Position estimation device, position estimation method and program

Abstract

A position estimation device (10) is provided with an image acquisition unit (110) and a position estimation unit (120). An image acquisition unit (110) acquires a plurality of images generated by an imaging device that captures an image of a target space, which is a space in which a flying body flies. The position estimation unit (120) estimates the position of the flying body by processing the plurality of images. A position estimation unit (120) temporarily sets the type of a flying body, and estimates the distance to the flying body and the speed. The position estimation unit (120) updates the type of the flying body using the speed and the rate of change in the area of the flying body in the image. The position estimation unit (120) repeats the above-mentioned processing.

Description

Technical Field

[0001] The present invention relates to a position estimating device, a position estimating method, and a program. Background Art

[0002] In recent years, large structures in the height direction have been installed in various places, represented by wind power generation devices. Flying objects such as birds may collide with such structures. In response to this, the device described in Patent Document 1 recognizes the arrival of birds, calculates the position of the flying birds, and estimates the location of the flying birds after a given time based on two image data obtained by two camera modules, and supplies sound signals to multiple speaker modules so that the sound reaches the estimated location.

[0003] Prior Art Literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 10-4858 Summary of the invention

[0006] -Problems to be solved by the invention-

[0007] In the technique described in Patent Document 1, at least two imaging devices are required to estimate the position of a flying object. In view of the above problems, one example of an object of the present invention is to estimate the position of a flying object even with a single imaging device.

[0008] -Methods for solving the problem-

[0009] According to one aspect of the present invention, there is provided a position estimating device,

[0010] The position estimation device comprises:

[0011] an image acquisition unit that acquires a plurality of images generated by an imaging device that captures a space in which the flying object flies, that is, a target space; and

[0012] a position estimating unit that estimates the position of the flying object by processing the plurality of images;

[0013] The position estimation unit performs the following processing:

[0014] (1) Temporarily set the type of the flying object,

[0015] (2) determining three or more images arranged in time series as a target image group,

[0016] (3) for each of the plurality of images included in the target image group, estimating the distance from the imaging device to the flying object using the temporarily set type and the area of ​​the flying object in the image belonging to the target image group,

[0017] (4) calculating a change rate of the area of ​​the flying object between the plurality of images included in the target image group,

[0018] (5) estimating the speed of the flying object using the distance to the flying object in each of the plurality of images included in the target image group and the position in the image;

[0019] (6) using the speed and the rate of change of the area, updating the type of the flying object;

[0020] (7) using the type updated in (6), the processing of (2) to (6) is performed again until a given criterion is satisfied.

[0021] Based on the position of the flying object in the image and the distance calculated based on the image, the estimated position of the flying object at the timing when the image was captured is indicated.

[0022] Furthermore, according to one aspect of the present invention, a method of estimating the position of a flying object using the above-mentioned position estimating device and a program for realizing the above-mentioned position estimating device can be provided.

[0023] -Effects of the Invention-

[0024] According to one aspect of the present invention, the position of a flying object can be estimated even with a single imaging device. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a diagram for explaining a first example of a usage environment of the position estimating device according to the embodiment.

[0026] Figure 2 This is a diagram for explaining a second example of the usage environment of the position estimating device.

[0027] Figure 3 It is a diagram showing an example of the functional configuration of a position estimating device.

[0028] Figure 4 It is a diagram showing a hardware configuration example of a position estimating device.

[0029] Figure 5 This is a diagram for explaining an example of processing performed by the position estimating device.

[0030] Figure 6It is a diagram for explaining step S30.

[0031] Figure 7 It is used to illustrate Figure 5 FIG. 5 is a diagram of the processing shown in steps S20 to S60.

[0032] Figure 8 It is a diagram for explaining a detailed example of step S90.

[0033] Fig. 9 It is a diagram for explaining a detailed example of step S90.

[0034] Fig.10 It is a diagram for explaining a detailed example of step S90.

[0035] Fig.11 It is a diagram for explaining a detailed example of step S90.

[0036] Fig.12 It is a diagram for explaining a usage environment of a position estimating device according to a modification example.

[0037] Fig.13 This is a diagram for explaining an example of a method of determining the estimated position of a flying object by the position estimating unit. DETAILED DESCRIPTION

[0038] Hereinafter, the embodiments of the present invention will be described using the drawings. In addition, in all the drawings, the same reference numerals are given to the same components, and the description thereof will be appropriately omitted.

[0039] (Implementation Method)

[0040] Figure 1 This is a diagram for illustrating a first example of a usage environment of the position estimation device 10 involved in the embodiment. In the example shown in this figure, the position estimation device 10 is a device that detects a flying object existing around a structure 20 and estimates its position. In the detection and estimation, the position estimation device 10 uses an image generated by a camera device 30. The object space is included in the camera range of the camera device 30. The object space includes an area that a flying object should not invade. An example of this area is the area around the structure 20. The object space may include the structure 20 or may not include the structure 20. In addition, the object space, for example, includes both the structure 20 and the space within 2 km from the structure 20. However, depending on the type of the camera device 30, the object space may also include the space within 10 km from the structure 20.

[0041] Typical examples of flying objects are animals such as birds, etc. However, the flying object may also be other objects, such as airplanes, helicopters, or objects flying with the wind.

[0042] The structure 20 is, for example, a wind turbine generator, but may also be other equipment such as a tower. Furthermore, when the structure 20 has a mechanical structure or an electrical structure, the structure is controlled by the control device. When the structure 20 is a wind turbine generator, the structure is a blade. When the position estimation device 10 determines that the position of the flying object and its displacement meet a given reference and may collide with the structure 20, in order to stop or slow down the movement of the mechanical structure or the electrical structure, the control device sends a certain information (control information described later) to the control device. Then, the control device slows down or stops the movement of the above-mentioned structure.

[0043] The camera device 30 is a single-lens camera. The camera device 30 preferably has a pitch function, a pan function, and a zoom function (hereinafter referred to as a TPZ function). It is desirable that the installation position of the camera device 30 is fixed. In addition, the frame rate of the image generated by the camera device 30 is arbitrary. In addition, the camera device 30 may also send the setting value of the camera device 30 when generating the image, such as the focal length, to the position estimation device 10 together with the generated image.

[0044] The installation position of the camera device 30 can also be determined using simulation, for example. In this case, if the viewing angle, installation position, and camera direction of the camera device 30 are input into the simulation device, the range in which the camera device 30 can perform imaging can be calculated. And, if the calculation result is used, the appropriate installation position of the camera device 30 can be estimated.

[0045] The position estimation device 10 estimates the current position of the flying object and estimates the future position of the flying object. Furthermore, when the flying object is an animal such as a bird, the position estimation device 10 controls the speaker 40 so that the sound arrives at the timing when the animal arrives at the future position. That is, the position estimation device 10 also functions as a control device for the speaker 40. At this time, the position estimation device 10 outputs a sound for conveying the given information to the animal from the speaker 40.

[0046] An example of the sound that position estimation device 10 causes speaker 40 to output is a sound for conveying certain information from a species having the same relative as the detected animal to the animal, or a sound for conveying certain information from a species having a close relative to the detected animal to the animal.

[0047] An example of given information transmitted by sound is information that can change the behavior of the animal, for example, a sound used to transmit that a natural enemy is approaching, or a sound used to transmit that bait is located in another place or direction. For example, in the case where the detected animal is an animal on the prey side, the sound output by the speaker 40 is a sound used to transmit that a predator is approaching. On the other hand, in the case where the detected animal is a predator, the sound output by the speaker 40 is a sound used to transmit that a predator is located in another place. That is, the position estimation device 10 changes the sound according to the type of animal detected.

[0048] In addition, the speaker 40 preferably has directivity. An example of the speaker 40 is a parametric speaker. In addition, the direction of the speaker 40 is variable. And the position estimation device 10 controls the direction of the speaker 40 so that the emission direction of the speaker 40 is directed toward the future position of the animal.

[0049] Figure 2 1 is a diagram for explaining a second example of the use environment of the position estimation device 10. In the example shown in this figure, the position estimation device 10 predicts the future position of an animal that is about to invade a specific land (hereinafter referred to as a target area) and controls the speaker 40 so that the animal does not invade the target area. In the example shown in this figure, the target animal is, for example, a pig, a deer, a monkey, a mouse, or a species closely related thereto, and is an animal that is the cause of so-called animal damage. In addition, in the case of the example shown in this figure, in the following description, "flying object" is replaced by "animal".

[0050] Figure 3 1 is a diagram showing an example of the functional structure of the position estimation device 10. The position estimation device 10 includes an image acquisition unit 110 and a position estimation unit 120. The image acquisition unit 110 acquires a plurality of images captured by the imaging device 30. The position estimation unit 120 estimates the position of the flying object by processing the plurality of images.

[0051] The position estimating unit 120 performs the following processing.

[0052] (1) Temporarily set the type of flying object.

[0053] (2) determining three or more images arranged in time series as a target image group,

[0054] (3) for each of the plurality of images included in the target image group, using the temporarily set category and the area of ​​the flying object in the image belonging to the target image group, estimating the distance from the imaging device to the flying object,

[0055] (4) calculating the rate of change of the area of ​​the flying object between the plurality of images included in the target image group,

[0056] (5) estimating the speed of the flying object using the distance to the flying object in each of the plurality of images included in the target image group and the position in the image;

[0057] (6) Use the speed and area change rate to update the type of flying object.

[0058] (7) Using the type updated in (6), the processes shown in (2) to (6) are repeated until the given criteria are satisfied.

[0059] Then, based on the position of the flying object in the image and the distance calculated based on the image, the estimated position of the flying object at the timing when the image was captured is shown.

[0060] In the above-mentioned (3), the position estimating unit 120 preferably uses the focal length when the imaging device 30 generates the image.

[0061] Furthermore, in (3), the position estimation unit 120 calculates the average value of the area occupied by the flying object between the currently processed image and at least one other image belonging to the target image group, and estimates the distance using the average value. At this time, the position estimation unit 120 further generates motion information representing the motion state of the flying object. The motion information includes at least one of the rotation radius, angular velocity, acceleration, and angular acceleration when the trajectory of the flying object is approximated as an arc. The center of the rotation radius is the position of the camera device 30. Furthermore, the position estimation unit 120 estimates the future position of the flying object. The future position is the estimated result of the position of the flying object at the first timing in the future. The first timing is a given time from the current time. The given time is, for example, a value greater than 1 / 120 seconds and less than 5 seconds. However, it may also be longer than these. When estimating the future position, the position estimation unit 120 uses the position, velocity, and motion information of the flying object and at least one of the time series information thereof.

[0062] In addition, the processing performed by the position estimating unit 120 will be described in detail using other drawings.

[0063] Furthermore, since the position estimating device 10 also functions as a control device that controls the speaker 40 , it includes a control unit 130 and a storage unit 140 .

[0064] When the flying object is an animal, the control unit 130 outputs a sound from the speaker 40 for conveying a given information to the animal so that the animal arrives at the future position at the first timing. A specific example of the given information is as follows: Figure 1 As described.

[0065] The storage unit 140 stores data as a sound source of the sound output by the speaker 40. Hereinafter, this data is described as sound data. The storage unit 140 stores the sound data by different types of animals, such as categories. In addition, the control unit 130 reads the sound data corresponding to the type of the animal detected by the position estimation unit 120 from the storage unit 140 and outputs it from the speaker 40.

[0066] In addition, if you use Figure 1 As described above, the speaker 40 has directivity and its direction is variable. The control unit 130 controls the direction of the speaker 40. As an example, the control unit 130 controls the direction of the speaker 40 so that the emission direction of the speaker 40 is directed toward the future position of the animal.

[0067] Figure 4 1 is a diagram showing an example of the hardware configuration of the position estimation apparatus 10. The position estimation apparatus 10 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0068] The bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the input / output interface 1050, and the network interface 1060 to transmit and receive data to and from each other. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0069] The processor 1020 is a processor realized by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0070] The memory 1030 is a main storage device implemented by a RAM (Random Access Memory) or the like.

[0071] The storage device 1040 is an auxiliary storage device implemented by a removable medium such as a HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, or a ROM (Read Only Memory). The storage device 1040 stores program modules that implement the various functions of the position estimation device 10 (for example, the image acquisition unit 110, the position estimation unit 120, and the control unit 130). The processor 1020 reads these various program modules to the memory 1030 and executes them to implement the various functions corresponding to the program modules. In addition, the storage device 1040 also functions as the storage unit 140.

[0072] The input / output interface 1050 is an interface for connecting the position estimation device 10 to various input / output devices. For example, the position estimation device 10 may communicate with at least one of the camera 30 and the speaker 40 via the input / output interface 1050 .

[0073] The network interface 1060 is an interface for connecting the position estimation device 10 to a network. The network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method of connecting the network interface 1060 to the network may be either a wireless connection or a wired connection. The position estimation device 10 may also communicate with at least one of the camera device 30 and the speaker 40 via the network interface 1060.

[0074] Figure 5 1 is a diagram for explaining an example of processing performed by the position estimation device 10. In the processing shown in this figure, the camera device 30 repeatedly generates images. Whenever an image is generated, the camera device 30 immediately sends the image to the position estimation device 10. The image acquisition unit 110 of the position estimation device 10 acquires these multiple images and stores them in a storage unit such as the storage unit 140.

[0075] Each time the image acquisition unit 110 acquires a new image, the position estimation unit 120 determines whether the image contains a flying object. For this process, for example, a process of determining whether there is a moving object in the image is used. If a flying object is contained, the process shown in this figure is started.

[0076] First, the position estimation unit 120 temporarily sets the type of the flying object. This process is equivalent to using Figure 2 (1) of the description: When an animal is temporarily set as a flying object, the type set here is preferably determined as the species of the animal (step S10).

[0077] Next, the position estimation unit 120 selects a given number of images from the images stored in the storage unit 140. The given number is at least 3 images, but may be more than 3. Hereinafter, the multiple images selected here are recorded as an object image group. The multiple images constituting the object image group are continuous in time series and all contain a flying body. For example, when the object image group is composed of 3 images, the initially generated object image group is composed of the image that initially contains the flying body and the 2 images generated thereafter (step S20). This processing is equivalent to using Figure 2 Description (2).

[0078] Next, the position estimation unit 120 estimates the distance from the camera device 30 to the flying object at the timing when the image is captured in each of the plurality of images constituting the target image group (step S30). The estimated position of the flying object at the timing of each image is generated by indicating the position of the flying object in the image and the distance calculated based on the image. This process is equivalent to using Figure 2 Explanation (3).

[0079] Figure 6 This is a diagram for explaining step S30. When the type of the flying object is determined, even if individual differences are taken into account, the absolute size of the flying object will converge within a given range set for each type. Therefore, the ratio of the area occupied by the flying object in the image (for example, the number of pixels) changes according to the distance from the camera device 30 to the flying object. Specifically, as the distance from the camera device 30 to the flying object becomes longer, the ratio of the area occupied by the flying object in the image becomes smaller. The position estimation unit 120 estimates the distance from the camera device 30 to the flying object using this relationship.

[0080] In addition, the ratio of the area occupied by the flying object in the image also changes according to the focal length of the camera 30. Therefore, when the focal length of the camera 30 is variable, the position estimating unit 120 preferably uses the focal length of the camera 30 when the image is generated when calculating the distance from the camera 30 to the flying object.

[0081] Back to Figure 5 After step S30, the position estimation unit 120 estimates the speed of the flying object, the rotation radius when the trajectory of the flying object is approximated as an arc, the angular velocity, the acceleration, and the angular acceleration using the position of the flying object at each timing of each image captured (step S40). This process is equivalent to using Figure 2 (3) and (5) of the description.

[0082] Two images are required for estimating the speed and angular velocity, and three or more images are required for estimating the acceleration and angular acceleration. Specifically, the position of the flying object calculated in step S30 shows the trajectory of the flying object. If this trajectory is used, the rotation radius of the flying object can be estimated. In addition, if the change in the position of the flying object between at least two images adjacent to each other on the time axis is used, the speed and acceleration of the flying object can be estimated. In addition, if the rotation radius of the flying object and the change in the position of the flying object between the above-mentioned two images are used, the angular velocity and angular acceleration of the flying object can be estimated. The position estimating unit 120 can perform the estimation shown in step S40 on images other than the image at the initial position on the time axis among the multiple images constituting the object image group.

[0083] Next, the position estimation unit 120 calculates the rate of change of the area occupied by the flying object calculated in step S30, and calculates the average value of the area (step S50). This process is equivalent to using Figure 2 Description (4).

[0084] For example, the position estimation unit 120 performs the following processing except for the image that is located at the last position on the time axis among the multiple images constituting the target image group. First, the ratio of the area of ​​the flying body in the image to the area of ​​the flying body in the next image is set as the area change rate. And the average value of the two areas is calculated. These area change rates and average values ​​are located in the middle of the timing of generating the two images on the time axis. In addition, when step S50 is performed, the amount of data on the time axis is reduced by one.

[0085] The position estimating unit 120 repeatedly performs the processes of steps S30 to S50 using the average value of the areas calculated in step S50 (step S60) until the first criterion is satisfied. An example of the first criterion is that the processes of steps S30 to S50 are repeated a given number of times.

[0086] Figure 7 It is used to illustrate Figure 5 FIG. 1 is a diagram of the processing shown in steps S20 to S60. In the example shown in this figure, the target image group consists of 10 images. And, Figure 7 (A) shows the moving path (trajectory) of the flying object on the image, that is, the trajectory projected onto the xz plane. Figure 7 Each of the graphs (B) shows the distance from the camera device 30 to the flying object, that is, the estimated path of the flying object projected onto the xz plane. In addition, the x-axis and the y-axis represent two axes constituting the image. Figure 1 As shown, the z-axis indicates a direction away from the imaging device 30 .

[0087] As for step S50, as described above, when step S50 is performed, the number of data on the time axis decreases by one. Therefore, each time the processing shown in steps S20 to S50 is repeated, the measurement points representing the estimated movement path, i.e., the measurement timing, will decrease one by one. Instead, the estimated accuracy of the distance, i.e., the estimated accuracy of the position of the flying object, becomes higher.

[0088] Back to Figure 6. When the first criterion is satisfied (step S60: Yes), the position estimation unit 120 determines whether it is necessary to update the target image group (step S70). An example of a situation where it is necessary to update the target image group is, for example, when there are still images that have not been selected as the target image group. In addition, a situation where the image acquisition unit 110 acquires a new image from the camera device 30 is also an example of a situation where it is necessary to update the target image group. When it is necessary to update the target image group (step S70: Yes), the position estimation unit 120 updates the target image group (step S20) and repeats the processing shown in steps S30 to S70.

[0089] In addition, the updating method of the target image group is a first-in-first-out method. That is, the position estimation unit 120 removes the earliest image in the time series from the target image group among the images included in the current target image group. In addition, the position estimation unit 120 determines the latest image among the images included in the current target image group, and newly adds the image located at the next position of the image in the time series to the target image group. That is, each target image group corresponds to the timing at which the latest image in the target image group was photographed.

[0090] Then, the position estimation unit 120 calculates the moving average of the values ​​calculated in steps S40 to S50 (step S80). This process is equivalent to Figure 2 The processing between (5) and (6) shown in the figure is performed. Then, the position estimating unit 120 estimates the future position of the flying object using the moving average of the position and the speed (step S90).

[0091] Figure 8 to Figure 11 It is a diagram for explaining a detailed example of step S90.

[0092] First, if Figure 8 As shown, the position estimation unit 120 calculates the K-point moving average of the area of ​​the flying body, the minimum value within the K points, and the maximum value within the K points according to the target image group. Specifically, the position estimation unit 120 calculates the K-point moving average of the area of ​​the flying body, and associates the calculated average with the latest image in the time series among the images used when calculating the moving average. In addition, the position estimation unit 120 identifies the area of ​​the flying body in each of the K images used when calculating the moving average. And, the position estimation unit 120 associates these K minimum values ​​and maximum values ​​of the area with the latest image in the time series among the images used when calculating the moving average. As a result, the minimum values ​​and maximum values ​​of the area are associated with multiple images respectively.

[0093] And, if Fig. 9As shown, the position estimation unit 120 determines an estimated movement path of the flying body based on the minimum value of the area (hereinafter referred to as the first estimated movement path) and an estimated movement path based on the maximum value of the area (hereinafter referred to as the second estimated movement path) according to the object image group. The first estimated movement path represents the movement path when the estimated distance from the camera device 30 to the flying body becomes the maximum value of the estimation range (i.e., when it is farthest from the camera device 30). On the other hand, the second estimated movement path represents the movement path when the estimated distance from the camera device 30 to the flying body becomes the minimum value of the estimation range (i.e., when it is closest to the camera device 30). The range sandwiched by these two estimated movement paths represents the estimated range of the movement path of the flying body. The flying body flies within this estimated range with a high probability. Thus, the estimated movement path of the flying body can be shown in a strip shape.

[0094] Although not shown, the position estimating unit 120 determines an estimated movement path based on a moving average of the area (hereinafter referred to as a third estimated movement path). The third estimated movement path is located between the first estimated movement path and the second estimated movement path.

[0095] And, if Fig.10 As shown, the position estimation unit 120 calculates, in each object image group, a rotation radius representing the first estimated movement path (the minimum value of the area), a rotation radius representing the second estimated movement path (the maximum value of the area), and a rotation radius representing the third estimated movement path (the moving average of the area).

[0096] And, if Fig.11 As shown, the position estimation unit 120 superimposes the estimated movement paths based on the plurality of target image groups. The plurality of target image groups correspond to the times (t0, t1, t2...) when the latest images in the target image groups were captured.

[0097] Each estimated movement path is represented as an arc having a radius based on the third estimated movement path and centered at the position of the camera device 30. Furthermore, the position estimation unit 120 estimates the future movement path of the flying object using the shifts of these estimated movement paths, and estimates the future position of the flying object using the movement path. As an example, the position estimation unit 120 can estimate the future position of the flying object using a Kalman filter. In this case, the future position of the flying object can be predicted even if there are missing values. In addition, the robustness of the prediction of the future position is also improved.

[0098] In addition, the moving average of the position, speed, and motion information of the flying object is used to calculate the estimated movement path. Therefore, the moving average of the position, speed, and motion information of the flying object is substantially used to predict the future position of the flying object.

[0099] In addition, Fig.11 In the method shown, each estimated movement path may estimate the future position of the flying object based on the first estimated latitude path (i.e., the path farthest from the camera device 30), and estimate the future position of the flying object based on the second estimated latitude path (i.e., the path closest to the camera device 30). In this case, the position estimating unit 120 may use these two future positions to calculate the future position actually used. As an example, the position estimating unit 120 may also set the average position of the two future positions as the future position actually used.

[0100] Back to Figure 5 . After step S90, the position estimation unit 120 estimates the type of the flying object using the speed and area change rate of the flying object (step S100). The speed and area change rate both represent the characteristics of the movement of the flying object. For example, when the flying object is a bird, the speed range is determined according to the species of the bird, and the movement of the feathers when flapping the wings and the characteristics of the movement when rotating change according to the species of the bird. Therefore, the position estimation unit 120 can determine the type of the flying object using the speed and area change rate. Here, when the flying object is an animal, the position estimation unit 120 preferably estimates the species. This process is equivalent to using Figure 2 Explanation (6).

[0101] If the second criterion is not satisfied (step S110: No), the position estimation unit 120 returns to step S30. This process is equivalent to using Figure 2 (7) of the description. Here, the second criterion is, for example, any one of the following (a) and (b).

[0102] (a) The loop of steps S30 to S110 is repeated a preset number of times.

[0103] This standard is suitable for a case where the processing by the position estimating unit 120 needs to be performed quickly to a certain extent.

[0104] (b) The difference between the estimated position of the flying object at the first timing and the future position of the flying object generated before the first timing (the position where the flying object is expected to be at the first timing) is equal to or smaller than a reference value.

[0105] This reference indicates that the difference between the predicted result of the future position (equivalent to the future position generated before the first timing mentioned above) and the measured value (equivalent to the estimated position at the first timing mentioned above) is equal to or less than the reference value, indicating that the accuracy is sufficiently high.

[0106] In addition, it is preferable that the above-mentioned second reference can be switched according to an input from a user, for example.

[0107] Then, when the type of the flying object estimated in step S100 is an animal, the control unit 130 reads the sound data corresponding to the species of the animal from the storage unit 140. In addition, the control unit 130 makes the speaker 40 face the future position determined in step S90. And the control unit 130 outputs the sound data read from the storage unit 140 from the speaker 40 (step S120). At this time, the control unit 130 controls the timing of emitting the sound so that the sound reaches the future position at the timing when the flying object is expected to reach the future position.

[0108] In addition, if you use Figure 1 As described above, the sound output from the speaker 40 is a sound for conveying a certain information to the animal. When the animal recognizes the information contained in the sound, it changes its moving direction according to the information. As a result, the animal will not invade an area that it should not invade. At this time, it is not necessary to intimidate the animal by the volume of the sound. Therefore, the volume of the sound emitted from the speaker 40 can be smaller than that of the prior art.

[0109] As described above, according to this embodiment, even a single camera can estimate the position and future position of a flying object. In addition, when the flying object is an animal such as a bird, even if the sound output by the speaker 40 is small, the animal can be prevented from intruding into an area that should not be intruded.

[0110] (Variation)

[0111] Fig.12 1 is a diagram for explaining the use environment of the position estimation device 10 involved in this modification. In the above-mentioned embodiment, the position estimation device 10 is used together with one camera 30. In this modification, the position estimation device 10 is used together with a plurality of camera devices 30, preferably three or more camera devices 30. The plurality of camera devices 30 are arranged separately from each other, and the object space (or object area) is included in the imaging range. That is, the plurality of camera devices 30 capture the object space from different directions.

[0112] It is preferable that all of the plurality of imaging devices 30 are single-lens cameras, so that the cost of the imaging devices 30 can be reduced.

[0113] Furthermore, the image acquisition unit 110 of the position estimation device 10 acquires multiple images from the multiple camera devices 30, and the position estimation unit 120 of the position estimation device 10 calculates information representing the estimated position of the flying object for each of the multiple camera devices 30, and uses the information from each of the camera devices 30 to determine the estimated position of the flying object.

[0114] An example of information indicating the estimated position of a flying object is to use Fig.10In this case, the position estimating unit 120 performs processing for calculating the rotation radius for each of the plurality of imaging devices 30. Then, the position estimating unit 120 determines the estimated position of the flying object using the calculation results of the plurality of rotation radii.

[0115] Fig.13 This is a diagram for explaining an example of a method for determining the estimated position of a flying object by the position estimating unit 120. In the example shown in this figure, the position estimating unit 120 calculates the rotation radius for each of the plurality of camera devices 30. Furthermore, the position estimating unit 120 draws a circle with the position of the camera device 30 as the center and the rotation radius corresponding to the camera device 30 as the radius for each of the plurality of camera devices 30. Furthermore, the position estimating unit 120 estimates that the flying object exists at a location where these plurality of circles overlap.

[0116] Alternatively, the position estimating unit 120 may calculate the position of the flying object in real space for each of the plurality of imaging devices 30 using the distance calculated in step S30 and the position of the flying object in the image, and may use the average of these calculation results as the estimated position of the flying object.

[0117] In addition, the position estimation unit 120 may calculate the position of each of the plurality of imaging devices 30. Fig. 9 The estimated moving paths in the form of strips are shown, and the flying object is estimated to exist in the overlapping area of ​​these multiple estimated moving paths, thereby determining the estimated moving path actually used. In this case, since the accuracy of the estimated moving path is improved, the estimation accuracy of the future position of the flying object is also improved.

[0118] Then, the position estimating unit 120 specifies the trajectory of the flying object using the change in the estimated position, and estimates the future position using the trajectory. Then, the control unit 130 directs the speaker 40 toward the future position, and then emits a sound from the speaker 40 .

[0119] According to the present embodiment, the position estimation device 10 estimates the position of the flying object using the images captured by the plurality of imaging devices 30. Therefore, the estimation accuracy of the position of the flying object is improved. In addition, the plurality of imaging devices 30 can all use single-lens cameras. Therefore, the cost of the imaging devices 30 can be reduced and the estimation accuracy of the position of the flying object can be improved.

[0120] As mentioned above, although embodiment of this invention was described with reference to drawings, these are illustrations of this invention, and various structures other than the above-mentioned can also be adopted.

[0121] In addition, in the multiple flow charts used in the above description, multiple steps (processes) are recorded in sequence, but the execution order of the steps executed in each embodiment is not limited to the order of the records. In each embodiment, the order of the steps shown in the figure can be changed within the scope that does not hinder the content. In addition, the above embodiments can be combined within the scope that the contents are not contradictory.

[0122] -Explanation of symbols-

[0123] 10 Position estimation device

[0124] 20 Structure

[0125] 30 Camera device

[0126] 40 Speakers

[0127] 110 Image acquisition unit

[0128] 120 Position estimation unit

[0129] 130 Control Department

[0130] 140 Storage unit.

Claims

1. A position estimation device comprising: an image acquisition unit that acquires a plurality of images generated by an imaging device that captures a space in which the flying object flies, that is, a target space; and a position estimating unit that estimates the position of the flying object by processing the plurality of images; The position estimation unit performs the following processing: (1) Temporarily set the type of the flying object, (2) determining three or more images arranged in time series as a target image group, (3) for each of the plurality of images included in the target image group, estimating the distance from the imaging device to the flying object using the temporarily set type and the area of ​​the flying object in the image belonging to the target image group, (4) calculating a change rate of the area of ​​the flying object between the plurality of images included in the target image group, (5) estimating the speed of the flying object using the distance to the flying object in each of the plurality of images included in the target image group and the position in the image; (6) using the speed and the rate of change of the area, updating the type of the flying object; (7) using the type updated in (6), the processing of (2) to (6) is performed again until a given criterion is satisfied. Based on the position of the flying object in the image and the distance calculated based on the image, the estimated position of the flying object at the timing when the image was captured is indicated.

2. The position estimation device according to claim 1, wherein: In the above (3), the position estimating unit uses a focal length when the image capturing device generates the image.

3. The position estimation device according to claim 1 or 2, wherein: In the above (3), the position estimating unit calculates an average value of the areas between the image and at least one other image belonging to the target image group, and estimates the distance using the average value.

4. The position estimation device according to claim 3, wherein: In the above (3), the position estimating unit further estimates motion information as at least one of a rotation radius, an angular velocity, an acceleration, and an angular acceleration of the flying object. The position estimating unit estimates a future position of the flying object using the position, the speed, and the motion information of the flying object.

5. The position estimation device according to claim 4, wherein: After the position estimation unit has performed the processing of (1) to (6) at least once, each time the image acquisition unit acquires a new image, the target image group is updated in (2), and the updated target image group is subjected to (3), Between (5) and (6), The position estimating unit calculates a moving average of each of the position, the speed, and the motion information using the position, the speed, and the motion information of the flying object repeatedly calculated in (3). The position estimating unit estimates the future position using the moving average.

6. The position estimation device according to claim 4 or 5, wherein: The given reference is that a difference between the estimated position at a first timing and the future position at the first timing generated before the first timing is equal to or smaller than a reference value.

7. The position estimation device according to any one of claims 1 to 6, wherein: The target space is imaged by a plurality of the image capturing devices from different directions. The image acquisition unit acquires the plurality of images from the plurality of camera devices respectively. The position estimating unit calculates information indicating the position of the flying object for each of the plurality of imaging devices, and estimates the position of the flying object using the information.

8. The flying object estimating device according to any one of claims 1 to 7, wherein: The camera device is a single-lens camera.

9. The flying object position estimating device according to any one of claims 1 to 8, wherein: The given reference is optional.

10. A method for estimating a position, The computer performs the following processing: An image acquisition process of acquiring a plurality of images generated by an imaging device that captures a space in which the flying object flies, that is, a target space; and Position estimation processing, estimating the position of the flying object by processing the plurality of images, In the position estimation process, the computer executes the following processes: (1) Temporarily set the type of the flying object, (2) determining three or more images arranged in time series as a target image group, (3) for each of the plurality of images included in the target image group, estimating the distance from the imaging device to the flying object using the temporarily set type and the area of ​​the flying object in the image belonging to the target image group, (4) calculating a change rate of the area of ​​the flying object between the plurality of images included in the target image group, (5) estimating the speed of the flying object using the distance to the flying object in each of the plurality of images included in the target image group and the position in the image; (6) using the speed and the rate of change of the area, updating the type of the flying object; (7) using the type updated in (6), the processing of (2) to (6) is performed again until a given criterion is satisfied. Based on the position of the flying object in the image and the distance calculated based on the image, the estimated position of the flying object at the timing when the image was captured is indicated.

11. A procedure, Enable the computer to have the following functions: An image acquisition function for acquiring a plurality of images generated by a camera device for capturing a space in which the flying object flies, that is, a target space; and A position estimation function estimates the position of the flying object by processing the plurality of images. The position estimation function performs the following processing: (1) Temporarily set the type of the flying object, (2) determining three or more images arranged in time series as a target image group, (3) for each of the plurality of images included in the target image group, estimating the distance from the imaging device to the flying object using the temporarily set type and the area of ​​the flying object in the image belonging to the target image group, (4) calculating a change rate of the area of ​​the flying object between the plurality of images included in the target image group, (5) estimating the speed of the flying object using the distance to the flying object in each of the plurality of images included in the target image group and the position in the image; (6) using the speed and the rate of change of the area, updating the type of the flying object; (7) using the type updated in (6), the processing of (2) to (6) is performed again until a given criterion is satisfied. Based on the position of the flying object in the image and the distance calculated based on the image, the estimated position of the flying object at the timing when the image was captured is indicated.

Images