (x, y, z) of the hand image object, a value obtained by subtracting a numerical value obtained by multiplying the distance from the code tip of the marker image object located farther from the vibrating body V than the hand image object (see FIG. 6) by a coefficient less than 1 is regarded as the z coordinate value of the location where tightening is being performed.

[0041] In this way, the estimation unit 35 estimates the location where tightening is being performed by preferentially using the three-dimensional absolute coordinate values of the image object closest to the vibrating body among the vibrating body image object, the marker image object, and the hand image object.

[0042] The display unit 36 displays the estimated position of the concrete where tightening has been performed by the estimation unit 35 in a visible manner to the operator or administrator. At this time, the display unit 36 displays the estimated position of the concrete where tightening has been performed in at least one of the planar shape, cross-sectional shape, or three-dimensional shape.

[0043] [Operation] Next, the operation of this embodiment will be described. First, imaging is performed by the imaging devices 10a and 10b over a period during which the tamping work is carried out at the concrete placement site. At this time, since there are many reinforcing bars and obstacles at this placement site, as illustrated in FIG. 7, by using the imaging devices 10a and 10b installed to image a plurality of different shooting directions at a plurality of locations on the site, the shooting range is made without omission. The plurality of image data thus captured are transmitted from each of the imaging devices 10a and 10b to the tamping work analysis device 30. The acquisition unit 31 of the tamping work analysis device 30 acquires this image data (step S11 in FIG. 11).

[0044] Next, the extraction unit 32 of the tamping work analysis device 30 extracts various image object groups (worker image object, vibrator image object, image object corresponding to the concrete surface, etc.) from the acquired image data (step S12).

[0045] The extraction unit 32 of the tamping work analysis device 30 extracts a hand image object, a vibrator image object, and a marker image object for which the imaging device coordinate values are to be specified from the above image object group using an image recognition algorithm such as pattern matching (step S13).

[0046] The specifying unit 33 specifies the imaging device coordinate values (X, Y, Z) for the extracted hand image object, vibrator image object, and marker image object according to the method illustrated in FIG. 8, respectively (step S14).

[0047] The conversion unit 41 converts the imaging device coordinate values of the hand image object, vibrator image object, and marker image object into three-dimensional absolute coordinate values according to the mathematical formula illustrated in FIG. 10 (step S15).

[0048] The estimation unit 38 estimates the position of the concreted concrete based on the three-dimensional absolute coordinate values of the hand image object, the vibrating body image object, and the marker image object (step S16). At this time, image objects with the same three-dimensional absolute coordinate values after being converted from each imaging device coordinate value are treated as one image object. This prevents duplicate position estimation for the same image object.

[0049] Then, the display unit 39 displays the position of the concrete estimated to have been concreted by the estimation unit 38 so that it can be visually recognized by the worker or the administrator (step S17). As a display method, it may be output and displayed on a mobile terminal, a smartphone, a personal computer in the office, etc., or may be printed by a printer.

[0050] According to the above-described embodiment, it is possible to accurately estimate the position where the concrete has been concreted by the concreting work performed by the worker.

[0051] [Modification Example] The above-described embodiment may be modified as follows. At the concrete placement site, concreting may be performed at a plurality of positions simultaneously. Therefore, the extraction unit 27 extracts a plurality of worker image objects corresponding to a plurality of workers working simultaneously and a plurality of vibrator image objects corresponding to a plurality of vibrators from the image data, associates each worker image object with the vibrator image object, and the estimation unit may estimate a plurality of locations where concreting is being performed simultaneously in the concrete.

Explanation of Reference Numerals

[0052] 10a, 10b: Imaging device, 20: Network, 30: Tightening operation analysis device, 3001: Processor, 3002: Memory, 3003: Storage, 3004: Communication device, 3005: Input device, 3006: Output device, 31: Acquisition unit, 32: Extraction unit, 33: Identification unit, 34: Conversion unit, 35: Estimation unit, 36: Display unit, s: Part, H: Human body, m: Marker, VR: Vibrator, V: Vibration body, C: Cord, P: Image object, Θa, Θb: Direction angle, WC: Three-dimensional absolute coordinate system, LC1, LC2: Imaging device coordinate system.

Claims

1. An acquisition unit that acquires, from a plurality of imaging devices, image data obtained by imaging a space in which an operator performs a concrete compaction operation while holding a vibrator; An extraction unit that extracts, from the plurality of acquired image data, an operator image object corresponding to the operator and a vibrator image object corresponding to the vibrator; A specifying unit that specifies imaging device coordinate values in an imaging device coordinate system, which is a unique coordinate system of the imaging device, for the operator image object or the vibrator image object extracted from each of the plurality of image data; A conversion unit that converts the specified imaging device coordinate values into three-dimensional absolute coordinate values; An estimation unit that estimates a location where compaction is being performed in the concrete based on the converted three-dimensional absolute coordinate values, and The extraction unit extracts at least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator and a marker image object corresponding to a marker provided on a cord extending from the vibrator as the vibrator image object, extracts a hand image object corresponding to the hand of the operator as the operator image object, and a compaction work analysis device that, in the extraction of the hand image object, extracts, as the hand image object, an image of a hand determined to be holding the vibrator and / or the cord among both hands of the operator using skeleton estimation.

2. The estimation unit estimates the location where compaction is being performed by preferentially using the three-dimensional absolute coordinate values of the image object closest to the vibrator among the vibrator image object, the marker image object, and the hand image object. The compaction work analysis device according to Claim 1.

3. The marker is configured of a single color or a combination of a plurality of single colors so as to have different color schemes before and after at a predetermined interval in the extension direction of the cord. The compaction work analysis device according to Claim 1.

4. The specifying unit specifies the imaging device coordinate values for the operator image object or the vibrator image object extracted from each of the plurality of image data based on the focal length of each imaging device and the planar coordinate values in the imaging element of each imaging device. The compaction work analysis device according to any one of Claims 1 to 3.

5. The extraction unit extracts a plurality of operator image objects corresponding to the plurality of operators who are working simultaneously from the image data, and a plurality of vibrator image objects corresponding to the plurality of vibrators, The estimation unit estimates a plurality of locations where consolidation is being performed simultaneously in the concrete The consolidation work analysis device according to any one of claims 1 to 4.

6. A step of respectively acquiring, from a plurality of imaging devices, image data obtained by imaging a space where an operator performs a consolidation operation on concrete while holding a vibrator; A step of extracting, from the plurality of acquired image data, an operator image object corresponding to the operator and a vibrator image object corresponding to the vibrator; A step of specifying imaging device coordinate values in an imaging device coordinate system, which is a unique coordinate system of the imaging device, for the operator image object or the vibrator image object respectively extracted from the plurality of image data; A step of converting the specified imaging device coordinate values into three-dimensional absolute coordinate values; A step of estimating locations where consolidation is being performed in the concrete based on the converted three-dimensional absolute coordinate values, and In the step of extracting, At least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator and a marker image object corresponding to a marker provided on a cord extending from the vibrator is extracted as the vibrator image object, An image of a hand corresponding to the hand of the operator is extracted as the operator image object, A consolidation work analysis method for extracting, as a hand image object, an image of a hand determined to be holding the vibrator and / or the cord among both hands of the operator using skeleton estimation in the extraction of the hand image object.

7. On a computer, A step of respectively acquiring, from a plurality of imaging devices, image data obtained by imaging a space where an operator performs a consolidation operation on concrete while holding a vibrator; A step of extracting an operator image object corresponding to the operator and a vibrator image object corresponding to the vibrator from the plurality of acquired image data, wherein at least one of a vibrator image object corresponding to a vibrator provided at the tip of the vibrator and a marker image object corresponding to a marker provided on a cord extending from the vibrator is extracted as the vibrator image object, a hand image object corresponding to the hand of the operator is extracted as the operator image object, and in the extraction of the hand image object, an image of the hand determined to be holding the vibrator and / or the cord among both hands of the operator using skeleton estimation is extracted as the hand image object; A step of specifying imaging device coordinate values in an imaging device coordinate system, which is a unique coordinate system of the imaging device, for the operator image object or the vibrator image object extracted from each of the plurality of image data; A step of converting the specified imaging device coordinate values into three-dimensional absolute coordinate values; A step of estimating a location where tamping is being performed in the concrete based on the converted three-dimensional absolute coordinate values A program for causing the above to be executed.

Images