Patent Application
20240221203
The present technology relates to a measuring device, a measurement method, a program, and more particularly, to a technology of measuring a target object in water.
There has been proposed a measuring device that irradiates phytoplankton with light of a predetermined wavelength to excite it and measures the intensity of fluorescence emitted from the excited phytoplankton to measure the abundance of the phytoplankton (see, for example, Patent Document 1).
The measuring device described above can only measure phytoplankton excited by excitation light. Furthermore, the measuring device can measure the abundance of the phytoplankton, but cannot measure information regarding its position.
Therefore, a purpose of the present technology is to efficiently measure information regarding the position of a target object.
A measuring device according to the present technology includes an imaging control unit configured to cause an imaging unit to capture an image of a predetermined imaging range in water, and a measurement unit configured to measure information regarding a position of a target object in an imaging direction on the basis of the image captured by the imaging unit.
Thus, the measuring device can measure information regarding the position of the target object in the imaging direction without having a complicated configuration.
Hereinafter, embodiments will be described in the following order.
First, a configuration of a measuring device 1 as a first embodiment according to the present technology will be described.
The measuring device 1 is a device that treats microorganisms or fine particles present in water such as in the sea as a target object, and measures information regarding the position of the target object in an imaging direction.
Here, the microorganisms as the target object are water microorganisms such as phytoplankton, zooplankton, larvae of aquatic organisms present in water.
Furthermore, the fine particles as the target object are micro plastics, dust, sand, marine snow, air bubbles, or the like. Note, however, that these are examples, and the target object may be other than these.
Furthermore, the information regarding the position of the target object in the imaging direction is, for example, a distance to the target object or a speed of the target object in the imaging direction (Z-axis direction in
As illustrated in
The main body portion 2 includes a control unit 10, a memory 11, a communication unit 12, a gravity sensor 13, an imaging unit 14, and a lens 15.
The control unit 10 includes, for example, a microcomputer including a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM). The control unit 10 performs the overall control of the measuring device 1. In the first embodiment, the control unit 10 functions as an imaging control unit 21, a class identification unit 22, and a distance/speed measurement unit 23. Note that the imaging control unit 21, the class identification unit 22 and the distance/speed measurement unit 23 will be described in more detail below.
Furthermore, the control unit 10 performs processing of reading data stored in the memory 11, processing of storing data in the memory 11, and transmission and reception of various kinds of data to and from an external device via the communication unit 12.
The memory 11 includes a non-volatile memory. The communication unit 12 performs wired or wireless data communication with an external device. The gravity sensor 13 detects gravitational acceleration (gravity direction) and outputs the detection result to the control unit 10. Note that the measuring device 1 may not include the gravity sensor 13.
The imaging unit 14 includes both or one of the vision sensor 14a and imaging sensor 14b. The vision sensor 14a is a sensor called a dynamic vision sensor (DVS) or an event-based vision sensor (EVS). The vision sensor 14a captures an image of a predetermined imaging range IR in water through the lens 15. Note that hereinafter, as illustrated in
The vision sensor 14a is an asynchronous image sensor that includes a plurality of pixels arranged two-dimensionally. Each pixel includes a photoelectric conversion device and a detection circuit that detects an address event in real time. Note that the address event is an event that occurs in accordance with an amount of incident light for each of addresses allocated respectively to the plurality of pixels arranged two-dimensionally. The address event is, for example, an event in which the value of a current based on a charge generated in the photoelectric conversion device or the variation thereof exceeds a certain threshold or the like.
The vision sensor 14a detects whether or not the address event occurs for each pixel. In a case where it is detected that the address event occurs, the vision sensor 14a reads a pixel signal as pixel data from the pixel in which the address event occurs. In other words, the vision sensor 14a acquires pixel data asynchronously in accordance with an amount of light incident on each of the plurality of pixels arranged two-dimensionally.
The vision sensor 14a performs an operation of reading a pixel signal on the pixel in which it is detected that the address event occurs. The vision sensor 14a may thus perform reading at an extremely high speed, compared to a synchronous image sensor that performs an operation of reading on all pixels at a predetermined frame rate, and may also read a small amount of data as one frame.
Therefore, the measuring device 1 may detect a motion of the target object more quickly using the vision sensor 14a. Furthermore, the vision sensor 14a may also reduce data amount and power consumption.
The imaging sensor 14b is, for example, a charge coupled device (CCD) or complementary metal-oxide-semiconductor (CMOS) image sensor. The imaging sensor 14b includes a plurality of pixels arranged two-dimensionally, each pixel including a photoelectric conversion device. The imaging sensor 14b captures an image of a predetermined imaging range IR through the lens 15 at certain intervals in accordance with a frame rate to generate image data. Note that the measuring device 1 may use a zone plate, a pinhole plate, or a transparent plate instead of the lens 15.
The vision sensor 14a and the imaging sensor 14b are arranged to capture an image of substantially the same imaging range IR through the lens 15. For example, a one-way mirror (not illustrated) is only required to be arranged between the vision and imaging sensors 14a and 14b and the lens 15 such that one part of light dispersed by the one-way mirror is incident on the vision sensor 14a and the other part is incident on the imaging sensor 14b.
The illumination unit 3 is driven on the basis of the control of the control unit 10, and irradiates the imaging range IR of the imaging unit 14 with light. The illumination unit 3 may switch and emit light of different wavelengths, and emits light of different wavelengths every 10 nm, for example.
As illustrated in
Moreover, it is known that some microorganisms exhibit cursoriality by being irradiated with light of a specific wavelength. Here, the cursoriality is an innate behavior of an organism reacting to light (external stimulus). Therefore, the microorganisms having cursoriality that is irradiated with light of a specific wavelength will move in accordance with the cursoriality.
The marine snow is, for example, a particle such as a discharge, a dead body, or a decomposition product thereof of a plankton present in the sea, and moves to sink in the sea (in the gravity direction).
The seabed sand is, for example, particles such as sand precipitating on the sea bed, and moves in a swirling manner by the sea bed flow.
The smoke is, for example, a phenomenon in which high temperature water heated by geothermal heat is ejected from a hydrothermal vent in the sea bed. Then, the hot water blown out of the hydrothermal vent may reach several hundred degrees. Since the hot water abundantly contains heavy metals and hydrogen sulfide as dissolved components, it reacts with seawater and provides black or white smoke that moves upward while swirling.
The air bubbles are, for example, natural gas such as methane and carbon dioxide leaking (ejecting) from the sea bed, or a carbon dioxide leaking from reservoir artificially injected in a carbon dioxide reserve (CCS), and the like, and move upward from the sea bed.
As described above, some target objects, not limited to microorganisms and even fine particles, move in a specific moving direction. Therefore, the measuring device 1 as the first embodiment identifies, as target objects, microorganisms and fine particles whose moving directions are known.
Next, a measurement method (measurement processing) for the target object as the first embodiment will be described.
The ocean is the aphotic zone which sunlight does not reach at a depth of about 150 m. The aphotic zone occupies most of the open ocean, and includes a lot of target objects described above. Meanwhile, it is known that the target object reflects or emits light of different wavelengths or intensities for each wavelength of the light that the object is irradiated with.
Therefore, on the assumption that the measurement is performed in the aphotic zone which sunlight does not reach, the measuring device 1 identifies the type of the target object by irradiating the target object with light of different wavelengths and capturing an image by the reflected light (or excitation light). Then, the measuring device 1 measures the distance and speed in the imaging direction for the target object whose type is identified.
The control unit 10 measures according to the measurement setting previously specified as illustrated in
The measurement start condition specifies a condition for starting the measurement, such as time to start the measurement or reception of the measurement start command that is input via the communication unit 12, and the like.
The operation time sheet specifies a time sheet for operating the illumination unit 3. For example, the operation time sheet illustrated in
As described above, the operation time sheet specifies that the imaging range IR is irradiated with light of what wavelength at what timing from the illumination unit 3. Note that the reason a timing is provided at which the illumination unit 3 is turned off, in other words, light is not emitted, is to capture an image of light when the target object is emitting light (being excited). Furthermore, having turn-off between each wavelength also has an effect that the asynchronous vision sensor 14a may easily detect an event for each wavelength.
The identification program specifies a program (method) for identifying the type of the target object, such as identification by machine learning, identification by rule base, and the like.
The distance/speed measurement program specifies a program (method) for measuring information regarding the position of the target object in the imaging direction, such as measurement by machine learning, measurement by rule base, and the like.
The measurement end condition specifies a condition for ending the measurement, such as time to end the measurement or reception of the measurement end command that is input via the communication unit 12, and the like.
In step S1, the control unit 10 reads external environment information as will be described in more detail below. Then, in step S2, the control unit 10 determines whether or not the measurement start condition specified in the measurement setting is satisfied. Then, the control unit 10 repeats steps S1 and S2 until the measurement start condition is satisfied.
Meanwhile, if the measurement start condition is satisfied (Yes in step S2), then in step S3, the imaging control unit 21 causes the illumination unit 3 to switch and emit light of different wavelengths according to the operation time sheet specified in the measurement setting. Furthermore, every time the wavelength and turn-on/off of light emitted from the illumination unit 3 are switched, the imaging control unit 21 causes the imaging unit 14 to capture an image of the imaging range IR and acquires pixel data and image data. Subsequently, in step S4, the class identification unit 22 performs the class identification processing.
In the class identification processing, the class identification unit 22 identifies (specifies) the type of the target object on the basis of the image (pixel data and image data) captured by the imaging unit 14. The class identification unit 22 derives identification information from the image captured by the imaging unit 14 and compares it with definition information stored in the memory 11 to detect the target object.
The definition information is provided for each target object and stored in the memory 11. The definition information includes the type of the target object, movement information, and image information.
The movement information is information that is detected mainly on the basis of the image captured by the vision sensor 14a and information based on movement of the target object as illustrated in the lower part of
The image information is information detected mainly on the basis of the image captured by the imaging sensor 14b and is external information of the target object. Note that the image information may be information detected on the basis of the image captured by the vision sensor 14a.
Furthermore, the definition information may include a gravity direction detected by the gravity sensor 13 and external environment information acquired via the communication unit 12. Note that the external environment information may include depth, position coordinate (latitude and longitude of the measurement point, plane rectangular coordinate), electrical conductivity, temperature, ph, concentration of gas (for example, methane, hydrogen, helium), concentration of metal (for example, manganese, iron), or the like.
The class identification unit 22 detects an object present in the imaging range IR on the basis of the image (pixel data) captured by the vision sensor 14a. For example, the class identification unit 22 creates one image (frame data) on the basis of pixel data that is input within a predetermined period. The class identification unit 22 then detects, as one object, a pixel group within a predetermined range in which a motion is detected in the image.
Furthermore, the class identification unit 22 tracks an object between a plurality of frames by pattern matching and the like. Then, on the basis of the tracking result of the object, the class identification unit 22 derives the moving direction, the speed, and the trajectory as the identification information.
Note that a cycle at which the class identification unit 22 generates an image from pixel data may be the same as or shorter than the cycle (frame rate) at which the imaging sensor 14b acquires image data.
Furthermore, with respect to the object from which the identification information is derived, the class identification unit 22 extracts an image portion corresponding to the object from the image data that is input from the imaging sensor 14b. Then, on the basis of the extracted image portion, the class identification unit 22 derives external characteristics as the identification information by image analysis. Note that the image analysis may be performed using known methods, and thus its description is omitted here.
The class identification unit 22 identifies which one the target object is by checking the wavelength of light emitted by the illumination unit 3 and the identification information (moving direction, trajectory, speed, external characteristics) derived for the detected object against the definition information according to the specified identification program. Here, for example, if the derived identification information of the object is within the range indicated in the definition information of the target object, then the class identification unit 22 identifies the derived object as the type indicated in the definition information.
These pieces of definition information are stored in the memory 11 by different methods for each identification program. For example, in the rule-based identification program, the definition information is preset by a user and stored in the memory 11. Furthermore, in the machine learning identification program, the definition information is generated and updated by machine learning in the learning mode, and stored in the memory 11.
Subsequently, the class identification unit 22 stores, in the memory 11, the identification result of the detected target object and the image captured by the imaging sensor 14b, and transmits them to an external device via the communication unit 12.
In step S5, the distance/speed measurement unit 23 performs distance/speed measurement processing of measuring the distance and speed of the target object in the imaging direction (information regarding the position of the target object) on the basis of the type of the target object identified by the class identification unit 22. Note that the distance/speed measurement processing in step S5 will be described in more detail below.
Subsequently, in step S6, the control unit 10 determines whether or not the measurement end condition is satisfied. Then, the control unit 10 repeats steps S1 to S6 until the measurement end condition is satisfied. If the ending condition is satisfied (Yes in step S6), then the control unit 10 ends the determination processing.
Next, the distance/speed measurement processing will be described. As described above, in step S5, the distance/speed measurement unit 23 performs distance/speed measurement processing on the basis of the rule-based or machine learning distance/speed measurement program.
Here, the rule-based distance/speed measurement processing and the distance/speed measurement processing in machine learning will be described with specific examples.
Furthermore, the memory 11 also stores statistical information (average size H) for each target object. This is previously registered by the user as a database.
Then, when the target object is identified from the image based on the pixel data, the distance/speed measurement unit 23 reads the average size H of the target object and the focal distance f of the vision sensor 14a from the memory 11. Subsequently, the distance/speed measurement unit 23 calculates the length s in the longitudinal direction of the image 42 of the target object that is captured on the imaging plane 40. This calculation is on the basis of, for example, the number of pixels in which the image 42 is captured.
Furthermore, the distance/speed measurement unit 23 calculates the distance D in the imaging direction (Z direction) from the measuring device 1 to the target object 41 using Formula (1).
In this manner, the distance/speed measurement unit 23 calculates (measures) the distance D from the measuring device 1 to the actual target object 41 every time the image based on the pixel data is acquired (every time the target object is detected from the image).
Furthermore, for the target object 41 tracked between consecutive images, the distance/speed measurement unit 23 calculates (measures) the speed in the imaging direction (Z-axis direction) on the basis of the interval at which the images are acquired and of the distance D in each image.
As described above, in the rule-based distance/speed measurement processing, the distance/speed measurement unit 23 measures information regarding the position of the target object on the basis of the statistical information (average size) for each target object.
The distance/speed measurement processing in machine learning performs machine learning using, for example, images that are training data as illustrated in
Specifically, images are previously prepared that are captured by the vision sensor 14a from a known target object. The images are provided in a total of 153 patterns including five patterns in which the distance from the measuring device 1 to the target object in the imaging direction is 1 mm, 5 mm, 10 mm, 100 mm, and 200 mm, multiplied by 31 patterns in which the wavelength of the emitted light is varied from 400 nm to 700 nm every 10 nm.
Then, for each of the prepared images, the distance/speed measurement unit 23 detects, as a target object, a pixel group within a predetermined range where a motion is detected and resizes the pixel group to 32 pixels by 32 pixels, thus generating images that are training data as illustrated in
Note that
Furthermore, as the distance from the measuring device 1 to the target object increases, the arrival factor of light decreases.
Therefore, as illustrated in
When the image as the training data is resized, the distance/speed measurement unit 23 applies machine learning to the training data including these images using a deep neural network, as illustrated in
Such machine learning using a deep neural network is performed for each target object, and a model is generated for each target object and stored in the memory 11.
Then, when the class identification unit 22 identifies the type of the target object (in step S4), the distance/speed measurement unit 23 reads a model of the identified type from the memory 11. Furthermore, the distance/speed measurement unit 23 resizes the target object portion in the image captured by the vision sensor 14a to 32 pixels by 32 pixels and inputs the resized image into the read model. Accordingly, the value of one-dimensional classification vector having five elements from Distance 1 mm to Distance 200 mm is output. Then, the distance/speed measurement unit 23 outputs (measures) the element having the highest value among the five elements (any one of Distance 1 mm to Distance 200 mm) as the distance of the target object in the imaging direction.
Furthermore, for the target object tracked between consecutive images, the distance/speed measurement unit 23 calculates (measures) the speed in the imaging direction (Z-axis direction) on the basis of the interval at which the images are acquired and the distance in the imaging direction in each image.
As described above, in the distance/speed measurement processing in machine learning, the distance/speed measurement unit 23 measures the information regarding the position of the target object on the basis of the learning result of the information regarding the position previously learned for each type of the target object.
Then, on the basis of the image captured by the vision sensor 14a, the measuring device 100 measures the distance to the target object in the imaging direction and the speed thereof without identifying the type of the target object.
The measurement start condition specifies a condition for starting the measurement, such as time to start the measurement or reception of the measurement start command that is input via the communication unit 12, and the like.
The operation time sheet specifies a time sheet for operating the illumination unit 3. For example, the operation time sheet illustrated in
The distance/speed measurement program specifies a program (method) for measuring information regarding the position of the target object in the imaging direction, such as measurement by machine learning, measurement by rule base, and the like.
The measurement end condition specifies a condition for ending the measurement, such as time to end the measurement or reception of the measurement end command that is input via the communication unit 12, and the like.
As described above, the measurement setting in the second embodiment is different from the measurement setting in the first embodiment in that the identification program is not provided.
In step S1, the control unit 110 reads external environment information. Then, in step S2, the control unit 10 determines whether or not the measurement start condition specified in the measurement setting is satisfied. Then, the control unit 110 repeats steps S1 and S2 until the measurement start condition is satisfied.
Meanwhile, if the measurement start condition is satisfied (Yes in step S2), then in step S3, the imaging control unit 21 causes the illumination unit 3 to switch and emit light of different wavelengths according to the operation time sheet specified in the measurement setting. Furthermore, every time the wavelength and turn-on/off of light emitted from the illumination unit 3 are switched, the imaging control unit 21 causes the imaging unit 14 to capture an image of the imaging range IR and acquires pixel data and image data.
Subsequently, in step S11, on the basis of the image based on the pixel data, the distance/speed measurement unit 23 detects the object present in the imaging range as the target object and performs distance/speed measurement processing of measuring the distance to the target object in the imaging direction and the speed thereof. Note that the distance/speed measurement processing in step S11 will be described in more detail below.
Subsequently, in step S6, the control unit 10 determines whether or not the ending condition for ending the determination processing is satisfied. Then, the control unit 10 repeats steps S1 to S6 until the ending condition for ending the determination processing is satisfied. If the ending condition for ending the purpose-specific measurement operation processing is satisfied (Yes in step S6), then the control unit 10 ends the determination processing.
As described above, in step S11, the distance/speed measurement unit 23 performs the distance/speed measurement processing on the basis of the rule-based or machine learning distance/speed measurement program. Here, the distance/speed measurement processing in machine learning will be described with specific examples.
The measuring device 100 creates a deep learning model as illustrated in
Here, in the first embodiment, the model is generated for each target object, while in the second embodiment, the model is not generated for each target object and only one model previously learned is generated regardless of the type of the target object.
Specifically, images are previously prepared that are captured by the vision sensor 14a. The images are provided in a total of 153 patterns multiplied by the number of types of different target objects. The 153 patterns include five patterns in which the distance from the measuring device 1 to the target object in the imaging direction is 1 mm, 5 mm, 10 mm, 100 mm, and 200 mm, multiplied by 31 patterns in which the wavelength of the emitted light is varied from 400 nm to 700 nm every 10 nm.
Then, for each of the prepared images, the distance/speed measurement unit 23 detects, as a target object, a pixel group within a predetermined range where a motion is detected and resizes the pixel group to 32 pixels by 32 pixels, thus generating images that are training data as illustrated in
When the image as the training data is resized, the distance/speed measurement unit 23 applies machine learning to the training data including these images using a deep neural network, as illustrated in
Then, the distance/speed measurement unit 23 resizes the target object portion in the image captured by the vision sensor 14a to 32 pixels by 32 pixels and inputs the resized image to the model that is read from the memory 11. Accordingly, the value of one-dimensional classification vector having five elements from Distance 1 mm to Distance 200 mm is output. Then, the distance/speed measurement unit 23 outputs (measures) the element having the highest value among the five elements (any one of Distance 1 mm to Distance 200 mm) as the distance of the target object in the imaging direction.
Furthermore, for the target object tracked between consecutive images, the distance/speed measurement unit 23 calculates (measures) the speed in the imaging direction (Z-axis direction) on the basis of the interval at which the images are acquired and the distance in the imaging direction in each image.
As described above, in the distance/speed measurement processing in machine learning, the distance/speed measurement unit 23 measures the information regarding the position of the target object on the basis of the learning result of the information regarding the position previously learned regardless of the type of the target object.
Therefore, the second embodiment uses a smaller number of models than the first embodiment and thus may reduce the data capacity. Furthermore, the second embodiment may decrease the calculation time while the distance measurement accuracy is reduced.
Note that the embodiments are not limited to the specific examples described above and may be configured as various modification examples.
In the embodiments described above, the measuring device 1 includes one illumination unit 3. However, the number of illumination units 3 is not limited to one, a plurality of illumination units 3 may be provided.
In such a measuring device 200, the two illumination units 3 may emit light of different wavelengths, and thus only one measurement may provide identification information of the target objects (microorganisms) that exhibit cursoriality for light of different wavelengths, thus providing an efficient measurement.
In such a measuring device 300, the two main body portions 2 (imaging units 14) may capture an image, and thus three-dimensional movement of the target object may be detected, thus providing a more efficient measurement.
Note that in a case where two main body portions 2 are provided, one of the main body portions 2 may include only the imaging unit 14.
Furthermore, in the embodiments described above, the imaging unit 14 includes the vision sensor 14a and the imaging sensor 14b. However, the imaging unit 14 may include only one of the vision sensor 14a or imaging sensor 14b as long as it may capture an image capable of measuring at least information regarding the position of the target object in the imaging direction. Furthermore, the imaging unit 14 may include a single photon avalanche diode (SPAD) sensor instead of the vision sensor 14a and imaging sensor 14b.
Furthermore, in the embodiments described above, the type of the target object is identified by deriving the identification information on the basis of the pixel data acquired by the vision sensor 14a and the image data acquired by the imaging sensor 14b. However, other methods may also be used for identification, if the type of the target object may be identified on the basis of at least one of the pixel data acquired by the vision sensor 14a and the image data acquired by the imaging sensor 14b.
Furthermore, in the described above embodiments, the machine learning is performed by deep learning. However, the method of machine learning is not limited thereto and the machine learning may be performed by other methods. Furthermore, the model generated by the machine learning may be created by an external device instead of the measuring device 1.
Meanwhile, in the vision sensor 14a, an address event occurs in each pixel due to a luminance change and a current value change that exceeds a certain threshold. Therefore, in a case where the target object TO is moving at extremely a low speed or not moving at all in the imaging range (hereinafter, these are collectively referred to as stopping), the address event does not occur in each pixel. Therefore, in such a case, the vision sensor 14a may not capture an image of the target object TO.
Therefore, in a case where the target object TO stops, the emission of light from the illumination unit 3 is temporarily stopped. Specifically, when the target object TO moves in the imaging range while the illumination unit 3 is emitting light as illustrated in the upper part of
Subsequently, when the target object TO stops, the address event does not occur in the vision sensor 14a and thus, as illustrated in
In a case where the target object TO may not be detected in the imaging range (in a case where the target object TO disappears in the imaging range), the imaging control unit 21 determines that the target object TO stops, the target object TO moves to the outside of the imaging range at a high speed, or the target object TO disappears. Then, the imaging control unit 21 temporarily stops the emission of light from the illumination unit 3 as illustrated in the middle part of
Furthermore, the imaging control unit 21 restarts the emission of light from the illumination unit 3, as illustrated in the lower part of
In this manner, in a case where the target object TO may not be detected in the imaging range, the emission of light from the illumination unit 3 is temporarily stopped. As a result, in a case where the target object TO is present in the imaging range, the target object TO appears in the image captured by the vision sensor 14a and thus the target object TO may be measured continuously.
Note that in a case where the target object TO may not be detected in the imaging range, the imaging control unit 21 may change the wavelength of light emitted from the illumination unit 3. Even changing the wavelength of light emitted from the illumination unit 3 may allow the vision sensor 14a to capture an image of the target object TO stopped in the imaging range.
For example, as illustrated in the upper part of
Meanwhile, when the target object TO stops in the imaging range, the address event does not occur in the vision sensor 14a, and thus the target object TO does not appear in the image captured by the vision sensor 14a.
In a case where the target object TO may not be detected in the imaging range, as illustrated in the lower part of
As described above, in modification example 2, similarly to modification example 1, the target object TO may be measured continuously.
Note that in a case where a plurality of illumination units 3 is not provided, the target object TO may be measured by moving the illumination unit 3 even when the target object TO is stopped, as in the case where a plurality of illumination units 3 is switched to emit light.
As described above, the measuring device 1 of the embodiments includes the imaging control unit 21 configured to cause the imaging unit 14 to capture an image of a predetermined imaging range in water, and the measurement unit (distance/speed measurement unit 23) configured to measure information regarding the position of the target object in then imaging direction on the basis of the image captured by the imaging unit 14.
Thus, the measuring device 1 may measure information regarding the position of the target object in the imaging direction without having a complicated configuration.
For example, it is also contemplated that two imaging units 14 provided in parallel are used as a stereo camera to measure information regarding the position of the target object in the imaging direction. However, in this method, the device becomes complicated and calibration of the two imaging units 14 becomes difficult.
In contrast, the measuring device 1 may efficiently measure information regarding the position of the target object.
In the measuring device 1 according to the present technology described above, it is contemplated that the imaging unit 14 includes a vision sensor 14a configured to acquire pixel data asynchronously in accordance with the amount of light incident on each of a plurality of pixels arranged two-dimensionally.
This makes it possible to read only the pixel data of the pixel in which the event occurs and measure the target object on the basis of the pixel data.
Therefore, the measuring device 1 may achieve high-speed imaging, power consumption reduction, and lower calculation cost of image processing by automatic separation from the background.
In the measuring device 1 according to the present technology described above, it is contemplated that the illumination unit 3 is provided that irradiates the imaging range with light of a predetermined wavelength and the imaging unit 14 captures an image of the imaging range irradiated with light of the predetermined wavelength by the illumination unit 3.
This makes it possible to capture only an image of reflected light or excitation light from the target object at a water depth where sunlight does not reach.
Therefore, the measuring device 1 may measure the target object efficiently.
In the measuring device 1 according to the present technology described above, it is contemplated that the illumination unit 3 may switch and emit light of different wavelengths and the imaging unit 14 captures an image of the imaging range irradiated with light of different wavelengths, respectively.
This makes it possible to capture an image of reflected light or excitation light that is different depending on the wavelength for each type of the target object.
Therefore, the measuring device 1 may acquire a characteristic image for each target object.
In the measuring device 1 according to the present technology described above, it is contemplated that the measurement unit measures the distance to the target object in the imaging direction.
This makes it possible to measure the distance to the target object in the imaging direction with a simple configuration without using a complicated configuration such as a stereo camera.
In the measuring device 1 according to the present technology described above, it is contemplated that the measurement unit measures the speed of the target object in the imaging direction.
This makes it possible to measure the speed of the target object in the imaging direction speed with a simple configuration without using a complicated configuration such as a stereo camera.
In the measuring device 1 according to the present technology described above, it is contemplated that the identification unit (class identification unit 22) is provided that identifies the type of the target object on the basis of the image captured by the imaging unit 14, and the measurement unit measures information regarding the position of the target object on the basis of the type of the target object identified by the identification unit.
This makes it possible to measure information regarding the position of the target object by a method (model) adapted for each type of the target object.
Therefore, the measuring device 1 may accurately measure information regarding the position of the target object in the imaging direction.
In the measuring device 1 according to the present technology described above, it is contemplated that the measurement unit measures information regarding the position of the target object on the basis of the statistical information for each type of the target object.
This makes it possible to measure information regarding the position of the target object in the imaging direction by a simple method.
In the measuring device 1 according to the present technology described above, it is contemplated that the measurement unit derives the information regarding the position of the target object on the basis of the learning result of information regarding the position previously learned for each type of the target object.
This makes it possible to accurately measure the information regarding the position of the target object in the imaging direction.
In the measuring device 1 according to the present technology described above, it is contemplated that the measurement unit derives the information regarding the position of the target object on the basis of the learning result of the information regarding the position previously learned regardless of the type of the target object.
This makes it possible to reduce data capacity and decrease calculation time.
In the measuring device 1 according to the present technology described above, it is contemplated that the imaging control unit 21 temporarily stops the emission of light from the illumination unit 3 in a case where the target object may not be detected in the imaging range.
This makes it possible to continuously measure the target object stopped in the imaging range.
In the measuring device 1 according to the present technology described above, it is contemplated that the imaging control unit 21 changes the wavelength of light emitted from the illumination unit 3 in a case where the target object may not be detected in the imaging range.
This makes it possible to continuously measure the target object stopped in the imaging range.
In the measuring device 1 according to the present technology described above, it is contemplated that the imaging control unit 21 moves the illumination unit 3 in a case where the target object may not be detected in the imaging range.
This makes it possible to continuously measure the target object stopped in the imaging range.
In the measuring device 1 according to the present technology described above, it is contemplated that a plurality of illumination units 3 is provided, and the imaging control unit 21 causes a different illumination unit 3 to emit light in a case where the target object may not be detected in the imaging range.
This makes it possible to continuously measure the target object stopped in the imaging range.
In the measurement method according to the present technology described above, an image of a predetermined imaging range in water is captured by the imaging unit, and information regarding the position of the target object in the imaging direction is measured on the basis of the captured image.
In the program according to the present technology described above, the information processing device is caused to execute processing of causing the imaging unit to capture an image of a predetermined imaging range in water and of measuring information regarding the position of the target object in the imaging direction on the basis of the captured image.
Such a program may be recorded in advance in an HDD as a storage medium built in a device such as a computer device, a ROM in a microcomputer having a CPU, or the like.
Alternatively, the program may be temporarily or permanently stored (recorded) in a removable recording medium such as a flexible disk, a compact disc read only memory (CD-ROM), a magneto optical (MO) disk, a digital versatile disc (DVD), a Blu-ray disc (registered trademark), a magnetic disk, a semiconductor memory, a memory card, or the like. Such a removable recording medium may be provided as what is called package software.
Furthermore, such a program may be installed from the removable recording medium into a personal computer or the like, or may be downloaded from a download site via a network such as a local area network (LAN) or the Internet.
Furthermore, such a program is suitable for providing the information processing device of the embodiments in a wide range. For example, by downloading the program to a mobile terminal device such as a smartphone, a tablet, or the like, a mobile phone, a personal computer, game equipment, video equipment, a personal digital assistant (PDA), or the like, such a device may be caused to function as the information processing device of the present disclosure.
Note that the effects described herein are merely examples and not limiting, and there may be other effects.
The present technology may also be configured as follows.
(1)
A measuring device including:
The measuring device according to (1),
The measuring device according to (1) or (2), further including
The measuring device according to (3), in which
The measuring device according to any one of (1) to (4), in which
The measuring device according to any one of (1) to (5), in which
The measuring device according to any one of (1) to (6), further including
The measuring device according to (7), in which
The measuring device according to any one of (1) to (6), in which
The measuring device according to any one of (1) to (6), in which
The measuring device according to (3) or (4), in which
The measuring device according to (3), in which
The measuring device according to (3) or (4), in which
The measuring device according to (3) or (4), in which
A measurement method including:
A program configured to cause a measuring device to execute processing of
| Number | Date | Country | Kind |
|---|---|---|---|
| 2021-093774 | Jun 2021 | JP | national |
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/JP2022/021150 | 5/23/2022 | WO |
