CN114419566A - Picture processing method and device - Google Patents
Picture processing method and device Download PDFInfo
- Publication number
- CN114419566A CN114419566A CN202111631909.3A CN202111631909A CN114419566A CN 114419566 A CN114419566 A CN 114419566A CN 202111631909 A CN202111631909 A CN 202111631909A CN 114419566 A CN114419566 A CN 114419566A
- Authority
- CN
- China
- Prior art keywords
- target
- desensitization
- model
- picture data
- processing
- 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
Images
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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Bioethics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for processing pictures, wherein the method comprises the following steps: acquiring target picture data acquired by a vehicle; determining a target model frame aiming at the target picture data from a plurality of preset model frames, and determining a target inference model from a plurality of inference models under the target model frame; and calling the target reasoning model to perform desensitization processing on the target picture data. According to the embodiment of the invention, desensitization of the picture by different inference models compatible with different model frames is realized, desensitization requirements of different pictures can be met, and expansibility and adaptability are improved.
Description
Technical Field
The present invention relates to the field of image technologies, and in particular, to a method and an apparatus for processing an image.
Background
In the field of intelligent automobiles, particularly in the aspect of automatic driving, pictures of public areas, other vehicles, pedestrians and the like can be shot by a vehicle-mounted camera in the driving process of a vehicle, and sensitive information can be involved in the pictures, but in the prior art, desensitization of the sensitive information is usually limited to a certain fixed mode, and different picture desensitization requirements are difficult to meet.
Disclosure of Invention
In view of the above, it is proposed to provide a method and apparatus for picture processing that overcomes or at least partially solves the above problems, comprising:
a method of picture processing, the method comprising:
acquiring target picture data acquired by a vehicle;
determining a target model frame aiming at target picture data from a plurality of preset model frames, and determining a target inference model from a plurality of inference models under the target model frame;
and calling a target reasoning model, and desensitizing the target picture data.
Optionally, invoking a target inference model, and performing desensitization processing on the target picture data, including:
calling a target reasoning model, and determining a target picture area in target picture data; the picture characteristics of the target picture area are matched with the target inference model;
and calling a target desensitization mask module to perform desensitization processing on the target image area.
Optionally, invoking a target desensitization mask module to perform desensitization processing on the target image region, including:
determining a masking degree for the target image region;
and calling a target desensitization mask module, and performing desensitization treatment on the target image area according to the mask degree.
Optionally, invoking a target desensitization mask module to perform desensitization processing on the target image region, including:
determining a mask shape for the target image region;
and calling a target desensitization mask module, and performing desensitization treatment on the target image area according to the mask shape.
Optionally, before invoking the target desensitization mask module to perform desensitization processing on the target image region, the method further includes:
a target desensitization mask module is determined from a plurality of desensitization modules under the target inference model.
Optionally, acquiring target picture data acquired by a vehicle includes:
acquiring a plurality of picture data including target image data acquired by a vehicle;
and calling a load balancing module to distribute the plurality of picture data to the plurality of graphics processors.
Optionally, the target picture data is picture data acquired by the vehicle in the automatic driving process.
An apparatus for picture processing, the apparatus comprising:
the target picture data acquisition module is used for acquiring target picture data acquired by a vehicle;
the target reasoning model determining module is used for determining a target model frame aiming at the target picture data from a plurality of preset model frames and determining a target reasoning model from a plurality of reasoning models under the target model frame;
and the desensitization processing module is used for calling the target reasoning model and carrying out desensitization processing on the target picture data.
An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of picture processing as described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of picture processing as set forth above.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, the target model frame aiming at the target picture data is determined from a plurality of preset model frames by acquiring the target picture data acquired by the vehicle, the target inference model is determined from a plurality of inference models under the target model frame, and the target inference model is called to desensitize the target picture data, so that the desensitization of the picture by different inference models compatible with different model frames is realized, the desensitization requirements of different pictures can be met, and the expansibility and the adaptability are improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating steps of a method for processing pictures according to an embodiment of the present invention;
FIG. 2 is a diagram of a system architecture according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of another method for processing pictures according to an embodiment of the present invention;
fig. 4 is a block diagram of an apparatus for processing pictures according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart illustrating steps of a method for Processing a picture according to an embodiment of the present invention is shown, where the method can be applied to a GPU (Graphics Processing Unit).
Specifically, the method can comprise the following steps:
The target picture data can be picture data acquired by the vehicle in the automatic driving process.
During the driving process of the vehicle, such as during the automatic driving process, pictures of the surrounding environment, such as pictures shot for public areas, other vehicles, pedestrians and the like, can be acquired through the vehicle-mounted camera.
In an embodiment of the present invention, step 101 may include:
acquiring a plurality of picture data including target image data acquired by a vehicle; and calling a load balancing module to distribute the plurality of picture data to the plurality of graphics processors.
In some scenarios, a system may be deployed with multiple GPUs, such as GPU _1, GPU _2, and GPU _3.... GPU _ N in fig. 2, and then multiple image data including target image data may be distributed to multiple graphics processors through a front load balancing module, so that the graphics processors obtain the target image data, and thus, a target of effectively controlling and distributing traffic may be achieved.
And 102, determining a target model frame aiming at the target picture data from a plurality of preset model frames, and determining a target inference model from a plurality of inference models under the target model frame.
As an example, the plurality of inference models may include any one or more of:
the system comprises a face-specific reasoning model, a license plate-specific reasoning model, a road sign-specific reasoning model and a traffic light-specific reasoning model.
In practical application, for different pictures, the inference model under different model frames can be adopted for desensitization, and then a plurality of model frames can be preset, so that the types of the inference model frames are effectively expanded, and as shown in fig. 2, the inference model frame analysis layer can comprise a tensrflow frame and a PyTorch frame.
Aiming at each model frame, a plurality of inference models which are used for being called by users can be arranged, the types of the inference models are effectively expanded, and as shown in figure 2, an inference model interface analysis layer can call model files of face inference, license plate inference and road sign inference through an inference model interface.
For the target picture data, a target model frame suitable for the target picture data can be determined from a plurality of model frames, and a target inference model suitable for the target picture data can be determined from a plurality of inference models under the target model frame. Specifically, as shown in fig. 2, the target model framework and the target inference model may be selected by configuring the parsing layer to parse the received input parameters.
And 103, calling a target reasoning model, and desensitizing the target picture data.
After the target inference model is determined, the target inference model can be adopted to perform desensitization processing on target picture data, such as face fuzzification processing on pictures, license plate fuzzification processing in pictures and the like.
In an embodiment of the present invention, step 103 may include:
substep 11, calling a target reasoning model and determining a target picture region in the target picture data; and matching the picture characteristics of the target picture area with the target inference model.
In a specific implementation, the target inference model may have one or more than one, and the different inference models may be for processing different types of picture data, such as an inference model for a human face being responsible for processing a human face region and an inference model for a license plate being responsible for processing a license plate region.
After invoking the target inference model, the target inference model may determine a target picture region matching the target inference model from the target picture data.
And a substep 12 of calling a target desensitization mask module and carrying out desensitization processing on the target image area.
As an example, the desensitization mask module may include any one or more of:
the desensitization mask module adopts fuzzification, the desensitization mask module adopts pixelation and the desensitization mask module adopts graying.
Due to the fact that different desensitization modes exist, different desensitization mask modules can be set according to the different desensitization modes, for example, as shown in fig. 2, an analytic layer of the desensitization mask module can include fuzzification, pixelation and graying desensitization mask modules, a target desensitization mask module can be determined from the desensitization mask modules, and then the target desensitization mask module can be called to perform desensitization processing on a target image area.
In an embodiment of the present invention, the substep 12 may include:
determining a masking degree for the target image region; and calling a target desensitization mask module, and performing desensitization treatment on the target image area according to the mask degree.
In specific implementation, desensitization of different contents can be performed to different degrees, and then the mask degree for the target image region can be determined, so that desensitization processing can be performed on the target image region by calling a target desensitization mask module, and the mask degree is used for controlling the desensitization degree.
In an embodiment of the present invention, the substep 12 may include:
determining a mask shape for the target image region; and calling a target desensitization mask module, and performing desensitization treatment on the target image area according to the mask shape.
In specific implementation, desensitization patterns of different shapes can be adopted for covering different contents, so that the mask shape for the target image area can be determined, then a target desensitization mask module can be called to perform desensitization processing on the target image area, and the mask shape is adopted to control the shape of the desensitization pattern.
In an embodiment of the present invention, before step 103, the method may further include:
a target desensitization mask module is determined from a plurality of desensitization modules under the target inference model.
In a particular implementation, since there are multiple desensitization modules, a target desensitization mask module for the target picture data may be predetermined.
In an example, a target model framework, a target inference model, a target desensitization masking module, a masking degree for the target picture data may be determined by input parameters received in the configuration parsing.
The parameters shown below:
in the embodiment of the invention, the target model frame aiming at the target picture data is determined from a plurality of preset model frames by acquiring the target picture data acquired by the vehicle, the target inference model is determined from a plurality of inference models under the target model frame, and the target inference model is called to desensitize the target picture data, so that the desensitization of the picture by different inference models compatible with different model frames is realized, the desensitization requirements of different pictures can be met, and the expansibility and the adaptability are improved.
And moreover, the automatic driving image real-time data desensitization is accelerated and enriched by setting different module frames, different inference models and different desensitization mask modules, a multistage layered adaptation mode is realized, and the inference model frames, the inference model types and the desensitization mask types are effectively expanded.
Referring to fig. 3, a flowchart illustrating steps of another method for processing a picture according to an embodiment of the present invention is shown, which may specifically include the following steps:
During the driving process of the vehicle, such as during the automatic driving process, pictures of the surrounding environment, such as pictures shot for public areas, other vehicles, pedestrians and the like, can be acquired through the vehicle-mounted camera.
In some scenarios, a system may be deployed with multiple GPUs, such as GPU _1, GPU _2, and GPU _3.... GPU _ N in fig. 2, and then multiple image data including target image data may be distributed to multiple graphics processors through a front load balancing module, so that the graphics processors obtain the target image data, and thus, a target of effectively controlling and distributing traffic may be achieved.
As an example, the plurality of inference models may include any one or more of:
the system comprises a face-specific reasoning model, a license plate-specific reasoning model, a road sign-specific reasoning model and a traffic light-specific reasoning model.
In practical application, for different pictures, the inference model under different model frames can be adopted for desensitization, and then a plurality of model frames can be preset, so that the types of the inference model frames are effectively expanded, and as shown in fig. 2, the inference model frame analysis layer can comprise a tensrflow frame and a PyTorch frame.
Aiming at each model frame, a plurality of inference models which are used for being called by users can be arranged, the types of the inference models are effectively expanded, and as shown in figure 2, an inference model interface analysis layer can call model files of face inference, license plate inference and road sign inference through an inference model interface.
For the target picture data, a target model frame suitable for the target picture data can be determined from a plurality of model frames, and a target inference model suitable for the target picture data can be determined from a plurality of inference models under the target model frame. Specifically, as shown in fig. 2, the target model framework and the target inference model may be selected by configuring the parsing layer to parse the received input parameters.
In a specific implementation, the target inference model may have one or more than one, and the different inference models may be for processing different types of picture data, for example, an inference model for a face is responsible for processing a face region, and an inference model for a license plate is responsible for processing a license plate region.
After invoking the target inference model, the target inference model may determine a target picture region matching the target inference model from the target picture data.
In a particular implementation, since there are multiple desensitization modules, a target desensitization mask module for the target picture data may be predetermined.
And step 306, calling a target desensitization mask module to perform desensitization treatment on the target image area.
Due to the fact that different desensitization modes exist, different desensitization mask modules can be set according to the different desensitization modes, for example, as shown in fig. 2, an analytic layer of the desensitization mask module can include fuzzification, pixelation and graying desensitization mask modules, a target desensitization mask module can be determined from the desensitization mask modules, and then the target desensitization mask module can be called to perform desensitization processing on a target image area.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 4, a schematic structural diagram of an image processing apparatus according to an embodiment of the present invention is shown, which may specifically include the following modules:
and a target picture data obtaining module 401, configured to obtain target picture data collected by a vehicle.
And a target inference model determining module 402, configured to determine a target model frame for the target picture data from a plurality of preset model frames, and determine a target inference model from a plurality of inference models under the target model frame.
And a desensitization processing module 403, configured to invoke the target inference model, and perform desensitization processing on the target picture data.
In an embodiment of the present invention, the desensitization processing module 403 may include:
the target picture area determining submodule is used for calling a target reasoning model and determining a target picture area in the target picture data; and matching the picture characteristics of the target picture area with the target inference model.
And the target image area desensitization sub-module is used for calling a target desensitization mask module to perform desensitization processing on the target image area.
In an embodiment of the present invention, the target picture region desensitization sub-module may include:
a masking degree determining unit for determining a masking degree for the target image area.
And the desensitization according to mask degree unit is used for calling a target desensitization mask module and desensitizing the target image area according to the mask degree.
In an embodiment of the present invention, the target picture region desensitization sub-module may include:
a mask shape determining unit for determining a mask shape for the target image area.
And the desensitization according to mask shape unit is used for calling a target desensitization mask module and desensitizing the target image area according to the mask shape.
In an embodiment of the present invention, the method may further include:
and the target desensitization mask module determining module is used for determining the target desensitization mask module from a plurality of desensitization modules under the target inference model.
In an embodiment of the present invention, the target picture data obtaining module 401 may include:
and the picture number acquisition submodule is used for acquiring a plurality of pieces of picture data which are acquired by the vehicle and contain the target image data.
And the picture number distribution submodule is used for calling the load balancing module and distributing the plurality of picture data to the plurality of graphics processors.
In an embodiment of the present invention, the target picture data is picture data collected during automatic driving of the vehicle.
An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the method for processing the picture as above is implemented.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for processing the picture is implemented.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and the apparatus for processing pictures provided above are introduced in detail, and a specific example is applied in this document to illustrate the principle and the implementation of the present invention, and the above description of the embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for picture processing, the method comprising:
acquiring target picture data acquired by a vehicle;
determining a target model frame aiming at the target picture data from a plurality of preset model frames, and determining a target inference model from a plurality of inference models under the target model frame;
and calling the target reasoning model to perform desensitization processing on the target picture data.
2. The method of claim 1, wherein invoking the target inference model to desensitize the target picture data comprises:
calling the target reasoning model to determine a target picture area in the target picture data; wherein the picture characteristics of the target picture region are matched with the target inference model;
and calling a target desensitization mask module to perform desensitization processing on the target image area.
3. The method of claim 2, wherein invoking a target desensitization mask module to desensitize the target image region comprises:
determining a degree of masking for the target image region;
and calling the target desensitization mask module, and performing desensitization processing on the target image area according to the mask degree.
4. The method of claim 2, wherein invoking a target desensitization mask module to desensitize the target image region comprises:
determining a mask shape for the target image region;
and calling the target desensitization mask module, and performing desensitization processing on the target image area according to the mask shape.
5. The method according to claim 2, before the invoking of the target desensitization mask module to desensitize the target image region, further comprising:
determining a target desensitization mask module from a plurality of desensitization modules under the target inference model.
6. The method according to any one of claims 1-5, wherein the obtaining of the target picture data collected by the vehicle comprises:
acquiring a plurality of picture data including target image data acquired by a vehicle;
and calling a load balancing module to distribute the plurality of picture data to a plurality of graphics processors.
7. The method of claim 1, wherein the target picture data is picture data collected by the vehicle during autonomous driving.
8. An apparatus for picture processing, the apparatus comprising:
the target picture data acquisition module is used for acquiring target picture data acquired by a vehicle;
the target reasoning model determining module is used for determining a target model frame aiming at the target picture data from a plurality of preset model frames and determining a target reasoning model from a plurality of reasoning models under the target model frame;
and the desensitization processing module is used for calling the target reasoning model and carrying out desensitization processing on the target picture data.
9. An electronic device comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing the method of picture processing according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of picture processing according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111631909.3A CN114419566A (en) | 2021-12-28 | 2021-12-28 | Picture processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111631909.3A CN114419566A (en) | 2021-12-28 | 2021-12-28 | Picture processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114419566A true CN114419566A (en) | 2022-04-29 |
Family
ID=81269110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111631909.3A Pending CN114419566A (en) | 2021-12-28 | 2021-12-28 | Picture processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114419566A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115987424A (en) * | 2022-11-29 | 2023-04-18 | 重庆长安汽车股份有限公司 | Information protection method, device, equipment and medium based on wireless communication |
-
2021
- 2021-12-28 CN CN202111631909.3A patent/CN114419566A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115987424A (en) * | 2022-11-29 | 2023-04-18 | 重庆长安汽车股份有限公司 | Information protection method, device, equipment and medium based on wireless communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114117740A (en) | Simulation test scene generation method and device based on automatic driving | |
| CN110077416B (en) | Decision tree-based driver intention analysis method and system | |
| CN110135356A (en) | The detection method and device of parking offense, electronic equipment, computer-readable medium | |
| CN112874519B (en) | Control method and system for adaptive cruise, storage medium and electronic device | |
| CN114419566A (en) | Picture processing method and device | |
| CN109624985B (en) | Early warning method and device for preventing fatigue driving | |
| CN113608881B (en) | Memory allocation method, device, equipment, readable storage medium and program product | |
| CN115082752A (en) | Target detection model training method, device, equipment and medium based on weak supervision | |
| CN111931644A (en) | Method, system and equipment for detecting number of people on vehicle and readable storage medium | |
| CN109747644A (en) | Vehicle tracking anti-collision early warning method, device, controller, system and vehicle | |
| CN116204726B (en) | Data processing method, device and equipment based on multi-mode model | |
| DE112017003712T5 (en) | Vehicle notification system and computer program | |
| CN108960160B (en) | Method and device for predicting structured state quantity based on unstructured prediction model | |
| CN111216723B (en) | Vehicle travel control method, device and storage medium | |
| CN114724011B (en) | Behavior determination method and device, storage medium and electronic device | |
| CN115952531A (en) | Image processing method, device, equipment and storage medium | |
| CN112989924B (en) | Target detection method, target detection device and terminal equipment | |
| CN115019242A (en) | Abnormal event detection method and device for traffic scene and processing equipment | |
| CN115098245A (en) | Task processing method, electronic device, storage medium, and computer program product | |
| EP3172719B1 (en) | Hardware-independent display of graphic effects | |
| CN109410582B (en) | Traffic condition analysis method and terminal equipment | |
| CN111310660A (en) | Target detection false alarm suppression method and device for ADAS scene | |
| CN113954853B (en) | Driving strategy processing method and device | |
| CN114495061B (en) | Road traffic sign board identification method and device | |
| CN113220819B (en) | Vehicle display method, device, electronic 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 |