JP2019033469A - Imaging apparatus, control method, and program - Google Patents

Abstract

To generate metadata of a captured image at an appropriate frequency.SOLUTION: An imaging apparatus includes setting means for setting the generation frequency of metadata based on the type of metadata to be given to a captured image and control means for performing control to generate metadata at the generation frequency set by the setting means.SELECTED DRAWING: Figure 5

Description

  The present invention relates to an imaging apparatus, a control method, and a program.

  In recent years, it has become possible to easily acquire information requested by a user from an acquired image by using a stationary imaging device such as a surveillance camera. In order to provide video and information required by the user, it is necessary to add video and metadata that can be acquired from the imaging device, and a plurality of types of metadata are required. In order to generate metadata, various image analysis processes such as object detection, color extraction, character recognition, and face recognition are required depending on the type of metadata.

  In Patent Document 1, when an imaging device and an external analysis server perform exchange, and there is a field (for humans, vehicles, etc.) in which the analysis server can analyze metadata, the analysis server performs processing. In the case where it is impossible, a technique is disclosed in which the imaging apparatus performs processing.

JP 2010-273125 A

  However, since the resources of the imaging device are limited, if the metadata is generated frequently, the imaging device is overloaded. In addition, the quality of the image obtained by the imaging device is not always good, and may deteriorate depending on the setting conditions at the time of shooting and the environment of the installation location.In this case, the reliability of the metadata is There is a low possibility.

  The present invention has been made in view of such a problem, and an object thereof is to perform control so that metadata of a captured image is generated at an appropriate frequency.

  Therefore, the present invention provides an imaging apparatus, wherein a setting unit that sets a generation frequency of the metadata based on a type of metadata to be added to a captured image, and a generation frequency set by the setting unit. And control means for controlling to generate the metadata.

  ADVANTAGE OF THE INVENTION According to this invention, it can control to produce | generate the metadata of a captured image with appropriate frequency.

It is a hardware block diagram of the imaging device which concerns on 1st Embodiment. It is a functional lineblock diagram of an imaging device. It is a figure which shows an example of the kind of metadata. It is a flowchart which shows a setting process. It is a flowchart which shows a 1st adjustment process. It is a flowchart which shows a 2nd adjustment process. It is a figure which shows an example of increase / decrease in the production | generation frequency of metadata. It is a flowchart which shows an apparatus setting process. It is a flowchart which shows a 3rd adjustment process. It is a flowchart which shows the generation frequency setting process for every area | region for metadata. It is a flowchart which shows a transmission frequency setting process. It is a figure which shows the example of a display of metadata.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(First embodiment)
FIG. 1 is a hardware configuration diagram of the imaging apparatus 100 according to the first embodiment. In FIG. 1, a lens group 101 is an optical system that condenses incident light from a subject on an image sensor 103. The lens group 101 includes a focus lens that focuses on the subject, a zoom lens that adjusts the angle of view, and the like. The light that has passed through the lens group 101 passes through the optical filter 102 and enters the image sensor 103. As the optical filter 102, for example, an infrared cut filter (IRCF) or the like is installed. The information of the captured image is received by the image sensor 103 through a color filter arranged in a predetermined order for each pixel on the light receiving surface of the image sensor 103. The image sensor 103 outputs an image to be captured as an analog signal.

  The video image formed by the image sensor 103 is gain-controlled by the AGC 104 and the luminance of the video signal is adjusted, and is converted from an analog signal to a digital signal by the A / D converter 105. The video signal processing unit 106 performs predetermined processing on the digital signal from the A / D conversion unit 105, outputs a luminance signal and a color signal for each pixel, creates an output video, and controls the imaging device 100. Create each parameter to do. Examples of parameters for controlling the imaging apparatus 100 include parameters used in aperture control, focus adjustment control, and white balance control for adjusting color.

  The exposure control unit 107 calculates luminance information in the shooting screen from the luminance information output from the video signal processing unit 106, and controls the aperture and AGC to adjust the captured image to a desired brightness. The operation unit 108 receives user operations. The shake detection unit 109 detects the presence / absence of shake of the imaging apparatus 100 and the amount of shake. The shake detection unit 109 is, for example, an acceleration sensor. The control unit 110 controls the entire imaging apparatus 100. The communication unit 120 communicates with the communication unit 121 of the external device. For example, the communication unit 120 transmits the video signal created by the video signal processing unit 106 to an external device. Further, the metadata generated by the imaging device 100 may be transmitted from the communication unit 120 to an external device. The external device processes the video signal and metadata received from the communication unit 121 by the control unit 122, and displays the video and metadata by the display unit 123.

  The CPU 111 of the control unit 110 reads the control program stored in the ROM 112 and executes various processes. The RAM 113 is used as a temporary storage area such as a main memory or work area for the CPU 111. Note that the functions and processing of the imaging apparatus 100 described later are realized by the CPU 111 reading a program stored in the ROM 112 and executing this program. As another example, the CPU 111 may read a program stored in a recording medium such as an SD card instead of the ROM 112 or the like.

  As another example, at least a part of the functions and processing of the imaging apparatus 100 may be realized by, for example, cooperating a plurality of CPUs, RAMs, ROMs, and storages. As another example, at least a part of the functions and processing of the imaging apparatus 100 may be realized using a hardware circuit.

  FIG. 2 is a functional configuration diagram of the imaging apparatus 100. The image analysis unit 201 performs image analysis processing on the video obtained by the video signal processing unit 106. Examples of the image analysis processing include object recognition, moving object detection, color extraction, face recognition, character recognition, and the like. The metadata generation unit 202 generates metadata from the analysis result of the image analysis unit 201 and adds it to the video. Note that the specific method for associating the metadata with the video is not limited to the embodiment. As another example, the metadata generation unit 202 may assign an identifier that links the video and metadata to each other. Here, the process of generating metadata by the metadata generation unit 202 is an example of a control process for controlling to generate metadata and a generation process for generating metadata.

  The generation management unit 203 manages the generation of metadata by the metadata generation unit 202. Specifically, the generation management unit 203 sets the generation frequency of metadata for each type of metadata. FIG. 3 is a diagram illustrating an example of types of metadata. In the present embodiment, the metadata is roughly classified into those relating to the human body, those relating to the car, and others. Examples of metadata relating to the human body include clothes color, height, sex, age, and direction of movement. Further, examples of the metadata relating to the vehicle include color, license plate display, vehicle type, moving direction, and the like. Other metadata includes the ID of the image capturing apparatus 100 that captured the video, the installation position, the orientation, the imaging parameters (zoom, shutter speed, etc.), weather, temperature, and the like. In addition, when the imaging apparatus 100 is transmitting metadata to an external apparatus, the generation management unit 203 also performs metadata transmission frequency setting processing.

  Here, for example, the ID and the installation position of the image capturing apparatus 100, which are other metadata, are invariant metadata that does not change for each shooting. On the other hand, the color of clothes worn by a person, the display of a license plate of a car, and the like are metadata that may be changed for each shooting. Since immutable metadata is unlikely to change, once it is acquired, it is not necessary to generate it again and again. In addition, since the color of a person's clothes, the color of a car, and the like can be determined with relatively high accuracy, there is no need to repeatedly generate metadata. On the other hand, the accuracy of image analysis, such as recognition of characters and the like displayed on the license plate and estimation of the age of a person, largely depends on the obtained video.

  The imaging apparatus 100 according to the present embodiment generates a plurality of metadata shown in FIG. 3 at predetermined intervals and adds them to the video. Furthermore, the imaging apparatus 100 sets the generation frequency of this metadata for each metadata. FIG. 4 is a flowchart showing setting processing by the imaging apparatus 100. The setting process is a process for setting the generation frequency of metadata. Note that at the start of the generation frequency setting process, a preset initial value is assigned as the generation frequency of each metadata shown in FIG. 3. In the setting process, the generation frequency is increased by appropriately increasing the initial value. Is set.

  In step S401, the image analysis unit 201 acquires a video. In step S402, the image analysis unit 201 detects a moving object in the video. If a moving object is detected (Yes in S402), the image analysis unit 201 advances the process to S403. If no moving object is detected (No in S402), the image analysis unit 201 advances the process to S401. In step S403, the image analysis unit 201 further performs recognition processing to determine whether the moving object is a human body or a car. If the moving body is a human body (human body in S403), the image analysis unit 201 advances the process to S404. If the moving body is a car (car in S403), the image analysis unit 201 advances the process to S405.

  In step S404, the generation management unit 203 increases the generation frequency of metadata related to the human body by n. On the other hand, in S405, the generation management unit 203 increases the generation frequency of the metadata related to the vehicle by m. This is the end of the process. Here, m is a value larger than n. With humans and cars, cars move faster. Therefore, the generation frequency of the metadata about the car is set to a value larger than the generation frequency of the metadata about the human body. Thereby, it is possible to prevent the metadata from being missed even for a high-speed vehicle. The processes of S403, S404, and S405 are processes that increase the generation frequency when the object is a moving object compared to when the object is not a moving object. That is, the processes of S403, S404, and S405 are an example of a process for setting the generation frequency based on the size of the object.

  FIG. 5 is a flowchart showing a first adjustment process by the imaging apparatus 100. The first adjustment process is a process for adjusting the generation frequency of the metadata set in the setting process. In step S501, the image analysis unit 201 identifies the size of the recognized moving object. In step S502, the generation management unit 203 compares the size of the moving object specified in step S501 with a preset threshold value. If the size of the moving object is greater than or equal to the threshold (Yes in S502), the generation management unit 203 advances the process to S503. If the size of the moving object is less than the threshold (No in S502), the generation management unit 203 ends the process.

  In step S503, the generation management unit 203 confirms whether the metadata to be processed among the metadata illustrated in FIG. 3 is metadata belonging to the first group. If the metadata belongs to the first group (Yes in S503), the generation management unit 203 advances the process to S504. If the metadata does not belong to the first group (No in S503), the generation management unit 203 ends the process. In step S504, the generation management unit 203 increases the generation frequency of the metadata to be processed by a predetermined amount. This is the end of the process. Note that the processing of S504 is a setting for setting a larger generation frequency in the first group metadata than in other metadata other than the first group metadata when the size of the object is equal to or larger than the threshold. It is an example of a process.

  Here, the metadata belonging to the first group is metadata that increases the accuracy and reliability of the metadata when the size of the moving object is greater than or equal to a certain level, and these metadata belong to the first group. It is assumed that the image capturing apparatus 100 is set in advance. The metadata belonging to the first group includes, for example, the display of a car license plate and the age of the human body. For example, with a license plate, the larger the car, the easier it is to recognize characters without crushing characters, the accuracy is improved, and the reliability of metadata is improved. Therefore, accurate information can be increased by increasing the generation frequency of metadata. On the other hand, for example, the color of a car can be extracted even if the car is small, and just because the car is large does not necessarily improve the accuracy. For this reason, it is not necessary to increase the generation frequency even when the size is a certain level or more. Therefore, the color of the car is set as metadata that does not belong to the first group.

  Note that the degree to which the generation frequency is increased in S504 is not particularly limited. As another example, the generation management unit 203 may increase by a predetermined ratio based on the generation frequency set before the processing of S504. As another example, the generation management unit 203 may change the degree of increase according to the size.

  FIG. 6 is a flowchart showing the second adjustment process by the imaging apparatus 100. Similar to the first adjustment process, the second adjustment process is a process for adjusting the generation frequency of metadata set in the setting process. It is assumed that the second adjustment process is performed after the first adjustment process. As another example, the second adjustment process may be performed first.

  In step S <b> 601, the generation management unit 203 acquires the shake amount detected by the shake detection unit 109. Note that the shake amount may be obtained by the image analysis unit 201 calculating a motion vector from the image instead of being detected by the shake detection unit 109. Next, in step S602, the shake amount is compared with a preset threshold value. If the amount of shake is equal to or greater than the threshold (Yes in S602), the generation management unit 203 advances the process to S603. If the shake amount is less than the threshold (No in S602), the generation management unit 203 ends the process.

  In step S603, the generation management unit 203 checks whether the metadata to be processed is metadata belonging to the second group among the metadata illustrated in FIG. If the metadata belongs to the second group (Yes in S603), the generation management unit 203 advances the process to S604. If the metadata does not belong to the second group (No in S603), the generation management unit 203 ends the process. In step S604, the generation management unit 203 decreases the generation frequency of the metadata to be processed by a predetermined amount. This is the end of the process. Note that the process of S604 is a setting process for setting a smaller generation frequency in the second group metadata than in other metadata than the second group metadata when the shake amount is equal to or greater than the threshold. It is an example.

  Here, the metadata belonging to the second group is metadata that reduces the reliability of the metadata when shake occurs, and it is assumed that these metadata belong to the second group. It is assumed that the device 100 is set in advance. As metadata belonging to the second group, for example, there is a display of a license plate of a car. In the license plate, the accuracy of character recognition decreases when characters are blurred. Therefore, when a shake amount of a certain value or more is detected, the generation frequency is reduced in order to reduce the processing load for generating low-precision metadata. On the other hand, the color of the car can be accurately extracted even if the image is blurred. Therefore, the color of the car is set as metadata that does not belong to the second group.

  Note that the degree of reducing the generation frequency in S604 is not particularly limited. As another example, the generation management unit 203 may reduce a predetermined ratio based on the generation frequency set before the processing of S604. As another example, the generation management unit 203 may change the degree of reduction according to the shake amount.

  FIG. 7 is a diagram illustrating an example of increase / decrease in the generation frequency of metadata by the setting process (FIG. 3), the first adjustment process (FIG. 5), and the second adjustment process (FIG. 6). The process of detecting the size of the moving body in the first adjustment process and the process of detecting the shake amount in the second adjustment process are examples of the image analysis process. The setting process, the first adjustment process, and the second adjustment process are examples of the setting process for setting the generation frequency based on the result of the image analysis.

  As described above, the imaging apparatus 100 according to the first embodiment sets the generation frequency of metadata according to the type of metadata, the analysis result of the image, the shake amount, and the like. Thereby, the imaging device 100 can control to generate metadata at an appropriate frequency so as to prevent excessive generation of metadata and lack of metadata. Assuming that the zoom amount and the installation environment are not frequently changed, it is considered that the size and the shake amount of the moving object do not change frequently. For this reason, the imaging apparatus 100 can continue to use the generation frequency once set.

  As a first modification of the first embodiment, the generation frequency is increased in S504 of the first adjustment process (FIG. 5). This is because more accurate information is accumulated by increasing the generation frequency. However, when the size is equal to or larger than the threshold and the metadata is the first group, the reliability of the metadata is high. For this reason, it may not be necessary to repeat the generation of metadata. In such a case, the generation frequency may be decreased in S504. Thereby, it is possible to reduce a processing load related to generation of metadata.

  As a second modification, the image analysis result referred to when setting the generation frequency is not limited to the size of the moving object or the shake amount. As another example, noise or the like at low illuminance may be used. That is, the imaging apparatus 100 may set the generation frequency according to noise.

  As a third modification, the imaging apparatus 100 may set the generation frequency of metadata according to a user operation. In this case, the imaging apparatus 100 gives priority to the setting by the user, and the processing related to the setting of the generation frequency as described above is performed on the type of metadata for which the generation frequency is not set by the user. And

  As a fourth modification, the imaging apparatus 100 is not particularly limited in the frequency of moving object detection in S402 illustrated in FIG. For example, the imaging apparatus 100 may perform moving image detection for each frame of the video, and perform other image analysis at the metadata generation frequency. As another example, the moving image detection may be performed at the metadata generation frequency. It is good also to do in.

  As a fifth modification, in the embodiment, the case where the captured image to which the metadata is added is a video has been described as an example, but the object to be disabled may be a still image.

  As a sixth modified example, the imaging apparatus 100 may set the generation frequency not only for moving objects in a video but also for metadata about stationary objects (people and cars) by the process described in the embodiment. . For example, the imaging apparatus 100 may acquire the size of an object instead of a moving object in S501 of FIG.

(Second Embodiment)
Next, the difference between the imaging apparatus 100 according to the second embodiment and the imaging apparatus 100 according to the first embodiment will be described. The imaging device 100 according to the second embodiment causes an external device to appropriately execute metadata generation processing. FIG. 8 is a flowchart illustrating a device setting process for setting a device that executes a metadata generation process. In step S <b> 801, the generation management unit 203 confirms whether the processing load related to metadata generation by the metadata generation unit 202 is equal to or greater than a preset threshold value. If the processing load is equal to or greater than the threshold (Yes in S801), the generation management unit 203 advances the process to S802. If the processing load is less than the threshold (No in S801), the generation management unit 203 advances the process to S804. The generation management unit 203 uses, for example, the resource usage ratio and the processing time when executing processing of the image analysis unit 201 and the metadata generation unit 202 related to metadata generation as the evaluation value of the processing load.

  In step S <b> 802, the generation management unit 203 checks the generation frequency set for the metadata to be processed. If the generation frequency is greater than or equal to a preset threshold value (Yes in S802), the generation management unit 203 advances the process to S803. If the generation frequency is less than the threshold (No in S802), the generation management unit 203 advances the process to S804. In step S803, the generation management unit 203 determines that the external device is a device that executes metadata generation processing. The process ends here. In this case, the generation management unit 203 transmits a metadata generation instruction together with the video to the external apparatus via the communication unit 120. This process is an example of a control process for controlling to generate metadata.

  In step S <b> 804, the generation management unit 203 confirms whether or not the resources that the imaging apparatus 100 can use for metadata generation are equal to or greater than a preset threshold value. If the resource is equal to or greater than the threshold (Yes in S804), the generation management unit 203 advances the process to S805. If the resource is less than the threshold (No in S804), the generation management unit 203 advances the process to S803. In step S805, the generation management unit 203 determines the imaging device 100 as a device that executes metadata generation processing. The process ends here. Note that other configurations and processes of the imaging apparatus 100 according to the second embodiment are the same as the configurations and processes of the imaging apparatus 100 according to the first embodiment.

  As described above, the imaging device 100 according to the second embodiment can distribute the metadata generation processing to the imaging device 100 and the external device. Thereby, it is possible to prevent the load in the metadata generation process from affecting the function at the time of shooting.

(Third embodiment)
Next, a third embodiment will be described. In the third embodiment, the image analysis unit 201 performs moving object detection from the acquired video, and acquires and assigns an ID for identifying the moving object for each detected moving object. Object ID, which is identification information of a moving object, may be used as metadata, but here it is used to set the generation frequency of metadata other than the moving object ID.

  FIG. 9 is a flowchart illustrating a third adjustment process by the imaging apparatus 100 according to the third embodiment. In step S901, the image analysis unit 201 determines the acquisition state of the moving object ID. If the moving object ID has not been acquired (No in S901), the image analysis unit 201 advances the process to S904. If the moving object ID has been acquired (Yes in S901), the image analysis unit 201 advances the process to S902. In step S902, the image analysis unit 201 further confirms the reliability of the acquired moving object ID. If the reliability of the moving object ID is equal to or greater than a preset threshold value (Yes in S902), the process proceeds to S903. If the reliability of the moving object ID is not greater than or equal to the preset threshold value (No in S902), the process proceeds to S904. The reliability of the moving object ID can be calculated from known methods such as the proximity of the spatial position of the moving object detected in each frame, the luminance of the moving object, and the degree of color similarity.

  In step S <b> 903, the generation management unit 203 decreases the generation frequency of metadata of moving objects that have acquired moving object IDs whose reliability is equal to or higher than a preset threshold by a predetermined amount. On the other hand, in S904, the generation management unit 203 increases the generation frequency of metadata by a predetermined amount. Note that other configurations and processes of the imaging apparatus 100 according to the third embodiment are the same as the configurations and processes of the imaging apparatus 100 according to other embodiments.

  Moving objects to which the same moving object ID is assigned between different frames can be regarded as the same moving object. In the third embodiment, when the same moving object ID is assigned and the moving object is regarded as the same moving object, when the image analyzing unit 201 recognizes that the moving object is a person, Avoid repeatedly generating metadata such as age. Further, when the image analysis unit 201 recognizes that the moving object is a car, it does not repeatedly generate metadata of a type such as a license plate or a car color.

  However, even if the same moving object ID is assigned, if metadata is not repeatedly generated uniformly, the metadata will be lost if the assigned moving object ID is incorrect. . Therefore, even if the same moving object ID is given as described above, if it is determined that the reliability of the moving object ID is less than a preset threshold, the frequency of generating metadata is increased. Thereby, even if an incorrect moving object ID is given, it is possible to prevent the metadata from being missed.

  Further, even if a moving object is detected from the captured video, if the moving object ID is not assigned, it is impossible to determine whether the moving object ID is the same moving object. Increase it.

  On the other hand, if it is determined that the accuracy and reliability of the moving object ID assigned to the moving object detected from the captured video is higher than a preset threshold, the same moving object exists in different frames. Therefore, for example, if the moving object is a person, it can be determined that there is no possibility that metadata such as age and height will change. In this case, it is possible to reduce the processing load by reducing the generation frequency of the metadata, and to prevent the function at the time of shooting from being affected. Even if it is determined that they are the same moving object, the generation frequency of metadata such as the direction of movement of a person who may change may not be decreased.

(Fourth embodiment)
Next, a fourth embodiment will be described. In the first embodiment, the imaging apparatus 100 adjusts the generation frequency of metadata for the detected person or vehicle for the entire area of the acquired video. This indicates that the metadata area is the entire video. On the other hand, the imaging apparatus 100 according to the fourth embodiment does not set the metadata area as the entire video, but sets one or more partial metadata areas at arbitrary positions in the video. The upper limit of the number of areas for metadata that can be set at an arbitrary position may be set in advance by the imaging apparatus 100, and is determined from the number of metadata, the amount of data, and the number of target objects for generating metadata. May be.

  FIG. 10 is a flowchart showing a generation frequency setting process for each metadata area. In S1001, the generation management unit 203 ends the process when the metadata area is not set (No in S1001). When setting the metadata area (Yes in S1001), the generation management unit 203 advances the process to S1002. The generation management unit 203 ends the process when the metadata generation frequency is not set to be different for each metadata area (No in S1002). When the generation management unit 203 sets the metadata generation frequency to be different for each metadata area (Yes in S1002), the process proceeds to S1003. If no event has occurred in the metadata area (No in S1003), the generation management unit 203 ends the process. If an event occurs in the metadata area (Yes in S1003), the generation management unit 203 advances the process to S1004. In step S1004, the generation management unit 203 increases the generation frequency of metadata related to a moving object existing in the metadata area where the event has occurred by a predetermined amount.

  A plurality of metadata areas can be set at any position according to a user operation, and the metadata area can be automatically set based on the result of image analysis by the image analysis unit 201. It is. When the metadata area is automatically set, for example, the image analysis unit 201 sets the metadata area by recognizing a road and a doorway through which moving objects frequently pass through image analysis. As another example, the image analysis unit 201 may set an area where the number of moving objects increases as a metadata area. Examples of the event that may occur include an event such as an abnormal intrusion in which an object enters a certain area, an object that has been placed at a predetermined location is taken away, or an object that is left behind. Note that other configurations and processes of the imaging apparatus 100 according to the fourth embodiment are the same as the configurations and processes of the imaging apparatus 100 according to other embodiments.

  As described above, it is possible to acquire metadata more efficiently by narrowing down an area rather than the entire video and generating metadata for a portion where an event has occurred.

  As a first modification of the fourth embodiment, the generation management unit 203 has a case where the number of target objects is greater than or equal to a preset threshold in the metadata area set at an arbitrary position. The generation frequency of metadata may be decreased by a predetermined amount. As a result, the processing load can be reduced when a considerable number of target objects are expected to exist in the metadata area as in crowd monitoring.

  As a second modification of the fourth embodiment, assuming that crowd monitoring is performed, the generation management unit 203 reduces the types of metadata to be generated when the number of target objects is greater than or equal to a preset threshold value. Then, the generation frequency may be further decreased by a predetermined amount.

(Fifth embodiment)
Next, a fifth embodiment will be described with reference to FIG. The generation management unit 203 ends the process when the imaging apparatus 100 has a configuration of a single imaging apparatus that does not communicate with an external apparatus (No in S1101). If the image capturing apparatus 100 and the external apparatus communicate with each other (Yes in S1101), the generation management unit 203 advances the process to S1102. If the metadata generated by the imaging apparatus 100 in the imaging apparatus is not transmitted to the external apparatus (No in S1102), the generation management unit 203 ends the process. When the metadata generated by the imaging apparatus 100 in the imaging apparatus is transmitted to the external apparatus (Yes in S1102), the generation management unit 203 advances the process to S1103.

  If the amount of metadata transmitted from the imaging device 100 to the external device is not equal to or greater than a preset threshold (No in S1103), the generation management unit 203 ends the process. If the amount of metadata transmitted from the image capturing apparatus 100 to the external apparatus is equal to or greater than a preset threshold (Yes in S1103), the generation management unit 203 advances the process to S1104. In step S1104, the generation management unit 203 decreases the transmission frequency of metadata to be transmitted to the external device by a predetermined amount.

  The metadata on the external device side is updated by transmitting the metadata from the imaging device 100 to the external device. In communication between an imaging device and an external device, video and data are transmitted and received in addition to metadata. Therefore, if the amount of metadata becomes large, communication is compressed. Therefore, as described above, when the amount of metadata to be transmitted to the external device is equal to or greater than a preset threshold, the transmission frequency is decreased. Thereby, it is possible to prevent the communication from being affected.

  As a modified example of the fifth embodiment, the imaging apparatus 100 adds and transmits the captured image as a means for transmitting metadata from the imaging apparatus to the external apparatus, or transmits only the metadata as text data separately. You may choose. As a selection method, when the number of metadata generation targets is larger than a preset threshold value, a method of transmitting text data only with metadata may be selected.

  The setting of the metadata generation frequency has been described so far, but FIG. 12 shows a display example of the generated metadata. As shown in the upper diagram of FIG. 12, it is possible to display the license plate and vehicle type metadata separately from the display video, or to display the metadata superimposed on the display video as shown in the lower diagram of FIG. Yes, you may change according to user operation.

  The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to such specific embodiments, and various modifications can be made within the scope of the gist of the present invention described in the claims.・ Change is possible.

(Other examples)
The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

DESCRIPTION OF SYMBOLS 100 Imaging device 201 Image analysis part 202 Metadata production | generation part 203 Generation | occurrence | production management part

Claims (25)

Setting means for setting the generation frequency of the metadata based on the type of metadata to be added to the captured image;
An imaging apparatus comprising: control means for controlling to generate the metadata at a generation frequency set by the setting means. Further comprising generating means for generating the metadata;
The imaging apparatus according to claim 1, wherein the control unit controls generation of the metadata by the generation unit. An analysis unit for performing image analysis of the captured image;
The imaging apparatus according to claim 1, wherein the setting unit further sets the generation frequency based on a result of the image analysis. The analyzing means specifies a size of an object included in the captured image;
The imaging apparatus according to claim 3, wherein the setting unit sets the generation frequency based on a size of the object.   The setting means generates metadata other than the preset type of metadata when the size of the object is equal to or greater than a threshold and the target metadata is a predetermined type of metadata. The imaging apparatus according to claim 4, wherein a value larger than the frequency is set as the generation frequency of the target metadata. The analysis means specifies whether the object in the captured image is a moving object,
The imaging apparatus according to claim 3, wherein the setting unit sets the generation frequency based on whether the object is a moving object.   The setting means sets, when the object is a moving object, a value larger than the generation frequency of the metadata about the object when the object is not a moving object, as the generation frequency of the metadata about the object. Item 7. The imaging device according to Item 6.   The imaging apparatus according to claim 1, wherein the setting unit further sets the generation frequency based on a shake amount of the imaging apparatus.   When the shake amount is equal to or greater than a threshold and the target metadata is a preset type of metadata, the setting unit determines whether to generate metadata other than the preset type metadata. The imaging apparatus according to claim 8, wherein a smaller value is set as a generation frequency of the target metadata.   The imaging apparatus according to claim 8, further comprising a detection unit configured to detect the shake amount of the imaging apparatus.   The imaging apparatus according to claim 8, further comprising an acquisition unit that acquires the shake amount based on the captured image. Based on a processing load related to the generation of the metadata, further comprising a determination unit that determines whether the device that performs the generation processing of the metadata is the imaging device or an external device;
The imaging apparatus according to claim 1, wherein the control unit controls the apparatus determined by the determination unit to generate the metadata.   13. The imaging apparatus according to claim 12, wherein the determination unit determines an apparatus that performs the generation process as an external apparatus when the processing load is equal to or greater than a preset threshold value.   13. The imaging apparatus according to claim 12, wherein the determination unit further determines an apparatus that performs the generation process based on a generation frequency of metadata.   The determination unit determines an apparatus to perform the generation process as an external apparatus when the processing load is equal to or greater than a preset threshold value and the generation frequency is equal to or greater than a preset threshold value. Item 14. The imaging device according to Item 13. The analysis means specifies identification information of an object included in the captured image;
The imaging apparatus according to claim 3, wherein the setting unit sets the generation frequency based on a state of acquisition of identification information of the object.   The imaging unit according to claim 16, wherein the setting unit sets a generation frequency smaller when the identification information of the object is acquired than when the identification information of the object is not acquired. apparatus.   The setting means obtains the identification information of the object, and when the reliability of the identification information of the object is greater than or equal to a threshold, the generation frequency is smaller than when the reliability of the identification information of the object is less than the threshold. The imaging apparatus according to claim 17, wherein the imaging apparatus is set.   The imaging apparatus according to claim 1, wherein the setting unit sets a metadata generation frequency for each of a plurality of metadata areas set in the captured image.   When the event occurs in the metadata area, the setting means sets a generation frequency larger than the generation frequency when no event occurs as the metadata generation frequency of the metadata area where the event occurred. The imaging apparatus according to claim 19, wherein: A communication means for communicating with an external device;
Setting means for setting the transmission frequency of the metadata based on the amount of metadata to be transmitted to the external device;
An imaging apparatus comprising: control means for controlling to transmit the metadata at a transmission frequency set by the setting means.   The image pickup apparatus according to claim 21, wherein the setting unit sets a transmission frequency smaller when the number of metadata generation target objects is equal to or greater than a threshold value, compared to when the number is less than the threshold value. A method for controlling an imaging apparatus,
A setting step for setting the generation frequency of the metadata based on the type of metadata to be added to the captured image;
And a control step for controlling to generate the metadata at the generation frequency set in the setting step. A method for controlling an imaging apparatus,
A communication step for communicating with an external device;
A setting step of setting the transmission frequency of the metadata based on the amount of metadata to be transmitted to the external device;
And a control step of controlling to transmit the metadata at the transmission frequency set in the setting step.   The program for functioning a computer as each means of the imaging device of any one of Claims 1 thru | or 22.

Images