CN110688510B - Face background image acquisition method and system - Google Patents

Abstract

The embodiment of the invention provides a method and a system for acquiring a face background image, wherein the method comprises the following steps: the image pickup equipment sends the face image to an analysis server and sends the video image to a storage server. The analysis server analyzes the face image to obtain face data, stores the face data in a database, and sends the face image to the storage server. And the storage server encodes and stores the video image and returns the storage information of the face image and the video image to the analysis server. After receiving the face image to be queried of the client, the analysis server identifies the face image to be queried to obtain storage information of the face image and the video image corresponding to the face image and the video image. And the client acquires a corresponding video image containing the background image of the face image to be inquired from one end of the storage server according to the storage information. The human face background acquisition scheme avoids the burden of a large number of video images on the analysis server, and improves the efficiency of human face background retrieval.

Description

Method and system for acquiring face background image

technical field

The invention relates to the technical field of computer vision, and in particular, to a method and system for acquiring a background image of a human face.

Background technique

Face recognition is a kind of biometric identification technology based on human facial feature information. It includes a series of related technologies that capture images or video streams containing human faces with cameras or cameras, and automatically detect and track human faces in the images to identify the detected human faces. After the face is recognized, a face cutout and a face background image are generally reserved. Generally, when performing face retrieval and comparison, only the face cutout needs to be presented. But sometimes you need to know the time, place and surrounding situation of the face, so you need to be able to query the background picture of the face

SUMMARY OF THE INVENTION

In view of this, the purpose of the present invention is to provide a method and system for acquiring a background image of a human face to solve the above problems.

A preferred embodiment of the present invention provides a method for acquiring a background image of a human face, which is applied to a system for acquiring a background image of a human face. The system includes an analysis server, a storage server, and a camera device that are connected in communication. The analysis server and the storage server can also be Establishing a communication connection with the client, the method includes:

The camera device sends the face image extracted from the collected video image to the analysis server, and sends the video image to the storage server, where the video image includes a face background image;

The analysis server analyzes and processes the face image to obtain corresponding face data, saves the face data in a database, and sends the face image to the storage server;

The storage server encodes the received video image, stores the face image and the encoded video image, and returns the storage combination information of the face image and the video image to the analysis server;

When receiving the face image to be queried sent by the client, the analysis server obtains the storage combination information of the face image, and feeds it back to the client, so that the client sends the storage combination information to the storage server;

The storage server finds the face image corresponding to the face image to be queried and the video image corresponding to the face image according to the storage combination information, and returns the face image and the video image. to the client.

Optionally, the step of the camera device sending the face image extracted from the collected video image to the analysis server includes:

The camera device extracts a face image from the collected video image, and obtains a reference frame image of the video image;

The timestamp information of the video image and the reference frame image is obtained, and the face image carrying the timestamp information is sent to the analysis server.

Optionally, the step of obtaining the time stamp information of the video image and the reference frame image, and sending the face image carrying the time stamp information to the analysis server, includes:

acquiring a first timestamp of the reference frame image, a second timestamp of the video image, and an offset of the video image relative to the reference frame image;

The first timestamp, the second timestamp and the offset are formed into timestamp information, and the face image carrying the timestamp information is sent to the analysis server.

Optionally, the storage server encodes the received video image, stores the face image and the encoded video image, and returns the storage combination information of the face image and the video image to the analysis server. ,include:

The storage server obtains, according to the time stamp information carried by the face image obtained from the analysis server, the position information in the video frame of the video image where the face image is located;

Obtain a reference frame image of the video image according to the location information and the timestamp information, obtain a video image where the face image is located according to the reference frame image, and combine the video image and the face image to store;

Send the storage combination information of the video image and the face image to the analysis server.

Optionally, the steps of obtaining a reference frame image of the video image according to the location information and the time stamp information, and obtaining a video image where the face image is located according to the reference frame image, include:

Obtain the reference frame image of the video image according to the position information and the offset between the video image and its reference frame image in the timestamp information;

The reference frame image is encoded according to the reference frame image and the offset to obtain a video image where the face image is located.

Optionally, the step of sending the storage combination information of the video image and the face image to the analysis server includes:

The storage server assembles the storage location of the video image and the storage location of the face image into storage combination information in URL format, and sends the storage combination information to the analysis server.

Another preferred embodiment of the present invention provides a system for acquiring a background image of a human face. The system includes an analysis server, a storage server, and a camera device that are connected in communication. The analysis server and the storage server can also establish a communication connection with a client. The analysis server includes a processing module and a storage combination information acquisition module, the storage server includes a storage module and a video image search module, and the camera device includes a sending module:

The sending module is configured to send the face image extracted from the collected video image to the analysis server, and send the video image to the storage server, where the video image includes a face background image;

The processing module is used to analyze and process the face image to obtain corresponding face data, save the face data in a database, and send the face image to the storage server;

The storage module is used to encode the received video image, store the face image and the encoded video image, and return the storage combination information of the face image and the video image to the analysis server;

The storage combination information acquisition module is used to obtain the storage combination information of the face image when receiving the face image to be queried sent by the client, and feed it back to the client, so that the client can Sending the storage combination information to the storage server;

The video image search module is used to find the face image corresponding to the face image to be queried and the video image corresponding to the face image according to the stored combination information, and compare the face image and all the face images. The video image is returned to the client.

Optionally, the sending module includes an extraction unit and a timestamp information acquisition unit;

The extraction unit is used to extract a face image from the collected video image, and obtain a reference frame image of the video image;

The time stamp information obtaining unit is configured to obtain time stamp information of the video image and the reference frame image, and send the face image carrying the time stamp information to the analysis server.

Optionally, the time stamp information obtaining unit includes an offset information obtaining subunit and a sending subunit;

The offset information obtaining subunit is configured to obtain a first timestamp of the reference frame image, a second timestamp of the video image, and an offset of the video image relative to the reference frame image;

The sending subunit is configured to combine the first timestamp, the second timestamp and the offset into timestamp information, and send the face image carrying the timestamp information to the analysis server.

Optionally, the storage module includes a location information acquisition unit, a storage unit and a sending unit;

The position information obtaining unit is configured to obtain the position information in the video frame of the video image where the face image is located according to the time stamp information carried by the face image obtained from the analysis server;

The storage unit is configured to obtain a reference frame image of the video image according to the position information and the time stamp information, obtain a video image where the face image is located according to the reference frame image, and store the video image. and the face image for storage;

The sending unit is configured to send the storage combination information of the video image and the face image to the analysis server.

The method and system for obtaining a face background image provided by the embodiments of the present invention store the storage information of the face image and the video image where the face image is located in the analysis server, and store the face image and the video image where the face image is located in the analysis server. Saved on the storage server. Therefore, when the analysis server receives the face image to be queried sent by the client, it can analyze the face image to be queried to find matching face data from the stored face data, and find the corresponding person according to the face data. The storage information of the face image and the video image where the face image is located. The client can obtain the video image corresponding to the face image to be queried from the storage server according to the stored information, so as to obtain the background image of the face of the face image to be queried. The face background acquisition scheme saves the storage information of the face image and the video image of the face image in the storage server in the analysis server, and saves the face image and the video image where the face image is located in the storage server. , which avoids the burden of a large number of video images on the analysis server, and improves the efficiency of face background retrieval.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.

FIG. 1 is a schematic diagram of an application scenario of a method for acquiring a background image of a face provided by a preferred embodiment of the present invention.

FIG. 2 is a flowchart of a method for acquiring a background image of a human face provided by a preferred embodiment of the present invention.

FIG. 3 is a flowchart of sub-steps of step S110 in FIG. 2 .

FIG. 4 is a flowchart of sub-steps of step S130 in FIG. 2 .

FIG. 5 is a block diagram of functional modules of a system for acquiring a background image of a human face provided by a preferred embodiment of the present invention.

FIG. 6 is a functional block diagram of a sending module provided by a preferred embodiment of the present invention.

FIG. 7 is a functional block diagram of a time stamp information obtaining unit provided by a preferred embodiment of the present invention.

FIG. 8 is a functional block diagram of a storage module provided by a preferred embodiment of the present invention.

Icon: 100-analysis server; 110-processing module; 120-storage combination information acquisition module; 200-storage server; 210-storage module; 211-location information acquisition unit; 212-storage unit; 213-transmission unit; 220-video 300-camera equipment; 310-sending module; 311-extracting unit; 312-time stamp information obtaining unit; 3121-offset information obtaining subunit; 3122-sending subunit.

Detailed ways

The inventor found through research that, in the existing storage methods of face backgrounds, the face capture camera generally pulls out the small face image, and then sends the large video image (including the background image) and the small face image to people. The face analysis server, after the face analysis server extracts the face features according to the small face image, stores the small face image and the large video image in a storage device such as a storage server. At the same time, the analysis data of the face, such as structured and unstructured feature information, is stored in the database. In addition, the face capture camera is also a video surveillance camera, so the related video recordings are also stored in the storage server at the same time.

In this method, the face recognition camera pushes both large and small images to the face analysis server at the same time, while the face device camera is generally deployed at the front end of subways, stations, etc., and the bandwidth is very limited. Therefore, the above method will increase the number of recognition cameras. Upload bandwidth. In addition, the face analysis server itself does not process the large face background image, and the large face background image will take up the bandwidth of the face analysis server to enter and exit from the face analysis server, and the multi-channel face capture cameras will send the pictures to After the same server, the bandwidth occupied will be very large.

Based on the above research findings, an embodiment of the present invention provides a solution for acquiring a background image of a face, by sending a face image in a video image collected by a camera device to an analysis server, and sending the video image to a storage server. After the analysis server processes the face image, the face image is then stored in the storage server. And, the storage server returns the storage information of the face image and the video image to the analysis server. In this way, when the client sends the face image to be queried, the analysis server can be used to analyze the face image and provide its storage location. Then use the storage server to find the corresponding video image containing the face image according to the storage location, and return it to the client. In this way, the burden on the analysis server caused by the storage of a large number of video images is avoided, and the efficiency of face retrieval is improved.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures. Meanwhile, in the description of the present invention, unless otherwise expressly specified and limited, the terms "installation", "arrangement" and "connection" should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection, or It can be connected in one piece; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be internal communication between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations.

Please refer to FIG. 1 , which is a schematic diagram of an application scenario of a method for acquiring a background image of a face provided by an embodiment of the present invention. The scene includes a face background image acquisition system, which includes an analysis server 100 , a storage server 200 and a camera device 300 . The analysis server 100 , the storage server 200 and the camera device 300 are connected through a network for communication or interaction. In this embodiment, the camera device 300 may include a plurality of camera devices, and the plurality of camera devices 300 are respectively connected in communication with the analysis server 100 and the storage server 200 . In this embodiment, the imaging device 300 may be a terminal device with an image capturing function, such as a camera or a camera. The analysis server 100 is a server that analyzes and processes face images, and the storage server 200 is a storage device, such as an IPSAN device.

Please refer to FIG. 2 , which is a flowchart of a method for acquiring a background image of a face applied to the above-mentioned system for acquiring a background image of a face provided by an embodiment of the present invention. It should be noted that the method provided by the present invention is not limited to the specific sequence described in FIG. 2 and the following. Each step shown in FIG. 2 will be described in detail below.

Step S110, the camera device 300 sends the face image extracted from the collected video image to the analysis server 100, and sends the video image to the storage server 200, where the video image includes a face background image.

In this embodiment, the camera device 300 captures video image data to obtain video image data, and determines whether the obtained video image data contains a human face. Good, the face angle is the best, etc., including the video image of the face. The camera device 300 can determine the position and size of the face in the video image, extract the face image from the video image, and send the extracted face image to the analysis server 100, and send the video image to the storage server 200. Wherein, the video image includes a background image of the face image.

In this embodiment, in order to facilitate the subsequent storage and restoration of face images and video images by the storage server 200, optionally, referring to FIG. 3, in this embodiment, step S110 may include the following sub-steps:

Step S111, the camera device 300 extracts a face image from the collected video image, and obtains a reference frame image of the video image.

Step S112: Obtain time stamp information of the video image and the reference frame image, and send the face image carrying the time stamp information to the analysis server 100.

In the process of video data transmission and storage, since the amount of video data is very large, it will bring a great burden to the network and storage. Therefore, in order to facilitate the transmission and storage of the video, the video data is generally compressed when it is sent, and then restored when the receiving end receives it, so as to reduce the file size of the video data. This relates to the I-frame and P-frame in the video data compression standard.

An I frame, also known as an intra-frame coded frame, is an independent frame with all its own information. It can be decoded independently without referring to other images. It can be simply understood as a static picture. The first frame in a video sequence is always an I-frame because it is a keyframe. A P frame is also called an inter-frame predictive coding frame, which needs to be encoded with reference to the previous I frame. Indicates the difference between the current frame and the previous frame (the previous frame may be an I frame or a P frame). When decoding, it is necessary to superimpose the difference defined in this frame with the previously buffered picture to generate the final picture. Compared with I-frames, P-frames usually occupy fewer data bits, but the disadvantage is that P-frames are very sensitive to transmission errors due to their complex dependencies on previous P and I reference frames.

In this embodiment, assuming that the current video image is a P frame, a reference frame image of this frame of video image can be obtained, and the first time stamp of the reference frame image and the second time stamp of the video image are recorded. Further, obtain the offset between the video image and its reference frame image, wherein, the offset takes I frame in the GOP length as the initial reference frame, if the GOP length is 25, the face capture camera currently selects the first reference frame. 10 P frames, then the offset is 10. Combine the first timestamp, the second timestamp and the offset into timestamp information. When the camera device 300 sends the face image to the analysis server 100, the time stamp information may be carried.

Step S120, the analysis server 100 analyzes and processes the face image to obtain corresponding face data, saves the face data in a database, and sends the face image to the storage server 200 .

In this embodiment, after receiving the face image, the analysis server 100 performs feature extraction on the face image and converts it into binary form of face data. The distance effect is used to obtain feature data that is helpful for face classification. The human face is composed of parts such as eyes, nose, mouth, and chin. The geometric description of these parts and the structural relationship between them can be used as an important feature for face recognition. The face data obtained in this embodiment includes structured data and semi-structured data, wherein the structured data may include intuitive information such as gender, short hair, long hair and the like. The semi-structured data may include face data such as interpupillary distance, distance between eyes and nose, position of human eyes on the face, and the like.

The analysis server 100 stores the face data obtained by the above analysis in a database, and sends the face image carrying the timestamp information to the storage server 200 .

Step S130, the storage server 200 encodes the received video image, stores the face image and the encoded video image, and returns the storage combination information of the face image and the video image to the analysis server 100 .

The storage server 200 stores the face image after receiving the face image sent by the analysis server 100 . And the time stamp information carried by the face image is analyzed to restore the video image according to the time stamp information and the reference frame image of the video image where the face image is located to obtain a clear video image.

Referring to FIG. 4 , in this embodiment, step S130 may include three sub-steps of step S131 , step S132 and step S133 .

Step S131, the storage server 200 obtains the position information in the video frame of the video image where the face image is located according to the timestamp information carried by the face image obtained from the analysis server 100.

Step S132: Obtain a reference frame image of the video image according to the location information and the time stamp information, obtain a video image where the face image is located according to the reference frame image, and combine the video image and the face images are stored.

Step S133: Send the storage combination information of the video image and the face image to the analysis server 100.

Since the following P frame is stored with reference to the previous frame when the video data is stored, the P frame image is not a clear and complete image, and the frame cannot be directly extracted and used. It needs to be decoded first according to the reference relationship of the previous frame. , and then re-encoded into a complete and clear image for storage on disk.

In this embodiment, the storage server 200 obtains the position information in the video frame of the video image where the face image is located according to the timestamp information carried by the face image obtained from the analysis server 100 . A reference frame image of the video image is obtained according to the location information and the timestamp information. Optionally, the reference frame image of the video image is obtained according to the position information and the offset between the video image and its reference frame image in the time stamp information. In this way, the video image can be re-encoded by using the reference frame image in combination with the offset between the video image and the reference frame image, so as to obtain a clear video image.

The storage server 200 generally uses a block structure storage mode, and generally stores audio and video file data packets in a secondary index mode. Among them, a 16K SUPER DATA is used to mark each file, and the SUPER DATA mainly includes a version number and a file mark. SUPER DATA is followed by a first-level index block with a size of 64K. The first-level index block is followed by a series of 256M data blocks, which are used to save data. The function of the first-level index block is to retrieve the following 256M data blocks. The 256M data block starts with a secondary index block. The secondary index block is followed by a series of I frame group data blocks. The function of the secondary index block is to retrieve the following I frame group data blocks. When storing data, when the remaining space of the 256M data block is not enough to store an I frame group, the system will take a 256M data block for storage, and fill the entire 256M space with 0 in this data block. All data packets of the I frame group are stored in the I frame group data block. The index in the file is recorded in time, and the minimum recording unit is seconds.

Since the image index information carried by the analysis server 100 is inconsistent with the index information stored in the video storage server 200, a conversion is required. The storage server 200 first obtains the time stamp information carried, finds the corresponding I frame group structure according to the time stamp information, then calculates which frame belongs to the I frame group structure according to the offset, and finds out this frame and all previous reference frames, Decode and encode again to obtain a clear video frame corresponding to the frame.

In this embodiment, after the storage server 200 obtains a clear and complete video image, it stores the video image and the face image, and sends the storage combination information of the two to the analysis server 100 . In this way, the analysis server 100 can store the face data of the face image collected by the camera device 300 within a period of time, and the storage information of the face image and the video image where the face image is located in the storage server 200 . In this way, when a certain face image needs to be retrieved subsequently to obtain the background image where it appears, it can be extracted from the storage server 200 .

Optionally, the storage server 200 assembles the storage location of the video image and the storage location of the face image into storage combination information in URL format, and sends the storage combination information to the analysis server 100 . The format of the stored combination information in the URL format may be as follows:

http://IPSANIpAddr:Port

/record#UsrCode/YYYY/MM/DD/HH/pic.jpg? dev=ndcode&fid

Among them, fid is the specific location of the image on the disk, fid=file block id+resid+sliceid+sliceops+len, resid is the ID of the resource, sliceid is the ID of the allocated storage block, and sliceops is the partial size of the image in the storage block. Shift, len represents the length of the image file size.

Step S140, when receiving the face image to be queried sent by the client, the analysis server 100 obtains the storage combination information of the face image, and feeds it back to the client, so that the client can store the stored face image. The combined information is sent to the storage server 200 .

The user can input a face image through the client, that is, the face image to be queried, and the face image to be queried may be taken from a mobile phone, a camera, or copied from other channels. The client sends the face image to be queried to the analysis server 100 . The analysis server 100 performs feature extraction on the image to be queried to obtain feature values of the face image to be queried. It can be seen from the above that there are multiple groups of face data stored in the analysis server 100. Therefore, the analysis server 100 can compare the obtained feature values with the face data in the database, so as to find the data that is the same as the face data to be queried. The face data matched with the eigenvalues of the face image. In addition, the analysis server 100 also stores the storage combination information of multiple groups of face images and the video images where the face images are located. Optionally, the analysis server 100 can obtain the person corresponding to the found face data. face image, and obtain the storage location of the face image and the video image where the face image is located in the storage server 200 .

The analysis server 100 returns the stored combination information to the client. The client may obtain, from the storage server 200 according to the storage combination information, a video image corresponding to the face image to be queried and including its background image.

Step S150, the storage server 200 finds a face image corresponding to the face image to be queried and a video image corresponding to the face image according to the storage combination information, and combines the face image and all the face images. The video image is returned to the client.

After receiving the storage combination information sent by the client, the storage server 200 can find the face image corresponding to the face image to be queried and the video image where the face image is located, and send them to the client. . In this way, the client can obtain the background image of the face image to be queried.

In addition, in this embodiment, when the above-mentioned scheme for acquiring the background image of the face is adopted, the storage server 200 needs to perform the process of decoding and re-encoding the background frame of the face image, and then store another copy, which needs to consume the storage server 200's Resources such as CPU and storage space. Therefore, on the basis of the above, consider using the client to directly return the length of a GOP at the time when retrieving the face background image. According to the normal configuration, the GOP length is 25, and a 1-second video is played during retrieval. Compared with the previous solution, the advantage of this solution is that it not only saves resource consumption such as CPU of the back-end storage device, but also saves storage space.

Optionally, after capturing and extracting the face image, the front-end device sends the face image and the timestamp of the I-frame group where the face image is located to the analysis server 100 . After analyzing and processing the face image, the analysis server 100 sends the device ID of the camera device 300 and the face image to the storage server 200 . The storage server 200 stores the face image after receiving it, and returns the stored information of the URL to the analysis server 100 .

The analysis server 100 stores the storage information of the face image, the time stamp of the I-frame group where the face image is located, and the rest of the face data into the database. When the analysis server 100 receives the image to be queried sent by the client, the analysis server 100 can obtain the face data matched with the face image to be queried after identifying it, and use the I of the face image corresponding to the face data to be obtained. The frame group timestamp is returned to the client. The client obtains the I-frame group of the face image to be queried from the storage server 200 according to the I-frame group timestamp, so that the I-frame group that contains the face image to be queried can be played on the client and is 1 second long. The video image corresponding to the frame group is obtained to obtain the background image of the face image to be queried.

Please refer to FIG. 5 , which is a system for acquiring a background image of a face provided by an embodiment of the present invention. The system includes an analysis server 100, a storage server 200, and a camera device 300 that are connected in communication. The analysis server 100 and the storage server 200 can also communicate with clients The terminal establishes a communication connection. The analysis server 100 includes a processing module 110 and a storage combination information acquisition module 120 , the storage server 200 includes a storage module 210 and a video image search module 220 , and the camera device 300 includes a sending module 310 .

The sending module 310 is configured to send the face image extracted from the collected video image to the analysis server 100, and send the video image to the storage server 200, where the video image includes the face background. image. The sending module 310 may be configured to execute step S110 shown in FIG. 2 , and the specific operation method can refer to the detailed description of step S110.

The processing module 110 is configured to encode the received video image, store the face image and the encoded video image, and return the storage combination information of the face image and the video image to the analysis server 100 . The processing module 110 may be configured to execute step S120 shown in FIG. 2 , and the specific operation method may refer to the detailed description of step S120 .

The storage module 210 is configured to store the received face image and video image, and return the storage combination information of the face image and the video image to the analysis server 100 . The storage module 210 can be used to execute step S130 shown in FIG. 2 , and the specific operation method can refer to the detailed description of step S130 .

The storage combination information acquisition module 120 is configured to obtain the storage combination information of the face image when receiving the face image to be queried sent by the client, and feed it back to the client, so that the client can retrieve all the information. The storage combination information is sent to the storage server 200 . The storage combination information acquisition module 120 may be configured to execute step S140 shown in FIG. 2 , and the specific operation method may refer to the detailed description of step S140.

The video image search module 220 is configured to search for a face image corresponding to the face image to be queried and a video image corresponding to the face image according to the storage combination information, and compare the face image and the face image. The video image is returned to the client. The video image search module 220 may be configured to perform step S150 shown in FIG. 2 , and the specific operation method may refer to the detailed description of step S150.

Optionally, referring to FIG. 6 , in this embodiment, the sending module 310 includes an extraction unit 311 and a timestamp information acquisition unit 312 .

The extraction unit 311 is configured to extract a face image from the collected video image, and obtain a reference frame image of the video image. The extracting unit 311 may be configured to perform step S111 shown in FIG. 3 , and reference may be made to the detailed description of step S111 for a specific operation method.

The time stamp information obtaining unit 312 is configured to obtain time stamp information of the video image and the reference frame image, and send the face image carrying the time stamp information to the analysis server 100 . The video image search module 220 may be configured to execute step S112 shown in FIG. 3 , and the specific operation method may refer to the detailed description of step S112 .

Optionally, referring to FIG. 7 , in this embodiment, the time stamp information obtaining unit 312 includes an offset information obtaining subunit 3121 and a sending subunit 3122 .

The offset information obtaining subunit 3121 is configured to obtain the first timestamp of the reference frame image, the second timestamp of the video image, and the offset of the video image relative to the reference frame image.

The sending subunit 3122 is configured to combine the first timestamp, the second timestamp and the offset into timestamp information, and send the face image carrying the timestamp information to the analysis server 100 .

Optionally, referring to FIG. 8 , in this embodiment, the storage module 210 includes a location information acquiring unit 211 , a storage unit 212 and a sending unit 213 .

The position information obtaining unit 211 is configured to obtain position information in the video frame of the video image where the face image is located according to the timestamp information carried by the face image obtained from the analysis server 100 . The location information obtaining unit 211 may be configured to execute step S131 shown in FIG. 4 , and the specific operation method may refer to the detailed description of step S131 .

The storage unit 212 is configured to obtain a reference frame image of the video image according to the position information and the timestamp information, obtain a video image where the face image is located according to the reference frame image, and store the video image. The image and the face image are stored. The storage unit 212 can be used to execute step S132 shown in FIG. 4 , and the specific operation method can refer to the detailed description of step S132 .

The sending unit 213 is configured to send the storage combination information of the video image and the face image to the analysis server 100 . The sending unit 213 may be configured to perform step S133 shown in FIG. 4 , and reference may be made to the detailed description of step S133 for the specific operation method.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method, which will not be repeated here.

To sum up, the method and system for obtaining a background image of a face provided by the embodiments of the present invention store the storage information of the face image and the video image where the face image is located in the analysis server 100, and store the face image and the human face image in the analysis server 100. The video image where the face image is located is stored in the storage server 200 . Thus, when the analysis server 100 receives the face image to be queried sent by the client, it can analyze the face image to be queried to find matching face data from the stored face data, and find the corresponding face data according to the face data. The storage information of the face image and the video image where the face image is located. The client can obtain the video image corresponding to the face image to be queried from one end of the storage server 200 according to the stored information, so as to obtain the face background image of the face image to be queried. In the face background acquisition scheme, the storage information of the face image and the video image of the face image in the storage server 200 is stored in the analysis server 100, and the face image and the video image where the face image is located are stored in the storage server 200. In the server 200, the burden caused by a large number of video images to the analysis server 100 is avoided, and the efficiency of face background retrieval is improved.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, eg, the flowcharts and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods and computer program products according to embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention. It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

Claims (10)

1. A face background image acquisition method is characterized in that the method is applied to a face background image acquisition system, the system comprises an analysis server, a storage server and a camera device which are in communication connection, the analysis server and the storage server can also establish communication connection with a client, and the method comprises the following steps:

the camera equipment sends a face image extracted from the collected video image to the analysis server and sends the video image to the storage server, wherein the video image comprises a face background image;

the analysis server analyzes and processes the face image to obtain corresponding face data, stores the face data in a database and sends the face image to the storage server;

the storage server encodes the received video image, stores the face image and the encoded video image, and returns the storage combination information of the face image and the video image to the analysis server;

when receiving a face image to be inquired sent by a client, the analysis server obtains storage combination information of the face image and feeds the storage combination information back to the client so that the client sends the storage combination information to the storage server;

And the storage server searches the face image corresponding to the face image to be inquired and the video image corresponding to the face image according to the storage combination information, and returns the face image and the video image to the client.

2. The method for acquiring the face background image according to claim 1, wherein the step of sending the face image extracted from the acquired video image to the analysis server by the camera device comprises:

the camera equipment extracts a face image from the acquired video image and obtains a reference frame image of the video image;

and acquiring the time stamp information of the video image and the reference frame image, and sending the face image carrying the time stamp information to the analysis server.

3. The method for acquiring the face background image according to claim 2, wherein the step of obtaining the time stamp information of the video image and the reference frame image and sending the face image carrying the time stamp information to the analysis server comprises:

acquiring a first time stamp of the reference frame image, a second time stamp of the video image and an offset of the video image relative to the reference frame image;

And forming timestamp information by the first timestamp, the second timestamp and the offset, and sending the face image carrying the timestamp information to the analysis server.

4. The method for obtaining the face background image according to claim 2, wherein the step of the storage server encoding the received video image, storing the face image and the encoded video image, and returning the storage combination information of the face image and the video image to the analysis server comprises:

the storage server obtains the position information of the video image where the face image is located in the video frame according to the timestamp information carried by the face image obtained from the analysis server;

obtaining a reference frame image of the video image according to the position information and the timestamp information, obtaining a video image where the face image is located according to the reference frame image, and storing the video image and the face image;

and sending the storage combination information of the video image and the face image to the analysis server.

5. The method for obtaining the face background image according to claim 4, wherein the step of obtaining a reference frame image of the video image according to the position information and the timestamp information, and obtaining a video image where the face image is located according to the reference frame image comprises:

Obtaining a reference frame image of the video image according to the position information and the offset between the video image and the reference frame image in the timestamp information;

and coding the reference frame image according to the reference frame image and the offset to obtain a video image where the face image is located.

6. The method for acquiring the face background image according to claim 4, wherein the step of sending the storage combination information of the video image and the face image to the analysis server includes:

and the storage server splices the storage position of the video image and the storage position of the face image into storage combination information in a URL format and sends the storage combination information to the analysis server.

7. The system for acquiring the face background image is characterized by comprising an analysis server, a storage server and a camera device which are in communication connection, wherein the analysis server and the storage server can also be in communication connection with a client, the analysis server comprises a processing module and a storage combination information acquisition module, the storage server comprises a storage module and a video image searching module, and the camera device comprises a sending module:

The sending module is used for sending a face image extracted from the collected video image to the analysis server and sending the video image to the storage server, wherein the video image comprises a face background image;

the processing module is used for analyzing and processing the face image to obtain corresponding face data, storing the face data in a database and sending the face image to the storage server;

the storage module is used for coding the received video image, storing the face image and the coded video image and returning the storage combination information of the face image and the video image to the analysis server;

the storage combination information acquisition module is used for acquiring the storage combination information of the face image when receiving the face image to be inquired sent by the client and feeding the storage combination information back to the client so that the client sends the storage combination information to the storage server;

the video image searching module is used for searching the face image corresponding to the face image to be inquired and the video image corresponding to the face image according to the storage combination information, and returning the face image and the video image to the client.

8. The face background image acquisition system according to claim 7, wherein the transmission module includes an extraction unit and a time stamp information acquisition unit;

the extraction unit is used for extracting a face image from the acquired video image and obtaining a reference frame image of the video image;

the time stamp information acquisition unit is used for acquiring the time stamp information of the video image and the reference frame image and sending the face image carrying the time stamp information to the analysis server.

9. The face background image acquisition system according to claim 8, wherein the time stamp information acquisition unit includes an offset information acquisition subunit and a transmission subunit;

the offset information acquisition subunit is used for acquiring a first time stamp of the reference frame image, a second time stamp of the video image and an offset of the video image relative to the reference frame image;

and the sending subunit is configured to combine the first timestamp, the second timestamp, and the offset into timestamp information, and send the face image carrying the timestamp information to the analysis server.

10. The system for acquiring a face background image according to claim 8, wherein the storage module comprises a position information acquisition unit, a storage unit and a transmission unit;

The position information acquisition unit is used for acquiring the position information of the video image in which the face image is positioned in the video frame according to the timestamp information carried by the face image acquired from the analysis server;

the storage unit is used for obtaining a reference frame image of the video image according to the position information and the timestamp information, obtaining a video image where the face image is located according to the reference frame image, and storing the video image and the face image;

the sending unit is used for sending the storage combination information of the video image and the face image to the analysis server.

Images