CN111723775A - Image processing method, image processing device, computer equipment and computer readable storage medium - Google Patents
Image processing method, image processing device, computer equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111723775A CN111723775A CN202010630765.9A CN202010630765A CN111723775A CN 111723775 A CN111723775 A CN 111723775A CN 202010630765 A CN202010630765 A CN 202010630765A CN 111723775 A CN111723775 A CN 111723775A
- Authority
- CN
- China
- Prior art keywords
- image
- window
- vehicle
- traffic
- license plate
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application relates to an image processing method, an image processing device, a computer device and a computer readable storage medium. The image processing method comprises the following steps: acquiring a traffic image to be processed; acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image; recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image. By the method, when whether sight line shielding exists on the window of the target vehicle is identified from the traffic image, the identification efficiency and the identification accuracy can be improved.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, a computer device, and a computer-readable storage medium.
Background
With the improvement of living standard, motor vehicles have gradually become one of the most common transportation means in daily trips of people, and bring safe driving problems which cannot be ignored.
At present, many motor vehicles can paste ornaments or spray coating advertisement on the door window, also have and hang or the placing object article in the front and back window within range of driver's cabin, and these all belong to the situation of violation of the rule, because when the driver need see through the door window and look over the road conditions, these all can cause the interference to driver's sight, seriously influence safe driving. In the field of intelligent transportation, after a monitoring device collects traffic images, the collected traffic images are manually checked to determine whether vehicles in the traffic images have the condition of violation of the anti-intersection rule.
However, the above manual inspection method has low recognition efficiency and recognition accuracy for the offending vehicle.
Disclosure of Invention
In view of the above, it is necessary to provide an image processing method, an image processing apparatus, a computer device, and a computer-readable storage medium, which can improve the recognition efficiency and the recognition accuracy for recognizing an illegal vehicle with a view-line blockage in a window from a traffic image.
In a first aspect, an embodiment of the present application provides an image processing method, where the image processing method includes:
acquiring a traffic image to be processed;
acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
In one embodiment, the acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image includes:
acquiring a vehicle image from the traffic image; the vehicle image includes the target vehicle;
acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image;
and intercepting a region corresponding to the license plate position information from the traffic image as the license plate image, and intercepting a region corresponding to the window position information from the traffic image as the window image.
In one embodiment, the acquiring the vehicle image from the traffic image includes:
adopting a target detection model to acquire vehicle position information of the target vehicle in the traffic image;
and intercepting an area corresponding to the vehicle position information from the traffic image as the vehicle image.
In one embodiment, the obtaining license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image includes:
inputting the vehicle image into a segmentation network model to obtain the category information of each pixel point in the vehicle image;
determining the license plate position information according to the position coordinates of a plurality of pixel points of the license plate in the traffic image by the category information;
and determining the position information of the vehicle window according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image according to the category information.
In one embodiment, the vehicle window position information includes a vehicle window position frame, and the intercepting a region corresponding to the vehicle window position information from the traffic image as the vehicle window image includes:
carrying out background processing on pixel points of which the category information is not the car window in an area corresponding to the traffic image and the car window position frame;
and intercepting an area corresponding to the car window position frame from the traffic image after background processing to be used as the car window image.
In one embodiment, the recognizing the license plate image and classifying the vehicle window image includes:
inputting the license plate image into a recognition model to obtain a recognition result of the license plate image;
and inputting the vehicle window image into a classification model to obtain a classification result of the vehicle window image.
In one embodiment, the window image includes a front window image, a rear window image, and a side window image, and the inputting the window image into a classification model to obtain a classification result of the window image includes:
inputting the front window image, the rear window image and the side window image into the classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image;
and if the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image are not shielded by sight lines, determining that the classification result of the window images is not shielded by sight lines.
In a second aspect, an embodiment of the present application provides an image processing apparatus, including:
the first acquisition module is used for acquiring a traffic image to be processed;
the second acquisition module is used for acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
the processing module is used for identifying the license plate image, classifying the vehicle window image and associating the identification result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
In a third aspect, an embodiment of the present application provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method according to the first aspect when executing the computer program.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the method according to the first aspect as described above.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
obtaining a traffic image to be processed; acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image; identifying the license plate image, classifying the vehicle window image, and associating the identification result of the license plate image with the classification result of the vehicle window image, wherein the classification result is used for indicating that the vehicle window image has sight line occlusion or does not have sight line occlusion; therefore, the computer equipment identifies the license plate images acquired from the traffic images, classifies the window images, and associates the identification results of the license plate images with the classification results of the window images to determine whether sight shielding exists in the window of the target vehicle, so that the problems of low identification efficiency and low identification accuracy caused by the fact that in the traditional technology, the collected traffic images are manually checked to determine whether sight shielding exists in the window of the vehicle in the traffic images are solved. According to the method and the device, the recognition efficiency and the recognition accuracy of the illegal vehicle with the sight line sheltered from the window can be improved.
Drawings
FIG. 1 is a flowchart illustrating an image processing method according to an embodiment;
FIG. 2 is a flowchart illustrating an image processing method according to another embodiment;
fig. 3 is a schematic diagram illustrating a refinement step of step S210 in an image processing method according to another embodiment;
fig. 4 is a schematic diagram illustrating a refinement step of step S220 in an image processing method according to another embodiment;
fig. 5 is a schematic diagram illustrating a refinement step of step S230 in an image processing method according to another embodiment;
FIG. 6 is a flowchart illustrating an image processing method according to another embodiment;
FIG. 7 is a flowchart illustrating an image processing method according to another embodiment;
fig. 8 is a block diagram of an image processing apparatus according to an embodiment;
FIG. 9 is an internal block diagram of a computer device provided in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image processing method, the image processing device, the computer equipment and the computer readable storage medium aim at solving the technical problems of low recognition efficiency and low recognition accuracy caused by the fact that whether sight line shielding exists in a vehicle window of a vehicle in a traffic image is determined by manually checking an acquired traffic image in the traditional technology. The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. The following specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
In the image processing method provided in the embodiments of the present application, the execution subject may be an image processing apparatus, and the image processing apparatus may be implemented as part or all of a computer device by software, hardware, or a combination of software and hardware. In the following method embodiments, the execution subject is a computer device, which may be a server; it is understood that the image processing method provided by the following method embodiments may also be applied to a terminal, and may also be applied to a system including the terminal and a server, and is implemented through interaction between the terminal and the server.
Referring to fig. 1, a flowchart of an image processing method according to an embodiment of the present application is shown. The embodiment relates to a specific implementation process for identifying whether sight line occlusion exists in a window of a target vehicle from a traffic image. As shown in fig. 1, the image processing method of the present embodiment may include the steps of:
and step S100, acquiring a traffic image to be processed.
In this embodiment, the traffic image may be acquired by an image acquisition device of the traffic monitoring system, and the computer device acquires the traffic image to be processed.
In other embodiments, the computer device may also acquire a surveillance video from the traffic surveillance system, and extract a traffic image to be processed from the acquired surveillance video; alternatively, the traffic image to be processed may be stored locally by the computer device, and is not limited in particular.
And S200, acquiring a license plate image and a window image corresponding to the target vehicle in the traffic image according to the traffic image.
And the computer equipment acquires a license plate image and a window image corresponding to the target vehicle in the traffic image according to the traffic image to be processed. In this embodiment, the traffic image may include a plurality of vehicles, and the target vehicle may be any one of the plurality of vehicles.
As an embodiment, the computer device may employ a target detection algorithm to locate a vehicle position of a target vehicle in the traffic image, and acquire a vehicle image including the target vehicle according to vehicle position information obtained by the locating; in other embodiments, the computer device may further obtain feature key points of the target vehicle in the traffic image, such as feature key points of wheels, roofs, car faces, car tails, and the like, through a feature extraction algorithm, and obtain contour position information of the target vehicle according to position coordinates of the feature key points, so as to obtain a vehicle image including the target vehicle, and the like, which is not limited herein.
Further, the computer device can perform segmentation processing on the vehicle image by adopting a segmentation algorithm to obtain a license plate image and a vehicle window image after segmentation; in other embodiments, the computer device may further perform pixel clustering on the vehicle image, the obtained clustering result may include a plurality of color blocks, the computer device compares each color block with a preset standard license plate color block and a standard vehicle window color block, and if the comparison is passed, determines the corresponding color block region as a region corresponding to the license plate image or a region corresponding to the vehicle window image, and so on.
And step S300, recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image.
And the classification result is used for indicating that the sight line occlusion exists or does not exist in the vehicle window image.
And after the computer equipment acquires the license plate image and the window image corresponding to the target vehicle, character recognition is carried out on the license plate image to obtain license plate information of the target vehicle.
Further, the computer device classifies the vehicle window images through the trained classification model to obtain a classification result, the classification result can be a probability value of the vehicle window images with sight shielding, the computer device can set a threshold, if the probability value obtained through classification is higher than the threshold, the classification result is determined that the vehicle window images have sight shielding, otherwise, the classification result is determined that the vehicle window images do not have sight shielding. And the computer equipment associates the license plate information of the target vehicle with the classification result of the window image to finish the automatic identification processing of whether the window of the target vehicle is shielded by sight.
In other embodiments, the computer device may further perform similarity calculation on the vehicle window image and a reference vehicle window image not including the sight line occlusion, and determine that the vehicle window image has no sight line occlusion if the similarity of the vehicle window image and the reference vehicle window image is higher than a set similarity threshold, or otherwise determine that the vehicle window image has the sight line occlusion. The similarity between the acquired vehicle window image and the reference vehicle window image may be obtained by comparing color histograms of the two, and this embodiment is not limited in this respect.
The embodiment obtains the traffic image to be processed; acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image; identifying the license plate image, classifying the vehicle window image, associating the identification result of the license plate image with the classification result of the vehicle window image, wherein the classification result is used for indicating that the vehicle window image has sight line occlusion or does not have sight line occlusion; therefore, the computer equipment identifies the license plate images acquired from the traffic images, classifies the window images, and associates the identification results of the license plate images with the classification results of the window images to determine whether sight shielding exists in the window of the target vehicle, so that the problems of low identification efficiency and low identification accuracy caused by the fact that in the traditional technology, the collected traffic images are manually checked to determine whether sight shielding exists in the window of the vehicle in the traffic images are solved. According to the embodiment, the recognition efficiency and the recognition accuracy rate of the illegal vehicle with the sight line sheltered in the vehicle window recognition can be improved.
Fig. 2 is a schematic flowchart of an image processing method according to another embodiment. On the basis of the embodiment shown in fig. 1, as shown in fig. 2, in the present embodiment, the step S200 includes a step S210, a step S220, and a step S230, specifically:
step S210, a vehicle image is acquired from the traffic image.
Wherein the vehicle image includes the target vehicle.
In this embodiment, after the computer device acquires the traffic image to be processed, a vehicle image including the target vehicle is acquired from the traffic image.
As an embodiment, the computer device may use an ssd (single Shot multi box detector) target detection algorithm to locate the vehicle position of the target vehicle in the traffic image. In other embodiments, the computer device may further use a Yolo target detection algorithm to locate the vehicle position of the target vehicle in the traffic image, and specifically may use Yolo v3 to locate the target vehicle.
After the computer equipment acquires the vehicle position information of the target vehicle in the traffic image through positioning, the vehicle image comprising the target vehicle is intercepted from the traffic image according to the vehicle position information.
And step S220, acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image.
In this embodiment, the computer device obtains the license plate position information and the window position information of the target vehicle from the traffic image according to the vehicle image. As the license plate and the window belong to different categories, as an implementation manner, the computer device may use a PSPNet (Scene parsing Network) to segment the vehicle image, so as to obtain category information of each pixel point in the vehicle image. The license plate position information of the target vehicle is the traffic image, and the category information corresponding to the target vehicle is the area where the plurality of pixel points of the license plate are located. The window position information of the target vehicle is the traffic image, and the category information corresponding to the target vehicle is the area where the multiple pixel points of the window are located.
In other embodiments, the computer device may further perform segmentation processing on the vehicle image by using a deplab segmentation algorithm or a CCNet segmentation algorithm to obtain category information of each pixel point in the vehicle image, and the like, which is not limited in this embodiment.
And step S230, intercepting a region corresponding to the license plate position information from the traffic image as a license plate image, and intercepting a region corresponding to the window position information from the traffic image as a window image.
The computer device intercepts a region corresponding to the license plate position information from the traffic image as a license plate image, intercepts a region corresponding to the window position information from the traffic image as a window image, and accordingly obtains a license plate image and a window image corresponding to a target vehicle in the traffic image; the computer equipment identifies the license plate images, classifies the vehicle window images and associates the identification results of the license plate images with the classification results of the vehicle window images, so that whether sight line shielding exists in the vehicle windows of the target vehicles in the traffic images or not is automatically identified through a deep learning algorithm, the identification accuracy is improved, the reusability of the deep learning algorithm is good, and the labor cost is greatly saved.
On the basis of the embodiment shown in fig. 2, referring to fig. 3, fig. 3 is a schematic diagram of a thinning step of step S210 in an image processing method provided by another embodiment. As shown in fig. 3, step S210 of the present embodiment includes step S211 and step S212, specifically:
and step S211, acquiring vehicle position information of the target vehicle in the traffic image by adopting the target detection model.
In this embodiment, the computer device obtains vehicle position information of the target vehicle in the traffic image by using the target detection model.
As an implementation manner, the target detection model may be obtained by training a training sample acquired from an actual application scene by a computer device based on a target detection algorithm framework, so that the detection accuracy of the target detection model in actual application can be improved; the target detection model can also be obtained by adopting a public data set by computer equipment, carrying out model pre-training based on a target detection algorithm framework, and then carrying out fine tuning on the pre-trained model by adopting a training sample collected from an actual application scene, so that the training speed of the target detection model can be improved.
In this embodiment, the computer device inputs the traffic image into the trained target detection model, and obtains vehicle position information of the target vehicle in the traffic image, where the vehicle position information may be coordinates of a vehicle position frame. It should be noted that the computer device may obtain vehicle position information respectively corresponding to each vehicle in the traffic image through the target detection model, that is, each vehicle corresponds to one piece of vehicle position information.
In step S212, an area corresponding to the vehicle position information is cut out from the traffic image as a vehicle image.
The computer device intercepts an area corresponding to the vehicle position information from the traffic image as a vehicle image. Specifically, after acquiring vehicle position information, namely vehicle position frame coordinates, of a target vehicle in a traffic image, the computer device intercepts an area corresponding to the vehicle position frame coordinates in the traffic image as a vehicle image.
In the embodiment, the computer device acquires the vehicle position information of the target vehicle in the traffic image by adopting a target detection model based on practical application scene training, and then intercepts an area corresponding to the vehicle position information from the traffic image as a vehicle image, wherein the vehicle image comprises the target vehicle; therefore, the positioning accuracy of the target vehicle in the traffic image is improved, and the identification accuracy of whether the sight line is shielded in the window of the target vehicle is further improved.
On the basis of the embodiment shown in fig. 2, referring to fig. 4, fig. 4 is a schematic diagram of a refining step of step S220 in an image processing method according to another embodiment. As shown in fig. 4, step S220 of the present embodiment includes step S221, step S222, and step S223, specifically:
step S221, inputting the vehicle image into the segmentation network model to obtain the category information of each pixel point in the vehicle image.
As an implementation manner, the segmentation network model may be obtained by training a training sample acquired from an actual application scene by a computer device based on a segmentation algorithm framework, so that the segmentation accuracy of the segmentation network model in actual application can be improved; the segmentation network model can also be obtained by adopting a public data set by computer equipment, performing model pre-training based on a segmentation algorithm frame and then performing fine tuning on the pre-trained model by adopting training samples collected from an actual application scene, so that the training speed of the segmentation network model can be improved.
And the computer equipment inputs the vehicle image into the segmentation network model to obtain the category information of each pixel point in the vehicle image. In this embodiment, the computer device performs pixel-level segmentation on the vehicle image through the segmentation network model to obtain category information of each pixel point in the vehicle image, where the category information may be a license plate, a window, a door, a car light, and the like.
Step S222, determining license plate position information according to the position coordinates of the plurality of pixel points of the license plate in the traffic image based on the category information.
In this embodiment, the computer device determines the license plate position information according to the category information as the position coordinates of the plurality of pixel points of the license plate in the traffic image. Specifically, since the vehicle image is captured from the traffic image, the position coordinates of each pixel point in the vehicle image in the traffic image are known, and after the computer device acquires the category information of each pixel point in the vehicle image, the category information is screened to be a plurality of pixel points of the license plate, so that the position coordinates of the plurality of pixel points of the license plate in the traffic image can be determined as the category information.
Further, the computer device obtains a first minimum external rectangular frame according to the position coordinates of the plurality of pixel points of the license plate in the traffic image by using the category information, wherein the category information is that the plurality of pixel points of the license plate are all located in the first minimum external rectangular frame, and the first minimum external rectangular frame is the license plate position information.
And step S223, determining the position information of the vehicle window according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image by the category information.
Specifically, after the computer device obtains the category information of each pixel point in the vehicle image, the category information is screened to be a plurality of pixel points of the vehicle window, and then the position coordinates of the plurality of pixel points of the vehicle window in the traffic image can be determined as the category information.
The computer equipment obtains a second minimum external rectangular frame according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image by the category information, the plurality of pixel points of the vehicle window are all located in the second minimum external rectangular frame by the category information, and the second minimum external rectangular frame is the vehicle window position information.
The computer equipment intercepts the area corresponding to the first minimum external rectangular frame from the traffic image to serve as the license plate image, intercepts the area corresponding to the second minimum external rectangular frame from the traffic image to serve as the vehicle window image, then identifies the license plate image, classifies the vehicle window image, and associates the identification result of the license plate image with the classification result of the vehicle window image, so that automatic identification of vehicle window sight line shielding based on a depth learning algorithm is realized, and the identification efficiency and the identification accuracy are improved.
On the basis of the embodiment shown in fig. 2, referring to fig. 5, fig. 5 is a schematic diagram illustrating a refinement step of step S230 in an image processing method according to another embodiment. As shown in fig. 5, step S230 of the present embodiment includes step S231, step S232, and step S233, specifically:
and step S231, performing background processing on the pixel points of which the category information is not the car window in the area corresponding to the traffic image and the car window position frame.
In this embodiment, the vehicle window position information includes a vehicle window position frame, and the computer device performs background processing on the pixel points of which the category information is not the vehicle window in the area where the traffic image corresponds to the vehicle window position frame.
Specifically, after obtaining a vehicle image from the traffic image, the computer device inputs the vehicle image into the segmentation network model to obtain category information of each pixel point in the vehicle image, and determines vehicle window position information, namely a vehicle window position frame, according to the category information as position coordinates of a plurality of pixel points of a vehicle window in the traffic image, wherein the vehicle window position frame is a minimum circumscribed rectangular frame of the category information of the plurality of pixel points of the vehicle window.
The computer equipment carries out background processing on the pixel points of which the category information is not the car window in the area corresponding to the traffic image and the car window position frame, and specifically sets the pixel value of the pixel points of which the category information is not the car window to 0, so that the pixel points of which the category information is not the car window are prevented from being included in the car window position frame.
And step S232, intercepting an area corresponding to the window position frame from the traffic image after the background processing as a window image.
And the computer device intercepts the area corresponding to the window position frame from the traffic image after background processing to be used as a window image. It can be understood that the category information of a plurality of pixel points included in the intercepted window image is the window, so that the intercepting accuracy of the window image is improved, and the accuracy of the classification result of the window image is improved.
And step S233, intercepting an area corresponding to the license plate position information from the traffic image as a license plate image.
In this embodiment, after obtaining the category information of each pixel point in the vehicle image, the computer device screens a plurality of pixel points of which the category information is a license plate, and obtains the position coordinates of the plurality of pixel points of which the category information is the license plate in the traffic image. And the computer equipment acquires a corresponding minimum external rectangular frame, namely license plate position information, according to the position coordinates of the plurality of pixel points of the license plate in the traffic image by using the category information, and then intercepts an area corresponding to the license plate position information from the traffic image to serve as the license plate image. Because the actual shape of the license plate is rectangular instead of irregular polygon, the computer device directly intercepts the area corresponding to the license plate position information from the traffic image as the license plate image, thereby ensuring the accuracy of intercepting the license plate image and reducing the data processing amount of the computer device.
Fig. 6 is a flowchart illustrating an image processing method according to another embodiment. On the basis of the embodiment shown in fig. 1, as shown in fig. 6, in the present embodiment, the step S300 includes a step S310, a step S320, and a step S330, specifically:
step S310, inputting the license plate image into the recognition model to obtain the recognition result of the license plate image.
In this embodiment, the computer device identifies the license plate image through a pre-trained identification model to obtain license plate information corresponding to the target vehicle. In this embodiment, the recognition model may be implemented by a network structure of LSTM (Long Short-term memory network) + CNN (Convolutional Neural Networks) + CTC network.
And step S320, inputting the vehicle window image into the classification model to obtain a classification result of the vehicle window image.
In this embodiment, when the computer device trains the classification model, the collected training samples may include various sample window images and sample shielding window images corresponding to the sample window images, respectively, where the sample window images are images without view shielding, the sample shielding window images are images corresponding to the sample window images with view shielding, and the computer device trains the classification model according to the sample window images and the corresponding sample shielding window images.
When the method is applied, the computer equipment inputs the acquired car window images into the classification model, and classification results of the car window images with or without sight line occlusion can be obtained.
And step S330, associating the recognition result of the license plate image with the classification result of the vehicle window image.
The computer equipment correlates the recognition result of the license plate image with the classification result of the vehicle window image to obtain an image processing result of the vehicle window with or without sight shielding, so that automatic recognition of whether sight shielding exists in the vehicle window of the vehicle in the traffic image is realized, and the intelligent level of recognition is improved.
Fig. 7 is a flowchart illustrating an image processing method according to another embodiment. On the basis of the embodiment shown in fig. 6, as shown in fig. 7, in the present embodiment, the step S320 includes a step S321 and a step S322, specifically:
step S321, inputting the front window image, the rear window image and the side window image into a classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image.
In this embodiment, the window image includes a front window image, a rear window image, and a side window image.
And the computer equipment acquires a license plate image, a front window image, a rear window image and a side window image corresponding to the target vehicle in the traffic image according to the traffic image. And the computer equipment inputs the front window image, the rear window image and the side window image into the classification model to obtain the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image.
In step S322, if there is no sight line occlusion in all of the classification result of the front window image, the classification result of the rear window image, and the classification result of the side window image, it is determined that there is no sight line occlusion in the classification result of the window images.
If the classification result of the front window image is that no sight line shielding exists, the classification result of the rear window image is that no sight line shielding exists, and the classification result of the side window image is that no sight line shielding exists, the computer device determines that the classification result of the window image of the target vehicle is that no sight line shielding exists, namely, the target vehicle does not have potential safety hazards of the window sight line, and the computer device associates the recognition result of the license plate image with the classification result of the window image.
If at least one classification result is that sight line shielding exists in the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image, the computer equipment determines that the classification result of the window image of the target vehicle is that sight line shielding exists, namely potential safety hazards of window lines of the window of the target vehicle such as spraying and shielding exist, and the computer equipment associates the recognition result of the license plate image with the classification result of the window image. Therefore, the safety hidden danger of the sight line of the window of the target vehicle in the traffic image is quickly and accurately checked, the recognition result of the license plate image is associated with the classification result of the window image, the driver of the target vehicle is favorably reminded or pursued, and the traffic accident is favorably avoided.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in the above-described flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided an image processing apparatus including:
the first acquisition module 10 is used for acquiring a traffic image to be processed;
the second obtaining module 20 is configured to obtain a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
the processing module 30 is configured to identify the license plate image, classify the window image, and associate the identification result of the license plate image with the classification result of the window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
Optionally, the second obtaining module 20 includes:
the image acquisition sub-module is used for acquiring a vehicle image from the traffic image; the vehicle image includes the target vehicle;
the position acquisition submodule is used for acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image;
and the intercepting submodule is used for intercepting the area corresponding to the license plate position information from the traffic image as the license plate image and intercepting the area corresponding to the window position information from the traffic image as the window image.
Optionally, the image acquisition sub-module includes:
the position acquisition unit is used for acquiring vehicle position information of the target vehicle in the traffic image by adopting a target detection model;
a first cutout unit that cuts out an area corresponding to the vehicle position information from the traffic image as the vehicle image.
Optionally, the position obtaining sub-module includes:
the classification acquisition unit is used for inputting the vehicle image into a segmentation network model to obtain classification information of each pixel point in the vehicle image;
the first position acquisition unit is used for determining the position information of the license plate according to the position coordinates of a plurality of pixel points of the license plate in the traffic image according to the category information;
and the second position acquisition unit is used for determining the position information of the car window according to the position coordinates of the plurality of pixel points of the car window in the traffic image according to the category information.
Optionally, the window position information includes a window position frame, and the intercepting submodule includes:
the preprocessing unit is used for carrying out background processing on pixel points of which the category information is not the car window in the area corresponding to the traffic image and the car window position frame;
and the second intercepting unit is used for intercepting the area corresponding to the car window position frame from the traffic image after background processing to be used as the car window image.
Optionally, the processing module 30 includes:
the recognition submodule is used for inputting the license plate image into a recognition model to obtain a recognition result of the license plate image;
and the classification submodule is used for inputting the vehicle window image into a classification model to obtain a classification result of the vehicle window image.
Optionally, the window image includes a front window image, a rear window image and a side window image, and the classification sub-module includes:
the classification unit is used for inputting the front window image, the rear window image and the side window image into the classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image;
and the determining unit is used for determining that the classification result of the vehicle window images is not shielded by the sight if the classification result of the front vehicle window images, the classification result of the rear vehicle window images and the classification result of the side vehicle window images are not shielded by the sight.
The image processing apparatus provided in this embodiment may implement the above-mentioned embodiment of the image processing method, and the implementation principle and the technical effect are similar, which are not described herein again. For specific limitations of the image processing apparatus, reference may be made to the above limitations of the image processing method, which are not described herein again. The respective modules in the image processing apparatus described above may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, there is also provided a computer device as shown in fig. 9, which may be a server. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing image processing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image processing method.
Those skilled in the art will appreciate that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computing device to which the present application is applied, and in particular that the computing device may include more or less components than those shown, or combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a traffic image to be processed;
acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a vehicle image from the traffic image; the vehicle image includes the target vehicle;
acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image;
and intercepting a region corresponding to the license plate position information from the traffic image as the license plate image, and intercepting a region corresponding to the window position information from the traffic image as the window image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
adopting a target detection model to acquire vehicle position information of the target vehicle in the traffic image;
and intercepting an area corresponding to the vehicle position information from the traffic image as the vehicle image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
inputting the vehicle image into a segmentation network model to obtain the category information of each pixel point in the vehicle image;
determining the license plate position information according to the position coordinates of a plurality of pixel points of the license plate in the traffic image by the category information;
and determining the position information of the vehicle window according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image according to the category information.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out background processing on pixel points of which the category information is not the car window in an area corresponding to the traffic image and the car window position frame;
and intercepting an area corresponding to the car window position frame from the traffic image after background processing to be used as the car window image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
inputting the license plate image into a recognition model to obtain a recognition result of the license plate image;
and inputting the vehicle window image into a classification model to obtain a classification result of the vehicle window image.
In one embodiment, the window images include a front window image, a rear window image and a side window image, and the processor when executing the computer program further implements the following steps:
inputting the front window image, the rear window image and the side window image into the classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image;
and if the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image are not shielded by sight lines, determining that the classification result of the window images is not shielded by sight lines.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Ramb microsecond direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a traffic image to be processed;
acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a vehicle image from the traffic image; the vehicle image includes the target vehicle;
acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image;
and intercepting a region corresponding to the license plate position information from the traffic image as the license plate image, and intercepting a region corresponding to the window position information from the traffic image as the window image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
adopting a target detection model to acquire vehicle position information of the target vehicle in the traffic image;
and intercepting an area corresponding to the vehicle position information from the traffic image as the vehicle image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting the vehicle image into a segmentation network model to obtain the category information of each pixel point in the vehicle image;
determining the license plate position information according to the position coordinates of a plurality of pixel points of the license plate in the traffic image by the category information;
and determining the position information of the vehicle window according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image according to the category information.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out background processing on pixel points of which the category information is not the car window in an area corresponding to the traffic image and the car window position frame;
and intercepting an area corresponding to the car window position frame from the traffic image after background processing to be used as the car window image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting the license plate image into a recognition model to obtain a recognition result of the license plate image;
and inputting the vehicle window image into a classification model to obtain a classification result of the vehicle window image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting the front window image, the rear window image and the side window image into the classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image;
and if the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image are not shielded by sight lines, determining that the classification result of the window images is not shielded by sight lines.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An image processing method, characterized in that the method comprises:
acquiring a traffic image to be processed;
acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
recognizing the license plate image, classifying the vehicle window image, and associating the recognition result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
2. The method according to claim 1, wherein the obtaining of the license plate image and the window image corresponding to the target vehicle in the traffic image according to the traffic image comprises:
acquiring a vehicle image from the traffic image; the vehicle image includes the target vehicle;
acquiring license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image;
and intercepting a region corresponding to the license plate position information from the traffic image as the license plate image, and intercepting a region corresponding to the window position information from the traffic image as the window image.
3. The method of claim 2, wherein the obtaining the vehicle image from the traffic image comprises:
adopting a target detection model to acquire vehicle position information of the target vehicle in the traffic image;
and intercepting an area corresponding to the vehicle position information from the traffic image as the vehicle image.
4. The method according to claim 2, wherein the obtaining license plate position information and window position information of the target vehicle in the traffic image according to the vehicle image comprises:
inputting the vehicle image into a segmentation network model to obtain the category information of each pixel point in the vehicle image;
determining the license plate position information according to the position coordinates of a plurality of pixel points of the license plate in the traffic image by the category information;
and determining the position information of the vehicle window according to the position coordinates of the plurality of pixel points of the vehicle window in the traffic image according to the category information.
5. The method according to claim 2, wherein the window position information comprises a window position frame, and the step of cutting out an area corresponding to the window position information from the traffic image as the window image comprises the steps of:
carrying out background processing on pixel points of which the category information is not the car window in an area corresponding to the traffic image and the car window position frame;
and intercepting an area corresponding to the car window position frame from the traffic image after background processing to be used as the car window image.
6. The method of claim 1, wherein the identifying the license plate image and the classifying the window image comprises:
inputting the license plate image into a recognition model to obtain a recognition result of the license plate image;
and inputting the vehicle window image into a classification model to obtain a classification result of the vehicle window image.
7. The method according to claim 6, wherein the window images comprise a front window image, a rear window image and a side window image, and the step of inputting the window images into a classification model to obtain a classification result of the window images comprises the steps of:
inputting the front window image, the rear window image and the side window image into the classification model to obtain a classification result of the front window image, a classification result of the rear window image and a classification result of the side window image;
and if the classification result of the front window image, the classification result of the rear window image and the classification result of the side window image are not shielded by sight lines, determining that the classification result of the window images is not shielded by sight lines.
8. An image processing apparatus, characterized in that the apparatus comprises:
the first acquisition module is used for acquiring a traffic image to be processed;
the second acquisition module is used for acquiring a license plate image and a window image corresponding to a target vehicle in the traffic image according to the traffic image;
the processing module is used for identifying the license plate image, classifying the vehicle window image and associating the identification result of the license plate image with the classification result of the vehicle window image; and the classification result is used for representing that the sight line occlusion exists or does not exist in the vehicle window image.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010630765.9A CN111723775A (en) | 2020-07-03 | 2020-07-03 | Image processing method, image processing device, computer equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010630765.9A CN111723775A (en) | 2020-07-03 | 2020-07-03 | Image processing method, image processing device, computer equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111723775A true CN111723775A (en) | 2020-09-29 |
Family
ID=72571427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010630765.9A Pending CN111723775A (en) | 2020-07-03 | 2020-07-03 | Image processing method, image processing device, computer equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723775A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106469309A (en) * | 2015-08-14 | 2017-03-01 | 杭州海康威视数字技术股份有限公司 | The method and apparatus of vehicle monitoring, processor, image capture device |
| CN107016362A (en) * | 2017-03-30 | 2017-08-04 | 华中科技大学 | Vehicle based on vehicle front windshield sticking sign recognition methods and system again |
| CN107292222A (en) * | 2016-04-01 | 2017-10-24 | 杭州海康威视数字技术股份有限公司 | A kind of vehicle peccancy detection method and device |
| CN107993451A (en) * | 2018-01-30 | 2018-05-04 | 张爱兰 | System for detecting regulation violation based on Plate searching |
| CN108491797A (en) * | 2018-03-22 | 2018-09-04 | 河北省科学院应用数学研究所 | A kind of vehicle image precise search method based on big data |
| CN109214336A (en) * | 2018-09-05 | 2019-01-15 | 高新兴科技集团股份有限公司 | A kind of vehicle window marker detection method and device |
| CN109885718A (en) * | 2019-02-28 | 2019-06-14 | 江南大学 | A kind of suspected vehicles search method based on the detection of depth traffic allowance |
| CN110503831A (en) * | 2019-08-28 | 2019-11-26 | 上海眼控科技股份有限公司 | A kind of method and apparatus identifying driver's illegal activities |
| CN110533925A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Processing method, device, computer equipment and the storage medium of vehicle illegal video |
-
2020
- 2020-07-03 CN CN202010630765.9A patent/CN111723775A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106469309A (en) * | 2015-08-14 | 2017-03-01 | 杭州海康威视数字技术股份有限公司 | The method and apparatus of vehicle monitoring, processor, image capture device |
| CN107292222A (en) * | 2016-04-01 | 2017-10-24 | 杭州海康威视数字技术股份有限公司 | A kind of vehicle peccancy detection method and device |
| CN107016362A (en) * | 2017-03-30 | 2017-08-04 | 华中科技大学 | Vehicle based on vehicle front windshield sticking sign recognition methods and system again |
| CN107993451A (en) * | 2018-01-30 | 2018-05-04 | 张爱兰 | System for detecting regulation violation based on Plate searching |
| CN108491797A (en) * | 2018-03-22 | 2018-09-04 | 河北省科学院应用数学研究所 | A kind of vehicle image precise search method based on big data |
| CN109214336A (en) * | 2018-09-05 | 2019-01-15 | 高新兴科技集团股份有限公司 | A kind of vehicle window marker detection method and device |
| CN109885718A (en) * | 2019-02-28 | 2019-06-14 | 江南大学 | A kind of suspected vehicles search method based on the detection of depth traffic allowance |
| CN110503831A (en) * | 2019-08-28 | 2019-11-26 | 上海眼控科技股份有限公司 | A kind of method and apparatus identifying driver's illegal activities |
| CN110533925A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Processing method, device, computer equipment and the storage medium of vehicle illegal video |
Non-Patent Citations (1)
| Title |
|---|
| 杜森: "车辆再识别研究" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9317752B2 (en) | Method for detecting large size and passenger vehicles from fixed cameras | |
| CN110188807B (en) | Tunnel pedestrian target detection method based on cascading super-resolution network and improved Faster R-CNN | |
| US9082038B2 (en) | Dram c adjustment of automatic license plate recognition processing based on vehicle class information | |
| CN108073928B (en) | License plate recognition method and device | |
| CN108268867B (en) | License plate positioning method and device | |
| CN106295541A (en) | Vehicle type recognition method and system | |
| CN111553214B (en) | Method and system for detecting smoking behavior of driver | |
| CN103093201B (en) | Vehicle-logo location recognition methods and system | |
| CN107886034B (en) | Driving reminding method and device and vehicle | |
| CN111539317A (en) | Vehicle illegal driving detection method and device, computer equipment and storage medium | |
| DE112017001951T5 (en) | APPARATUS AND METHOD FOR OBJECT DETECTION FOR AN INPUT IMAGE FOR A VEHICLE | |
| CN113971821A (en) | Driver information determination method and device, terminal device and storage medium | |
| CN111753592A (en) | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium | |
| CN111191482A (en) | Brake lamp identification method and device and electronic equipment | |
| CN112115800A (en) | Vehicle combination recognition system and method based on deep learning target detection | |
| CN113408364B (en) | Temporary license plate recognition method, system, device and storage medium | |
| CN114332783A (en) | Vehicle refitting detection method and device, electronic equipment and storage medium | |
| CN113283303A (en) | License plate recognition method and device | |
| CN108873097B (en) | Safety detection method and device for parking of vehicle carrying plate in unmanned parking garage | |
| CN111598054A (en) | Vehicle detection method and device, computer equipment and storage medium | |
| CN111723775A (en) | Image processing method, image processing device, computer equipment and computer readable storage medium | |
| CN115797880A (en) | Method and device for determining driving behavior, storage medium and electronic device | |
| CN116030663A (en) | Vehicle early warning method and device, electronic equipment and storage medium | |
| CN116434548A (en) | Vehicle data analysis method and device and electronic equipment | |
| CN113326831B (en) | Method and device for screening traffic violation data, 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 |