阅读说明：本技术 一种视频实时检索方法、装置和系统 (Video real-time retrieval method, device and system ) 是由 张敬深 单发喜 张二萌 于 2021-08-04 设计创作，主要内容包括：本发明公开了一种视频实时检索方法,包括如下步骤：步骤一：将待检索的视频数据集在本地进行加密处理,得到加密数据集；步骤二：将所述加密数据集上传至云端服务器,以供所述云端服务器以不解密的方式在加密视频数据中实时检索所述加密数据集,得到加密检索数据；步骤三：从所述云端服务器处接收所述加密检索数据,并将所述加密检索数据在本地进行解密,得到视频检索结果。一种视频实时检索方法,可在云端以不解密方式对视频进行实时检索。本发明还公开了一种视频实时检索装置和系统。(The invention discloses a video real-time retrieval method, which comprises the following steps: the method comprises the following steps: carrying out local encryption processing on a video data set to be retrieved to obtain an encrypted data set; step two: uploading the encrypted data set to a cloud server so that the cloud server can retrieve the encrypted data set in real time in encrypted video data in a non-decryption mode to obtain encrypted retrieval data; step three: and receiving the encrypted retrieval data from the cloud server, and decrypting the encrypted retrieval data locally to obtain a video retrieval result. A real-time video retrieval method can perform real-time video retrieval in a non-decryption mode at the cloud. The invention also discloses a video real-time retrieval device and a video real-time retrieval system.)

1. A video real-time retrieval method is characterized by comprising the following steps:

the method comprises the following steps: carrying out local encryption processing on a video data set to be retrieved to obtain an encrypted data set;

step two: uploading the encrypted data set to a cloud server so that the cloud server can retrieve the encrypted data set in real time in encrypted video data in a non-decryption mode to obtain encrypted retrieval data;

step three: and receiving the encrypted retrieval data from the cloud server, and decrypting the encrypted retrieval data locally to obtain a video retrieval result.

2. The method for retrieving video in real time as claimed in claim 1, wherein in step one, the video data set to be retrieved is encrypted locally by using a homomorphic encryption algorithm.

3. The method for real-time video retrieval according to claim 1, wherein in step three, the encrypted retrieval data is decrypted locally using a homomorphic decryption algorithm.

4. The method for real-time video retrieval according to any one of claims 1-3, wherein the number of the cloud servers is at least two, and each cloud server receives the encrypted video data.

5. The method according to claim 4, wherein in the second step, the same encrypted data set is uploaded to at least two cloud servers, so that the at least two cloud servers can retrieve the same encrypted data set from the encrypted video data without decryption at the same time, thereby obtaining at least two sets of encrypted retrieval data.

6. The real-time video retrieval method of claim 4, wherein in the first step, the video data set to be retrieved is firstly subjected to fragmentation processing to obtain at least two groups of fragmentation data sets, and then each group of fragmentation data sets is respectively subjected to encryption processing to obtain at least two groups of encryption data sets; in the second step, at least two groups of encrypted data sets are uploaded to different cloud servers, so that at least two cloud servers can simultaneously retrieve different encrypted data sets in the encrypted video data in real time in a non-decryption mode, and at least two groups of encrypted retrieval data are obtained.

7. The method for retrieving video in real time according to claim 1, further comprising, before step one: the collected video is encrypted locally to obtain the encrypted video data, and the encrypted video data is uploaded to the cloud server.

8. The method for real-time video retrieval according to claim 7, wherein the captured video is encrypted locally by using a homomorphic encryption algorithm.

9. A video real-time search device comprising a processor and a memory connected to the processor, the memory storing a computer program for execution by the processor, wherein the processor executes the computer program to perform the video real-time search method according to any one of claims 1 to 8.

10. A video real-time retrieval system, comprising the video real-time retrieval device of claim 9 and a cloud server, wherein the video real-time retrieval device and the cloud server perform data transmission via a network.

Technical Field

The invention relates to a video retrieval technology, in particular to a method, a device and a system for retrieving videos in real time.

Background

Video real-time retrieval refers to identifying the content of a video picture using image recognition techniques to find a desired data set in a video.

Currently, video real-time retrieval usually adopts the following two ways: one is to upload the video to the cloud server in real time and search in real time in the cloud server; the other is to retrieve the video in real time at a local server.

The inventor finds that: when the cloud server carries out real-time retrieval on the video, whether the video is encrypted or not during uploading, the video needs to be decrypted on the cloud server and retrieved in a plain text mode, and the risk of data leakage exists; when the local server performs real-time video retrieval, the real-time video retrieval is usually limited by the resources of the local server, and the real-time performance is difficult to guarantee for complex scenes with large calculation amount.

Disclosure of Invention

In order to solve the above-mentioned deficiencies of the prior art, the present invention provides a real-time video retrieval method, which can perform real-time video retrieval in a non-decryption manner at the cloud.

The invention also provides a video real-time retrieval device and a video real-time retrieval system.

The technical problem to be solved by the invention is realized by the following technical scheme:

a video real-time retrieval method comprises the following steps:

the method comprises the following steps: carrying out local encryption processing on a video data set to be retrieved to obtain an encrypted data set;

step two: uploading the encrypted data set to a cloud server so that the cloud server can retrieve the encrypted data set in real time in encrypted video data in a non-decryption mode to obtain encrypted retrieval data;

step three: and receiving the encrypted retrieval data from the cloud server, and decrypting the encrypted retrieval data locally to obtain a video retrieval result.

Further, in the first step, a homomorphic encryption algorithm is locally adopted to encrypt the video data set to be retrieved.

Further, in step three, the encrypted retrieval data is decrypted locally by adopting a homomorphic decryption algorithm.

Furthermore, the number of the cloud servers is at least two, and each cloud server receives the encrypted video data.

Further, in the second step, the same encrypted data set is uploaded to at least two cloud servers, so that the at least two cloud servers can retrieve the same encrypted data set in the encrypted video data in a non-decryption manner at the same time, and at least two groups of encrypted retrieval data are obtained.

Further, in the first step, the video data set to be retrieved is firstly subjected to fragmentation processing to obtain at least two groups of fragmentation data sets, and then each group of fragmentation data sets is respectively subjected to encryption processing to obtain at least two groups of encryption data sets; in the second step, at least two groups of encrypted data sets are uploaded to different cloud servers, so that at least two cloud servers can simultaneously retrieve different encrypted data sets in the encrypted video data in real time in a non-decryption mode, and at least two groups of encrypted retrieval data are obtained.

Further, before the step one, the method further comprises the following steps: the collected video is encrypted locally to obtain the encrypted video data, and the encrypted video data is uploaded to the cloud server.

Furthermore, the collected video is encrypted locally by adopting a homomorphic encryption algorithm.

A video real-time retrieval device comprises a processor and a memory connected with the processor, wherein a computer program executed by the processor is stored in the memory, and the video real-time retrieval method is carried out when the processor executes the computer program.

A real-time video retrieval system comprises the real-time video retrieval device and a cloud server, wherein data transmission is carried out between the real-time video retrieval device and the cloud server through a network.

The invention has the following beneficial effects: the video real-time retrieval method, the video real-time retrieval device and the video real-time retrieval system encrypt and decrypt video data locally, the video data are directly retrieved and processed in an encrypted state at the cloud end, the video data uploaded to the cloud end can be prevented from leaking due to decryption at the cloud end, meanwhile, the encryption algorithm and the decryption algorithm are stored locally, the encryption algorithm and the decryption algorithm can be prevented from leaking from the cloud end, the video retrieval efficiency and real-time performance are improved through a distributed server at the cloud end, and missing or false detection is reduced.

Drawings

FIG. 1 is a block diagram illustrating the steps of a video real-time retrieval method according to the present invention;

FIG. 2 is a block diagram illustrating steps of an embodiment of a video real-time retrieval method according to the present invention;

FIG. 3 is a block diagram illustrating another embodiment of a video real-time retrieval method according to the present invention;

fig. 4 is a schematic block diagram of a video real-time retrieval system provided by the present invention.

Detailed Description

The present invention will be described in detail below with reference to the accompanying drawings and examples.

Example one

As shown in fig. 1, a video real-time retrieval method includes the following steps:

the method comprises the following steps: and carrying out local encryption processing on the video data set to be retrieved to obtain an encrypted data set.

In the first step, a homomorphic encryption algorithm is locally adopted to encrypt the video data set to be retrieved. The homomorphic encryption algorithm is an encryption method with special natural attributes, data which is subjected to homomorphic encryption is processed to obtain an output, the output is decrypted, the result of the output is the same as the output result obtained by processing the unencrypted original data by adopting the same method, namely the data which is subjected to homomorphic encryption can be directly subjected to data processing without being decrypted in advance.

Step two: and uploading the encrypted data set to a cloud server so that the cloud server can retrieve the encrypted data set in real time in the encrypted video data in a non-decryption manner to obtain encrypted retrieval data.

In the second step, the encrypted video data is also encrypted by the homomorphic encryption algorithm, and since the encrypted data set and the encrypted video data are homomorphic encrypted, the cloud server does not need to decrypt the encrypted data set and the encrypted video data in advance before retrieving the encrypted data set in the encrypted video data in real time.

The encrypted video data can be formed by uploading and storing the locally encrypted video acquired in the past in the cloud server, or can be formed by uploading the locally encrypted video acquired in real time to the cloud server when video retrieval is needed; after the video retrieval is completed, the encrypted video data can be continuously stored in the cloud server or deleted from the cloud server.

Therefore, before the step one, the method further comprises the following steps: the collected video is encrypted locally to obtain the encrypted video data, and the encrypted video data is uploaded to the cloud server.

In the step, the collected video is encrypted locally by adopting a homomorphic encryption algorithm.

The number of the cloud servers is at least two, and each cloud server receives the encrypted video data.

As shown in fig. 2, in an embodiment, in the second step, the same encrypted data set is uploaded to at least two cloud servers, so that the at least two cloud servers can retrieve the same encrypted data set in the encrypted video data without decryption at the same time, thereby obtaining at least two sets of encrypted retrieval data.

In the embodiment, a plurality of cloud servers are adopted to retrieve the same encrypted data set, at least two groups of obtained encrypted retrieval data can be verified mutually, and missing or false detection of a single cloud server is avoided.

As shown in fig. 3, in another embodiment, in the first step, a video data set to be retrieved is firstly subjected to fragmentation processing to obtain at least two groups of fragmentation data sets, and then each group of fragmentation data sets is respectively subjected to encryption processing to obtain at least two groups of encryption data sets; in the second step, at least two groups of encrypted data sets are uploaded to different cloud servers, so that at least two cloud servers can simultaneously retrieve different encrypted data sets in the encrypted video data in real time in a non-decryption mode, and at least two groups of encrypted retrieval data are obtained.

In this embodiment, the video data set is firstly subjected to fragmentation processing and then encrypted, then a plurality of cloud servers are used for retrieving different encrypted data sets in real time, each cloud server is only responsible for retrieving one part of the video data set, and finally at least two groups of encrypted retrieval data are collected, so that the retrieval efficiency can be improved.

Step three: and receiving the encrypted retrieval data from the cloud server, and decrypting the encrypted retrieval data locally to obtain a video retrieval result.

In the third step, a homomorphic decryption algorithm is locally adopted to decrypt the encrypted retrieval data.

The video real-time retrieval method is used for encrypting and decrypting video data locally, the video data are directly retrieved and processed in an encrypted state at the cloud end, the video data uploaded to the cloud end can be prevented from leaking due to decryption at the cloud end, meanwhile, the encryption algorithm and the decryption algorithm are stored locally, the encryption algorithm and the decryption algorithm can be prevented from leaking from the cloud end, the video retrieval efficiency and real-time performance are improved through a distributed server at the cloud end, and missing or false detection is reduced.

Example two

As shown in fig. 4, a video real-time search device includes a processor and a memory connected to the processor, where the memory stores a computer program for the processor to execute, and when the processor executes the computer program, the video real-time search device performs the video real-time search method according to the first embodiment.

EXAMPLE III

As shown in fig. 4, a video real-time retrieval system includes the video real-time retrieval device and the cloud server according to the second embodiment, and data transmission is performed between the video real-time retrieval device and the cloud server through a network.

The above-mentioned embodiments only express the embodiments of the present invention, and the description is more specific and detailed, but not understood as the limitation of the patent scope of the present invention, but all the technical solutions obtained by using the equivalent substitution or the equivalent transformation should fall within the protection scope of the present invention.