WO2021027890A1

Movatterモバイル変換

Info

Publication number: WO2021027890A1
Application number: PCT/CN2020/108967
Authority: WO
Inventors: 李欢
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2019-08-15
Filing date: 2020-08-13
Publication date: 2021-02-18
Anticipated expiration: 2022-02-15
Also published as: CN112396076B; CN112396076A

Abstract

The present application relates to the technical field of neural network training, and disclosed are a license plate image generation method and device, and a computer storage medium. The method comprises: constructing a three-dimensional model of a virtual license plate, and determining license plate surface attribute information of the virtual license plate, so as to generate a license plate image for the virtual license plate. Therefore, when a training sample for a neural network model for license plate recognition is determined, a license plate image can be directly generated by means of the embodiments of the present application according to actual demands, without collecting a real license plate by means of a camera to obtain the license plate image, thereby improving the efficiency of obtaining the license plate image. In addition, because the virtual license plate is a license plate simulated according to actual demands, license plate images corresponding to different types of virtual license plates may be generated by means of the embodiments of the present application, thereby improving the diversity of license plate images in the training sample, and thus improving the recognition accuracy of the neural network model trained on the basis of the training sample.

Description

Translated fromChinese

车牌图像生成方法、装置及计算机存储介质Method and device for generating license plate image and computer storage medium

本申请实施例要求于2019年08月15日提交的申请号为201910755413.3、发明名称为“车牌图像生成方法、装置及计算机存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请实施例中。The embodiments of this application require the priority of the Chinese patent application filed on August 15, 2019 with the application number 201910755413.3 and the invention title "License Plate Image Generation Method, Apparatus and Computer Storage Medium", the entire content of which is incorporated herein by reference Application examples.

技术领域Technical field

本申请实施例涉及神经网络训练技术领域，特别涉及一种车牌生成方法、装置及计算机存储介质。The embodiments of the present application relate to the technical field of neural network training, and in particular to a method, device and computer storage medium for generating a license plate.

背景技术Background technique

随着大数据技术的发展，可以通过神经网络进行车牌识别。在通过神经网络实现车牌识别之前，需要先使用训练样本对初始化的神经网络进行训练。训练样本包括多个车牌图像，每个车牌图像中标注有用于指示车牌标识的标签。车牌标识包括多个字符。With the development of big data technology, license plate recognition can be performed through neural networks. Before realizing license plate recognition through neural network, it is necessary to use training samples to train the initialized neural network. The training sample includes multiple license plate images, and each license plate image is marked with a label indicating the license plate identification. The license plate identification includes multiple characters.

相关技术中，可以先获取摄像机针对车牌采集的图像。对于采集的每个图像，通过人工方式标注用于指示车牌标识的标签，将标注后的各个图像称为车牌图像。将标注后的各个车牌图像作为训练样本对初始化的神经网络进行训练。也即是，相关技术是通过摄像机采集和人工标注的方式来生成用于训练的车牌图像。In related technologies, the image collected by the camera for the license plate can be acquired first. For each image collected, the label used to indicate the license plate identification is manually marked, and each of the marked images is called the license plate image. Use each annotated license plate image as a training sample to train the initialized neural network. That is, the related technology is to generate license plate images for training through camera collection and manual labeling.

由于摄像机针对车牌采集的图像中覆盖的车牌的种类有限，导致上述生成用于训练的车牌图像的种类比较单一，不利于对神经网络模型进行训练。Due to the limited types of license plates covered in images collected by the camera for license plates, the types of license plate images generated for training are relatively single, which is not conducive to training the neural network model.

发明内容Summary of the invention

本申请实施例提供了一种车牌图像生成方法、装置及计算机存储介质，可以提高根据生成的车牌图像训练的神经网路模型的识别精度。所述技术方案如下：The embodiments of the present application provide a method, a device and a computer storage medium for generating a license plate image, which can improve the recognition accuracy of a neural network model trained on the generated license plate image. The technical solution is as follows:

一方面，提供了一种车牌图像生成方法，所述方法包括：In one aspect, a method for generating a license plate image is provided, and the method includes:

构建虚拟车牌的三维模型，所述虚拟车牌为根据需求模拟出的车牌；Constructing a three-dimensional model of a virtual license plate, where the virtual license plate is a simulated license plate according to requirements;

确定所述虚拟车牌的车牌表面属性信息；Determining the surface attribute information of the virtual license plate;

根据所述车牌表面属性信息和所述三维模型，生成针对所述虚拟车牌的车牌图像。According to the surface attribute information of the license plate and the three-dimensional model, a license plate image for the virtual license plate is generated.

可选地，所述构建虚拟车牌的三维模型，包括：Optionally, the constructing a three-dimensional model of a virtual license plate includes:

确定所述虚拟车牌的边框的形状；Determining the shape of the frame of the virtual license plate;

确定所述虚拟车牌的底色；Determine the background color of the virtual license plate;

确定所述虚拟车牌上用于指示车牌标识的多个字符以及所述多个字符的排列顺序；Determining a plurality of characters on the virtual license plate for indicating a license plate identifier and an arrangement order of the plurality of characters;

根据所述边框的形状、所述底色、所述多个字符以及所述多个字符的排列顺序，生成所述虚拟车牌的三维模型。A three-dimensional model of the virtual license plate is generated according to the shape of the frame, the background color, the plurality of characters, and the sequence of the plurality of characters.

可选地，所述确定所述虚拟车牌的边框的形状，包括：Optionally, the determining the shape of the frame of the virtual license plate includes:

根据所述虚拟车牌的形变情况，确定所述虚拟车牌的边框的形状。Determine the shape of the frame of the virtual license plate according to the deformation of the virtual license plate.

可选地，所述根据所述边框的形状、所述底色、所述多个字符以及所述多个字符的排列顺序，生成所述虚拟车牌的三维模型，包括：Optionally, the generating a three-dimensional model of the virtual license plate according to the shape of the frame, the background color, the plurality of characters, and the arrangement sequence of the plurality of characters includes:

根据所述边框的形状、所述底色、所述多个字符以及所述多个字符的排列顺序，生成所述虚拟车牌的理论三维视图；Generating a theoretical three-dimensional view of the virtual license plate according to the shape of the frame, the background color, the plurality of characters, and the sequence of the plurality of characters;

根据所述虚拟车牌的折痕情况，对所述虚拟车牌的理论三维视图进行调整，得到所述虚拟车牌的三维模型。According to the crease condition of the virtual license plate, the theoretical three-dimensional view of the virtual license plate is adjusted to obtain the three-dimensional model of the virtual license plate.

可选地，所述车牌表面属性信息至少包括以下属性信息中的一种或多种：Optionally, the surface attribute information of the license plate includes at least one or more of the following attribute information:

所述虚拟车牌的金属属性；The metallic properties of the virtual license plate;

所述虚拟车牌的漫反射属性；The diffuse reflection attribute of the virtual license plate;

所述虚拟车牌的平整度；The flatness of the virtual license plate;

所述虚拟车牌的镜面反射属性；The specular reflection attribute of the virtual license plate;

所述虚拟车牌上的灰尘情况；The dust condition on the virtual license plate;

所述虚拟车牌上的污渍情况、覆盖情况以及遮挡情况。The stain condition, coverage condition and occlusion condition on the virtual license plate.

可选地，所述根据所述车牌属性信息和所述三维模型，生成针对所述虚拟车牌的车牌图像，包括：Optionally, the generating a license plate image for the virtual license plate according to the license plate attribute information and the three-dimensional model includes:

确定虚拟拍摄场景的拍摄参数；Determine the shooting parameters of the virtual shooting scene;

根据所述拍摄参数、所述车牌属性信息和所述三维模型，生成针对所述虚拟车牌的虚拟照片；Generating a virtual photo for the virtual license plate according to the shooting parameters, the license plate attribute information and the three-dimensional model;

对所述虚拟照片进行后处理，得到所述车牌图像。Perform post-processing on the virtual photo to obtain the license plate image.

可选地，所述虚拟拍摄场景的拍摄参数至少包括以下参数中的一种或多种：Optionally, the shooting parameters of the virtual shooting scene include at least one or more of the following parameters:

所述虚拟拍摄场景中的灯光的颜色、所述灯光的亮度、所述虚拟拍摄场景中虚拟摄像机的曝光参数、在所述虚拟拍摄场景中所述虚拟摄像机和所述虚拟车牌的位置。The color of the light in the virtual shooting scene, the brightness of the light, the exposure parameter of the virtual camera in the virtual shooting scene, the positions of the virtual camera and the virtual license plate in the virtual shooting scene.

可选地，所述根据所述车牌属性信息和所述三维模型，生成针对所述虚拟车牌的车牌图像之后，还包括：Optionally, after generating the license plate image for the virtual license plate according to the license plate attribute information and the three-dimensional model, the method further includes:

在所述车牌图像中标注所述虚拟车牌上的车牌识别结果。Mark the license plate recognition result on the virtual license plate in the license plate image.

另一方面、提供了一种车牌图像生成装置，所述装置包括：In another aspect, there is provided a license plate image generating device, the device comprising:

构建模块，用于构建虚拟车牌的三维模型，所述虚拟车牌为根据需求模拟出的车牌；The construction module is used to construct a three-dimensional model of a virtual license plate, where the virtual license plate is a license plate simulated according to requirements;

确定模块，用于确定所述虚拟车牌的车牌表面属性信息；The determining module is used to determine the surface attribute information of the virtual license plate;

生成模块，用于根据所述车牌表面属性信息和所述三维模型，生成针对所述虚拟车牌的车牌图像。The generating module is used to generate a license plate image for the virtual license plate according to the surface attribute information of the license plate and the three-dimensional model.

可选地，所述构建模块，具体用于：Optionally, the building module is specifically used for:

可选地，所述构建模块，具体用于：根据所述虚拟车牌的形变情况，确定所述虚拟车牌的边框的形状。Optionally, the building module is specifically configured to determine the shape of the frame of the virtual license plate according to the deformation of the virtual license plate.

所述虚拟车牌的平整度；The flatness of the virtual license plate;

所述虚拟车牌镜面反射属性；The specular reflection attribute of the virtual license plate;

可选地，所述生成模块，具体用于：Optionally, the generating module is specifically used for:

可选地，所述装置还包括：Optionally, the device further includes:

标注模块，用于在所述车牌图像中标注所述虚拟车牌上的车牌识别结果。The marking module is used for marking the license plate recognition result on the virtual license plate in the license plate image.

处理器；processor;

用于存储处理器可执行指令的存储器；A memory for storing processor executable instructions;

其中，所述处理器被配置为执行上述任一方面提供的车牌图像的生成方法的步骤。Wherein, the processor is configured to execute the steps of the method for generating a license plate image provided by any one of the above aspects.

另一方面，提供了一种计算机可读存储介质，计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述任一方面提供的牌图像的生成方法的步骤。On the other hand, a computer-readable storage medium is provided, and instructions are stored in the computer-readable storage medium, which when run on a computer, cause the computer to execute the steps of the card image generation method provided in any one of the above aspects.

另一方面，提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述任一方面提供的牌图像的生成方法的步骤。On the other hand, a computer program product containing instructions is provided, which when running on a computer, causes the computer to execute the steps of the card image generation method provided by any of the above aspects.

本申请实施例提供的技术方案带来的有益效果至少包括：The beneficial effects brought by the technical solutions provided by the embodiments of the present application include at least:

在本申请实施例中，可以根据实际需求模拟虚拟车牌，然后构建虚拟车牌的三维模型，并确定虚拟车牌的车牌表面属性信息，以生成针对该虚拟车牌的车牌图像。因此，在确定针对用于车牌识别的神经网络模型的训练样本时，可以根据实际需求直接通过本申请实施例生成车牌图像，无需通过摄像机针对真实的车牌进行采集才能获取到车牌图像，提高了获取车牌图像的效率。另外，由于虚拟车牌是根据实际需求模拟的车牌，因此，可以通过本申请实施例生成不同类型的虚拟车牌对应的车牌图像，提高了训练样本中的车牌图像的多样性，从而提高了后续根据训练样本训练出的神经网络模型的识别精度。In the embodiment of the present application, a virtual license plate can be simulated according to actual needs, and then a three-dimensional model of the virtual license plate can be constructed, and the license plate surface attribute information of the virtual license plate can be determined to generate a license plate image for the virtual license plate. Therefore, when determining the training samples for the neural network model for license plate recognition, the license plate image can be directly generated through the embodiment of the application according to actual needs, and the license plate image can be obtained without the need for the camera to collect the real license plate, which improves the acquisition The efficiency of license plate images. In addition, since the virtual license plate is a license plate simulated according to actual needs, the license plate images corresponding to different types of virtual license plates can be generated through the embodiments of the present application, which improves the diversity of the license plate images in the training samples, thereby improving the subsequent training according to The recognition accuracy of the neural network model trained by the sample.

附图说明Description of the drawings

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained from these drawings without creative work.

图1是本申请实施例提供的一种车牌图像生成方法流程图。Fig. 1 is a flowchart of a method for generating a license plate image provided by an embodiment of the present application.

图2是本申请实施例提供的一种车牌图像生成装置框图。Fig. 2 is a block diagram of a device for generating a license plate image provided by an embodiment of the present application.

图3是本申请实施例提供的一种终端的结构示意图。FIG. 3 is a schematic structural diagram of a terminal provided by an embodiment of the present application.

具体实施方式detailed description

为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。In order to make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

在对本申请实施例进行解释说明之前，先对本申请实施例涉及的应用场景进行解释说明。车牌识别是指：对车牌图像中用于指示车牌标识的字符进行识别，以获取该车牌图像对应的车牌标识。车牌标识包括多个字符，该多个字符可以为数字、英文字母、汉字以及其他字符中的一种或多种。车牌标识也可以称为车牌号码。目前，通过神经网络技术可以实现快速的车牌识别。而在通过神经网络实现车牌识别的过程中，用于训练神经网络的训练样本的多样性直接影响训练后的神经网络的识别精确度。因此，需要获取大量的不同类型的训练样本，以提高训练后的神经网络模型的识别精确度。针对用于车牌识别的神经网络模型，训练样本是指多个车牌图像，每个车牌图像中标注有用于指示车牌标识的标签。本申请实施例通过的车牌图像生成方法就应用于获取针对用于车牌识别的神经网络模型的训练样本的场景中。Before explaining the embodiments of the present application, the application scenarios involved in the embodiments of the present application are first explained. License plate recognition refers to: recognizing the characters used to indicate the license plate mark in the license plate image to obtain the license plate mark corresponding to the license plate image. The license plate identification includes multiple characters, and the multiple characters may be one or more of numbers, English letters, Chinese characters, and other characters. The license plate identification can also be called the license plate number. At present, fast license plate recognition can be achieved through neural network technology. In the process of realizing license plate recognition through neural network, the diversity of training samples used to train neural network directly affects the recognition accuracy of neural network after training. Therefore, it is necessary to obtain a large number of different types of training samples to improve the recognition accuracy of the trained neural network model. For the neural network model used for license plate recognition, the training samples refer to multiple license plate images, and each license plate image is marked with a label indicating the license plate identification. The license plate image generation method adopted in the embodiment of the present application is applied to the scene of obtaining training samples for the neural network model for license plate recognition.

图1是本申请实施例提供的一种车牌图像生成方法流程图。如图1所示，该方法包括如下步骤：Fig. 1 is a flowchart of a method for generating a license plate image provided by an embodiment of the present application. As shown in Figure 1, the method includes the following steps:

步骤101：构建虚拟车牌的三维模型，虚拟车牌为根据需求模拟出的车牌。Step 101: Construct a three-dimensional model of a virtual license plate. The virtual license plate is a simulated license plate according to requirements.

本申请实施例可以根据实际需求模拟虚拟车牌，然后通过步骤101至步骤103生成针对该虚拟车牌的车牌图像。因此，在确定针对用于车牌识别的神经网络模型的训练样本时，可以根据实际需求直接通过步骤101至步骤103生成车牌图像，无需通过摄像机针对真实的车牌进行采集才能获取到车牌图像，提高了获取车牌图像的效率。另外，由于虚拟车牌是根据实际需求模拟的车牌，因此，可以通过步骤101至步骤103生成不同类型的虚拟车牌对应的车牌图像，提高了训练样本中的车牌图像的多样性，从而提高了后续根据训练样本训练出的神经网络模型的识别精度。The embodiment of the present application can simulate a virtual license plate according to actual needs, and then generate a license plate image for the virtual license plate throughstep 101 to step 103. Therefore, when determining the training samples for the neural network model for license plate recognition, the license plate image can be directly generated throughsteps 101 to 103 according to actual needs, and the license plate image can be obtained without the need for the camera to collect the real license plate. The efficiency of obtaining license plate images. In addition, since the virtual license plate is a license plate simulated according to actual needs, the license plate images corresponding to different types of virtual license plates can be generated throughsteps 101 to 103, which improves the diversity of license plate images in the training sample, thereby improving the subsequent basis The recognition accuracy of the neural network model trained by the training sample.

三维模型用于指示虚拟车牌在三维空间中的视图。在一种可能的实现方式中，步骤101具体可以为：确定虚拟车牌的边框框的形状；确定虚拟车牌的底色；确定虚拟车牌上用于指示车牌标识的多个字符以及多个字符的排列顺序；根据边框的形状、底色、多个字符以及多个字符的排列顺序，生成虚拟车牌的三维模型。The three-dimensional model is used to indicate the view of the virtual license plate in the three-dimensional space. In a possible implementation,step 101 may specifically be: determine the shape of the frame of the virtual license plate; determine the background color of the virtual license plate; determine the multiple characters and the arrangement of multiple characters on the virtual license plate for indicating the license plate identifier Sequence: According to the shape of the frame, the background color, multiple characters and the sequence of multiple characters, a three-dimensional model of the virtual license plate is generated.

虚拟车牌的边框的形状可以包括外框的形状，还可以包括内框的形状。其中，确定虚拟车牌的外框的形状的实现方式可以为：当前显示界面中显示有多个外框选项，每个外框选项指示一种外框形状。当检测到针对该多个外框选项中任一外框选项的选择操作时，基于该选择操作对应的外框选项确定该虚拟车牌的外框的形状。The shape of the frame of the virtual license plate may include the shape of the outer frame and may also include the shape of the inner frame. Wherein, the realization of determining the shape of the outer frame of the virtual license plate may be: a plurality of outer frame options are displayed in the current display interface, and each outer frame option indicates a kind of outer frame shape. When a selection operation for any one of the plurality of outer frame options is detected, the shape of the outer frame of the virtual license plate is determined based on the outer frame option corresponding to the selection operation.

选择操作可以由管理人员根据实际需求触发。也即是，上述虚拟车牌的外框的形状是根据实际需求确定的。比如，当前需要生成一种针对军用车牌的虚拟车牌的车牌图像，则可以从多个外框选项中选择与军用车牌对应的外框选项，以使确定虚拟车牌的外框的形状具有军用车牌的外框的形状。The selection operation can be triggered by the manager according to actual needs. That is, the shape of the outer frame of the virtual license plate is determined according to actual needs. For example, if it is currently necessary to generate a license plate image for a virtual license plate of a military license plate, you can select the frame option corresponding to the military license plate from a number of frame options, so that the shape of the frame of the virtual license plate is determined to have the shape of the military license plate. The shape of the frame.

另外，上述确定车牌的内框的形状、虚拟车牌的底色均可以参考上述确定虚拟车牌的外框的形状的实现方式，在此就不再一一展开阐述。In addition, the foregoing determination of the shape of the inner frame of the license plate and the background color of the virtual license plate can refer to the foregoing implementation of determining the shape of the outer frame of the virtual license plate, which will not be elaborated here.

另外，在确定虚拟车牌的边框的形状时，还可以考虑虚拟车牌的形变情况。该形变情况包括由于破损引起的形变情况、由于折叠引起的形变情况、由于褶皱扭曲引起的形变情况等等。比如，正常的车牌的外框的形状为一个矩形，当车牌出现破损时，该车牌的外框的某个角可能被磨损掉。此时，该车牌的外框的形状就不是一个矩形，可能为梯形。因此，在上述通过显示界面中显示的外框选项来确定外框的形状时，还可以在基于该选择操作对应的外框选项确定该虚拟车牌的外框的形状之后，根据虚拟车牌的形变情况，对确定的形状进行调整，将调整之后的形状作为虚拟车牌的外框的形状。In addition, when determining the shape of the frame of the virtual license plate, the deformation of the virtual license plate can also be considered. The deformation conditions include deformation due to breakage, deformation due to folding, deformation due to wrinkle distortion, and so on. For example, the shape of the frame of a normal license plate is a rectangle. When the license plate is damaged, a certain corner of the frame of the license plate may be worn away. At this time, the shape of the outer frame of the license plate is not a rectangle, but may be a trapezoid. Therefore, when the shape of the outer frame is determined by the outer frame options displayed on the display interface, the shape of the outer frame of the virtual license plate may be determined based on the outer frame options corresponding to the selection operation, and then according to the deformation of the virtual license plate , Adjust the determined shape, and use the adjusted shape as the shape of the outer frame of the virtual license plate.

上述用于指示车牌标识的多个字符可以包括中文省份简称、英文字母、数字等任意字符。多个字符的排列顺序是指多个字符排列之后能够指示一个车牌标识。比如，在应用本申请实施例时，可以根据需要生成的虚拟车牌的类型，来确定这多个字符的排列顺序。虚拟车牌的类型包括普通车牌、军用车牌以及其他特殊车牌等。The multiple characters used to indicate the license plate identification may include any characters such as Chinese province abbreviations, English letters, and numbers. The sequence of multiple characters means that a license plate mark can be indicated after multiple characters are arranged. For example, when applying the embodiment of the present application, the sequence of the multiple characters can be determined according to the type of virtual license plate to be generated. The types of virtual license plates include ordinary license plates, military license plates, and other special license plates.

在通过上述任一方式确定出边框的形状、底色、多个字符以及多个字符的排列顺序之后，便可根据边框的形状、底色、多个字符以及多个字符的排列顺序，生成虚拟车牌的三维模型。虚拟车牌的三维模型用于指示虚拟车牌的三维视图。After determining the frame shape, background color, multiple characters, and the sequence of multiple characters by any of the above methods, a virtual virtual machine can be generated according to the frame shape, background color, multiple characters, and the sequence of multiple characters. Three-dimensional model of license plate. The three-dimensional model of the virtual license plate is used to indicate the three-dimensional view of the virtual license plate.

另外，如果车牌出现折痕，那么该车牌相对于正常的车牌的三维视图将发生变化。因此，在本申请实施例中，在根据边框的形状、底色、以及多个字符的排列顺序，生成虚拟车牌的三维模型的实现方式可以为：根据边框的形状、底色、以及多个字符的排列顺序，生成虚拟车牌的理论三维视图；根据虚拟车牌的折痕情况，对虚拟车牌的理论三维视图进行调整，得到虚拟车牌的三维模型。也即是，最终得到的虚拟车牌的三维模型是可以指示车牌的存在折叠、褶皱或折痕情况的三维模型。In addition, if the license plate has a crease, the three-dimensional view of the license plate relative to the normal license plate will change. Therefore, in the embodiment of the present application, according to the shape of the frame, the background color, and the arrangement sequence of multiple characters, the realization of generating a three-dimensional model of the virtual license plate may be: according to the shape, background color, and multiple characters of the frame According to the crease of the virtual license plate, the theoretical three-dimensional view of the virtual license plate is adjusted to obtain the three-dimensional model of the virtual license plate. That is, the finally obtained three-dimensional model of the virtual license plate is a three-dimensional model that can indicate the presence of folding, wrinkles or creases of the license plate.

比如，根据边框的形状、底色、以及多个字符的排列顺序，生成的虚拟车牌的理论三维视图可能是一个扁平的正六面体。但是如果该虚拟车牌的某个角出现折痕，该正六面体对应的角也将发生弯曲，因此可以根据虚拟车牌的折痕情况，对虚拟车牌的理论三维视图进行调整，以使得到的虚拟车牌的三维模型符合实际的发生折痕的车牌的三维视图。For example, according to the shape of the frame, the background color, and the arrangement order of multiple characters, the theoretical three-dimensional view of the generated virtual license plate may be a flat regular hexahedron. But if there is a crease at a corner of the virtual license plate, the corresponding corner of the regular hexahedron will also be bent. Therefore, the theoretical three-dimensional view of the virtual license plate can be adjusted according to the crease of the virtual license plate to make the virtual license plate The 3D model corresponds to the actual 3D view of the crease license plate.

步骤102：确定虚拟车牌的车牌表面属性信息。Step 102: Determine the license plate surface attribute information of the virtual license plate.

基于步骤101可以确定出虚拟车牌的三维模型。但是对于具有同样三维模型的车牌，如果这些车牌的表明具有不同的属性，那么摄像机针对这些车牌采集的车牌图像极有可能是不同的。因此，在本申请实施例中，为了使得最终生成的虚拟车牌的车牌图像能够接近摄像机采集的车牌图像，在生成虚拟车牌的车牌图像时，还可以考虑虚拟车牌的车牌表面属性信息。Based onstep 101, a three-dimensional model of the virtual license plate can be determined. But for license plates with the same three-dimensional model, if the indications of these license plates have different attributes, the license plate images collected by the camera for these license plates are most likely to be different. Therefore, in the embodiment of the present application, in order to make the finally generated license plate image of the virtual license plate close to the license plate image collected by the camera, when generating the virtual license plate image, the license plate surface attribute information of the virtual license plate can also be considered.

在一种可能的实现方式中，车牌表面属性信息至少包括以下属性信息中的一种或多种：In a possible implementation, the surface attribute information of the license plate includes at least one or more of the following attribute information:

虚拟车牌的金属属性，金属属性用于指示虚拟车牌的金属属性，金属属性包括光线照射在虚拟车牌的表面时，虚拟车牌反射光线的强度，以及虚拟车牌反射出的光线形成的倒影的颜色。该金属属性还可以称为金属度。比如，金属度可以设置在0.0-1.0之间，金属度对应的数值越靠近1，表明虚拟车牌的表明的金属感越强，金属度对应的数值越靠近0，表明虚拟车牌的金属感越弱。The metal property of the virtual license plate is used to indicate the metal property of the virtual license plate. The metal property includes the intensity of the light reflected by the virtual license plate when light is irradiated on the surface of the virtual license plate, and the color of the reflection formed by the light reflected by the virtual license plate. This metallic property can also be referred to as metallicity. For example, the metallicity can be set between 0.0-1.0. The closer the value of the metallicity is to 1, the stronger the metallicity of the virtual license plate is. The closer the metallicity is to 0, the weaker the metallicity of the virtual license plate is. .

虚拟车牌的漫反射属性，漫反射属性用于指示光线照射在虚拟车牌的表面时，光线在虚拟车牌上形成漫反射的程度。该漫反射属性还可以称为粗糙度。The diffuse reflection property of the virtual license plate is used to indicate the degree of diffuse reflection of the light on the virtual license plate when the light illuminates the surface of the virtual license plate. This diffuse reflection property can also be referred to as roughness.

虚拟车牌的平整度。The flatness of the virtual license plate.

虚拟车牌的镜面反射属性，镜面反射属性用于指示光线投射在虚拟车牌的表面时，光线在虚拟车牌上形成镜面反射的程度。该漫反射属性还可以称为反射度。The specular reflection property of the virtual license plate, which is used to indicate the degree of specular reflection of the light on the virtual license plate when the light is projected on the surface of the virtual license plate. This diffuse reflection property can also be referred to as reflectance.

虚拟车牌上的灰尘情况。The dust on the virtual license plate.

虚拟车牌上的污渍情况、覆盖情况以及遮挡情况。The stain, coverage and occlusion on the virtual license plate.

上述车牌表面属性信息仅仅用于举例说明，在使用本申请实施例时，车牌表面属性信息可以包括任何能够影响摄像机采集的车牌图像的车牌表面因素，在此就不再一一举例说明。The above-mentioned license plate surface attribute information is only used for illustration. When using the embodiment of the present application, the license plate surface attribute information may include any license plate surface factors that can affect the license plate image collected by the camera, which will not be described here.

步骤103：根据车牌表面属性信息和三维模型，生成针对虚拟车牌的车牌图像。Step 103: Generate a license plate image for the virtual license plate according to the surface attribute information of the license plate and the three-dimensional model.

在根据步骤101和步骤102确定出虚拟车牌的车牌表面属性信息和三维模型之后，便可通过步骤103生成针对虚拟车牌的车牌图像。After determining the license plate surface attribute information and the three-dimensional model of the virtual license plate according to step 101 and step 102, the license plate image for the virtual license plate can be generated throughstep 103.

在一种可能的实现方式中，步骤103具体可以为：确定虚拟拍摄场景的拍摄参数；根据拍摄参数、车牌属性信息和三维模型，生成针对虚拟车牌的虚拟照片；对虚拟照片进行后处理，得到车牌图像。In a possible implementation,step 103 may specifically include: determining the shooting parameters of the virtual shooting scene; generating a virtual photo for the virtual license plate according to the shooting parameters, license plate attribute information, and three-dimensional model; performing post-processing on the virtual photo to obtain License plate image.

对于同一车牌，在不同的拍摄场景中，摄像机采集的车牌图像也是不同的。因此，在本申请实施例中，为了使得最终生成的车牌图像与摄像机采集的车牌图像比较接近，还可以确定一个虚拟拍摄场景，以通过上述实现方式得到车牌图像。For the same license plate, in different shooting scenes, the license plate images collected by the camera are also different. Therefore, in the embodiment of the present application, in order to make the finally generated license plate image closer to the license plate image collected by the camera, a virtual shooting scene can also be determined to obtain the license plate image through the foregoing implementation.

由于拍摄场景中灯光的颜色、亮度发生变化时，摄像机针对同一车牌采集的车牌图像极有可能是不同的。另外，摄像机的曝光参数发生变化时，摄像机针对同一车牌采集的车牌图像极有可能是不同的。另外，如果车牌在摄像机拍摄区域内，但是车牌和摄像机之间的距离发生变化时，摄像机针对同一车牌采集的车牌图像极有可能是不同的。另外，如果车牌在摄像机拍摄区域边缘，摄像机针对车牌采集的车牌图像可能会发生镜头畸变。因此，在本申请实施例中，上述虚拟拍摄场景的拍摄参数至少包括以下参数中的一种或多种：虚拟拍摄场景中的灯光的颜色、灯光的亮度、虚拟拍摄场景中虚拟摄像机的曝光参数、在虚拟拍摄场景中虚拟摄像机和虚拟车牌的位置。虚拟摄像机的曝光参数可以包括虚拟摄像机的曝光时间、曝光强度等。As the color and brightness of the lights in the shooting scene change, the license plate images collected by the camera for the same license plate are most likely to be different. In addition, when the camera's exposure parameters change, the license plate images collected by the camera for the same license plate are most likely to be different. In addition, if the license plate is in the camera shooting area, but the distance between the license plate and the camera changes, the license plate images collected by the camera for the same license plate are most likely to be different. In addition, if the license plate is at the edge of the camera's shooting area, the license plate image collected by the camera for the license plate may suffer lens distortion. Therefore, in the embodiment of the present application, the shooting parameters of the virtual shooting scene described above include at least one or more of the following parameters: the color of the light in the virtual shooting scene, the brightness of the light, and the exposure parameters of the virtual camera in the virtual shooting scene , The position of the virtual camera and the virtual license plate in the virtual shooting scene. The exposure parameters of the virtual camera may include the exposure time and exposure intensity of the virtual camera.

上述拍摄参数仅仅用于举例说明，在使用本申请实施例时，拍摄参数可以包括任何能够影响摄像机采集的车牌图像的拍摄因素，在此就不再一一举例说明。The above shooting parameters are only used for illustration. When using the embodiment of the present application, the shooting parameters may include any shooting factors that can affect the license plate image collected by the camera, and the examples are not described here.

另外，上述根据拍摄参数、车牌属性信息和三维模型，生成针对虚拟车牌的虚拟照片的过程可以通过光线追踪技术来实现，在此不再详细阐述。In addition, the above-mentioned process of generating a virtual photo for the virtual license plate based on the shooting parameters, the license plate attribute information and the three-dimensional model can be implemented by ray tracing technology, which will not be elaborated here.

由于直接生成的针对虚拟车牌的虚拟照片中有很多噪点，因此，在本申请实施例中，还可以对虚拟照片进行后处理，将后处理后的图像作为车牌图像。后处理可以包括降噪、白平衡等处理。其中，降噪处理可以通过AI(artificial intelligence，人工智能)技术来实现，在此同样不再详细阐述。Since there are a lot of noise in the directly generated virtual photo for the virtual license plate, in the embodiment of the present application, the virtual photo can also be post-processed, and the post-processed image is used as the license plate image. Post-processing can include noise reduction, white balance and other processing. Among them, the noise reduction processing can be realized by AI (artificial intelligence, artificial intelligence) technology, which is also not elaborated here.

另外，本申请实施例构建的虚拟车牌是用于后续训练识别模型时使用的，因此，在通过步骤103根据车牌属性信息和三维模型，生成针对虚拟车牌的车牌图像之后，还可以在车牌图像中标注该虚拟车牌上的车牌识别结果，以便于后续将该车牌识别结果和该车牌图像作为一个训练样本。In addition, the virtual license plate constructed by the embodiment of the present application is used for subsequent training of the recognition model. Therefore, after generating the license plate image for the virtual license plate according to the license plate attribute information and the three-dimensional model instep 103, it can also be included in the license plate image Annotate the license plate recognition result on the virtual license plate, so that the license plate recognition result and the license plate image are used as a training sample in the future.

上述车牌识别结果可以为车牌上用于进行识别的属性，例如车牌颜色。The foregoing license plate recognition result may be an attribute on the license plate used for recognition, such as the color of the license plate.

又例如，该车牌识别结果可以为车牌标识。此时，在构建虚拟车牌的三维模型时，需要虚拟车牌上用于指示车牌标识的多个字符。也即是，在生成虚拟车牌的车牌图像的过程中，用于指示车牌标识的多个字符是已知的。因此，在本申请实施中，在生成虚拟车牌的车牌图像之后，可以直接在车牌图像中标注虚拟车牌上的车牌标识，以便于后续直接根据标注后的车牌图像进行神经网络模型的训练。避免了需要通过人工方式来标注车牌图像中的车牌标识，从而提高了确定训练样本的效率。又例如，该车牌识别结果可以包括车牌号和遮挡情况。For another example, the license plate recognition result may be a license plate identification. At this time, when constructing a three-dimensional model of the virtual license plate, multiple characters used to indicate the license plate identifier on the virtual license plate are required. That is, in the process of generating the license plate image of the virtual license plate, multiple characters used to indicate the license plate identifier are known. Therefore, in the implementation of the present application, after the license plate image of the virtual license plate is generated, the license plate identification on the virtual license plate can be directly marked in the license plate image, so that the subsequent training of the neural network model is directly based on the marked license plate image. It avoids the need to manually label the license plate identifier in the license plate image, thereby improving the efficiency of determining training samples. For another example, the license plate recognition result may include the license plate number and the occlusion situation.

在本申请实施例中，可以根据实际需求模拟虚拟车牌，然后构建虚拟车牌的三维模型，并确定虚拟车牌的车牌表面属性信息，以生成针对该虚拟车牌的车牌图像。因此，在确定针对用于车牌识别的神经网络模型的训练样本时，可以根据实际需求直接通过本申请实施例生成车牌图像，无需通过摄像机针对真实的车牌进行采集才能获取到车牌图像，提高了获取车牌图像的效率。另外，由于虚拟车牌是根据实际需求模拟的车牌，因此，可以通过本申请实施例生成不同类型的虚拟车牌对应的车牌图像，提高了训练样本中的车牌图像的多样性，从而提高了后续根据训练样本训练出的神经网络模型的识别精度。In the embodiment of the present application, a virtual license plate can be simulated according to actual needs, and then a three-dimensional model of the virtual license plate is constructed, and the license plate surface attribute information of the virtual license plate is determined to generate a license plate image for the virtual license plate. Therefore, when determining the training samples for the neural network model for license plate recognition, the license plate image can be directly generated through the embodiment of the application according to actual needs, and the license plate image can be obtained without the need for the camera to collect the real license plate, which improves the acquisition The efficiency of license plate images. In addition, since the virtual license plate is a license plate simulated according to actual needs, the license plate images corresponding to different types of virtual license plates can be generated through the embodiments of the present application, which improves the diversity of the license plate images in the training samples, thereby improving the subsequent training according to The recognition accuracy of the neural network model trained by the sample.

图2是本申请实施例提供的一种车牌图像生成装置示意图。如图2所示，该装置200包括：Fig. 2 is a schematic diagram of a license plate image generating device provided by an embodiment of the present application. As shown in Fig. 2, the device 200 includes:

构建模块201，用于构建虚拟车牌的三维模型，虚拟车牌为根据需求模拟出的车牌；The construction module 201 is used to construct a three-dimensional model of a virtual license plate, and the virtual license plate is a simulated license plate according to requirements;

确定模块202，用于确定虚拟车牌的车牌表面属性信息；The determining module 202 is used to determine the surface attribute information of the virtual license plate;

生成模块203，用于根据车牌表面属性信息和三维模型，生成针对虚拟车牌的车牌图像。The generating module 203 is configured to generate a license plate image for a virtual license plate according to the surface attribute information of the license plate and the three-dimensional model.

可选地，构建模块，具体用于：Optionally, the building module is specifically used for:

确定虚拟车牌的边框的形状；Determine the shape of the frame of the virtual license plate;

确定虚拟车牌的底色；Determine the background color of the virtual license plate;

确定虚拟车牌上用于指示车牌标识的多个字符以及多个字符的排列顺序；Determine the multiple characters used to indicate the license plate mark and the sequence of multiple characters on the virtual license plate;

根据边框的形状、底色、多个字符以及多个字符的排列顺序，生成虚拟车牌的三维模型。According to the shape of the frame, the background color, multiple characters and the sequence of multiple characters, a three-dimensional model of the virtual license plate is generated.

可选地，构建模块，具体用于：根据虚拟车牌的形变情况，确定虚拟车牌的边框的形状。Optionally, the building module is specifically used to determine the shape of the frame of the virtual license plate according to the deformation of the virtual license plate.

根据边框的形状、底色、多个字符以及多个字符的排列顺序，生成虚拟车牌的理论三维视图；Generate a theoretical three-dimensional view of the virtual license plate according to the shape of the frame, the background color, multiple characters and the sequence of multiple characters;

根据虚拟车牌的折痕情况，对虚拟车牌的理论三维视图进行调整，得到虚拟车牌的三维模型。According to the crease condition of the virtual license plate, the theoretical three-dimensional view of the virtual license plate is adjusted to obtain the three-dimensional model of the virtual license plate.

可选地，车牌表面属性信息至少包括以下属性信息中的一种或多种：Optionally, the surface attribute information of the license plate includes at least one or more of the following attribute information:

虚拟车牌的金属属性；Metal properties of virtual license plates;

虚拟车牌的漫反射属性；The diffuse reflection properties of virtual license plates;

虚拟车牌的平整度；The flatness of the virtual license plate;

虚拟车牌的镜面反射属性；Specular reflection properties of virtual license plates;

虚拟车牌上的灰尘情况；The dust on the virtual license plate;

可选地，生成模块，具体用于：Optionally, the generating module is specifically used for:

根据拍摄参数、车牌属性信息和三维模型，生成针对虚拟车牌的虚拟照片；According to shooting parameters, license plate attribute information and three-dimensional model, generate virtual photos for virtual license plates;

对虚拟照片进行后处理，得到车牌图像。Perform post-processing on virtual photos to obtain license plate images.

可选地，虚拟拍摄场景的拍摄参数至少包括以下参数中的一种或多种：Optionally, the shooting parameters of the virtual shooting scene include at least one or more of the following parameters:

虚拟拍摄场景中的灯光的颜色、灯光的亮度、虚拟拍摄场景中虚拟摄像机的曝光参数、在虚拟拍摄场景中虚拟摄像机和虚拟车牌的位置。The color of the light in the virtual shooting scene, the brightness of the light, the exposure parameters of the virtual camera in the virtual shooting scene, the position of the virtual camera and the virtual license plate in the virtual shooting scene.

可选地，装置还包括：Optionally, the device further includes:

标注模块，用于在车牌图像中标注虚拟车牌上的车牌识别结果。The marking module is used to mark the license plate recognition result on the virtual license plate in the license plate image.

需要说明的是：上述实施例提供的车牌图像的生成装置在生成车牌图像时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的车牌图像的生成装置与车牌图像的生成方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。It should be noted that when the license plate image generation device provided in the above embodiment generates the license plate image, only the division of the above functional modules is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs. Complete, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above. In addition, the license plate image generation device provided in the foregoing embodiment belongs to the same concept as the license plate image generation method embodiment. For the specific implementation process, please refer to the method embodiment, which will not be repeated here.

图3是本申请实施例提供的一种终端300的结构框图。该终端300可以是：智能手机、平板电脑、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、笔记本电脑或台式电脑。终端300还可能被称为用户设备、便携式终端、膝上型终端、台式终端等其他名称。FIG. 3 is a structural block diagram of a terminal 300 provided by an embodiment of the present application. The terminal 300 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, moving picture expert compression standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, moving picture expert compressing standard audio Level 4) Player, laptop or desktop computer. The terminal 300 may also be called user equipment, portable terminal, laptop terminal, desktop terminal and other names.

通常，终端300包括有：处理器301和存储器302。Generally, the terminal 300 includes aprocessor 301 and amemory 302.

处理器301可以包括一个或多个处理核心，比如4核心处理器、8核心处理器等。处理器301可以采用DSP(Digital Signal Processing，数字信号处理)、FPGA(Field－Programmable Gate Array，现场可编程门阵列)、PLA(Programmable Logic Array，可编程逻辑阵列)中的至少一种硬件形式来实现。处理器301也可以包括主处理器和协处理器，主处理器是用于对在唤醒状态下的数据进行处理的处理器，也称CPU(Central Processing Unit，中央处理器)；协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中，处理器301可以在集成有GPU(Graphics Processing Unit，图像处理器)，GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中，处理器301还可以包括AI(Artificial Intelligence，人工智能)处理器，该AI处理器用于处理有关机器学习的计算操作。Theprocessor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. Theprocessor 301 can adopt at least one hardware form among DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array, Programmable Logic Array). achieve. Theprocessor 301 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also called a CPU (Central Processing Unit, central processing unit); the coprocessor is A low-power processor used to process data in the standby state. In some embodiments, theprocessor 301 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used to render and draw content that needs to be displayed on the display screen. In some embodiments, theprocessor 301 may also include an AI (Artificial Intelligence, artificial intelligence) processor, which is used to process computing operations related to machine learning.

存储器302可以包括一个或多个计算机可读存储介质，该计算机可读存储介质可以是非暂态的。存储器302还可包括高速随机存取存储器，以及非易失性存储器，比如一个或多个磁盘存储设备、闪存存储设备。在一些实施例中，存储器302中的非暂态的计算机可读存储介质用于存储至少一个指令，该至少一个指令用于被处理器301所执行以实现本申请中方法实施例提供的车牌图像的生成方法。Thememory 302 may include one or more computer-readable storage media, which may be non-transitory. Thememory 302 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in thememory 302 is used to store at least one instruction, and the at least one instruction is used to be executed by theprocessor 301 to implement the license plate image provided in the method embodiment of the present application The generation method.

在一些实施例中，终端300还可选包括有：外围设备接口303和至少一个外围设备。处理器301、存储器302和外围设备接口303之间可以通过总线或信号线相连。各个外围设备可以通过总线、信号线或电路板与外围设备接口303相连。具体地，外围设备包括：射频电路304、触摸显示屏305、摄像头306、音频电路307、定位组件308和电源309中的至少一种。In some embodiments, the terminal 300 may optionally further include: aperipheral device interface 303 and at least one peripheral device. Theprocessor 301, thememory 302, and theperipheral device interface 303 may be connected by a bus or signal line. Each peripheral device can be connected to theperipheral device interface 303 through a bus, a signal line or a circuit board. Specifically, the peripheral device includes at least one of aradio frequency circuit 304, atouch screen 305, acamera 306, anaudio circuit 307, apositioning component 308, and apower supply 309.

外围设备接口303可被用于将I/O(Input/Output，输入/输出)相关的至少一个外围设备连接到处理器301和存储器302。在一些实施例中，处理器301、存储器302和外围设备接口303被集成在同一芯片或电路板上；在一些其他实施例中，处理器301、存储器302和外围设备接口303中的任意一个或两个可以在单独的芯片或电路板上实现，本实施例对此不加以限定。Theperipheral device interface 303 may be used to connect at least one peripheral device related to I/O (Input/Output) to theprocessor 301 and thememory 302. In some embodiments, theprocessor 301, thememory 302, and theperipheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one of theprocessor 301, thememory 302, and theperipheral device interface 303 or The two can be implemented on separate chips or circuit boards, which are not limited in this embodiment.

射频电路304用于接收和发射RF(Radio Frequency，射频)信号，也称电磁信号。射频电路304通过电磁信号与通信网络以及其他通信设备进行通信。射频电路304将电信号转换为电磁信号进行发送，或者，将接收到的电磁信号转换为电信号。可选地，射频电路304包括：天线系统、RF收发器、一个或多个放大器、调谐器、振荡器、数字信号处理器、编解码芯片组、用户身份模块卡等等。射频电路304可以通过至少一种无线通信协议来与其它终端进行通信。该无线通信协议包括但不限于：城域网、各代移动通信网络(2G、3G、4G及5G)、无线局域网和/或WiFi(Wireless Fidelity，无线保真)网络。在一些实施例中，射频电路304还可以包括NFC(Near Field Communication，近距离无线通信)有关的电路，本申请对此不加以限定。Theradio frequency circuit 304 is used for receiving and transmitting RF (Radio Frequency, radio frequency) signals, also called electromagnetic signals. Theradio frequency circuit 304 communicates with a communication network and other communication devices through electromagnetic signals. Theradio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, theradio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on. Theradio frequency circuit 304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area network and/or WiFi (Wireless Fidelity, wireless fidelity) network. In some embodiments, theradio frequency circuit 304 may also include a circuit related to NFC (Near Field Communication), which is not limited in this application.

显示屏305用于显示UI(User Interface，用户界面)。该UI可以包括图形、文本、图标、视频及其它们的任意组合。当显示屏305是触摸显示屏时，显示屏305还具有采集在显示屏305的表面或表面上方的触摸信号的能力。该触摸信号可以作为控制信号输入至处理器301进行处理。此时，显示屏305还可以用于提供虚拟按钮和/或虚拟键盘，也称软按钮和/或软键盘。在一些实施例中，显示屏305可以为一个，设置终端300的前面板；在另一些实施例中，显示屏305可以为至少两个，分别设置在终端300的不同表面或呈折叠设计；在再一些实施例中，显示屏305可以是柔性显示屏，设置在终端300的弯曲表面上或折叠面上。甚至，显示屏305还可以设置成非矩形的不规则图形，也即异形屏。显示屏305可以采用LCD(Liquid Crystal Display，液晶显示屏)、OLED(Organic Light-Emitting Diode,有机发光二极管)等材质制备。Thedisplay screen 305 is used to display a UI (User Interface, user interface). The UI can include graphics, text, icons, videos, and any combination thereof. When thedisplay screen 305 is a touch display screen, thedisplay screen 305 also has the ability to collect touch signals on or above the surface of thedisplay screen 305. The touch signal can be input to theprocessor 301 as a control signal for processing. At this time, thedisplay screen 305 may also be used to provide virtual buttons and/or virtual keyboards, also called soft buttons and/or soft keyboards. In some embodiments, there may be onedisplay screen 305, which is provided with the front panel of the terminal 300; in other embodiments, there may be at least twodisplay screens 305, which are respectively provided on different surfaces of the terminal 300 or in a folded design; In still other embodiments, thedisplay screen 305 may be a flexible display screen, which is arranged on the curved surface or the folding surface of the terminal 300. Furthermore, thedisplay screen 305 can also be set as a non-rectangular irregular pattern, that is, a special-shaped screen. Thedisplay screen 305 may be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

摄像头组件306用于采集图像或视频。可选地，摄像头组件306包括前置摄像头和后置摄像头。通常，前置摄像头设置在终端的前面板，后置摄像头设置在终端的背面。在一些实施例中，后置摄像头为至少两个，分别为主摄像头、景深摄像头、广角摄像头、长焦摄像头中的任意一种，以实现主摄像头和景深摄像头融合实现背景虚化功能、主摄像头和广角摄像头融合实现全景拍摄以及VR(Virtual Reality，虚拟现实)拍摄功能或者其它融合拍摄功能。在一些实施例中，摄像头组件306还可以包括闪光灯。闪光灯可以是单色温闪光灯，也可以是双色温闪光灯。双色温闪光灯是指暖光闪光灯和冷光闪光灯的组合，可以用于不同色温下的光线补偿。Thecamera assembly 306 is used to capture images or videos. Optionally, thecamera assembly 306 includes a front camera and a rear camera. Generally, the front camera is set on the front panel of the terminal, and the rear camera is set on the back of the terminal. In some embodiments, there are at least two rear cameras, each of which is a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth-of-field camera to realize the background blur function, the main camera Integrate with the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, thecamera assembly 306 may also include a flash. The flash can be a single-color flash or a dual-color flash. Dual color temperature flash refers to the combination of warm light flash and cold light flash, which can be used for light compensation under different color temperatures.

音频电路307可以包括麦克风和扬声器。麦克风用于采集用户及环境的声波，并将声波转换为电信号输入至处理器301进行处理，或者输入至射频电路304以实现语音通信。出于立体声采集或降噪的目的，麦克风可以为多个，分别设置在终端300的不同部位。麦克风还可以是阵列麦克风或全向采集型麦克风。扬声器则用于将来自处理器301或射频电路304的电信号转换为声波。扬声器可以是传统的薄膜扬声器，也可以是压电陶瓷扬声器。当扬声器是压电陶瓷扬声器时，不仅可以将电信号转换为人类可听见的声波，也可以将电信号转换为人类听不见的声波以进行测距等用途。在一些实施例中，音频电路307还可以包括耳机插孔。Theaudio circuit 307 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals to be input to theprocessor 301 for processing, or input to theradio frequency circuit 304 to implement voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively set in different parts of the terminal 300. The microphone can also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from theprocessor 301 or theradio frequency circuit 304 into sound waves. The speaker can be a traditional membrane speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into human audible sound waves, but also convert the electrical signal into human inaudible sound waves for purposes such as distance measurement. In some embodiments, theaudio circuit 307 may also include a headphone jack.

定位组件308用于定位终端300的当前地理位置，以实现导航或LBS(Location Based Service，基于位置的服务)。定位组件308可以是基于美国的GPS(Global Positioning System，全球定位系统)、中国的北斗系统、俄罗斯的格雷纳斯系统或欧盟的伽利略系统的定位组件。Thepositioning component 308 is used to locate the current geographic location of the terminal 300 to implement navigation or LBS (Location Based Service, location-based service). Thepositioning component 308 may be a positioning component based on the GPS (Global Positioning System, Global Positioning System) of the United States, the Beidou system of China, the Granus system of Russia, or the Galileo system of the European Union.

电源309用于为终端300中的各个组件进行供电。电源309可以是交流电、直流电、一次性电池或可充电电池。当电源309包括可充电电池时，该可充电电池可以支持有线充电或无线充电。该可充电电池还可以用于支持快充技术。Thepower supply 309 is used to supply power to various components in theterminal 300. Thepower source 309 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When thepower source 309 includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

在一些实施例中，终端300还包括有一个或多个传感器310。该一个或多个传感器310包括但不限于：加速度传感器311、陀螺仪传感器312、压力传感器313、指纹传感器314、光学传感器315以及接近传感器316。In some embodiments, the terminal 300 further includes one or more sensors 310. The one or more sensors 310 include, but are not limited to: an acceleration sensor 311, a gyroscope sensor 312, a pressure sensor 313, a fingerprint sensor 314, an optical sensor 315, and a proximity sensor 316.

加速度传感器311可以检测以终端300建立的坐标系的三个坐标轴上的加速度大小。比如，加速度传感器311可以用于检测重力加速度在三个坐标轴上的分量。处理器301可以根据加速度传感器311采集的重力加速度信号，控制触摸显示屏305以横向视图或纵向视图进行用户界面的显示。加速度传感器311还可以用于游戏或者用户的运动数据的采集。The acceleration sensor 311 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by theterminal 300. For example, the acceleration sensor 311 may be used to detect the components of the gravitational acceleration on three coordinate axes. Theprocessor 301 may control thetouch screen 305 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 311. The acceleration sensor 311 may also be used for the collection of game or user motion data.

陀螺仪传感器312可以检测终端300的机体方向及转动角度，陀螺仪传感器312可以与加速度传感器311协同采集用户对终端300的3D动作。处理器301根据陀螺仪传感器312采集的数据，可以实现如下功能：动作感应(比如根据用户的倾斜操作来改变UI)、拍摄时的图像稳定、游戏控制以及惯性导航。The gyroscope sensor 312 can detect the body direction and rotation angle of the terminal 300, and the gyroscope sensor 312 can cooperate with the acceleration sensor 311 to collect the user's 3D actions on theterminal 300. Theprocessor 301 can implement the following functions according to the data collected by the gyroscope sensor 312: motion sensing (for example, changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

压力传感器313可以设置在终端300的侧边框和/或触摸显示屏305的下层。当压力传感器313设置在终端300的侧边框时，可以检测用户对终端300的握持信号，由处理器301根据压力传感器313采集的握持信号进行左右手识别或快捷操作。当压力传感器313设置在触摸显示屏305的下层时，由处理器301根据用户对触摸显示屏305的压力操作，实现对UI界面上的可操作性控件进行控制。可操作性控件包括按钮控件、滚动条控件、图标控件、菜单控件中的至少一种。The pressure sensor 313 may be disposed on the side frame of the terminal 300 and/or the lower layer of thetouch screen 305. When the pressure sensor 313 is arranged on the side frame of the terminal 300, the user's holding signal of the terminal 300 can be detected, and theprocessor 301 performs left and right hand recognition or quick operation according to the holding signal collected by the pressure sensor 313. When the pressure sensor 313 is arranged on the lower layer of thetouch display screen 305, theprocessor 301 controls the operability controls on the UI interface according to the user's pressure operation on thetouch display screen 305. The operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

指纹传感器314用于采集用户的指纹，由处理器301根据指纹传感器314采集到的指纹识别用户的身份，或者，由指纹传感器314根据采集到的指纹识别用户的身份。在识别出用户的身份为可信身份时，由处理器301授权该用户执行相关的敏感操作，该敏感操作包括解锁屏幕、查看加密信息、下载软件、支付及更改设置等。指纹传感器314可以被设置终端300的正面、背面或侧面。当终端300上设置有物理按键或厂商Logo时，指纹传感器314可以与物理按键或厂商Logo集成在一起。The fingerprint sensor 314 is used to collect the user's fingerprint. Theprocessor 301 can identify the user's identity based on the fingerprint collected by the fingerprint sensor 314, or the fingerprint sensor 314 can identify the user's identity based on the collected fingerprint. When it is recognized that the user's identity is a trusted identity, theprocessor 301 authorizes the user to perform related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings. The fingerprint sensor 314 may be provided on the front, back or side of the terminal 300. When a physical button or a manufacturer logo is provided on the terminal 300, the fingerprint sensor 314 can be integrated with the physical button or the manufacturer logo.

光学传感器315用于采集环境光强度。在一个实施例中，处理器301可以根据光学传感器315采集的环境光强度，控制触摸显示屏305的显示亮度。具体地，当环境光强度较高时，调高触摸显示屏305的显示亮度；当环境光强度较低时，调低触摸显示屏305的显示亮度。在另一个实施例中，处理器301还可以根据光学传感器315采集的环境光强度，动态调整摄像头组件306的拍摄参数。The optical sensor 315 is used to collect the ambient light intensity. In an embodiment, theprocessor 301 may control the display brightness of thetouch screen 305 according to the intensity of the ambient light collected by the optical sensor 315. Specifically, when the ambient light intensity is high, the display brightness of thetouch screen 305 is increased; when the ambient light intensity is low, the display brightness of thetouch screen 305 is decreased. In another embodiment, theprocessor 301 may also dynamically adjust the shooting parameters of thecamera assembly 306 according to the ambient light intensity collected by the optical sensor 315.

接近传感器316，也称距离传感器，通常设置在终端300的前面板。接近传感器316用于采集用户与终端300的正面之间的距离。在一个实施例中，当接近传感器316检测到用户与终端300的正面之间的距离逐渐变小时，由处理器301控制触摸显示屏305从亮屏状态切换为息屏状态；当接近传感器316检测到用户与终端300的正面之间的距离逐渐变大时，由处理器301控制触摸显示屏305从息屏状态切换为亮屏状态。The proximity sensor 316, also called a distance sensor, is usually arranged on the front panel of the terminal 300. The proximity sensor 316 is used to collect the distance between the user and the front of the terminal 300. In one embodiment, when the proximity sensor 316 detects that the distance between the user and the front of the terminal 300 gradually decreases, theprocessor 301 controls thetouch screen 305 to switch from the on-screen state to the off-screen state; when the proximity sensor 316 detects When the distance between the user and the front of the terminal 300 gradually increases, theprocessor 301 controls thetouch display screen 305 to switch from the on-screen state to the on-screen state.

本领域技术人员可以理解，图3中示出的结构并不构成对终端300的限定，可以包括比图示更多或更少的组件，或者组合某些组件，或者采用不同的组件布置。Those skilled in the art can understand that the structure shown in FIG. 3 does not constitute a limitation on the terminal 300, and may include more or fewer components than shown, or combine certain components, or adopt different component arrangements.

本申请实施例还提供了一种非临时性计算机可读存储介质，当所述存储介质中的指令由终端的处理器执行时，使得终端能够执行上实施例提供的车牌图像的生成方法。The embodiment of the present application also provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor of the terminal, the terminal can execute the method for generating the license plate image provided in the above embodiment.

本申请实施例还提供了一种包含指令的计算机程序产品，当其在终端上运行时，使得终端执行上述实施例提供的车牌图像的生成方法。The embodiment of the present application also provides a computer program product containing instructions, which when running on a terminal, causes the terminal to execute the method for generating a license plate image provided in the foregoing embodiment.

本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps in the foregoing embodiments can be implemented by hardware, or by a program instructing relevant hardware to be completed. The program can be stored in a computer-readable storage medium. The storage medium mentioned can be a read-only memory, a magnetic disk or an optical disk, etc.

以上所述仅为本申请的较佳实施例，并不用以限制本申请实施例，凡在本申请实施例的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请实施例的保护范围之内。The above descriptions are only preferred embodiments of the application, and are not intended to limit the embodiments of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the application shall be included in Within the protection scope of the embodiments of this application.