JP2016122892A - Video system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve such a problem that a mask function to a privacy part is necessary for protecting the privacy, in order to deliver or publish a surveillance video.SOLUTION: In a video system having an imaging unit and a data correction unit, the data correction unit has an image data reception unit for receiving image data captured by the imaging unit, a positional information data reception unit for receiving positional information data identifying a shooting place, and a mask data storage unit for storing mask data masking a predetermined region of the image data. An image correction unit performs masking of a predetermined region of the image data by mask data stored in the mask data storage unit, based on the positional information data of the image data.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a video apparatus.

Conventionally, surveillance cameras have been installed in facilities such as stores, public facilities, factories, and transportation facilities to check the situation when crimes or incidents occur. However, since an unspecified number of people and buildings are reflected in the surveillance video, it may lead to privacy infringement. For example, there are cases where the state of a house or facility, a car license plate, or the like is reflected. In this case, if the angle of view is changed so that an unspecified number of objects are not reflected, or if the angle of view cannot be set, there are even cases where the surveillance camera cannot be attached.
On the other hand, the video surveillance system has a privacy mask function that applies image processing such as blacking and blurring to the area that is infringing on privacy in the video so that it cannot be recognized by the person viewing the video. More and more devices are being used.
Since most surveillance cameras are installed at fixed points to monitor a defined area, the subject is often fixed. In this case, after the angle of view is determined, the video is confirmed, a masking portion is designated, and the area is always masked so that it cannot be seen by a person viewing the video.
In addition, even in a camera (PTZ camera) that can change the shooting direction such as pan, tilt, and zoom, the mask area is calculated from the movement amount of the camera direction and the like, and the designated position of the image is masked. .

  As a prior art, for example, in Patent Document 1, the moving range of the camera platform is limited so that a private house that is not a monitoring target or a place where privacy is a problem is not reflected on the TV camera while tracking an intruding object.

JP-A-2005-57743

  When the incident occurred, the surveillance camera and other images could only be viewed by the police and other authorized persons as evidence of the situation. However, surveillance video is being distributed or released to the general public from the viewpoint of information disclosure. Therefore, in order to distribute or publish the monitoring video, a mask function for the privacy portion is necessary to protect privacy.

  The video device of the present invention is a video device having an imaging unit and a data correction unit, and the data correction unit includes an image data reception unit that receives image data captured by the imaging unit, and position information data that specifies a shooting location. A position information data receiving unit for receiving, and a mask data storage unit for storing mask data for masking a predetermined region of the image data, and the image correction unit stores the position information data of the image data in the predetermined region of the image data. Based on this, masking is performed with mask data stored in a mask data storage unit.

  The video device of the present invention is the video device described above, wherein the position information data is position information data or train mileage information data output from a GPS receiver.

  Furthermore, the video device of the present invention is a video device having an imaging unit and a data correction unit, and the data correction unit is an image data receiving unit that receives image data captured by the imaging unit, and position information that specifies a shooting location. A position information data receiving unit for receiving data, a mask data storage unit for storing mask data for masking a predetermined area of image data, and a mask target recognition unit for searching for a mask target, and image correction The masking unit masks the mask object stored in the mask data storage unit based on the position information data of the image data in a predetermined area of the image data or masks the mask object searched by the mask object recognition unit.

  According to the present invention, by performing masking processing on an image of a privacy part using position information, it is possible to distribute or release an image for general public.

It is a block diagram for demonstrating the structure of the video device which is one Example of this invention. It is a block diagram for demonstrating the structure of the data correction part which is one Example of this invention. It is the flowchart 1 for demonstrating operation | movement of the data correction part which is one Example of this invention. It is a flowchart 2 for demonstrating operation | movement of the data correction part which is one Example of this invention. It is a block diagram for demonstrating the structure of the data correction part which is another Example of this invention.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a block diagram for explaining the configuration of a video apparatus according to an embodiment of the present invention.
In FIG. 1, the video apparatus 100 includes an imaging unit 101, a data correction unit 102, an encoding unit 103, a video distribution unit 104, and a lens unit 110.

The video apparatus 100 photoelectrically converts incident light imaged through the lens unit 110 by the imaging unit 101 to generate one piece of digital image data.
The digital image data output from the imaging unit 101 is subjected to image signal processing by the data correction unit 102, sent to the encoding unit 103, encoded by the encoding unit 103, and distributed from the video distribution unit 104 to the network 120. Is done.
For example, the data correction unit 102 can know the shooting location of the video device 100 from position information received by a GPS (Global Positioning System) attached to a vehicle, train travel distance information data from a train operation system, or the like. Receive location information data.
Note that the data correction unit 102 may always receive position information data, for example, and change the reception interval depending on the system.

  In the encoding unit 103, for example, JPEG (Joint Photographic Experts Group), H.264, etc. Video compression may be performed using H.264 or the like. Further, it may have a function of preventing image data from being illegally viewed from outside by encryption, signature, or the like.

The digital image data encoded by the encoding unit 103 can be distributed from the video distribution unit 104 to the client terminal 130 such as a video display device or a video recording device via the network 120.
For distribution to the network 120 of the video distribution unit 104, for example, data is sent by receiving an acquisition request from the client terminal 130, or is transmitted to the network itself.
In addition, the video distribution unit 104 includes a memory unit and buffers (stores) image data in the memory unit in order to enable distribution in response to video requests from a plurality of client terminals 130.

Next, the configuration of the data correction unit according to an embodiment of the present invention will be described with reference to FIG.
FIG. 2 is a block diagram for explaining the configuration of a data correction unit according to an embodiment of the present invention.
In FIG. 2, the data correction unit 102 includes an image data reception unit 201, a position information data reception unit 202, a mask data R / W (Read / Write) unit 203, a mask data storage unit 204, and an image correction unit 205. The shared memory unit 206 is configured.

The data correction unit 102 receives one piece of digital image data output from the imaging unit 101 by the image data reception unit 201, and the image data output from the image data reception unit 201 by the image correction unit 205 and the mask data R / The mask data output from the W unit 203 is combined and output.
The position information data receiving unit 202 receives the position information data output from the GPS receiver or the like and outputs it to the mask data R / W unit 203.
Note that the position information data includes information on the shooting direction of the video apparatus 100 in addition to longitude, latitude, and altitude.

The mask data R / W unit 203 reads out mask coordinates for privacy masking registered (stored) in the mask data storage unit 204 in advance based on the position information data received by the position information data receiving unit 202.
Note that the mask coordinates are used to identify a masking range in an image captured at an arbitrary position.

For example, the mask coordinates are first recorded by associating the video data and the position information by mounting the video device 100 on the vehicle and running the vehicle.
Next, the mask coordinates are generated by, for example, reproducing recorded video data using a not-shown PC (Personal Computer) or the like and designating an area (region) to be masked for the image. At the time of generation, the mask data associated with the position information of the image data and the mask coordinates is added to the mask data by adding the position information associated with the video data together with the coordinates of the generated mask area. It can be registered (stored) in the storage unit 204.

Next, the operation of the image correction unit 205 will be described.
The image correcting unit 205 applies a mask to the digital image data output from the image data receiving unit 201 based on the mask coordinates output from the mask data R / W unit 203. The mask is an image that cannot identify an object related to privacy by a method such as blacking, blurring, or blocking.
However, since the surveillance video is a proof of the situation at the time of the accident, etc., it is necessary to view all of the captured videos. In this case, the image itself is not masked, but mask data is attached so that the image can be masked when displayed. As a result, a person who is permitted to view such as the police can view all of the video, and can put a privacy mask on the public video to the general public.
Therefore, the image correction unit 205 adds mask data to the image data and outputs the image data to the encoding unit 103.

Next, the detailed operation of the data correction unit 102 will be described with reference to FIGS.
FIG. 3 is a flowchart 1 for explaining the operation of the data correction unit according to the embodiment of the present invention.
FIG. 4 is a flowchart 2 for explaining the operation of the data correction unit according to the embodiment of the present invention.
The data correction unit 102 is roughly divided into two processes.
One is processing when digital image data is received, and will be described with reference to FIG. The other is processing upon reception of position information data, which will be described with reference to FIG.

In FIG. 3, the data correction unit 102 receives and acquires the digital image data output from the imaging unit 101 in the process of S <b> 301 by the image data reception unit 201.
In the process of S302, the mask data R / W unit 203 reads out and acquires the mask data from the shared memory unit 204.
In the process of S303, the image correction unit 205 masks the image data based on the mask data.
The digital image data masked by the data correction unit 102 is output to the encoding unit 103.

In FIG. 4, the data correction unit 102 acquires position information data from the position information data receiving unit 202 in the process of S401.
In the process of S402, position data is extracted from the position information data acquired by the mask data R / W unit 203, and the mask data is stored as a mask data storage unit (recording medium such as a hard disk drive (HDD)) 204 using the position data as a key. Read from and get.
In the process of S403, the mask data R / W unit 203 determines whether or not there is mask data corresponding to the position data. If there is mask data corresponding to the position data (YES), the process proceeds to S405 and corresponds to the position data. If there is no mask data (NO), the process proceeds to S404.

In the process of S404, the mask coordinates are calculated from the position information data, and the process proceeds to S405.
In the process of S405, the mask data is written in the shared memory unit 206, and the process proceeds to S406.
By writing the mask data to the shared memory unit 206, the mask data can be read out and acquired from the shared memory unit 206 in the process of S302 of FIG.

In the process of S406, the process waits for a predetermined time and proceeds to the process of S407. The predetermined time is, for example, a reception interval of reception position data.
In the process of S407, the end of the process is determined. If the process is completed (YES), the process is terminated. If the process is not completed (NO), the process returns to S401.

  3 and FIG. 4, the captured image data is privacy-masked, so monitoring images captured while moving like a vehicle are monitored without worrying about privacy. be able to.

(Details of how to create mask data)
Next, details of a method for creating mask data will be described.
The video device 100 captures an image without masking once, and records the captured image data with a video recording device or the like in synchronization with the position information.
A mask object is searched from the image data, and a polygonal mask region is manually set for a representative video frame.
For the mask object, for example, an image feature quantity detection method such as SIFT (Scale-Invariant Feature Transform) is used to perform image recognition of the object in the mask area, and automatically detect similar objects from adjacent frames. Similarly, a mask area is set. Thereby, time-series mask data (primary) is obtained.
If the mask data (primary) is applied as it is, the mask may be shifted due to an error in position information. For this reason, in mask data (primary), a plurality of mask areas that are temporally adjacent to each other are combined (in a logical sum) and combined in a time series as mask data, which is stored in a recording medium.

(Another example)
Next, another embodiment of the present invention will be described with reference to FIG.
FIG. 5 is a block diagram for explaining the configuration of a data correction unit according to another embodiment of the present invention. The same reference numerals as those in FIG. 2 perform the same operation.
In the above-described embodiment, the mask may be shifted due to an error in position information.
In another embodiment of the present invention, the feature quantity of the mask object found manually is included in the mask data together with the position range information where it is detected.
In FIG. 5, the image data receiving unit 201 extracts the same type of feature quantity as included in the mask data from the input image data, and the position information from the position information data receiving unit 202 is the position range information of the mask data. Is further provided with a mask object recognition unit 207 that searches for an object similar to the feature amount corresponding to the position range information.
When the mask object detection / recognition unit 207 finds a mask object, it outputs a mask image for masking the area.
The image correction unit 205 obtains a mask image from both the mask data R / W unit 203 and the mask object recognition unit 207. If a mask image can be obtained from only one of them, it is adopted from both. If it is obtained, the one with higher reliability (one that has been adopted until just before or the mask object recognition unit 207) is adopted.

  The video device according to the embodiment of the present invention can perform image distribution or disclosure to the general public by performing a masking process on the image of the privacy portion using the position information.

  Although the present invention has been described in detail above, it is needless to say that the present invention is not limited to the video apparatus described here, and can be widely applied to video apparatuses other than those described above.

  DESCRIPTION OF SYMBOLS 100: Image | video apparatus, 101: Image pick-up part, 102: Data correction part, 103: Coding part, 104: Image | video delivery part, 110: Lens part, 120: Network, 130: Client terminal, 201: Image data receiving part, 202 : Position information data receiving unit, 203: mask data R / W unit, 204: mask data storage unit, 205: image correction unit, 206: shared memory unit.

Claims (3)

In a video apparatus having an imaging unit and a data correction unit,
The data correction unit masks a predetermined area of the image data, an image data receiving unit that receives image data captured by the imaging unit, a position information data receiving unit that receives position information data specifying a shooting location, and the like. A mask data storage unit for storing mask data for
The image correction unit masks a predetermined area of image data with mask data stored in the mask data storage unit based on position information data of image data. The video device according to claim 1,
The video apparatus, wherein the position information data is position information data or train mileage information data output from a GPS receiver. In a video apparatus having an imaging unit and a data correction unit,
The data correction unit masks a predetermined area of the image data, an image data receiving unit that receives image data captured by the imaging unit, a position information data receiving unit that receives position information data specifying a shooting location, and the like. A mask data storage unit for storing mask data and a mask object recognition unit for searching for a mask object,
The image correction unit masks a predetermined area of image data with mask data stored in the mask data storage unit based on position information data of image data or masks a mask object searched by the mask object recognition unit. A video apparatus characterized by that.

Images