CN117455751A - Road section image processing system and method - Google Patents
Road section image processing system and method Download PDFInfo
- Publication number
- CN117455751A CN117455751A CN202311776015.2A CN202311776015A CN117455751A CN 117455751 A CN117455751 A CN 117455751A CN 202311776015 A CN202311776015 A CN 202311776015A CN 117455751 A CN117455751 A CN 117455751A
- Authority
- CN
- China
- Prior art keywords
- image
- road section
- sensitive
- desensitized
- original
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims description 45
- 238000012360 testing method Methods 0.000 claims abstract description 71
- 238000013507 mapping Methods 0.000 claims abstract description 58
- 238000005516 engineering process Methods 0.000 claims abstract description 22
- 238000003672 processing method Methods 0.000 claims abstract description 21
- 238000000586 desensitisation Methods 0.000 claims description 26
- 230000033001 locomotion Effects 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 13
- 230000007547 defect Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 44
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 230000002457 bidirectional effect Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000011842 forensic investigation Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/44—Secrecy systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a road section image processing system and a road section image processing method. By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
Description
Technical Field
The application relates to a vehicle-road cooperation technology, in particular to a road section image processing method and a road section image processing system.
Background
With the rapid increase of the amount of urban vehicles kept, urban traffic problems become more and more serious. In order to relieve traffic pressure and improve traffic safety level, more and more operation platforms begin to use vehicle-road cooperation technology to sense traffic situation of each road section for related functional platforms.
In the related art, with the rapid development of computer image processing technology, each operation platform often senses the traffic situation of a traffic road section through the technology of image acquisition and identification on the road section, and sends the corresponding sensing result to the functional platform.
However, the above manner may cause private information of pedestrians or vehicles to be revealed to the operation platform, and thus there may be a problem of potential safety hazard of data.
Disclosure of Invention
The embodiment of the application provides a processing method and a processing system for road section images, so that the problem that potential data safety hazards possibly exist due to the fact that an operation platform grasps private information of pedestrians and vehicles in the related technology is solved.
According to one aspect of the embodiments of the present application, a system for processing a road segment image is provided, where the system includes: drive test equipment, operation platform and function platform, wherein:
the road test equipment is used for transmitting the desensitized road section image obtained after the desensitization processing of the original road section image to the operation platform after the original road section image of the target road section is acquired; transmitting sensitive data to a role platform, wherein the sensitive data comprises a sensitive area image contained in the original road section image and a first mapping relation for the role platform to acquire the original road section image, and the first mapping relation comprises an image identifier corresponding to the desensitized road section image and a mapping relation between original distribution positions of the sensitive area image in the desensitized road section image;
The operation platform is used for receiving and storing the desensitized road section image; after receiving the image identification sent by the job platform, sending a desensitized road section image associated with the image identification to the job platform;
the job platform is used for sending an image identifier to the operation platform; and after the desensitization road section image and the sensitive data are received, replacing a fuzzy area in the desensitization road section image with the sensitive area image based on the original distribution position included in the first mapping relation, and obtaining an original road section image associated with the sensitive area image.
According to one aspect of the embodiment of the application, a method for processing a road section image is provided, and is applied to a road test device, and the method comprises the following steps:
after an original road section image of a target road section is acquired, identifying and obtaining a sensitive area image containing a sensitive object in the original road section image;
carrying out fuzzy processing on the sensitive area image in the original road section image to obtain a desensitized road section image; recording the original distribution position of the sensitive area image in the desensitized road section image;
transmitting the desensitized road section image to an operation platform; and transmitting sensitive data to a job function platform, wherein the sensitive data comprises the sensitive area image and a first mapping relation for the job function platform to acquire the original road section image, and the first mapping relation is a mapping relation between an image identifier corresponding to the desensitized road section image and the original distribution position.
According to one aspect of the embodiments of the present application, a method for processing a road section image is provided, which is applied to a functional platform and includes:
receiving sensitive data sent by a road test device, wherein the sensitive data comprises a sensitive area image and a first mapping relation comprising image identifications and original distribution positions, the image identifications are used for representing desensitized road section images associated with the sensitive area image, and the original distribution positions are used for representing positions of the sensitive area image originally in the desensitized road section images;
the image identification is sent to an operation platform, and a desensitization road section image which is returned by the operation platform and is associated with the image identification is received;
and replacing a fuzzy area in the desensitized road section image with the sensitive area image based on the original distribution position to obtain an original road section image associated with the sensitive area image.
According to still another aspect of the embodiments of the present application, a processing apparatus for a road segment image is provided, which is applied to a road test device, and the apparatus includes:
the acquisition module is used for acquiring an original road section image of a target road section and then identifying and obtaining a sensitive area image containing a sensitive object in the original road section image;
The processing module is used for carrying out fuzzy processing on the sensitive area image in the original road section image to obtain a desensitized road section image; recording the original distribution position of the sensitive area image in the desensitized road section image;
the transmission module is used for transmitting the desensitized road section image to an operation platform; and transmitting sensitive data to a job function platform, wherein the sensitive data comprises the sensitive area image and a first mapping relation for the job function platform to acquire the original road section image, and the first mapping relation is a mapping relation between an image identifier corresponding to the desensitized road section image and the original distribution position.
According to still another aspect of the embodiments of the present application, there is provided an electronic device including:
a memory for storing executable instructions; and
and the processor is used for executing the executable instructions with the memory so as to finish the operation of any road section image processing method.
According to still another aspect of the embodiments of the present application, there is provided a computer-readable storage medium storing computer-readable instructions that, when executed, perform the operations of any one of the road segment image processing methods described above.
In the application, the drive test equipment is used for transmitting the desensitized road section image after desensitizing the original road section image to the operation platform after acquiring the original road section image of the target road section; transmitting sensitive data to a functional platform, wherein the sensitive data comprises a sensitive area image contained in an original road section image and a first mapping relation for the functional platform to acquire the original road section image; the operation platform is used for receiving and storing the desensitized road section images, and after receiving the image identifications sent by the function platform, sending the desensitized road section images associated with the image identifications to the function platform; and the function platform is used for replacing the fuzzy area in the desensitized road section image with the sensitive area image based on the original distribution position included in the first mapping relation after receiving the desensitized road section image and the sensitive area image, so as to obtain the original road section image associated with the sensitive area image.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
The technical scheme of the present application is described in further detail below through the accompanying drawings and examples.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.
The present application will be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:
fig. 1 is a system architecture diagram of a road section image processing method provided in the present application;
fig. 2 is a schematic diagram of a transmission data of a road test device according to the present application;
fig. 3 is a schematic diagram of a processing method of a road section image applied to a road test device according to the present application;
fig. 4 is an overall flowchart of a processing method of a road section image applied to a road test device according to the present application;
fig. 5 is a schematic diagram of a processing method of a road section image applied to a functional platform according to the present application;
fig. 6 is an overall flowchart of a processing method of a road section image applied to a functional platform according to the present application;
fig. 7 is an overall flowchart of another processing method for a road segment image applied to a functional platform according to the present application;
fig. 8 is an overall flow diagram of a processing method of a road section image provided in the present application;
Fig. 9 is a schematic structural diagram of an electronic device according to the present application;
fig. 10 is a schematic structural diagram of an electronic device according to the present application.
Detailed Description
Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
In addition, the technical solutions of the embodiments of the present application may be combined with each other, but it is necessary to be based on the fact that those skilled in the art can implement the technical solutions, and when the technical solutions are contradictory or cannot be implemented, the combination of the technical solutions should be considered to be absent, and is not within the scope of protection claimed in the present application.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present application are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is correspondingly changed.
A processing method for performing a road segment image according to an exemplary embodiment of the present application is described below with reference to fig. 1 to 8. It should be noted that the following application scenario is only shown for the convenience of understanding the spirit and principles of the present application, and embodiments of the present application are not limited in any way in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
The application also provides a road section image processing method and a road section image processing system.
With the rapid increase of the amount of urban vehicles kept, urban traffic problems become more and more serious. In order to alleviate traffic pressure and improve traffic safety levels, more and more research institutions begin to research vehicle-road cooperative systems. The vehicle-road cooperative system senses traffic situation through wireless communication, sensor detection and other modes, so that the traffic infrastructure and vehicles can be more intelligently cooperated, and the purposes of optimizing system resource allocation, improving traffic safety level and relieving traffic pressure are achieved.
In the related art, the vehicle-road cooperation technology is a technology for realizing acquisition of road environment, motor vehicles and pedestrian information by constructing a road test unit infrastructure, so that functional departments such as traffic and the like can know road section information and road section illegal states more quickly and comprehensively.
It can be appreciated that the perception of traffic situation is a very important link in a vehicle-road collaboration system. With the rapid development of computer image processing technology, more and more operation platforms use image recognition technology to perceive traffic situation. The method has the advantages of low cost, high data accuracy, high real-time performance, small interference to traffic flow and the like.
However, the above manner may cause private information of pedestrians or vehicles to be revealed to the operation platform, and thus there may be a problem of potential safety hazard of data.
Based on the problems in the related art, the present application proposes a flow diagram of a road section image processing system. As shown in fig. 1, the system is composed of a drive test device, an operation platform and a function platform, and includes:
the road test equipment is used for transmitting the desensitized road section image obtained after the desensitization processing of the original road section image to the operation platform after the original road section image of the target road section is acquired; transmitting sensitive data to a functional platform, wherein the sensitive data comprises a sensitive area image contained in an original road section image and a first mapping relation for the functional platform to acquire the original road section image, and the first mapping relation comprises an image identifier corresponding to a desensitized road section image and a mapping relation between the recording of the original distribution position of the sensitive area image in the desensitized road section image;
the operation platform is used for receiving and storing the desensitized road section image; after receiving the image identification sent by the function platform, sending the desensitized road section image associated with the image identification to the function platform;
the function platform is used for sending the image identification to the operation platform; and after receiving the desensitized road section image and the sensitive data, replacing a fuzzy area in the desensitized road section image with a sensitive area image based on the original distribution position included in the first mapping relation, and obtaining an original road section image associated with the sensitive area image.
In one manner, the drive test device may be a device with an image acquisition function that is disposed in each road section of the city. Including for example cameras, street lights, traffic lights, etc.
In one manner, the functional platform in the embodiment of the present application may be: the platform is provided with a functional department management platform for storing and processing sensitive information rights, and the platform can restore original data by a technical means to perform evidence collection analysis under the legal condition.
In one manner, the operation platform in the embodiment of the present application may be: the vehicle-road cooperative operation management platform is mainly used for providing real-time monitoring and risk early warning service for related vehicles and operators by analyzing traffic conditions under a vehicle-road cooperative scene.
In one manner, the number of the original road section images is not specifically limited, and may be, for example, one frame of image. Or for each frame of image in a video. As an example, a frame of the original road segment image corresponds to one or more sensitive area images (i.e., a frame of the original road segment image may contain a plurality of sensitive objects).
In one mode, after the road test device collects the original road section image aiming at the target road section, the embodiment of the application can detect whether the original road section image contains the corresponding sensitive object or not by adopting an MTCNN algorithm and a Yolov5 algorithm based on the face recognition model and the license plate recognition model. And taking the image containing the sensitive object as a sensitive area image.
By way of example, the sensitive object may be a face or a license plate, or the like.
It can be understood that when the road test device finds that the original road section image contains the sensitive object, the position and the size of the road section image can be marked, and the image area containing the sensitive object is cut through the image cutting function, so that the sensitive area image is obtained.
In one mode, the road test device may further store sensitive area images corresponding to each original road section image, and mark information such as a video name, a belonging frame, an image position, a sensitive object type (face and/or license plate), a tracking identifier, and the like corresponding to the original road section image corresponding to each sensitive area image.
Furthermore, the road test device may further perform desensitization processing on the original road section image (i.e. perform blurring processing on the sensitive area image in the original road section image), so as to obtain a desensitized road section image.
In one mode, after the road test device determines that the desensitization processing is performed on one or more original road section images belonging to the same video data, the embodiment of the application can transmit the one or more desensitized road section images belonging to the same video data to an operation platform (or transmit the original video data including the desensitized road section images after the desensitization processing is performed on the whole video).
It will be appreciated that the above approach not only saves traffic over the prior art. The risk of security data leakage caused by transmitting the original road section image containing the sensitive information to the operation platform can also be avoided.
In another manner, the drive test device in the embodiment of the application may further transmit multiple sensitive data belonging to the same video data to the job platform. It will be appreciated that one sensitive data corresponds to one original road segment image.
As an example, the sensitive data includes a sensitive area image corresponding to an original road section image, and a first mapping relationship corresponding to the sensitive area image. It can be appreciated that the first mapping relationship is used for the job platform to obtain the original road segment image. The method at least comprises an image identifier corresponding to the desensitized road section image and an original distribution position.
In one mode, the road test device may adopt an encryption transmission mode in the process of transmitting the sensitive data to the functional platform.
As an example, as shown in fig. 2, the drive test equipment may first obtain upload address information (i.e., including operation platform address information and function platform address information). As an example, the address information includes a communication address, a type of demand data, and the like.
Further, the road test equipment judges whether the data to be transmitted currently is sensitive data or not, and if the data to be transmitted currently is sensitive data, the road test equipment transmits corresponding video stream data to the operation platform based on the video stream channel. If not, adopting a special channel and performing bidirectional authentication with the operation platform, and then transmitting the desensitized road section image to the operation platform and transmitting the sensitive data information to the function platform.
In one mode, when the job platform needs to perform evidence collection investigation on a certain sensitive object later, the job platform can firstly extract sensitive data of the sensitive object, and extract a desensitization road section image associated with the image identifier from the operation platform according to the image identifier contained in the sensitive data.
Further, after the functional platform acquires the desensitized road section image, a coordinate point range included in the original distribution position corresponding to the desensitized road section image can be acquired, when the coordinate point range is a fuzzy area in the subsequent detection of the desensitized road section image, the coordinate point range can be determined to be matched with the desensitized road section image, and further the fuzzy area in the desensitized road section image can be replaced by a sensitive area image, so that the original road section image is obtained.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the drive test equipment is used for identifying and obtaining a sensitive area image containing a sensitive object in the original road section image after the original road section image is acquired;
and the drive test equipment is used for carrying out fuzzy processing on the sensitive area image in the original road section image to obtain a desensitized road section image.
Optionally, in another embodiment of the system according to the present application, the method further includes:
The drive test equipment is specifically used for identifying a sensitive area image containing a face image in an original road section image by utilizing a face recognition model; and/or the number of the groups of groups,
and identifying a sensitive area image containing the license plate image in the original road section image by using the license plate identification model.
In one mode, after the road test device collects the original road section image aiming at the target road section, the embodiment of the application can detect whether the original road section image contains the corresponding sensitive object or not by adopting an MTCNN algorithm and a Yolov5 algorithm based on the face recognition model and the license plate recognition model. And taking the image containing the sensitive object as a sensitive area image.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the drive test equipment is used for transmitting a plurality of desensitized road section images belonging to the same video data to the operation platform;
the operation platform is used for storing the plurality of desensitized road section images in the same storage file after receiving the plurality of desensitized road section images in the same video data, wherein one storage file corresponds to one video data;
the drive test equipment is used for transmitting a plurality of sensitive data belonging to the same video data to the function platform;
And the function platform is used for storing the plurality of desensitized road section images in the same storage file after receiving the plurality of desensitized road section images in the same video data.
In one manner, if the drive test device uses a certain video as an object to perform data transmission, after receiving corresponding data, the operation platform and the function platform also need to store the data belonging to the same video into the same storage file.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the road test equipment is used for establishing a communication data channel with the operation platform, determining that the road test equipment passes the bidirectional authentication with the operation platform by utilizing a preset authentication rule, and transmitting the sensitive data to the function platform.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the drive test equipment is used for acquiring the sensitive category corresponding to each sensitive data;
each sensitive data is transmitted to a functional platform matched with the corresponding sensitive category.
In one mode, the road test device can transmit the sensitive data to different functional platforms based on the sensitive categories corresponding to the sensitive data in the process of transmitting the sensitive data to the functional platforms.
As an example, the sensitivity category may correspond to a number and category of sensitive objects, such as a number of faces or a number of vehicles. As another example, the sensitivity category may also correspond to a sensitivity level, such as high-level sensitive data being transmitted into the job platform a, low-level sensitive data being transmitted into the job platform B, and so on.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the function platform is used for obtaining a coordinate point range included in the original distribution position;
and if the coordinate point range is detected to be positioned in the fuzzy area in the desensitization road section image, replacing the fuzzy area in the desensitization road section image with the sensitive area image.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the function platform is used for determining the sensitive object contained in the sensitive area image and storing the second mapping relation between the sensitive data and the sensitive object into a storage node of the function platform;
when a evidence obtaining instruction aiming at a sensitive object is detected, the image identification is sent to the operation platform, and a desensitization road section image returned by the operation platform is received.
Optionally, in another embodiment of the system according to the present application, the method further includes:
And the function platform is used for carrying out association combination on the sensitive area images corresponding to the same sensitive object after the sensitive objects contained in the sensitive area images are determined.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the function platform is used for acquiring a plurality of target sensitive area images belonging to the same video data, wherein each target sensitive area image comprises at least one sensitive object;
sequentially adding a plurality of target sensitive area images into blank image frames according to time sequence to obtain restored video data, wherein one blank image corresponds to one target sensitive area image;
and establishing a second mapping relation between the restored video data and the sensitive object, and storing the second mapping relation into a storage node.
Optionally, in another embodiment of the system according to the present application, the method further includes:
the function platform is used for sequentially adding the multiple target sensitive area images into the blank image frames according to the time sequence to obtain initial restored video data;
identifying and labeling the same sensitive object in the initial restored video data by utilizing a target identification model and a motion tracking technology, wherein the target identification model comprises a face recognition model and/or a license plate identification model;
Taking the initial restored video data marked with the same sensitive object as restored video data;
and taking the optimal sensitive area image as a retrieval index of the restored video data, wherein the optimal sensitive area image is the sensitive area image with the highest picture characteristic value in the restored video data.
In one mode, after the functional platform receives the sensitive data corresponding to each original road section image sent by the road test device, the functional platform can perform similar combination and feature extraction on the sensitive data belonging to the same sensitive object for the purposes of subsequent data evidence obtaining and restoring and improving retrieval efficiency.
As an example, the job platform may merge the sensitive data of the same user under the same video data and/or merge the sensitive data of the same license plate under the same directory.
In one mode, the embodiment of the application can expand the association range by utilizing a motion tracking technology and package and store according to the frame sequence of the video stream.
By way of example, when the sensitive object of the current image is recognized as a human face according to the image information, the embodiment of the application can calculate the characteristic value of the sensitive information picture by using an MTCNN algorithm, correlate pictures with similar characteristics, add combined motion tracking identification information on the basis, expand the association range, and pack and store according to the frame sequence of the video stream.
As another example, when the sensitive object of the current image is identified as a license plate according to the image information, the embodiment of the application can also identify and extract license plate information by adopting an LPRNet algorithm, add combined operation tracking identification information, associate license plates with incomplete information caused by angles or shielding, merge and package the associated license plate pictures, and store license plate numbers corresponding to the package in a license plate number library for retrieval.
Based on the problems in the related art, the application provides a flow diagram of a processing method of a road section image. As shown in fig. 3, the method is applied to a drive test device, and includes:
s201, after the original road section image of the target road section is acquired, identifying and obtaining a sensitive area image containing a sensitive object in the original road section image.
In one manner, the drive test device may be a device with an image acquisition function that is disposed in each road section of the city. Including for example cameras, street lights, traffic lights, etc.
In one manner, the number of the original road section images is not specifically limited, and may be, for example, one frame of image. Or for each frame of image in a video.
In one manner, the sensitive object in the embodiments of the present application may be a face or a license plate.
In one mode, after the road test device collects the original road section image aiming at the target road section, the embodiment of the application can detect whether the original road section image contains the corresponding sensitive object or not by adopting an MTCNN algorithm and a Yolov5 algorithm based on the face recognition model and the license plate recognition model. And taking the image containing the sensitive object as a sensitive area image.
As an example, the MTCNN algorithm is a face detection network algorithm, which is fully called as Multi-task Cascaded Convolutional Networks, is a face detection and face alignment method based on deep learning, can complete the tasks of face detection and face alignment at the same time, and has better performance and faster detection speed compared with the traditional algorithm. Meanwhile, the method has higher recognition rate for the side faces of the people, and can be better applied to multi-angle face recognition in traffic environment.
As another example, the face recognition model can be an Arcface model, which has the characteristics of high performance, easy programming realization, low complexity and high training efficiency, can effectively support the face matching scene requirement, and realizes the face matching work by inputting face image information and searching an image library
As yet another example, the license plate recognition model may be an LPRNet model, which is a real-time, high quality license plate recognition network architecture that supports variable length license plates. The structure does not need to carry out license plate character segmentation in advance, and can be used for end-to-end training. Meanwhile, the method has good enough robustness and is not influenced by various camera parameters, visual angles, illumination and the like.
S202, blurring processing is carried out on sensitive area images in the original road section images, and desensitized road section images are obtained; and recording the original distribution position of the sensitive area image in the desensitized road section image.
As shown in fig. 4, in the embodiment of the present application, after detecting that an original road section image includes a sensitive object such as a face and/or a license plate by using means such as a face recognition model or a license plate recognition model, the road section image may be marked in position and size, and an image area including the face and/or the license plate is cut by using an image cutting function, so as to obtain a sensitive area image.
In one mode, the road test device may further store the sensitive area image corresponding to each original road segment image, and mark the information such as the image identifier corresponding to the original road segment image corresponding to each sensitive area image (for example, in which frame of which video), the video name, the frame to which the image belongs, the image position, the sensitive object type (face and/or license plate), the tracking identifier, and the like.
Furthermore, the road test device may further perform desensitization processing on the original road section image (i.e. perform blurring processing on the sensitive area image in the original road section image), so as to obtain a desensitized road section image.
S203, transmitting the desensitized road section image to an operation platform; and transmitting the sensitive data to the functional platform, wherein the sensitive data comprises a sensitive area image and a first mapping relation for the functional platform to acquire an original road section image, and the first mapping relation is a mapping relation between an image identifier corresponding to the desensitized road section image and an original distribution position.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage.
On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
Optionally, in another embodiment of the method according to the present application, identifying and obtaining a sensitive area image including a sensitive object in an original road section image includes:
identifying a sensitive area image containing a face image in an original road section image by using a face identification model; and/or the number of the groups of groups,
and identifying a sensitive area image containing the license plate image in the original road section image by using the license plate identification model.
Optionally, in another embodiment based on the above method of the present application, the desensitized road section image is transmitted to an operation platform; and transmitting the sensitive data to a job platform, comprising:
transmitting a plurality of desensitized road section images belonging to the same video data to an operation platform; and transmitting the plurality of sensitive data belonging to the same video data to the job function platform.
Optionally, in another embodiment based on the above method of the present application, transmitting the sensitive data to the job platform includes:
and establishing a communication data channel with the operation platform, determining that the bidirectional authentication with the operation platform is passed by utilizing a preset authentication rule, and transmitting the sensitive data to the function platform.
Based on the problems in the related art, the application provides a flow diagram of a processing method of a road section image. As shown in fig. 5, the method is applied to a functional platform, and includes:
S301, receiving sensitive data sent by a road test device, wherein the sensitive data comprises a sensitive area image and a first mapping relation comprising image identifications and original distribution positions, the image identifications are used for representing desensitized road section images associated with the sensitive area image, and the original distribution positions are used for representing positions of the sensitive area image in the desensitized road section images.
In one mode, after the function platform receives the sensitive data corresponding to each original road section image sent by the road test equipment, the function platform can perform similar combination and feature extraction on the sensitive data belonging to the same sensitive object for the purposes of subsequent data evidence obtaining and restoring and improving the retrieval efficiency.
As an example, the job platform may merge the sensitive data of the same user under the same video data and/or merge the sensitive data of the same license plate under the same directory.
As shown in fig. 6, the job platform may perform the following steps:
and a, after receiving each sensitive data packet, decompressing the content of the data packet.
And b, establishing a plurality of blank image frames with equal resolution, and restoring each sensitive area image under the same video data into the corresponding blank image frame by frame according to time sequence to obtain the initial restored video data.
And c, marking the same associated sensitive object by utilizing a Camshift algorithm through a motion tracking technology, so as to obtain restored video data.
Wherein the other target sensitive area image and the target sensitive area image contain the same sensitive object. That is, when a part of sensitive objects in an image frame cannot be identified by a face detection technology or the like due to motion or shielding or the like, the embodiment of the application can enlarge the association range by utilizing a motion tracking technology and package and store according to the frame sequence of the video stream.
By way of example, when the sensitive object of the current image is recognized as a human face according to the image information, the embodiment of the application can calculate the characteristic value of the sensitive information picture by using an MTCNN algorithm, correlate pictures with similar characteristics, add combined motion tracking identification information on the basis, expand the association range, and pack and store according to the frame sequence of the video stream.
As another example, when the sensitive object of the current image is identified as a license plate according to the image information, the embodiment of the application can also identify and extract license plate information by adopting an LPRNet algorithm, add combined operation tracking identification information, associate license plates with incomplete information caused by angles or shielding, merge and package the associated license plate pictures, and store license plate numbers corresponding to the package in a license plate number library for retrieval.
And d, taking the optimal sensitive area image as a retrieval index of the restored video data.
The optimal sensitive area image is the sensitive area image with the highest picture characteristic value in the restored video data.
And e, establishing a second mapping relation between the restored video data and the sensitive object, and storing the second mapping relation into a storage node.
In one mode, in the embodiment of the present application, an image picture with the best frame feature value may be selected for each second mapping relationship as a retrieval identifier of the mapping relationship.
S302, the image identification is sent to the operation platform, and the desensitization road section image which is returned by the operation platform and is associated with the image identification is received.
S303, based on the original distribution position, the fuzzy area in the desensitized road section image is replaced by the sensitive area image, and the original road section image associated with the sensitive area image is obtained.
In one approach, when a job platform subsequently needs to conduct a forensic investigation on a sensitive object, it first needs to provide object information of the sensitive object to be retrieved.
By way of example, taking fig. 7 as an example, the functional platform may perform the following steps:
and a step a, providing portrait pictures or license plate information to be retrieved. If the image is the portrait picture, the step b is skipped, otherwise the step d is skipped.
And b, comparing the optimal picture in the privacy feature library by using an arcface algorithm, and identifying a sensitive area image conforming to the portrait.
Step c, if the matched portrait data is found, the step e is skipped, otherwise, the process is ended.
Step d, using the license plate information to correlate with the license plate information base, if the sensitive area image which accords with the license plate is found, jumping to the step e, otherwise ending the flow.
And e, acquiring a first mapping relation associated with the sensitive area image according to the retrieved sensitive area image, and further acquiring an image identifier included in the first mapping relation.
And f, submitting an acquisition application of the desensitized road section image to an operation platform according to the image identification.
And g, after the desensitization road section images are obtained, replacing the fuzzy area in each desensitization road section image with a sensitive area image frame by frame according to the original position distribution included in the first mapping relation, and obtaining the original road section images.
And i, after the fact that all the desensitized road section images are replaced is determined, video restoration is carried out on all the original road section images.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
Optionally, in another embodiment based on the above method of the present application, after receiving the sensitive data sent by the road test device, the method further includes:
determining a sensitive object contained in the sensitive area image, and storing a second mapping relation between sensitive data and the sensitive object into a storage node of the sensitive area image;
when a evidence obtaining instruction aiming at a sensitive object is detected, the image identification is sent to the operation platform, and a desensitization road section image returned by the operation platform is received.
Optionally, in another embodiment based on the above method of the present application, receiving the desensitized road section image returned by the operation platform includes:
if video data sent by the operation platform are received, obtaining video frame identifiers included in the sensitive data;
and taking the target video frame matched with the video frame identification in the video data as a desensitization road section image.
In another manner, as shown in fig. 8, an overall flow chart of a processing method of a road section image according to an embodiment of the present application includes:
step 1, after the road test equipment acquires an original road section image of a target road section, identifying and obtaining a sensitive area image containing a sensitive object in the original road section image.
Step 2, the road test equipment carries out fuzzy processing on sensitive area images in the original road section images to obtain desensitized road section images; and recording the original distribution position of the sensitive area image in the desensitized road section image. And then, simultaneously or not sequentially entering the step 3a and the step 3b.
And 3a, transmitting the desensitized road section image to an operation platform.
And 3b, acquiring the sensitive category corresponding to each sensitive data, and transmitting each sensitive data to a function platform matched with the corresponding sensitive category.
The sensitive data comprises sensitive area images and a first mapping relation for enabling the functional platform to acquire original road section images, wherein the first mapping relation comprises image identifications corresponding to desensitized road section images and original distribution positions.
And 4, receiving the sensitive data sent by the road test equipment by the function platform.
And 5, the function platform sends the image identification to the operation platform and receives the desensitized road section image which is returned by the operation platform and is associated with the image identification.
And 6, the function platform acquires a coordinate point range included in the original distribution position.
And 7, when the functional platform detects that the coordinate point range is positioned in the fuzzy area in the desensitized road section image, replacing the fuzzy area in the desensitized road section image with the sensitive area image to obtain an original road section image associated with the sensitive area image.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
Alternatively, in another embodiment of the present application, as shown in fig. 9, the present application further provides a processing device for a road section image. Applied to a drive test device, comprising:
the acquisition module 401 is configured to identify and obtain a sensitive area image containing a sensitive object in an original road section image of a target road section after the original road section image of the target road section is acquired;
the processing module 402 is configured to perform blurring processing on the sensitive area image in the original road section image, so as to obtain a desensitized road section image; recording the original distribution position of the sensitive area image in the desensitized road section image;
A transmission module 403, configured to transmit the desensitized road section image to an operation platform; and transmitting sensitive data to a job function platform, wherein the sensitive data comprises the sensitive area image and a first mapping relation for the job function platform to acquire the original road section image, and the first mapping relation is a mapping relation between an image identifier corresponding to the desensitized road section image and the original distribution position.
By applying the technical scheme, after the road test equipment collects the image of the traffic road section, the road test equipment can directly separate the sensitive information covered in the collected image from the original image, and then the desensitized image and the sensitive information are respectively transmitted to different platforms for storage. On the one hand, the problem that a large amount of transmission resources are occupied due to the fact that the complete original road section image is transmitted to the operation platform in the related technology is avoided. On the other hand, when the function platform is required for later evidence collection, the original road section image is spliced through the original distribution positions recorded in the mapping relation, so that the defect that the privacy data of the user are exposed can be avoided.
In another embodiment of the present application, the processing module 402 is configured to:
Identifying a sensitive area image containing a face image in the original road section image by using a face identification model; and/or the number of the groups of groups,
and identifying a sensitive area image containing the license plate image in the original road section image by using a license plate identification model.
In another embodiment of the present application, the processing module 402 is configured to:
transmitting a plurality of desensitized road segment images belonging to the same video data to the operation platform; and transmitting a plurality of the sensitive data belonging to the same video data to the job platform.
In another embodiment of the present application, the processing module 402 is configured to:
and establishing a communication data channel with the operation platform, and transmitting the sensitive data to the job platform after the bidirectional authentication with the operation platform is determined to pass by utilizing a preset authentication rule.
The embodiment of the application also provides an electronic device for executing the processing method of the road section image. Referring to fig. 10, a schematic diagram of an electronic device according to some embodiments of the present application is shown. As shown in fig. 10, the electronic apparatus 3 includes: a processor 300, a memory 301, a bus 302 and a communication interface 303, the processor 300, the communication interface 303 and the memory 301 being connected by the bus 302; the memory 301 stores a computer program that can be executed by the processor 300, and the processor 300 executes the processing method for the road segment image provided in any of the foregoing embodiments of the present application when executing the computer program.
The memory 301 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the device network element and at least one other network element is achieved through at least one communication interface 303 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 302 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. The memory 301 is configured to store a program, and the processor 300 executes the program after receiving an execution instruction, and the video transmission method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 300 or implemented by the processor 300.
The processor 300 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 300 or by instructions in the form of software. The processor 300 may be a general-purpose processor, including a processor (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301, and in combination with its hardware, performs the steps of the above method.
The electronic device provided by the embodiment of the application and the road section image processing method provided by the embodiment of the application are the same in the same invention conception, and have the same beneficial effects as the method adopted, operated or realized by the electronic device.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (17)
1. A system for processing an image of a road segment, the system comprising: drive test equipment, operation platform and function platform, wherein:
the road test equipment is used for transmitting the desensitized road section image obtained after the desensitization processing of the original road section image to the operation platform after the original road section image of the target road section is acquired; transmitting sensitive data to a role platform, wherein the sensitive data comprises a sensitive area image contained in the original road section image and a first mapping relation for the role platform to acquire the original road section image, and the first mapping relation comprises an image identifier corresponding to the desensitized road section image and a mapping relation between original distribution positions of the sensitive area image in the desensitized road section image;
The operation platform is used for receiving and storing the desensitized road section image; after receiving the image identification sent by the job platform, sending a desensitized road section image associated with the image identification to the job platform;
the job platform is used for sending an image identifier to the operation platform; and after the desensitization road section image and the sensitive data are received, replacing a fuzzy area in the desensitization road section image with the sensitive area image based on the original distribution position included in the first mapping relation, and obtaining an original road section image associated with the sensitive area image.
2. The system of claim 1, wherein,
the drive test equipment is specifically used for identifying the sensitive area image containing the sensitive object from the original road section image; and carrying out fuzzy processing on the sensitive area image in the original road section image to obtain the desensitized road section image.
3. The system of claim 1 or 2, wherein,
the drive test equipment is specifically used for identifying a sensitive area image containing a face image in the original road section image by using a face recognition model; and/or the number of the groups of groups,
And identifying a sensitive area image containing the license plate image in the original road section image by using a license plate identification model.
4. The system of claim 1, wherein,
the drive test equipment is used for transmitting a plurality of desensitized road section images in the same video data to the operation platform;
the operation platform is used for storing a plurality of desensitized road section images in the same storage file after receiving the plurality of desensitized road section images in the same video data, wherein one storage file corresponds to one video data;
the drive test equipment is used for transmitting a plurality of sensitive data belonging to the same video data to the job platform;
the job platform is used for storing a plurality of desensitized road section images in the same storage file after receiving the plurality of desensitized road section images in the same video data.
5. The system of claim 1, wherein,
the drive test equipment is used for acquiring the sensitive category corresponding to each sensitive data;
each sensitive data is transmitted to a functional platform matched with the corresponding sensitive category.
6. The system of claim 1, wherein,
The job platform is used for obtaining a coordinate point range included in the original distribution position;
and if the coordinate point range is detected to be located in the fuzzy area in the desensitization road section image, replacing the fuzzy area in the desensitization road section image with the sensitive area image.
7. The system of claim 1, wherein,
the job function platform is used for determining a sensitive object contained in the sensitive area image and storing a second mapping relation between the sensitive data and the sensitive object into a storage node of the job function platform;
when a evidence obtaining instruction aiming at the sensitive object is detected, the image identification is sent to the operation platform, and the desensitized road section image returned by the operation platform is received.
8. The system of claim 7, wherein the system comprises a plurality of sensors,
the role platform is used for carrying out association combination on the sensitive area images corresponding to the same sensitive object after the sensitive object contained in the sensitive area images is determined.
9. The system of claim 1, wherein,
the job platform is used for acquiring a plurality of target sensitive area images belonging to the same video data, wherein each target sensitive area image comprises at least one sensitive object;
Sequentially adding the multiple target sensitive area images into blank image frames according to time sequence to obtain restored video data, wherein one blank image corresponds to one target sensitive area image;
and establishing a second mapping relation between the restored video data and the sensitive object, and storing the second mapping relation to the storage node.
10. The system of claim 9, wherein the system comprises a plurality of sensors,
the job platform is used for sequentially adding the multiple target sensitive area images into blank image frames according to time sequence to obtain initial restored video data;
identifying and labeling the same sensitive object in the initial restored video data by utilizing a target identification model and a motion tracking technology, wherein the target identification model comprises a face recognition model and/or a license plate identification model;
taking the initial restored video data marked with the same sensitive object as the restored video data;
and taking the optimal sensitive area image as a retrieval index of the restored video data, wherein the optimal sensitive area image is the sensitive area image with the highest picture characteristic value in the restored video data.
11. A method for processing a road segment image, which is applied to a road test device, comprising:
after an original road section image of a target road section is acquired, identifying and obtaining a sensitive area image containing a sensitive object in the original road section image;
carrying out fuzzy processing on the sensitive area image in the original road section image to obtain a desensitized road section image; recording the original distribution position of the sensitive area image in the desensitized road section image;
transmitting the desensitized road section image to an operation platform; and transmitting sensitive data to a job function platform, wherein the sensitive data comprises the sensitive area image and a first mapping relation for the job function platform to acquire the original road section image, and the first mapping relation is a mapping relation between an image identifier corresponding to the desensitized road section image and the original distribution position.
12. The method of claim 11, wherein the identifying the sensitive area image containing the sensitive object in the original road segment image comprises:
identifying a sensitive area image containing a face image in the original road section image by using a face identification model; and/or the number of the groups of groups,
And identifying a sensitive area image containing the license plate image in the original road section image by using a license plate identification model.
13. The method of claim 11, wherein the transmitting the desensitized road segment image to an operator platform; and transmitting the sensitive data to a job platform, comprising:
transmitting a plurality of desensitized road segment images belonging to the same video data to the operation platform; and transmitting a plurality of the sensitive data belonging to the same video data to the job platform.
14. The processing method of the road section image is characterized by being applied to a function platform and comprising the following steps of:
receiving sensitive data sent by a road test device, wherein the sensitive data comprises a sensitive area image and a first mapping relation comprising image identifications and original distribution positions, the image identifications are used for representing desensitized road section images associated with the sensitive area image, and the original distribution positions are used for representing positions of the sensitive area image originally in the desensitized road section images;
the image identification is sent to an operation platform, and a desensitization road section image which is returned by the operation platform and is associated with the image identification is received;
And replacing a fuzzy area in the desensitized road section image with the sensitive area image based on the original distribution position to obtain an original road section image associated with the sensitive area image.
15. The method of claim 14, further comprising, after receiving the sensitive data sent by the drive test device:
determining a sensitive object contained in the sensitive area image, and storing a second mapping relation between the sensitive data and the sensitive object into a storage node of the sensitive area image;
when a evidence obtaining instruction aiming at the sensitive object is detected, the image identification is sent to the operation platform, and the desensitized road section image returned by the operation platform is received.
16. The method of claim 14 or 15, wherein said receiving the desensitized road segment image returned by the operation platform comprises:
if video data sent by the operation platform are received, acquiring a video frame identifier included in the sensitive data;
and taking the target video frame matched with the video frame identifier in the video data as the desensitized road section image.
17. The method of claim 14, wherein the replacing the blurred region in the desensitized road section image with the sensitive region image based on the original distribution location comprises:
Acquiring a coordinate point range included in the original distribution position;
and if the coordinate point range is detected to correspond to the fuzzy area in the desensitization road section image, replacing the fuzzy area in the desensitization road section image with the sensitive area image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311776015.2A CN117455751B (en) | 2023-12-22 | 2023-12-22 | Road section image processing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311776015.2A CN117455751B (en) | 2023-12-22 | 2023-12-22 | Road section image processing system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117455751A true CN117455751A (en) | 2024-01-26 |
| CN117455751B CN117455751B (en) | 2024-03-26 |
Family
ID=89589473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311776015.2A Active CN117455751B (en) | 2023-12-22 | 2023-12-22 | Road section image processing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117455751B (en) |
Citations (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101691620B1 (en) * | 2016-04-06 | 2017-01-02 | 에스제이데이타 주식회사 | System for update of road facilitie data by analysing the visual images and connecting the mms |
| CN106408944A (en) * | 2016-11-17 | 2017-02-15 | 国网山东省电力公司东营供电公司 | Congestion level analysis platform based on double communication data |
| CN206282356U (en) * | 2016-08-30 | 2017-06-27 | 江苏鸿信***集成有限公司 | Wisdom traffic big data analysis system |
| CN106911913A (en) * | 2017-02-24 | 2017-06-30 | 深圳凯达通光电科技有限公司 | A kind of efficient road section traffic volume condition monitoring system |
| US20190050592A1 (en) * | 2018-09-27 | 2019-02-14 | Intel IP Corporation | Systems and methods for processing and handling privacy-sensitive image data |
| CN109800868A (en) * | 2018-12-25 | 2019-05-24 | 福州瑞芯微电子股份有限公司 | A kind of data encoding chip and method based on deep learning |
| US20190362162A1 (en) * | 2018-05-23 | 2019-11-28 | Here Global B.V. | Method, apparatus, and system for detecting a physical divider on a road segment |
| KR20200022285A (en) * | 2018-08-22 | 2020-03-03 | 한국건설기술연구원 | Apparatus of mapping 3d information model about road field for augmented reality service and method thereof |
| US20200077035A1 (en) * | 2018-08-28 | 2020-03-05 | Baidu Online Network Technology (Beijing) Co., Ltd. | Video recording method and apparatus, electronic device and readable storage medium |
| CN111797430A (en) * | 2020-06-30 | 2020-10-20 | 平安国际智慧城市科技股份有限公司 | Data verification method, device, server and storage medium |
| CN112329757A (en) * | 2020-10-20 | 2021-02-05 | 安诚迈科(北京)信息技术有限公司 | Method, device and system for desensitizing acquisition of bill information |
| CN112528318A (en) * | 2020-11-27 | 2021-03-19 | 国家电网有限公司大数据中心 | Image desensitization method and device and electronic equipment |
| US20210150053A1 (en) * | 2018-04-16 | 2021-05-20 | Alibaba Group Holding Limited | Method, device, and storage medium for image desensitization |
| CN113077633A (en) * | 2021-02-24 | 2021-07-06 | 克拉玛依油城数据有限公司 | Novel smart city system and application method thereof |
| CN113259721A (en) * | 2021-06-18 | 2021-08-13 | 长视科技股份有限公司 | Video data sending method and electronic equipment |
| CN113918990A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Data desensitization processing method and device |
| CN113989156A (en) * | 2021-11-01 | 2022-01-28 | 北京地平线信息技术有限公司 | Method, apparatus, medium, device, and program for reliability verification of desensitization method |
| US20220067209A1 (en) * | 2018-03-05 | 2022-03-03 | Mobileye Vision Technologies Ltd. | Systems and methods for anonymizing navigation information |
| US20220116742A1 (en) * | 2020-07-15 | 2022-04-14 | Visual Defence Inc. | System and method for optimizing collection and transmission of surveying data across a road network |
| CN114463755A (en) * | 2021-12-13 | 2022-05-10 | 武汉中海庭数据技术有限公司 | Automatic sensitive information detection desensitization method in high-precision map-based acquired picture |
| CN114817991A (en) * | 2022-05-10 | 2022-07-29 | 上海计算机软件技术开发中心 | Internet of vehicles image desensitization method and system |
| CN114841377A (en) * | 2022-06-28 | 2022-08-02 | 国汽智控(北京)科技有限公司 | Federal learning model training method and recognition method applied to image target recognition |
| CN115033902A (en) * | 2022-06-02 | 2022-09-09 | 支付宝(杭州)信息技术有限公司 | Multi-entity image privacy protection method, device and equipment |
| CN115238309A (en) * | 2022-07-22 | 2022-10-25 | 零束科技有限公司 | Data desensitization method and device, electronic equipment and storage medium |
| CN115270184A (en) * | 2022-08-01 | 2022-11-01 | 零束科技有限公司 | Video desensitization method, vehicle video desensitization method and vehicle-mounted processing system |
| CN115408710A (en) * | 2022-08-30 | 2022-11-29 | 腾讯科技（深圳）有限公司 | Image desensitization method and related device |
| WO2023012671A1 (en) * | 2021-08-02 | 2023-02-09 | Mobileye Vision Technologies Ltd. | Vulnerable road user (vru) collision avoidance system |
| US20230076648A1 (en) * | 2020-05-20 | 2023-03-09 | State Farm Mutual Automobile Insurance Company | Synchronizing image data with either vehicle telematics data or infrastructure data pertaining to a road segment |
| CN115810160A (en) * | 2022-10-29 | 2023-03-17 | 武汉中海庭数据技术有限公司 | Automatic desensitization processing method and system for sensitive information in road traffic video |
| CN115830690A (en) * | 2022-12-22 | 2023-03-21 | 云控智行(上海)汽车科技有限公司 | Traffic image desensitization method and equipment |
| WO2023051143A1 (en) * | 2021-09-28 | 2023-04-06 | 北京地平线信息技术有限公司 | Data desensitization method and apparatus |
| CN115952531A (en) * | 2022-10-14 | 2023-04-11 | 国汽智控(北京)科技有限公司 | Image processing method, device, equipment and storage medium |
| CN116152763A (en) * | 2023-01-03 | 2023-05-23 | 奇瑞汽车股份有限公司 | Picture desensitization and picture data cleaning method and system based on intelligent driving |
| CN116186770A (en) * | 2023-02-14 | 2023-05-30 | 重庆长安汽车股份有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
| KR20230101118A (en) * | 2021-12-29 | 2023-07-06 | (주) 경성테크놀러지 | A system for providing road guidance service by judging sections of road surface abnormalities and creating maps for the transportation vulnerable |
| WO2023137863A1 (en) * | 2022-01-19 | 2023-07-27 | 浙江吉利控股集团有限公司 | Method, apparatus and device for generating road data evaluation report, and storage medium |
| CN116563860A (en) * | 2023-04-19 | 2023-08-08 | 平安科技（深圳）有限公司 | Data desensitization method, device, computer equipment and medium based on artificial intelligence |
| CN116847334A (en) * | 2023-08-08 | 2023-10-03 | 四川汇浪佳宇新能源科技有限公司 | Data safety transmission method |
| CN116881967A (en) * | 2023-07-20 | 2023-10-13 | 周佳庆 | Privacy protection method, device and equipment |
| CN116958582A (en) * | 2023-06-20 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Data processing method and related device |
| CN116977484A (en) * | 2023-01-17 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
| CN117201208A (en) * | 2023-11-08 | 2023-12-08 | 新华三网络信息安全软件有限公司 | Malicious mail identification method, malicious mail identification device, electronic equipment and storage medium |
| CN117216758A (en) * | 2023-11-08 | 2023-12-12 | 新华三网络信息安全软件有限公司 | Application security detection system and method |
-
2023
- 2023-12-22 CN CN202311776015.2A patent/CN117455751B/en active Active
Patent Citations (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101691620B1 (en) * | 2016-04-06 | 2017-01-02 | 에스제이데이타 주식회사 | System for update of road facilitie data by analysing the visual images and connecting the mms |
| CN206282356U (en) * | 2016-08-30 | 2017-06-27 | 江苏鸿信***集成有限公司 | Wisdom traffic big data analysis system |
| CN106408944A (en) * | 2016-11-17 | 2017-02-15 | 国网山东省电力公司东营供电公司 | Congestion level analysis platform based on double communication data |
| CN106911913A (en) * | 2017-02-24 | 2017-06-30 | 深圳凯达通光电科技有限公司 | A kind of efficient road section traffic volume condition monitoring system |
| US20220067209A1 (en) * | 2018-03-05 | 2022-03-03 | Mobileye Vision Technologies Ltd. | Systems and methods for anonymizing navigation information |
| US20210150053A1 (en) * | 2018-04-16 | 2021-05-20 | Alibaba Group Holding Limited | Method, device, and storage medium for image desensitization |
| US20190362162A1 (en) * | 2018-05-23 | 2019-11-28 | Here Global B.V. | Method, apparatus, and system for detecting a physical divider on a road segment |
| KR20200022285A (en) * | 2018-08-22 | 2020-03-03 | 한국건설기술연구원 | Apparatus of mapping 3d information model about road field for augmented reality service and method thereof |
| US20200077035A1 (en) * | 2018-08-28 | 2020-03-05 | Baidu Online Network Technology (Beijing) Co., Ltd. | Video recording method and apparatus, electronic device and readable storage medium |
| US20190050592A1 (en) * | 2018-09-27 | 2019-02-14 | Intel IP Corporation | Systems and methods for processing and handling privacy-sensitive image data |
| CN109800868A (en) * | 2018-12-25 | 2019-05-24 | 福州瑞芯微电子股份有限公司 | A kind of data encoding chip and method based on deep learning |
| US20230076648A1 (en) * | 2020-05-20 | 2023-03-09 | State Farm Mutual Automobile Insurance Company | Synchronizing image data with either vehicle telematics data or infrastructure data pertaining to a road segment |
| CN111797430A (en) * | 2020-06-30 | 2020-10-20 | 平安国际智慧城市科技股份有限公司 | Data verification method, device, server and storage medium |
| US20220116742A1 (en) * | 2020-07-15 | 2022-04-14 | Visual Defence Inc. | System and method for optimizing collection and transmission of surveying data across a road network |
| CN112329757A (en) * | 2020-10-20 | 2021-02-05 | 安诚迈科(北京)信息技术有限公司 | Method, device and system for desensitizing acquisition of bill information |
| CN112528318A (en) * | 2020-11-27 | 2021-03-19 | 国家电网有限公司大数据中心 | Image desensitization method and device and electronic equipment |
| CN113077633A (en) * | 2021-02-24 | 2021-07-06 | 克拉玛依油城数据有限公司 | Novel smart city system and application method thereof |
| CN113259721A (en) * | 2021-06-18 | 2021-08-13 | 长视科技股份有限公司 | Video data sending method and electronic equipment |
| WO2023012671A1 (en) * | 2021-08-02 | 2023-02-09 | Mobileye Vision Technologies Ltd. | Vulnerable road user (vru) collision avoidance system |
| WO2023051143A1 (en) * | 2021-09-28 | 2023-04-06 | 北京地平线信息技术有限公司 | Data desensitization method and apparatus |
| CN113918990A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Data desensitization processing method and device |
| CN113989156A (en) * | 2021-11-01 | 2022-01-28 | 北京地平线信息技术有限公司 | Method, apparatus, medium, device, and program for reliability verification of desensitization method |
| CN114463755A (en) * | 2021-12-13 | 2022-05-10 | 武汉中海庭数据技术有限公司 | Automatic sensitive information detection desensitization method in high-precision map-based acquired picture |
| KR20230101118A (en) * | 2021-12-29 | 2023-07-06 | (주) 경성테크놀러지 | A system for providing road guidance service by judging sections of road surface abnormalities and creating maps for the transportation vulnerable |
| WO2023137863A1 (en) * | 2022-01-19 | 2023-07-27 | 浙江吉利控股集团有限公司 | Method, apparatus and device for generating road data evaluation report, and storage medium |
| CN114817991A (en) * | 2022-05-10 | 2022-07-29 | 上海计算机软件技术开发中心 | Internet of vehicles image desensitization method and system |
| CN115033902A (en) * | 2022-06-02 | 2022-09-09 | 支付宝(杭州)信息技术有限公司 | Multi-entity image privacy protection method, device and equipment |
| CN114841377A (en) * | 2022-06-28 | 2022-08-02 | 国汽智控(北京)科技有限公司 | Federal learning model training method and recognition method applied to image target recognition |
| CN115238309A (en) * | 2022-07-22 | 2022-10-25 | 零束科技有限公司 | Data desensitization method and device, electronic equipment and storage medium |
| CN115270184A (en) * | 2022-08-01 | 2022-11-01 | 零束科技有限公司 | Video desensitization method, vehicle video desensitization method and vehicle-mounted processing system |
| CN115408710A (en) * | 2022-08-30 | 2022-11-29 | 腾讯科技（深圳）有限公司 | Image desensitization method and related device |
| CN115952531A (en) * | 2022-10-14 | 2023-04-11 | 国汽智控(北京)科技有限公司 | Image processing method, device, equipment and storage medium |
| CN115810160A (en) * | 2022-10-29 | 2023-03-17 | 武汉中海庭数据技术有限公司 | Automatic desensitization processing method and system for sensitive information in road traffic video |
| CN115830690A (en) * | 2022-12-22 | 2023-03-21 | 云控智行(上海)汽车科技有限公司 | Traffic image desensitization method and equipment |
| CN116152763A (en) * | 2023-01-03 | 2023-05-23 | 奇瑞汽车股份有限公司 | Picture desensitization and picture data cleaning method and system based on intelligent driving |
| CN116977484A (en) * | 2023-01-17 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
| CN116186770A (en) * | 2023-02-14 | 2023-05-30 | 重庆长安汽车股份有限公司 | Image desensitizing method, device, electronic equipment and storage medium |
| CN116563860A (en) * | 2023-04-19 | 2023-08-08 | 平安科技（深圳）有限公司 | Data desensitization method, device, computer equipment and medium based on artificial intelligence |
| CN116958582A (en) * | 2023-06-20 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Data processing method and related device |
| CN116881967A (en) * | 2023-07-20 | 2023-10-13 | 周佳庆 | Privacy protection method, device and equipment |
| CN116847334A (en) * | 2023-08-08 | 2023-10-03 | 四川汇浪佳宇新能源科技有限公司 | Data safety transmission method |
| CN117201208A (en) * | 2023-11-08 | 2023-12-08 | 新华三网络信息安全软件有限公司 | Malicious mail identification method, malicious mail identification device, electronic equipment and storage medium |
| CN117216758A (en) * | 2023-11-08 | 2023-12-12 | 新华三网络信息安全软件有限公司 | Application security detection system and method |
Non-Patent Citations (7)
| Title |
|---|
| ZIZHANG WU ET AL.: "ADD: An automatic desensitization fisheye dataset for autonomous driving", 《ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE》, vol. 126, 30 November 2023 (2023-11-30) * |
| 吴兰，范晋卿，文成林: "道路交通模糊图像多尺度清晰化复原方法研究", 《现代电子技术》, vol. 45, no. 9, 1 May 2022 (2022-05-01), pages 21 - 28 * |
| 杜圣东;杨燕;滕飞;: "交通大数据:一种基于微服务的敏捷处理架构设计", 大数据, no. 03, 20 May 2017 (2017-05-20) * |
| 王振;张志敏;禚保玲;杜臣昌;: "基于车辆牌照识别数据的城市居民出行特征研究――以青岛市为例", 青岛理工大学学报, no. 02, 30 April 2020 (2020-04-30) * |
| 胡庆勇;王斌;傅强;裴钟哲;: "交通大数据智能***工程在道路交通风险主动防控中的应用", 交通运输研究, no. 05, 16 January 2020 (2020-01-16) * |
| 辜丽琼;宋祖康;杨阳;: "基于改进支持向量机模型的交通拥堵情况预测", 软件导刊, no. 12 * |
| 马云琪;陈庆春;周国剑;类先富;: "在线传输电子文档图像脱敏***设计与实现", 信息通信, no. 04, 15 April 2019 (2019-04-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117455751B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705405B (en) | Target labeling method and device | |
| CN110929589B (en) | Method, apparatus, computer apparatus and storage medium for identifying vehicle characteristics | |
| CN111612104B (en) | Vehicle loss assessment image acquisition method, device, medium and electronic equipment | |
| CN108323209B (en) | Information processing method, system, cloud processing device and computer storage medium | |
| CN112085952A (en) | Vehicle data monitoring method and device, computer equipment and storage medium | |
| CN106919610B (en) | Internet of vehicles data processing method, system and server | |
| CN113496213A (en) | Method, device and system for determining target perception data and storage medium | |
| CN112381092B (en) | Tracking method, tracking device and computer readable storage medium | |
| CN110298302B (en) | Human body target detection method and related equipment | |
| CN112183321A (en) | Method and device for optimizing machine learning model, computer equipment and storage medium | |
| JP6098841B2 (en) | Pedestrian image acquisition device for vehicles | |
| CN111368617B (en) | Vehicle access data processing method and device | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN117455751B (en) | Road section image processing system and method | |
| CN111985304A (en) | Patrol alarm method, system, terminal equipment and storage medium | |
| CN113014876A (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN111340837A (en) | Image processing method, device, equipment and storage medium | |
| CN112733864A (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| CN114495244B (en) | Electrographic calculation data anomaly detection method, device, equipment and storage medium | |
| CN114119953A (en) | Method for quickly positioning and correcting license plate, storage medium and equipment | |
| CN108363985B (en) | Target object perception system testing method and device and computer readable storage medium | |
| CN112766746A (en) | Traffic accident recognition method and device, electronic equipment and storage medium | |
| CN113642533B (en) | Lane level positioning method and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |