CN117556438A - Image desensitizing method and device - Google Patents
Image desensitizing method and device Download PDFInfo
- Publication number
- CN117556438A CN117556438A CN202311508634.3A CN202311508634A CN117556438A CN 117556438 A CN117556438 A CN 117556438A CN 202311508634 A CN202311508634 A CN 202311508634A CN 117556438 A CN117556438 A CN 117556438A
- Authority
- CN
- China
- Prior art keywords
- frame image
- image
- sensitive information
- desensitization
- coordinates
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000000586 desensitisation Methods 0.000 claims abstract description 82
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 230000001360 synchronised effect Effects 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 58
- 230000007613 environmental effect Effects 0.000 description 16
- 238000012549 training Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 10
- 238000013136 deep learning model Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The disclosure provides an image desensitizing method and device, relates to the technical field of artificial intelligence, and particularly relates to the technical fields of computer vision, image processing, automatic driving and the like. One embodiment of the method comprises the following steps: receiving sensitive information coordinates of an ith frame of image sent by a software system, wherein i is a positive integer; receiving an (i+1) th frame image transmitted by a sensor of a vehicle; based on the sensitive information coordinates of the ith frame image, determining the sensitive information position of the (i+1) th frame image, and performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image. This embodiment combines a software system with a hardware system for desensitizing the image. Synchronous desensitization operation is carried out according to coordinates in the real-time transmission process of sensor data, and time delay brought by desensitization processing is reduced.
Description
Technical Field
The present disclosure relates to the technical field of artificial intelligence, and in particular to the technical fields of computer vision, image processing, automatic driving, and the like.
Background
With the rapid development and landing of automatic driving technology, huge sensor acquisition systems acquire a large amount of environmental data every day, including but not limited to pedestrians, vehicles, obstacles, traffic lights, etc. As early as 2022, the chinese automobile technical research center (abbreviated as "middle automobile assistant") has set requirements for desensitization of automobile data, including image data of both the inside (face) and the outside (face and license plate) of the automobile. However, the data collected by the automobile is often dynamic video, and the capability of artificial intelligence is required to identify and track sensitive data, and perform corresponding operations such as erasing, smearing and the like.
The on-line desensitization of the vehicle end aims at the sensor data, and real-time desensitization is needed for a later-stage processing unit. The desensitized data are directly used for an automatic driving sensing system to realize real-time identification of road condition information such as barriers, traffic lights and the like, and are provided for a rear-stage module to realize final vehicle control. The desensitization of the vehicle end has extremely high requirements on the time delay of the sensor, and any increase of the time delay can lead to the reduction of the automatic driving performance and potential safety hazard.
Disclosure of Invention
Embodiments of the present disclosure provide an image desensitizing method, apparatus, device, storage medium, and program product.
In a first aspect, embodiments of the present disclosure provide an image desensitizing method, including: receiving sensitive information coordinates of an ith frame of image sent by a software system, wherein i is a positive integer; receiving an (i+1) th frame image transmitted by a sensor of a vehicle; based on the sensitive information coordinates of the ith frame image, determining the sensitive information position of the (i+1) th frame image, and performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
In a second aspect, embodiments of the present disclosure provide an image desensitizing apparatus, including: the coordinate receiving module is configured to receive sensitive information coordinates of an ith frame of image sent by the software system, wherein i is a positive integer; an image receiving module configured to receive an i+1st frame image transmitted by a sensor of the vehicle; the image desensitization module is configured to determine the sensitive information position of the (i+1) th frame image based on the sensitive information coordinates of the (i) th frame image, and perform desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
In a third aspect, an embodiment of the present disclosure proposes an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method as described in the first aspect.
In a fifth aspect, embodiments of the present disclosure propose a computer program product comprising a computer program which, when executed by a processor, implements a method as described in the first aspect.
The image desensitizing method combines a software system and a hardware system to desensitize an image. The method fully plays the advancement of the software system in the field of target detection and the superiority of the hardware system in low-delay processing. The software system is responsible for identifying the sensitive information and sending the coordinates of the sensitive information to the hardware system. The hardware system receives the sensitive information coordinates from the software system, and synchronous desensitization operation is carried out according to the coordinates in the real-time transmission process of the sensor data, so that the time delay caused by desensitization is reduced. Because the hardware system does not need to realize a complex target detection algorithm, the complexity and cost of the hardware system design can be greatly reduced.
Nor is it intended to limit the scope of the present disclosure to the critical or important features of the embodiments of the present disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
Other features, objects and advantages of the present disclosure will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of an image desensitization method according to the present disclosure;
FIG. 3 is a flow chart of yet another embodiment of an image desensitization method according to the present disclosure;
FIG. 4 is a flow chart of another embodiment of an image desensitization method according to the present disclosure;
FIG. 5 is an application scenario diagram in which the image desensitization method of the present disclosure may be implemented;
FIG. 6 is a schematic structural view of one embodiment of an image desensitizing apparatus according to the present disclosure;
fig. 7 is a block diagram of an electronic device for implementing an image desensitization method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 in which embodiments of an image desensitization method or image desensitization apparatus of the present application may be applied.
As shown in fig. 1, a system architecture 100 may include a sensor 101, a network 102, and a server 103. Network 102 is the medium used to provide a communication link between sensor 101 and server 103. Network 102 may include various connection types such as wired, wireless communication links, or fiber optic cables, among others.
The sensor 101 may be mounted on an autonomous vehicle, interact with the server 103 via the network 102 to receive or send messages, etc. The sensor 101 may include a camera, lidar, etc. for collecting environmental data of the autonomous vehicle and sending to the server 103 for processing.
The server 103 may be an on-board server or a cloud server of the autonomous vehicle. The server 103 may perform processing such as analysis on the received data such as the image and generate processing results (e.g., desensitized images) for subsequent control of the autonomous vehicle.
The server 103 may be hardware or software. When the server 103 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 103 is software, it may be implemented as a plurality of software or software modules (for example, to provide distributed services), or may be implemented as a single software or software module. The present invention is not particularly limited herein.
It should be noted that, the image desensitizing method provided in the embodiment of the present application is generally performed by the server 103, and accordingly, the image desensitizing device is generally disposed in the server 103.
With continued reference to fig. 2, a flow 200 of one embodiment of an image desensitization method according to the present disclosure is shown. The image desensitizing method comprises the following steps:
and step 201, receiving sensitive information coordinates of an ith frame image sent by a software system.
In this embodiment, the hardware system may receive the sensitive information coordinates of the i-th frame image sent by the software system. Wherein i is a positive integer.
Typically, an autonomous vehicle has a large number of sensors mounted thereon for collecting environmental data of the autonomous vehicle. The sensor may include, but is not limited to, a camera, a lidar, etc. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame. The hardware system may transmit the image directly to the software system or may desensitize the image before transmitting to the software system. Where the environmental data collected by the sensor may include a number of objects such as pedestrians, vehicles, obstacles, traffic, etc. Some sensitive information exists in these targets and require desensitization processes such as faces in-car images, faces in out-of-car images and license plates.
For example, when the hardware system receives the first frame image, the first frame image may be directly transmitted to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
For another example, when the hardware system receives the first frame image, sensitive information of the first frame image may be identified and desensitized. The hardware system may then transmit the first frame desensitized image to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
For another example, when the hardware system receives the i-th frame image, the i-th frame image may be directly transmitted to the software system. The software system can identify the sensitive information coordinates of the ith frame of image through the target detection model and transmit the sensitive information coordinates to the hardware system. When the hardware system receives the (i+1) th frame image, the hardware system can directly transmit the (i+1) th frame image to the software system on one hand, and can desensitize the (i+1) th frame image based on sensitive information coordinates of the (i) th frame image sent by the software system on the other hand. The software system can identify the coordinates of the sensitive information of the image through the object detection model and transmit the coordinates to the hardware system.
Here, the object detection model may be a training of the deep learning model using the sample image. Wherein the sample image may be annotated with sensitive information. And taking the sample image as input, taking the marked sensitive information as output, and performing supervised training on the deep learning model to obtain the target detection model. The object detection model may be a single type of object detection model or may be a plurality of types of object detection models. For a detection model of a single type of object, a sample image comprising one type of sensitive information may train one object detection model for detecting one type of sensitive information. For example, training is performed by using images labeled with faces, so that a face detection model can be obtained and used for detecting faces in the images. For another example, training is performed on the image marked with the license plate, so that a license plate detection model can be obtained and used for detecting the license plate in the image. For detection models of multiple classes of targets, sample images including multiple types of sensitive information may train one target detection model for detecting multiple types of sensitive information. For example, training is performed by using images marked with faces and license plates, so that a face and license plate detection model can be obtained and used for detecting the license plates and the faces in the images.
Step 202, an i+1st frame image transmitted by a sensor of a vehicle is received.
In this embodiment, the hardware system may receive the i+1st frame image transmitted by the sensor of the vehicle. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame.
Step 203, determining the sensitive information position of the (i+1) th frame image based on the sensitive information coordinates of the (i) th frame image, and performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
In this embodiment, the hardware system may determine the sensitive information position of the i+1st frame image based on the sensitive information coordinate of the i+1st frame image, and perform desensitization processing on the information at the sensitive information position of the i+1st frame image, to obtain a desensitized image corresponding to the i+1st frame image.
Typically, the frame interval in the environmental data collected by the sensor is extremely short, typically on the order of milliseconds. Therefore, the position change of the sensitive information in the adjacent frame images is small, and the desensitization position precision requirement can be met. In this case, the sensitive information coordinate of the previous frame image can be directly used as the sensitive information coordinate of the current frame image to determine the sensitive information position of the current frame. And carrying out desensitization processing on the information at the sensitive information position of the current frame image, so as to obtain a desensitization image corresponding to the current frame image. Wherein the desensitizing treatment is typically a malefactor treatment.
The image desensitizing method combines a software system and a hardware system to desensitize an image. The method fully plays the advancement of the software system in the field of target detection and the superiority of the hardware system in low-delay processing. The software system is responsible for identifying the sensitive information and sending the coordinates of the sensitive information to the hardware system. The hardware system receives the sensitive information coordinates from the software system, and synchronous desensitization operation is carried out according to the coordinates in the real-time transmission process of the sensor data, so that the time delay caused by desensitization is reduced. Because the hardware system does not need to realize a complex target detection algorithm, the complexity and cost of the hardware system design can be greatly reduced.
With further reference to fig. 3, a flow 300 of yet another embodiment of an image desensitization method according to the present disclosure is shown. The image desensitizing method comprises the following steps:
step 301, receiving sensitive information coordinates of an ith frame of image sent by a software system.
In this embodiment, the hardware system may receive the sensitive information coordinates of the i-th frame image sent by the software system. Wherein i is a positive integer.
Typically, an autonomous vehicle has a large number of sensors mounted thereon for collecting environmental data of the autonomous vehicle. The sensor may include, but is not limited to, a camera, a lidar, etc. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame. The hardware system may transmit the image directly to the software system or may desensitize the image before transmitting to the software system. Where the environmental data collected by the sensor may include a number of objects such as pedestrians, vehicles, obstacles, traffic, etc. Some sensitive information exists in these targets and require desensitization processes such as faces in-car images, faces in out-of-car images and license plates.
For example, when the hardware system receives the first frame image, the first frame image may be directly transmitted to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
For another example, when the hardware system receives the first frame image, sensitive information of the first frame image may be identified and desensitized. The hardware system may then transmit the first frame desensitized image to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
Here, the object detection model may be a training of the deep learning model using the sample image. Wherein the sample image may be annotated with sensitive information. And taking the sample image as input, taking the marked sensitive information as output, and performing supervised training on the deep learning model to obtain the target detection model. The object detection model may be a single type of object detection model or may be a plurality of types of object detection models. For a detection model of a single type of object, a sample image comprising one type of sensitive information may train one object detection model for detecting one type of sensitive information. For example, training is performed by using images labeled with faces, so that a face detection model can be obtained and used for detecting faces in the images. For another example, training is performed on the image marked with the license plate, so that a license plate detection model can be obtained and used for detecting the license plate in the image. For detection models of multiple classes of targets, sample images including multiple types of sensitive information may train one target detection model for detecting multiple types of sensitive information. For example, training is performed by using images marked with faces and license plates, so that a face and license plate detection model can be obtained and used for detecting the license plates and the faces in the images.
Step 302, an i+1st frame image transmitted by a sensor of a vehicle is received.
In this embodiment, the hardware system may receive the i+1st frame image transmitted by the sensor of the vehicle. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame.
Step 303, determining the sensitive information position of the (i+1) th frame image based on the sensitive information coordinates of the (i) th frame image, and performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
In this embodiment, the hardware system may determine the sensitive information position of the i+1st frame image based on the sensitive information coordinate of the i+1st frame image, and perform desensitization processing on the information at the sensitive information position of the i+1st frame image, to obtain a desensitized image corresponding to the i+1st frame image.
Typically, the frame interval in the environmental data collected by the sensor is extremely short, typically on the order of milliseconds. Therefore, the position change of the sensitive information in the adjacent frame images is small, and the desensitization position precision requirement can be met. In this case, the sensitive information coordinate of the previous frame image can be directly used as the sensitive information coordinate of the current frame image to determine the sensitive information position of the current frame. And carrying out desensitization processing on the information at the sensitive information position of the current frame image, so as to obtain a desensitization image corresponding to the current frame image. Wherein the desensitizing treatment is typically a malefactor treatment.
Step 304, the desensitized image corresponding to the i+1st frame image is sent to the software system, so that the software system identifies the sensitive information coordinates of the i+1st frame image based on the desensitized image corresponding to the i+1st frame image.
In this embodiment, the hardware system may send the desensitized image corresponding to the i+1st frame image to the software system. The software system may identify the sensitive information coordinates of the i+1th frame image based on the desensitized image corresponding to the i+1th frame image. The software system can identify the desensitized image corresponding to the (i+1) th frame image through the target detection model, obtain the sensitive information coordinate of the (i+1) th frame image, and transmit the sensitive information coordinate to the hardware system.
In step 305, the sensitive information coordinates of the (i+1) th frame image sent by the software system are received.
In this embodiment, the hardware system may receive the sensitive information coordinates of the i+1st frame image sent by the software system. The hardware system can determine the sensitive information position of the (i+2) th frame image based on the sensitive information coordinates of the (i+1) th frame image, and desensitize the information at the sensitive information position of the (i+2) th frame image to obtain a desensitized image corresponding to the (i+2) th frame image. Therefore, synchronous desensitization operation according to coordinates in the real-time transmission process of sensor data is realized.
The image desensitizing method combines a software system and a hardware system to desensitize an image. The software system is responsible for identifying the sensitive information of the previous frame and sending the sensitive information coordinates of the previous frame to the hardware system. The hardware system receives the sensitive information coordinates of the last frame from the software system and desensitizes the current frame. The hardware system in turn transmits the desensitized image of the current frame to the software system. The software system is responsible for identifying the sensitive information of the current frame and sending the sensitive information coordinates of the current frame to the hardware system. The hardware system receives the sensitive information coordinates of the current frame from the software system and desensitizes the next frame. The hardware system and the software system interact in this way, so that synchronous desensitization operation can be realized according to coordinates in the real-time transmission process of sensor data, and time delay caused by desensitization processing is greatly reduced.
With further reference to fig. 4, a flow 400 of another embodiment of an image desensitization method according to the present disclosure is shown. The image desensitizing method comprises the following steps:
step 401, receiving sensitive information coordinates of an ith frame image sent by a software system
In this embodiment, the hardware system may receive the sensitive information coordinates of the i-th frame image sent by the software system. Wherein i is a positive integer.
Typically, an autonomous vehicle has a large number of sensors mounted thereon for collecting environmental data of the autonomous vehicle. The sensor may include, but is not limited to, a camera, a lidar, etc. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame. The hardware system may transmit the image directly to the software system or may desensitize the image before transmitting to the software system. Where the environmental data collected by the sensor may include a number of objects such as pedestrians, vehicles, obstacles, traffic, etc. Some sensitive information exists in these targets and require desensitization processes such as faces in-car images, faces in out-of-car images and license plates.
For example, when the hardware system receives the first frame image, the first frame image may be directly transmitted to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
For another example, when the hardware system receives the first frame image, sensitive information of the first frame image may be identified and desensitized. The hardware system may then transmit the first frame desensitized image to the software system. The software system can identify the sensitive information coordinates of the first frame image through the target detection model and transmit the sensitive information coordinates to the hardware system. For the second frame image and the later images received by the hardware system, the hardware system can perform desensitization processing based on the sensitive information coordinates of the previous frame image sent by the software system and then transmit the desensitized information coordinates to the software system. The software system can identify the coordinates of the sensitive information of the desensitized image through the object detection model and transmit the coordinates to the hardware system.
For another example, when the hardware system receives the i-th frame image, the i-th frame image may be directly transmitted to the software system. The software system can identify the sensitive information coordinates of the ith frame of image through the target detection model and transmit the sensitive information coordinates to the hardware system. When the hardware system receives the (i+1) th frame image, the hardware system can directly transmit the (i+1) th frame image to the software system on one hand, and can desensitize the (i+1) th frame image based on sensitive information coordinates of the (i) th frame image sent by the software system on the other hand. The software system can identify the coordinates of the sensitive information of the image through the object detection model and transmit the coordinates to the hardware system.
Here, the object detection model may be a training of the deep learning model using the sample image. Wherein the sample image may be annotated with sensitive information. And taking the sample image as input, taking the marked sensitive information as output, and performing supervised training on the deep learning model to obtain the target detection model. The object detection model may be a single type of object detection model or may be a plurality of types of object detection models. For a detection model of a single type of object, a sample image comprising one type of sensitive information may train one object detection model for detecting one type of sensitive information. For example, training is performed by using images labeled with faces, so that a face detection model can be obtained and used for detecting faces in the images. For another example, training is performed on the image marked with the license plate, so that a license plate detection model can be obtained and used for detecting the license plate in the image. For detection models of multiple classes of targets, sample images including multiple types of sensitive information may train one target detection model for detecting multiple types of sensitive information. For example, training is performed by using images marked with faces and license plates, so that a face and license plate detection model can be obtained and used for detecting the license plates and the faces in the images.
Step 402, an i+1st frame image transmitted by a sensor of a vehicle is received.
In this embodiment, the hardware system may receive the i+1st frame image transmitted by the sensor of the vehicle. The environmental data collected by the sensor can be transmitted to the hardware system frame by frame.
Step 403, counting the number of rows and pixel information of the received i+1st frame image.
In this embodiment, in the transmission process of the i+1st frame image, the hardware system may count the number of rows and pixel information of the received i+1st frame image in real time, so as to track the transmitted image position.
Step 404, determining whether the sensitive information position of the i+1st frame image is reached based on the line number and the pixel point information.
In this embodiment, the hardware system may determine whether the sensitive information position of the i+1st frame image is reached based on the line number and the pixel point information. If the sensitive information location is reached, go to step 406; if the sensitive information location is not reached, step 406 is performed.
And step 405, performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image.
In this embodiment, if the sensitive information position of the i+1st frame image is reached, the hardware system may perform desensitization processing on the information at the sensitive information position of the i+1st frame image. Wherein the desensitizing treatment is typically a malefactor treatment.
Step 406, determining whether the transmission of the i+1st frame image is completed.
In this embodiment, if the sensitive information position of the i+1th frame image is not reached, or the information at the sensitive information position of the i+1th frame image is subjected to desensitization processing, the hardware system may determine whether the transmission of the i+1th frame image is completed. If the transmission is completed, go to step 407; if the transmission is not complete, the process returns to step 403.
Step 407, obtaining a desensitized image corresponding to the i+1st frame image.
In this embodiment, if the transmission of the i+1st frame image is completed, the hardware system may obtain a desensitized image corresponding to the i+1st frame image, and add 1 to the value of i, and return to continue to execute step 401.
The image desensitizing method combines a software system and a hardware system to desensitize an image. In the image transmission process, the hardware system can count the number of lines and pixel point information of the received image in real time, so that the real-time desensitization processing is realized when the sensitive information of the image is received, and the introduced time delay is basically zero.
For ease of understanding, fig. 5 illustrates an application scenario diagram in which the image desensitization method of the present disclosure may be implemented. As shown in fig. 5, the hardware system receives raw image data acquired by the camera sensor and transmits it to the software system. When the software system receives the original image data, the sensitive information coordinates are automatically identified through the target detection algorithm, and the sensitive information coordinates are sent to the hardware system. After the hardware system receives the sensitive information coordinates, the hardware system uses the sensitive information coordinates in the desensitization processing of the original image data of the next frame, and transmits the desensitized image data to the software system.
With further reference to fig. 6, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of an image desensitizing apparatus, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 6, the image desensitizing apparatus 600 of the present embodiment may include: a coordinate receiving module 601, an image receiving module 602, and an image desensitizing module 603. The coordinate receiving module 601 is configured to receive sensitive information coordinates of an ith frame of image sent by the software system, wherein i is a positive integer; an image receiving module 602 configured to receive an i+1st frame image transmitted by a sensor of the vehicle; the image desensitizing module 603 is configured to determine the sensitive information position of the i+1st frame image based on the sensitive information coordinates of the i+1st frame image, and perform desensitization processing on the information at the sensitive information position of the i+1st frame image, so as to obtain a desensitized image corresponding to the i+1st frame image.
In the present embodiment, in the image desensitizing apparatus 600: the specific processing of the coordinate receiving module 601, the image receiving module 602 and the image desensitizing module 603 and the technical effects thereof may refer to the relevant descriptions of steps 201 to 203 in the corresponding embodiment of fig. 2, and are not repeated herein.
In some optional implementations of this embodiment, the image desensitizing apparatus 600 further includes: the image sending module is configured to send the desensitized image corresponding to the (i+1) th frame image to the software system, so that the software system can identify the sensitive information coordinates of the (i+1) th frame image based on the desensitized image corresponding to the (i+1) th frame image; and the coordinate receiving module 601 is further configured to: and receiving the sensitive information coordinates of the (i+1) th frame image sent by the software system.
In some optional implementations of this embodiment, the image desensitization module 603 is further configured to: the following desensitization treatment steps are performed: counting the number of lines and pixel point information of the received (i+1) th frame image; determining whether the sensitive information position of the (i+1) th frame image is reached or not based on the line number and the pixel point information; and if the sensitive information position of the (i+1) th frame image is reached, desensitizing the information at the sensitive information position of the (i+1) th frame image.
In some optional implementations of this embodiment, the image desensitization module 603 is further configured to: if the sensitive information position of the (i+1) th frame image is not reached, or the information at the sensitive information position of the (i+1) th frame image is subjected to desensitization treatment, determining whether the transmission of the (i+1) th frame image is completed; if the transmission of the (i+1) th frame image is completed, a desensitization image corresponding to the (i+1) th frame image is obtained.
In some optional implementations of this embodiment, the image desensitization module 603 is further configured to: if the i+1st frame image is not transmitted, returning to the desensitization processing step.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the respective methods and processes described above, such as an image desensitization method. For example, in some embodiments, the image desensitizing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the image desensitization method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the image desensitization method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions provided by the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (13)
1. A method of image desensitization comprising:
receiving sensitive information coordinates of an ith frame of image sent by a software system, wherein i is a positive integer;
receiving an (i+1) th frame image transmitted by a sensor of a vehicle;
based on the sensitive information coordinates of the ith frame image, determining the sensitive information position of the (i+1) th frame image, and performing desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
2. The method of claim 1, wherein the method further comprises:
transmitting the desensitization image corresponding to the i+1st frame image to the software system, so that the software system identifies the sensitive information coordinates of the i+1st frame image based on the desensitization image corresponding to the i+1st frame image;
and receiving the sensitive information coordinates of the (i+1) th frame image sent by the software system.
3. The method according to claim 1 or 2, wherein the determining the sensitive information position of the i+1st frame image based on the sensitive information coordinates of the i+1st frame image, and performing a desensitization process on the information at the sensitive information position of the i+1st frame image, to obtain a desensitized image corresponding to the i+1st frame image, includes:
the following desensitization treatment steps are performed: counting the number of lines and pixel point information of the received (i+1) th frame image; determining whether the sensitive information position of the (i+1) th frame image is reached or not based on the line number and the pixel point information; and if the sensitive information position of the (i+1) th frame image is reached, carrying out desensitization treatment on the information at the sensitive information position of the (i+1) th frame image.
4. The method according to claim 3, wherein the determining the sensitive information position of the i+1st frame image based on the sensitive information coordinates of the i+1st frame image, and performing a desensitization process on the information at the sensitive information position of the i+1st frame image, to obtain a desensitized image corresponding to the i+1st frame image, further includes:
if the sensitive information position of the (i+1) th frame image is not reached, or the information at the sensitive information position of the (i+1) th frame image is subjected to desensitization treatment, whether the (i+1) th frame image is transmitted is determined; and if the transmission of the (i+1) th frame image is completed, obtaining a desensitization image corresponding to the (i+1) th frame image.
5. The method according to claim 4, wherein the determining the sensitive information position of the i+1st frame image based on the sensitive information coordinates of the i+1st frame image, and performing a desensitization process on the information at the sensitive information position of the i+1st frame image, to obtain a desensitized image corresponding to the i+1st frame image, further includes:
and if the (i+1) th frame image is not transmitted, returning to the desensitization processing step.
6. An image desensitizing apparatus comprising:
the coordinate receiving module is configured to receive sensitive information coordinates of an ith frame of image sent by the software system, wherein i is a positive integer;
an image receiving module configured to receive an i+1st frame image transmitted by a sensor of the vehicle;
the image desensitization module is configured to determine the sensitive information position of the (i+1) th frame image based on the sensitive information coordinates of the (i+1) th frame image, and perform desensitization processing on the information at the sensitive information position of the (i+1) th frame image to obtain a desensitized image corresponding to the (i+1) th frame image.
7. The apparatus of claim 6, wherein the apparatus further comprises:
an image transmission module configured to transmit a desensitized image corresponding to the i+1st frame image to the software system, so that the software system identifies sensitive information coordinates of the i+1st frame image based on the desensitized image corresponding to the i+1st frame image; and
the coordinate receiving module is further configured to:
and receiving the sensitive information coordinates of the (i+1) th frame image sent by the software system.
8. The apparatus of claim 6 or 7, wherein the image desensitizing module is further configured to:
the following desensitization treatment steps are performed: counting the number of lines and pixel point information of the received (i+1) th frame image; determining whether the sensitive information position of the (i+1) th frame image is reached or not based on the line number and the pixel point information; and if the sensitive information position of the (i+1) th frame image is reached, carrying out desensitization treatment on the information at the sensitive information position of the (i+1) th frame image.
9. The apparatus of claim 8, wherein the image desensitizing module is further configured to:
if the sensitive information position of the (i+1) th frame image is not reached, or the information at the sensitive information position of the (i+1) th frame image is subjected to desensitization treatment, whether the (i+1) th frame image is transmitted is determined; and if the transmission of the (i+1) th frame image is completed, obtaining a desensitization image corresponding to the (i+1) th frame image.
10. The apparatus of claim 9, wherein the image desensitizing module is further configured to:
and if the (i+1) th frame image is not transmitted, returning to the desensitization processing step.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311508634.3A CN117556438A (en) | 2023-11-14 | 2023-11-14 | Image desensitizing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311508634.3A CN117556438A (en) | 2023-11-14 | 2023-11-14 | Image desensitizing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117556438A true CN117556438A (en) | 2024-02-13 |
Family
ID=89819762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311508634.3A Pending CN117556438A (en) | 2023-11-14 | 2023-11-14 | Image desensitizing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117556438A (en) |
-
2023
- 2023-11-14 CN CN202311508634.3A patent/CN117556438A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220035733A1 (en) | Method and apparatus for checking automatic driving algorithm, related device and storage medium | |
| CN113011323B (en) | Method for acquiring traffic state, related device, road side equipment and cloud control platform | |
| CN113704116A (en) | Data processing method, device, electronic equipment and medium for automatic driving vehicle | |
| CN109878512A (en) | Automatic Pilot control method, device, equipment and computer readable storage medium | |
| CN112863187B (en) | Detection method of perception model, electronic equipment, road side equipment and cloud control platform | |
| CN113378834B (en) | Object detection method, device, apparatus, storage medium, and program product | |
| CN113392794A (en) | Vehicle over-line identification method and device, electronic equipment and storage medium | |
| JP2023038164A (en) | Obstacle detection method, device, automatic driving vehicle, apparatus, and storage medium | |
| CN115147831A (en) | Training method and device of three-dimensional target detection model | |
| CN113391627A (en) | Unmanned vehicle driving mode switching method and device, vehicle and cloud server | |
| CN113052047A (en) | Traffic incident detection method, road side equipment, cloud control platform and system | |
| CN114429631B (en) | Three-dimensional object detection method, device, equipment and storage medium | |
| CN115861755A (en) | Feature fusion method and device, electronic equipment and automatic driving vehicle | |
| CN117556438A (en) | Image desensitizing method and device | |
| CN113344121B (en) | Method for training a sign classification model and sign classification | |
| CN115891868A (en) | Fault detection method, device, electronic apparatus, and medium for autonomous vehicle | |
| CN113869147A (en) | Target detection method and device | |
| CN113591569A (en) | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium | |
| CN114120651B (en) | Method, apparatus, device, medium and product for testing perceived target number | |
| CN114596708B (en) | Intelligent scheduling system, method, apparatus and computer program product | |
| CN113963322B (en) | Detection model training method and device and electronic equipment | |
| CN113177077B (en) | Abnormal event determination method and device for automatic driving and electronic equipment | |
| CN115049895B (en) | Image attribute identification method, attribute identification model training method and device | |
| CN113591709B (en) | Motion recognition method, apparatus, device, medium, and product | |
| CN114407916B (en) | Vehicle control and model training method and device, vehicle, equipment and storage medium |
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 |