JP2023101515A - Imaging apparatus, imaging method, and imaging program - Google Patents

Abstract

To provide an imaging apparatus that provides one method for specifying a position of a subject, an imaging method, and an imaging program.SOLUTION: An imaging apparatus comprises: a fixed-point imaging part that generates image data by imaging a subject; a storage part that stores image position information in which position information indicating an actual position of the subject is associated with each pixel in which the subject of the image data exists when the subject exists in the image data imaged by the fixed-point imaging part; and a specification part that specifies the position of the new subject on the basis of image data in which a new subject exists and the image position information when the new subject is imaged by the fixed-point imaging part.SELECTED DRAWING: Figure 1

Description

The present invention relates to an imaging device, an imaging method, and an imaging program.

2. Description of the Related Art Conventionally, there is a technique of recognizing a subject based on an image captured by an imaging unit and obtaining the position and the like of the subject. Patent Document 1 describes that a difference image is created from two images captured by an imaging unit (a reference image that serves as a standard and an image that captures a subject), the subject is recognized from the difference image, and the position of the recognized subject is obtained based on the angle of view, installation angle, and installation position of the imaging unit.

JP 2016-181786 A

However, although Patent Document 1 describes obtaining the position of the subject based on the angle of view, installation angle, and installation position of the imaging unit, it does not describe how to specifically acquire the position of the object based on the angle of view, installation angle, and installation position of the imaging unit.
Conventionally, there is a case where an image of a subject is imaged by an imaging unit, and the position of the subject on the image based on the image data generated by the imaging unit is repeatedly associated with the actual position of the subject, and then the position of the subject newly imaged by the imaging unit is specified based on the association.

SUMMARY OF THE INVENTION An object of the present invention is to provide an imaging apparatus, an imaging method, and an imaging program that provide a technique for specifying the position of a subject.

An imaging device according to one aspect includes a fixed-point imaging unit that images a subject and generates image data, a storage unit that stores position information indicating the actual position of the subject when the subject exists in image data captured by the fixed-point imaging unit, and image position information in which image position information indicating the actual position of the subject is associated with each pixel of the image data where the subject exists, and a specifying unit that specifies the position of the new subject based on the image data in which the new subject is present and the image position information when the new subject is captured by the fixed-point imaging unit.

An imaging device of one aspect may include at least one of a power generation panel that receives light to generate power and a power supply, and the fixed-point imaging unit may be supplied with power from at least one of the power generation panel and the power supply.

In one aspect of the imaging device, the storage unit may further store a correspondence relationship between the subject and the feature of the subject, and based on the correspondence relationship obtained by learning the feature of the subject in advance, the feature of the subject may be extracted from an image based on the image data generated by the fixed-point imaging unit, and the recognition unit may further include a recognition unit that recognizes the subject from the extracted feature.

An imaging device of one aspect may include an acquisition unit that acquires image position information based on the height of a subject in image data captured by the fixed-point imaging unit and the angle of view of the fixed-point imaging unit.

In one aspect of the imaging device, the acquisition unit includes: a first acquisition unit that acquires in advance the height of the subject, the angle of view of the fixed-point imaging unit, and the width of the image captured by the fixed-point imaging unit; the second acquisition unit that, when the subject moves, acquires the number of pixels forming image data per 1 m based on the height of the subject acquired by the first acquisition unit; a fourth obtaining unit that obtains the actual width of the image at a predetermined position based on the width of the image obtained by the first obtaining unit and the number of pixels per meter obtained by the second obtaining unit; obtains a first distance that is the distance from the fixed point imaging unit to the center position in the image based on the actual width of the image that is obtained by the fourth obtaining unit and the angle of view that is obtained by the first obtaining unit; and obtains a second distance that is the distance from the ground to the center position. a sixth obtaining unit that obtains the angle between the ground and the center line in the imaging direction of the fixed-point imaging unit based on the first distance and the second distance obtained by the fifth obtaining unit; a seventh obtaining unit that obtains the height from the ground to the fixed-point imaging unit based on the first and second distances obtained by the fifth obtaining unit and the angle formed by the sixth obtaining unit; an eighth acquisition unit that acquires the position from the imaging position where the fixed-point imaging unit is arranged to the subject based on the angle acquired by the acquisition unit 6, and further acquires the image position information based on multiple acquisitions of the positions of the subject.

In one aspect of the imaging device, the acquisition unit may include a ninth acquisition unit that acquires the width ratio to the Y coordinate based on the width of the actual image acquired by the fourth acquisition unit at the reference position in the Y coordinate direction and the width at the predetermined position in the Y coordinate direction.

In one aspect of the imaging method, the computer performs a fixed-point imaging step of imaging a subject by the fixed-point imaging section and generating image data, a storing step of storing position information indicating the actual position of the subject in the storage section when the subject exists in image data captured by the fixed-point imaging section, and image position information in which the subject exists in correspondence with each pixel of the image data, and specifying the position of the new subject based on the image data in which the new subject exists and the image position information when the new subject is captured by the fixed-point imaging section. perform the specific steps to

In one aspect, the imaging program includes a fixed-point imaging function of imaging a subject by a fixed-point imaging unit to generate image data, a storage function of storing, in a storage unit, image position information indicating the actual position of the subject in the case where the subject exists in the image data imaged by the fixed-point imaging unit, in association with each pixel of the image data where the subject exists, and when a new subject is imaged by the fixed-point imaging unit, the position of the new subject is specified based on the image data in which the new subject exists and the image position information. and a specific function to implement.

The image capturing apparatus of one aspect stores image position information in advance in the storage unit, and when the fixed-point image capturing unit captures an image of the subject, the image capturing apparatus identifies the position of the subject based on the image position information.
Further, the imaging method and the imaging program of one aspect can achieve the same effect as the imaging apparatus of one aspect described above.

1 is a block diagram for explaining an imaging device according to an embodiment; FIG. FIG. 10 is a diagram for use in explaining a case of acquiring image position information; FIG. 4 is a diagram for explaining an example of an image captured by a fixed-point imaging section; FIG. It is a graph which shows the relationship between a Y-coordinate and the number of pixels. 7 is a graph for explaining an example of image position information; 4 is a graph showing the relationship between the Y coordinate and the width ratio of an image; 4 is a first flowchart for explaining an imaging method according to one embodiment; 4 is a second flow chart for explaining an imaging method according to one embodiment;

An embodiment of the present invention will be described below.
An image capturing apparatus according to an embodiment is configured to capture an image of a subject using a fixed-point image capturing section, and acquire the distance from the fixed-point image capturing section to the subject based on the recorded image of the subject. When the fixed-point imaging unit is arranged at a predetermined position, the imaging device, for example, makes a person walk within the imaging range of the fixed-point imaging unit, and identifies the position of the person (acquires image position information). As a result, even when a new subject is captured by the fixed-point imaging section, the imaging device identifies the position of the subject based on the image position information, that is, acquires the distance from the fixed-point imaging section to the subject in the image.

FIG. 1 is a block diagram for explaining an imaging device according to one embodiment.

The imaging device 1 includes a fixed-point imaging unit 11 , a storage unit 12 , an identification unit 13 , a recognition unit 14 and an acquisition unit 15 . The imaging device 1 also includes at least one of the power generation panel 16 and the power source 17 .

The fixed-point imaging section 11 images a subject and generates image data. That is, the fixed-point imaging unit 11 continuously generates a moving image or still images at predetermined time intervals. The fixed-point imaging unit 11 is arranged at a predetermined location and captures an image in a predetermined direction.
The fixed-point imaging unit 11 is installed on a pole or the like fixed to the ground, or installed on a movable tripod or the like. When the fixed-point imaging unit 11 is installed on a movable tripod or the like, it can be moved together with the tripod. As a result, the fixed-point imaging unit can be easily arranged at a user's desired location, and can be arranged at a desired location only for a period required by the user.
If there is distortion or the like in the image captured by the fixed-point imaging unit 11, it affects the positional accuracy when acquiring the position of the subject. For this reason, it is preferable that the fixed-point imaging section 11 use an imaging lens or the like that can obtain an image with relatively little distortion.

The fixed-point imaging unit 11 is powered by at least one of the power generation panel 16 and the power supply 17, for example.
The power generation panel 16 receives light and generates power. The power generation panel 16 may be a device that utilizes energy harvesting technology, i.e., a device that harvests energy from the surrounding environment and converts it into electrical power. As a specific example, the power generation panel 16 may be a solar panel. The power generated by the power generation panel 16 may be stored in, for example, a battery, and the fixed-point imaging unit 11 may be supplied with power from the battery.
The power source 17 is, for example, a primary battery, a secondary battery, or a commercial power source. When a primary battery or secondary battery is used as the power supply 17, the primary battery or secondary battery is arranged in the imaging device 1 so as to be replaceable. Further, when a secondary battery is used as the power source 17, the secondary battery may be arranged in the imaging device 1 so as to be rechargeable.
Note that the power generation panel 16 or the power source 17 may supply power to the storage unit 12 , the identification unit 13 , the recognition unit 14 and the acquisition unit 15 in addition to the fixed point imaging unit 11 .

The storage unit 12 stores a correspondence (learning model) that associates a subject with the characteristics of the subject. The correspondence relationship is used when the recognition unit 14 recognizes the subject. The correspondence is generated by deep learning or the like, for example. That is, the correspondence relationship is generated by learning the features of the subject based on deep learning or the like, and by associating the relationship between the subject and the features of the subject. The subject that is used when generating the correspondence is not the subject that is constantly photographed by the fixed-point imaging unit (“new subject” described later), but the subject that is used only when generating the correspondence (learning model). The correspondence is generated by the recognition unit 14 and stored in the storage unit 12, for example. Alternatively, the correspondence may be generated by another device (not shown). The correspondence generated by another device may be downloaded (stored) to the storage unit 12 via a recording medium such as an external memory or a communication network.

Further, the storage unit 12 stores image position information in which position information indicating the actual position of the object is associated with each pixel of the image data where the object exists when the object exists in the image data captured by the fixed-point imaging unit 11. A method of generating image position information will be described later.

When a subject is recorded in the image data generated by the fixed-point imaging section 11 , the recognition section 14 recognizes the subject based on the correspondence (learning model) stored in the storage section 12 . That is, the recognition unit 14 learns the features of the subject in advance and stores the correspondence (learning model) in the storage unit 12 . Based on the correspondence (learning model), the recognition unit 14 extracts features of the subject from the image based on the image data generated by the fixed-point imaging unit 11, and recognizes the subject from the extracted features.
For example, the recognition unit 14 learns features of the subject in advance by using deep learning or the like. The recognition unit 14 stores, in the storage unit 12, a relationship (correspondence relationship) in which the feature of the subject as a learning result is associated with the subject corresponding to the feature. In this case, the recognition unit 14 may learn in advance the features of the subject based on the subject included in the image data generated by the fixed-point imaging unit 11 . Further, the recognition unit 14 may recognize the subject by performing pattern matching, for example, instead of using deep learning.

The acquisition unit 15 acquires image position information in the image data based on the height of the subject recorded in the image data generated by the fixed-point imaging unit 11 and the angle of view of the fixed-point imaging unit 11 . That is, the acquiring unit 15 acquires information (image position information) regarding the position within the image based on the image captured by the fixed-point imaging unit 11 . Specifically, when the recognition unit 14 recognizes the subject based on the image data captured by the fixed-point imaging unit 11, the acquisition unit 15 acquires position information (image position information (information related to the distance from the fixed-point imaging unit 11 to the subject)) in the image captured by the fixed-point imaging unit 11 based on the height of the subject and the angle of view of the fixed-point imaging unit 11.

FIG. 2 is a diagram for use in explaining the acquisition of image position information.
FIG. 3 is a diagram for explaining an example of an image captured by a fixed-point imaging unit.
FIG. 4 is a graph showing the relationship between the Y coordinate and the number of pixels. The horizontal axis of FIG. 4 indicates the Y coordinate, and the vertical axis indicates the number of pixels per meter. Here, the depth direction in the image captured by the fixed-point imaging unit is the Y coordinate, and the width direction of the image is the X coordinate.
FIG. 5 is a graph for explaining an example of image position information. The horizontal axis in FIG. 5 indicates the Y coordinate, and the vertical axis indicates the distance from the position of the ground where the fixed-point imaging unit is arranged to an arbitrary Y coordinate position.
FIG. 6 is a graph showing the relationship between the Y coordinate and the width ratio of the image. The horizontal axis of FIG. 6 indicates the Y coordinate, and the vertical axis indicates the width ratio of the image.

Here, in FIG. 2, the Y-axis direction (Y-coordinate direction) is the depth direction. In FIG. 2, when the subject 110 at a predetermined position in the Y-axis direction (Y-coordinate direction) is imaged by the fixed-point imaging unit 11, the image at the predetermined position is denoted by reference numeral 100a. The width (size in the X-axis direction) of the image 100a is indicated by w. Assuming that the center position of the image 100a is denoted by Pc, the distance from the fixed-point imaging unit 11 to the center position Pc is defined as a first distance L1, and the distance from the center position Pc to the ground is defined as a second distance L2. The angle formed by the ground and a straight line from the fixed-point imaging unit 11 to the position corresponding to the ground in the image 100a along the Y-axis direction is denoted by θ. Further, let H be the height of the fixed-point imaging unit 11 from the ground, P0 be the ground position where the fixed-point imaging unit 11 is arranged, and the third distance L3 be the distance from the ground position P0 to the image 100a along the Y-axis direction.
The acquisition unit 15 acquires the third distance L3, and associates the third distance L3 with the position in the image captured by the fixed-point imaging unit 11, thereby acquiring image position information.

Specifically, as shown in FIG. 1, the obtaining unit 15 includes a first obtaining unit 151, a second obtaining unit 152, a third obtaining unit 153, a fourth obtaining unit 154, a fifth obtaining unit 155, a sixth obtaining unit 156, a seventh obtaining unit 157, an eighth obtaining unit 158, and a ninth obtaining unit 159.

The first acquisition unit 151 acquires in advance the height of the subject, the angle of view of the fixed-point imaging unit 11 , and the width of the image captured by the fixed-point imaging unit 11 .
To acquire the image position information, first, the subject 110 is moved within the imaging range of the fixed-point imaging section 11 . Subject 110 is, for example, a person. When the subject 110 is a person, for example, the height of the person (the height of the subject) is input using an input device (not shown). The first acquisition unit 151 acquires the input height of the person.
Also, the first acquisition unit 151 acquires the angle of view θ2 captured by the fixed-point imaging unit 11 . The angle of view θ2 is input using, for example, an input device (not shown). The first acquisition unit 151 acquires the input angle of view θ2. The angle of view θ2 is determined by the planar size of the imaging element (not shown) of the fixed-point imaging section 11, the focal length of the imaging lens (not shown) of the fixed-point imaging section 11, and the like.
Also, the first obtaining unit 151 obtains the width of the image obtained by the fixed-point imaging unit 11 (for example, the number of pixels). The width of the image (image width) is input using, for example, an input device (not shown).

The second acquisition unit 152 acquires the number of pixels forming the image data per 1 m based on the height of the subject acquired by the first acquisition unit 151 .
The second acquisition unit 152 acquires the number of pixels per 1 m in the image captured by the fixed-point imaging unit 11 at any position in the image by making the subject (person) 110 walk within the imaging range. That is, the second acquisition unit 152 acquires the size (length) of 1 m in the image 100a based on the height of the person acquired by the first acquisition unit 151, and further acquires the number of pixels of the image per the acquired size of 1 m.
In the case illustrated in FIG. 3, the size of the imaging device (the image obtained by the fixed-point imaging section 11) used for the fixed-point imaging section 11 is 1280 pixels×960 pixels. When the subject 110 (not shown in FIG. 3) is recorded in the image illustrated in FIG. 3, the second acquisition unit 152 acquires the number of pixels per 1 m size based on the height of the subject 110 and the number of pixels of the imaging device (image).

The third acquisition unit 153 acquires the relationship between the Y coordinate, which is the coordinate in the depth direction of the image based on the image data, and the number of pixels per meter of the object acquired by the second acquisition unit 152 .
In the case of FIG. 3, the vertical direction of the image corresponds to the depth direction of the real space, and the vertical coordinate of the image is the Y coordinate. Also, in the case of FIG. 3, the horizontal direction of the image corresponds to the width direction of the real space, and the horizontal coordinate of the image is the X coordinate. Assuming that the upper left pixel in FIG. 3 has coordinates (0, 0) of the origin, the coordinates of the upper right pixel are (1280, 0). The coordinates of the pixel at the center position in FIG. 3 are (640, 480). The coordinates of the lower left pixel in FIG. 3 are (0,960), and the coordinates of the lower right pixel are (1280,960).

For example, by making the subject (person) walk vertically and horizontally within the imaging range of the fixed-point imaging unit 11 (within the range surrounded by coordinates (0, 0), coordinates (1280, 0), coordinates (1280, 960), and coordinates (0, 960)), the third acquisition unit 153 acquires the number of pixels per 1 m at a plurality of Y coordinate positions.

As an example is shown in FIG. 4, the relationship between the Y coordinate acquired by the third acquisition unit 153 and the number of pixels per meter is linear. Here, as shown in FIG. 2, the numerical value of the Y coordinate increases as the fixed-point imaging unit 11 is approached. That is, as the Y coordinate increases (as the subject approaches the fixed-point imaging section 11), the number of pixels per meter increases. In other words, as the Y coordinate becomes smaller (as the subject moves away from the fixed-point imaging section 11), the number of pixels per meter decreases.

The fourth acquisition unit 154 acquires the actual width w of the image 100a in which the subject 110 is detected at the predetermined position based on the width of the image acquired by the first acquisition unit 151 and the number of pixels per meter acquired by the second acquisition unit 152.
As illustrated in FIG. 2, consider an image 100a at the Y coordinate position (predetermined position in the Y coordinate direction) where the subject 110 is present. Since the number of pixels in the width direction of the image captured by the fixed-point imaging unit 11 (1280 pixels in the example shown in FIG. 3) is obtained by the first obtaining unit 151, the fourth obtaining unit 154 obtains the actual length of the width w of the image 100a at the predetermined position of the Y coordinate based on the number of pixels per meter.

Based on the width w of the actual image acquired by the fourth acquisition unit 154 and the angle of view θ2 acquired by the first acquisition unit 151, the fifth acquisition unit 155 acquires a first distance, which is the distance from the fixed-point imaging unit 11 to the center position Pc in the image 100a, and acquires a second distance, which is the distance from the ground to the center position Pc.
The fifth acquisition unit 155 acquires the actual distance (first distance L1) from the fixed-point imaging unit 11 to the center position Pc of the image 100a based on the actual length of the width w of the image 100a at the predetermined position of the Y coordinate and the angle of view θ2 of the fixed-point imaging unit 11. In addition, the fifth acquisition unit 155 acquires the actual distance (second distance L2) from the center position Pc of the image 100a to the ground based on the number of pixels of the image, the number of pixels per 1 m, the actual length of the width w of the image 100a at a predetermined position of the Y coordinate, and the angle of view of the fixed-point imaging unit 11.

Based on the first distance L1 and the second distance L2 obtained by the fifth obtaining unit 155, the sixth obtaining unit 156 obtains the angle θ between the center line in the imaging direction of the fixed-point imaging unit 11 and the ground. That is, the sixth obtaining unit 156 obtains the angle θ between the ground and the fixed-point imaging unit 11 based on the first distance L1 and the second distance L2 obtained by the fifth obtaining unit 155 by using a trigonometric function.

The seventh obtaining unit 157 obtains the height H from the ground to the fixed-point imaging unit 11 based on the first distance L1 and the second distance L2 obtained by the fifth obtaining unit 155 and the angle θ obtained by the sixth obtaining unit 156. That is, the seventh acquisition unit 157 acquires the height H from the ground to the fixed-point imaging unit 11 based on the first distance L1, the second distance L2, and the angle θ by using a trigonometric function.

The eighth acquisition unit 158 acquires the position from the imaging position where the fixed-point imaging unit 11 is arranged to the object based on the height H from the ground to the fixed-point imaging unit 11 acquired by the seventh acquisition unit 157 and the angle θ formed by the sixth acquisition unit 156, and acquires the image position information based on acquiring a plurality of positions of the object.
That is, the eighth acquisition unit 158 acquires the distance L3 from the ground position P0 where the fixed-point imaging unit 11 is arranged to the predetermined position (image 100a) on the Y coordinate based on the height H from the ground to the fixed-point imaging unit 11 and the angle θ between the fixed-point imaging unit 11 and the ground. The eighth obtaining unit 158 obtains information (image position information) regarding the position within the image by associating the distance L3 with the Y coordinate at the predetermined position within the image. Further, the eighth acquisition unit 158 acquires image position information based on moving the subject 110 within the imaging range of the fixed-point imaging unit 11 and acquiring the distance from the ground position P0, where the fixed-point imaging unit 11 is arranged, to the subject (person) 110 at an arbitrary position within the imaging range. The eighth obtaining section 158 stores the image position information in the storage section 12 .

The image position information is information indicating the distance in meters from the fixed-point imaging unit 11 to the position (coordinates) of any pixel in the image captured by the fixed-point imaging unit 11 . As a specific example, the image position information is information that the pixel coordinates (640, 480) shown in FIG.

As shown in FIG. 5, the image position information is information indicating that as the Y coordinate increases, the distance from the ground position P0 where the fixed-point imaging unit 11 is arranged decreases. In other words, the image position information is information indicating that the distance from the ground position P0 where the fixed-point imaging section 11 is arranged increases as the Y coordinate decreases.

Here, the ninth acquiring unit 159 acquires the width ratio to the Y coordinate based on the width at the reference position in the Y coordinate direction and the width at the predetermined position in the Y coordinate direction among the actual widths w of each of the plurality of images acquired by the fourth acquiring unit 154.
That is, the fourth acquisition unit 154 acquires the actual width w of the image. At a position where the subject 110 does not exist (the Y coordinate corresponding to the position where no person is walking), the fourth acquisition unit 154 cannot acquire the actual width w of the image. Therefore, when the fourth obtaining unit 154 obtains the width w of the image at a plurality of positions of the Y coordinate, the ninth obtaining unit 159 calculates the width of the image at an arbitrary position of the Y coordinate based on the width w of the image at the plurality of positions. For example, the ninth acquisition unit 159 sets one of the widths of the plurality of images acquired by the fourth acquisition unit 154 as the width of the image at the reference position of the Y coordinate (reference width), and obtains the ratio (width ratio) between the width of the other images excluding the reference width among the widths of the plurality of images and the reference width. The ninth acquisition unit 159 obtains a ratio (width ratio) to the reference width based on each of the plurality of images acquired by the fourth acquisition unit 154 . A graph of this width ratio is shown in FIG.

As illustrated in FIG. 6, as the Y coordinate increases (as the distance from the fixed-point imaging unit 11 decreases), the width ratio of the image decreases. In other words, the width ratio of the image increases as the Y coordinate decreases (as the distance from the fixed-point imaging section 11 increases).

Even at a position where the image width w is not acquired by the fourth acquisition unit 154, the fifth acquisition unit 155 described above can acquire the width of the image at an arbitrary Y coordinate by using the width ratio of the image acquired by the ninth acquisition unit 159, and therefore can acquire the first distance L1 and the second distance L2.
This completes the acquisition of the image position information.

Next, in the position measurement of the subject after acquiring the image position information, when a new subject is imaged by the fixed-point imaging section 11, the specifying unit 13 specifies the position of the new subject based on the image data in which the new subject exists and the image position information. That is, when a new subject is imaged by the fixed point imaging section 11, the specifying section 13 specifies the position of the new subject based on the position (Y coordinate) of the subject in the image and the image position information. The specifying unit 13 specifies the distance from the ground position where the fixed-point imaging unit 11 is arranged to the new subject as specifying the position of the new subject.
More specifically, when a new subject is recorded in the image captured by the fixed-point imaging section 11, the identifying section 13 acquires the position (pixel position (coordinates)) of the subject in the image. The identifying unit 13 identifies the distance from the fixed-point imaging unit 11 to the new subject by comparing the acquired pixel position of the new subject with the image position information.

Each part of such an imaging device 1 may be implemented as one function of a processing device arranged in a computer. That is, one function may be realized by executing a program on a computer. The program may be recorded in a recording medium such as an external memory or an optical disc, for example.

Next, an imaging method according to one embodiment will be described.

First, a method for acquiring image position information will be described.
FIG. 7 is a first flowchart for explaining an imaging method according to one embodiment.

In step ST11, the fixed-point imaging section 11 images an object.

In step ST12, the recognition unit 14 extracts the features of the subject imaged in step ST11 based on the results of pre-learning, and recognizes the subject based on the extraction results.

In step ST13, the acquisition unit 15 acquires image position information based on the height of the subject imaged in step ST11, ie, the height of the subject recognized in step ST12, and the angle of view of the fixed-point imaging unit 11.
That is, the acquisition unit 15 performs the following processing using the first to ninth acquisition units 151-159.
The first acquisition unit 151 acquires in advance the height of the subject, the angle of view of the fixed-point imaging unit 11 , and the width of the image differentially captured by the fixed-point imaging unit 11 .
The second acquisition unit 152 acquires the number of pixels per meter based on the height of the object acquired by the first acquisition unit 151 when the subject moves.
The third acquisition unit 153 acquires the relationship between the Y coordinate, which is the coordinate in the depth direction of the image, and the number of pixels per meter of the subject acquired by the second acquisition unit 152 .
The fourth acquisition unit 154 acquires the actual image width w at the predetermined position based on the width of the image acquired by the first acquisition unit 151 and the number of pixels per 1 m acquired by the second acquisition unit 152 .
The fifth acquisition unit 155 acquires a first distance L1, which is the distance from the fixed-point imaging unit 11 to the center position Pc in the image, and a second distance L2, which is the distance from the ground to the center position Pc, based on the actual image width w acquired by the fourth acquisition unit 154 and the angle of view θ2 acquired by the first acquisition unit 151.
Based on the first distance L1 and the second distance L2 obtained by the fifth obtaining unit 155, the sixth obtaining unit 156 obtains the angle θ between the ground and the center line (line along the Y-axis direction) in the imaging direction of the fixed-point imaging unit 11.
The seventh obtaining unit 157 obtains the height H from the ground to the fixed-point imaging unit 11 based on the first distance L1 and the second distance L2 obtained by the fifth obtaining unit 155 and the angle θ obtained by the sixth obtaining unit 156.
The eighth acquisition unit 158 acquires the position from the imaging position where the fixed-point imaging unit 11 is arranged to the subject based on the height H from the ground to the fixed-point imaging unit 11 acquired by the seventh acquisition unit 157 and the angle θ formed by the sixth acquisition unit 156, and acquires image position information.
Here, the ninth acquiring unit 159 may acquire the width ratio for the Y coordinate based on the width of the image acquired by the fourth acquiring unit 154 at the reference position in the Y coordinate direction and the width at the predetermined position in the Y coordinate direction.

In step ST<b>14 , the acquisition unit 15 stores the image position information acquired in step ST<b>13 in the storage unit 12 .

Next, a method of measuring the distance to the subject using the fixed point imaging section 11 will be described.
FIG. 8 is a second flowchart for explaining the imaging method according to one embodiment.

In step ST21, the fixed-point imaging section 11 images a subject.

In step ST22, the recognition unit 14 extracts the features of the subject imaged in step ST21 based on the results of pre-learning, and recognizes the subject based on the extraction results.

In step ST23, the specifying unit 13 specifies the position of the subject imaged in step ST21, that is, when the subject is recognized in step ST22. That is, the specifying unit 13 acquires the distance from the ground position where the fixed-point imaging unit 11 is arranged to the subject based on the Y coordinate in the image of the subject recognized by the recognition unit 14 and the image position information stored in the storage unit 12.

According to this embodiment, the following effects are obtained.
The imaging device 1 includes a fixed-point imaging unit 11 that captures an image of a subject and generates image data, a storage unit 12 that stores image position information, and a specifying unit 13 that specifies the position of the subject based on the image data generated by the fixed-point imaging unit 11 and the image position information stored in the storage unit 12.
Thereby, the imaging device 1 can acquire the position of the subject (the distance to the subject).
Also, the imaging device 1 acquires the distance to the subject based on the image position information stored in the storage unit 12 . Therefore, the imaging apparatus 1 of the present embodiment can acquire the distance to the subject by a method different from the conventional method of obtaining the distance to the subject by using parallax with a stereo camera. Since the imaging apparatus 1 of the present embodiment can be realized with one imaging system (imaging lens and imaging element), the configuration of the fixed-point imaging unit 11 can be simplified compared to the case of using a conventional stereo camera (two imaging systems).
Further, the imaging device 1 acquires image position information through computer processing, and acquires the distance to the subject based on the image position information. Therefore, unlike the conventional method, the imaging apparatus 1 of the present embodiment does not need to repeatedly perform the work of associating the position of the subject in the image with the actual distance to the subject.

In the imaging device 1 , the fixed-point imaging section 11 may be powered by at least one of the power generation panel 16 and the power source 17 .
By supplying power to the fixed-point imaging unit 11 from the power generation panel 16, the imaging device 1 can operate even in places where commercial power is not provided. In addition, since the fixed-point imaging unit 11 is supplied with power from the power source 17, the imaging apparatus 1 can obtain stable power supply.

The imaging device 1 may include a recognition unit 14 that learns the characteristics of the subject in advance, extracts the characteristics of the subject from the image based on the image data generated by the fixed-point imaging unit 11, and recognizes the subject from the extracted characteristics based on the result of the learning.
As an example, the imaging device 1 recognizes the subject using deep learning or the like, so if the correspondence relationship is stored in the storage unit 12, the subject can be recognized even when a relatively low-performance CPU (Central Processing Unit) is used.
When the imaging device 1 uses a relatively low-performance CPU, the price of the imaging device 1 can be made relatively low.
In addition, of course, the imaging apparatus 1 may use a relatively medium-performance or high-performance CPU. An example of a relatively low-to-medium performance CPU is a VPU (Visual Processing Unit) or the like. An example of a CPU with relatively medium performance is an FPGA (Field Programmable Gate Array) or the like. An example of a relatively medium to high performance CPU is a GPU (Graphics Processing Unit) or the like.

The imaging device 1 may include an acquisition unit 15 that acquires image position information based on the height of the subject in the image data captured by the fixed-point imaging unit 11 and the angle of view of the fixed-point imaging unit 11 .
The imaging device 1 can obtain image position information by calculation by inputting the height of the subject and the angle of view of the fixed-point imaging unit 11 .

In the imaging device 1, the acquisition unit 15 includes: a first acquisition unit 151 that acquires in advance the height of the subject, the angle of view of the fixed-point imaging unit 11, and the width of the image captured by the fixed-point imaging unit 11; the second acquisition unit 152 that acquires the number of pixels per meter based on the height of the subject acquired by the first acquisition unit 151; a third acquisition unit 153 that acquires the relationship; a fourth acquisition unit 154 that acquires the actual image width at a predetermined position based on the width of the image acquired by the first acquisition unit 151 and the number of pixels per meter acquired by the second acquisition unit 152; A fifth acquisition unit 155 that acquires the first distance and a second distance that is the distance from the ground to the center position; a sixth acquisition unit 156 that obtains an angle θ between the ground and the center line in the imaging direction of the fixed-point imaging unit 11 based on the first distance and the second distance acquired by the fifth acquisition unit 155; A seventh acquisition unit 157 that acquires the height to the unit 11, and an eighth acquisition unit 158 that acquires the position from the imaging position where the fixed-point imaging unit 11 is arranged to the subject based on the height from the ground to the fixed-point imaging unit 11 acquired by the seventh acquisition unit 157 and the angle formed by the sixth acquisition unit 156, and acquires the image position information.
The imaging device 1 can acquire the image position information based on the height of the subject and the angle of view of the fixed-point imaging section 11 by performing processing by the first to eighth acquisition sections 151 to 158, respectively.

In the imaging device 1, the acquisition unit 15 may include a ninth acquisition unit 159 that acquires the width ratio to the Y coordinate based on the width of the actual image acquired by the fourth acquisition unit 154 at the reference position in the Y coordinate direction and the width at the predetermined position in the Y coordinate direction.
The imaging device 1 can acquire the width of the image even at the Y-coordinate position where the subject (for example, a person) is not walking by acquiring the width ratio by the ninth acquisition unit 159 . Thereby, the imaging device 1 can acquire the distance to the subject at an arbitrary Y-coordinate position.

In the imaging method, the computer performs a fixed-point imaging step of imaging a subject by the fixed-point imaging section 11 to generate image data, a storage step of storing, in the storage section 12, image position information indicating the actual position of the subject when the subject exists in the image data captured by the fixed-point imaging section 11, and image position information associated with each pixel of the image data where the subject exists, and when a new subject is imaged by the fixed-point imaging section 11, based on the image data in which the new subject exists and the image position information. and an identifying step of identifying the position of the subject.
Thereby, the imaging method can acquire the position of the subject (the distance to the subject).
Also, the imaging method acquires the distance to the subject based on the image position information stored in the storage unit 12 . Therefore, the imaging apparatus 1 of this embodiment can acquire the distance to the subject by a method different from the conventional method.

The imaging program includes a fixed-point imaging function of imaging a subject by the fixed-point imaging section 11 to generate image data, a storage function of storing, in the storage section 12, image position information indicating the actual position of the subject when the subject exists in the image data captured by the fixed-point imaging section 11, and image position information associated with each pixel of the image data where the subject exists, and when a new subject is imaged by the fixed-point imaging section 11, the image data in which the new subject exists and the image position information. and a specifying function for specifying the position of a subject.
Thereby, the imaging program can acquire the position of the subject (the distance to the subject).
Also, the imaging program acquires the distance to the subject based on the image position information stored in the storage unit 12 . Therefore, the imaging apparatus 1 of this embodiment can acquire the distance to the subject by a method different from the conventional method.

1 Imaging device 11 Fixed point imaging unit 12 Storage unit 13 Identification unit 14 Recognition unit 15 Acquisition unit 151 First acquisition unit 152 Second acquisition unit 153 Third acquisition unit 154 Fourth acquisition unit 155 Fifth acquisition unit 156 Sixth acquisition unit 157 Seventh acquisition unit 158 Eighth acquisition unit 159 Ninth acquisition unit 16 Power generation panel 17 Power supply

Claims (8)

a fixed-point imaging unit that captures an image of a subject and generates image data;
a storage unit for storing image position information obtained by associating, when an object exists in the image data captured by the fixed point imaging unit, position information indicating an actual position of the object with each pixel of the image data where the object exists;
a specifying unit that specifies the position of the new subject based on the image data in which the new subject exists and the image position information when the new subject is imaged by the fixed-point imaging unit;
An imaging device comprising: At least one of a power generation panel and a power supply that receives light and generates power,
The imaging device according to claim 1, wherein the fixed-point imaging unit is powered by at least one of the power generation panel and the power supply. The storage unit further stores a correspondence relationship that associates a subject with features of the subject,
The imaging apparatus according to claim 1 or 2, further comprising a recognition unit that extracts features of a subject from an image based on image data generated by the fixed-point imaging unit and recognizes the subject from the extracted features, based on the correspondence relationship that is a result of learning the features of the subject in advance. The imaging device according to any one of claims 1 to 3, comprising an acquisition unit that acquires the image position information based on the height of the subject in the image data captured by the fixed-point imaging unit and the angle of view of the fixed-point imaging unit. The acquisition unit
a first acquisition unit that acquires in advance the height of the subject, the angle of view of the fixed-point imaging unit, and the width of the image captured by the fixed-point imaging unit;
a second obtaining unit that obtains the number of pixels constituting image data per meter based on the height of the subject obtained by the first obtaining unit when the subject moves;
a third acquiring unit for acquiring a relationship between a Y coordinate, which is a coordinate in the depth direction of an image based on image data, and the number of pixels per meter of the subject acquired by the second acquiring unit;
a fourth obtaining unit that obtains an actual image width at a predetermined position based on the width of the image obtained by the first obtaining unit and the number of pixels per meter obtained by the second obtaining unit;
a fifth acquisition unit that acquires a first distance that is the distance from the fixed-point imaging unit to the center position in the image based on the width of the actual image acquired by the fourth acquisition unit and the angle of view that is acquired by the first acquisition unit, and acquires a second distance that is the distance from the ground to the center position;
a sixth obtaining unit that obtains an angle between the ground and a center line in the imaging direction of the fixed-point imaging unit based on the first distance and the second distance that are obtained by the fifth obtaining unit;
a seventh acquisition unit that acquires the height from the ground to the fixed-point imaging unit based on the first distance and the second distance acquired by the fifth acquisition unit and the angle formed by the sixth acquisition unit;
an eighth acquisition unit that acquires a position from an imaging position where the fixed-point imaging unit is arranged to an object based on the height from the ground to the fixed-point imaging unit acquired by the seventh acquisition unit and the angle formed by the sixth acquisition unit, and further acquires the image position information based on acquiring a plurality of positions of the object;
The imaging device according to claim 4, comprising: 6. The imaging apparatus according to claim 5, wherein the obtaining unit includes a ninth obtaining unit that obtains a width ratio with respect to the Y coordinate based on a width of the actual image obtained by the fourth obtaining unit at a reference position in the Y coordinate direction and a width at a predetermined position in the Y coordinate direction. the computer
a fixed-point imaging step of imaging a subject by a fixed-point imaging unit and generating image data;
a storage step of storing, in a storage unit, image position information obtained by associating position information indicating the actual position of the subject with each pixel of the image data where the subject exists when the subject exists in the image data captured by the fixed-point imaging unit;
a specifying step of specifying a position of a new subject based on image data in which the new subject exists and image position information when a new subject is imaged by the fixed-point imaging unit;
An imaging method that performs to the computer,
a fixed-point imaging function for imaging a subject by a fixed-point imaging unit and generating image data;
a storage function of storing, in a storage unit, image position information obtained by associating position information indicating an actual position of the subject with each pixel of the image data where the subject exists when the subject exists in the image data captured by the fixed-point imaging unit;
a specifying function of specifying a position of a new subject based on image data in which the new subject exists and image position information when the fixed point imaging unit captures an image of the new subject;
An imaging program that realizes

Images