JP2011170400A - Program, method, and apparatus for identifying facility - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To identify facilities such as a utility pole and a steel tower which have been photographed. <P>SOLUTION: This method performs image recognition processing to a first image stored in an image data storage portion for storing an image whose reference line perpendicular to an upper side or a bottom side is specified and which is photographed so that a distance of the upper side or the bottom side is in proportion to an angle viewed from a photographing point, photographing position data of the photographing point, and an azimuth angle of the reference line, extracts an image portion of facilities to be identified, the facilities including the utility pole and the steel tower, calculates a displacement angle of the image portion from a relationship between a straight line passing through the extracted image portion, and the reference line, calculates an azimuth angle of the image portion based on the displacement angle, and the azimuth angle of the reference line, and extracts an identifier of the facilities to be identified closest to the photographing point among the facilities to be identified included in a range specified from the photographing position data of the photographing point and the calculated azimuth angle of the image portion from a facilities data storage portion in which the identifier of the facilities to be identified and position data are registered. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a technique for identifying equipment such as utility poles and steel towers in an image.

  For example, Japanese Patent Application Laid-Open No. 2001-273481 discloses a technique for easily taking a photograph of a utility pole wired overhead, standardizing it, and managing it centrally. More specifically, the utility pole is imaged as a wide-angle three-dimensional fisheye image, the fisheye image information is converted into two-dimensional video information, and the two-dimensional video information is converted into a visual image for recording or recording. Display or further convert the visual image into digital information, record or display it, and check the entire view and installation environment of the utility pole. However, the direction of the camera is different and the image from the traveling vehicle is not processed.

  Japanese Laid-Open Patent Publication No. 2002-357557 discloses a management system for roads and surrounding facilities that can reduce the labor burden on workers when checking roads and surrounding facilities. Specifically, abnormalities in roads and surrounding facilities can be detected by image processing the video data and a data recording unit that records video data such as roads and surrounding facilities acquired by a camera mounted on a patrol car. Second video data acquired by shooting on a second date different from the first date, image data to be detected and video data to be compared with the first video data acquired by shooting on the first date A video data specifying unit for specifying from the group. The image processing unit detects abnormalities such as roads and surrounding facilities by comparing and contrasting the first video data and the second video data using an image processing technique. It is not considered to identify which equipment on the map is the equipment taken.

  Further, Japanese Patent Application Laid-Open No. 10-294932 discloses a digital image photographing apparatus that automatically performs photographing at a place where a photographing position for a patrol work or the like is designated in advance. Specifically, a database that stores a list of planned shooting locations, a DGPS (Differential Global Positioning System) that measures the current position, and the position information recorded in the database from the database and DGPS position information. Means for identifying this, means for digitally capturing an image, and means for recording the captured image. Then, when it is determined that the image is within the range of the shooting location, the image shot by the shooting means is recorded in the recording means. According to this, it becomes possible to automate the photographing of the inspection place. Even if the shooting position is not accurately known, it is possible to set the shooting location by specifying the name of the device or the spot. However, a technique for identifying a specific facility from an image is not disclosed.

Japanese Patent Laid-Open No. 2001-273481 JP 2002-357557 A JP-A-10-294932

  It is very expensive for one person to go around the facilities such as power poles and steel towers installed around the road and the roads. To reduce this cost, take an image of the equipment while driving the car. Can be considered. However, there is no conventional technique for automatically identifying which equipment is being photographed.

  Accordingly, an object of the present invention is to provide a novel technique for identifying facilities such as photographed utility poles and steel towers.

  In the equipment identification method of the present invention, (A) a first reference image or reference point perpendicular to the upper side or the bottom side is specified, and the first image is taken so that the distance on the upper side or the bottom side is proportional to the angle viewed from the imaging point. Image recognition processing is performed on the first image stored in the first image data storage unit that stores the image, the shooting position data of the shooting point, and the reference line or the azimuth angle of the reference point. And (B) calculating the displacement angle of the image part from the relationship between the straight line passing through the extracted image part and the straight line passing through the reference line or reference point and perpendicular to the top or bottom side. An azimuth angle calculating step for calculating an azimuth angle of the image portion based on the displacement angle and the azimuth angle of the reference line or the reference point stored in the first image data storage unit; and (C) the first image Stored in the data storage Among the identification target facilities included in the range specified from the shooting position data of the shadow point and the calculated azimuth angle of the image portion, the identifier of the identification target facility closest to the shooting point is the identifier of the identification target facility and the position data. Extracting from the registered facility data storage unit.

  In this way, even an image taken while a vehicle in which a camera is installed travels can be properly identified even with relatively thin equipment such as utility poles and steel towers.

  The azimuth angle calculating step described above includes a step of calculating a displacement angle of the image part from a distance from a straight line passing through the reference line or the reference point and perpendicular to the upper side or the bottom side to the straight line passing through the extracted image part; The step of calculating the azimuth angle of the image portion by the sum of the displacement angle and the azimuth angle may be included. From the definition of the first image, the angle can be determined if the distance is known, so that the azimuth angle of the facility can be obtained.

  Further, the equipment identification method generates a first image by inverse polar coordinate transformation on a second image taken with a fisheye lens facing the zenith and stored in the second image data storage unit, and stores the first image data. The method may further include a step of storing in the unit. In this way, the first image can be obtained at a low cost.

  Note that the azimuth angle calculating step described above includes a step of generating a third image by polar coordinate conversion on the first image, a straight line passing through a portion corresponding to the image portion in the third image, a reference line or a reference point. And calculating a displacement angle of the image portion as an angle formed by a second straight line corresponding to a straight line perpendicular to the top or bottom of the street. By performing such polar coordinate conversion, for example, subsequent processing such as recognizing an electric wire can be easily performed.

  It is possible to create a program for causing the hardware to perform the processing described above, and the program can be read by a computer such as a flexible disk, a CD-ROM, a magneto-optical disk, a semiconductor memory, and a hard disk. It is stored in a possible storage medium or storage device. Note that data being processed is temporarily stored in a storage device such as a computer memory.

  According to the present invention, it is possible to appropriately identify a photographed facility.

FIG. 1 is a schematic diagram showing a state of photographing. FIG. 2 is a functional block diagram of the measuring apparatus. FIG. 3 is a diagram illustrating a process flow of the measurement process. FIG. 4 is a diagram illustrating an example of an image captured in the first embodiment. FIG. 5 is a diagram illustrating an example of data stored together with a captured image. FIG. 6 is a functional block diagram of the analysis apparatus according to the first embodiment. FIG. 7 is a diagram illustrating a processing flow of analysis processing according to the first embodiment. FIG. 8 is a diagram for explaining the inverse polar coordinate transformation. FIG. 9 is a diagram for explaining the inverse polar coordinate transformation. FIG. 10 is a diagram for explaining the image recognition processing. FIG. 11 is a diagram illustrating a processing flow of equipment identification processing. FIG. 12 is a diagram for explaining processing for calculating the displacement angle between the recognized equipment and the traveling direction. FIG. 13 is a diagram for explaining processing for equipment identification. FIG. 14 is a diagram illustrating an example of data stored in the equipment position DB. FIG. 15 is a diagram illustrating an example of data stored in the identification result storage unit. FIG. 16 is a diagram for explaining processing after polar coordinate conversion. FIG. 17 is a functional block diagram of the analysis apparatus according to the third embodiment. FIG. 18 is a diagram illustrating a processing flow of analysis processing according to the third embodiment. FIG. 19 is a functional block diagram of a computer.

[Embodiment 1]
In the present embodiment, as shown in FIG. 1, a camera 200 is mounted on a vehicle 100, the vehicle 100 travels on a road, and shooting is performed at a predetermined interval by the camera 200. As will be described below, the vehicle 100 is also equipped with a measurement device 300, and a predetermined interval is determined according to a measurement interval of a GPS (Global Positioning System) device included in the measurement device 300. In the present embodiment, a fisheye lens is used for the camera 200, and the fisheye lens is installed in a shape facing the zenith.

  FIG. 2 shows a functional block diagram of the measuring apparatus 300 mounted on the vehicle 100. The measurement apparatus 300 includes a GPS device 311, an image data storage processing unit 313, and an image data storage unit 315. The image data storage processing unit 313 causes the camera 200 to capture images at predetermined intervals, and associates image data captured by the camera 200 with imaging position data measured by the GPS device 311 and the like. Store in the data storage unit 315.

  FIG. 3 shows a processing flow of the measuring apparatus 300. The image data storage processing unit 313 waits until the shooting time is reached (step S1), and instructs the camera 200 when the predetermined time elapses and the shooting time is reached. The camera 200 performs shooting according to an instruction from the image data storage processing unit 313 (step S3), and outputs the image data of the captured image to the image data storage processing unit 313. The image data storage processing unit 313 stores the image data from the camera 200 in the image data storage unit 315 together with the shooting position data and the traveling direction data of the image shooting time measured by the GPS device 311 (step S5). Such a process is repeated until the end of the process is instructed (step S7).

  The traveling direction data is an azimuth angle. For example, the azimuth angle is calculated from a straight line connecting the position measured immediately before and the position measured this time.

  An example of data stored in the image data storage unit 315 is shown in FIGS. FIG. 4 shows an example of an image taken by the camera 200 with a fisheye lens in the present embodiment. As shown in FIG. 4, in the present embodiment, the center of the circular image portion is adjusted so as to face the zenith, and the traveling direction in the image is specified in advance according to the installation mode on the vehicle 100. In the present embodiment, it is assumed that the horizontal left direction is the traveling direction in the image of FIG.

  The image data storage unit 315 stores data as shown in FIG. 5 in association with each image data. That is, latitude and longitude and an azimuth that is a traveling direction are stored as shooting position data. Instead of the latitude and longitude, an X coordinate value and a Y coordinate value may be calculated and stored. Data stored in the image data storage unit 315 is used for analysis processing described below.

  Next, an analysis apparatus 400 that performs processing for identifying specific equipment (electric poles and steel towers in the present embodiment) in an image using data stored in the image data storage unit 315 will be described. FIG. 6 shows a functional block diagram of the analysis apparatus 400. The analysis apparatus 400 includes (A) an image data storage unit 315, (B) an image conversion unit 411 that performs polar coordinate inverse conversion processing on the image data stored in the image data storage unit 315, and (C) an image. A second image data storage unit 413 that stores the processing result of the conversion unit 411; (D) a recognition rule data storage unit 419; and (E) an image learning unit that generates a recognition rule stored in the recognition rule data storage unit 419. 417 and (F) an image recognition unit 415 that performs image recognition processing on the image data stored in the second image data storage unit 413 using the recognition rule data stored in the recognition rule data storage unit 419. (G) a recognition result storage unit 421 that stores the processing result of the image recognition unit 415, and (H) equipment that performs processing using the data stored in the recognition result storage unit 421. Degree calculation unit 423, (I) equipment angle storage unit 425 for storing the processing result of equipment angle calculation unit 423, (J) equipment position database (DB) 429 for storing position data for each equipment, and (K) The equipment identification unit 427 that performs equipment identification processing using the equipment angle storage unit 425 and the data stored in the recognition result storage unit 421 and the equipment position DB 429, and (L) the processing result by the equipment identification unit 427 is stored. An identification result storage unit 431; and (M) an output unit 433 that outputs data stored in the identification result storage unit 431.

  Next, processing contents of the analysis apparatus 400 will be described with reference to FIGS. First, the image conversion unit 411 specifies an unprocessed image among the images stored in the image data storage unit 315 (FIG. 7: Step S11). Then, the image conversion unit 411 performs polar coordinate inverse conversion processing on the identified image, and the image data after the processing and the data associated with the image data (imaging position data and traveling direction data) are the second image. The data is stored in the data storage unit 413 (step S13).

  Step S13 will be described with reference to FIG. The center position (Cx, Cy) of the circular image portion is specified in advance. Furthermore, the radius r of the circular image portion is also specified.

  Furthermore, when the camera 200 is installed in the vehicle 100, the traveling direction is adjusted so that it can be easily understood such as 0 degrees and 90 degrees on the image so that the following calculation is simplified. In the present embodiment, 0 degree is the traveling direction. In FIG. 8, it is assumed that the horizontal right is −180 degrees and the angle is set counterclockwise.

Under these assumptions, the following calculation is performed.
(1) A rectangular image having a width of 2πr [pixel] and a height of r [pixel] is prepared as an image after the inverse polar coordinate transformation.
(2) The following calculation is repeated while changing the variable x corresponding to the coordinate of the horizontal axis in the image after the inverse polar coordinate transformation from −πr to πr in increments of 1.
(A) The angle variable angle = x * (360 / (2πr)) (hereinafter referred to as equation (1)) is calculated, and a line segment of length r is drawn from the center of the image in the direction of angle degree. In FIG. 8, a line segment having a length r such as arrows 1001 to 1003 is set.
(A) A pixel value is read at a distance of 1 [pixel] in the direction of the arrow along the line segment, and the read pixel value is drawn vertically from top to bottom at the position x from the left end in the image after the inverse polar coordinate transformation. .

  Then, for example, an image as shown in FIG. 9 is generated. In the example of FIG. 9, the left end is −180 degrees, the right end is 179 degrees, the center (the traveling direction in the present embodiment) is 0 degrees, and the height is r. Then, as shown in FIG. 9, the arrows 1001 to 1003 shown in FIG. 8 are mapped to the vertical arrows having the same reference numbers. Thus, the upper side of this rectangular image corresponds to the center of the image in FIG. In addition, by the processes (a) and (b) described above, the length (also referred to as distance) of the bottom of this rectangular image (also referred to as the upper side in this example) is determined from the shooting position (also referred to as shooting point). It is proportional to the expected angle. That is, if the distance is known, the angle can be understood. The relationship between the distance and the angle is as shown in the equation (1). If the distance is known, the angle can be understood. Further, since the traveling direction is 0 degree, it is represented by a straight line perpendicular to the upper side and the bottom side in FIG. 9, but any point on this straight line may be specified as a point representing the traveling direction. Note that such polar coordinate inverse transformation is well known and will not be described further.

  Although a relatively inexpensive fish-eye lens can be used to obtain an image as shown in FIG. 8, in the image as shown in FIG. 8, it is difficult to recognize the utility pole or tower because the direction of the utility pole or tower is not constant. It is. Therefore, if the image is converted into an image as shown in FIG. 9, the direction of the utility pole and the steel tower becomes constant, so that it can be recognized relatively easily.

  Next, the image recognizing unit 415 performs identification target equipment (recognition target) on the image after the polar coordinate inverse transformation stored in the second image data storage unit 413 in accordance with the recognition rule stored in the recognition rule data storage unit 419. Although it is an equipment, it is the same as the equipment to be identified and performs recognition processing of utility poles, steel towers, etc.), and image data including a mark indicating the equipment recognized as the processing result is stored in the second image data storage unit 413 It is stored in the recognition result storage unit 421 together with the photographing position data and the traveling direction data (step S15).

  This recognition process itself is a well-known technique, and a large number of utility poles and steel tower images are input to the image learning unit 417, and the image learning unit 417 learns and recognizes them using a well-known learning algorithm. A rule is generated and recognition rule data is stored in the recognition rule data storage unit 419. Thereafter, at a necessary timing, the image recognition unit 415 performs image recognition processing in accordance with the recognition rules stored in the recognition rule data storage unit 419.

  For example, in the image shown in FIG. 9, a utility pole is recognized as shown by a thick line frame 1101 in FIG. 10. A thick line frame 1101 is a mark.

  And the equipment angle calculation part 423 and the equipment identification part 427 implement an equipment identification process using the data stored in the recognition result storage part 421 and equipment position DB429 (step S17). The facility identification process will be described with reference to FIGS.

  First, the equipment angle calculation unit 423 specifies an unprocessed recognition result among the data stored in the recognition result storage unit 421 (FIG. 11: step S21). Then, the azimuth angle of the identification target equipment is calculated from the identified recognition result, and stored in the equipment angle storage unit 425 (step S22). First, the distance d from the straight line 1111 representing the traveling direction (FIG. 12) to the center line 1102 of the rectangle 1101 (FIG. 10) including the equipment recognized in step S15 is calculated. In the example of FIG. 12, since the left angle from the center is negative and the right angle is positive, when the center line 1102 is included on the left side from the straight line 1111, the distance d is a negative value. When the center line 1102 is included on the right side from 1111, the distance d is a positive value. In the example of FIG. 12, since the center line 1102 is on the left side of the straight line 1111, the distance d is a negative value.

  Then, the displacement angle “angle” is calculated from the distance “d” according to the equation (1) described above. For example, it is assumed that the displacement angle (−30 degrees) is calculated. Then, the azimuth angle of the facility to be identified is calculated based on the sum of the azimuth angle that is the traveling direction data stored in the recognition result storage unit 421 and the calculated displacement angle. As shown in FIG. 5, since the azimuth angle which is the traveling direction data is 278 degrees, the azimuth angle of the equipment is calculated as 248 degrees (= 278-30).

  Next, the facility identification unit 427 reads out the shooting position data stored in the recognition result storage unit 421, and is determined in advance from the shooting position among the facilities (electric poles, steel towers, etc.) registered in the facility position DB 429. The equipment name of the equipment with the radius R is extracted (step S23). An example is shown in FIG. A point 1203 is an imaging position, and equipment included in a radius R range centered on the point 1203 is extracted. In FIG. 13, black circles represent utility poles, and the utility poles shown in FIG. 13 are extracted. FIG. 14 shows an example of data stored in the equipment position DB 429. In the example of FIG. 14, an equipment name (such as column 235) and position data represented by the latitude and longitude of the equipment are stored. The processing in this step may be performed after converting the values of latitude and longitude into X coordinate values and Y coordinate values.

  And the equipment identification part 427 narrows down to the equipment which falls into the predetermined angle (alpha) centering on the direction 1202 specified by the azimuth calculated in step S22 among the equipment extracted in step S23 (step S25). In the example of FIG. 13, the electric pole 1211 is narrowed down. That is, the facility name of the utility pole 1211 is specified and stored in a storage device such as a main memory.

  Thereafter, the facility identification unit 427 determines whether the number of facilities remaining after narrowing down in step S25 is “0” (step S27). If the number of remaining facilities is “0”, it means that there is no corresponding facility. Therefore, the facility identification unit 427 uses the data indicating “not applicable” among the image data stored in the recognition result storage unit 421. The image data in the mark is stored in the identification result storage unit 431 (step S29). Then, the process returns to the original process.

  On the other hand, when the number of remaining facilities is not “0”, the facility identification unit 427 determines whether the number of remaining facilities is “1” (step S31). If the number of the remaining facilities is “1”, the facility identification unit 427 identifies the image data in the mark among the facility names of the remaining facilities and the image data stored in the recognition result storage unit 421. It stores in 431 (step S33). Then, the process returns to the original process.

  Furthermore, when the number of remaining facilities is not “1”, the facility identification unit 427 stores the facility name and the recognition result storage unit 421 of the facility closest to the photographing position among the remaining facilities narrowed down in step S25. The image data in the mark for the equipment among the image data being stored is stored in the identification result storage unit 431 (step S35). Then, the process returns to the original process.

  For example, data as shown in FIG. 15 is stored in the identification result storage unit 431. That is, the equipment name of the identified equipment (for example, column 236) and the image data of the equipment are stored in association with each other.

  The facility identification unit 427 determines whether all the recognition results stored in the recognition result storage unit 421 have been processed (step S37). If there is an unprocessed recognition result, the process returns to step S21. On the other hand, when all the recognition results have been processed, the process returns to the original process.

  Returning to the description of FIG. 7, the image conversion unit 411 determines whether all the images stored in the image data storage unit 315 have been processed (step S19). If an unprocessed image exists, the process returns to step S11. On the other hand, when all the images have been processed, the output unit 433 outputs the image data and the equipment name that are the processing results stored in the identification result storage unit 431 to an output device such as a display device or a printing device. (Step S20). For example, only requested data may be output in response to an instruction from the user.

  By carrying out the processing as described above, it becomes possible to identify an elongated facility such as a utility pole or a steel tower with an inexpensive camera.

[Embodiment 2]
The analysis apparatus 400 according to the first embodiment can be modified into a shape including, for example, the configuration of the dotted line in FIG.

  That is, the analysis apparatus 400 further includes the second image conversion unit 451 that performs polar coordinate conversion processing on the image data stored in the recognition result storage unit 421, and the processing results of the second image conversion unit 451. 3 image data storage unit 453. The processing content of the equipment angle calculation unit 423 is also different from that in the first embodiment.

  Only different parts will be described below. The second image conversion unit 451 performs polar coordinate conversion that is the reverse process of the image conversion unit 411. That is, the image data including the thick line frame 1101 and the center line 1102 which are marks that are the recognition results by the image recognition unit 415 are returned to the original image data. For example, the image data as shown in FIG. 10 is converted into the image data as shown in FIG. As shown in FIG. 16, the thick line frame 1101 is transformed into a mark 1101b distorted by polar coordinate transformation. Since the center line 1102 is a straight line perpendicular to the bottom and top sides, the center line 1102 is converted into a straight line 1102b passing through the center of the image as shown in FIG.

  Thereafter, the equipment angle calculation unit 423 calculates an angle β between the straight line 1501 and the straight line 1102b representing the traveling direction in the image as illustrated in FIG. In the case of an image as shown in FIG. 16, since the angle is set counterclockwise, a negative displacement angle is calculated in the case of an angle relative to a straight line above the traveling direction, and represents the traveling direction. In the case of an angle with respect to a straight line below the straight line, a positive displacement angle is calculated. In the example of FIG. 16, when it is calculated that β = −30 degrees, the azimuth angle 278 degrees to 248 degrees (= 278-30) in the traveling direction is calculated. The following processing is the same as that of the first embodiment.

  Thus, by providing the 2nd image conversion part 451 and returning to the original image data, there exists an effect that it becomes easy to identify the electric wire connected to the utility pole or the steel tower. In the image as shown in FIG. 10, the utility poles and the steel tower are easily recognized, but the wires are distorted and are difficult to recognize. On the other hand, after recognizing a utility pole and a steel tower, if it returns to the original image as shown in FIG. 16, it will identify the power pole and the steel tower using the point that the power pole and the steel tower are known. There is an effect that it becomes easy.

[Embodiment 3]
In the present embodiment, a camera 200 different from the first and second embodiments is used. The camera 200 in the present embodiment is a camera that captures images with a plurality of cameras instead of a fisheye lens, and is a camera that combines images as shown in FIG. In the case of such a camera, in the captured image, an image in which the distance on the upper side or the bottom side is substantially proportional to the angle viewed from the shooting point is obtained. That is, some errors are included in the angle calculation. In some cases, a camera that rotates 360 degrees and performs shooting may be employed. It is assumed that a straight line or a point indicating the traveling direction is specified in the image as shown in FIG.

  The image data storage processing unit 313 stores the data shown in FIG. 5 in association with the image as shown in FIG.

  And the analysis apparatus 500 in this Embodiment has a structure as shown in FIG. Note that elements having the same function as in FIG. 6 or holding similar data are given the same reference numerals. That is, the analysis apparatus 500 includes (A) an image data storage unit 315, (B) a recognition rule data storage unit 419, and (C) an image learning unit 417 that generates recognition rules stored in the recognition rule data storage unit 419. (D) an image recognition unit 415 that performs image recognition processing on image data stored in the image data storage unit 315 using the recognition rule data stored in the recognition rule data storage unit 419; E) a recognition result storage unit 421 that stores the processing result of the image recognition unit 415, (F) an equipment angle calculation unit 423 that performs processing using data stored in the recognition result storage unit 421, and (G) equipment Equipment angle storage section 425 for storing the processing result of the angle calculation section 423, (H) equipment position DB 429 for storing position data for each equipment, and (I) equipment angle storage section 4 5 and the equipment identification part 427 which performs equipment identification processing using the data stored in the recognition result storage part 421 and the equipment position DB 429, and (J) the identification result storage part which stores the processing result by the equipment identification part 427 431, and (K) an output unit 433 that outputs data stored in the identification result storage unit 431.

  In this way, the configuration is such that some components of the analysis apparatus 400 are removed.

  Next, processing of the analysis apparatus 400 will be described using FIG. First, the image recognition unit 415 specifies an unprocessed image among the images stored in the image data storage unit 315 (step S41). Then, the image recognizing unit 415 recognizes the image stored in the image data storage unit 315 in accordance with the recognition rule stored in the recognition rule data storage unit 419. The image data including the mark including the equipment recognized as the processing result, together with the shooting position data and the traveling direction data stored in the image data storage unit 315. The result is stored in the recognition result storage unit 421 (step S43). This step is the same process as step S15. Similar to the first embodiment, for example, in the image shown in FIG. 9, a utility pole is recognized as shown by a thick line frame 1101 in FIG. 10.

  Then, the equipment angle calculation unit 423 and the equipment identification unit 427 perform equipment identification processing using the data stored in the recognition result storage unit 421 and the equipment position DB 429 (step S45). This facility identification process is the same as the process described with reference to FIGS.

  Thereafter, the image recognition unit 415 determines whether all the images stored in the image data storage unit 315 have been processed (step S47). If an unprocessed image exists, the process returns to step S41. On the other hand, when all the images have been processed, the output unit 433 outputs the image data and the equipment name that are the processing results stored in the identification result storage unit 431 to an output device such as a display device or a printing device. (Step S49). For example, only requested data may be output in response to an instruction from the user.

  If the above processing is performed, if there is an image shot so that the distance on the upper side or the bottom side is proportional to the angle viewed from the shooting point, it is possible to appropriately identify a long and narrow facility such as a utility pole or a steel tower. become.

  Although the embodiment of the present technology has been described above, the present technology is not limited to this. For example, although an example in which shooting is performed while moving with the vehicle 100 has been shown, shooting may be performed while moving with a method other than the vehicle 100. Further, the functional block diagrams of the measurement apparatus and the analysis apparatus are examples, and may not necessarily match the actual program module configuration.

  Furthermore, as for the processing flow, as long as the processing result does not change, the order of the processing steps may be changed or executed in parallel.

  In addition, although the measurement device and the analysis device are examples of separate devices, all the functions described above may be performed by one device, or all the functions can be realized by more devices. You may make it do. Furthermore, as described above, related facilities such as electric wires may be identified together. Further, after a predetermined time has elapsed, image data may be acquired for the same equipment, and a process of comparing from a predetermined viewpoint may be performed.

  Note that the measurement device and the analysis device are computer devices, and as shown in FIG. 19, in the computer device, a memory 2501 (storage unit), a CPU 2503 (processing unit), a hard disk drive (HDD) 2505, and a display device 2509. A display control unit 2507 connected to the computer, a drive device 2513 for a removable disk 2511, an input device 2515, and a communication control unit 2517 for connecting to a network are connected by a bus 2519. Application programs including an operating system (OS) and a Web browser are stored in the HDD 2505, and are read from the HDD 2505 to the memory 2501 when executed by the CPU 2503. If necessary, the CPU 2503 controls the display control unit 2507, the communication control unit 2517, and the drive device 2513 to perform necessary operations. Further, data in the middle of processing is stored in the memory 2501 and stored in the HDD 2505 if necessary. Such a computer realizes various functions as described above by organically cooperating hardware such as the CPU 2503 and the memory 2501 described above with the OS and necessary application programs.

200 Camera 311 GPS Device 313 Image Data Storage Processing Unit 315 Image Data Storage Unit 411 Image Conversion Unit 413 Second Image Data Storage Unit 415 Image Recognition Unit 417 Image Learning Unit 419 Recognition Rule Data Storage Unit 421 Recognition Result Storage Unit 423 Equipment Angle Calculation Part 425 equipment angle storage part 427 equipment identification part 429 equipment position DB
431 Identification result storage unit 433 Output unit 451 Second image conversion unit 453 Third image data storage unit

Claims (6)

A first image photographed such that a reference line or a reference point perpendicular to the top side or the bottom side is specified and a distance on the top side or the bottom side is proportional to an angle viewed from the photographing point, and photographing position data of the photographing point; Image recognition processing is performed on the first image stored in the first image data storage unit that stores the reference line or the azimuth angle of the reference point, and an image of an identification target facility including a utility pole and a steel tower Extracting a portion;
The displacement angle of the image portion is calculated from the relationship between the extracted straight line passing through the image portion and the straight line passing through the reference line or the reference point and perpendicular to the upper side or the bottom side, and the displacement angle and the first image are calculated. An azimuth calculation step for calculating an azimuth angle of the image portion based on the azimuth angle of the reference line or the reference point stored in the data storage unit;
Of the identification target equipment included in the range specified by the shooting position data of the shooting point stored in the first image data storage unit and the calculated azimuth angle of the image portion, the closest to the shooting point. Extracting the identifier of the identification target facility from the facility data storage unit in which the identifier of the identification target facility and the position data are registered;
A program for causing a computer to execute. The azimuth calculation step includes
Calculating a displacement angle of the image portion from a distance from the reference line or a straight line passing through the reference point and perpendicular to the upper side or the bottom side to a straight line passing through the extracted image portion;
Calculating the azimuth angle of the image portion by the sum of the displacement angle and the azimuth angle;
The program according to claim 1, including: The step of generating the first image by inverse polar coordinate transformation with respect to a second image taken with a fisheye lens facing the zenith and stored in the second image data storage unit, and storing the first image in the first image data storage unit. The program according to claim 1 or 2, further causing the computer to execute the program. The azimuth calculation step includes
Generating a third image by polar coordinate transformation on the first image;
In the third image, an angle formed by a straight line passing through a portion corresponding to the image portion and a second straight line passing through the reference line or the reference point and corresponding to a straight line perpendicular to the top side or the bottom side is defined by the image portion. Calculating the displacement angle;
The program according to claim 1 or 3, comprising: A first image photographed such that a reference line or a reference point perpendicular to the top side or the bottom side is specified and a distance on the top side or the bottom side is proportional to an angle viewed from the photographing point, and photographing position data of the photographing point; Image recognition processing is performed on the first image stored in the first image data storage unit that stores the reference line or the azimuth angle of the reference point, and an image of an identification target facility including a utility pole and a steel tower Extracting a portion;
The displacement angle of the image portion is calculated from the relationship between the extracted straight line passing through the image portion and the straight line passing through the reference line or the reference point and perpendicular to the upper side or the bottom side, and the displacement angle and the first image are calculated. An azimuth calculation step for calculating an azimuth angle of the image portion based on the azimuth angle of the reference line or the reference point stored in the data storage unit;
Of the identification target equipment included in the range specified by the shooting position data of the shooting point stored in the first image data storage unit and the calculated azimuth angle of the image portion, the closest to the shooting point. Extracting the identifier of the identification target facility from the facility data storage unit in which the identifier of the identification target facility and the position data are registered;
A facility identification method executed by a computer. A first image photographed such that a reference line or a reference point perpendicular to the top side or the bottom side is specified and a distance on the top side or the bottom side is proportional to an angle viewed from the photographing point, and photographing position data of the photographing point; Image recognition processing is performed on the first image stored in the first image data storage unit that stores the reference line or the azimuth angle of the reference point, and an image of an identification target facility including a utility pole and a steel tower Means for extracting the part;
The displacement angle of the image portion is calculated from the relationship between the extracted straight line passing through the image portion and the straight line passing through the reference line or the reference point and perpendicular to the upper side or the bottom side, and the displacement angle and the first image are calculated. Means for calculating an azimuth angle of the image portion based on the azimuth angle of the reference line or the reference point stored in a data storage unit;
Of the identification target equipment included in the range specified by the shooting position data of the shooting point stored in the first image data storage unit and the calculated azimuth angle of the image portion, the closest to the shooting point. Means for extracting the identifier of the identification target facility from the facility data storage unit in which the identifier of the identification target facility and the position data are registered;
An equipment identification device having