KR20180014524A - Video report filtering apparatus - Google Patents

Abstract

The present invention relates to a video report filtering apparatus for providing an application, receiving metadata corresponding to a video photographed by the provided application, and receiving the transmitted video. The video report filtering apparatus comprises: a receiving unit for receiving the metadata and the transmitted video; a filtering unit for determining whether the video is counterfeit based on the received video and the metadata; and a notifying unit for displaying the received video and the metadata corresponding to the received video determined by the filtering unit that the video is not counterfeit. Therefore, the video report filtering apparatus enables a surveillant to filter false report contents or to easily obtain only necessary information without observing all report videos.

Description

[0001] The present invention relates to a video report filtering apparatus,

The present invention relates to an apparatus for receiving an image photographed in real time, and more particularly to an apparatus for receiving and filtering an image photographed by a terminal.

In a conventional monitoring or reporting system, when an accident or a crime occurs, a monitoring system pre-installed everywhere in the related agencies such as the National Police Agency, the 119 Safety Report Center, and the National Emergency Management Agency or periodic patrolling officers, , The camera connected to the NVR could be constantly monitored or an alarm could be triggered to identify it. Otherwise, citizens could voluntarily report it.

Such reports have conventionally been carried out by a complainant directly at a public office or by phone, but due to the development of information and communication technology, photographs of mobile phones or smart phones, video recording functions, It became possible to securely confirm the evidence of illegal acts or violations of the law and to promptly report it. The related administrative authorities have been able to raise the awareness of compliance with the law by providing compensation accordingly.

However, in the case of such a conventional monitoring or reporting system, even if the administrative office receives a report on the basis of a photograph or a moving picture, there is a problem that the person in charge has to directly verify again whether the photograph and the moving picture have not been edited or manipulated. There is no way to distinguish a case in which someone reported malicious manipulated images or curiosity as a prank, or a case in which a report was made with a simple mistake, There is the inconvenience that it should examine.

Japanese Patent Application Laid-Open No. 2003-123182

SUMMARY OF THE INVENTION An object of the present invention is to provide an image reporting apparatus that filters an image that has been manipulated and reported as a mistake or a mischief.

The problems of the present invention are not limited to the above-mentioned problems, and other problems not mentioned can be clearly understood by those skilled in the art from the following description.

An image information filtering apparatus for providing an app according to an embodiment of the present invention for receiving the meta data corresponding to an image photographed by the provided app and a transmitted image, A receiving unit for receiving the metadata and the transmitted image; A filter unit for determining whether the image is forged or falsified based on the received image and the metadata; And an announcement unit for displaying the received video image and the metadata corresponding to the received video image, which are determined by the filter unit as an un-forged image.

And a decoding unit decoding the received image and the metadata, wherein the filter unit can determine whether the image is forged or not based on the received image and the metadata decoded by the decoding unit.

The metadata may include a hash value of the photographed image.

A metadata extracting unit for checking whether metadata other than the hash value is present among the metadata received by the receiving unit and extracting the metadata from the received image when the received metadata does not exist other than the hash value .

The filter unit may check whether the metadata exists or not, and may determine whether the image is forged or falsified based on the received image and the metadata when the metadata exists.

The filter unit may include a forgery-and-proofing unit for determining whether the image is forged or falsified by comparing the hash value of the received image with the received hash value.

According to the embodiment of the present invention, at least the following effects are obtained.

The informant can easily report the information using the terminal application for reporting, and the observer can easily filter out the fault information or retrieve only the necessary information without having to observe all the informative images.

The effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the specification. Other effects not mentioned may be clearly understood by those skilled in the art from the description of the claims.

1 is a block diagram illustrating a configuration of an image information filtering apparatus according to an embodiment of the present invention.
2A and 2B are flowcharts illustrating a process of performing image information filtering and notification according to an embodiment of the present invention.
3 is a flowchart illustrating an image filtering process of the image information filtering apparatus according to an exemplary embodiment of the present invention.
4 is a flowchart illustrating a metadata check process of the image information filtering apparatus according to an exemplary embodiment of the present invention.
FIG. 5 is a diagram illustrating a state in which metadata of an image taken by a video image filtering apparatus according to an exemplary embodiment of the present invention is extracted.
FIG. 6 is a view showing a state in which metadata is extracted from an image captured by an image information filtering apparatus according to an exemplary embodiment of the present invention.
7 is a conceptual diagram illustrating a metadata protocol structure of an image information filtering apparatus according to an embodiment of the present invention.
FIG. 8 is a flowchart illustrating a forgery-and-false inspection process of the forgery-proofing unit of the image information filtering apparatus according to an exemplary embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms " comprises "and / or" comprising "used in the specification do not exclude the presence or addition of one or more other elements in addition to the stated element.

Further, the embodiments described herein will be described with reference to cross-sectional views and / or schematic drawings that are ideal illustrations of the present invention. Thus, the shape of the illustrations may be modified by manufacturing techniques and / or tolerances. In addition, in the drawings of the present invention, each component may be somewhat enlarged or reduced in view of convenience of explanation. Like reference numerals refer to like elements throughout the specification and "and / or" include each and every combination of one or more of the mentioned items.

Hereinafter, the configuration of a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing the configuration of an image information filtering apparatus 1 according to an embodiment of the present invention.

1, an image information filtering apparatus 1 according to an embodiment of the present invention includes a receiving unit 11, a decoding unit 12, a metadata extracting unit 13, a filter unit 14, 15 and a storage unit 16. The filter unit 14 includes a metadata checking unit 141 and a forgery check unit 142. [

In addition, it can be seen that the image information filtering apparatus 1 according to the embodiment of the present invention is connected to the terminal 2 that makes a notification, and thus constitutes one image information reporting system as a whole.

Hereinafter, the components of the image information filtering apparatus 1 according to an embodiment of the present invention will be schematically described with reference to FIG.

The receiving unit 11 receives an image, a photograph and metadata from a terminal 2 used by a user in the form of wired or wireless. The contents received by the receiving unit 11 include not only texts that can be transmitted through a short message service (sms) but also images or movie clips through a multimedia messaging system (mms), video and text files transmitted while maintaining the original file format, And a file of a standard of a registered standard. The image received by the receiving unit 11 may be the image already stored after the image capture, but may be the image being captured in real time. The receiving unit 11 may be configured as a 3G modem or an LTE modem for wireless communication and may use other ZigBee, WLAN, Bluetooth, or the like. A LAN card for wired communication may also be used.

In the specification of the present invention, metadata refers to data representing the characteristics of an image or a photograph, and includes a size of an object of interest in the image or a photograph, skin color, sex, hat or glasses, A vehicle number and vehicle type when the object of interest is a vehicle, a place and time information on which the image or photograph was taken, and the hash value calculated from the image taken for the integrity check of the image is included do. However, the type and the number of the metadata are not limited thereto, and if the data is meaningful to the report, the metadata can be used as the metadata.

The storage unit 16 stores the image or the photograph and the meta data received by the receiving unit 11. The storage unit 16 may be a cloud storage or a network video recorder (NVR), but is not limited thereto. The image information filtering apparatus 1 stores the received data in the storage unit 16 and determines whether to continue storing the data in the storage unit 16 through an operation such as filtering.

The decryption unit 12 receives the data received by the receiving unit 11 and receives the data from the receiving unit 11 to decrypt the encrypted file. Therefore, the processor for the calculation is used as the decoding unit 12. [ The algorithm by which the decryption unit 12 decrypts the encrypted data is determined according to what type of encryption the initial data is. This can be done by designing the initial system by associating the way in which the application provided to the terminal 2 encrypts the data and the way in which the decryption unit 12 decrypts the encrypted data. Encryption and decryption methods may be symmetric key algorithms such as DES (Data Encryption Standard), 3-DES, AES (Advanced Encryption Standard), SEED, ARIA, MASK, asymmetric key algorithms such as RSA (Rivest Shamir Adleman) Digital Signature Standard), Diffle-Hellman key exchange, ElGamal, but is not limited thereto.

The metadata extracting unit 13 extracts metadata from the image or photo data received by the receiving unit 11 when the terminal 2 used by the user does not extract enough metadata . Therefore, it extracts the area of interest from an image or a photograph, recognizes the part of the object, the face, etc., and stores the information that can be obtained therefrom as meta data. If the received data is encrypted, it decrypts the received data through the decryption unit 12, extracts a region of interest from the decrypted image or photograph, or recognizes the portion, face, etc. of the object, Metadata is stored and stored as metadata.

The filter unit 14 determines whether the image or the photo data received by the receiving unit 11 is forged or forged as a report image or can grasp the related information in detail. If so, it is used as a report image, It sends a list. If the data received by the receiving unit 11 is encrypted data, the same filtering is performed using the data decrypted through the decryption unit 12. The filter unit 14 performs filtering on the image and the metadata after obtaining the metadata up to the extent possible through the metadata extracting unit 13.

The filter unit 14 determines whether the corresponding image contains useful information as a report or not whether it is a mistransmitted image or not based on whether the metadata received by the receiving unit 11 and the metadata extracted by the metadata extracting unit 13 exist or not And thus includes a metadata checking unit 141. In addition, since the image or photograph received by the receiving unit 11 is checked for forgery or falsification and the forgery-proofed image is judged not to be a correct reference image, the filter unit 14 includes a forgery inspection unit 142.

The notification unit 15 receives the image or the photograph determined by the filter unit 14 as a thumbnail image or photograph, and notifies the surveillant of the received image or photograph. The notification unit 15 may inform the monitor of the notification image or photograph by pop-up through a display device, sounding an alarm, or creating a new job on the event management system.

Hereinafter, with reference to FIG. 2A and FIG. 2B, a process of receiving a report by the image information filtering apparatus 1 according to an embodiment of the present invention, filtering the received content and informing the surveillant will be described step by step.

2A and 2B are flowcharts illustrating a process of performing image information filtering and notification according to an embodiment of the present invention.

The supervisor provides a reporting application that can be reported to this device on the medium that can distribute the application to the public such as the app store and the application market. The informer downloads the notification application to the terminal 2 and installs it. Here, the terminal 2 may be a device such as a mobile phone or smart phone capable of downloading an application, installing and using a wireless modem such as 3G or LTE, It is possible to download and install the application, but it is not limited to Wearable devices such as tablet PC, smart watch, etc., which can wirelessly communicate with the AP through WLAN or Wibro and capture images or images .

When the informant witnesses an accident scene or a crime scene as shown in Fig. 1, the user takes a picture of the scene using the terminal 2. At this time, the informant executes the notification application installed in the terminal 2, and photographs the site through the notification application (S10). Therefore, the notification application provided by the watcher must include a function of photographing images using the camera module of the terminal 2. [

 In order to filter the image by the image information filtering apparatus 1 according to an embodiment of the present invention, metadata needs to be extracted from the image. Therefore, meta data should be generated for the image captured by the reporting application. However, the hardware specification or configuration of the terminal 2 in which the application is installed may not be enough to extract the meta data from the photographed image. Accordingly, the reporting application goes through a step S11 in which the installed terminal 2 analyzes the image and determines whether the metadata can be extracted. If it is determined that the metadata can be extracted at this stage, the reporting application extracts the metadata about the image photographed through the reporting application (S12). If it is determined that extraction is not possible, metadata is not extracted.

Regardless of whether the metadata is extracted, the application calculates the hash value for the captured image and adds it to the metadata. Here, the method of determining the hash value for the image is to judge whether a forgery or falsification is performed through the integrity check, and a method such as CRC (Cyclic Redundancy Check), MD5 (Message Digest Algorithm 5) But is not limited to. In addition, the reporting application receives the position information, the time, and the personal information of the informant, which are photographed from the terminal 2, adds the information to the metadata, and encrypts the metadata and the photographed image (S13). The encryption method is the same as that described above for the decryption unit 12 in the description of FIG.

In order to report the image photographed by the reporting application, the user is authenticated (S14). It is a method to confirm the identity of a whistleblower more clearly and to block the false report at the stage before reporting it. In order to authenticate the user, a certificate such as an official certificate, an i-pin, or a mobile phone authentication may be used, but the present invention is not limited thereto. If you fail to verify your identity, you can not report. So we go back to the first step.

If the authentication is successful, the encrypted image and the metadata are transmitted using a wireless communication module such as a wireless modem or WLAN of the terminal 2 (S15). At this time, the image and data may be transmitted to the receiving unit 11 of the nearest government office or public institution, or the image and data may be transmitted to the receiving unit 11 of the 112 general communication room of the local police office, but the present invention is not limited thereto. In addition, since the image and the transmission of the terminal 2 must also be transmitted through the notification application, the notification application must include a function of controlling the wireless communication module of the terminal 2.

The receiving unit 11 receives the image and metadata transmitted through the reporting application, and the storing unit 16 stores the received image and metadata (S16). The received image and metadata are stored in a storage device and filtered to determine whether to use the image or metadata as a report.

The decryption unit 12 decrypts the received image and metadata if they are encrypted (S17). The decryption algorithm used by the decryption unit 12 should correspond to the encryption algorithm used by the notification application of the terminal 2.

When the decoding is completed, the received image and data are passed through the metadata extracting unit 13. The metadata extracting unit 13 determines whether or not the received metadata is preferentially received (S18), and if the metadata does not exist, the metadata extracting unit 13 further extracts the metadata from the received image S19). The meta data for determining whether or not the metadata extracted by the metadata extracting unit 13 is the data of the size of the object of interest in the image and the face or the accessory to be worn if the object of interest is a person, It does not. This is because the hash value is to be calculated at the time of the initial photographing using the reporting application and will be compared with the hash value calculated by the forgery and alteration inspection unit 142 to be described later.

The received image and meta data passed through the metadata extracting unit 13 pass through the filtering of the filter unit 14 (S20). The filter unit 14 is a place to judge whether the image or the photo data received by the receiving unit 11 is forged or forged or to be able to grasp the related information in detail. Therefore, when the filtering is not passed, And metadata are recorded (S21).

The step S21 of recording in the garbage list is a step of filtering an image having no value as a reference image and recording the rest of the image. The contents corresponding to the image and the metadata recorded in the list are deleted in the storage unit 16 .

The filtered image and metadata are displayed to the observer through the notification unit 15 (S22). The metadata necessary for the monitor may be displayed on the image together with the display image, but the present invention is not limited thereto. In addition, the notification unit 15 may notify that an event has occurred by using other notification means. The corresponding image and metadata remain in the storage unit 16, and the watcher who has confirmed it by the notification unit 15 confirms the notification image and takes appropriate action according to the situation.

Hereinafter, the image filtering process of the filter unit 14 will be described in more detail with reference to FIGS. 3 and 4. FIG.

FIG. 3 is a flowchart illustrating an image filtering process S20 of the image information filtering apparatus 1 according to an exemplary embodiment of the present invention. FIG. 4 is a block diagram illustrating an image information filtering apparatus 1 according to an exemplary embodiment of the present invention. FIG. 2 is a flowchart illustrating a metadata checking process of the first embodiment of the present invention.

The filter unit 14 for image filtering is divided into a metadata checking unit 141 and a forgery testing unit 142 as described above with reference to FIG.

The metadata checking unit 141 checks the metadata received or extracted by the metadata extracting unit 13, checks whether there is metadata, and records the determination (S201). Whether the corresponding image contains information useful for informing, whether it is a simple mistake or a video noticed as mischievous, based on whether the metadata received by the receiving unit 11 and the metadata extracted by the metadata extracting unit 13 exist or not It is because we have to judge. However, the metadata to be judged here can exclude the hash value. This is because the hash value can be filtered by the forgery-and-altering inspection unit 142.

It is determined whether the received meta data and the extracted meta data do not exist (S2011). In the case of an image without metadata, it means that it can not obtain meaningful information about the image. Therefore, the same result will be obtained even if the monitor monitors the image with the naked eye. Accordingly, the corresponding image is recorded in the garbage list (S21). If there is significant metadata, the metadata about the person and the metadata about the object among the corresponding metadata are classified (S2012). It is in order to roughly judge what kind of information is included, and what contents are contained in the reference image. The contents of the classified metadata are recorded in the database (S2013).

The forgery check unit 142 compares the hash value with the hash value calculated from the received image to check whether the image has passed through the metadata checking unit 141 (S202). If not, Video and metadata are recorded (S21). The forgery check process of the forgery falsification checking unit 142 will be described later in detail with reference to FIG.

Hereinafter, the extracted metadata will be described with reference to FIGS. 5 and 6. FIG.

FIG. 5 is a diagram showing a state in which metadata of an image taken by a video image filtering apparatus 1 according to an exemplary embodiment of the present invention is extracted.

5 is a view of a scene of an image taken by the informer through a reporting application for the rear view of the vehicle. If the object of interest is a vehicle, a region of interest 30 for the object of interest is designated. The metadata extracting unit 13 of the image information filtering apparatus 1 according to an embodiment of the present invention or a notification application can extract the metadata from the image by using the OCR (Optical Character Recognition) The license plate information 32 including the vehicle number written on the license plate of the vehicle, the manufacturer information 31 of the vehicle, and the vehicle information 33 such as the vehicle type, the color of the vehicle, and the position of the vehicle in the image. Therefore, the vehicle information 33 thus determined is textized and stored as meta data to be stored together with the photographed image.

Since the characteristic vehicle information 33 is extracted and provided, it is possible to easily check information that is difficult to visually recognize, and it is possible to promptly confirm the necessary vehicle information 33 to be obtained from the incident image even if the monitor does not check the image have.

FIG. 6 is a diagram showing a state in which metadata extracted from an image captured by an image information filtering apparatus 1 according to an exemplary embodiment of the present invention.

FIG. 6 is a representation of a scene of an image taken by an informer through a reporting application on an incident scene where a person is associated. If the object of interest is a person, a region of interest 40 for the object of interest is designated. The metadata extracting unit 13 of the image information filtering apparatus 1 according to an embodiment of the present invention or a report application can extract the metadata of the corresponding person from the region of interest 40 of the image through a face recognition technology, It is possible to grasp the person information 41 such as the face, the height, the sex, and the color of the garment being worn. Accordingly, the person information 41 thus determined is textized and stored as meta data to be stored together with the photographed image.

As a face recognition method that can be used by the metadata extraction unit 13 of the image information filtering apparatus 1 according to an information application or an embodiment of the present invention, there may be a method using eigenfaces, fisherfaces, neural networks, But is not limited thereto. In addition, the object recognizing method includes, but is not limited to, SURF (Speed Up Robust Features) and FAST (Features from Accelerated Segment Test).

Since the characteristic person information 41 is extracted and provided as described above, the necessary information to be obtained from the event image can be immediately confirmed without having to monitor the image one by one.

Also, since the position information can be obtained from the terminal 2 at the time of capturing an image as described above, the position information 42 of the place where the image is captured can also be added as metadata. In this case, only the corresponding address may be added as metadata, or the corresponding map information may be requested to an external service or a map database owned by the image information filtering apparatus 1 of the present invention to add the map image 43 as metadata It is possible. When the address is received, the notification unit 15 requests map information from an external service or a map database held by the image information filtering apparatus 1 of the present invention, and displays the map image 43 together with the received image, May be displayed.

Hereinafter, the protocol structure of the metadata will be described with reference to FIG.

7 is a conceptual diagram illustrating a structure of a metadata protocol 5 of the image information filtering apparatus 1 according to an embodiment of the present invention.

The metadata is divided into a header (51) and a body (52). The header 51 is a part representing general information of the metadata. The header 51 includes a version of the metadata protocol, a total number (count) of metadata to be transmitted, and event occurrence time information (time). The body 52 is a part that contains the extracted metadata, and the metadata is stored in a set together with the type, length, and time of the extracted metadata.

7, the structure of the metadata of the image information filtering apparatus 1 according to an embodiment of the present invention has been described. However, the present invention is not limited to this, and unnecessary information may be removed or additional information may be added, The protocol structure can be changed.

Hereinafter, with reference to FIG. 8, the structure of the process of forgery inspection of the forgery and fuzzy checking unit 142 of the image information filtering apparatus 1 according to an embodiment of the present invention will be described in more detail step by step.

FIG. 8 is a flowchart illustrating a forgery-and-false inspection process of the forgery falsification checking unit 142 of the image information filtering apparatus 1 according to an embodiment of the present invention in more detail.

If the received image or picture is forged or distorted by the receiving unit 11, it is determined that the received image or picture is not a correct notified image. Therefore, the filter unit 14 includes the forgery inspection unit 142. Also, as described above, the forgery check section 142 uses the hash value.

The forgery checker 142 calculates a hash value for the received image (S2021). A method of extracting a hash value is the same as a method of extracting a hash value for an image captured by the reporting application.

The forgery checker 142 compares the calculated hash value with the hash value included in the received metadata (S2022). The hash value calculated by the forgery inspection unit 142 is extracted from the received image, and the hash value included in the received metadata is extracted from the captured image at the time of photographing. Thus, if the two hash values do not match, it can be evidence that there was a transmission problem after the shot. In addition, even if an image is manipulated or an interchanged image is transmitted by an artificial operation after taking an image through an application, since the two hash values do not coincide with each other, the method of comparing the two hash values is effective, It can be used for inspection.

If they do not coincide with each other, the image and metadata are recorded in the garbage list (S21). If they match, the corresponding video and metadata are recorded in the database (S2023).

It will be understood by those skilled in the art that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

Although the present invention has been described in connection with the above-mentioned preferred embodiments, it is possible to make various modifications and variations without departing from the spirit and scope of the invention. Accordingly, it is intended that the appended claims cover all such modifications and variations as fall within the true spirit of the invention.

1: image information filtering device 2:
5: Metadata Protocol 11: Receiver
12: Decoding unit 13: Metadata extracting unit
14: filter unit 15:
16: storage unit 30, 40: area of interest
31: Manufacturer information 32: License plate information
33: vehicle information 41: person information
42: Location information 43: Map image
51: Header 52: Body
141: metadata checking unit 142: forgery checker

Claims (6)

1. An image information filtering apparatus for providing an application and receiving meta data corresponding to an image photographed by the provided app and a transmitted image,
A receiving unit for receiving the metadata and the transmitted image;
A filter unit for determining whether the image is forged or falsified based on the received image and the metadata; And
And a notification unit configured to display the received video image and the metadata corresponding to the received video image, which are determined by the filter unit as an unmodified image. The method according to claim 1,
And a decoding unit decoding the received image and the metadata,
Wherein the filter unit determines whether the image is forged or not based on the received image decoded by the decryption unit and the metadata. The method according to claim 1,
Wherein the metadata includes a hash value of the photographed image. The method of claim 3,
A metadata extracting unit for checking whether metadata other than the hash value is present among the metadata received by the receiving unit and extracting the metadata from the received image when the received metadata does not exist other than the hash value Further comprising a video information filtering device. 5. The method of claim 4,
Wherein the filter unit checks whether the metadata is present and determines whether the image is forged or not based on the received image and the metadata when the metadata exists. The method of claim 3,
Wherein the filter unit comprises a forgery-and-proofing unit for determining whether the image is forged or falsified by comparing the hash value of the received image with the received hash value.

Images