Apparatus and method for signing metadata frames corresponding to image frames

Abstract

An apparatus, method, and non-transitory computer-readable storage medium are disclosed that sign a metadata frame corresponding to an image frame. The metadata frame includes metadata of one or more detected objects in the image frame, and the metadata of each detected object includes coordinates defining a location of the detected object in the image frame. A digital signature is generated based on at least a subset of the metadata in the metadata frame, and additional metadata is added to the metadata frame. The additional metadata includes the digital signature and a predefined coordinate defining that the additional metadata includes the digital signature. Further, an apparatus, method, and non-transitory computer-readable storage medium are disclosed that authenticate a digitally signed metadata frame corresponding to an image frame of a sequence of image frames.

Description

Technical Field

[0001] This invention relates to the authentication of metadata, and more particularly to the signing of metadata frames corresponding to image frames in an image frame sequence. Background Technology

[0002] In some applications, it is desirable to verify that the metadata of a metadata frame is intact, meaning it has not been tampered with since its generation and that the metadata originates from a legitimate source. Each metadata frame corresponds to a specific image frame in an image frame sequence. One way to achieve this verification of the metadata corresponding to an image frame sequence is to generate a digital signature for the metadata frame. The digital signature can then be sent in the header of the metadata stream containing the metadata frame, and used at the receiver to verify that the metadata of the metadata frame is intact and that the digital signature was generated from a legitimate source. However, if digital signatures are generated for all metadata frames associated with an image frame sequence, then if the digital signatures cannot be verified, all metadata frames will be considered not intact or received from a non-legitimate source. Therefore, changes in a single metadata frame can have the effect that multiple metadata frames in a stream segment are considered illegitimate and untrustworthy. To address this problem, it is necessary to improve the method of signing metadata. Summary of the Invention

[0003] The purpose of this invention is to help enhance the signing and transmission of metadata corresponding to image frame sequences.

[0004] According to a first aspect, a method is provided for signing a metadata frame corresponding to an image frame in an image frame sequence. The metadata frame includes metadata of one or more detected objects in the image frame. Furthermore, the metadata of each detected object includes coordinates defining the location of the detected object in the image frame. The method includes: generating a digital signature based on at least a subset of the metadata in the metadata frame; and adding additional metadata to the metadata frame, the additional metadata including the digital signature and predefined coordinates defining that the additional metadata includes the digital signature.

[0005] By generating separate digital signatures for each metadata frame, the metadata frame can be authenticated independently. Furthermore, by including the digital signature as additional metadata within the metadata frame and using predefined coordinates to indicate that the additional metadata includes the digital signature, the digital signature can be transmitted for each metadata frame without adjusting the metadata frame format (i.e., how the metadata is represented) or the protocol used to transmit the metadata. Instead, the receiving device can be informed of predefined coordinates that define the additional metadata including the digital signature. The receiving device only needs to know the predefined coordinates once, and this can be done offline. Moreover, the digital signature can be transmitted within the metadata frame, for which it is used for authentication. This is more efficient and discrete than transmitting the digital signature separately from the metadata frame.

[0006] A digital signature is any type of digital signature that can verify the authenticity of a metadata frame.

[0007] Predefined coordinates can be used exclusively to define additional metadata, including digital signatures. This means that predefined coordinates cannot be used as coordinates for real objects. By choosing such dedicated coordinates, there is no risk that detected objects will have predefined coordinates, and therefore the metadata of the detected objects will be interpreted as digital signatures.

[0008] For example, predefined coordinates can define the positions of objects without extensions. Thus, since detected objects will have extensions, there is no risk that detected objects will have predefined coordinates.

[0009] Coordinates can, for example, represent the top-left and bottom-right corners of the bounding box associated with the detected object, and predefined coordinates represent the same coordinates for both the top-left and bottom-right corners. Thus, since detected objects will have different coordinates for their top-left and bottom-right corners, there is no risk that detected objects will have predefined coordinates.

[0010] In the process of generating a digital signature, it can be generated based on the private key in the public key and private key pair.

[0011] The act of generating a digital signature may include hashing at least a subset of metadata to generate a hash value; and generating a digital signature based on the hash value.

[0012] The metadata for each detected object can be represented as a separate item in a metadata frame, where each separate item includes coordinates defining the location of the detected object in the image frame, and additional metadata is represented as an additional separate item.

[0013] Attached metadata can use the same syntax as the metadata for each detected object.

[0014] The method may further include forming metadata frames based on objects detected in the image frames.

[0015] The method may further include obtaining an image frame sequence and detecting objects in the image frames of the image frame sequence.

[0016] According to a second aspect, a method is provided for authenticating a digitally signed metadata frame corresponding to an image frame in an image frame sequence. The metadata frame includes metadata of one or more detected objects in the image frame. The metadata of each detected object includes coordinates defining the location of the detected object in the image frame. Furthermore, the metadata frame further includes additional metadata, which includes a digital signature for at least a subset of the metadata in the metadata frame and predefined coordinates defining the additional metadata including the digital signature. The method includes identifying the predefined coordinates that define the additional metadata including the digital signature; retrieving the digital signature from the additional metadata; and authenticating the metadata frame based on the digital signature.

[0017] By including the digital signature as additional metadata in the metadata frame and using predefined coordinates to indicate that the additional metadata includes the digital signature, the predefined coordinate digital signature can be identified, and the digital signature can be retrieved in the receiver for authentication of the metadata frame. This eliminates the need to adjust the protocol used to transmit the metadata or the format of the metadata frame (i.e., how the metadata is represented). Instead, the receiving device only needs to know the predefined coordinates that define the additional metadata including the digital signature. The receiving device only needs to know the predefined coordinates once, and this can be done offline.

[0018] According to a third aspect, a non-transitory computer-readable storage medium is provided having instructions stored thereon, which, when executed in a device having at least one processor, are used to implement the method according to the first or second aspect.

[0019] According to a fourth aspect, an apparatus is provided for signing a metadata frame corresponding to an image frame in an image frame sequence. The metadata frame includes metadata of one or more detected objects in the image frame. Furthermore, the metadata of each detected object includes coordinates defining the position of the detected object in the image frame. The apparatus includes circuitry configured to perform a generation function and an addition function. The generation function is configured to generate a digital signature using at least a subset of the metadata in the metadata frame, and the addition function is configured to add supplementary metadata to the metadata frame, the supplementary metadata including the digital signature and predefined coordinates defining that the supplementary metadata includes the digital signature.

[0020] The generation function can be configured to hash at least a subset of the metadata to generate a hash value, and then generate a digital signature based on that hash value.

[0021] The circuit can be further configured to perform a forming function that is configured to form a metadata frame based on the objects detected in the image frame.

[0022] The circuit can be further configured to perform an acquisition function and a detection function, the acquisition function being configured to acquire a sequence of image frames and the detection function being configured to detect objects in the image frames of the sequence of image frames.

[0023] The optional additional features described above in the method according to the first aspect, when applicable, also apply to the device according to the fourth aspect. To avoid unnecessary repetition, please refer to the above.

[0024] The further applicability of the invention will become apparent from the detailed description given below. However, it should be understood that while indicating preferred embodiments of the invention, the detailed description and specific examples are given only by way of illustration, as various variations and modifications within the scope of the invention will become apparent to those skilled in the art from this detailed description.

[0025] Therefore, it should be understood that the present invention is not limited to the specific components of the described device or the operation of the described method, as such devices and methods can vary. It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. It must be noted that, as used in this specification and the appended claims, the words “a,” “an,” “the,” and “the” are intended to indicate the presence of one or more elements unless the context clearly specifies otherwise. Thus, for example, a reference to “a unit” or “the unit” can include several devices, etc. Furthermore, the words “comprising,” “including,” and “containing,” and similar wording do not exclude other elements or steps. Attached Figure Description

[0026] The above and other aspects of the invention will now be described in more detail with reference to the accompanying drawings. These drawings should not be considered limiting, but rather for explanation and understanding.

[0027] Figure 1 A flowchart illustrating an embodiment of a method for signing metadata corresponding to image frames in an image frame sequence is shown.

[0028] Figure 2 A flowchart illustrating an embodiment of a method for authenticating digitally signed metadata frames corresponding to image frames in an image frame sequence is shown.

[0029] Figure 3 A schematic diagram of an embodiment of a device for signing metadata corresponding to image frames in an image frame sequence is shown.

[0030] Figure 4 A schematic diagram of an embodiment of a device for authenticating digitally signed metadata frames corresponding to image frames in an image frame sequence is shown. Detailed Implementation

[0031] The invention will now be described below with reference to the accompanying drawings, which illustrate presently preferred embodiments of the invention. However, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

[0032] Embodiments of this invention can be used to verify the authenticity of metadata, ensuring that the metadata is intact, i.e., has not been tampered with after generation and originates from a genuine source. In application, metadata frames correspond to image frames in an image frame sequence, and each metadata frame includes metadata related to one or more objects detected in the corresponding image frame, with the location of each object defined by object coordinates. Metadata is typically generated by analyzing image frames and can be further associated with, for example, further analytical information such as object ID, object category, and object color. Metadata can also be related to other information besides objects (such as information related to audio, radar, etc.). It should be understood that the format and syntax used to represent metadata are predefined, so that both the sender and receiver are aware of these formats and syntaxes (e.g., by means of standards). One standard for metadata representation and transmission is ONVIF profile M. An example of what metadata according to ONVIF profile M looks like for a metadata frame including metadata for an object is shown below.

[0033]

[0034]

[0035] The label “BoundingBox” is used to represent the image coordinates of the bounding box of the detected object. In this example, the coordinates of the object with ID 12 are represented by a bounding box with image coordinates (20, 180) for the top-left corner and (30, 100) for the bottom-right corner. If the frame will include another object, the metadata for that other object will be included in relation to the object with a different ID (i.e., a different value for the label “ObjectId”).

[0036] On the receiver side, including the decoder, the authenticity of the metadata frame can be verified using a digital signature for the metadata frame. For example, if the digital signature for the metadata frame is created by encrypting the hash value of at least a portion of the metadata frame using the private key from a public-private key pair, then the metadata can be verified as intact and originating from a genuine source by decrypting it using the public key from the public-private key pair and comparing the result with the corresponding hash value of at least a portion of the metadata frame received on the receiver side. If they are equal, the metadata frame is intact and originates from a genuine source; if they are not equal, the metadata frame is not intact (has been altered / tampered with) or does not originate from a genuine source.

[0037] In the following text, reference will be made to Figure 1 An embodiment of a method 100 for signing metadata frames corresponding to image frames in an image frame sequence is discussed. The metadata frame includes metadata of one or more detected objects in the image frame. Furthermore, the metadata of each detected object includes coordinates defining the location of the detected object within the image frame. Method 100 includes: generating (S110) a digital signature based on at least a subset of the metadata in the metadata frame; and adding (S120) additional metadata to the metadata frame. The additional metadata includes the digital signature and predefined coordinates that define the additional metadata as including the digital signature. This differs from the prior art, where the digital signature is sent, for example, in the header of a metadata stream and is associated with all metadata frames in the metadata stream. By including the digital signature as additional metadata in the metadata frame and using predefined coordinates to indicate that the additional metadata includes the digital signature, a separate digital signature can be transmitted for each metadata frame. Furthermore, the digital signature can be identified using the predefined coordinates, and can be retrieved in a receiver for authentication of the metadata frame without adjusting the protocol used to transmit the metadata. This can be achieved without adjusting the format of the metadata frame (i.e., how the metadata is represented). Conversely, the receiving device only needs to know predefined coordinates, which define additional metadata including a digital signature. The receiving device only needs to know the predefined coordinates once, and this can be done offline.

[0038] The requirement that a digital signature be based on "at least a subset" of the metadata in a metadata frame means that a digital signature only needs to be based on the metadata of the metadata frame that can be verified. For example, a digital signature can be based on metadata that is only relevant to a subset of the objects detected in the frame. For instance, it can be determined that metadata for only one or more specific types of objects needs to be verifiable. In this case, a digital signature can be generated based on the metadata that is relevant to the objects in those one or more specific types of objects.

[0039] It should be understood that the predefined coordinates are also known to the device receiving the metadata frame. The receiving device will interpret the metadata according to the predefined format and syntax used, and interpret the metadata accordingly. When interpreting additional metadata, the receiving device will recognize the coordinates as those defining the additional metadata, including the digital signature.

[0040] Predefined coordinates are preferably static, meaning the same predefined coordinates are used over time to define additional metadata, including digital signatures. Alternatively, the predefined coordinates can change over time; however, this approach requires the receiving device to know which coordinates to use relative to each metadata frame.

[0041] Predefined coordinates can be used exclusively to define additional metadata, including digital signatures; that is, they cannot be used as coordinates of the real object. By selecting such dedicated coordinates, there is no risk that the real object will have predefined coordinates, and therefore the metadata of the real object will be interpreted as a digital signature. Method 100 can then further include the action of selecting predefined coordinates and using those predefined coordinates exclusively to define the additional metadata, including the digital signature.

[0042] Furthermore, if the predefined format and syntax used to represent metadata require additional metadata to specify objects in order to include coordinates, then dummy objects can be identified using an identifier different from that of all identified real objects for which metadata is provided in the metadata frame. Therefore, the additional metadata can further include an object ID, and predefined coordinates can be indicated as being associated with that object ID.

[0043] To implement dedicated predefined coordinates, these coordinates can be made unrelated to actual objects. For example, predefined coordinates can define the location of objects without extension. For instance, if the coordinates represent the top-left and bottom-right corners of the bounding box associated with a detected object (e.g., in ONVIF profile M), the predefined coordinates would have the same coordinates for the top-left and bottom-right corners. This also applies when using different formats and syntaxes where the bounding box is defined by the top-right and bottom-left corners. In another example, the coordinates could represent the top-left corner and the distance to the bottom-right corner. To define the location of objects without extension, the predefined coordinates would have any coordinates for the top-left corner and an indication of zero distance to the bottom-right corner. This also applies if the bounding box is defined by the coordinates of any other corner and the distance from that corner to the corner diagonally across the bounding box. Predefined coordinates can remain the same over time, or they can vary, as long as they indicate objects without extension (i.e., a zero-pixel bounding box).

[0044] Other alternatives for implementing dedicated predefined coordinates are also envisioned. For example, predefined coordinates could allow objects to have negative expansion, such that the top-left corner is below and / or to the right of the bottom-right corner. In another example, predefined coordinates could allow objects to be completely or partially outside the image frame, such as the top-left and / or bottom-right corners being outside the image frame.

[0045] The advantage of using predefined coordinates that prevent them from being associated with real objects is that if the device receiving the metadata frame is unaware of the predefined coordinates, it will simply ignore the additional metadata because the predefined coordinates cannot be interpreted as being associated with an object.

[0046] A digital signature can be any type of digital signature capable of verifying authenticity. For example, a digital signature can be generated based on the private key in a public-private key pair. For instance, RSA (Rivest Shamir Adleman) 256-bit encryption, Digital Signature Algorithm (DSA), and Elliptic Curve Digital Signing Algorithm (ECDSA) can be used to generate a digital signature. A digital signature for a metadata frame can be generated by applying the private key to the metadata of the metadata frame or a subset of that metadata. However, to reduce the size of the digital signature, the metadata can first be hashed (S112) using a hash function (e.g., a cryptographic hash function) to generate a hash value. The digital signature can then be generated (S114) based on this hash value (e.g., by applying the private key to the hash value). Examples of cryptographic hash functions are MD5, SHA-1, SHA-2 (SHA-256 / SHA-512), SHA-3, and BLAKE-3.

[0047] The metadata for each detected object can be represented as a separate item in a metadata frame, where each separate item includes coordinates defining the detected object's location within the image frame. As an example, for metadata based on the ONVIF profile M as illustrated above, the object-related item is stated in the metadata declaration "<tt:objectObjectId="12"> The line containing the declaration is between and includes those lines. In this case, the same format and syntax can also be used to represent additional metadata as separate additional items.

[0048] The additional metadata can use the same syntax and / or format as the metadata for each detected object. Therefore, the syntax and / or format used for the detected objects are also used for the additional metadata. Thus, the additional metadata will be interpreted as object-related metadata, and the receiving device will be able to interpret this additional data. When the receiving device recognizes predefined coordinates, it will be able to interpret the additional metadata to include a digital signature.

[0049] For example, if additional metadata is added according to ONVIF profile M as object-related metadata, the label “BoundingBox” could include “left="20.0" top="180.0" right="20.0" bottom="180.0””, or could include any other coordinates indicating an unextended (i.e., zero-pixel) bounding box. A digital signature could then be included in the label “Type”, at the same location as “Vehicle” in the example metadata frame based on ONVIF profile M above.

[0050] Depending on the syntax and format used for the metadata frame, existing variables or tags can be used to include the digital signature in the additional metadata, which is used to provide metadata about some other characteristics of the object. The only requirement is that the existing variables or tags include a sufficient number of bits to contain the digital signature. The receiving device must then be informed that, when the predefined coordinates are identified, the existing tag or variable was used to include the digital signature in the additional metadata. Alternatively, a new variable or tag, "Digital Signature," or similar can be added.

[0051] Method 100 may further include obtaining (S102) an image frame sequence. If method 100 is performed in a camera, the image frame sequence (S102) can be obtained by capturing the image frame sequence through the camera. Alternatively, if the method is performed in a device separate from the camera, the image frame sequence (S102) can be obtained by receiving it directly from the camera or via another device from the camera.

[0052] Method 100 may then further include (S104) detecting objects in the image frames of the image frame sequence. Any type of object detection method can be used to detect objects.

[0053] Method 100 may further include forming a metadata frame (S106) based on the detected objects in the image frame. The formation of the metadata frame may be based on information from the object detection method and / or further analysis of the detected objects.

[0054] Even if a digital signature is described with respect to a single metadata frame, it can also be included in a metadata frame in which the digital signature is for two or more metadata frames, for example, for metadata frames in sequence associated with all image frames of a group of pictures (GOP). The digital signature will then be based on at least a subset of the metadata of each of the metadata frames.

[0055] In the following text, reference will be made to Figure 2 This section discusses an embodiment of a method 200 for authenticating digitally signed metadata frames corresponding to image frames in an image frame sequence. The metadata frame includes metadata about one or more detected objects in the image frame. The metadata for each detected object includes coordinates defining the location of the detected object within the image frame. Furthermore, the metadata frame includes additional metadata and predefined coordinates, the additional metadata including a digital signature for at least a subset of the metadata in the metadata frame, the predefined coordinates defining the additional metadata including the digital signature. In other words, the metadata frame is authenticated by... Figure 1 The described method 100 generates a metadata frame. Method 200 includes identifying (S210) predefined coordinates that define additional metadata, including a digital signature. The digital signature is then retrieved (S220) from the additional metadata, and at least one subset of the metadata is authenticated based on the digital signature (S230). How the digital signature is used to authenticate the metadata frame (verify its authenticity) depends on the type of digital signature used. For example, a digital signature for the metadata frame can be created by applying the private key from a public-private key pair to the hash value of at least a portion of the metadata frame. The authenticity of the metadata frame can then be verified by decrypting the digital signature using the public key from the public-private key pair and comparing the result with the corresponding hash value of at least a portion of the metadata frame received in the metadata frame. The same hash function used to generate the hash value on which the digital signature is based should be used to generate the hash value from at least one subset of the received metadata. If they are equal, the authenticity of the metadata frame is verified, i.e., the metadata frame is intact and originates from a genuine source. If they are not equal, the authenticity of the metadata frame has not been verified, and the metadata frame is either not intact or does not originate from a genuine source.

[0056] In the following text, reference will be made to Figure 3An embodiment of a device 300 for signing metadata corresponding to image frames in an image frame sequence is discussed. The metadata frame includes metadata of one or more detected objects in the image frame. Furthermore, the metadata for each detected object includes coordinates defining the location of the detected object within the image frame. Device 300 includes circuitry 310. Circuitry 310 is configured to perform the functions of device 300. Circuitry 310 may include a processor 312, such as a central processing unit (CPU), microcontroller, or microprocessor. Processor 312 is configured to execute program code. The program code may, for example, be configured to perform the functions of device 300.

[0057] Device 300 may further include memory 330. Memory 330 may be one or more of a buffer, flash memory, hard disk drive, removable media, volatile memory, non-volatile memory, random access memory (RAM), or another suitable device. In a typical arrangement, memory 330 may include non-volatile memory for long-term data storage and volatile memory used as system memory for circuit 310. Memory 330 may exchange data with circuit 310 via a data bus. Additional control lines and an address bus may also exist between memory 330 and circuit 310.

[0058] The functionality of device 300 can be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.), which are stored on a non-transitory computer-readable medium (e.g., memory 330) of system 300 and executed by circuitry 310 (e.g., using processor 312). Furthermore, the functionality of the system device can be a standalone software application or part of a software application for performing additional tasks associated with the system device. The described functionality can be considered as a method by which a processing unit (e.g., processor 312 of circuitry 310) is configured to execute it. Moreover, while the described functionality can be implemented in software, it can also be implemented via dedicated hardware or firmware, or a combination of hardware, firmware, and / or software.

[0059] Circuit 310 is configured to perform generation function 331, which is configured to generate a digital signature using at least a subset of metadata in a metadata frame.

[0060] Circuit 310 is further configured to perform an add function 332, which is configured to add additional metadata to a metadata frame, the additional metadata including a digital signature and predefined coordinates, the predefined coordinates defining the additional metadata including the digital signature.

[0061] The generation function 331 can be configured to hash at least a subset of the metadata to generate a hash value, and generate a digital signature based on the hash value.

[0062] Circuit 330 may be further configured to perform an acquisition function 333 and a detection function 334, wherein the acquisition function 333 is configured to acquire an image frame sequence and the detection function 334 is configured to detect objects in the image frames of the image frame sequence.

[0063] Circuit 310 may be further configured to perform a forming function 335, which is configured to form a metadata frame based on objects detected in the image frame.

[0064] Device 300 can be implemented in a single physical unit, so that all functions are implemented in that single physical unit. Alternatively, device 300 can be implemented in more than one physical unit, so that functions are implemented in two or more different physical units.

[0065] The function performed by circuit 310 can be further adapted to be about Figure 1 The corresponding steps of an embodiment of the described method.

[0066] In the following text, reference will be made to Figure 4 An embodiment of a device 400 for authenticating digitally signed metadata frames corresponding to image frames in an image frame sequence will be discussed. Figure 4 A schematic diagram related to an embodiment of device 400 is shown. A metadata frame includes metadata for one or more detected objects in an image frame. The metadata for each detected object includes coordinates defining the location of the detected object in the image frame. Furthermore, the metadata frame further includes additional metadata and predefined coordinates, the additional metadata including a digital signature for at least a subset of the metadata in the metadata frame, the predefined coordinates defining the additional metadata including the digital signature. Device 400 includes circuitry 410. Circuitry 410 is configured to perform the functions of device 400. Circuitry 410 may include a processor 412, such as a central processing unit (CPU), microcontroller, or microprocessor. Processor 412 is configured to execute program code. This program code may, for example, be configured to perform the functions of device 400.

[0067] Device 400 may further include memory 430. Memory 430 may be one or more of a buffer, flash memory, hard disk drive, removable media, volatile memory, non-volatile memory, random access memory (RAM), or another suitable device. In a typical arrangement, memory 430 may include non-volatile memory for long-term data storage and volatile memory serving as system memory for circuit 410. Memory 430 may exchange data with circuit 410 via a data bus. Additional control lines and an address bus may also exist between memory 430 and circuit 410.

[0068] The functionality of device 400 can be implemented as an executable logic routine (e.g., lines of code, software program, etc.) stored on a non-transitory computer-readable medium (e.g., memory 430) of system 400 and executed by circuitry 410 (e.g., using processor 412). Furthermore, the functionality of the system device can be a standalone software application or part of a software application for performing additional tasks associated with the system device. The described functionality can be considered as a method by which a processing unit (e.g., processor 412 of circuitry 410) is configured to execute it. Moreover, while the described functionality can be implemented in software, it can also be implemented via dedicated hardware or firmware, or a combination of hardware, firmware, and / or software.

[0069] Circuit 410 is configured to perform identification function 431, which is configured to identify predefined coordinates that define additional metadata including a digital signature.

[0070] Circuit 410 is further configured to perform a retrieval function 432, which is configured to retrieve a digital signature from additional metadata.

[0071] Circuit 410 is also configured to perform authentication function 433, which is configured to authenticate metadata frames based on digital signatures.

[0072] By including the digital signature as additional metadata in the metadata frame and using predefined coordinates to indicate that the additional metadata includes the digital signature, the predefined coordinate digital signature can be identified, and the digital signature can be retrieved in the receiver for authentication of the metadata frame without adjusting the protocol used to transmit the metadata or the format of the metadata frame (i.e., how the metadata is represented). Instead, device 400 only needs to know the predefined coordinates that define the additional metadata including the digital signature. Device 400 only needs to know the predefined coordinates once, and this can be done offline.

[0073] The authentication function 433 can be configured to hash at least a subset of the received metadata to generate a hash value, decrypt the digital signature, and compare the hash value with the decrypted digital signature. If they are equal, the metadata frame is authenticated, meaning the metadata frame is intact and originates from a legitimate source. If they are not equal, the metadata frame is either not intact or does not originate from a legitimate source.

[0074] Device 400 can be implemented in a single physical unit, such that all functions are implemented within that single physical unit. Alternatively, device 400 can be implemented in more than one physical unit, such that functions are implemented in two or more different physical units.

[0075] The function performed by circuit 410 can be further adapted to be about Figure 2 The corresponding steps of an embodiment of the described method.

Claims

1. A method for signing a metadata frame corresponding to an image frame in an image frame sequence, wherein the metadata frame includes a separate metadata item for each of one or more detected objects in the image frame, wherein the separate metadata item for each detected object includes coordinates defining the location of the detected object in the image frame and includes further information about the detected object, the method comprising: A digital signature is generated based on at least a subset of the metadata items in the metadata frame, wherein the digital signature is capable of verifying the authenticity of the metadata frame; as well as An additional separate metadata item is added to the metadata frame, the additional separate metadata item including the digital signature and predefined coordinates, the predefined coordinates being specifically used to define the additional separate metadata item including the digital signature and to ensure that the predefined coordinates are not associated with the detected object.

2. The method according to claim 1, wherein, The predefined coordinates define the position of objects without extensions.

3. The method according to claim 1, wherein, The coordinates represent the top-left and bottom-right corners of the bounding box associated with the detected object, and the predefined coordinates represent the same coordinates for the top-left corner and the bottom-right corner.

4. The method according to claim 1, wherein, In the process of generating the digital signature, the digital signature is generated based on the private key in the public key and private key pair.

5. The method of claim 1, wherein, The actions for generating the digital signature include: Hash at least one subset of the metadata item to generate a hash value; and The digital signature is generated based on the hash value.

6. The method according to claim 1, wherein, The additional separate metadata item uses the same syntax as the metadata item for each detected object.

7. The method of claim 1, further comprising: The metadata frame is formed based on one or more detected objects in the image frame.

8. The method of claim 7, further comprising: Obtain the image frame sequence; as well as Detect one or more objects in the image frames of the image frame sequence.

9. A method for authenticating a digitally signed metadata frame corresponding to an image frame in an image frame sequence, wherein the metadata frame includes a separate metadata item for each of one or more detected objects in the image frame, wherein the separate metadata item for each detected object includes coordinates defining the location of the detected object in the image frame and including further information about the detected object, and wherein the metadata frame further includes an additional separate metadata item, the additional separate metadata item including a digital signature for at least a subset of the metadata items in the metadata frame and predefined coordinates specifically used to define the additional separate metadata item including the digital signature and such that the predefined coordinates cannot be associated with the detected object, the method comprising: Identify the predefined coordinates, which are dedicated to defining the additional separate metadata item including the digital signature and cannot be associated with the detected object; Retrieve the digital signature from the additional separate metadata item; as well as The metadata frame is authenticated based on the digital signature.

10. A non-transitory computer-readable storage medium having instructions stored thereon, which, when executed in a device having at least one processor, are used to implement the method according to any one of claims 1 and 9.

11. An apparatus for signing metadata frames corresponding to image frames in an image frame sequence, wherein the metadata frame includes a separate metadata item for each of one or more detected objects in the image frame, wherein the separate metadata item for each detected object includes coordinates defining the location of the detected object in the image frame and includes further information about the detected object, the apparatus including circuitry configured to perform: A generation function is configured to generate a digital signature using at least a subset of the metadata items in the metadata frame, wherein the digital signature is capable of verifying the authenticity of the metadata frame; and An add function is configured to add an additional separate metadata item to the metadata frame, the additional separate metadata item including the digital signature and predefined coordinates, the predefined coordinates being specifically used to define the additional separate metadata item including the digital signature and to ensure that the predefined coordinates are not associated with the detected object.

12. The apparatus of claim 11, wherein, The generation function is configured as follows: Hash at least one subset of the metadata item to generate a hash value; as well as The digital signature is generated based on the hash value.

13. The device according to claim 11, wherein, The circuit is further configured to perform: The forming function is configured to form the metadata frame based on the detected objects in the image frame.

14. The device according to claim 11, wherein, The circuit is further configured to perform: The function is configured to acquire the image frame sequence, and The detection function is configured to detect objects in the image frames of the image frame sequence.

Images