CN114025173A - Image processing method, terminal and computer readable storage medium - Google Patents
Image processing method, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN114025173A CN114025173A CN202111362329.9A CN202111362329A CN114025173A CN 114025173 A CN114025173 A CN 114025173A CN 202111362329 A CN202111362329 A CN 202111362329A CN 114025173 A CN114025173 A CN 114025173A
- Authority
- CN
- China
- Prior art keywords
- target object
- privacy
- video frame
- image
- processing method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 40
- 238000001514 detection method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000006399 behavior Effects 0.000 claims description 44
- 238000000605 extraction Methods 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 description 17
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000009191 jumping Effects 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/88—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving rearrangement of data among different coding units, e.g. shuffling, interleaving, scrambling or permutation of pixel data or permutation of transform coefficient data among different blocks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0861—Generation of secret information including derivation or calculation of cryptographic keys or passwords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Security & Cryptography (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides an image processing method, a terminal and a computer readable storage medium, wherein the image processing method comprises the steps of obtaining a first video frame, and acquiring the first video frame by first image acquisition equipment; performing target detection on the first video frame, and determining a first target object contained in the first video frame; carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information; and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information. The method and the device for processing the privacy of the first target object carry out privacy processing on the area containing the first target object, and therefore it is guaranteed that the privacy of the first target object is not revealed; when the first target object has the preset behavior track, privacy restoration processing can be performed on privacy shielding image information, namely when a behavior violating public safety occurs, important information of an area containing the first target object is restored, and then public safety is guaranteed.
Description
Technical Field
The present invention relates to the field of image recognition technologies, and in particular, to an image processing method, a terminal, and a computer-readable storage medium.
Background
With the rapid development of the internet, especially the rapid development of the video service based on the network, great convenience is brought to the production and the life of people. Nowadays, video monitoring systems can be seen anywhere and anytime, such as public areas like communities, shopping malls, roads, parking lots, etc. However, reports that people's private data is frequently revealed are endless, and people are more eager to protect their privacy friendly as people's safety awareness increases.
At present, the privacy blocking requirement of a video is frequently proposed, and the main purpose of the privacy blocking requirement is to protect private data of a user from being illegally acquired so as to cause personal information leakage. However, when the privacy is blocked, important information is lost, and for special industries, especially for public safety industries, the privacy of users is not leaked and the public safety is difficult.
Disclosure of Invention
The invention mainly solves the technical problem of providing an image processing method, a terminal and a computer readable storage medium, and solves the problem that in the prior art, in the target tracking process, public safety cannot be guaranteed and the privacy of a user cannot be guaranteed to be leaked.
In order to solve the technical problems, the first technical scheme adopted by the invention is as follows: there is provided an image processing method including: acquiring a first video frame, wherein the first video frame is acquired by first image acquisition equipment; performing target detection on the first video frame, and determining a first target object contained in the first video frame; carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information; and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information.
The method comprises the following steps of carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information, wherein the method comprises the following steps: generating corresponding identity information according to the first target object; performing feature extraction on the first target object to obtain a first feature map; and associating the identity information of the first target object with the first feature map.
The image processing method further comprises the following steps: acquiring a second video frame, wherein the second video frame is acquired by second image acquisition equipment; performing target detection on the second video frame, and determining a second target object contained in the second video frame; in response to the second target object being the first target object; the identity information of the first target object is sent to the second image acquisition device.
The image processing method further comprises the following steps: extracting the features of the second target object to obtain a second feature map; in response to the second feature map being the first feature map, the trajectory information of the second target object is associated with the first target object.
The method for processing privacy occlusion of the area containing the first target object in the first video frame to obtain privacy occlusion image information includes: acquiring data of a region containing a first target object in a first video frame; encrypting data of an area containing the first target object through a CP-ABE algorithm to obtain privacy blocking data; and merging the privacy occlusion data with the data of other areas of the first video frame, which do not contain the first target object, so as to obtain privacy occlusion image information.
The target detection is performed on the first video frame, and the determination of the first target object contained in the first video frame includes: carrying out target detection on the first video frame to obtain a candidate target object contained in the first video frame; judging whether the candidate target object belongs to a preset target object or not; and if the candidate target object belongs to the preset target object, determining that the candidate target object is the first target object.
Wherein obtaining the first video frame previously comprises: and pre-storing a preset behavior track, and setting an access structure according to the preset behavior track.
Wherein, in response to the area containing the first target object having the preset behavior track, the privacy-masked image information is subjected to privacy restoration processing, including: if the area containing the first target object has the preset behavior track, verifying the preset behavior track through the access structure; and if the verification is successful, carrying out privacy restoration processing on the privacy sheltered image information.
The preset action track comprises one of stealing action, fighting action and stagnation dangerous area action.
In order to solve the above technical problems, the second technical solution adopted by the present invention is: there is provided a terminal comprising a memory, a processor and a computer program stored in the memory and running on the processor, the processor being adapted to execute the sequence data to implement the steps in the image processing method described above.
In order to solve the above technical problems, the third technical solution adopted by the present invention is: there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the above-described image processing method.
The invention has the beneficial effects that: different from the situation of the prior art, the image processing method, the terminal and the computer readable storage medium are provided, wherein the image processing method is used for acquiring a first video frame, and the first video frame is acquired by a first image acquisition device; performing target detection on the first video frame, and determining a first target object contained in the first video frame; carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information; and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information. The method and the device have the advantages that the acquired first video frame is detected to obtain a first target object, and privacy processing is performed on the area containing the first target object, so that the privacy of the first target object is guaranteed not to be revealed; when the area of the first target object has the preset behavior track, privacy restoration processing can be performed on privacy-shielded image information, namely when a behavior violating public safety occurs, important information of the area containing the first target object is restored, and then public safety is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of an image processing method provided by the present invention;
FIG. 2 is a flowchart illustrating an exemplary embodiment of an image processing method according to the present invention;
FIG. 3 is a flowchart illustrating an image processing method according to another embodiment of the present invention;
FIG. 4 is a layout diagram of an image capture device;
FIG. 5 is a schematic block diagram of one embodiment of a terminal provided by the present invention;
FIG. 6 is a schematic block diagram of one embodiment of a computer-readable storage medium provided by the present invention.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
In order to make those skilled in the art better understand the technical solution of the present invention, an image processing method provided by the present invention is further described in detail below with reference to the accompanying drawings and the detailed description.
Referring to fig. 1, fig. 1 is a schematic flow chart of an image processing method according to the present invention.
The embodiment provides an image processing method, which can process an image acquired in real time and can also process a video frame in an offline video. The image processing method includes the following steps.
S11: a first video frame is acquired.
Specifically, a first video frame is acquired by a first image acquisition device. In an optional embodiment, a preset behavior track is pre-stored, and the access structure is set according to the preset behavior track.
S12: and carrying out target detection on the first video frame, and determining a first target object contained in the first video frame.
Specifically, target detection is performed on a first video frame to obtain a candidate target object contained in the first video frame; judging whether the candidate target object belongs to a preset target object or not; and if the candidate target object belongs to the preset target object, determining that the candidate target object is the first target object. Generating corresponding identity information according to the first target object; performing feature extraction on the first target object to obtain a first feature map; and associating the identity information of the first target object with the first feature map.
S13: and carrying out privacy occlusion processing on an area containing the first target object in the first video frame to obtain privacy occlusion image information.
Specifically, data of an area containing a first target object in a first video frame is acquired; encrypting data of an area containing a first target object by using a CP-ABE (Ciphertext Policy Attribute Based Encryption) algorithm to obtain privacy occlusion data; and merging the privacy occlusion data with the data of other areas of the first video frame, which do not contain the first target object, so as to obtain privacy occlusion image information.
S14: and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information.
Specifically, if the area containing the first target object has a preset behavior track, verifying the preset behavior track through the access structure; and responding to successful verification, and performing privacy restoration processing on the privacy sheltered image information.
In a specific embodiment, a second video frame is obtained, and the second video frame is acquired by a second image acquisition device; performing target detection on the second video frame, and determining a second target object contained in the second video frame; in response to the second target object being the first target object; the identity information of the first target object is sent to the second image acquisition device. Extracting the features of the second target object to obtain a second feature map; in response to the second feature map being the first feature map, the trajectory information of the second target object is associated with the first target object.
The image processing method provided by the embodiment acquires a first video frame, and the first video frame is acquired by a first image acquisition device; performing target detection on the first video frame, and determining a first target object contained in the first video frame; carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information; and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information. The method and the device have the advantages that the acquired first video frame is detected to obtain a first target object, and privacy processing is performed on the area containing the first target object, so that the privacy of the first target object is guaranteed not to be revealed; when the area of the first target object has the preset behavior track, privacy restoration processing can be performed on privacy-shielded image information, namely when a behavior violating public safety occurs, important information of the area containing the first target object is restored, and then public safety is guaranteed.
Referring to fig. 2, fig. 2 is a flowchart illustrating an image processing method according to an embodiment of the present invention. The embodiment provides an image processing method, which can process an image acquired in real time and can also process a video frame in an offline video. The image processing method includes the following steps.
S201: and pre-storing a preset behavior track, and setting an access structure according to the preset behavior track.
Specifically, in the present embodiment, a preset behavior trace is first set. The preset action track comprises stealing actions, fighting actions, stagnation dangerous area actions and other illegal violations. When the preset behavior track appears in the image, the image in the image acquisition equipment can be subjected to privacy restoration viewing after the access structure is verified. The access structure comprises image acquisition equipment managers, image acquisition equipment maintainers and public security system personnel. When at least one of an image acquisition equipment manager and an image acquisition equipment maintainer in the access structure and a public security system person agree to view the image information, the access structure verification is successful. In a specific embodiment, the characteristic information of the image capturing device manager, the image capturing device maintainer and the public security system personnel can be recorded in the image capturing device in advance and stored. For example, the feature information includes information such as occupation, working age, department of the department, and specific matters, and the access authority of the image capturing device is managed by setting the access structure, so that privacy data included in the image information captured by the image capturing device is protected from being leaked.
The access structure can be set reasonably according to specific application scenarios and actual needs of users. The characteristic data of the public security system personnel in the access structure input into the image acquisition equipment is as follows: traffic police, five years of work age, ten years of work age, beaches, running red lights and logistics departments as examples, then correspondingly, this image acquisition equipment can constitute an access structure according to this characteristic data and be: traffic polices of non-logistics departments in the coastal region with the working age of more than five years and less than ten years can check the information of the vehicle monitoring image which removes privacy occlusion in the image when the red light is run. And the personnel who do not meet the access structure can not remove the corresponding privacy mask, so that the fine-grained access authority of the privacy mask part can be controlled by setting the access structure.
The method comprises the steps of acquiring an image of a monitored area based on first image acquisition equipment, carrying out target detection to obtain a first target object, and carrying out privacy shielding processing on the detected first target object. For example, privacy-mask processing is performed on the detected face of the first target object.
S202: a first video frame is acquired.
Specifically, a current video frame is acquired through a first image acquisition device, and the current video frame is used as a first video frame. In other optional embodiments, the first image capturing device acquires video data, and takes a video frame to be detected as the first video frame. That is, the first video frame in the method may be image data acquired in real time, or may be image data in an offline state. The first image capturing device may be an internet protocol Camera (IP Camera, IPC).
S203: and carrying out target detection on the first video frame to obtain a candidate target object contained in the first video frame.
Specifically, target detection is performed on the acquired first video frame to obtain a detection frame of the candidate target object. The detection frame of the candidate target object may be understood as an area portion of the first video frame that needs privacy blocking processing to prevent privacy information from being leaked, and specifically, the detection frame of the candidate target object may be detected by using a trained network detection model integrated on the first image capturing device, or detected by capturing a special icon or a graphic area, so as to mark the detection frame including the candidate target object after detecting the detection frame including the candidate target object in the first video frame. The first video frame may be video code stream information or picture information, which is not limited in this application.
S204: and judging whether the candidate target object belongs to a preset target object.
Specifically, a preset target object to be monitored is set, and the method only tracks the preset target object. The preset target object comprises a person, an animal, a vehicle and the like. And comparing the candidate target object in the detection frame obtained by detection in the first video frame with a preset target object. If the candidate target object belongs to the preset target object, directly jumping to the step S205; if the candidate target object does not belong to the preset target object, the process directly jumps to step S206.
S205: and determining the candidate target object as the first target object.
Specifically, if the candidate target object belongs to a preset target object, the candidate target object is determined to be the first target object.
S206: the next video frame is acquired.
Specifically, if the candidate target object does not belong to the preset target object, it is determined that the candidate target object does not belong to the tracked object, and the next video frame may be directly acquired for target detection.
S207: and generating corresponding identity information according to the first target object.
Specifically, when a first target object is determined among the candidate target objects, corresponding identity information is generated for the first target object. The Identity information is an Identity identifier unique to the first target object, and is recorded as Identity Information (ID).
S208: and performing feature extraction on the first target object to obtain a first feature map.
Specifically, feature extraction is performed on a detection frame including the first target object, so as to obtain a first feature map of the first target object. The detection frame containing the first target object is subjected to feature extraction through a convolutional neural network to obtain a first feature map.
S209: and associating the identity information of the first target object with the first feature map.
Specifically, the ID of the first target object detected in the first video frame is associated with the extracted first feature map and stored.
S210: and acquiring data of an area containing the first target object in the first video frame and encrypting the data to obtain privacy blocking data.
Specifically, privacy occlusion processing is performed on a detection frame containing a first target object in a first video frame by setting a privacy occlusion rule. Data of a preset area of the first target object can be extracted and encrypted. For example, data of the face of the first target object is extracted and encrypted. The data of the preset area of the first target object may be encrypted by the system common parameters of the first image capturing device and the preset access structure. The client may also extract and encrypt data of a preset region of the first target object included in the received first video frame. In a specific embodiment, the data of the preset area of the first target object is encrypted through a CP-ABE algorithm to obtain privacy occlusion data.
S211: and merging the privacy occlusion data with the data of other areas of the first video frame, which do not contain the first target object, so as to obtain privacy occlusion image information.
Specifically, the pixel value of the image corresponding to the data of the preset area of the first target object is adjusted to 0, so that the encrypted data of the preset area of the first target object is merged into the first video frame data subjected to the cropping processing. That is, the data of the detection frame containing the first target object subjected to the encryption processing is combined with other data not subjected to the encryption processing in the first video frame to generate privacy-masked image information.
In another optional embodiment, a picture with a background color of any one of white, blue, and the like and having the same size as the preset area containing the first target object is generated and overlaid on the preset area of the first target object in the first video frame, so as to obtain privacy-masked image information obtained after performing privacy masking processing on data of the preset area of the first target object in the first video frame.
The first image acquisition equipment sends privacy shielding image information corresponding to the first video frame to the client, and the client judges the motion track of the first target object in the privacy shielding image information so as to determine whether privacy restoration needs to be carried out on the first target object.
S212: and judging whether the first target object has a preset behavior track.
Specifically, since the privacy blocking is performed on the preset area of the first target object through the above steps, whether the first target object has the preset behavior track is determined by judging whether the detection frame including the first target object is in the preset range or not, or by judging whether the behavior of the first target object in the detection frame belongs to the preset behavior.
If the first target object has the preset behavior track, directly jumping to the step S213; if the first target object does not have the preset behavior trace, directly jumping to step S215.
S213: and verifying the preset behavior track through the access structure.
Specifically, if the area containing the first target object has a preset behavior track, the preset behavior track is verified through the access structure. When at least one of an image acquisition equipment manager and an image acquisition equipment maintainer in the access structure and a public security system person agree to view the image information, the access structure verification is successful. So that when at least one of the image acquisition equipment manager and the image acquisition equipment maintainer coexist with the public security system personnel, the first target object in the first video frame is subjected to privacy restoration.
S214: and responding to successful verification, and performing privacy restoration processing on the privacy sheltered image information.
Specifically, when at least one of an image acquisition device manager and an image acquisition device maintainer in the access structure and a public security system person agree to view image information, privacy restoration processing is performed on privacy-blocked image information in the first video frame. The manager can conveniently preview the first video frame to check the illegal behavior of the first target object, and the public safety maintenance is carried out.
S215: privacy restoration processing is not required to be performed on privacy-masked image information.
Specifically, if the area containing the first target object does not have the preset behavior track, it is indicated that the behavior track of the first target object belongs to a normal behavior, and the preset area in the detection frame containing the first target object still exists in a privacy-shielded state, so that the privacy of the first target object is protected from being leaked.
Referring to fig. 3 and 4, fig. 3 is a schematic flowchart illustrating an image processing method according to another embodiment of the present invention; fig. 4 is a layout diagram of the image pickup apparatus. In an alternative embodiment, at least two image capturing devices are deployed according to fig. 4, i.e. at least two different image capturing devices monitor coverage areas that partially overlap. Specifically, the image capturing apparatuses include IPC1, IPC2, and IPC3, and when the first target object moves from the monitoring coverage of the first image capturing apparatus (IPC1) to the monitoring coverage of the second image capturing apparatus (IPC2), the specific implementation steps are as follows.
S31: and acquiring a second video frame through second image acquisition equipment, and sending the second video frame to the first image acquisition equipment.
Specifically, the second image capturing device performs target detection on the acquired second video frame, and determines whether a detection frame including a second target object is detected in the second video frame. And when the detection frame containing the second target object is detected in the second video frame, the second image acquisition equipment sends a signal to the first image acquisition equipment. For example, an overlapping region S appears in the monitoring coverage areas of the first image capturing device and the second image capturing device, when the first target object enters the region S, the second image capturing device acquires the second video frame and performs target detection on the second video frame, and when a detection frame including the second target object is detected in the second video frame, the second image capturing device sends a signal to the first image capturing device, which indicates that the first target object about to leave the monitoring coverage area of the first image capturing device may enter the monitoring coverage area of the second image capturing device.
S32: the first image acquisition device synchronizes the identity information of the first target object to the second target object.
Specifically, the first image acquisition device receives a signal sent by the second image acquisition device, sends the identity information of the first target object to the second image acquisition device, and takes the identity information of the first target object as the identity information of the second target object.
S33: and performing feature extraction on the second target object to obtain a second feature map.
Specifically, feature extraction is performed on the detection frame including the second target object, so as to obtain a second feature map of the second target object. And performing feature extraction on the detection frame containing the second target object through a convolutional neural network to obtain a second feature map. In a specific embodiment, feature extraction may be directly performed on the detection frame including the second target object in the second video frame, or a clearly recognizable video frame may be re-acquired by the second image acquisition device, and target detection is performed on the video frame to obtain a detection frame including the second target object, and feature extraction is performed on the detection frame including the second target object to obtain a second feature map. In this embodiment, the second image capturing device performs feature extraction on the region including the second target object to obtain a second feature map. And associating the second characteristic diagram with the identity information of the second target object, and sending the associated second characteristic diagram and the identity information of the second target object to the first image acquisition equipment. In another optional embodiment, the second image capturing device sends the captured second video frame to the first image capturing device, and the first image capturing device performs feature extraction on the detection frame including the second target object to obtain a second feature map, and associates the second feature map with the identity information of the second target object.
S34: it is determined whether the second target object is the first target object.
Specifically, whether the similarity between the second feature map of the second target object and the first feature map of the first target object exceeds a threshold value is judged, and whether the second target object is the first target object is determined. The first image acquisition equipment acquires a second feature map associated with the identity information of the second target object, searches the target object with the same identity information in the first image acquisition equipment, and judges whether the similarity between the second feature map and the first feature map with the same identity information exceeds a threshold value.
If the similarity between the second feature map of the second target object and the first feature map of the first target object exceeds the threshold, directly jumping to step 35; if the similarity between the second feature map of the second target object and the first feature map of the first target object does not exceed the threshold, the process goes directly to step 36.
S35: the trajectory information of the first target object is associated with the second target object.
Specifically, if the similarity between the second feature map of the second target object and the first feature map of the first target object exceeds a threshold, it indicates that the second target object is the first target object, the first target object moves from the monitoring coverage of the first image acquisition device to the monitoring coverage of the second image acquisition device, the trajectory information of the second target object in the monitoring coverage of the second image acquisition device is sent to the first image acquisition device, the trajectory information of the second target object in the monitoring coverage of the second image acquisition device is correlated with the trajectory information of the first target object in the monitoring coverage of the first image acquisition device, the trajectory information of the first target object in the monitoring coverage of the first image acquisition device is sent to the second image acquisition device by the first image acquisition device, and the trajectory information of the first target object in the monitoring coverage of the first image acquisition device and the trajectory information of the second target object in the monitoring coverage of the second image acquisition device are correlated with each other The track information in the monitoring coverage range of the second image acquisition equipment is correlated, so that the whole motion track of the first target object in the whole monitoring area can be conveniently checked.
S36: new identity information is generated for the second target object.
Specifically, if the similarity between the second feature map of the second target object and the first feature map of the first target object does not exceed the threshold, it indicates that the second target object is not the first target object, and the identity information of the first target object synchronized with the second target object before is incorrect, and new identity information needs to be generated for the second target object again.
S37: and the second image acquisition equipment encrypts data of a preset area of the detection frame containing the second target object in the acquired second video frame and generates corresponding privacy-shielding image information.
The specific implementation is the same as steps S210 and S211, and is not described herein again.
The viewing mode of the second video frame acquired by the second image acquisition device is the same as the viewing mode of the first video frame, and details are not repeated here.
The image processing method provided by the embodiment acquires a first video frame, and the first video frame is acquired by a first image acquisition device; performing target detection on the first video frame, and determining a first target object contained in the first video frame; carrying out privacy occlusion processing on an area containing a first target object in a first video frame to obtain privacy occlusion image information; and responding to the area containing the first target object to have a preset behavior track, and performing privacy restoration processing on the privacy sheltered image information. The method and the device have the advantages that the acquired first video frame is detected to obtain the first target object, and privacy processing is carried out on the first video frame and areas containing the first target object in other acquired video frames, so that the privacy of the first target object is guaranteed not to be revealed; when the area of the first target object has the preset behavior track, privacy restoration processing can be performed on privacy-shielded image information, namely when a behavior violating public safety occurs, important information of the area containing the first target object is restored, and then public safety is guaranteed.
Referring to fig. 5, fig. 5 is a schematic block diagram of an embodiment of a terminal provided in the present invention. The terminal 70 in this embodiment includes: the processor 71, the memory 72, and a computer program stored in the memory 72 and capable of running on the processor 71 are not repeated herein to avoid repetition in the above-mentioned image processing method when the computer program is executed by the processor 71.
Referring to fig. 6, fig. 6 is a schematic block diagram of an embodiment of a computer-readable storage medium provided by the present invention.
In an embodiment of the present application, a computer-readable storage medium 90 is further provided, where the computer-readable storage medium 90 stores a computer program 901, and the computer program 901 includes program instructions, and a processor executes the program instructions to implement the image processing method provided in the embodiment of the present application.
The computer-readable storage medium 90 may be an internal storage unit of the computer device of the foregoing embodiment, such as a hard disk or a memory of the computer device. The computer-readable storage medium 90 may also be an external storage device of the computer device, such as a plug-in hard disk provided on the computer device, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (11)
1. An image processing method, characterized in that the image processing method comprises:
acquiring a first video frame, wherein the first video frame is acquired by first image acquisition equipment;
performing target detection on the first video frame, and determining a first target object contained in the first video frame;
carrying out privacy occlusion processing on an area containing the first target object in the first video frame to obtain privacy occlusion image information;
and responding to the area containing the first target object to have a preset behavior track, and then carrying out privacy restoration processing on the privacy sheltered image information.
2. The image processing method according to claim 1,
the privacy-blocking processing is performed on the area, which includes the first target object, in the first video frame to obtain privacy-blocking image information, and the method includes the following steps:
generating corresponding identity information according to the first target object;
performing feature extraction on the first target object to obtain a first feature map;
associating the identity information of the first target object with the first feature map.
3. The image processing method according to claim 2, further comprising:
acquiring a second video frame, wherein the second video frame is acquired by second image acquisition equipment;
performing target detection on the second video frame, and determining a second target object contained in the second video frame;
in response to the second target object being the first target object; the identity information of the first target object is sent to the second image acquisition device.
4. The image processing method according to claim 3, characterized by further comprising:
performing feature extraction on the second target object to obtain a second feature map;
in response to the second feature map being the first feature map, associating trajectory information of the second target object with the first target object.
5. The image processing method according to claim 1,
the privacy-blocking processing is performed on the area containing the first target object in the first video frame to obtain privacy-blocking image information, and the privacy-blocking processing includes:
acquiring data of a region containing the first target object in the first video frame;
encrypting the data of the area containing the first target object through a CP-ABE algorithm to obtain privacy blocking data;
and merging the privacy occlusion data with the data of other areas of the first video frame, which do not contain the first target object, so as to obtain the privacy occlusion image information.
6. The image processing method according to claim 1,
the performing target detection on the first video frame and determining a first target object included in the first video frame includes:
performing target detection on the first video frame to obtain a candidate target object contained in the first video frame;
judging whether the candidate target object belongs to a preset target object or not;
and if the candidate target object belongs to the preset target object, determining that the candidate target object is the first target object.
7. The image processing method according to claim 6,
the obtaining a first video frame, previously comprising:
and pre-storing a preset behavior track, and setting an access structure according to the preset behavior track.
8. The image processing method according to claim 7,
and in response to the preset behavior track existing in the area containing the first target object, performing privacy restoration processing on the privacy-blocked image information, including:
if the area containing the first target object has the preset behavior track, verifying the preset behavior track through the access structure;
and responding to successful verification, and performing privacy restoration processing on the privacy sheltered image information.
9. The image processing method of claim 7, wherein the predetermined behavior trace comprises one of a theft action, a fighting action, and a stagnation danger area action.
10. A terminal, characterized in that the terminal comprises a memory, a processor and a computer program stored in the memory and running on the processor, the processor being configured to execute sequence data to implement the steps in the image processing method according to any of claims 1-9.
11. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the image processing method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111362329.9A CN114025173A (en) | 2021-11-17 | 2021-11-17 | Image processing method, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111362329.9A CN114025173A (en) | 2021-11-17 | 2021-11-17 | Image processing method, terminal and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114025173A true CN114025173A (en) | 2022-02-08 |
Family
ID=80064892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111362329.9A Pending CN114025173A (en) | 2021-11-17 | 2021-11-17 | Image processing method, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114025173A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419720A (en) * | 2022-03-30 | 2022-04-29 | 浙江大华技术股份有限公司 | Image occlusion method and system and computer readable storage medium |
| CN115379260A (en) * | 2022-08-19 | 2022-11-22 | 杭州华橙软件技术有限公司 | Video privacy processing method and device, storage medium and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110990849A (en) * | 2019-11-20 | 2020-04-10 | 维沃移动通信有限公司 | Encryption and decryption method for private data and terminal |
| CN111277728A (en) * | 2020-02-13 | 2020-06-12 | 浙江大华技术股份有限公司 | Video detection method and device, computer-readable storage medium and electronic device |
| CN111586361A (en) * | 2020-05-19 | 2020-08-25 | 浙江大华技术股份有限公司 | Image processing method and related device |
| CN111866600A (en) * | 2020-06-10 | 2020-10-30 | 北京沃东天骏信息技术有限公司 | Method, device and system for protecting privacy |
| CN112488024A (en) * | 2020-12-08 | 2021-03-12 | 平安国际智慧城市科技股份有限公司 | High-altitude parabolic tracing method and device, computer equipment and storage medium |
-
2021
- 2021-11-17 CN CN202111362329.9A patent/CN114025173A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110990849A (en) * | 2019-11-20 | 2020-04-10 | 维沃移动通信有限公司 | Encryption and decryption method for private data and terminal |
| CN111277728A (en) * | 2020-02-13 | 2020-06-12 | 浙江大华技术股份有限公司 | Video detection method and device, computer-readable storage medium and electronic device |
| CN111586361A (en) * | 2020-05-19 | 2020-08-25 | 浙江大华技术股份有限公司 | Image processing method and related device |
| CN111866600A (en) * | 2020-06-10 | 2020-10-30 | 北京沃东天骏信息技术有限公司 | Method, device and system for protecting privacy |
| CN112488024A (en) * | 2020-12-08 | 2021-03-12 | 平安国际智慧城市科技股份有限公司 | High-altitude parabolic tracing method and device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419720A (en) * | 2022-03-30 | 2022-04-29 | 浙江大华技术股份有限公司 | Image occlusion method and system and computer readable storage medium |
| CN114419720B (en) * | 2022-03-30 | 2022-10-18 | 浙江大华技术股份有限公司 | Image occlusion method and system and computer readable storage medium |
| WO2023185646A1 (en) * | 2022-03-30 | 2023-10-05 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image processing |
| CN115379260A (en) * | 2022-08-19 | 2022-11-22 | 杭州华橙软件技术有限公司 | Video privacy processing method and device, storage medium and electronic device |
| CN115379260B (en) * | 2022-08-19 | 2023-11-03 | 杭州华橙软件技术有限公司 | Video privacy processing method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111586361B (en) | Image processing method and related device | |
| US8752197B2 (en) | Application independent system, method, and architecture for privacy protection, enhancement, control, and accountability in imaging service systems | |
| US20070201694A1 (en) | Privacy management in imaging system | |
| CN114025173A (en) | Image processing method, terminal and computer readable storage medium | |
| US20170076572A1 (en) | Privacy masking video content of alarm exceptions and mask verification | |
| CN109886204A (en) | A kind of Multidimensional Awareness system based on the application of big data police service | |
| KR102012672B1 (en) | Anti-crime system and method using face recognition based people feature recognition | |
| EP2283472A1 (en) | A system and method for electronic surveillance | |
| CN109598426A (en) | A kind of railway police intelligent security system | |
| CN111866600B (en) | Method, device and system for protecting privacy | |
| KR101951605B1 (en) | Cctv image security system to prevent image leakage | |
| US10419728B2 (en) | Monitoring system having personal information protection function and method thereof | |
| CN108230669B (en) | Road vehicle violation detection method and system based on big data and cloud analysis | |
| Davies et al. | A progress review of intelligent CCTV surveillance systems | |
| CN112464755A (en) | Monitoring method and device, electronic equipment and storage medium | |
| CN111526325A (en) | Privacy masking method and recording medium using morphological preserving encryption technique | |
| CN112818758A (en) | Monitoring method, system and device for electric power construction site and storage medium | |
| CN112016526B (en) | Behavior monitoring and analyzing system, method, device and equipment for site activity object | |
| CN109741224A (en) | Supervision method and Related product | |
| CN111432286B (en) | Video processing method, device and system | |
| KR101929212B1 (en) | Apparatus and method for masking moving object | |
| JP2012133411A (en) | Face collation system, face collation device and face collation method | |
| CN115359539A (en) | Office place information security detection method, device, equipment and storage medium | |
| CN115100572A (en) | System and method for analyzing abnormal behaviors of campus | |
| CN114120597A (en) | Public place epidemic situation normalized prevention and control system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |