DEVICE AND METHOD FOR SIGNING METADATA FRAME CORRECTING IMAGE FRAME OF A SEQUENCE OF IMAGE FRAMES - Patent application

Abstract

To provide a device and a method of signing a metadata frame corresponding to an image frame of a sequence of image frames, and a non-transitory computer-readable storage medium.SOLUTION: In a method 100 for signing metadata, a device acquires a sequence of an image frame (S102), detects an object in the image frame of the sequence of the image frame (S104), forms a metadata frame on the basis of the detected object in the image frame (S106), generates a digital signature on the basis of at least a subset of the metadata in the metadata frame (S110), and adds additional metadata to the metadata frame (S120). The metadata frame comprises metadata of one or more detected objects in the image frame, and the metadata comprises coordinates defining a location in the image frame of the object.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to authenticating metadata, and in particular to signing metadata frames corresponding to image frames of a sequence of image frames. [Background technology]

[0002] In some applications, it is desirable to verify that the metadata in metadata frames, each of which corresponds to a respective image frame in a sequence of image frames, is intact, i.e., has not been tampered with since its generation, and that the metadata originates from an authentic source. One way to enable such verification of metadata corresponding to a sequence of image frames is to generate a digital signature for the metadata frame. The digital signature is then transmitted in a header of a metadata stream containing the metadata frame and can be used at the receiver side to verify that the metadata in the metadata frame is intact and that the digital signature was generated by an authentic source. However, if a digital signature is generated for every metadata frame associated with a sequence of image frames, all of the metadata frames will be considered to be incomplete or received from an inauthentic source if the digital signature cannot be verified. Thus, an alteration in a single metadata frame has the effect of causing multiple metadata frames in a stream segment to be considered inauthentic and untrustworthy. Regarding this issue, there is a need for an improved method for signing metadata. Summary of the Invention

[0003] It is an object of the present invention to facilitate enhancements to the signing and transmission of metadata corresponding to a sequence of image frames.

[0004] According to a first aspect, there is provided a method for signing a metadata frame corresponding to an image frame of a sequence of image frames. The metadata frame includes metadata for one or more detected objects within the image frame. Further, the metadata for each detected object includes coordinates defining a location of the detected object within 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 that define that the additional metadata includes the digital signature.

[0005] By generating a separate digital signature for the metadata frame, the metadata frame can be authenticated separately. Furthermore, by including the digital signature as additional metadata within the metadata frame and using predefined coordinates to indicate that the additional metadata includes a digital signature, the digital signature can be transmitted in each metadata frame without having to conform to the format of the metadata frame, i.e., the format of how the metadata is expressed, and without having to conform to a protocol for transmitting the metadata. Instead, the receiving device can recognize the predefined coordinates that specify that the additional metadata includes a digital signature. The receiving device only needs to recognize the predefined coordinates once, and this can be done offline. Furthermore, the digital signature can be transmitted within the metadata frame for which the digital signature will be used for authentication. This is more efficient and discrete than transmitting the digital signature separately from the metadata frame.

[0006] By digital signature we mean any kind of digital signature that allows to verify the authenticity of the metadata frame.

[0007] The predefined coordinates may be dedicated to defining that the additional metadata includes a digital signature. This also means that the predefined coordinates cannot be used as coordinates for the actual object. By choosing such dedicated coordinates, there is no risk that the detected object will have predefined coordinates, and thus the metadata of the detected object will be interpreted as a digital signature.

[0008] The predefined coordinates may define the position of an object that does not have an extension, so that there is no risk that the detected object has predefined coordinates because the detected object has an extension.

[0009] The coordinates may, for example, represent the upper left and lower right corners of a bounding box associated with the detected object, and the predefined coordinates represent the same coordinates for the upper left and lower right corners, such that there is no risk that the detected object will have predefined coordinates because the detected object will have different coordinates for the upper left and lower right corners.

[0010] In the act of generating a digital signature, the digital signature may be generated based on a private key of a public and private key pair.

[0011] The act of generating a digital signature may include hashing at least a subset of the metadata, thereby generating a hash, and generating a digital signature based on the hash.

[0012] The metadata for each detected object may be represented as a separate item in the metadata frame, each separate item including coordinates defining the location of the detected object within the image frame, and additional metadata being represented as additional separate items.

[0013] The additional metadata may use the same syntax as the metadata for each detected object.

[0014] The method may further include forming a metadata frame based on the detected object in the image frame.

[0015] The method may further include obtaining a sequence of image frames and detecting an object within an image frame of the sequence of image frames.

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

[0017] By including a digital signature as additional metadata in a metadata frame and using predefined coordinates to indicate that the additional metadata includes a digital signature, the digital signature can be identified and extracted at a receiver for authentication of the metadata frame without having to conform to a protocol for transmitting the metadata and without having to conform to the format of the metadata frame, i.e., how the metadata is represented. Instead, the receiving device only needs to recognize the predefined coordinates that specify that the additional metadata includes a digital signature. The receiving device only needs to recognize the predefined coordinates once, and this can be done offline.

[0018] According to a third aspect, there is provided a non-transitory computer-readable storage medium storing instructions for implementing a method according to the first or second aspect when executed on a device having at least one processor.

[0019] According to a fourth aspect, there is provided a device for signing a metadata frame corresponding to an image frame of a sequence of image frames. The metadata frame includes metadata for one or more detected objects within the image frame. Further, the metadata for each detected object includes coordinates defining a location of the detected object within the image frame. The device includes circuitry configured to perform a generating function configured to generate a digital signature based on at least a subset of the metadata in the metadata frame, and an adding function configured to add additional metadata to the metadata frame, the additional metadata including the digital signature and predefined coordinates that define the additional metadata to include the digital signature.

[0020] The generating function may be configured to hash at least a subset of the metadata, thereby generating a hash, and generate a digital signature based on the hash.

[0021] The circuitry may be further configured to perform a formation function configured to form a metadata frame based on the detected object within the image frame.

[0022] The circuitry may be further configured to perform an acquisition function configured to acquire a sequence of image frames and a detection function configured to detect an object within an image frame of the sequence of image frames.

[0023] The above-mentioned optional additional features of the method according to the first aspect, when applicable, also apply to the device according to the fourth aspect, and to avoid undue repetition, reference is made thereto.

[0024] Further scope of the applicability of the present invention will become apparent from the detailed description given hereinafter. However, the detailed description and specific examples are given by way of illustration only, since while indicating preferred embodiments of the invention, various changes and modifications within the scope of the invention will become apparent to those skilled in the art from this detailed description.

[0025] Thus, it will be understood that the present invention is not limited to the specific component parts of such devices or the operation of such methods, as the described devices and methods may vary. It will 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 should be noted that, as used in the specification and the appended claims, the articles "a," "an," "the," and "said" are intended to mean that one or more of an element are present, unless the context clearly dictates otherwise. Thus, for example, reference to "a unit" or "the unit" can include several devices, and the like. Furthermore, the words "comprising," "including," "containing," and similar words do not exclude other elements or steps.

[0026] These and other aspects of the present invention will now be described in more detail with reference to the accompanying figures, which should not be considered limiting, but instead are used for purposes of explanation and understanding. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a flowchart relating to an embodiment of a method for signing metadata corresponding to an image frame of a sequence of image frames. [Figure 2] 1 is a flowchart relating to an embodiment of a method for authenticating a digitally signed metadata frame corresponding to an image frame of a sequence of image frames. [Figure 3] 1 is a schematic diagram relating to an embodiment of a device for signing metadata corresponding to an image frame of a sequence of image frames; [Figure 4] 1 is a schematic diagram relating to an embodiment of a device for authenticating a digitally signed metadata frame corresponding to an image frame of a sequence of image frames; DETAILED DESCRIPTION OF THE INVENTION

[0028] The present invention will now be described below with reference to the accompanying drawings, in which presently preferred embodiments of the invention are illustrated. However, this invention may be embodied in many different forms and should not be taken as limited to the embodiments set forth herein.

[0029] In applications where metadata frames correspond to image frames of a sequence of image frames, each metadata frame containing metadata related to one or more objects detected in the corresponding image frame and defining the location of each object by means of object coordinates, embodiments of the invention can be used to verify the authenticity of the metadata to ensure that it is intact, i.e., has not been tampered with since its generation, and comes from an authentic source. The metadata is typically generated using analysis of the image frames and may further relate to further analytical information, such as object ID, object class, object color, etc. The metadata may also relate to things other than objects, such as information related to audio, radar, etc. The format and syntax used to represent the metadata are predefined, for example, by standard means, so that both the transmitter and receiver recognize the format and syntax. One standard for metadata representation and transmission is ONVIF Profile M. An example of what metadata according to ONVIF Profile M might look like for a metadata frame containing metadata about an object is shown below. TIFF0007784399000001.tif133170

[0030] The tag "BoundingBox" is used to represent the image coordinates of the bounding box for the detected object. In this example, the coordinates for 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 contained further objects, metadata for such further objects would have been included in association with objects that had different IDs, i.e., different values ​​for the tag "ObjectId".

[0031] At the receiver side, including the decoder, the digital signature for the metadata frame can be used to verify the authenticity of the metadata frame. For example, if the digital signature for the metadata frame was created by encryption of a hash of at least a portion of the metadata frame by means of the private key of a public-private key pair, it can be verified that the metadata is uncorrupted and comes from an authentic source by decrypting using the public key of the public-private key pair of the digital signature and comparing the result to the corresponding hash of at least a portion of the metadata frame as received at the receiver side. If they are equal, the metadata frame is uncorrupted and comes from an authentic source; if they are not equal, the metadata frame has either been corrupted (altered / tampered with) or does not come from an authentic source.

[0032] An embodiment of a method 100 for signing a metadata frame corresponding to an image frame of a sequence of image frames will be discussed below with reference to FIG. 1. The metadata frame includes metadata of one or more detected objects within the image frame. Furthermore, the metadata for each detected object includes coordinates defining the location of the detected object within the image frame. The method 100 includes generating a digital signature based on at least a subset of the metadata within the metadata frame (S110) and adding additional metadata to the metadata frame (S120). The additional metadata includes the digital signature and predefined coordinates that define that the additional metadata includes the digital signature. This differs from prior art, in which the digital signature is transmitted, for example, within a header of a metadata stream and is associated with all metadata frames within the metadata stream. By including the digital signature as additional metadata within the metadata frame and using the predefined coordinates to indicate that the additional metadata includes the digital signature, a respective digital signature can be transmitted in each metadata frame. Furthermore, the predefined coordinates allow the digital signature to be identified and extracted at a receiver for authentication of the metadata frame without the need to comply with a protocol for transmitting the metadata. This can be achieved without having to conform to the format of the metadata frame, i.e., the format of how the metadata is represented. Instead, the receiving device only needs to recognize predefined coordinates that specify that the additional metadata includes a digital signature. The receiving device only needs to recognize the predefined coordinates once, and this can be done offline.

[0033] By the digital signature being based on "at least a subset" of the metadata in the metadata frame, it is meant that the digital signature need only be based on the metadata of the metadata frame to be able to be verified. For example, the digital signature may be based on metadata associated with only a subset of the objects found in the frame. For example, it may be determined that only metadata for one or more particular types of objects needs to be able to be verified. In such a case, the digital signature may be generated based on object-related metadata for those one or more particular types of objects.

[0034] It will be appreciated that the predefined coordinates are also known to the device receiving the metadata frame. The receiving device interprets the metadata according to the predefined format and syntax used and interprets the metadata accordingly. When interpreting the additional metadata, the receiving device identifies the coordinates as being coordinates that specify that the additional metadata includes a digital signature.

[0035] The predefined coordinates are preferably static, i.e., the same predefined coordinates are used over time to define the additional metadata including the digital signature. Alternatively, the predefined coordinates may be variable over time, but in such a way that the receiving device knows which coordinates are used in association with each metadata frame.

[0036] The predefined coordinates may be dedicated for defining that the additional metadata includes a digital signature, i.e., the predefined coordinates may not also be used as coordinates for the actual object. By selecting such dedicated coordinates, there is no risk that the actual object will have the predefined coordinates, and thus the metadata of the actual object will be interpreted as a digital signature. Method 100 may further include the operations of selecting the predefined coordinates and dedicating the predefined coordinates for defining that the additional metadata includes a digital signature.

[0037] Furthermore, if the predefined format and syntax used for expressing the metadata requires that the additional metadata specify an object, to include coordinates, then the dummy object may be identified using an identifier that is different from any actual object identified for which metadata is provided in the metadata frame. Thus, the additional metadata may further include an object ID, and the predefined coordinates may be indicated in relation to that object ID.

[0038] To implement dedicated predefined coordinates, the predefined coordinates may not be related to an actual object. For example, the predefined coordinates may define the location of an object without extension. For example, if the coordinates represent the upper left and lower right corners of a bounding box associated with a detected object, such as ONVIF Profile M, the predefined coordinates have the same coordinates for the upper left corner as for the lower right corner. This is also applicable when using a different format and syntax in which the bounding box is defined by the upper right and lower left corners. In another example, the coordinates may represent the upper left corner and the distance to the lower right corner. To define the location of an object without extension, the predefined coordinates have an arbitrary coordinate for the upper left corner and an indication of a zero distance to the lower right corner. This is also applicable when the bounding box is defined by the coordinates of any of the other corners and the distance from that corner to the corner diagonally across the bounding box. The predefined coordinates may remain the same over time or may change as long as the predefined coordinates indicate an object without extension, i.e., a bounding box of zero pixels.

[0039] Other alternatives for realizing the dedicated predefined coordinates are also envisioned. For example, the predefined coordinates may be such that the object has a negative extension, e.g., the top left corner is located below and / or to the right of the bottom right corner. In another example, the predefined coordinates may be such that the object is located completely or partially outside the image frame, e.g., the top left corner and / or the bottom right corner is located outside the image frame.

[0040] The advantage of using predefined coordinates that cannot be associated with an actual object is that if a device receiving the metadata frame does not recognize the predefined coordinates, it will simply ignore the additional metadata as it will not be able to interpret the predefined coordinates as relating to an object.

[0041] The digital signature may be any type of digital signature that allows authenticity to be verified. For example, the digital signature may be generated based on the private key of a public and private key pair. For example, Rivest-Shamir-Adleman (RSA) 256-bit encryption, Digital Signature Algorithm (DSA), and Elliptic Curve Digital Signing Algorithm (ECDSA) may be used to generate the digital signature. A digital signature for a metadata frame may be generated by applying a private key to the metadata or a subset of the metadata of the metadata frame. However, to reduce the size of the digital signature, the metadata may first be hashed by means of a hash function, such as a cryptographic hash function, to generate a hash (S112). A digital signature may then be generated based on the hash (S114), for example, by applying the private key to the hash. Examples of cryptographic hash functions are MD5, SHA-1, SHA-2 (SHA-256 / SHA-512), SHA-3, and BLAKE-3.

[0042] The metadata for each detected object may be represented as a separate item in the metadata frame, with each separate item including coordinates that define the location of the detected object within the image frame. By way of example, for metadata according to ONVIF Profile M as illustrated above, an item associated with an object may refer to the metadata as "<tt:Object ObjectId”12”> " and " are located between the lines that state "<tt:Object ObjectId”12”> " and " In such cases, the additional metadata may also be represented as additional separate items using the same format and syntax.

[0043] The additional metadata may use the same syntax and / or format as the metadata of each detected object. Thus, the syntax and / or format used for the detected object is also used for the additional metadata. Thus, the additional metadata is interpreted as metadata related to the object, and the receiving device can interpret the additional data. When the receiving device identifies the predefined coordinates, the receiving device can interpret the additional metadata as including a digital signature.

[0044] For example, if additional metadata is added as metadata associated with an object according to ONVIF Profile M, the tag "BoundingBox" may contain left="20.0" top="180.0" right="20.0" bottom="180.0", or any other coordinates that indicate a bounding box of no extent, i.e., zero pixels. The digital signature may then be included in the same position as the tag "Type", i.e., "Vehicle", is in the example metadata frame according to ONVIF Profile M as described above.

[0045] The digital signature may be included in the additional metadata using an existing variable or tag, according to the syntax and format used for the metadata frame, which is used to provide metadata about some other characteristic of the object. The only requirement is that the existing variable or tag be allowed to contain a sufficient number of bits to contain the digital signature. The receiving device then needs to know that when the predefined coordinates are identified, an existing tag or variable will be used to contain the digital signature in the additional metadata. Alternatively, a new variable or tag "Digital Signature" or similar may be added.

[0046] The method 100 may further include acquiring the sequence of image frames (S102). The sequence of image frames may be acquired by capturing the sequence of image frames with the camera if the method 100 is performed in a camera (S102). Alternatively, the sequence of image frames may be acquired by receiving them directly from the camera or via another device if the method is performed in a device separate from the camera (S102).

[0047] The method 100 may further include detecting an object in an image frame of the sequence of image frames (S104). The object may be detected using any type of object detection method.

[0048] The method 100 may further include forming a metadata frame (S106) based on the detected objects in the image frame. Forming the metadata frame may be based on information from the object detection method and / or further analysis of the detected objects.

[0049] Even when a digital signature is described relative to one metadata frame, the digital signature may be included in a metadata frame for more than one metadata frame, for example, for sequential metadata frames associated with all image frames of a group of pictures (GOP). The digital signature is then based on at least a subset of the metadata of each of the metadata frames.

[0050] In the following, an embodiment of a method 200 for authenticating a digitally signed metadata frame corresponding to an image frame of a sequence of image frames will be discussed with reference to FIG. 2. The metadata frame includes metadata of one or more detected objects within the image frame. The metadata of each detected object includes coordinates that define the location of the detected object within the image frame. Furthermore, the metadata frame includes additional metadata including a digital signature for at least a subset of the metadata in the metadata frame and predefined coordinates that define that the additional metadata includes the digital signature. In other words, the metadata frame is a metadata frame such as that generated by the method 100 described with reference to FIG. 1. The method 200 includes identifying (S210) the predefined coordinates that define that the additional metadata includes the digital signature. The digital signature is then extracted from the additional metadata (S220), and at least the subset of the metadata is authenticated based on the digital signature (S230). How the digital signature is used to authenticate the metadata frame (verify the authenticity of the metadata frame) depends on the type of digital signature used. For example, a digital signature for a metadata frame could be created by applying the private key of a public and private key pair to hash 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 of the public and private key pair and comparing the result to the corresponding hash of at least a portion of the metadata frame as received in the metadata frame. The same hash function used to generate the hash on which the digital signature is based should be used to generate the hash from at least a subset of the metadata as received. If they are equal, the authenticity of the metadata frame is verified, i.e., the metadata frame is uncorrupted and comes from an authentic source. If they are not equal, the authenticity of the metadata frame is not verified, and the metadata frame is either corrupted or does not come from an authentic source.

[0051] In the following, an embodiment of a device 300 for signing metadata corresponding to an image frame of a sequence of image frames will be discussed with reference to FIG. 3. The metadata frame includes metadata of one or more detected objects within the image frame. Furthermore, the metadata of each detected object includes coordinates defining the position of the detected object within the image frame. The device 300 includes a circuit 310. The circuit 310 is configured to perform the functions of the device 300. The circuit 310 may include a processor 312, such as a central processing unit (CPU), a microcontroller, or a microprocessor. The processor 312 is configured to execute program code. The program code may, for example, be configured to perform the functions of the device 300.

[0052] The device 300 may further include a memory 330. The memory 330 may be one or more of a buffer, flash memory, a hard drive, removable media, volatile memory, non-volatile memory, random access memory (RAM), or another suitable device. In a typical arrangement, the memory 330 may include non-volatile memory for long-term data storage and volatile memory that serves as system memory for the circuit 310. The memory 330 may exchange data with the circuit 310 over a data bus. There may also be associated control lines and address buses between the memory 330 and the circuit 310.

[0053] The functionality of device 300 may be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.) stored in a non-transitory computer-readable medium (e.g., memory 330) of system 300 and executed by circuit 310 (e.g., using processor 312). Furthermore, the functionality of the system device may be a standalone software application or may form part of a software application that performs additional tasks related to the system device. The described functions may be considered as methods that a processing unit, e.g., processor 312 of circuit 310, is configured to perform. Also, while the described functions may be implemented in software, such functionality may also be implemented via dedicated hardware or firmware, or some combination of hardware, firmware, and / or software.

[0054] The circuit 310 is configured to execute a generating function 331 configured to generate a digital signature using at least a subset of the metadata in the metadata frame.

[0055] The circuit 310 is further configured to perform an additional function 332 configured to add additional metadata to the metadata frame, the additional metadata including a digital signature and predefined coordinates that specify that the additional metadata includes the digital signature.

[0056] The generation function 331 may be configured to hash at least a subset of the metadata, thereby generating a hash, and to generate a digital signature based on the hash.

[0057] The circuit 310 may be further configured to perform an acquisition function 333 configured to acquire a sequence of image frames and a detection function 334 configured to detect an object within an image frame of the sequence of image frames.

[0058] The circuit 310 may further be configured to execute a forming function 335 configured to form a metadata frame based on the detected objects in the image frame.

[0059] Device 300 may be realized in a single physical unit, such that all of the functionality is implemented in the single physical unit, or alternatively, device 300 may be realized in more than one physical unit, such that the functionality is implemented in two or more different physical units.

[0060] The functions performed by circuit 310 may further be adapted as corresponding steps of the method embodiments described in connection with FIG.

[0061] In the following, an embodiment of a device 400 for authenticating a digitally signed metadata frame corresponding to an image frame of a sequence of image frames will be discussed with reference to Fig. 4. Fig. 4 shows a schematic diagram relating to an embodiment of the device 400. The metadata frame includes metadata of one or more detected objects within the image frame. The metadata of each detected object includes coordinates that define the location of the detected object within the image frame. Furthermore, the metadata frame includes It also contains additional metadata , Additional metadata is A digital signature of at least a subset of the metadata within the metadata frame Name and , predefined coordinates specifying that the additional metadata includes a digital signature; Including The device 400 includes a circuit 410. The circuit 410 is configured to perform the functions of the device 400. The circuit 410 may include a processor 412, such as a central processing unit (CPU), a microcontroller, or a microprocessor. The processor 412 is configured to execute program code. The program code may be configured to perform the functions of the device 400, for example.

[0062] The device 400 may further include a memory 430. The memory 430 may be one or more of a buffer, flash memory, a hard drive, removable media, volatile memory, non-volatile memory, random access memory (RAM), or another suitable device. In a typical arrangement, the memory 430 may include non-volatile memory for long-term data storage and volatile memory that serves as system memory for the circuit 410. The memory 430 may exchange data with the circuit 410 over a data bus. There may also be associated control lines and address buses between the memory 430 and the circuit 410.

[0063] The functionality of device 400 may be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.) stored in a non-transitory computer-readable medium (e.g., memory 430) of system 400 and executed by circuit 410 (e.g., using processor 412). Furthermore, the functionality of the system device may be a standalone software application or may form part of a software application that performs additional tasks related to the system device. The described functionality may be considered as a method that a processing unit, e.g., processor 412 of circuit 410, is configured to perform. Also, while the described functionality may be implemented in software, such functionality may also be implemented via dedicated hardware or firmware, or some combination of hardware, firmware, and / or software.

[0064] The circuit 410 is configured to perform an identification function 431 configured to identify predefined coordinates that specify that the additional metadata includes a digital signature.

[0065] The circuit 410 is further configured to execute a retrieval function 432 configured to retrieve the digital signature from the additional metadata.

[0066] The circuit 410 is further configured to perform an authentication function 433 configured to authenticate the metadata frame based on the digital signature.

[0067] By including a digital signature as additional metadata in the metadata frame and using predefined coordinates to indicate that the additional metadata includes a digital signature, the digital signature at the predefined coordinates can be identified and extracted at a receiver for authentication of the metadata frame without having to conform to a protocol for transmitting the metadata and without having to conform to the format of the metadata frame, i.e., how the metadata is represented. Instead, device 400 only needs to recognize the predefined coordinates that specify that the additional metadata includes a digital signature. Device 400 only needs to recognize the predefined coordinates once, and this can be done offline.

[0068] The authentication function 433 may be configured to hash at least a subset of the received metadata, thereby generating a hash, decrypting the digital signature, and comparing the hash to the decrypted digital signature. If they are equal, the metadata frame is authenticated, i.e., the metadata frame is uncorrupted and comes from an authentic source. If they are not equal, the metadata frame is either corrupted or does not come from an authentic source.

[0069] Device 400 may be realized in a single physical unit, such that all of the functionality is implemented in the single physical unit, or alternatively, device 400 may be realized in more than one physical unit, such that the functionality is implemented in two or more different physical units.

[0070] The functions performed by circuit 410 may further be adapted as corresponding steps of the method embodiments described in connection with FIG.

Claims

1. 1. A method of operating at least one processor to sign metadata frames corresponding to image frames of a sequence of image frames, the metadata frames including metadata for one or more detected objects within the image frames, the metadata for each detected object including coordinates defining a position of the detected object within the image frame, the method comprising: generating, by the at least one processor, a digital signature based on at least a subset of the metadata in the metadata frame; adding, by the at least one processor, additional metadata to the metadata frame, the additional metadata including the digital signature and predefined coordinates that specify that the additional metadata includes the digital signature; A method comprising:

2. The method of claim 1 , wherein the predefined coordinates are dedicated to defining that the additional metadata includes the digital signature.

3. The method of claim 1 , wherein the predefined coordinates define a position of an object that has no extension.

4. The method of claim 1 , wherein the coordinates represent the upper left and lower right corners of a bounding box associated with the detected object, and the predefined coordinates represent the same coordinates for the upper left and lower right corners.

5. 2. The method of claim 1, wherein in the act of generating the digital signature, the at least one processor generates the digital signature based on a private key of a public and private key pair.

6. The act of generating a digital signature comprises: the at least one processor hashing the at least a subset of the metadata, thereby generating a hash; the at least one processor generating the digital signature based on the hash; and The method of claim 1 , comprising:

7. 2. The method of claim 1 , wherein the metadata for each detected object is represented as a separate item in the metadata frame, each separate item including the coordinates defining the position of the detected object in the image frame, and the additional metadata is represented as an additional separate item.

8. The method of claim 1 , wherein the additional metadata uses the same syntax as the metadata for each detected object.

9. The method of claim 8, wherein the at least one processor forms the metadata frame based on the one or more detected objects in the image frame. The method of claim 1 further comprising:

10. The method of claim 1, wherein the at least one processor acquires the sequence of image frames; the at least one processor detecting one or more objects within the image frames of the sequence of image frames; 10. The method of claim 9, further comprising:

11. 1. A method of operating at least one processor to authenticate a digitally signed metadata frame corresponding to an image frame of a sequence of image frames, the metadata frame including metadata of one or more detected objects within the image frame, the metadata for each detected object including coordinates defining a location of the detected object within the image frame, the metadata frame further including additional metadata including a digital signature for at least a subset of the metadata in the metadata frame and predefined coordinates that specify that the additional metadata includes the digital signature, the method comprising: the at least one processor identifying the predefined coordinates that specify that the additional metadata includes the digital signature; the at least one processor extracting the digital signature from the additional metadata; the at least one processor authenticating the metadata frame based on the digital signature; A method comprising:

12. A non-transitory computer-readable storage medium storing instructions for implementing the method of any one of claims 1 to 11 when executed on a device having at least one processor.

13. 1. A device for signing a metadata frame corresponding to an image frame of a sequence of image frames, the metadata frame including metadata of one or more detected objects within the image frame, the metadata for each detected object including coordinates defining a position of the detected object within the image frame, the device: a generating function configured to generate a digital signature using at least a subset of the metadata in the metadata frame; an add function configured to add additional metadata to the metadata frame, the additional metadata including the digital signature and predefined coordinates that specify that the additional metadata includes the digital signature; and 11. A device comprising: circuitry configured to perform

14. The generating function is hashing the at least a subset of the metadata, thereby generating a hash; generating the digital signature based on the hash; The device of claim 13 configured to:

15. The circuit comprises: a forming function configured to form the metadata frame based on the detected object in the image frame; 15. The device of claim 13 or 14, further configured to:

16. The circuit comprises: an acquisition function configured to acquire the sequence of image frames; a detection function configured to detect an object within an image frame of the sequence of image frames; 15. The device of claim 13 or 14, further configured to:

Images