Recording system, recording method, and recording program
Patent Information
- Application Number
- JP2025509729
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Filing Date
- 2025-09-05
- Publication Date
- 2025-11-19
Abstract
Description
Recording system, recording method, and recording program
[0001] The present disclosure relates to a recording system, a recording method, and a recording program.
[0002] The use of drones and other aerial vehicles is increasing. This is expected to lead to a diversification of drone usage. For example, the use of drones to inspect infrastructure facilities such as power transmission towers has been proposed.
[0003] Patent Literature 1 describes an information processing device that appropriately controls camera exposure using images captured by multiple cameras. The information processing device disclosed in Patent Literature 1 predicts the future position of a first camera, and predicts the brightness of an image captured by the first camera at the predicted position from images captured by a second camera in the present or past. As a result, the information processing device disclosed in Patent Literature 1 controls the image captured by the first camera at the predicted position to have appropriate brightness.
[0004] International Publication No. 2022 / 065039
[0005] In the information processing device disclosed in Patent Document 1, the user needs to operate the moving object to take pictures with the first camera and the second camera, and if the user is not familiar with operating the moving object, there is a risk that the user will not be able to capture the image of the target and will not be able to fully confirm the target.
[0006] In view of the above-mentioned problems, an object of the present disclosure is to provide a recording system, a recording method, and a recording program that enable more reliable confirmation of a shooting target.
[0007] A recording system according to one aspect of the present disclosure includes an image data acquisition unit that acquires first image data captured by a camera attached to a moving body that has moved to a target space based on pre-registered position data; a condition setting unit that sets recognition conditions for recognizing a target to be photographed based on at least one of the position in the target space and the date and time when the first image data was photographed; a target identification unit that identifies the target to be photographed from the first image data; a position and attitude determination unit that determines the position and attitude of the moving body relative to the target to be photographed based on the recognition conditions in order to photograph second image data including the target to be photographed; and a recording control unit that records the second image data.
[0008] A recording method according to one aspect of the present disclosure includes a computer executing the following processes: acquiring first image data captured by a camera attached to a moving object that has moved to a target space based on pre-registered position data; setting recognition conditions for recognizing a target to be photographed based on at least one of the position in the target space and the date and time when the first image data was photographed; identifying the target to be photographed from the first image data; determining the position and orientation of the moving object relative to the target to photograph a second image including the target to be photographed according to the recognition conditions; and recording the second image data of the target to be photographed.
[0009] A recording program according to one aspect of the present disclosure causes a computer to perform the following processes: acquire first image data captured by a camera attached to a moving object that has moved to a target space based on pre-registered position data; set recognition conditions for recognizing a target to be photographed based on at least one of the position in the target space and the date and time when the first image data was photographed; identify the target to be photographed from the first image data; determine the position and attitude of the moving object relative to the target to photograph a second image including the target to be photographed according to the recognition conditions; and record the second image data of the target to be photographed.
[0010] The present disclosure makes it possible to provide a recording system, a recording method, and a recording program that enable more reliable confirmation of a shooting target.
[0011] FIG. 1 is a block diagram showing a configuration of a recording system according to the present disclosure. FIG. 2 is a flowchart illustrating a recording method according to the present disclosure. FIG. 3 is a block diagram showing a usage example of a recording system according to the present disclosure. FIG. 4 is a schematic diagram showing first image data and second image data in a recording system according to the present disclosure. FIG. 5 is a schematic diagram showing a usage example of a recording system according to the present disclosure. FIG. 6 is a schematic diagram showing a usage example of a recording system according to the present disclosure. FIG. 7 is a diagram showing an example of learning of a position and orientation determination unit in a recording system according to the present disclosure. FIG. 8 is a block diagram showing a usage example of a recording system according to the present disclosure. FIG. 9 is a schematic diagram showing a usage example of a recording system according to the present disclosure. FIG. 10 is a block diagram showing a recording system according to the present disclosure. FIG. 11 is a flowchart illustrating a recording method according to the present disclosure. FIG. 12 is a flowchart illustrating a recording method according to the present disclosure. FIG. 13 is a block diagram showing a configuration example of a management device 201, etc. according to the present disclosure.
[0012] The present disclosure will be described below through embodiments, but the disclosure according to the claims is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential as means for solving the problems. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are designated by the same reference numerals, and repeated explanations are omitted as necessary.
[0013] <First Embodiment> <Recording System> A recording system according to the present disclosure will be described below with reference to the drawings. Fig. 1 is a block diagram showing the configuration of a recording system according to the present disclosure. A recording system 10 according to the present disclosure includes an image data acquisition unit 11, a condition setting unit 12, a target identification unit 13, a position and orientation determination unit 14, and a recording control unit 15.
[0014] The image data acquisition unit 11 acquires first image data captured by a camera attached to a mobile object that has moved to a target space based on pre-registered position data. The target space is a space that includes a target for imaging. For example, in the inspection of a power transmission tower, multiple inspection points on the tower are inspected together, and the target for imaging is each inspection point on the power transmission tower, and the target space is the surrounding space that includes each inspection point on the power transmission tower. The target space may be a single space corresponding to multiple targets for imaging, or multiple spaces that correspond one-to-one to each target for imaging.
[0015] For example, if there are three shooting targets, the target space may be one space including the three shooting targets, or two spaces including one space including two shooting targets and one space including the remaining shooting target. The first image data includes the shooting targets because it is captured by a camera provided on a moving object that has moved into the target space.
[0016] The mobile object is a mobile object that moves through the air, such as a drone (autonomous flying object) or a flying car. The mobile object estimates its own position using, for example, SLAM (Simultaneous Localization and Mapping). In SLAM, the position of the mobile object is calculated based on an environmental map, which is point cloud data of the surrounding environment obtained by a distance measurement sensor such as LIDAR. The mobile object estimates its own position and moves toward a target space based on the received pre-registered position data.
[0017] The condition setting unit 12 sets recognition conditions for recognizing the photographing target based on at least one of the position of the target space and the date and time when the first image data was photographed. The recognition conditions include geographical conditions, seasonal conditions, meteorological conditions such as weather, temperature, and wind speed, and date and time conditions. The geographical conditions include topographical information associated with the position indicated using latitude and longitude, and information on the surrounding environment indicating natural and artificial structures. The recognition conditions also include color, brightness, and contrast depending on the weather based on the geographical conditions, seasonal conditions, meteorological conditions such as weather, temperature, and wind speed, and the date and time conditions.
[0018] The target identification unit 13 identifies a photographing target from the first image data. For example, since inspection locations are predetermined for periodic inspections of infrastructure maintenance, the target identification unit 13 determines the type of infrastructure facility from the first image data and identifies the inspection location that is the photographing target.
[0019] The position and attitude determination unit 14 determines the position and attitude of the moving body relative to the shooting target based on the recognition conditions in order to capture second image data including the shooting target. The position and attitude of the moving body relative to the shooting target is, for example, the direction in which the moving body is located relative to the shooting target and the altitude at which the moving body is flying. The position and attitude of the moving body relative to the shooting target is, for example, flying eastward from the shooting target while maintaining an altitude of 100 meters. The position and attitude of the moving body relative to the shooting target also includes the degree of inclination of the aircraft, and may, for example, be flying at an inclination of several degrees relative to the horizon. The position and attitude determination unit 14 may also determine not only the direction and altitude of the moving body relative to the shooting target but also the distance from the shooting target.
[0020] When the position and orientation determination unit 14 determines the position and orientation of the moving body, it transmits a signal to the moving body to control the position and orientation of the moving body. When the moving body receives the signal, it moves based on the determined position and orientation and captures second image data including the shooting target. For example, the moving body may approach the shooting target to capture the second image, or may zoom in on a camera provided on the moving body to capture the second image.
[0021] Here, the first image data is captured by a camera mounted on a moving object that has moved into the target space and includes the target. However, the first image data is an image for identifying the target, and the user cannot confirm the target using the first image data, for example, because the target in the first image data is small.
[0022] On the other hand, the second image data, like the first image data, is captured by a camera mounted on the moving object and includes the target. Furthermore, the second image data is an image captured taking into consideration the recognition conditions. For example, the target in the second image data is large and clear, allowing the user to confirm the target using the second image data. In this way, the second image data is a confirmation image for the user to confirm the target.
[0023] The recording control unit 15 records the second image data including the shooting target. The recording destination by the recording control unit 15 is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory).
[0024] <Recording Method> Next, a recording method according to the present disclosure will be described. Fig. 2 is a flowchart illustrating the recording method according to the present disclosure.
[0025] First, the image data acquisition unit 11 acquires first image data captured by a camera attached to a moving object that has moved to a target space based on pre-registered position data (step ST1).
[0026] Next, the condition setting unit 12 sets a recognition condition for recognizing the photographing target based on at least one of the position in the target space and the date and time when the first image data was photographed (step ST2).
[0027] Next, the target identification unit 13 identifies the shooting target from the first image data (step ST3), and the position and orientation determination unit 14 determines the position and orientation of the moving body relative to the shooting target based on the recognition conditions in order to photograph the second image data including the shooting target (step ST4).
[0028] Then, the recording control unit 15 records the second image data including the shooting target in a memory such as a RAM or a ROM (step ST5).
[0029] In this way, in the recording system 10 according to the present disclosure, the position and orientation of the moving body relative to the shooting target are determined based on the recognition conditions for recognizing the shooting target, and the second image data captured by the moving body is recorded based on the determined position and orientation. With this configuration, even if the user is not familiar with operating the moving body, the user can easily capture the shooting target and can more reliably confirm the shooting target using the second image data.
[0030] Here, the inspection of a power transmission tower is used as an example of confirming a photographic target using the recording system 10, but this is not limited to this, and the recording system 10 disclosed herein can also be used in infrastructure maintenance such as substation inspections and in disasters such as fires and tsunamis.
[0031] Second Embodiment Recording System A recording system according to the present disclosure will now be described with reference to the drawings. Fig. 3 is a block diagram showing an example of use of the recording system according to the present disclosure. Fig. 3 shows a mobile object 101 and a management device 201. The mobile object 101 and the management device 201 are connected to each other so as to be able to communicate wirelessly.
[0032] The mobile object 101 includes a drive unit 111, a communication unit 112, an imaging unit 113, a mobile object control unit 114, a position data storage unit 115, and a self-position estimation unit 116. The management device 201 includes a communication unit 211, a second image data storage unit 212, an image data acquisition unit 11, a condition setting unit 12, a target identification unit 13, a position and attitude determination unit 14, and a recording control unit 15. As shown in Fig. 3 , the management device 201 includes the recording system 10 according to the present disclosure shown in Fig. 1 .
[0033] First, the configuration of the mobile object 101 will be described. The drive unit 111 includes a motor for rotating a propeller, which is the means of movement of the mobile object 101. The imaging unit 113 is, for example, a camera that captures first image data and second image data. The mobile object control unit 114 includes a calculation device such as a CPU or MCU, and controls each component of the mobile object 101. That is, the mobile object control unit 114 exchanges information with the management device 201 via the communication unit 112, and issues instructions to each component of the mobile object 101 in response. The position data storage unit 115 includes a non-volatile memory such as a flash memory or SSD, and stores position data of the target space. The self-position estimation unit 116 estimates its own position using SLAM or the like.
[0034] Next, the configuration of the management device 201 will be described. The image data acquisition unit 11, condition setting unit 12, target identification unit 13, position and attitude determination unit 14, and recording control unit 15 are the same as those in FIG. 1 , and therefore description thereof will be omitted. The management device 201 exchanges information with the mobile object 101 via a communication unit 211. The second image data storage unit 212 includes a non-volatile memory such as a flash memory or an SSD, and stores the second image data obtained by the imaging unit 113 of the mobile object 101.
[0035] The recording system according to the present disclosure will now be described in more detail with reference to Figures 4 to 6. Figures 4 and 6 are schematic diagrams showing examples of use of the recording system according to the present disclosure. Figure 5 is a schematic diagram showing first image data and second image data in the recording system according to the present disclosure. The examples shown in Figures 4 to 6 illustrate the inspection of a power transmission tower T1.
[0036] As shown in Figure 4, the transmission tower T1 has one inspection location, inspection location CP1, where there is a scratch CR1. The target for photography in Figures 4 to 6 is inspection location CP1. In addition, in Figures 4 to 6, the left side of the figure is the west side, and the depth direction of the figure is the north side. In the examples shown in Figures 4 and 6, the target space is TS1.
[0037] First, since the position data storage unit 115 stores the position data of the target space TS1, the mobile body 101 can move toward the target space TS1 as shown in Fig. 4. Then, the mobile body 101 captures the first image data 300 shown in Fig. 5 using the imaging unit 113. The first image data 300 shown in Fig. 5 includes the entire power transmission tower T1. Note that the first image data 300 does not confirm the presence of a scratch CR1 at the inspection point CP1.
[0038] Next, the management device 201 acquires the first image data 300 captured by the mobile object 101 using the image data acquisition unit 11. The condition setting unit 12 sets a recognition condition based on the position of the target space TS1 and the date and time when the first image data 300 was captured. For example, if the power transmission tower T1 is located at 45 degrees north latitude and 140 degrees east longitude, and the date and time when the first image data 300 was captured is an evening in February as shown in Fig. 5, the condition setting unit 12 sets a recognition condition such as winter twilight at a position of 45 degrees north latitude and 140 degrees east longitude.
[0039] Next, the target identification unit 13 identifies the inspection point CP1 from the first image data 300. Then, the position and orientation determination unit 14 determines the position and orientation of the moving object relative to the imaging target based on the recognition conditions in order to capture the second image data.
[0040] The position and orientation of the moving body 101 will be described with reference to FIG. 6 . The position and orientation determination unit 14 determines that the sun is located in the west based on the recognition condition that it is dusk at a position of 45 degrees north latitude and 140 degrees east longitude. In this case, if an attempt is made to capture the second image data of the inspection point CP1 from the east side (right side of the drawing) toward the west side (left side of the drawing), the image will be backlit and a clear image of the inspection point CP1 will not be obtained. On the other hand, if the second image data is captured from the west side (left side of the drawing) toward the east side (right side of the drawing), a clear image of the inspection point CP1 can be obtained without backlighting.
[0041] Therefore, the position and attitude determination unit 14 determines that the moving body 101 will fly at an altitude of 20 m west of the inspection point CP1 so that it can photograph the inspection point CP1 from the west side.
[0042] Next, as shown in Fig. 6, the mobile object 101 flies while maintaining an altitude of 20 m west of the inspection point CP1, and then the imaging unit 113 captures the second image data 400 shown in Fig. 5. Next, the management device 201 causes the recording control unit 15 to store the second image data 400 captured by the imaging unit 113 in the second image data storage unit 212.
[0043] 5, the inspection point CP1 is enlarged in the second image data 400 compared to the first image data 300. As a result, the user is able to confirm that there is a scratch CR1 at the inspection point CP1 in the second image data 400, whereas he or she was unable to confirm that there is a scratch CR1 at the inspection point CP1 in the first image data 300.
[0044] <Planned Movement Route> In the example shown in FIG. 5, the first image data 300 includes only one inspection point CP1, but this is not limited thereto, and the first image data may include multiple shooting targets. In this case, the target identification unit 13 creates a planned movement route for the shooting target from the first image data based on the recognition conditions. This will be described in more detail with reference to FIG. 7. FIG. 7 is a schematic diagram showing an example of use of the recording system according to the present disclosure.
[0045] In the example shown in Figure 7, the inspection locations for the transmission tower T11 are three inspection locations CP1 to CP3. The shooting targets in Figure 7 are three inspection locations CP1 to CP3. In addition, in Figure 7, the right side of the figure is the west side, and the front side of the figure is the north side. Note that in the example shown in Figure 7, the target space is not shown, but is assumed to be a single space that includes the three inspection locations CP1 to CP3.
[0046] 7, the transmission tower T11 is located at 25 degrees north latitude and 130 degrees east longitude, and the first image data was captured at noon in summer. That is, the condition setting unit 12 sets a recognition condition such as a summer noon time period at 25 degrees north latitude and 130 degrees east longitude.
[0047] Based on the recognition conditions, such as the summer noon time zone at 25 degrees north latitude and 130 degrees east longitude, the target identification unit 13 determines that the sun is located directly above the transmission tower T11 at 12 o'clock, as shown in Fig. 7. Furthermore, as shown in Fig. 7, the target identification unit 13 determines that at 13 o'clock, the sun is located slightly to the west of the transmission tower T11 (to the right in Fig. 7).
[0048] In this case, inspection points CP11 and CP13 are brightly illuminated by the sun at 12:00, but are slightly darker at 13:00 because the sun's position shifts to the west. On the other hand, inspection point CP12 is brighter illuminated by the sun at 13:00 than at 12:00.
[0049] Therefore, the target identification unit 13 creates the movement plan path L1 so that the inspection points CP11 and CP13 are photographed first, and the inspection point CP12 is photographed later. This prevents the second image data from failing to be photographed even if the user is not familiar with operating the moving object, and enables efficient acquisition.
[0050] 7 shows an example in which the target identification unit 13 creates a movement plan route based on brightness according to seasonal conditions. However, the present invention is not limited to this, and the target identification unit 13 may create a movement plan based on at least one of geographical conditions, seasonal conditions, meteorological conditions such as weather, temperature, and wind speed, recognition conditions such as date and time conditions, and flight time.
[0051] The target identification unit 13 may also be configured as follows: First, the target identification unit 13 calculates the success rate of capturing the second image data for each capture target based on at least one of the recognition conditions and the flight time.
[0052] The following describes the shooting success rate calculated by the target identification unit 13, taking as an example a case where a moving object photographs two distant shooting targets in weather conditions where rain is predicted to fall 30 minutes later than the weather forecast. Here, it is assumed that the flight time to one shooting target located close to the moving object is within 30 minutes, and the flight time to the other shooting target located farther away from the moving object is more than 30 minutes.
[0053] Since the flight time of the moving body to one of the shooting targets located close to the moving body is within 30 minutes, there is a high possibility that it will not rain yet, and therefore there is a high possibility that the second image data will be successfully captured. However, since the travel time of the moving body to the other shooting target located farther away from the moving body is more than 30 minutes, there is a possibility that the weather will change during the travel, and it will start raining by the time the moving body arrives at the other shooting target. Therefore, compared to one shooting target located close to the moving body, there is a lower possibility that the second image data will be successfully captured for the other shooting target located farther away from the moving body. In this way, the target identification unit 13 calculates the shooting success rate of the second image data for each shooting target.
[0054] The calculation of the imaging success rate of the target identification unit 13 may be performed by the user selecting conditions related to at least one of the recognition conditions and the flight time. Alternatively, the user may select whether or not to calculate the imaging success rate of the target identification unit 13. Naturally, the target identification unit 13 may calculate the imaging success rate of the second image data using a numerical value such as 50%, 0.5, etc.
[0055] The target identification unit 13 then creates a travel plan indicating the order in which to fly over each of the capture targets based on the capture success rate. In the example described above, a travel plan is created in which one capture target located near the moving body is captured and the other capture target located farther from the moving body is captured in order of the likelihood of successful capture of the second image data. This makes it possible to further reduce failures in capturing the second image data and enable efficient acquisition, even if the user is not familiar with operating the moving body.
[0056] <Determining Position and Attitude of Moving Object Using a Learning Model> Here, the position and attitude determination unit 14 may determine the position and attitude of the moving object using a learned model that has learned to determine the position and attitude of the moving object using the recognition conditions and first image data including the shooting target as input. This will be described in more detail with reference to Fig. 8. Fig. 8 is a diagram showing an example of learning performed by the position and attitude determination unit in the recording system according to the present disclosure.
[0057] As shown in Figure 8, the learning model LM1 is a model generated by associating geographical conditions, seasonal conditions, meteorological conditions such as weather, temperature, and wind speed, and date and time conditions with a sample image and learning the data. The learning model LM1 is generated, for example, by associating geographical conditions such as latitude and longitude and meteorological conditions such as rain with a sample image of a power transmission tower including an inspection location, which is the target of photography, and learning the data. The learning model LM1 is generated, for example, by learning using a neural network or the like. The trained model LM2 is a model of the learning model LM1 that has completed training or is currently being trained.
[0058] As a result, as shown in FIG. 8 , the position and attitude determination unit 14 can use the learned model LM2 to determine the position and attitude of the moving body using the recognition conditions and the first image data as input. For example, in the example shown in FIG. 6 , the first image data is of a power transmission tower photographed at a position of 45 degrees north latitude and 140 degrees east longitude, and the recognition conditions are that the photograph was taken at winter dusk at a position of 45 degrees north latitude and 140 degrees east longitude. Therefore, the position and attitude determination unit 14 uses the learned model LM2 and these as inputs to determine that the inspection point CP1 should be approached from the west while maintaining an altitude of 20 m. In this way, the position and attitude determination unit 14 can automatically determine the position and attitude of the moving body using the learned model LM2.
[0059] Furthermore, if the capture of the second image data fails, the learning model LM1 may be re-trained using a neural network or the like. That is, the learning model LM1 may be generated by learning sample images associated with geographical conditions, seasonal conditions, meteorological conditions such as weather, temperature, and wind speed, and date and time conditions not only for cases where the capture of the second image data is successful but also for cases where the capture of the second image data is unsuccessful. In this way, the position and orientation determination unit 14 can determine the position and orientation of the moving object using the trained model LM2, thereby preventing failures in the capture of the second image data.
[0060] <Identifying a Photographing Target Using a Trained Model> Here, it has been described that the position and attitude determination unit 14 determines the position and attitude of the moving object using a trained model. Similarly, the target identification unit 13 may also identify a photographing target from the first image data using a trained model. More specifically, the trained model is generated by learning by associating the photographing target with a sample image. For example, in the case of a high-rise building, inspection points that serve as photographing targets are lightning rods and windows on the roof, so the trained model is generated by learning by associating the lightning rods and windows with sample images of the high-rise building. This allows the target identification unit 13 to use the trained model to identify a photographing target using the first image data as input.
[0061] Furthermore, if the capture of the second image data fails, the learning model may be re-trained using a neural network or the like. That is, the learning model may be generated by learning not only sample images associated with the shooting target when the capture of the second image data is successful, but also sample images associated with the shooting target when the capture of the second image data fails. In this way, the target identification unit 13 can identify the shooting target using the trained model and prevent failures in capturing the second image data.
[0062] <Creating a movement plan using a learning model> Furthermore, the target identification unit 13 may create a movement plan for the photographing target using a learning model. In this case, the learning model is generated by learning sample images in which the first image data is associated with at least one of the recognition conditions and the flight time. The target identification unit 13 can use the learned model to create a movement plan for the photographing target by inputting the first image data and at least one of the recognition conditions and the flight time.
[0063] The learning model is not limited to learning sample images in which at least one of the recognition conditions and flight time is associated with the first image data when the second image data is successfully captured. The learning model may also learn sample images in which at least one of the recognition conditions and flight time is associated with the first image data when the second image data is unsuccessfully captured. By configuring in this way, even if the moving object moves along the movement plan created by the target identification unit 13 and fails to capture the second image data, the failure result can be reflected when creating the next movement plan. Therefore, failure to capture the second image data can be suppressed.
[0064] In this way, the target identification unit 13 can identify the shooting target using the learned model, and can also create a movement plan for the shooting target using the learned model.
[0065] In the example of use of the recording system shown in FIG. 3 , the mobile object 101 and the management device 201 are connected to each other so as to be able to communicate wirelessly. The example of use of the recording system is not limited to this, and may be the example shown in FIG. 9 . FIG. 9 is a block diagram showing an example of use of the recording system according to the present disclosure. In FIG. 9 , the mobile object 102 includes a drive unit 111, a communication unit 112, an imaging unit 113, a mobile object control unit 114, a position data storage unit 115, a second image data storage unit 212, an image data acquisition unit 11, a condition setting unit 12, a target identification unit 13, a position and orientation determination unit 14, and a recording control unit 15. In other words, compared to the example of use of the recording system shown in FIG. 3 , the mobile object 102 can perform all of the processing of each functional block without communicating with the management device.
[0066] <Embodiment 3> <Recording System> A recording system according to the present disclosure will be described below with reference to the drawings. Fig. 10 is a block diagram of a recording system according to the present disclosure. As shown in Fig. 10, a recording system 20 includes a weather information acquisition unit 16, a shooting condition setting unit 17, an image data acquisition unit 11, a condition setting unit 12, a target identification unit 13, a position and orientation determination unit 14, and a recording control unit 15. The image data acquisition unit 11, the target identification unit 13, the position and orientation determination unit 14, and the recording control unit 15 are the same as those in Figs. 1 and 3, and therefore description thereof will be omitted. Here, the weather information acquisition unit 16, the condition setting unit 12, and the shooting condition setting unit 17 will be described.
[0067] <Setting Recognition Conditions Based on Weather Information> The weather information acquisition unit 16 acquires weather information for the target space. The weather information includes information about the weather, temperature, and wind speed. The weather information includes past weather data and weather forecast data. For example, the weather information acquisition unit 16 acquires weather data for a location corresponding to the target space from weather data from the Japan Meteorological Agency. The condition setting unit 12 further sets recognition conditions based on the weather information for the date and time the first image data was captured.
[0068] The weather information acquisition unit 16, the condition setting unit 12, and the position and attitude determination unit 14 will be described in more detail. Here, an example will be described in which the first image data is an image of a power transmission tower located at 35 degrees north latitude and 140 degrees east longitude, captured at 11:00 a.m. on February 20th. Also, the weather forecast for February 20th at the location of 35 degrees north latitude and 140 degrees east longitude is rain in the morning and sunny in the afternoon.
[0069] In this case, the weather information acquisition unit 16 first acquires weather data for a location at 35 degrees north latitude and 140 degrees east longitude, such as rain in the morning and sunny skies in the afternoon. Next, the condition setting unit 12 determines that the first image data was captured at 11:00 AM on February 20th at a location at 35 degrees north latitude and 140 degrees east longitude, and that rain is forecast at 11:00 AM at the location at 35 degrees north latitude and 140 degrees east longitude. The condition setting unit 12 then sets a recognition condition, such as a time period before noon at a location at 35 degrees north latitude and 140 degrees east longitude, and that it is raining. Based on this recognition condition, the position and orientation determination unit 14 determines the position and orientation of the moving body for capturing the second image data. An example of the position and orientation of the moving body determined by the position and orientation determination unit 14 will be described with reference to FIG. 11 .
[0070] Fig. 11 is a schematic diagram showing an example of use of the recording system according to the present disclosure. Fig. 11 shows an image of an inspection point CP51 of a radio tower T51 located at 35 degrees north latitude and 140 degrees east longitude being captured at 11:00 a.m. using a mobile object 311. In Fig. 11, the left side of the figure is the west side, and the depth direction of the figure is the north side.
[0071] 11 , because it is raining around the radio tower T51, if an image of the inspection point CP51 is captured from the west side, the rain will be included in the second image data. On the other hand, if the inspection point CP51 is captured from the east side while the inspection point CP51 is located below the radio tower T51, the rain will be blocked by the radio tower T51, and the second image data will contain no rain and will be a clear image. Therefore, the position and attitude determination unit 14 determines, for example, to fly at an altitude of 20 m east of the inspection point CP1 so that the mobile unit 311 can capture the inspection point CP51 from the east side.
[0072] In this way, by including the weather information acquisition unit 16, the recording system 20 can set the recognition conditions taking into account the weather information in the target space and determine the position and orientation of the moving object according to the recognition conditions. As a result, more accurate second image data can be acquired, and the user can more reliably confirm the shooting target.
[0073] <Setting of Photographing Conditions> The photographing condition setting unit 17 sets photographing conditions for photographing the second image data based on the recognition conditions. The photographing conditions are settings of the imaging unit of the moving object, such as zoom, brightness, contrast, color setting, whether or not to use a flash, photographing time, shutter speed, etc. More specifically, in the case of recognition conditions such as a time period before noon at a location of 35 degrees north latitude and 140 degrees east longitude, and it is raining, the photographing condition setting unit 17 adjusts brightness and contrast to photograph the second image data.
[0074] In this way, by providing the shooting condition setting unit 17, the second image data can be captured in accordance with the recognition conditions, so that more accurate second image data can be obtained and the user can confirm the shooting target.
[0075] <Fourth Embodiment> <Recording System> A recording system according to the present disclosure will be described below with reference to the drawings. Fig. 12 is a block diagram of a recording system according to the present disclosure. As shown in Fig. 12, a recording system 40 includes a photographing feasibility determination unit 30, a control unit 31, an image data acquisition unit 11, a condition setting unit 12, a target identification unit 13, a position and orientation determination unit 14, and a recording control unit 15. The image data acquisition unit 11, the condition setting unit 12, the target identification unit 13, the position and orientation determination unit 14, and the recording control unit 15 are the same as those in Figs. 1, 3, and 10, and therefore description thereof will be omitted. Here, the photographing feasibility determination unit 30 and the control unit 31 will be described.
[0076] The photographing feasibility determination unit 30 determines whether photographing of the photographing target was successful based on the second image data. For example, if the second image data includes the photographing target and the user can confirm the photographing target, the photographing feasibility determination unit 30 determines that photographing of the photographing target was successful. On the other hand, for example, if the second image data does not include the photographing target or if the second image data includes the photographing target but the photographing target cannot be confirmed because it is too dark and unclear, the photographing feasibility determination unit 30 determines that photographing of the photographing target was not successful.
[0077] The control unit 31 controls the moving object in accordance with the determination result of the photographing feasibility determination unit 30. More specifically, when the photographing feasibility determination unit 30 determines that photographing of the photographing target has been successful, the control unit 31 controls the moving object to leave the target space.
[0078] On the other hand, if the photographing possibility determination unit 30 does not determine that photographing of the photographing target was successful, the recognition conditions are reset, and the control unit 31 controls the moving body to photograph the photographing target again.
[0079] With this configuration, even if the weather was sunny when the recognition conditions were set but changed to rain when the second image data was captured, accurate second image data can be obtained by resetting the recognition conditions and capturing the image again, allowing the user to more reliably confirm the target.
[0080] Furthermore, if the photographing feasibility determination unit 30 does not determine that photographing of the photographing target has been successful, the control unit 31 may control the moving object to leave the target space after a predetermined time has elapsed since the start of photographing of the photographing target. By adopting such a configuration, for example, if second image data that allows the photographing target to be confirmed cannot be obtained no matter how many times photographs are taken due to recognition conditions such as bad weather, second image data of another photographing target can be obtained first.
[0081] Furthermore, if the photographing feasibility determination unit 30 does not determine that photographing of the photographing target has been successful, the control unit 31 may control the moving object to leave the target space after photographing the photographing target a predetermined number of times. With this configuration, accurate second image data can be obtained by photographing multiple times, for example, even in unstable weather.
[0082] Here, the recording system 40 may further include an approach detection unit that detects that another moving object is approaching the moving object that captured the image of the target. The approach detection unit may, for example, acquire position data from the self-position estimation unit 116 of each moving object shown in FIG. 3 to detect that another moving object is approaching. The approach detection unit may also be configured to detect that another moving object is approaching using a proximity sensor provided in the moving object and acquire information that the other moving object is approaching.
[0083] If the photographing feasibility determination unit 30 does not determine that photographing the photographing target has been successful, the control unit 31 may execute the following process: When the approach detection unit detects that another moving object is approaching, the control unit 31 controls the moving object that has photographed the photographing target to leave the target space so that the other moving object does not interfere with the moving object that has photographed the photographing target.
[0084] Furthermore, the timing at which the control unit 31 causes the moving body that photographed the photographing target to leave the target space may be any timing as long as there is no interference between the moving body that photographed the photographing target and another moving body. For example, the control unit 31 may cause the moving body that photographed the photographing target to leave the target space when another moving body enters the target space. As another example, the control unit 31 may cause the moving body that photographed the photographing target to leave the target space before the other moving body moves to a position where it overlaps with the moving body that photographed the photographing target.
[0085] By adopting such a configuration, even if another moving body flies in to photograph the target, the second image data can be acquired without the moving bodies interfering with each other, and the user can confirm the target.
[0086] <Recording Method> Next, a recording method according to the present disclosure will be described. Figures 13 to 15 are flowcharts illustrating an example of a recording method according to the present disclosure. Note that steps ST1 to ST5 are the same as the recording method shown in Figure 2, and therefore description thereof will be omitted.
[0087] 13, following step ST5, the photographing possibility determination unit 30 determines whether photographing of the photographing target was successful (step ST6). If the photographing possibility determination unit 30 determines that photographing of the photographing target was successful (step ST6YES), the recording control unit 15 records the second image data in a memory such as RAM or ROM (step ST7).
[0088] On the other hand, if the photographing feasibility determination unit 30 does not determine that the photographing of the photographing target was successful (step ST6 NO), the control unit 31 determines whether a predetermined time has elapsed since the start of photographing the second image data (step ST11), as shown in Fig. 14. If the predetermined time has elapsed since the start of photographing the second image data (step ST11 YES), the control unit 31 controls the moving object that photographed the photographing target to leave the target space (step ST12). If the predetermined time has not elapsed since the start of photographing the second image data (step ST11 NO), the control unit 31 returns to step ST2 and resets the recognition conditions.
[0089] Here, when the approach detection unit detects that another moving object is approaching the moving object that has photographed the photographing target, the following may be performed.
[0090] If the photographing feasibility determination unit 30 does not determine that photographing the photographing target has been successful (step ST6 NO), the control unit 31 causes the approach detection unit to determine whether another moving object is approaching the moving object that photographed the photographing target (step ST21), as shown in Fig. 15. If the approach detection unit detects that another moving object is approaching the moving object that photographed the photographing target (step ST21 YES), the control unit 31 controls the moving object that photographed the photographing target to leave the target space (step ST22). If the approach detection unit does not detect that another moving object is approaching the moving object that photographed the photographing target (step ST21 NO), the control unit 31 returns to step ST2 and resets the recognition conditions.
[0091] Here, whether a predetermined time has elapsed since the start of capturing the second image data and whether another moving object is approaching the moving object that captured the image of the target are shown using separate flowcharts. However, this is not limited to this, and it may be possible to determine both whether a predetermined time has elapsed since the start of capturing the second image data and whether another moving object is approaching the moving object that captured the image of the target. For example, if the approach detection unit does not detect that another moving object is approaching the moving object that captured the image of the target (NO in step ST21), the control unit 31 may perform the determination in step ST11.
[0092] Returning to Fig. 13, the explanation will be continued. Following step ST7, the photographing possibility determination unit 30 determines whether or not all photographing targets have been photographed (step ST8). If the photographing possibility determination unit 30 determines that all photographing targets have been photographed (step ST8 YES), the present recording method is terminated. On the other hand, if the photographing possibility determination unit 30 determines that all photographing targets have not been photographed (step ST8 NO), the process returns to step ST1, and the image data acquisition unit 11 acquires first image data in order to photograph the next photographing target.
[0093] In this way, in the recording system 40 according to the present disclosure, the photographing feasibility determination unit 30 determines whether or not photographing the photographing target was successful based on the second image data, and the control unit 31 controls the moving object based on the determination result of the photographing feasibility determination unit 30. With this configuration, even if photographing the photographing target was not successful, accurate second image data can be obtained by resetting the recognition conditions and photographing again, thereby allowing the user to more reliably confirm the photographing target.
[0094] Furthermore, the recording system 40 according to the present disclosure can control the moving object that captured the image of the target to leave the target space if a predetermined time has elapsed since the start of capturing the second image or if another moving object is approaching, even if the image of the target is not successfully captured. By configuring in this way, the recording system 40 according to the present disclosure can prevent collisions between the moving objects even if another moving object flies in to capture the image of the target.
[0095] <Configuration Example> Fig. 16 is a block diagram showing a configuration example of a management device 201 and mobile objects 101, 102, 311 (hereinafter referred to as the management device 201, etc.) according to the present disclosure. Referring to Fig. 16, the management device 201, etc. includes a network interface 1201, a processor 1202, and a memory 1203. The network interface 1201 may be used to communicate with a network node. The network interface 1201 may include, for example, a network interface card (NIC) compliant with the IEEE 802.3 series. IEEE stands for Institute of Electrical and Electronics Engineers.
[0096] The processor 1202 reads and executes software (computer programs) from the memory 1203 to perform the processes of the management device 201 and the like described using flowcharts in the above-described embodiment. The processor 1202 may be, for example, a microprocessor, an MPU, or a CPU. The processor 1202 may include multiple processors.
[0097] The memory 1203 is configured by a combination of volatile memory and non-volatile memory. The memory 1203 may include storage located remotely from the processor 1202. In this case, the processor 1202 may access the memory 1203 via an I / O (Input / Output) interface (not shown).
[0098] 16, the memory 1203 is used to store software modules. The processor 1202 reads and executes these software modules from the memory 1203, thereby performing the processing of the management device 201 and the like described in the above embodiment.
[0099] As explained using FIG. 16, each of the processors included in the management device 201 or the like executes one or more programs including a group of instructions for causing a computer to execute the algorithm explained using the drawing.
[0100] Furthermore, part or all of the processing in the recording system according to the present disclosure can be realized as a computer program. Such a program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.
[0101] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.
[0102] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.
[0103] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A recording system comprising: an image data acquisition unit that acquires first image data captured by a camera attached to a moving object that has moved to a target space based on pre-registered position data; a condition setting unit that sets recognition conditions for recognizing a target for photography based on at least one of the position in the target space and the date and time when the first image data is captured; a target identification unit that identifies the target for photography from the first image data; a position and orientation determination unit that determines a position and orientation of the moving object with respect to the target for photography based on the recognition conditions in order to capture second image data including the target for photography; and a recording control unit that records the second image data. (Supplementary Note 2) The recording system according to Supplementary Note 1, further comprising a photographing feasibility determination unit that determines whether or not the photographing of the target for photography was successful based on the second image data. (Supplementary Note 3) The recording system according to Supplementary Note 2, further comprising a control unit that controls the moving body in accordance with a determination result of the photographing feasibility determination unit, wherein if the photographing feasibility determination unit determines that photographing of the photographing target has been successful, the control unit controls the moving body to leave the target space, and if the photographing feasibility determination unit does not determine that photographing of the photographing target has been successful, the recognition condition is reset, and the control unit controls the moving body to photograph the photographing target again. (Supplementary Note 4) The recording system according to Supplementary Note 3, wherein if the photographing feasibility determination unit does not determine that photographing of the photographing target has been successful, the control unit controls the moving body to leave the target space after a predetermined time has elapsed since photographing of the photographing target started. (Supplementary Note 5) The recording system described in Supplementary Note 3 or 4 further comprises an approach detection unit that detects that another moving body is approaching the moving body that photographed the shooting target, and if the shooting feasibility determination unit does not determine that the shooting of the shooting target was successful, the control unit, when the approach detection unit detects that another moving body is approaching, controls the moving body that photographed the shooting target to leave the target space so that the other moving body does not interfere with the moving body that photographed the shooting target.(Supplementary Note 6) The recording system according to Supplementary Note 1 or 2, wherein the first image data includes a plurality of the shooting targets, and the target identification unit creates a movement plan for the shooting targets from the first image data based on the recognition conditions. (Supplementary Note 7) The recording system according to Supplementary Note 1 or 2, wherein the condition setting unit sets the recognition conditions based on a position of the target space and a date and time when the first image data is captured. (Supplementary Note 8) The recording system according to Supplementary Note 1 or 2, further comprising a weather information acquisition unit that acquires weather information, and the condition setting unit sets the recognition conditions based on weather information at a date and time when the first image data is captured. (Supplementary Note 9) The recording system according to Supplementary Note 1 or 2, wherein the position and attitude determination unit determines the position and attitude of the moving body using a trained model that has learned to determine the position and attitude of the moving body using the recognition conditions and the first image data including the shooting targets as input. (Supplementary Note 10) The recording system according to Supplementary Note 1 or 2, further comprising a shooting condition setting unit that sets shooting conditions when shooting second image data based on the recognition conditions. (Supplementary Note 11) The recording system according to Supplementary Note 1 or 2, wherein the moving body is an autonomous flying body capable of autonomous flight. (Supplementary Note 12) A recording method in which a computer executes the following processes: acquires first image data captured by a camera attached to a moving body that has moved to a target space based on pre-registered position data, sets recognition conditions for recognizing a shooting target based on at least one of the position in the target space and the date and time when the first image data was captured, identifies the shooting target from the first image data, and determines a position and attitude of the moving body with respect to the shooting target in accordance with the recognition conditions, for capturing a second image including the shooting target, and records second image data of the shooting target. (Supplementary Note 13) The recording method according to Supplementary Note 12, further comprising determining whether or not the shooting of the shooting target was successful based on the second image data.(Supplementary Note 14) The recording method according to Supplementary Note 13, wherein, if it is determined that the photographing of the photographing target has been successful, the moving body is controlled to leave the target space, and if it is not determined that the photographing of the photographing target has been successful, the recognition condition is reset and the moving body is controlled to photograph the photographing target again. (Supplementary Note 15) The recording method according to Supplementary Note 14, wherein, if it is not determined that the photographing of the photographing target has been successful, the moving body is controlled to leave the target space after a predetermined time has elapsed since the start of photographing the photographing target. (Supplementary Note 16) The recording method according to Supplementary Note 14 or 15, further detecting that another moving body is approaching the moving body that photographed the photographing target, and if it is not determined that the photographing of the photographing target has been successful, controlling the moving body that photographed the photographing target to leave the target space so that the other moving body does not interfere with the moving body that photographed the photographing target. (Supplementary Note 17) The recording method according to Supplementary Note 12 or 13, wherein the first image data includes a plurality of the shooting targets, and a movement plan for the shooting targets is created from the first image data based on the recognition conditions. (Supplementary Note 18) The recording method according to Supplementary Note 12 or 13, wherein the recognition conditions are set based on a position in the target space and a date and time when the first image data was captured. (Supplementary Note 19) The recording method according to Supplementary Note 12 or 13, wherein weather information is acquired, and the recognition conditions are set based on the weather information at the date and time when the first image data was captured. (Supplementary Note 20) The recording method according to Supplementary Note 12 or 13, wherein the position and attitude of the moving body are determined using a trained model that has learned to determine the position and attitude of the moving body using the recognition conditions and the first image data including the shooting targets as input. (Supplementary Note 21) The recording method according to Supplementary Note 12 or 13, wherein shooting conditions for capturing second image data are set based on the recognition conditions. (Supplementary Note 22) The recording method according to Supplementary Note 12 or 13, wherein the moving body is an autonomous flying vehicle capable of autonomous flight.(Supplementary Note 23) A recording program that causes a computer to execute the following processes: acquire first image data captured by a camera attached to a moving object that has moved to a target space based on pre-registered position data; set recognition conditions for recognizing a shooting target based on at least one of the position in the target space and the date and time when the first image data was captured; identify the shooting target from the first image data; determine a position and attitude of the moving object with respect to the shooting target for capturing a second image including the shooting target according to the recognition conditions; and record second image data of the shooting target. (Supplementary Note 24) The recording program according to Supplementary Note 23, that determines whether or not the shooting of the shooting target was successful based on the second image data. (Supplementary Note 25) The recording program according to Supplementary Note 24, that controls the moving object to leave the target space if it is determined that the shooting of the shooting target was successful; and that resets the recognition conditions and controls the moving object to photograph the shooting target again if it is determined that the shooting of the shooting target was not successful. (Supplementary Note 26) The recording program according to Supplementary Note 24, wherein, if it is determined that the photographing of the photographing target is not successful, the moving body is controlled to leave the target space after a predetermined time has elapsed since the start of photographing the photographing target. (Supplementary Note 27) The recording program according to Supplementary Note 25 or 26, further detecting that another moving body is approaching the moving body that photographed the photographing target, and, if it is determined that the photographing of the photographing target is not successful, controlling the moving body that photographed the photographing target to leave the target space when it detects that another moving body is approaching so as to prevent interference between the other moving body and the moving body that photographed the photographing target. (Supplementary Note 28) The recording program according to Supplementary Note 23 or 24, wherein the first image data includes a plurality of the photographing targets, and a planned movement path for the photographing target is created from the first image data based on the recognition condition. (Supplementary Note 29) The recording program according to Supplementary Note 23 or 24, wherein the recognition condition is set based on a position in the target space and a date and time when the first image data is photographed.(Supplementary Note 30) The recording program according to Supplementary Note 23 or 24, further comprising: acquiring weather information; and setting the recognition conditions based on the weather information at the date and time when the first image data was captured. (Supplementary Note 31) The recording program according to Supplementary Note 23 or 24, further comprising: determining a position and attitude of the moving body using a trained model that has learned to determine the position and attitude of the moving body using the recognition conditions and the first image data including the capture target as input. (Supplementary Note 32) The recording program according to Supplementary Note 23 or 24, further comprising: setting shooting conditions for capturing second image data based on the recognition conditions. (Supplementary Note 33) The recording program according to Supplementary Note 23 or 24, further comprising:
[0104] This application claims priority based on Japanese Patent Application No. 2023-049090, filed on March 24, 2023, the disclosure of which is incorporated herein in its entirety.
[0105] DESCRIPTION OF SYMBOLS 10, 20, 40 Recording system 11 Image data acquisition unit 12 Condition setting unit 13 Target identification unit 14 Position and attitude determination unit 15 Recording control unit 16 Weather information acquisition unit 17 Shooting condition setting unit 30 Shooting possibility determination unit 31 Control unit 101, 102, 311 Mobile body 111 Driving unit 112 Communication unit 113 Imaging unit 114 Mobile body control unit 115 Position data storage unit 116 Self-position estimation unit 201 Management device 211 Communication unit 212 Second image data storage unit 300 First image data 400 Second image data 1201 Network interface 1202 Processor 1203 Memory CP1, CP11, CP12, CP13, CP51 Inspection location L1 Movement route LM1 Learning model LM2 Learned model T1, T11 Transmission tower T51 Radio tower TS1 Target space
Claims
1. image data acquisition means for acquiring first image data captured by a camera provided on a moving object that has moved to a target space based on pre-registered position data; a condition setting means for setting a recognition condition for recognizing a photographing target based on at least one of a position in the target space and a date and time when the first image data was photographed; a target identification means for identifying the photographing target from the first image data; a position and orientation determining means for determining a position and orientation of the moving object relative to the target based on the recognition conditions in order to capture second image data including the target; a recording control means for recording the second image data; A recording system comprising:
2. The camera further includes a photographing success / failure determination unit that determines whether or not photographing of the photographing target has been successful based on the second image data. The recording system of claim 1 .
3. a control unit that controls the moving body in accordance with the determination result of the photographing possibility determination unit; When the photographing possibility determination means determines that the photographing of the photographing target has been successful, the control means controls the moving body to leave the target space; When the photographing possibility determination means determines that photographing of the photographing target has not been successful, the recognition condition is reset, and the control means controls the moving body to photograph the photographing target again. The recording system of claim 2 .
4. When the photographing possibility determination means determines that photographing of the photographing target has not been successful, the control means controls the moving body to leave the target space after a predetermined time has elapsed since the start of photographing of the photographing target. The recording system according to claim 3 .
5. Further, an approach detection means is provided for detecting that another moving body is approaching the moving body that has photographed the photographing target, When the photographing possibility determination means does not determine that photographing of the photographing target has been successful, the control means, upon detecting that another moving object is approaching by the approach detection means, controls the moving object that has photographed the photographing target to leave the target space so that the other moving object does not interfere with the moving object that has photographed the photographing target.
5. A recording system according to claim 3 or 4.
6. the first image data includes a plurality of the photographing targets; the target identification means creates a movement plan path for the photographing target from the first image data based on the recognition conditions; 3. A recording system according to claim 1 or 2.
7. Further comprising a weather information acquisition means for acquiring weather information, the condition setting means further sets the recognition conditions based on weather information at the date and time when the first image data was captured.
3. A recording system according to claim 1 or 2.
8. the position and orientation determination means determines the position and orientation of the moving body using a trained model that has learned to determine the position and orientation of the moving body using the recognition conditions and the first image data including the shooting target as inputs; 3. A recording system according to claim 1 or 2.
9. acquiring first image data captured by a camera provided on a moving object that has moved to a target space based on pre-registered position data; setting a recognition condition for recognizing a photographing target based on at least one of a position in the target space and a date and time when the first image data was photographed; Identifying the photographing target from the first image data, and determining a position and orientation of the moving object with respect to the photographing target in accordance with the recognition conditions in order to photograph a second image including the photographing target; recording second image data obtained by photographing the target; The computer performs the processing, Recording method.
10. Acquiring first image data captured by a camera installed on a moving object that has moved to a target space based on pre-registered position data; setting a recognition condition for recognizing a photographing target based on at least one of a position in the target space and a date and time when the first image data was photographed; Identifying the photographing target from the first image data, and determining a position and orientation of the moving object with respect to the photographing target in accordance with the recognition conditions in order to photograph a second image including the photographing target; recording second image data obtained by photographing the target; Have the computer perform the process, Recording program.