JP7311963B2 - Information processing device, control method and program for information processing device - Google Patents

Description

The present invention relates to an information processing device, a control method for an information processing device, and a program.

In inspections of concrete wall surfaces of structures such as bridges, dams, and tunnels, an investigative engineer approaches the concrete wall surface and visually confirms deformations such as cracks. Since such inspection work called close-up visual inspection is costly, in recent years, inspection by a method of automatically detecting deformation from images of concrete wall surfaces has been proposed. Patent Literature 1 discloses a technique of detecting cracks from a concrete wall image using wavelet transform.

In addition, in order to check aging such as extension of cracks, it is necessary to conduct inspections every few years and compare them with past inspection results. Here, in order to capture an image in which thin cracks and other hard-to-see cracks can be confirmed, it is necessary to appropriately set shooting parameters such as focus and exposure. However, thin cracks and the like may or may not be detected by automatic detection due to subtle differences in shooting parameters. Therefore, it is necessary to finely adjust the photographing parameters, and it is difficult to adjust the photographing parameters.

On the other hand, Patent Document 2 discloses a method of adjusting shooting parameters. In Patent Document 2, first, a plurality of images are captured with a plurality of different shooting parameters, and the captured images are displayed on a display. The user selects the most preferable image among the plurality of images. As a result, shooting parameters for shooting the selected image are set.

JP 2014-228357 A Japanese Patent No. 4534816

However, since delicate photographing parameter adjustments are performed in structural inspections, if the method of Patent Document 2 is applied to structural inspections, a plurality of images with small changes between images will be displayed. It is difficult for the user to compare images with small changes and select the optimum image. Furthermore, since the images are taken outdoors, it is difficult to judge subtle differences in the images due to the effects of external light, the size of the available display, and the like. Therefore, there is a problem that it is difficult to capture an image suitable for comparison with past results.

The present invention has been made in view of the above problems, and aims to provide a technique for estimating an image capturing method suitable for comparison with past results without the user checking the captured image. aim.

An information processing apparatus according to the present invention that achieves the above object includes:
a storage means for storing past information of the target in the shooting range as past data;
detection means for detecting the target from the image of the imaging range captured by the imaging means with predetermined imaging parameters;
an estimation means for obtaining an evaluation value based on the detection result of the detection means and the past data, and estimating a shooting method suitable for shooting the target based on the evaluation value;
with
The estimation means acquires the evaluation value based on the degree of similarity between the past image of the imaging range and the current image of the imaging range, the detection result of the detection means, and the past data. do.

The present invention has been made in view of the above problems, and aims to provide a technique for estimating an image capturing method suitable for comparison with past results without the user checking the captured image. aim.

It is a figure which shows the structure of the information processing apparatus which concerns on one Embodiment. It is a figure explaining an inspection object structure, its drawing, and a photography range. 4 is a flowchart showing the procedure of processing performed by the information processing apparatus according to the first embodiment; FIG. 4 is a diagram for explaining a plurality of imaging parameters; FIG. It is a figure explaining the past data and the detection result of a target. It is a figure explaining the concept of an evaluation value. It is a figure explaining the example of the concrete calculation method of an evaluation value. It is a figure explaining evaluation value calculation using the crack which changed from the past inspection. FIG. 5 is a diagram for explaining selection of imaging parameters and estimation of an improvement method for imaging parameters; FIG. 4 is a diagram showing an example of display contents of an operation unit; FIG. 11 is a diagram illustrating a plurality of imaging ranges according to Embodiment 3; FIG. FIG. 12 is a diagram for explaining an example of appearance inspection according to the fifth embodiment;

Hereinafter, embodiments will be described with reference to the drawings. Note that the configurations shown in the following embodiments are merely examples, and the present invention is not limited to the illustrated configurations.

(Embodiment 1)
In the first embodiment, adjustment of photographing parameters in image inspection of an infrastructure structure will be described as an example. Infrastructure structures are, for example, bridges, dams, tunnels, etc. The concrete walls of these structures are photographed to create images for image inspection. The image targeted by the embodiment is not limited to this, and may be an image targeted for another structure or the surface of a material other than concrete. For example, an inspection image may be created by photographing an image of the asphalt surface, with the road being the inspection target.

In the first embodiment, it is assumed that the object to be inspected is deformation of a concrete wall surface. Deformation of a concrete wall surface includes, for example, cracks, efflorescence, junkers, cold joints, exposure of reinforcing bars, etc. In the first embodiment, an example in which cracks are particularly inspected will be described.

First, the outline of this embodiment will be described. As a premise, cracks in concrete walls will not recover naturally unless they are repaired. Therefore, the cracks recorded in the past inspection results should be observable even in the current concrete walls. In this embodiment, based on this premise, the imaging parameters are adjusted so that cracks in the past inspection results can be observed. By doing so, it is possible to set imaging parameters for appropriately imaging the concrete wall surface to be inspected. More specifically, crack detection processing is performed on each of the images photographed with a plurality of photographing parameters, and an evaluation value for each photographing parameter is calculated from each detection result and past inspection results. Then, based on the evaluation value, selection of imaging parameters and estimation of an improvement method are performed. A specific embodiment of this process will be described below.

<Configuration of information processing device>
FIG. 1 is a diagram showing a configuration example of an information processing apparatus 100 according to one embodiment of the present invention. The information processing apparatus 100 can be realized by executing software (programs) acquired via a network or various recording media by a computer configured by a CPU, memory, storage device, input/output device, bus, display device, and the like. . As for the computer, a general-purpose computer may be used, or hardware optimally designed for the software of the present invention may be used. Further, the information processing apparatus 100 may be integrated with the photographing unit 101 as shown in FIG. 1 and included in the housing of the camera. Alternatively, the information processing apparatus 100 may be configured as a housing (for example, a notebook PC or a tablet) different from the camera including the imaging unit 101 and receiving an image captured by the imaging unit 101 transmitted wirelessly or by wire. good.

The information processing apparatus 100 includes an imaging unit 101 , an imaging parameter setting unit 102 , a target detection unit 103 , an estimation unit 104 , an operation unit 105 and a past data storage unit 106 . The photographing unit 101 photographs an inspection object. The imaging parameter setting unit 102 sets imaging parameters when the imaging unit 101 performs imaging. A target detection unit 103 detects a crack or the like as an inspection target. An estimation unit 104 estimates a method for improving the imaging parameters. The operation unit 105 presents necessary information to the user and also receives operation input from the user. The past data storage unit 106 is a storage that stores past inspection results.

First, the past data storage unit 106 will be described in more detail. The past data storage unit 106 may be included in the information processing apparatus as shown in FIG. 1, or may be configured such that a remote server serves as the past data storage unit 106 . When the past data storage unit 106 is configured by a server, the information processing apparatus 100 can acquire past data stored in the past data storage unit 106 via a network.

FIG. 2 is a diagram for explaining data stored in the past data storage unit 106. As shown in FIG. FIG. 2 shows how past data of a bridge 200, which is an object to be inspected, is stored. Past inspection results are recorded in the past data storage unit 106 in association with the drawing of the bridge 200 . For example, for a bridge pier 201 with a bridge 200, the drawing 202 records the positions and shapes of cracks 210 and the like as past inspection results. In the first embodiment, it is assumed that this inspection result is a result of capturing an image of the bridge pier 201 during past inspection work and detecting it by automatic detection processing of the target detection unit 103, which will be described later.

The past inspection results are not limited to this embodiment. For example, the results obtained by the automatic detection process may be corrected by a human, or recorded by a human by a close visual inspection without going through the automatic detection process. It may be the result of The information processing apparatus 100 can call the inspection results of any part of the inspection target structure from the past inspection results recorded in the past data recording unit 106 . Hereinafter, the past inspection results (in the first embodiment, the position and shape of the crack in the image) will be referred to as past data.

FIG. 2 further shows the relationship between the range photographed by the photographing unit 101 and the past data to be recalled. In image inspection, it is necessary to take high-definition photographs of concrete walls in order to confirm cracks with a width of 1 mm or less. Therefore, in many cases, it is not possible to capture the entire wall surface of a bridge pier in one shot, so multiple shots are taken while shifting the shooting position, and the images are combined to create a high-definition image of the entire wall surface.

FIG. 2 shows a photographing range 220 as an example of a range that can be photographed in one photographing in the bridge pier drawing 202 . In this way, partial photographing of the pier wall surface is repeated to photograph the entire pier 201 . In this embodiment, the shooting parameters are adjusted using the past data included in a certain shooting range (for example, the shooting range 220 in FIG. 2). In photographing the bridge pier 201, the entire bridge pier 201 may be photographed using the photographing parameters adjusted using the photographing range 220 in FIG.

Next, past data called from the past data storage unit 106 will be described. In the first embodiment, it is assumed that the past data of the photographing range is called as an image. FIG. 2 shows past data 230 to be called up when photographing the photographing range 220 . The past data 230 is an image including the crack 211 and having the same size as the image captured by the imaging unit 101 . More specifically, it is an image in which 1's are recorded in pixels where cracks exist and 0's are recorded in other pixels. It is assumed that the past data storage unit 106 generates such an image of past data when an arbitrary shooting range is specified. In the description of the first embodiment, the image data in which the cracks of the past inspection results are drawn in the image corresponding to the imaging range is called past data.

<Processing>
Next, the procedure of processing performed by the information processing apparatus 100 according to the present embodiment will be described with reference to the flowchart of FIG.

[Step S301]
First, in step S301, the information processing apparatus 100 determines the imaging range of the structure to be inspected. The method of determining the imaging range is implemented, for example, as follows. First, the first method is a method in which the user designates the range to be photographed from the drawing. For example, when inspecting the bridge pier 201 in FIG. 2, a drawing 202 is displayed on the display unit of the operation unit 105, and the user designates an imaging range 220 of the drawing. Here, it is assumed that the user selects an area including cracks in the past inspection result as the photographing range. If the past inspection results of the imaging range specified by the user do not include cracks, the information processing apparatus 100 notifies the user of a warning and prompts the user to reset the imaging range.

After specifying the imaging range, the user adjusts the position/orientation of the imaging unit 101 with respect to the actual bridge pier 201 so that the specified imaging range can be captured. Here, in order to assist the user's operation of selecting the imaging range, the drawing displayed for determining the imaging range may display the positions of the cracks in the past inspection results. Information such as an ID may be added to the cracks recorded in the past data storage unit 106 so that the user can easily search for and select an area containing any cracks.

For example, when the user inputs the ID of a crack to be included in the imaging range to the operation unit 105 , the crack with the corresponding ID is selected from the past data storage unit 106 . Then, the area including the crack is automatically set as the imaging range. In this example, an ID is used to search for cracks, but the crack search method is not limited to this, and information such as crack coordinates may be used to search for cracks. By doing so, the user can easily set an imaging range including a specific crack.

A second method of determining the imaging range is an embodiment in which the information processing apparatus 100 recommends the imaging range to the user. Since the imaging parameters are adjusted using the past inspection results, the imaging range must include the past inspection results. Therefore, the information processing apparatus 100 selects an imaging range that includes the past inspection results of the structure to be inspected, and recommends it to the user as the imaging range. The recommendation of the imaging range may be displayed by displaying the imaging range 220 in the drawing as shown in FIG. The user confirms the recommended imaging range and adjusts the position/orientation of the imaging unit 101 with respect to the actual bridge pier 201 so that the recommended imaging range can be captured. The shooting range recommended by the information processing apparatus 100 may be not only one shooting range, but also a plurality of shooting ranges may be presented to the user so that the user can select the shooting range to actually shoot.

Also, the photographing range to be preferentially recommended may be determined according to the cracks in the past inspection results. For example, past inspection results may preferentially recommend an area including a large and important crack or a crack occurring at a structurally important position as the imaging range. On the other hand, cracks that have been repaired after the past inspection cannot be observed, so it is not preferable to set the range including the repaired cracks as the shooting range. Therefore, when information on the execution of repair is recorded along with past inspection results, that portion is not selected as the photographing range.

Further, in the above embodiment, the user adjusts the position/orientation of the imaging unit 101 with respect to the actual structure. may be supported. For example, when adjusting the position/orientation of the imaging unit 101 toward the imaging range selected by the user or the imaging range recommended by the information processing apparatus 100, the target imaging range is determined based on the position/orientation of the imaging unit 101 measured by the sensor. To inform the user of the adjustment method to the position/posture that can be photographed.

As a sensor for measuring the position/orientation of the imaging unit 101, there are various methods such as an acceleration sensor, a gyro sensor, and GPS, and any method may be used. Alternatively, the position/orientation of the imaging unit 101 may be determined by determining which part of the target structure is being imaged from the image captured by the imaging unit 101 instead of the sensor. Existing methods may be used for obtaining the position/orientation of the imaging unit 101, so detailed description thereof will be omitted.

Furthermore, when a configuration for measuring the position/orientation of the imaging unit 101 is provided, the imaging range may be determined from the position/orientation of the imaging unit 101 . In this case, first, the user directs the photographing unit 101 toward the actual structure to be inspected. Then, the position/orientation of the photographing unit 101 is measured, and the photographed portion of the structure to be inspected is taken as the photographing range.

Furthermore, in the above embodiment, the configuration in which the user operates the imaging unit 101 to determine the position/orientation of the imaging unit 101 has been described. However, the information processing apparatus 100 including the photographing unit 101 may be installed in an automatic pan head, and the pan head may be automatically operated so as to assume a posture for photographing a predetermined photographing range. Further, for example, the information processing apparatus 100 may be installed on a moving object such as a drone, and controlled to assume a position/orientation for photographing a predetermined photographing range.

By the above step S301, the photographing range of the structure to be inspected is determined, and the photographing unit 101 assumes a position/posture for photographing the photographing range.

[Step S302]
In step S<b>302 in FIG. 3 , the information processing apparatus 100 calls the past data corresponding to the shooting range from the past data storage unit 106 . This past data is image data in which cracks included in the photographing range are drawn, as described with reference to FIG.

[Step S303]
In the next step S303, the information processing apparatus 100 determines initial values of imaging parameters (hereinafter referred to as initial imaging parameters). For setting the initial imaging parameters, for example, imaging parameters obtained when the same location was photographed in the past may be recorded in the past data storage unit 106, and the imaging parameters may be called and set as initial imaging parameters. Alternatively, shooting parameters determined by a normal shooting parameter adjusting method (automatic parameter adjustment) of the shooting apparatus may be set as initial parameters.

[Step S304]
In the next step S304, the information processing apparatus 100 sets a plurality of shooting parameters using the shooting parameter setting unit 102 based on the initial shooting parameters. FIG. 4 shows how a plurality of shooting parameters are set based on the initial shooting parameters. First, FIG. 4A is a diagram illustrating an embodiment in which exposure (EV) is adjusted as an example of shooting parameters to be adjusted. In FIG. 4A, a white triangle 401 indicates that EV0 is set as the initial parameter. The imaging parameter setting unit 102 sets a plurality of imaging parameters centering on these initial parameters.

In FIG. 4A, the exposure is changed by one step around EV0, and EV-1 (black triangle 402 in FIG. 4) and EV+1 (black triangle 403 in FIG. 4) are set as multiple parameters. In this example, three shooting parameters are set together with the initial shooting parameters, but the number of shooting parameters to be set is not limited to this. For example, a total of five shooting parameters may be set by setting exposures that differ by two levels. Also, in this example, a plurality of shooting parameters are set according to the rule of changing the exposure by one step, but the steps of changing the shooting parameters may be set by other setting methods. For example, the exposure may be set in 1/2 step increments, or may be set randomly around the initial photographing parameters.

Although the embodiment has been described above in which exposure (EV) is used as the shooting parameter, the shooting parameter to be set is not limited to exposure. Any shooting parameters may be used as long as they are parameters for controlling the shooting unit 101. For example, focus, white balance (color temperature), shutter speed, aperture, ISO sensitivity, image saturation and hue, and the like may be used. may be used as an imaging parameter.

Also, in FIG. 4A, an embodiment has been described in which only the exposure is the shooting parameter to be adjusted, but a plurality of shooting parameters may be adjusted at the same time. For example, FIG. 4B is a diagram illustrating an embodiment in which a combination of exposure and focus is used as a shooting parameter to be adjusted. In FIG. 4B, a certain combination of exposure and focus parameters is set as an initial parameter, indicated by a white circle 411 . Centering on these initial parameters, a combination of shooting parameters such as a black circle 412 is set as a plurality of shooting parameters.

Note that the combination of shooting parameters to be adjusted is not limited to the combination of exposure and focus shown in FIG. 4B, and other combinations of shooting parameters may be used. Also, in the above description, an embodiment in which a combination of two parameters is adjusted has been described, but the number of combinations of imaging parameters is not limited to this, and combinations of three or more imaging parameters may be adjusted simultaneously. .

As described above, the imaging parameter setting unit 102 sets a plurality of imaging parameters. In the following, an embodiment in which exposure is used as the shooting parameter to be adjusted as shown in FIG. 4A will be described.

[Step S305]
Subsequently, in the next step S305, the information processing apparatus 100 uses the photographing unit 101 to photograph the photographing range of the object to be inspected using the plurality of photographing parameters set in step S304. Specifically, when three exposures are set as shown in FIG. 4A, three images are shot while changing the exposure.

[Step S306]
In the next step S306, the information processing apparatus 100 uses the target detection unit 103 to perform target detection processing on the plurality of images captured in step S305. In this embodiment, the target is a crack, so crack detection processing is performed on each image. As a crack detection method from an image, for example, a method such as that disclosed in Patent Document 1 may be used. The crack detection method is not limited to the method of Patent Document 1. For example, the image features of cracks are learned from an image in which the positions and shapes of cracks are known in advance, and the positions of cracks in the input image are determined based on the learning results. , a method of detecting the shape may be used. The crack detected in step S306 is hereinafter referred to as a detection result.

Processing after step S307 in FIG. 3 is processing mainly executed by the estimation unit 104, and is processing for selecting the optimum imaging parameter or processing for further searching for the optimum imaging parameter.

[Step S307]
First, in step S307, the information processing apparatus 100 uses the estimation unit 104 to calculate an evaluation value for each of a plurality of shooting parameters. The evaluation value indicates a value that is as high as the photographing parameters are appropriate for photographing an inspection image. This evaluation value is calculated by comparing crack detection results for each image captured with a plurality of shooting parameters and cracks in past data.

For explanation of step S307, first, FIG. 5 shows examples of past data and detection results. FIG. 5A shows past data of the photographing range, including cracks 501 that are past inspection results. FIG. 5B shows the result of crack detection performed on an image shot with certain shooting parameters, and a crack 502 is detected. FIG. 5C shows the past data of FIG. 5A superimposed on the detection results of FIG. represent. Ideally, the crack 511 of the past data and the crack 512 of the detection result are completely overlapped, but for the convenience of the drawing, they are shown shifted.

Next, the concept of evaluation values will be described with reference to FIG. FIGS. 6A to 6C are diagrams in which cracks 601, 602, and 603, which are detection results of different captured images, are superimposed on a crack 511 of the same past data.

First, FIG. 6A shows a case where the crack 511 in the past data matches the crack 601 in the detection result. In this case, it shows that the past inspection results can be captured with images that can be fully automatically detected. Therefore, this imaging parameter is appropriate, and the evaluation value s _A in the case of FIG. 6A is a high value.

Next, FIG. 6B shows a case where the crack 602 in the detection result is longer than the crack 511 in the past data. Since cracks extend over time, it is possible that the current cracks are longer than the past inspection results. Therefore, in the case of FIG. 6B as well, since an image in which past cracks can be confirmed can be photographed, it is considered that the photographing parameters for photographing an inspection image are suitable. The evaluation value _sB of is also a high value. Rather, assuming that cracks will almost certainly extend over time, cracks that have extended as shown in FIG. It can be considered appropriate to be able to do so. Therefore, although both the evaluation values s _A and s _B are high evaluation values, s _B may be given a higher evaluation value.

Thus, the evaluation value is a high value when the crack as the detection result matches the crack in the past data, or when the crack as the detection result extends over a larger area including the crack in the past data. to indicate

On the other hand, FIG. 6C shows a case where a crack 603 as a detection result is only partially obtained for a crack 511 in the past data. Cracks that have been recorded in the past will not disappear unless they are repaired. Therefore, since the imaging parameters for capturing an image in which the entire crack 511 in the past data cannot be detected are not suitable as the imaging parameters for the inspection image, the evaluation value s _C in the case of FIG. 6C is a low value. In the case of FIG. 6C, it is necessary to further adjust the imaging parameters in order to obtain imaging parameters with a high evaluation value and suitable for inspection image imaging. To summarize the above, the evaluation values in each case in FIG.

This is the relationship.

Next, a specific method for calculating the evaluation value s will be described with reference to FIG. In FIG. 7, which is an enlarged view of FIG. 6(C), cracks in the past data are indicated by a dashed line 511, and detection results 721 to 723 are indicated by solid lines. In the calculation method of the evaluation value s here, each pixel on the crack 511 of the past data is associated with the detection results 721 to 723, and the evaluation value s is calculated based on the number of corresponding pixels. Correlation between cracks in past data and cracks in detection results is performed, for example, as follows.

First, a pixel 701 in FIG. 7 is a certain pixel on the crack 511 of the past data. A predetermined peripheral range 702 of this pixel 701 is searched, and if there is a crack in the detection result, the pixel 701 is determined to be a pixel associated with the detection result. Note that the predetermined peripheral range 702 is defined as, for example, a 5-pixel range centered on the pixel 701 . In the example of FIG. 7, since cracks in the detection result are not included in the periphery 702 of the pixel 701, the pixel 701 is a pixel that could not be associated with the detection result. On the other hand, since a pixel 711 on crack 511 of another past data has a crack 721 of the detection result in the peripheral range 712 thereof, the pixel 711 is a pixel that can be associated with the detection result. Such determination is repeated for pixels on one crack in the past data, and an evaluation value s based on one crack is calculated. At this time, the evaluation value s is represented by the following formula.

Here, C indicates a crack in certain past data, and p(C) indicates the number of pixels of the crack C. i indicates a pixel on the crack C, f _i is 1 when the pixel i can be associated with the detection result, and 0 when it cannot be associated.

Note that the formula (2) shows a method of calculating the evaluation value s based on a crack in one piece of past data. An evaluation value may be calculated by the formula (2), and the sum or average thereof may be used as the final evaluation value.

Also, when the evaluation values s _A and s _B in FIGS. 6A and 6B are calculated by the method of formula (2),

As a result, the maximum evaluation value is output for each. Here, considering aging deterioration from past cracks, as shown in FIG. 6(A), the extension part can also be detected as shown in FIG. If it is better to have s _B >s _A , a method of calculating an evaluation value is required. For this purpose, for example, the above evaluation value may be calculated after extending a predetermined number of pixels in the direction in which the crack end point of the past data is expected to be extended.

If the aging of cracks can be regarded as the extension of cracks only, the evaluation value can be calculated as described above, but the appearance of cracks may change significantly due to aging. For example, when the lime component of concrete precipitates from cracks, the lime component may harden on the concrete surface so as to cover the cracks. When such precipitation of lime components (hereinafter referred to as efflorescence) occurs, cracks cannot be completely confirmed from the appearance, and only the efflorescence region is confirmed. Thus, it is impossible to detect cracks similar to past data from images of cracks that have changed significantly from past inspection results. Therefore, as described above, the method of associating past data with cracks cannot correctly calculate an evaluation value for selecting an imaging parameter.

Therefore, in order to deal with such a problem, the target detection unit 103 may detect not only cracks but also efflorescence, and limit the evaluation value calculation region based on the cracks in the past data. FIG. 8 is a diagram for explaining this processing. First, FIG. 8A shows past data. FIG. 8(B) shows the current actual state of the same concrete wall surface as the past data, showing a state in which efflorescence 802 is generated from cracks 801 due to aged deterioration. This efflorescence 802 occurs so as to cover up part of the cracks that were observable in the past data. FIG. 8C shows the detection result of crack detection performed by the target detection unit 103 on the image of the concrete wall surface of FIG. 8B photographed with certain photographing parameters. In the concrete wall surface of FIG. 8(B), the crack in the area where the efflorescence 802 appears is not visible, so in the detection result of FIG. 8(C), only part of the crack in the past data is detected. is in a state of

FIG. 8D is a diagram in which past data cracks 811 and 812 indicated by dashed lines and a detection result crack 803 indicated by a solid line are superimposed. FIG. 8D further shows an efflorescence region 802 detected by the target detection unit 103 . Among the broken lines indicating cracks in the past data, a broken line 811 is a portion overlapping the efflorescence region 802, and a broken line 812 is a portion not overlapping the efflorescence region. In such a situation, the evaluation value is calculated based on the crack 812, which is a portion of the cracks in the past data that does not overlap with the efflorescence, and the crack 803 in the detection result. That is, the evaluation value is calculated by excluding a region where a predetermined aging change (efflorescence) is detected.

The evaluation value can be calculated by the above-described inter-pixel correspondence method using the crack 812 of the past data and the crack 803 of the detection result. By doing so, it is possible to calculate the evaluation value of the photographing parameter using the crack whose appearance has changed due to efflorescence occurring in the past inspection.

In this embodiment, efflorescence is the factor that changes the appearance of cracks, but other factors that change the appearance of cracks are also conceivable. For example, as the deterioration of cracks progresses, peeling and spalling of crack surfaces occur. When this happens, the appearance of the cracks in the past inspection may change greatly. Therefore, as in the case of efflorescence, it is possible to detect a region where a predetermined aging such as peeling or peeling has occurred, and exclude the region from the evaluation value calculation region based on cracks in past data. .

Also, the appearance of cracks from previous inspections may be completely changed. For example, aging can cause the entire crack to become covered with efflorescence. In an imaging area including cracks whose appearance has completely changed, comparison with past cracks cannot be made, and therefore imaging parameter adjustment cannot be performed. Therefore, if it is determined that the appearance of cracks has changed completely, such as when efflorescence that erases cracks in past data is detected, shooting parameter adjustment in the current shooting range may be canceled. good. In this case, the information processing apparatus 100 recommends that the area of the concrete wall surface containing other past data is set as the imaging range.

In step S307, an evaluation value is calculated for each of the plurality of shooting parameters as described above.

[Steps S308 to S311]
Next, in step S308, the information processing apparatus 100 evaluates the shooting parameters based on the evaluation values calculated in step S307. In step S309, the information processing apparatus 100 determines whether or not to readjust the imaging parameters based on the evaluation result. When readjusting, the process proceeds to step S310. On the other hand, when not readjusting, the process proceeds to step S311. In step S310, the information processing apparatus 100 estimates a method for improving the imaging parameters. After that, the process returns to step S305. In step S311, the information processing apparatus 100 sets shooting parameters. Then, the series of processing for photographing parameter adjustment ends. The details of these processes will be described below.

First, in the imaging parameter evaluation in step S308, the maximum evaluation value is selected from a plurality of imaging parameter evaluation values and compared with a predetermined threshold value. FIG. 9A is a diagram for explaining evaluation of each imaging parameter. In this embodiment, three exposures (EV) are set as a plurality of shooting parameters. In FIG. 9A, as in FIG. 4A, triangles 401, 402, and 403 indicate how exposures of -1, 0, and +1 are set as a plurality of shooting parameters. In the lower portion of FIG. 9A, evaluation values s ₋₁ , s ₀ , and s ₊₁ obtained from detection results of images shot with each shooting parameter are shown. In FIG. 9A, the evaluation value s ₊₁ of the exposure 403 of +1 is the highest evaluation value and indicates a value exceeding the predetermined threshold s _th . If there is a photographing parameter showing an evaluation value exceeding a predetermined threshold value _sth , it is determined that the photographing parameter is suitable as a photographing parameter for an inspection image.

In the case of FIG. 9A, +1 exposure 403 is selected as the optimum parameter, and in step S309 it is determined that readjustment of the shooting parameters is unnecessary, and the process advances to step S311 for setting shooting parameters. In step S311, an exposure of +1 is set for the photographing unit 101 via the photographing parameter setting unit 102, and the process ends.

On the other hand, FIG. 9B shows an example of calculating an evaluation value by setting exposures of -1, 0, and +1 as a plurality of shooting parameters as in FIG. 9A. indicates a situation in which different evaluation values are obtained. In FIG. 9B, the maximum evaluation value is the evaluation value s ₊₁ , but even s ₊₁ does not exceed the predetermined threshold value s _th . Images captured with these imaging parameters do not provide detection results that sufficiently match the cracks in the past data, and these imaging parameters are not suitable as imaging parameters for inspection images. In this case, in step S309, it is determined that the imaging parameters need to be readjusted, and in step S310, a method for improving the imaging parameters is estimated.

Next, estimation of a method for improving imaging parameters will be described with reference to FIG. 9B. In FIG. 9B, the evaluation value s ₊₁ of +1 exposure is less than the threshold value s _th , but shows the maximum evaluation value among the evaluation values s ₋₁ to s ₊₁ . Therefore, in the readjustment of the shooting parameters, a plurality of shooting parameters are set from shooting parameters around this shooting parameter (exposure of +1). For example, when three shooting parameters are set in the next shooting parameter adjustment as well, as shown in FIG. 9B, exposures 921, 922, and 923 around +1 exposure 403 are set as multiple parameters. Then, the process returns to step S305, these shooting parameters are set in the shooting unit 101 via the shooting parameter setting unit 102, and multiple images are shot again. Then, the processing (target detection processing, evaluation value calculation processing) after step S306 in FIG. 3 is executed again to search for the optimum shooting parameter. If an evaluation value equal to or _greater than the threshold value sth is not obtained even after evaluating this imaging parameter set, a plurality of new imaging parameters are again determined around the imaging parameters showing the maximum evaluation value, and imaging processing is performed again. Execute. This loop is repeatedly executed until an imaging parameter that gives an evaluation value exceeding the threshold _sth is determined.

Note that the maximum number of repetitions may be determined in advance, and the process may be aborted if the optimum imaging parameters (imaging parameters with which an evaluation value equal to or greater than the threshold value _sth is obtained) are not obtained by then. When the shooting parameter adjustment processing is aborted, a warning is displayed on the display unit of the operation unit 105 to notify the user that the shooting parameters have not been sufficiently adjusted. Further, the shooting parameters for shooting the image for which the maximum evaluation value obtained before the processing is terminated may be set in the shooting unit 101 via the shooting parameter setting unit 102 .

In the above description, an embodiment has been described in which, when an evaluation value equal to or greater than the threshold value s _th is not obtained in step S308, estimation of improved imaging parameters and repeated adjustment are performed. However, even if a shooting parameter indicating an evaluation value equal to or higher than the threshold value _sth is found, a search may be made for a shooting parameter indicating a higher evaluation value. In this case, after setting the shooting parameters around the shooting parameters showing the maximum evaluation value as improved shooting parameters, a plurality of images are shot again, and the crack detection processing and evaluation value calculation processing are repeatedly executed. The end condition of this repetition processing is when a predetermined number of repetitions is reached, or when the evaluation value does not change even if the imaging parameters are changed near the maximum evaluation value.

In the process of looping and adjusting the imaging parameters as described above, the imaging and evaluation of a plurality of images and the next parameter estimation may be repeated automatically. In this case, the user may fix the imaging unit 101 to a tripod or the like and wait until the adjustment of the imaging parameters is completed.

On the other hand, the user may check the shooting parameters and detection results and determine whether to end the repeated processing for adjusting the shooting parameters. In this case, in step S309 of FIG. 3, the user determines whether or not to readjust the imaging parameters without performing optimum imaging parameter determination using the evaluation value threshold _sth . For this purpose, the operation unit 105 presents necessary information to the user and accepts input from the user. Here, FIG. 10 is a diagram illustrating a display unit 1000 as an example of the operation unit 105 when adjusting shooting parameters based on user determination. Information presented to the user and user operations will be described below with reference to FIG. 10 .

First, a display unit 1000 in FIG. 10 is a display for displaying information. For example, when the information processing apparatus 100 is a photographing apparatus including the photographing unit 101, it is a touch panel display provided on the back surface of the photographing apparatus. An image 1001 displayed on the display unit 1000 is an image obtained by superimposing a crack in the past data indicated by a dotted line and a crack in the detection result indicated by a solid line on an image captured with a shooting parameter of +1 exposure. . In this example, each crack is displayed with a dotted line and a solid line, but past data and cracks in detection results may be displayed in different colors.

An image 1002 that is hidden in the image 1001 is an image obtained by superimposing cracks in the past data and cracks in the detection results on an image captured with a shooting parameter of 0 exposure. By switching and displaying these images, the user can confirm the change in the detection result of the crack accompanying the change in the imaging parameter. In addition, the user may arbitrarily display or hide the superimposed cracks. By hiding the crack, it becomes possible to check the portion of the captured image that is hidden by the display of the crack.

Also, in the lower part of the image 1001, a plurality of shooting parameters set for adjustment of the shooting parameters are shown. In FIG. 10, three levels of exposure (EV) are indicated by black triangles as examples of a plurality of shooting parameters. Among them, the black triangle 1011 indicating the exposure +1 indicating the maximum evaluation value is highlighted (displayed large). Also, white triangles 1012 and the like indicate a plurality of shooting parameter candidates for further adjustment of the shooting parameters set based on the shooting parameters 1011 of exposure +1.

In this embodiment, the user confirms these pieces of information displayed on the display unit 1000 as the operation unit 105 and determines whether to adopt the current imaging parameters or to further execute imaging parameter adjustment processing. do. Specifically, the user compares the cracks in the past data with the cracks in the detection results in the image 1001 that gave the maximum evaluation value, and indicates the maximum evaluation value if the degree of matching is satisfactory. It can be determined to adopt the imaging parameters. The user presses an icon 1021 displaying "set" when adopting the shooting parameter showing the maximum evaluation value. By this operation, the imaging parameter indicating the maximum evaluation value is set in the imaging unit 101 (step S311 in FIG. 3), and the imaging parameter adjustment processing ends.

On the other hand, if it is determined by checking the image 1001 that the current optimal imaging parameters are unsatisfactory, the user presses an icon 1022 displaying "readjustment". In response to this instruction, the processing (target detection processing, evaluation value calculation processing) after step S306 in FIG. 3 is executed again using the next plurality of shooting parameters (for example, exposure indicated by an outline triangle 1012). After that, various kinds of information are again presented to the user as in the example of FIG. Based on the presented information, the user determines whether to adopt the imaging parameters again or further adjust the imaging parameters.

If the adjustment of the shooting parameters is to be stopped halfway, the icon 1023 displaying "end" is pressed. With this operation, the processing for adjusting the shooting parameters (the loop in the flow chart of FIG. 3) can be terminated. At this time, among the shooting parameters that have been shot and evaluated so far, the shooting parameter with the maximum evaluation value may be set in the shooting unit 101 .

In this way, by displaying images shot with a plurality of shooting parameters, crack detection results obtained from the images, past data, and evaluation results of each shooting parameter, the user can easily set shooting parameters suitable for inspection. Become.

Also in this case, a threshold value s- _th for the evaluation value may be set in advance, and the presence of the imaging parameter having an evaluation value exceeding the threshold value s- _th may be displayed. For example, in FIG. 10, when the evaluation value s ₁₀₁₁ of the image captured with the shooting parameters indicated by the black triangle 1011 exceeds the threshold s _th , the black triangle 1011 indicating the shooting parameters may blink. The user can adopt the imaging parameter regardless of the evaluation value, and by visually displaying the existence of the imaging parameter exceeding the evaluation value in this way, it is possible to assist the determination of the adoption of the imaging parameter. become.

Moreover, although not shown in FIG. 10, the concrete wall image when the past inspection result was created may be displayed in addition to the display contents of the display unit 1000 of FIG. In this case, images taken during past inspections are stored in the past data storage unit 106, and in step S302 of FIG. Also call the image.

[Variation]
Below, the modification of Embodiment 1 is demonstrated. When shooting multiple times in step S305 in FIG. 3, if the images are shot handheld or mounted on a drone, the shooting positions of the multiple images may slightly shift even if the same shooting area is shot. There is In the description of the first embodiment, no particular reference was made to this image misalignment, but alignment may be performed between past data and images. This process is executed immediately after the multiple images are captured in step S305.

Existing methods can be used to align multiple images, so a detailed explanation will be omitted, but matching of feature points between images, affine transformation of images (may be limited to translation and rotation), etc. It can be implemented by the processing of Furthermore, in order to calculate the evaluation value, it is necessary to align the cracks in the past data. For this purpose, alignment is performed so that the detection result of the crack detected from each image in step S306 and the position and shape of the crack in the past data are most similar. Positioning in this process may be performed by converting the photographed image itself, or by converting the image of the crack detection result.

Further, in the first embodiment, an example of estimating a method for improving an imaging parameter has been described, but the imaging method suitable for imaging an estimated crack is not limited to the imaging parameter, and other imaging methods may be estimated. . In the embodiment for estimating the imaging method other than the imaging parameters, the image and the imaging situation are further analyzed when the evaluation value equal to or higher than the predetermined threshold is not obtained even if the loop of the processing flow in FIG. 3 is executed multiple times. , to recommend appropriate shooting methods.

For example, when it is determined that the brightness of the image is insufficient, or when it is determined that the white balance cannot be adjusted with the shooting parameters, the user is asked to use lighting or change the shooting time. Then, a notification recommending shooting at a brighter time may be issued. As another example, when the position/orientation of the imaging unit 101 can be acquired, the position/orientation with respect to the structure to be inspected is analyzed, and the position/orientation for improving the imaging is proposed. More specifically, for example, when shooting in a position/orientation with a large tilt angle with respect to the wall surface of the structure to be inspected, the user is recommended to shoot in a position/orientation that reduces the tilt.

Further, in the first embodiment, cracks are used as inspection targets, but inspection targets are not limited to cracks, and other deformations may be used. In this case, it is preferable to use, as a target of the inspection used for adjusting the imaging parameters, a deformation that causes little change in the appearance of the results of past inspections due to secular change. For example, a cold joint, which is a discontinuous surface during concrete placement, is an example of a suitable target because, like cracks, the appearance of previously recorded portions does not change significantly. Also, concrete joints and joints can be targeted for inspection, although they are not deformations. In this case, the photographing parameters can be adjusted by comparing the positions and shapes of concrete joints and joints observed during past inspections with the positions and shapes of joints and joints detected in images currently being captured. You can do it.

As described above, in this embodiment, a structure to be inspected for which past inspection results are recorded is photographed with a plurality of photographing parameters to create a plurality of images. Inspection target detection processing is performed on each of the plurality of images. An evaluation value for each imaging parameter is calculated from the detection result of each image and the past inspection result. Then, if the maximum evaluation value is greater than or equal to the threshold, the imaging parameter indicating the maximum evaluation value is set as the imaging parameter to be used. On the other hand, if the maximum evaluation value is equal to or less than the threshold, the imaging parameters that improve the evaluation value are estimated.

According to this embodiment, it is possible for the user to estimate an image capturing method (for example, capturing parameters) suitable for comparison with past results without checking the captured image.

(Embodiment 2)
In the first embodiment, photographing parameters are adjusted by comparing past data (past crack inspection results) with crack detection results in photographed images. In addition to this, an image taken in the past (hereafter referred to as the past image) is further compared with an image currently taken for shooting parameter adjustment (hereafter referred to as the current image) to adjust the shooting parameters. can be

In the second embodiment, an example will be described in which a past image and a current image are compared to adjust shooting parameters.

In order to make a comparison with past inspection results, it is necessary to take images in which at least the cracks recorded in the past inspection results can be observed even in the images taken during the current inspection. For this purpose, in the first embodiment, shooting parameters are adjusted using past data and detection results. Here, if there is an image taken in the past inspection, it is desired to visually compare the past image and the current image to confirm the secular change such as extension of deformation. At this time, in order to compare the past image with the current image, not only is the current image an image in which the cracks recorded in the past inspection results can be observed, but the appearance of the image such as brightness and white balance must also be checked. It should be similar to the image.

Therefore, in the second embodiment, the degree of similarity between the past image and the current image is calculated, and an evaluation value is calculated in consideration of this degree of similarity to adjust the imaging parameters. Thus, it is possible to set the shooting parameters for performing shooting in which the past image and the current image are similar in appearance. Differences from the first embodiment will be mainly described below. Since other configurations and processes are the same as those of the first embodiment, description thereof is omitted.

First, the past data storage unit 106 stores not only the results of past inspections but also images of structures to be inspected in the past. Then, in step S301 of FIG. 3, when an arbitrary imaging range of the structure to be inspected is set, in step S302, past data and past images relating to the imaging range are called. After shooting with multiple parameters in step S305 and crack detection for each current image in step S306, an evaluation value is calculated in step S307. In the second embodiment, the evaluation value s' is calculated as follows based on one photographed image (current image) photographed with certain photographing parameters, past images, and past data.

The first term of expression (4) is an evaluation value based on cracks in expression (2) of the first embodiment. The second term r(I _o , _In ) indicates the degree of similarity between the past image I _o and the current image _In . The degree of similarity between images may be obtained in any manner, but is, for example, a value indicating similarity in luminance distribution or color distribution. In addition to this, the distance in some image feature space may be used as the degree of similarity. similarity should be calculated. Note that α and β in Equation (4) are weighting factors for the first term (evaluation value of cracks) and the second term (similarity between the past image and the current image). ' is a parameter that determines whether to calculate '. Here, α≧0 and β≧0.

By executing the processing of the first embodiment using the evaluation value s′ calculated as described above, it is possible to adjust the shooting parameters so that the past image and the current image are similar.

(Embodiment 3)
In the first embodiment, an example has been described in which the imaging parameters are adjusted using the past data of one imaging range 220 of the bridge pier 201 in FIG. 2, and the bridge pier 201 is imaged using the imaging parameters. In photographing the bridge pier 201, a plurality of images are photographed by repeatedly photographing a portion of the bridge pier 201, and a high-definition concrete wall surface image is created by connecting the plurality of images. However, even in the same bridge pier 201, it is better to shoot with appropriate shooting parameters depending on the part.

In the third embodiment, an example will be described in which imaging parameters are adjusted in a plurality of portions (a plurality of imaging ranges) on one wide wall surface of a structure to be inspected.

FIG. 11 shows a drawing 252 of the pier 251 of FIG. 2 (a pier different from the pier 201 used in the description of the first embodiment). Shooting ranges 1101, 1102, 1103, and 1104 are shooting ranges including cracks. For these imaging ranges, the method of the first embodiment is used to set imaging parameters suitable for imaging each imaging range. The imaging ranges 1101, 1102, 1103, and 1104 are determined by the user's selection or by the information processing apparatus 100 recommending an area including cracks in past data, as in the first embodiment.

Further, in the third embodiment, the positions are selected from the positions that are distributed as sparsely or as evenly as possible within the range of a certain wall surface (the range of drawing 252 in FIG. 11 in this embodiment). As shown in FIG. 11, these photographing ranges are not adjacent to each other and are set at positions distributed over the entire drawing 252 . The information processing apparatus 100 recommends a shooting range to the user so that a plurality of shooting ranges are set in this way.

In the example of FIG. 11, an example of setting four shooting ranges is described, but the number of shooting ranges set for a certain wall surface is not limited to this. If there are many imaging ranges, it is possible to set imaging parameters suitable for each portion of the wall surface, but it takes time to adjust the imaging parameters. Since these are in a trade-off relationship, the number of shooting ranges to be set may be set according to the request.

Next, by the method described in the first embodiment, the past data of each imaging range is used to determine imaging parameters suitable for imaging each imaging range. The imaging parameters for portions other than these imaging ranges are obtained by interpolation or extrapolation based on the imaging parameters set for each imaging range. For example, the shooting parameters for shooting the range 1120 are the shooting parameters obtained by linear interpolation based on the shooting parameters of the surrounding shooting ranges (for example, the shooting parameters of the shooting ranges 1101 and 1102). By doing so, it is possible to set the imaging parameters for each portion of the wall surface.

Furthermore, in the third embodiment, the imaging parameters may be adjusted with a constraint condition so that the imaging parameters do not change significantly for the same imaging target. For example, when photographing the bridge pier 251 in FIG. 2 corresponding to the drawing 252 in FIG. 11, if the photographing parameters differ greatly depending on the portion of the bridge pier 251, the high-definition image obtained by connecting the photographed images will lose a sense of unity. Therefore, when photographing a continuous mass portion such as the bridge pier 251, it is better to photograph with similar photographing parameters as much as possible. For this reason, the larger the difference between the evaluation value for adjusting the imaging parameters and the imaging parameters determined in the imaging area adjacent to the imaging area currently being imaged or in another imaging area included in the wall surface being imaged, Make a configuration that gives a penalty. This makes it possible to suppress large changes in imaging parameters when imaging a continuous block portion such as the bridge pier 251 .

According to this embodiment, it is possible to estimate an image capturing method suitable for comparison with past results for each capturing range.

(Embodiment 4)
In each of the above-described embodiments, a method of estimating a method of improving an imaging parameter using a plurality of evaluation values when the evaluation value is less than a predetermined threshold has been described (eg, FIG. 9B). However, the method of estimating the imaging parameter improvement method is not limited to processing using a plurality of evaluation values, and may be a method of estimating based on one evaluation value and imaging parameters related to that evaluation value. In Embodiment 4, differences from Embodiment 1 will be described with reference to the flowchart of FIG.

First, since multiple evaluation values are not calculated in the fourth embodiment, there is no need to perform imaging with multiple imaging parameters. Therefore, in the flowchart of FIG. 3 of the first embodiment, step S304 for setting a plurality of shooting parameters and step S305 for shooting multiple times are not executed. Therefore, in the fourth embodiment, one image in the shooting range is shot with certain initial parameters. Processing S306 for detecting a target (crack) and processing S307 for comparing the detection result with past data and calculating an evaluation value are executed for this one image. These are processes similar to those of the first embodiment. Furthermore, when the calculated evaluation value is equal to or greater than the threshold, the process of ending parameter setting (S308, S309, and S311 in FIG. 3) may be executed in the same manner as in the first embodiment.

A process different from that of the first embodiment is the process of step S310 for estimating a method for improving the imaging parameter when the evaluation value is equal to or less than the threshold. In the fourth embodiment, improved imaging parameters are estimated by a statistical method from one evaluation value and the imaging parameters at that time. For this reason, in the fourth embodiment, the relationship between the evaluation value and the improved imaging parameter is learned in advance. This relationship can be learned using, for example, the following data.

Here, _pn in Equation (5) is a photographing parameter, and _sn is an evaluation value obtained from an image photographed with _pn . s _n is an evaluation value below the threshold. p _{dst — n} in equation (6) is the shooting parameter when the shooting parameter is adjusted from the state of (s _n , p _n ) and the final evaluation value becomes equal to or greater than the threshold. Collect n sets of these data to create learning data (X, Y). This learning data is used to learn a model M that outputs an improved parameter _{p_dst} when an evaluation value s less than a certain threshold and a shooting parameter p are input.

Any algorithm may be used for learning this model. For example, if the imaging parameters are continuous values, a regression model such as linear regression can be applied.

By using the model M prepared in advance as described above in the improved imaging parameter estimation processing in step S310, in the fourth embodiment, improved imaging parameters can be estimated from one image.

As a method for obtaining improved imaging parameters, the configuration using a learned model may be used in the method of capturing an image with a plurality of imaging parameters in the first embodiment. That is, the model M is not limited to the configuration for estimating imaging parameters from one image, and may be used in a method for estimating imaging parameters from a plurality of images. In this case, as in the first embodiment, evaluation values are calculated from a plurality of images captured with a plurality of imaging parameters, and a model M for obtaining improved imaging parameters by inputting the plurality of imaging parameters and the plurality of evaluation values is learned. do. The learning data X for learning this model M is rewritten from equation (5) as shown in the following equation (8), where m is the number of multiple images to be shot in the shooting parameter adjustment. Note that the target variable (or teacher data) Y is the same as in Equation (6).

According to this embodiment, it becomes possible to estimate an improved imaging parameter from one image.

(Embodiment 5)
In each of the above-described embodiments, inspection of a structure having concrete wall surfaces has been described as an example. However, application examples of the present invention are not limited to this, and may be used for other purposes. In the fifth embodiment, an apparatus (appearance inspection apparatus) that takes an image of a product in a factory or the like and detects defects such as scratches will be described as an example.

FIG. 12 is a diagram for explaining the appearance inspection. First, an object 1200 is an object of appearance inspection such as a part or a product. In the appearance inspection, these are photographed by the photographing unit 101 and defects 1201 of the object 1200 are detected. In order to detect a defect from a photographed image, it is necessary to adjust parameters of predetermined image processing for emphasizing the defect in advance. Also, in visual inspection using machine learning, it is necessary to learn a model that identifies image features of defects from images of normal objects and images of objects containing defects.

Here, consider a case in which the photographing unit 101 (the photographing unit 101 may include a lighting device) is replaced. If the specifications of the new imaging unit 101 are different from those of the old imaging unit 1001, even if the same imaging parameters are set, the captured image will be slightly changed. Here, since the image processing parameters and the defect identification model are determined based on the image captured by the old image capturing unit 101, readjustment and relearning are required. For readjustment and re-learning, it is necessary to capture a large number of images of the object 1200 with the new imaging unit 101 . Therefore, it takes time to restart the production line using the visual inspection apparatus.

Therefore, by applying the imaging parameter adjustment method of the present invention, imaging parameters are set for the new imaging unit 101 that enable imaging of the same image as that of the previous imaging unit 101 . For this purpose, first an object containing defects is prepared. Hereinafter, this is called a reference object. It is assumed that the reference object has been inspected by the old imaging unit 101 in the past, and the detection result of the defect is stored in the past data storage unit 106 . Then, the new photographing unit 101 photographs the reference object with a plurality of different photographing parameters.

FIG. 12 shows images 1211 to 121n photographed with n photographing parameters of the new photographing unit 101 when the object 1200 is used as a reference object. Defect detection processing is performed on these n images, and the detection result is compared with the detection result of the old imaging unit stored in the past data storage unit 106 to calculate the evaluation value for each imaging parameter. . Then, the imaging parameters of the new imaging unit 101 are adjusted based on these evaluation values. The above processing is the same as that of the first embodiment except that the object to be photographed is different, so detailed description will be omitted.

This makes it possible to easily set, for the new imaging unit, imaging parameters that can detect defects detected by the old imaging unit.

In the above description, an example in which the present invention is applied when the imaging unit of the visual inspection apparatus is replaced has been described, but the method of applying the present invention to the visual inspection apparatus is not limited to this. For example, consider the case of newly introducing a visual inspection device to a plurality of production lines that manufacture the same product in a factory. Different production lines are affected by different external light, and for other reasons, it is necessary to adjust optimum imaging parameters for each production line.

In this case, first, the parameters of the photographing unit of the visual inspection apparatus of the first production line are manually adjusted. Then, an image of the object is photographed by the visual inspection apparatus of the first production line, and image processing parameter adjustment for defect detection and defect identification model learning are performed. Then, using at least one object including a defect as a reference object, the visual inspection apparatus of the first production line executes defect detection of the reference object. This detection result is stored in the past data storage unit 106 as past data.

Next, in a second production line different from the first production line, the image processing parameters and defect identification model set in the first production line are diverted. Then, the photographing parameters of the photographing section of the second production line are adjusted by the method of the present invention so that detection results similar to those of the first production line can be obtained. In this photographing parameter adjustment, the reference object is photographed by the photographing unit of the second production line and compared with the detection result of the reference object in the first production line stored in the past data storage unit 106. Calculate the evaluation value of the imaging parameter. Then, the imaging parameters of the second manufacturing line are adjusted based on the evaluation value.

According to the present embodiment, when the imaging unit is replaced in the visual inspection apparatus, the imaging parameters capable of detecting defects detected by the old imaging unit can be easily set for the new imaging unit. become.

(Other embodiments)
The present invention supplies a program that implements one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and one or more processors in the computer of the system or device reads and executes the program. It can also be realized by processing to It can also be implemented by a circuit (for example, ASIC) that implements one or more functions.

100: information processing apparatus, 101: imaging unit, 102: imaging parameter setting unit, 103: target detection unit, 104: estimation unit, 105: operation unit, 106: past data storage unit

Claims (15)

a storage means for storing past information of the target in the shooting range as past data;
detection means for detecting the target from the image of the imaging range captured by the imaging means with predetermined imaging parameters;
an estimation means for obtaining an evaluation value based on the detection result of the detection means and the past data, and estimating a shooting method suitable for shooting the target based on the evaluation value;
with
The estimation means acquires the evaluation value based on the degree of similarity between the past image of the imaging range and the current image of the imaging range, the detection result of the detection means, and the past data. information processing equipment. further comprising setting means for setting a plurality of imaging parameters for the imaging means;
The detection means detects the target from a plurality of images of the imaging range captured by the imaging means with a plurality of imaging parameters,
3. The estimating means obtains a plurality of evaluation values based on a plurality of detection results by the detecting means and the past data, and estimates the photographing method based on the plurality of evaluation values. 1. The information processing device according to 1. 3. The information processing apparatus according to claim 2, wherein said setting means sets said plurality of photographing parameters based on past photographing parameters as initial parameters. The evaluation value indicates a higher value when the detection result and the past data match, or when the detection result is a larger area including the past data than otherwise. 4. The information processing apparatus according to any one of claims 1 to 3. 5. The apparatus according to any one of claims 1 to 4, wherein said estimation means obtains said evaluation value based on a secular change of said photographing range, a result of detection by said detection means, and said past data. The information processing device described. 6. The information according to claim 5, wherein the estimation means obtains the evaluation value based on the detection result of the detection means and the past data, after excluding the area where the secular change is large. processing equipment. 7. The information processing apparatus according to claim 1, wherein said photographing method is a photographing parameter of said photographing means. an operation unit that displays the detection result, the past data, and the shooting method estimated by the estimation unit, and receives a user's operation for selecting the shooting method or readjusting the shooting method; 8. The information processing apparatus according to any one of claims 1 to 7, comprising: 9. The information processing apparatus according to any one of claims 1 to 8, wherein the target is deformation of a wall surface of a structure to be inspected. 10. An information processing apparatus according to claim 9, wherein said deformation is a crack in a concrete wall surface. 2. The information processing apparatus according to claim 1, wherein said similarity includes information on at least one of luminance distribution and color distribution of said past image and said current image. The photographing parameters are at least exposure of the photographing means, focus of the photographing means, white balance of the photographing means, shutter speed of the photographing means, sensitivity of the photographing means, saturation of the image, and hue of the image. 8. An information processing apparatus according to claim 7, comprising parameters relating to one. 13. The information processing apparatus according to claim 1, further comprising said photographing means. A control method for an information processing apparatus comprising storage means for storing past information of a target in an imaging range as past data,
a detection step of detecting the target from the image of the imaging range captured by the imaging means with predetermined imaging parameters;
an estimation step of obtaining an evaluation value based on the detection result of the detection step and the past data, and estimating an imaging method suitable for imaging the target based on the evaluation value;
has
In the estimating step, the evaluation value is obtained based on a degree of similarity between a past image of the imaging range and a current image of the imaging range, a detection result of the detection step, and the past data. A control method for an information processing device. A program for causing a computer to function as the information processing apparatus according to any one of claims 1 to 13 .

Images