JP7597352B2 - Cable detection device, method, and program - Google Patents

Description

The present invention relates to a cable detection device, method, and program.

To prevent electric shock accidents, electric power companies must comply with regulations (Wired Telecommunications Equipment Ordinance) regarding the distance between electric wires and surrounding structures. Workers measure the distance periodically using measuring equipment. As there are a huge number of electric wires, there is a demand for making it easier to measure the distance. One way to make distance measurement easier is to use a 3D sensor to measure the distance. Measuring distance using a 3D sensor requires technology to selectively detect electric wires from the point cloud of image data acquired from the 3D sensor.

As a technique for selectively detecting electric wires from a point cloud, for example, Patent Document 1 discloses a technique for learning the regularity (shape, etc.) of a cable (electric wire) and detecting the wire constituent point cloud that constitutes the wire based on the learned cable regularity.

Patent Document 2 also discloses a technology for detecting constituent points that constitute a thin linear object based on the positional relationship of the point included in three-dimensional point cloud information with surrounding points, detecting straight line elements from the constituent points based on tangent direction information for each of the detected constituent points, treating the detected straight line elements as a thin linear object model representing an initial thin linear object, generating a thin linear object model based on the proximity state between thin linear object models and a predetermined connectivity index, estimating the length of the thin linear object model from the positions of the points included in the thin linear object model, and determining whether the thin linear object model is an appropriate model based on the estimated length and a predetermined threshold value.

Furthermore, Non-Patent Document 1 discloses a technique for extracting electric wires from a point cloud obtained by airborne laser scanning.

JP 2019-109839 A JP 2015-1901 A

T. Melzer et al., "Extraction and Modeling of Power Lines from ALS Point Clouds", URL=https://publik.tuwien.ac.at/files/PubDat_119606.pdf

The following analysis is provided by the present inventors.

However, the techniques described in Patent Documents 1 and 2 and Non-Patent Document 1 have the following problems. Patent Document 1 requires learning the regularity of the cables, which is a time-consuming process. Patent Document 2 generates a thin-line object model, which is three-dimensional point cloud data, and determines whether the model is appropriate, which results in a high computational load. Non-Patent Document 1 also performs clustering as a preprocessing step for detecting catenary lines, which are models of electric wires hanging between two points, which results in a decrease in detection accuracy when the point cloud related to the electric wires is sparse.

The main objective of the present invention is to provide a cable detection device, method, and program that can contribute to detecting cable-like objects with high accuracy while reducing the effort and computational load.

A cable detection device according to a first aspect includes a line detection unit that detects a line by projecting a point cloud related to the cable in a region of any height including the point cloud related to the cable in a point cloud related to the detection object in imaging data obtained by imaging the detection object including a cable onto a horizontal plane, and a catenary detection unit that detects a catenary related to the cable by restoring the point cloud related to the cable included in the line detected by the line detection unit and projecting it onto a predetermined vertical plane parallel to the line , wherein the line detection unit angle-converts the point cloud related to the detection object in the imaging data using an IMU sensor or based on the angle of a wall of a building in the detection object so that the direction of gravity in the imaging data is downward, and detects the line using the angle-converted point cloud related to the cable in the detection object .

A cable detection method according to a second aspect is a cable detection method for detecting a catenary- like cable from photography data obtained by photographing a detection object including a cable using a computer , the method including the steps of: detecting a straight line by projecting a point cloud in an arbitrary height region including the point cloud related to the cable in a point cloud related to the detection object in the photography data onto a horizontal plane; and detecting a catenary line related to the cable by restoring the point cloud related to the cable included in the detected straight line and projecting it onto a predetermined vertical plane parallel to the straight line.
Includes.

The program relating to the third viewpoint is a program that causes a computer to execute a process of detecting a catenary-like cable from imaging data of a detection object including a cable , and causes the computer to execute a process of detecting a straight line by projecting a point cloud in an arbitrary height region including the point cloud related to the cable in the point cloud related to the detection object in the imaging data onto a horizontal plane, and a process of restoring the point cloud related to the cable included in the detected straight line and projecting it onto a specified vertical plane parallel to the straight line , thereby detecting the catenary line related to the cable.

The program can be recorded on a computer-readable storage medium. The storage medium can be a non-transient medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. In the present disclosure, the program can also be embodied as a computer program product. The program is input to the computer device from an input device or an external device via a communication interface, stored in a storage device, and drives the processor according to a predetermined step or process, and can display the processing results, including intermediate states as necessary, at each stage via a display device, or can communicate with the outside via the communication interface. As an example, a computer device for this purpose typically includes a processor, a storage device, an input device, a communication interface, and a display device as necessary, all of which can be connected to each other via a bus.

The first to third aspects described above can contribute to detecting cable-like objects with high accuracy without incurring any effort or computational burden.

1 is a conceptual diagram illustrating an example of a usage mode of a cable detection device according to a first embodiment. FIG. 1 is a block diagram illustrating a schematic configuration of a cable detection device according to a first embodiment. 4 is a flowchart illustrating an operation of the cable detection device according to the first embodiment. 5 is a flowchart illustrating in schematic detail the operation of the cable detection unit of the cable detection device according to the first embodiment. 4 is a process image of the first half of an example of the operation of a cable detection unit in the cable detection device according to the first embodiment; 6 is a second half process image following FIG. 5 which illustrates an example of the operation of the cable detection unit in the cable detection device according to the first embodiment. FIG. 11 is a conceptual diagram illustrating an example of a usage mode of the cable detection device according to the second embodiment. FIG. 11 is an image diagram illustrating an example of a usage mode of the cable detection device according to the third embodiment. FIG. 11 is a block diagram illustrating a configuration of a cable detection device according to a fourth embodiment. FIG. 2 is a block diagram illustrating a schematic configuration of hardware resources.

The following describes the embodiments with reference to the drawings. Note that when reference symbols are used in this application, they are intended to aid understanding and are not intended to limit the invention to the illustrated form. The following embodiments are merely illustrative and do not limit the invention. The connection lines between blocks in the drawings and the like referred to in the following description include both bidirectional and unidirectional lines. One-way arrows are used to diagrammatically indicate the flow of the main signal (data) and do not exclude bidirectionality. Furthermore, although not explicitly shown in the circuit diagrams, block diagrams, internal configuration diagrams, connection diagrams, and the like shown in this disclosure, input ports and output ports exist at the input and output ends of each connection line. The same is true for input/output interfaces. The program is executed via a computer device, which includes, for example, a processor, a storage device, an input device, a communication interface, and a display device as necessary, and the computer device is configured to be able to communicate with devices inside or outside the device (including a computer) via the communication interface, whether wired or wireless.

[Embodiment 1]
The cable detection device according to the first embodiment will be described with reference to the drawings. Fig. 1 is an image diagram showing an example of a usage mode of the cable detection device according to the first embodiment. Fig. 2 is a block diagram showing a configuration of the cable detection device according to the first embodiment.

The cable detection device 1 is a device that selectively detects a catenary-like cable (e.g., an electric wire, an overhead line, a wire, a communication line, etc.) hanging down from both ends based on the photographic data 2 related to the detection object 90 (see Figures 1 and 2). The cable detection device 1 can be used, for example, for measuring the separation distance (e.g., the shortest distance between an electric wire and a surrounding structure) at an electric power company, for detecting and measuring the distance of wires in the construction industry, for detecting and measuring the distance of overhead lines in the railway field, and for detecting and measuring the distance of communication lines in the communication industry. The cable detection device 1 is connected to a three-dimensional sensor 60 so as to be able to communicate with it. The cable detection device 1 acquires the photographic data 2 related to the detection object 90 from the three-dimensional sensor 60.

Here, the three-dimensional sensor 60 is a device that three-dimensionally senses and photographs the surface (surface that can be photographed) of the detection object 90 (see Figures 1 and 2). The three-dimensional sensor 60 is connected to the cable detection device 1 so as to be able to communicate with it. The three-dimensional sensor 60 generates photographed data 2 in a predetermined format by photographing the detection object 90, and outputs the generated photographed data 2 to the cable detection device 1. For the three-dimensional sensor 60, for example, a ToF (Time of Flight) camera, a stereo camera, a 3D-LIDAR (Laser Imaging Detection And Ranging), a depth sensor, a distance measurement sensor, a distance camera, etc. can be used. The three-dimensional sensor 60 is operated by an operator. Note that the photographed data 2 is data generated by the three-dimensional sensor 60 in a predetermined format, and is point cloud data drawn with a point cloud (a collection of many points having XYZ coordinate (three-dimensional coordinate) information) (see Figure 2). The three-dimensional sensor 60 can be changed to a sensor device with various output formats according to the customer's request.

The cable detection device 1 can be a device (computer device) having functional units that constitute a computer (e.g., a processor, a storage device, an input device, a communication interface, and a display device), such as a notebook personal computer, a smartphone, or a tablet terminal. The cable detection device 1 realizes a preprocessing unit 10, a cable detection unit 20, and a user interface unit 30 by executing a predetermined program.

The pre-processing unit 10 is a functional unit that performs pre-processing on the shooting data 2 to detect cables (see FIG. 2). The pre-processing unit 10 outputs the pre-processed shooting data 2 to the cable detection unit 20. The pre-processing unit 10 includes a format conversion unit 11 and a noise removal unit 12. The pre-processing unit 10 may also include a functional unit that interpolates missing points based on shooting data from other 3D sensors or points in the shooting data 2.

The format conversion unit 11 is a functional unit that converts the format of the shooting data 2 into a common format that can be used in common in the cable detection device 1 as pre-processing (see FIG. 2). The format conversion unit 11 outputs the converted shooting data 2 in the common format to the noise removal unit 12. Note that if the format of the shooting data 2 is originally a common format, the format conversion can be omitted.

The noise removal unit 12 is a functional unit that removes noise (points unnecessary for detection) from the point cloud in the shooting data 2 from the format conversion unit 11 as pre-processing (see FIG. 2). The noise removal unit 12 outputs the shooting data 2 from which noise has been removed to the cable detection unit 20. Examples of noise removal methods include smoothing processing, filtering (e.g., moving average filter processing, median filter processing, etc.), and outlier removal processing (e.g., outlier removal processing by chi-squared test). Note that if there is almost no noise, noise removal may be omitted.

The cable detection unit 20 is a functional unit that selectively detects a catenary-like cable (electric wire 92 in FIG. 1) hanging down from both ends of the detection object 90 from the photographic data 2 preprocessed by the preprocessing unit 10 (see FIG. 2). The cable detection unit 20 detects the cable based on the characteristics of the cable (e.g., it is a straight line when viewed from directly above, and a catenary exists in a vertical plane including the entire straight line when viewed from the side). The cable detection unit 20 outputs the cable detection result to the user interface unit 30. The cable detection unit 20 includes a straight line detection unit 21 and a catenary detection unit 22.

The straight line detection unit 21 is a functional unit that detects straight lines by projecting a point cloud in an area of any height in the point cloud related to the shooting data 2 onto a horizontal plane (see FIG. 2). The straight line detection unit 21 converts (rotates) the point cloud related to the shooting data 2 at an angle so that the direction of gravity of the shooting data 2 at the time of shooting is downward. If the shooting data 2 is photographed so that the direction of gravity is downward at the time of shooting, the angle conversion may be omitted. The straight line detection unit 21 specifies an area of any height (designated area 96 in FIG. 1) including a point cloud related to a cable (electric wire 92 in FIG. 1) in the vertical direction (Y-axis direction) in a space including the point cloud related to the angle-converted shooting data 2. The straight line detection unit 21 divides the specified area (designated area 96 in FIG. 1) into multiple small areas in the vertical direction (Y-axis direction). The line detector 21 projects the point cloud (three-dimensional data) in each divided small area onto a horizontal plane (XZ plane) and compresses it into two-dimensional data (data that uses only the XZ coordinates of the point cloud and does not use the Y coordinate). The line detector 21 detects lines from the compressed two-dimensional data. Details of the operation of the line detector 21 (see Figures 4 to 6) will be described later.

The catenary detection unit 22 is a functional unit that restores the point cloud based on the straight line detected by the straight line detection unit 21, projects it onto a predetermined vertical plane, and detects the catenary as a cable (see FIG. 2). The catenary detection unit 22 restores the point cloud (restores the Y coordinate) based on two-dimensional data (data that uses only the XZ coordinates of the point cloud and does not use the Y coordinate) related to the straight line detected by the straight line detection unit 21, and decompresses it into three-dimensional data (data that uses all of the XYZ coordinates of the point cloud). The catenary detection unit 22 performs angle conversion (rotation) on a predetermined horizontal plane so that any straight line detected by the straight line detection unit 21 (for example, a straight line related to the electric wire 92) becomes parallel to the XY plane (or the YZ plane). The catenary detection unit 22 projects the angle-converted point cloud onto the XY plane (or the YZ plane) and compresses it into two-dimensional data. The catenary detection unit 22 detects the catenary as a cable from the compressed two-dimensional data. Details of the operation of the catenary detection unit 22 (see Figures 4 to 6) will be described later.

The user interface unit 30 is a functional unit equipped with a user interface (see FIG. 2). The user interface unit 30 includes a display unit 31 and an input unit 32.

The display unit 31 is a functional unit that displays information (see FIG. 2). The display unit 31 displays the detection results of the cable (electric wire 92 in FIG. 1) detected by the cable detection unit 20.

The input unit 32 is a functional unit that inputs information to the cable detection device 1 through user operation (see FIG. 2). When detecting a cable with the cable detection unit 20, the input unit 32 can be used to specify an area (specified area 96 in FIG. 1) in which a cable (e.g., electric wire 92 in FIG. 1) exists, or to specify (select) an area in which a cable to be detected exists from among multiple cables.

Next, the operation of the cable detection device according to the first embodiment will be described with reference to the drawings. FIG. 3 is a flow chart that shows the operation of the cable detection device according to the first embodiment. Please refer to FIG. 1 and FIG. 2 for the configuration of the cable detection device and an image of the object to be measured.

First, the pre-processing unit 10 of the cable detection device 1 acquires the image data 2 relating to the detection object 90 imaged by the 3D sensor 60 (step A1).

Next, as preprocessing, the format conversion unit 11 of the preprocessing unit 10 of the cable detection device 1 converts the format of the shooting data 2 acquired in step A1 into a common format that can be commonly used in the cable detection device 1 (step A2). Note that if the format of the shooting data 2 is originally a common format, the format conversion may be omitted.

Next, the noise removal unit 12 of the pre-processing unit 10 of the cable detection device 1 removes noise from the point cloud in the shooting data 2 converted to the common format in step A2 as pre-processing (step A3). Note that if there is almost no noise, noise removal may be omitted.

Next, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 projects the point cloud in an area of any height in the point cloud related to the photographed data 2 from which noise has been removed in step A3 onto a horizontal plane to detect straight lines (step A4). The area of any height can be a height input (specified, selected) by a user's operation at the input unit 32, or a preset height. Details of straight line detection (see Figures 4 to 6) will be described later.

Finally, the catenary detection unit 22 of the cable detection unit 20 of the cable detection device 1 reconstructs the point cloud based on the straight lines detected by the straight line detection unit 21 and projects them onto a predetermined vertical plane to detect the catenary lines as cables (step A5). Details of the detection of catenary lines (see Figures 4 to 6) will be described later.

Next, the operation of the cable detection device according to embodiment 1 when detecting straight lines and catenary lines will be described with reference to the drawings. FIG. 4 is a flow chart that shows in schematic detail the operation of the cable detection unit of the cable detection device according to embodiment 1. FIG. 5 is a first half process image that shows in schematic detail an example of the operation of the cable detection unit in the cable detection device according to embodiment 1. FIG. 6 is a second half process image following FIG. 5 that shows in schematic detail an example of the operation of the cable detection unit in the cable detection device according to embodiment 1.

First, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 performs angle conversion (rotation) of the point cloud related to the shooting data 2 so that the direction of gravity of the shooting data 2 at the time of shooting is downward (step B1).

Here, an example of a method for angle conversion is to use an IMU (Inertial Measurement Unit) sensor to convert the angle of the inclination of the shooting data 2 at the time of shooting to match the direction of gravity. Also, instead of using an IMU sensor, angle conversion may be performed based on the angle of the wall of the building 93 so that the wall becomes a vertical surface.

Next, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 designates an area of any height (designated area 96 in FIG. 5(A)) that includes the point cloud related to the cable (electric wire 92 in FIG. 5(A)) in the vertical direction (Y-axis direction) in a space that includes the point cloud related to the shooting data 2 that was angle-converted in step B1 (step B2).

Here, the area of any height (corresponding to the designated area 96) can be a height input (specified, selected) by the user through the input unit 32, or a preset height. The designated area 96 is specified to include a point cloud relating to the entire electric wire 92, but not to include a point cloud relating to a structure that impedes the detection of the electric wire 92 (a building 94 that overlaps with the electric wire 92 when viewed from directly above in FIG. 5(A)).

Next, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 divides the area of the arbitrary height specified in step B2 (specified area 96 in FIG. 5(A)) into multiple small areas (small areas 96a, 96b, 96c in FIG. 5(A)) in the vertical direction (Y-axis direction) (step B3).

Next, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 projects the point cloud (three-dimensional data) in each small area divided in step B3 onto a horizontal plane (XZ plane) and compresses it into two-dimensional data (step B4).

Here, the two-dimensional data can be data that uses only the XZ coordinates of the point cloud and does not use the Y coordinate, and as shown in Figure 5 (B), the point cloud of the utility pole 91, the electric wire 92, and the building designated area portion 93a (the part of the building 93 that is in the designated area 96) can be projected onto the XZ plane and represented linearly (straight or curved) on the XZ plane.

Next, the straight line detection unit 21 of the cable detection unit 20 of the cable detection device 1 detects straight lines from the two-dimensional data compressed in step B4 (step B5). As a result, as shown in FIG. 5(C), only the electric wire 92 and the building designated area 93a related to the straight lines are detected, and the electric pole 91 related to the curved lines is excluded.

Here, as a method for detecting a straight line, for example, a method for detecting a straight line from an image that has been Hough transformed can be given. When detecting a straight line, if the point cloud relating to the part of the electric wire 92 far from the shooting position becomes sparse and the straight line cannot be sufficiently detected from the HOUGH transformed image, the point cloud may be weighted according to the distance from a predetermined position (e.g., the origin) when voting for the HOUGH transformation. For example, the distance of the target point from the origin (0,0,0) may be calculated, and the number of votes may be multiplied by a coefficient according to the distance from the origin. Regarding the coefficient and vote, if the distance (m) from the origin is the same, the coefficient value may be the same. If the distance from the origin is 1m, the coefficient may be 1 and the number of votes may be 1, and if the distance is 5m, the coefficient may be 5 and the number of votes may be 5.

Next, the catenary detection unit 22 of the cable detection unit 20 of the cable detection device 1 restores the point cloud (restores the Y coordinate) based on the two-dimensional data (data that uses only the XZ coordinates of the point cloud and does not use the Y coordinate) related to the straight line detected in step B5, and decompresses it into three-dimensional data (step B6). As a result, the three-dimensional data can be such that only the electric wire 92 related to the straight line and the building designated area portion 93a are shown, as shown in Figure 5 (D).

Next, the catenary detection unit 22 of the cable detection unit 20 of the cable detection device 1 performs angle conversion (rotation) of the point cloud related to the decompressed three-dimensional data so that any straight line detected by the straight line detection unit 21 (for example, the straight line related to the electric wire 92 in FIG. 5(C)) becomes parallel to the XY plane (a specified vertical plane; the YZ plane is also acceptable) (step B7). This makes it possible to make the point cloud related to the electric wire 92 parallel to the XY plane, as shown in FIG. 6(A).

Next, the catenary detection unit 22 of the cable detection unit 20 of the cable detection device 1 projects the point cloud angle-converted in step B7 onto a vertical plane (the XY plane in FIG. 6(B) ; it can also be the YZ plane) and compresses it into two-dimensional data (step B8).

Here, the two-dimensional data can be data that uses only the XY coordinates of the point cloud and does not use the Z coordinate, and can be data that projects the point cloud of the electric wires 92 and the building designated area portion 93a onto the XY plane and represents it as catenary lines and a plane on the XY plane, as shown in FIG. 6(B).

Finally, the catenary detection unit 22 of the cable detection unit 20 of the cable detection device 1 selects and detects catenary lines as cables (electric wires 92) from the two-dimensional data compressed in step B8 (step B9). As a result, as shown in FIG. 6(C), only the electric wires 92 related to the catenary lines are detected, and the building designation area portion 93a related to the plan is excluded.

Here, an example of a method for detecting catenary lines is to detect catenary lines from a HOUGH transformed image.

According to the first embodiment, by combining techniques with low effort and computational load, such as angle transformation, projection, and point cloud restoration, it is possible to contribute to selectively detecting cable-like objects with high accuracy from three-dimensional data (point cloud).

Furthermore, according to embodiment 1, it is possible to selectively detect cable-like objects from three-dimensional data with high accuracy, which makes it easier to measure the distance between cables and structures in the power industry, for example.

Furthermore, according to the first embodiment, even when detecting catenary lines such as various electric wires 92 with different degrees of slack (the degree of slackness of the wire stretched between two points), it is possible to detect cables without using machine learning.

In addition, according to the first embodiment, the cable can be accurately detected from the three-dimensional data using only the three-dimensional sensor 60 and the cable detection device 1, such as a notebook personal computer or a tablet terminal, so that the worker can easily detect the cable without using a dedicated detection device.

Furthermore, according to the first embodiment, the three-dimensional data captured by the three-dimensional sensor 60 can be used, so that when performing photography work in dangerous locations such as high places or dark places, photography work can be performed from a safe location without going to the source of the cable that is the object to be detected.

[Embodiment 2]
The cable detection device according to the second embodiment will be described with reference to the drawings. Fig. 7 is a schematic conceptual diagram showing an example of a usage mode of the cable detection device according to the second embodiment.

Embodiment 2 is a modified example of embodiment 1, in which a cable detection device 1 with a built-in three-dimensional sensor unit 40 is used. As the cable detection device 1, for example, a portable information processing device such as a smartphone or tablet terminal that originally has a built-in three-dimensional sensor unit 40 (e.g., a depth sensor, a ToF camera, etc.) can be used. The configuration and operation of the cable detection device 1 according to embodiment 2, other than the three-dimensional sensor unit 40, are the same as the configuration and operation of the cable detection device according to embodiment 1 (see FIG. 2).

According to the second embodiment, similar to the first embodiment, by combining techniques with low effort and computational load such as angle transformation, projection, and point cloud restoration, it is possible to contribute to selectively detecting cable-like objects with high accuracy from three-dimensional data (point clouds) and to facilitate the handling of the cable detection device 1.

[Embodiment 3]
The cable detection device according to the third embodiment will be described with reference to the drawings. Fig. 8 is a schematic conceptual diagram showing an example of a usage mode of the cable detection device according to the third embodiment.

The third embodiment is a modified example of the first embodiment, in which the cable detection device 1 is communicatively connected to an information communication terminal 70 incorporating a three-dimensional sensor unit 71 via a network 80.

The cable detection device 1 may be the same as the cable detection device according to embodiment 1 (see FIG. 2), and may be a cloud-based device or server device. The cable detection device 1 is connected to the network 80 so as to be capable of wired communication, but may also be connected to the network 80 so as to be capable of wireless communication. The operation of the cable detection device 1 is the same as the operation of the cable detection device according to embodiment 1 (see FIG. 3 to FIG. 5).

The information communication terminal 70 is a terminal device that communicates information. For example, a smartphone, tablet terminal, or the like that originally has a built-in three-dimensional sensor unit 71 (e.g., a depth sensor, a ToF camera, etc.) can be used as the information communication terminal 70. The information communication terminal 70 is connected to the network 80 so as to be capable of wireless communication, but may also be connected to the network 80 so as to be capable of wired communication. The information communication terminal 70 has a function of transmitting image data (corresponding to 2 in FIG. 2) of the detection target object 90 captured by the three-dimensional sensor unit 71 to the cable detection device 1.

The network 80 is an information and communication network that connects the cable detection device 1 and the information and communication terminal 70 so that they can communicate with each other. For example, the network 80 may be a communication network such as a personal area network (PAN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), or a global area network (GAN). The network 80 includes wireless base stations, communication equipment, wired cables, etc.

According to the third embodiment, as in the first embodiment, a combination of techniques with low effort and computational load, such as angle transformation, projection, and point cloud restoration, can contribute to selective detection of cable-like objects with high accuracy from three-dimensional data (point clouds), and can also contribute to centralized management of the distance between the cable and the structure by simultaneously photographing the detection target 90 at multiple locations and performing cable detection in one location.

[Embodiment 4]
A cable detection device according to the fourth embodiment will be described with reference to the drawings. Fig. 9 is a block diagram showing a schematic configuration of the cable detection device according to the fourth embodiment.

The cable detection device 1 is a device that detects a catenary-shaped cable from the photographed data 2. The cable detection device 1 includes a straight line detection unit 21 and a catenary line detection unit 22. The straight line detection unit 21 is configured to detect a straight line by projecting a point cloud in an area of any height in the point cloud related to the photographed data 2 onto a horizontal plane. The catenary line detection unit 22 is configured to reconstruct the point cloud based on the straight line detected by the straight line detection unit and project it onto a specified vertical plane, thereby detecting a catenary line as a cable.

According to the fourth embodiment, a combination of techniques with low effort and computational load, such as projection and point cloud restoration, can contribute to selectively detecting cable-like objects with high accuracy from a point cloud related to the captured data.

The cable detection device according to the first to fourth embodiments can be configured using so-called hardware resources (information processing device, computer), and a device having the configuration shown in FIG. 10 can be used. For example, the hardware resource 100 includes a processor 101, a memory 102, a network interface 103, and the like, which are interconnected by an internal bus 104.

Note that the configuration shown in FIG. 10 is not intended to limit the hardware configuration of the hardware resource 100. The hardware resource 100 may include hardware (e.g., an input/output interface) that is not shown. Furthermore, the number of units such as the processor 101 included in the device is not intended to be limited to the example shown in FIG. 10, and for example, multiple processors 101 may be included in the hardware resource 100. The processor 101 may be, for example, a CPU (Central Processing Unit), an MPU (Micro Processor Unit), a GPU (Graphics Processing Unit), etc.

Memory 102 may be, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a HDD (Hard Disk Drive), or a SSD (Solid State Drive).

The network interface 103 may be, for example, a LAN (Local Area Network) card, a network adapter, a network interface card, etc.

The functions of the hardware resource 100 are realized by the above-mentioned processing module. The processing module is realized, for example, by the processor 101 executing a program stored in the memory 102. The program can be downloaded via a network or updated using a storage medium on which the program is stored. Furthermore, the processing module may be realized by a semiconductor chip. In other words, it is sufficient that the functions performed by the processing module are realized by the execution of software on some kind of hardware.

A part or all of the above embodiments may be described as follows, but is not limited to the following:

[Appendix 1]
a straight line detection unit configured to detect a straight line by projecting a point cloud in an area of a given height in the point cloud related to the photographing data onto a horizontal plane;
a catenary detection unit configured to reconstruct a point cloud based on the straight line detected by the straight line detection unit and project the point cloud onto a predetermined vertical plane to detect a catenary as a cable;
Equipped with
Cable detection device.
[Appendix 2]
the straight line detection unit is configured to convert an angle of the point cloud related to the imaging data so that the gravity direction of the imaging data is downward, and to detect the straight line using the point cloud related to the imaging data that has been subjected to the angle conversion.
2. The cable detection apparatus of claim 1.
[Appendix 3]
Further comprising an input unit for inputting information,
The straight line detection unit is configured to specify, in a space including the point cloud related to the shooting data, an area of the arbitrary height including the point cloud related to the cable in a vertical direction based on the information input by the input unit.
3. The cable detection device of claim 1 or 2.
[Appendix 4]
the straight line detection unit is configured to divide the specified area at the arbitrary height into a plurality of small areas in the vertical direction, and detect the straight line by projecting a point cloud in each of the divided small areas onto the horizontal plane.
4. The cable detection apparatus of claim 3.
[Appendix 5]
The catenary detection unit is configured to perform angle conversion of the restored point cloud so that any straight line detected by the straight line detection unit becomes parallel to a predetermined vertical plane, and to detect the catenary using the angle-converted point cloud.
5. The cable detection device of claim 1 .
[Appendix 6]
The catenary detection unit is configured to project the angle-transformed point cloud onto the predetermined vertical plane to detect the catenary.
6. The cable detection apparatus of claim 5.
[Appendix 7]
The cable detection device is configured to be communicatively connected to a three-dimensional sensor that photographs an object to be measured and outputs the photographed data.
7. The cable detection device of claim 1 .
[Appendix 8]
Further comprising a three-dimensional sensor unit for photographing the measurement object and outputting the photographed data.
7. The cable detection device of claim 1 .
[Appendix 9]
The cable detection device is configured to be communicably connected via a network to a mobile communication terminal including a three-dimensional sensor unit that photographs an object to be measured and outputs the photographed data.
7. The cable detection device of claim 1 .
[Appendix 10]
A cable detection method for detecting a catenary cable from imaging data using hardware resources, comprising:
A step of detecting a straight line by projecting a point cloud in an area of a given height in the point cloud related to the photographing data onto a horizontal plane;
A step of recovering the point cloud based on the detected straight line and projecting the point cloud onto a predetermined vertical plane to detect the catenary as the cable;
Including,
Cable detection methods.
[Appendix 11]
A program for causing a hardware resource to execute a process for detecting a catenary cable from photographed data,
A process of detecting a straight line by projecting a point cloud in an area of a given height in the point cloud related to the photographing data onto a horizontal plane;
A process of recovering a point cloud based on the detected straight line and projecting the point cloud onto a predetermined vertical plane to detect a catenary as the cable;
causing the hardware resource to execute
program.

The disclosures of the above patent and non-patent documents are incorporated herein by reference and may be used as the basis or part of the present invention as necessary. Within the framework of the entire disclosure of the present invention (including the claims and drawings), and further based on the basic technical ideas, modifications and adjustments of the embodiments and examples are possible. Furthermore, within the framework of the entire disclosure of the present invention, various combinations or selections (or non-selection as necessary) of various disclosed elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible. In other words, the present invention naturally includes various modifications and corrections that a person skilled in the art would be able to make in accordance with the entire disclosure, including the claims and drawings, and the technical ideas. Furthermore, with regard to the numerical values and numerical ranges described in this application, any intermediate value, lower numerical value, and small range are considered to be described even if not specified. Furthermore, the disclosures of the above cited documents may be used in part or in whole in combination with the descriptions in this document as part of the disclosure of the present invention as necessary, in accordance with the spirit of the present invention, and are considered to be included (belong) to the disclosures of this application.

REFERENCE SIGNS LIST 1 Cable detection device 2 Photographed data 10 Pre-processing unit 11 Format conversion unit 12 Noise removal unit 20 Cable detection unit 21 Straight line detection unit 22 Catenary detection unit 30 User interface unit 31 Display unit 32 Input unit 40 Three-dimensional sensor unit 60 Three-dimensional sensor 70 Information communication terminal 71 Three-dimensional sensor unit 80 Network 90 Detection target 91 Utility pole 92 Electric wire 93, 94 Building 93a Building designated area unit 95 Ground 96 Designated area 96a, 96b, 96c Small area 100 Hardware resources 101 Processor 102 Memory 103 Network interface 104 Internal bus

Claims (9)

a line detection unit that detects a line by projecting a point cloud related to the cable, which is in an arbitrary height region including the point cloud related to the cable in a point cloud related to the detection object in imaging data obtained by imaging the detection object including the cable, onto a horizontal surface;
a catenary detection unit that detects catenary lines associated with the cable by restoring a point cloud associated with the cable that is included in the straight line detected by the straight line detection unit and projecting the point cloud onto a predetermined vertical plane that is parallel to the straight line;
Equipped with
the straight line detection unit converts an angle of a point cloud related to the detection object in the photographing data by using an IMU sensor or based on an angle of a wall surface of a building in the detection object so that the direction of gravity in the photographing data is downward, and detects the straight line by using the angle-converted point cloud related to the cable in the detection object.
Cable detection device. An input unit for inputting information related to the area at any height including the point cloud related to the cable,
the straight line detection unit, based on the information input by the input unit, specifies, in a space including the point cloud related to the imaging data, an area of the arbitrary height including the point cloud related to the cable in a vertical direction;
2. The cable detection apparatus of claim 1. the line detection unit divides the specified area at the arbitrary height into a plurality of small areas in the vertical direction, and projects a point cloud in each of the divided small areas onto the horizontal plane to detect the line;
3. The cable detection device of claim 2. the catenary detection unit performs angle conversion on a point cloud related to the cable included in the restored straight line so that any of the straight lines detected by the straight line detection unit becomes parallel to the predetermined vertical plane, and detects a catenary related to the cable using the angle-converted point cloud related to the cable.
4. A cable detection device according to claim 1. the catenary detection unit projects the angle-converted point cloud relating to the cable onto the predetermined vertical plane to detect catenary lines relating to the cable.
5. The cable detection apparatus of claim 4. The cable detection device is communicatively connected to a three-dimensional sensor that captures an image of the detection object and outputs the captured image data.
6. A cable detection device according to any one of the preceding claims. Further comprising a three-dimensional sensor unit that captures an image of the detection object and outputs the captured image data.
6. A cable detection device according to any one of the preceding claims. A cable detection method for detecting a catenary cable from image data obtained by photographing an object to be detected, the object including a cable, using a computer, comprising:
a step of detecting a straight line by projecting a point cloud in an arbitrary height region including the point cloud related to the cable in the point cloud related to the detection object in the photographing data onto a horizontal plane;
A step of detecting a catenary of the cable by recovering a point cloud related to the cable included in the detected straight line and projecting the point cloud onto a predetermined vertical plane parallel to the straight line;
Including,
In the step of detecting the straight line, an angle conversion is performed on a point cloud related to the detection object in the photographing data, using an IMU sensor or based on an angle of a wall surface of a building in the detection object, so that the direction of gravity in the photographing data is downward, and the straight line is detected using the angle-converted point cloud related to the cable in the detection object.
Cable detection methods. A program for causing a computer to execute a process for detecting a catenary-shaped cable from image data obtained by photographing a detection object including a cable,
A process of detecting a straight line by projecting a point cloud in an arbitrary height region including the point cloud related to the cable in the point cloud related to the detection object in the photographed data onto a horizontal plane;
A process of recovering a point cloud related to the cable included in the detected straight line and projecting the point cloud onto a predetermined vertical plane parallel to the straight line to detect a catenary related to the cable;
causing the computer to execute
In the process of detecting the straight line, an angle conversion is performed on a point cloud related to the detection object in the photographing data, using an IMU sensor or based on an angle of a wall surface of a building in the detection object, so that the direction of gravity in the photographing data is downward, and the straight line is detected using the angle-converted point cloud related to the cable in the detection object.
program.

Images