Lighting confirmation system and lighting confirmation method

Abstract

This invention provides a lighting confirmation system and method that allow for easy confirmation of the lighting status of a light fixture. [Solution] The system includes an image and position acquisition means 10 that acquires an image taken of the direction of travel of a moving body by a shooting means mounted on the moving body, and the shooting position of the image; a lighting position registration means 20 that registers the position of lighting lights; a target lighting light extraction means 30 that extracts lighting lights that are located within a predetermined extraction range in the direction of travel from the shooting position as target lighting lights; and a determination means 40 that determines whether or not the light of a target lighting light is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light of the target lighting light is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting light.

Description

Technical Field

[0001] The present invention relates to an illumination lighting confirmation system and an illumination lighting confirmation method for confirming the lighting states of a plurality of lighting lamps arranged along a road.

Background Art

[0002] On roads such as highways, regular inspections are carried out to confirm the lighting of road lighting facilities so that vehicles can travel safely even at night. Conventionally, for example, maintenance personnel have performed night vehicle patrols and visually inspected. However, since the inspection work is at night, there is a problem that the burden on the maintenance personnel is large and there is also a risk of accidents due to vehicle patrols. Furthermore, since exhaust gas is emitted from vehicles, improvement has been desired also from the meaning of environmental conservation.

[0003] In recent years, it has been proposed to use a patrol car to perform lighting confirmation inspections. For example, Patent Document 1 describes a device that mounts a lighting detection unit on a vehicle and detects the lighting state based on the illumination light from a lighting lamp when the vehicle is located near the lighting lamp arranged along the road. In this lighting detection unit, two cameras are arranged at intervals so as to be parallel to each other and face the same direction, and the direction of the cameras is set to be inclined at a predetermined angle within a range of 15° to 25° with respect to the vertical direction to the left in a plane perpendicular to the traveling direction of the vehicle. In this lighting detection unit, since noise light such as building lighting and sign lighting is located farther from the camera than the lighting lamp, in the original images of the two cameras, the image of the lighting lamp has a larger horizontal displacement than the image of the noise light, and this is used to distinguish the lighting lamp from the noise light and detect the illumination light from the lighting lamp.

[0004] However, in the device of Patent Document 1, since it uses the fact that the amount of displacement generated horizontally in the images of the two cameras differs depending on the distance between the camera and the object, two cameras are required, and it is also necessary to finely adjust the installation angle, viewing angle, aperture, etc. of the camera, and there is a problem that the structure is complicated. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2001-85174 [Overview of the project] [Problems that the invention aims to solve]

[0006] This invention was made based on the above problems and aims to provide a lighting confirmation system and lighting confirmation method that can easily confirm the lighting status of a light fixture. [Means for solving the problem]

[0007] The present invention provides a lighting confirmation system for confirming the lighting status of multiple lighting fixtures arranged along a road, and includes: an image and position acquisition means for acquiring an image taken in the direction of travel of a moving body by a shooting means mounted on the moving body that moves along the road, and the shooting position of the image; a lighting fixture position registration means for registering the positions of multiple lighting fixtures; a target lighting fixture extraction means for extracting, as target lighting fixtures, lighting fixtures that are located within a predetermined extraction range in the direction of travel from the shooting position among the lighting fixtures registered by the lighting fixture position registration means; and a determination means for determining whether or not the light of a target lighting fixture is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light of the target lighting fixture is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting fixture.

[0008] The present invention provides a method for confirming the illumination status of multiple lighting fixtures arranged along a road, and includes a procedure for acquiring an image and position, which captures an image of the direction of travel of a moving body using a camera mounted on the moving body that moves along the road, and the position of the captured image; a procedure for registering the positions of multiple lighting fixtures; a procedure for extracting target lighting fixtures from among the lighting fixtures registered in the lighting fixture position registration procedure that are located within a predetermined extraction range in the direction of travel from the shooting position; and a determination procedure that determines whether or not the light of a target lighting fixture is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light of the target lighting fixture is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting fixture. [Effects of the Invention]

[0009] According to the present invention, lighting fixtures located within a predetermined extraction range in the direction of travel from the shooting position are extracted as target lighting fixtures. Furthermore, by utilizing the fact that the area in which the light of the target lighting fixture is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting fixture, it is possible to determine whether or not the light of the target lighting fixture is captured within the corresponding area of ​​the captured image. Thus, the lighting status of lighting fixtures can be confirmed easily and with high accuracy.

[0010] Furthermore, by dividing the captured image into a first region corresponding to a first range within the extraction range that is further than a predetermined reference distance from the shooting position, and a second region corresponding to a second range within the extraction range that is within the reference distance from the shooting position, it is possible to determine whether or not the light of the target lighting is captured in the image, thereby confirming the lighting status with higher accuracy.

[0011] Furthermore, by extracting candidate light sources from the binarized image of the captured image, and selecting those light sources larger than a predetermined standard size as the light source of the target lamp, the illumination status can be confirmed with even greater accuracy. [Brief explanation of the drawing]

[0012] [Figure 1]This figure shows the configuration of a lighting activation confirmation system according to one embodiment of the present invention. [Figure 2] This diagram shows an example of how the location of lighting fixtures, shooting locations, and extraction range are displayed on an electronic map. [Figure 3] This figure shows an example of a binarized image of a captured image. [Figure 4] This figure shows examples of the first and second ranges in the extraction range. [Figure 5] This figure shows an example of the first and second regions in a captured image. [Figure 6] This diagram shows the flow of a method for confirming that lighting is on according to one embodiment of the present invention. [Modes for carrying out the invention]

[0013] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0014] Figure 1 shows the configuration of a lighting confirmation system 10 according to one embodiment of the present invention. This lighting confirmation system 1 confirms the lighting status of multiple lighting fixtures arranged along a road. Specifically, for example, it confirms whether multiple lighting fixtures arranged at intervals along a road such as a highway are lit or not.

[0015] This lighting confirmation system 1 includes, for example, an image and position acquisition means 10 that acquires an image taken of the direction of travel of a moving body by a shooting means mounted on the moving body that moves along the road, and the shooting position; a lighting position registration means 20 that registers the positions of multiple lightings arranged along the road; a target lighting extraction means 30 that extracts a target lighting from the lightings registered in the lighting position registration means 20; a determination means 40 that determines whether or not the light of the target lighting is captured in the image; and a determination result recording means 50 that records the determination result.

[0016] The imaging image / position acquisition means 10, the lighting lamp position registration means 20, the target lighting lamp extraction means 30, the determination means 40, and the determination result recording means 50 can be configured by, for example, a computer, and are configured to function as the imaging image / position acquisition means 10, the lighting lamp position registration means 20, the target lighting lamp extraction means 30, the determination means 40, or the determination result recording means 50 by executing a program.

[0017] The imaging image / position acquisition means 10 acquires, for example, an imaging image captured by imaging means mounted on a moving body that moves along a road in association with the imaging position when the imaging image is captured. The imaging image and the imaging position can be acquired by receiving them via a network such as the Internet. Also, the imaging image and the imaging position may be stored in a storage means such as a memory, and the storage means may be connected to the imaging image / position acquisition means 10 and read to acquire them. The acquisition of the imaging image and the imaging position may be real-time processing for processing data at any time or batch processing for processing data at regular intervals.

[0018] Examples of the moving body on which the imaging means is mounted preferably include a patrol car that regularly patrols a road. Examples of the imaging means include a CCD camera, and the imaging means is installed, for example, to image the traveling direction of the moving body. The imaging position can be obtained, for example, by using GPS (Global Positioning System). For example, it is preferable to use a mobile terminal such as a smartphone equipped with a CCD camera and a GPS receiver as the imaging means because the imaging image and the imaging position can be easily obtained.

[0019] The imaging image may be a continuous moving image or a still image every predetermined time, for example, every 5 seconds, but it is preferable to use a still image every predetermined time. This is because the burden of transmitting and storing the imaging image data can be reduced, and coordinates for specifying the facility position can be input as property information. The imaging image is preferably captured at night.

[0020] The lighting fixture position registration means 20, for example, pre-registers the positions of the lighting fixtures. Examples of the positions of the lighting fixtures include the coordinates (latitude and longitude) where the lighting fixtures are installed. The position of the lighting fixture can be obtained, for example, by writing the position coordinates in a management drawing file and performing editing and calibration. Also, the lighting fixture position registration means 20 is preferably configured to be able to display the registered positions of the lighting fixtures on an electronic map. FIG. 2 shows an example in which the positions of the lighting fixtures are represented by black map pins on the electronic map. In FIG. 2, the portion shown in gray is a road.

[0021] The target lighting fixture extraction means 30 extracts, as target lighting fixtures, those of the lighting fixtures registered in the lighting fixture position registration means 20 that are located within a predetermined extraction range in the traveling direction from the shooting position. In FIG. 2, the position indicated by the white map pin is the shooting position, and the range surrounded by the broken line is the extraction range. The extraction range is, for example, a range from a position 20 m away from the shooting position to a position 120 m away from the shooting position in the traveling direction of the moving body. That is, it is preferable to extract, as target lighting fixtures, the lighting fixtures whose distance between the shooting position and the position of the lighting fixture is within a predetermined distance in the traveling direction of the shooting position. This is because the lighting state can be determined with high accuracy by extracting the lighting fixtures whose distance between the shooting position and the position of the lighting fixture is within a predetermined distance. The traveling direction of the moving body can be determined from the shooting position, that is, the moving direction of the shooting position coordinates.

[0022] The extraction range is preferably set, for example, in the range from a position 20 m away from the shooting position to a position 120 m away from the shooting position. That is, it is preferable to set the extraction range so that the maximum distance between the shooting position and the position of the lighting fixture is, for example, 20 m or more and 120 m or less. The target lighting fixtures can be extracted, for example, by searching for the positions, that is, the coordinates, of the lighting fixtures registered in the lighting fixture position registration means 20.

[0023] The determination means 40 determines whether or not the light from the target lighting is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light from the target lighting is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting. This means that when the distance between the shooting position and the position of the target lighting is far, the light from the target lighting is captured in the central area of ​​the captured image, and when the distance between the shooting position and the position of the target lighting is close, the light is captured in the upper and left and right areas of the captured image, and the determination means 40 determines whether or not the light from the target lighting is captured in the captured image.

[0024] The determination means 40 preferably includes, for example, a binarization processing means 41 that obtains a binarized image by binarizing the captured image according to a predetermined threshold, and a light candidate extraction means 42 that extracts light candidates for the target lighting from the binarized image obtained by the binarization processing means 41. The binarization processing means 41 is for simplifying the image to make it easier to analyze. The threshold is preferably adjusted according to the ambient brightness, for example, according to the season, sunrise time, sunset time, etc. An example of a binarized image is shown in Figure 3.

[0025] The light candidate extraction means 42 is preferably configured to extract, for example, portions that appear to be light from a target lighting fixture as light candidates from a binarized image using AI (Artificial Intelligence) image recognition. The light candidate extraction means 42 preferably includes, for example, a light candidate learning model 42A that has learned the characteristics of the light from a lighting fixture by machine learning, a detection means 42B that detects light candidates from a binarized image using the light candidate learning model 42A by image recognition, and a light candidate learning model generation means 42C that generates the light candidate learning model 42A.

[0026] Preferably, the light candidate extraction means 42 also includes a size determination means 42D that extracts light candidates larger than a predetermined standard size from the light candidates detected by the detection means 42B as the light of the target lighting lamp, and a target light recording means 42E that records the position and size of the extracted light of the target lighting lamp.

[0027] Furthermore, it is preferable that the determination means 40 includes, for example, a distance calculation means 43 that calculates the distance between the position of the target lighting lamp extracted by the target lighting lamp extraction means 30 and the shooting position, and a matching means 44 that, based on the calculation result of the distance calculation means 43, compares and determines whether or not there is light from the target lighting lamp recorded in the target light recording means 42E within the corresponding area of ​​the captured image.

[0028] Preferably, the matching means 44 is configured to determine whether or not the light from the target illuminator is captured in the captured image by dividing the captured image into, for example, a first region corresponding to a first region that is farther from the shooting position than a predetermined reference distance within the extraction range, and a second region corresponding to a second region that is within the extraction range up to a predetermined reference distance from the shooting position. In Figure 4, the area enclosed by the dashed line is the extraction range, the area enclosed by the dotted line is the first region, and the area enclosed by the single-dot dashed line is the second region. Also, in Figure 5, the area enclosed by the dotted line is the first region, and the area enclosed by the single-dot dashed line is the second region. The light from the target illuminator located in the first region that is farther from the shooting position within the extraction range is captured in the first region in the central part of the captured image, and the light from the target illuminator located in the second region that is closer to the shooting position within the extraction range is captured in the second region on the upper and left and right sides of the captured image. Therefore, by selecting and matching the first region or the second region according to the distance between the shooting position and the position of the target illuminator, a highly accurate determination can be made. In Figure 4, the gray areas represent roads, the black map pins indicate the locations of streetlights, and the white map pins indicate the shooting locations.

[0029] The matching means 44 is preferably configured such that, for example, when the target illuminator is located in the first range, it determines that the illuminator is turned on if there is light from the target illuminator in the first area, and not turned on if there is no light from the target illuminator. When the target illuminator is located in the second range, it is preferably configured to determine that the illuminator is turned on if there is light from the target illuminator in the second area, and not turned on if there is no light from the target illuminator. The reference distance separating the first range and the second range can be set as appropriate, and is preferably set within the range of 20m to 50m.

[0030] This lighting confirmation system 1 checks the lighting status of multiple streetlights arranged along a road, for example, as follows. Figure 6 shows the flow of the lighting confirmation method.

[0031] In this lighting confirmation method, first, the image and position acquisition means 10 acquires an image taken of the direction of travel of a moving body by a camera mounted on the moving body that is moving along the road, and the position in which the image was taken (Step S110; Image and position acquisition procedure). In addition, the lighting position registration means 20 registers the positions of multiple lighting fixtures arranged along the road (Step S120; Lighting position registration procedure).

[0032] Next, the target lighting lamp extraction means 30 extracts, as target lighting lamps, those registered in the lighting lamp position registration procedure (step S120) that are located within a predetermined extraction range in the direction of travel from the shooting position (step S130; target lighting lamp extraction procedure). That is, it is preferable to extract as target lighting lamps lighting lamps where the distance between the shooting position and the lighting lamp position is less than or equal to a predetermined distance in the direction of travel from the shooting position. The extraction range is as described above.

[0033] Next, the determination means 40 determines whether or not the light from the target lighting is captured in the corresponding area of ​​the captured image, by utilizing the fact that the area in which the light from the target lighting is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting (step S140; determination procedure).

[0034] In the determination procedure (step S140), for example, first, the captured image is binarized by the binarization processing means 41 according to a predetermined threshold to obtain a binarized image (step S141; binarization processing procedure). Next, the light candidate extraction means 42 extracts light candidates for the target lighting lamp from the binarized image (step S142; light candidate extraction procedure). For example, it is preferable to use AI-based image recognition, specifically using a light candidate learning model 42A that has learned the characteristics of the light of the lighting lamp by machine learning to detect light candidates for the target lighting lamp, and then use the size determination means 42D to extract from the light candidates those that are larger than a predetermined standard size as the light of the target lighting lamp.

[0035] In the determination procedure (step S140), for example, the distance calculation means 43 calculates the distance between the position of the target lighting fixture and the shooting position (step S143; distance calculation procedure). Next, for example, the matching means 44 compares the calculation results to determine whether or not there is light from the target lighting fixture within the corresponding area of ​​the captured image (step S144; matching procedure).

[0036] In this case, it is preferable to divide the captured image into a first region corresponding to a first region that is farther from the shooting position than a predetermined reference distance within the extraction range, and a second region corresponding to a second region that is within the extraction range up to a predetermined reference distance from the shooting position, and to determine whether or not there is light from the target illuminator by comparing the two regions. Specifically, for example, if the target illuminator is located in the first region, it is determined that the illuminator is lit if there is light from the target illuminator in the first region, and not lit if there is no light from the target illuminator in the second region. If the target illuminator is located in the second region, it is determined that the illuminator is lit if there is light from the target illuminator in the second region, and not lit if there is no light from the target illuminator in the second region. The determination result is recorded, for example, by the determination result recording means 50 (step S150; determination result recording procedure).

[0037] As described above, according to this embodiment, lighting fixtures located within a predetermined extraction range in the direction of travel from the shooting position are extracted as target lighting fixtures, and by utilizing the fact that the area in which the light of the target lighting fixture is captured in the captured image differs depending on the distance between the shooting position and the position of the target lighting fixture, it is possible to determine whether or not the light of the target lighting fixture is captured in the corresponding area of ​​the captured image. Thus, the lighting status of the lighting fixtures can be confirmed easily and with high accuracy.

[0038] Furthermore, by dividing the captured image into a first region corresponding to a first range within the extraction range that is further than a predetermined reference distance from the shooting position, and a second region corresponding to a second range within the extraction range that is within the reference distance from the shooting position, it is possible to determine whether or not the light of the target lighting is captured in the image, thereby confirming the lighting status with higher accuracy.

[0039] Furthermore, by extracting candidate light sources from the binarized image of the captured image, and selecting those light sources larger than a predetermined standard size as the light source of the target lamp, the illumination status can be confirmed with even greater accuracy.

[0040] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments and can be modified in various ways. For example, although each component was described in detail in the above embodiments, it is not necessary to have all components, and other components may also be included. [Explanation of Symbols]

[0041] 1... Lighting confirmation system, 10... Captured image / position acquisition means, 20... Lighting lamp position registration means, 30... Target lighting lamp extraction means, 40... Judgment means, 41... Binarization processing means, 42... Light candidate extraction means, 42A... Light candidate learning model, 42B... Detection means, 42C... Light candidate learning model generation means, 42D... Size determination means, 42E... Target light recording means, 43... Distance calculation means, 44... Matching means, 50... Judgment result recording means

Claims

1. A lighting confirmation system for checking the lighting status of multiple streetlights arranged along a road, A means for capturing images of the direction of travel of a moving body, which is mounted on a moving body that moves along the aforementioned road, and an image / position acquisition means for acquiring the position where the captured image was taken. A lighting position registration means for registering the positions of the aforementioned plurality of lighting lights, A target lighting lamp extraction means extracts, as target lighting lamps, lighting lamps registered in the lighting lamp position registration means that are located within a predetermined extraction range in the direction of travel from the shooting position, A determination means that determines whether or not the light of the target light is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light of the target light is captured in the captured image differs depending on the distance between the shooting position and the position of the target light, A lighting activation confirmation system characterized by having the following features.

2. The determination means divides the captured image into a first region corresponding to a first region within the extraction range that is further than a predetermined reference distance from the shooting position, and a second region within the extraction range that is within the second region that is between the shooting position and the reference distance, and determines whether or not the light from the target lighting fixture is captured in the image. The lighting confirmation system according to feature 1.

3. The determination means determines whether or not the light from the target lamp is captured within a corresponding area, based on the binarized image obtained by binarizing the captured image using a predetermined threshold. The lighting confirmation system according to feature 1.

4. The determination means extracts candidate light sources from the binarized image, and determines whether or not the light from the target lighting source is captured within the corresponding area, using the light sources larger than a predetermined standard size as the light from the target lighting source. The lighting confirmation system according to claim 3, characterized in that it is a lighting system.

5. A method for checking the lighting status of multiple streetlights arranged along a road, A photographic means mounted on a moving body that moves along the aforementioned road captures an image of the direction of travel of the moving body, and a procedure for acquiring the position of the captured image, A procedure for registering the positions of the aforementioned multiple lighting fixtures, A target lighting lamp extraction procedure is performed to extract, among the lighting lamps registered in the lighting lamp position registration procedure, those located within a predetermined extraction range in the direction of travel from the shooting position, as target lighting lamps. A determination procedure for determining whether or not the light of the target light is captured in a corresponding area of ​​the captured image, by utilizing the fact that the area in which the light of the target light is captured in the captured image differs depending on the distance between the shooting position and the position of the target light, A method for confirming that a light is turned on, characterized by including the following:

Images