技术领域Technical Field
本说明书涉及图像处理技术领域，特别涉及图像处理方法及装置。The present invention relates to the field of image processing technology, and in particular to an image processing method and device.
背景技术Background Art
随着计算机技术的发展，对图像中的目标对象进行检测逐渐成为一个重要的研究问题。目标对象检测可以包括目标对象定位和目标对象识别两个过程，其中的目标对象识别主要是为了确定图像中目标对象的类别。现有技术通常是根据图像识别算法来确定图像中目标对象的类别，需要计算设备执行比较繁琐的图像识别算法，识别速率可能比较慢。With the development of computer technology, the detection of target objects in images has gradually become an important research issue. Target object detection can include two processes: target object positioning and target object recognition. Target object recognition is mainly used to determine the category of the target object in the image. The existing technology usually determines the category of the target object in the image based on the image recognition algorithm, which requires the computing device to execute a relatively cumbersome image recognition algorithm, and the recognition rate may be relatively slow.
发明内容Summary of the invention
有鉴于此，本说明书实施例提供了一种图像处理方法。本说明书同时涉及一种图像处理装置，一种计算设备，以及一种计算机可读存储介质，以解决现有技术中存在的技术缺陷。In view of this, the embodiment of this specification provides an image processing method. This specification also relates to an image processing device, a computing device, and a computer-readable storage medium to solve the technical defects existing in the prior art.
根据本说明书实施例的第一方面，提供了一种图像处理方法，包括：According to a first aspect of an embodiment of this specification, there is provided an image processing method, including:
接收针对当前场景的图像获取任务；Receive an image acquisition task for the current scene;
基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；Based on the image acquisition task, a first image of the current scene is acquired, and configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object;
基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。Based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object.
可选地，所述对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像，包括：Optionally, rendering the target object to obtain a second image of the current scene including the target object includes:
基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色；Based on the target category label, determining a target rendering color corresponding to the target object;
基于所述目标渲染颜色对所述当前场景中包括的目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。The target object included in the current scene is rendered based on the target rendering color to obtain a second image of the current scene including the target object.
可选地，所述基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色之前，还包括：Optionally, before determining the target rendering color corresponding to the target object based on the target category label, the method further includes:
确定类别标签与渲染颜色的对应关系；Determine the correspondence between category labels and rendering colors;
相应地，所述基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色，包括：Accordingly, determining the target rendering color corresponding to the target object based on the target category label includes:
基于所述目标类别标签，从所述对应关系中确定与所述目标类别标签对应的渲染颜色，以所确定的渲染颜色为所述目标渲染颜色。Based on the target category label, a rendering color corresponding to the target category label is determined from the corresponding relationship, and the determined rendering color is used as the target rendering color.
可选地，所述基于所述图像获取任务，采集所述当前场景的第一图像之前，还包括：Optionally, before acquiring the first image of the current scene based on the image acquisition task, the method further includes:
生成所述目标对象的目标类别标签；Generating a target category label of the target object;
将所述目标类别标签存储至所述目标对象的配置信息中。The target category label is stored in the configuration information of the target object.
可选地，所述基于所述图像获取任务，采集所述当前场景的第一图像之前，还包括：Optionally, before acquiring the first image of the current scene based on the image acquisition task, the method further includes:
基于检测到的行为指令生成所述目标对象的目标行为标签；generating a target behavior label of the target object based on the detected behavior instruction;
将所述目标行为标签存储至所述目标对象的配置信息中。The target behavior tag is stored in the configuration information of the target object.
可选地，所述方法还包括：Optionally, the method further comprises:
若所述目标类别为预设类别，确定完成所述图像获取任务。If the target category is a preset category, it is determined that the image acquisition task is completed.
可选地，所述配置信息还包括目标行为标签，所述方法还包括：Optionally, the configuration information further includes a target behavior tag, and the method further includes:
基于所述目标行为标签，确定所述目标对象的目标行为。Based on the target behavior label, a target behavior of the target object is determined.
可选地，所述方法还包括：Optionally, the method further comprises:
若所述目标类别为预设类别，且所述目标行为为预设行为，确定完成所述图像获取任务。If the target category is a preset category and the target behavior is a preset behavior, it is determined that the image acquisition task is completed.
根据本说明书实施例的第二方面，提供了一种图像处理装置，包括：According to a second aspect of the embodiments of this specification, there is provided an image processing device, including:
接收模块，被配置为接收针对当前场景的图像获取任务；A receiving module, configured to receive an image acquisition task for a current scene;
获取模块，被配置为基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；an acquisition module, configured to acquire a first image of the current scene based on the image acquisition task, acquire configuration information of a target object included in the current scene and add the configuration information to the first image, wherein the configuration information includes a target category label of the target object;
渲染模块，被配置为基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。The rendering module is configured to determine the target category of the target object based on the target category label, and render the target object to obtain a second image of the current scene including the target object.
可选地，所述渲染模块被配置为：Optionally, the rendering module is configured to:
基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色；Based on the target category label, determining a target rendering color corresponding to the target object;
基于所述目标渲染颜色对所述当前场景中包括的目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。The target object included in the current scene is rendered based on the target rendering color to obtain a second image of the current scene including the target object.
可选地，所述渲染模块还被配置为：Optionally, the rendering module is further configured to:
确定类别标签与渲染颜色的对应关系；Determine the correspondence between category labels and rendering colors;
基于所述目标类别标签，从所述对应关系中确定与所述目标类别标签对应的渲染颜色，以所确定的渲染颜色为所述目标渲染颜色。Based on the target category label, a rendering color corresponding to the target category label is determined from the corresponding relationship, and the determined rendering color is used as the target rendering color.
可选地，所述获取模块还被配置为：Optionally, the acquisition module is further configured to:
生成所述目标对象的目标类别标签；Generating a target category label of the target object;
将所述目标类别标签存储至所述目标对象的配置信息中。The target category label is stored in the configuration information of the target object.
可选地，所述获取模块还被配置为：Optionally, the acquisition module is further configured to:
基于检测到的行为指令生成所述目标对象的目标行为标签；generating a target behavior label of the target object based on the detected behavior instruction;
将所述目标行为标签存储至所述目标对象的配置信息中。The target behavior tag is stored in the configuration information of the target object.
可选地，所述渲染模块还被配置为：Optionally, the rendering module is further configured to:
若所述目标类别为预设类别，确定完成所述图像获取任务。If the target category is a preset category, it is determined that the image acquisition task is completed.
可选地，所述渲染模块还被配置为：Optionally, the rendering module is further configured to:
所述配置信息还包括目标行为标签，基于所述目标行为标签，确定所述目标对象的目标行为。The configuration information also includes a target behavior tag, based on which the target behavior of the target object is determined.
可选地，所述渲染模块被配置为：Optionally, the rendering module is configured to:
若所述目标类别为预设类别，且所述目标行为为预设行为，确定完成所述图像获取任务。If the target category is a preset category and the target behavior is a preset behavior, it is determined that the image acquisition task is completed.
根据本说明书实施例的第三方面，提供了一种计算设备，包括：According to a third aspect of an embodiment of this specification, a computing device is provided, including:
存储器和处理器；Memory and processor;
所述存储器用于存储计算机可执行指令，所述处理器用于执行所述计算机可执行指令：The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:
接收针对当前场景的图像获取任务；Receive an image acquisition task for the current scene;
基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；Based on the image acquisition task, a first image of the current scene is acquired, and configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object;
基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。Based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object.
根据本说明书实施例的第四方面，提供了一种计算机可读存储介质，其存储有计算机可执行指令，该指令被处理器执行时实现所述图像处理方法的步骤。According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the image processing method are implemented.
本说明书提供的图像处理方法，接收针对当前场景的图像获取任务；基于所述图像获取任务，基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。通过预先为目标对象设置目标类别标签并将目标类别标签添加至第一图像中，可以快速确定第一图像中目标对象的类别，并且，根据目标对象的目标类别标签对目标对象进行渲染，可以直观地将目标对象的类别展示出来，以便于后续进行调试。The image processing method provided in this specification receives an image acquisition task for a current scene; based on the image acquisition task, a first image of the current scene is collected, configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object; based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object. By setting a target category label for the target object in advance and adding the target category label to the first image, the category of the target object in the first image can be quickly determined, and by rendering the target object according to the target category label of the target object, the category of the target object can be intuitively displayed for subsequent debugging.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是本说明书一实施例提供的一种图像处理方法的流程图；FIG1 is a flow chart of an image processing method provided by an embodiment of the present specification;
图2是本说明书一实施例提供的一种应用于游戏场景的图像处理方法的处理流程图；FIG2 is a processing flow chart of an image processing method applied to a game scene provided in an embodiment of the present specification;
图3是本说明书一实施例提供的一种图像处理装置的结构示意图；FIG3 is a schematic diagram of the structure of an image processing device provided by an embodiment of the present specification;
图4是本说明书一实施例提供的一种计算设备的结构框图。FIG. 4 is a structural block diagram of a computing device provided in an embodiment of the present specification.
具体实施方式DETAILED DESCRIPTION
在下面的描述中阐述了很多具体细节以便于充分理解本说明书。但是本说明书能够以很多不同于在此描述的其它方式来实施，本领域技术人员可以在不违背本说明书内涵的情况下做类似推广，因此本说明书不受下面公开的具体实施的限制。Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
在本说明书一个或多个实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本说明书一个或多个实施例。在本说明书一个或多个实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本说明书一个或多个实施例中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and/or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
应当理解，尽管在本说明书一个或多个实施例中可能采用术语第一、第二等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本说明书一个或多个实施例范围的情况下，第一也可以被称为第二，类似地，第二也可以被称为第一。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
首先，对本说明书一个或多个实施例涉及的名词术语进行解释。First, the terms involved in one or more embodiments of this specification are explained.
第一图像：包括目标对象的当前场景的真实场景图像，是展示给用户看的图像，该图像中包括当前场景的真实色彩。The first image: a real scene image of the current scene including the target object, which is an image displayed to the user and includes the real colors of the current scene.
第二图像：包括目标对象的当前场景的渲染图像，是展示给开发人员看的图像，该图像中相同类别的目标对象的色彩是相同的，但与真实色彩可能是不同的，仅为了区分不同类别的目标对象，以便于可以直观地展示出该图像中包括几种类别的目标对象。Second image: A rendered image of the current scene including the target object. This image is displayed to the developer. The colors of the target objects of the same category in this image are the same, but may be different from the real colors. This is only used to distinguish target objects of different categories so that the image can be intuitively displayed to include several categories of target objects.
在本说明书中，提供了一种图像处理方法，本说明书同时涉及一种图像处理装置，一种计算设备，以及一种计算机可读存储介质，在下面的实施例中逐一进行详细说明。In this specification, an image processing method is provided. This specification also relates to an image processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.
图1示出了根据本说明书一实施例提供的一种图像处理方法的流程图，具体包括以下步骤：FIG1 shows a flow chart of an image processing method provided according to an embodiment of the present specification, which specifically includes the following steps:
步骤102，接收针对当前场景的图像获取任务。Step 102: receiving an image acquisition task for the current scene.
作为一种示例，图像获取任务可以是获取当前场景的图像。As an example, the image acquisition task may be to acquire an image of the current scene.
示例性地，在游戏场景中，用户在玩游戏的过程中，可能会接收到游戏中的任务，该任务可能需要提供游戏中采集到的图像。For example, in a game scenario, a user may receive a task in the game while playing the game, and the task may require providing images captured in the game.
步骤104，基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签。Step 104: based on the image acquisition task, collect a first image of the current scene, obtain configuration information of the target object included in the current scene and add it to the first image, wherein the configuration information includes a target category label of the target object.
作为一种示例，配置信息可以用于描述目标对象的特征。目标类别标签可以用于标识目标对象的类别。例如，该类别可以是猫、狗、电视、人、沙发、桌子等等。As an example, the configuration information can be used to describe the characteristics of the target object. The target category label can be used to identify the category of the target object. For example, the category can be a cat, a dog, a television, a person, a sofa, a table, etc.
作为一种示例，配置信息还可以包括目标对象的全局标识，该全局标识可以用于唯一标识一个目标对象，且该全局标识可以是在创建目标对象时设置的，并且，该全局标识可以是数字、字母等。As an example, the configuration information may also include a global identifier of the target object, which may be used to uniquely identify a target object. The global identifier may be set when the target object is created, and the global identifier may be numbers, letters, and the like.
在一些实施例中，设备在采集当前场景的第一图像的过程中，可以获取当前场景包括的目标对象的全局标识，基于全局标识和配置信息的对应关系，可以确定每个目标对象的配置信息，该配置信息中可以包括目标对象的目标类别标签，因此，可以将该目标类别标签添加至第一图像的目标对象中。In some embodiments, during the process of capturing the first image of the current scene, the device can obtain a global identifier of the target objects included in the current scene, and based on the correspondence between the global identifier and the configuration information, can determine the configuration information of each target object. The configuration information may include a target category label of the target object, and therefore, the target category label can be added to the target object in the first image.
示例性地，假设当前场景中包括两个目标对象，接收到图像获取任务后，用户可以点击屏幕的拍照按钮，对屏幕上显示的当前场景进行拍摄，在此过程中，设备可以获取到当前场景中两个目标对象的全局标识，分别为A和B，且根据该两个目标对象的全局标识获取每个目标对象的配置信息，即获取目标对象A的配置信息和目标对象B的配置信息，可以将目标对象A的配置信息中的目标类别标签a添加至第一图像中目标对象A处，将目标对象B的配置信息中的目标类别标签b添加至第一图像中目标对象B处。Exemplarily, assuming that the current scene includes two target objects, after receiving the image acquisition task, the user can click the photo button on the screen to take a picture of the current scene displayed on the screen. During this process, the device can obtain the global identification of the two target objects in the current scene, namely A and B, and obtain the configuration information of each target object based on the global identification of the two target objects, that is, obtain the configuration information of target object A and the configuration information of target object B, and the target category label a in the configuration information of target object A can be added to the target object A in the first image, and the target category label b in the configuration information of target object B can be added to the target object B in the first image.
需要说明的是，在图像获取任务对采集到的图像有要求的情况下，采集到图像后需要确定图像是否符合要求，为了便于后续识别采集到的图像中的目标对象是否符合要求，可以预先为目标对象设置标签。It should be noted that when the image acquisition task has requirements for the collected image, it is necessary to determine whether the image meets the requirements after the image is collected. In order to facilitate the subsequent identification of whether the target object in the collected image meets the requirements, a label can be set for the target object in advance.
在一些实施例中，对获取到的图像的要求可能是需要包括特定类别的目标对象。因此，基于所述图像获取任务，采集所述当前场景的第一图像之前，还包括：生成所述目标对象的目标类别标签；将所述目标类别标签存储至所述目标对象的配置信息中。In some embodiments, the requirement for the acquired image may be to include a target object of a specific category. Therefore, based on the image acquisition task, before acquiring the first image of the current scene, it also includes: generating a target category label for the target object; and storing the target category label in the configuration information of the target object.
也就是说，可以预先为目标对象设置目标类别标签，并将目标类别标签存储至目标对象的配置信息中。如此，在获取目标对象的配置信息时，可以获取到目标对象的目标类别标签并添加至第一图像中，以便于对第一图像进行识别，确定第一图像中的目标对象是否符合要求。That is, a target category label can be set for the target object in advance, and the target category label can be stored in the configuration information of the target object. In this way, when the configuration information of the target object is obtained, the target category label of the target object can be obtained and added to the first image, so as to identify the first image and determine whether the target object in the first image meets the requirements.
例如，在创建目标对象时，可以设置目标对象的全局标识为A，且该目标对象是沙发，可以设置目标对象的目标类别标签为shafa，则可以将该目标类别标签存储至目标对象的配置信息中。For example, when creating a target object, the global identifier of the target object may be set to A, and the target object is a sofa, the target category label of the target object may be set to shafa, and the target category label may be stored in the configuration information of the target object.
在另一些实施例中，对获取到的图像的要求可能是需要包括特定行为的目标对象，因此，基于所述图像获取任务，采集所述当前场景的第一图像之前还包括：基于检测到的行为指令生成所述目标对象的目标行为标签；将所述目标行为标签存储至所述目标对象的配置信息中。In other embodiments, the requirement for the acquired image may be to include a target object with specific behavior. Therefore, based on the image acquisition task, before collecting the first image of the current scene, it also includes: generating a target behavior label of the target object based on the detected behavior instructions; and storing the target behavior label in the configuration information of the target object.
作为一种示例，行为指令中可以包括具体的行为。例如，行为指令中可以包括跑、跳、跨等等行为。As an example, the behavior instruction may include specific behaviors, such as running, jumping, leaping, etc.
其中，目标行为标签可以用于表示目标对象的行为。例如，目标对象的行为可以是跑、跳、走等等。The target behavior tag may be used to represent the behavior of the target object. For example, the behavior of the target object may be running, jumping, walking, etc.
也就是说，可以预先根据检测到的行为指令生成目标对象的目标行为标签，用于标识目标对象的行为，并将该目标行为标签存储至目标对象的配置信息中。如此，在获取目标对象的配置信息时，可以获取到目标对象的目标行为标签并添加至第一图像中，以便于对第一图像进行识别，确定第一图像中的目标对象是否符合要求。That is, a target behavior tag of the target object can be generated in advance according to the detected behavior instruction to identify the behavior of the target object, and the target behavior tag is stored in the configuration information of the target object. In this way, when the configuration information of the target object is obtained, the target behavior tag of the target object can be obtained and added to the first image, so as to identify the first image and determine whether the target object in the first image meets the requirements.
例如，若用户想要目标对象A执行蹦的动作，则可以通过设备的交互界面触发目标对象A对应的行为空间中“蹦”对应的选项，则设备可以检测到针对目标对象的行为指令，且该行为指令中包括“蹦”这个行为，则可以基于该行为指令为目标对象A生成目标行为标签，该目标行为标签可以是beng，用于表示目标对象A在执行“蹦”这个行为，并且，可以将该目标行为标签存储至目标对象的配置信息中。For example, if the user wants the target object A to perform a jumping action, the user can trigger the option corresponding to "jump" in the behavior space corresponding to the target object A through the device's interactive interface. The device can detect the behavior instructions for the target object, and the behavior instructions include the "jump" behavior. A target behavior label can be generated for the target object A based on the behavior instructions. The target behavior label can be beng, which is used to indicate that the target object A is performing the "jump" behavior, and the target behavior label can be stored in the configuration information of the target object.
步骤106，基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。Step 106: determine the target category of the target object based on the target category label, and render the target object to obtain a second image of the current scene including the target object.
其中，第二图像可以是包括目标对象的当前场景的渲染图像，该图像中目标对象的颜色与目标对象的真实色彩是不同的，其色彩仅为了区分不同类别的目标对象。The second image may be a rendered image of the current scene including the target object, and the color of the target object in the image is different from the real color of the target object, and the color is only used to distinguish target objects of different categories.
在实施中，可以预先设置类别标签与类别的对应关系，如此，基于目标类别标签，可以从该对应关系中确定与该目标类别标签对应的类别，并以确定的类别为目标类别。In implementation, the correspondence between the category label and the category may be preset, so that based on the target category label, the category corresponding to the target category label may be determined from the correspondence, and the determined category may be used as the target category.
例如，可以预先设置类别标签shafa与类别沙发对应，类别标签yizi与类别椅子对应，类别标签dianshi与类别电视对应。假设目标类别标签为dianshi，则可以确定目标对象的目标类别为电视。For example, the category label shafa may be preset to correspond to the category sofa, the category label yizi may correspond to the category chair, and the category label dianshi may correspond to the category television. Assuming that the target category label is dianshi, it may be determined that the target category of the target object is television.
进一步地，所述方法还包括：若所述目标类别为预设类别，确定完成所述图像获取任务。Furthermore, the method further includes: if the target category is a preset category, determining that the image acquisition task is completed.
在一种可能的实现方式中，若图像获取任务对获取的第一图像的要求是必须包括预设类别的目标图像，则可以对第一图像进行识别，由于第一图像中包括目标对象的目标类别标签，则可以基于目标类别标签确定第一图像中目标对象的目标类别，如果目标类别是预设类别，可以确定该第一图像符合图像获取任务的要求，即完成了图像获取任务。In one possible implementation, if the image acquisition task requires that the first image acquired must include a target image of a preset category, the first image can be identified. Since the first image includes a target category label of the target object, the target category of the target object in the first image can be determined based on the target category label. If the target category is a preset category, it can be determined that the first image meets the requirements of the image acquisition task, that is, the image acquisition task is completed.
进一步地，所述配置信息还可以包括目标行为标签，所述方法还包括：基于所述目标行为标签，确定所述目标对象的目标行为。Furthermore, the configuration information may further include a target behavior tag, and the method further includes: determining a target behavior of the target object based on the target behavior tag.
也就是说，若配置信息中包括目标行为标签，则第一图像中可以包括目标对象的目标行为标签，可以根据目标行为标签确定目标对象的目标行为。That is, if the configuration information includes a target behavior tag, the first image may include the target behavior tag of the target object, and the target behavior of the target object may be determined according to the target behavior tag.
示例性地，可以预先设置行为标签与行为的对应关系，如此，基于目标行为标签，可以从该对应关系中确定与该目标行为标签对应的行为，并以确定的行为为目标行为。Exemplarily, a correspondence between a behavior label and a behavior may be preset, so that based on a target behavior label, a behavior corresponding to the target behavior label may be determined from the correspondence, and the determined behavior may be used as the target behavior.
例如，可以预先设置行为标签pao与行为“跑”对应，行为标签tiao与行为“跳”对应，行为标签kua与行为“跨”对应。假设目标行为标签为tiao，则可以确定目标对象的目标行为为“跳”。For example, the behavior label pao can be preset to correspond to the behavior "run", the behavior label tiao can correspond to the behavior "jump", and the behavior label kua can correspond to the behavior "cross". Assuming that the target behavior label is tiao, the target behavior of the target object can be determined to be "jump".
进一步地，所述方法还包括：若所述目标类别为预设类别，且所述目标行为为预设行为，确定完成所述图像获取任务。Furthermore, the method further includes: if the target category is a preset category, and the target behavior is a preset behavior, determining that the image acquisition task is completed.
在另一种可能的实现方式中，若图像获取任务对获取的第一图像的要求是必须包括预设类别的目标图像，且预设类别的目标图像的行为是预设行为，则可以对第一图像进行识别，由于第一图像中包括目标对象的目标类别标签和目标行为标签，则可以基于目标类别标签确定第一图像中目标对象的目标类别，并基于目标对象的目标行为标签确定第一图像中目标对象的目标行为，如果目标类别是预设类别，且预设类别的目标对象的目标行为是预设行为，可以确定该第一图像符合图像获取任务的要求，即完成了图像获取任务。In another possible implementation, if the image acquisition task requires that the first image acquired must include a target image of a preset category, and the behavior of the target image of the preset category is a preset behavior, the first image can be recognized. Since the first image includes a target category label and a target behavior label of the target object, the target category of the target object in the first image can be determined based on the target category label, and the target behavior of the target object in the first image can be determined based on the target behavior label of the target object. If the target category is a preset category, and the target behavior of the target object of the preset category is a preset behavior, it can be determined that the first image meets the requirements of the image acquisition task, that is, the image acquisition task is completed.
在一些实施例中，对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像的具体实现可以包括：基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色；基于所述目标渲染颜色对所述当前场景中包括的目标对象进行渲染，得到包括所述目标对象的当前场景的第二图像。In some embodiments, a specific implementation of rendering the target object to obtain a second image of the current scene including the target object may include: determining a target rendering color corresponding to the target object based on the target category label; and rendering the target object included in the current scene based on the target rendering color to obtain a second image of the current scene including the target object.
也就是说，可以根据目标类别标签确定目标对象对应的目标渲染颜色，并根据该目标渲染颜色对目标对象进行渲染，可以得到第二图像。That is, the target rendering color corresponding to the target object can be determined according to the target category label, and the target object can be rendered according to the target rendering color to obtain the second image.
如此，按照不同的颜色将不同类别的目标对象进行渲染，可以直观地看出第二图像中包括的多个目标对象的类别，若第二图像中多个目标对象的类别与当前场景中实际存在的多个目标对象的类别不同，可以认为识别程序可能存在问题，进而可以对程序进行调试，以使得识别更加准确。In this way, by rendering target objects of different categories according to different colors, the categories of multiple target objects included in the second image can be intuitively seen. If the categories of the multiple target objects in the second image are different from the categories of the multiple target objects actually existing in the current scene, it can be considered that there may be problems with the recognition program, and the program can be debugged to make the recognition more accurate.
作为一种示例，基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色之前，还包括：确定类别标签与渲染颜色的对应关系；相应地，所述基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色可以包括：基于所述目标类别标签，从所述对应关系中确定与所述目标类别标签对应的渲染颜色，以所确定的渲染颜色为所述目标渲染颜色。As an example, before determining the target rendering color corresponding to the target object based on the target category label, the method further includes: determining a correspondence between the category label and the rendering color; accordingly, determining the target rendering color corresponding to the target object based on the target category label may include: based on the target category label, determining the rendering color corresponding to the target category label from the correspondence, and using the determined rendering color as the target rendering color.
也就是说，可以预先设置类别标签与渲染颜色的对应关系，则根据目标类别标签，可以从第一关系中获取与该目标类别标签对应的渲染颜色，并将该渲染颜色确定为目标对象的目标渲染颜色。That is, the correspondence between the category label and the rendering color may be preset, and then according to the target category label, the rendering color corresponding to the target category label may be acquired from the first relationship, and the rendering color may be determined as the target rendering color of the target object.
例如，可以确定类别标签shafa与渲染颜色黄色对应，类别标签dianshiji与渲染颜色绿色对应，类别标签mao与渲染颜色蓝色对应，如此，可以确定多组对应关系。在确定目标对象对应的目标渲染颜色时，可以基于目标对象的目标类别标签，确定目标对象对应的目标渲染颜色。假设目标对象的目标类别标签为dianshi，在对应关系中，与类别标签dianshi对应的渲染颜色为绿色，则可以确定目标对象的目标渲染颜色为绿色。For example, it can be determined that the category label shafa corresponds to the rendering color yellow, the category label dianshiji corresponds to the rendering color green, and the category label mao corresponds to the rendering color blue. In this way, multiple sets of corresponding relationships can be determined. When determining the target rendering color corresponding to the target object, the target rendering color corresponding to the target object can be determined based on the target category label of the target object. Assuming that the target category label of the target object is dianshi, in the corresponding relationship, the rendering color corresponding to the category label dianshi is green, then it can be determined that the target rendering color of the target object is green.
本说明书提供的图像处理方法，接收针对当前场景的图像获取任务；基于所述图像获取任务，基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。通过预先为目标对象设置目标类别标签并将目标类别标签添加至第一图像中，可以快速确定第一图像中目标对象的类别，并且，根据目标对象的目标类别标签对目标对象进行渲染，可以直观地将目标对象的类别展示出来，以便于后续进行调试。The image processing method provided in this specification receives an image acquisition task for a current scene; based on the image acquisition task, a first image of the current scene is collected, configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object; based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object. By setting a target category label for the target object in advance and adding the target category label to the first image, the category of the target object in the first image can be quickly determined, and by rendering the target object according to the target category label of the target object, the category of the target object can be intuitively displayed for subsequent debugging.
下述结合附图2，以本说明书提供的图像处理方法在游戏场景的应用为例，对所述图像处理方法进行进一步说明。其中，图2示出了本说明书一实施例提供的一种应用于游戏场景的图像处理方法的处理流程图，具体包括以下步骤：The following is a further description of the image processing method provided in this specification, taking the application of the image processing method provided in this specification in a game scene as an example, in conjunction with FIG2. FIG2 shows a processing flow chart of an image processing method applied to a game scene provided in an embodiment of this specification, which specifically includes the following steps:
步骤202，生成游戏对象的目标类别标签，将所述目标类别标签存储至所述游戏对象的配置信息中。Step 202: Generate a target category tag for the game object, and store the target category tag in the configuration information of the game object.
在本实施例中，该游戏对象可以为家具、宠物等等。例如，游戏对象可以为沙发、电视机、猫等等。相应地，游戏对象的目标类别标签可以为shafa、dainshiji、mao等等。In this embodiment, the game object may be furniture, pets, etc. For example, the game object may be a sofa, a television, a cat, etc. Accordingly, the target category label of the game object may be shafa, dainshiji, mao, etc.
例如，可以生成沙发的目标类别标签为shafa，并将该标签shafa存储至游戏对象沙发的配置信息中。生成宠物A的目标类别标签为mao，并将该标签mao存储至宠物A的配置信息中。For example, a target category label of a sofa may be generated as shafa, and the label shafa may be stored in the configuration information of the game object sofa. A target category label of pet A may be generated as mao, and the label mao may be stored in the configuration information of pet A.
步骤204，基于检测到的行为指令生成所述游戏对象的目标行为标签，将所述目标行为标签存储至所述游戏对象的配置信息中。Step 204: Generate a target behavior tag for the game object based on the detected behavior instruction, and store the target behavior tag in the configuration information of the game object.
在本步骤中，游戏对象可以为宠物，进一步地，游戏对象可以为猫、狗、鸟等等。相应地，游戏对象的目标类别标签可以为mao、gou、naio等等。In this step, the game object may be a pet, and further, the game object may be a cat, a dog, a bird, etc. Accordingly, the target category label of the game object may be mao, gou, naio, etc.
例如，若接收到针对宠物A的“跑”指令，可以生成宠物A的目标行为标签为pao，并将该标签pao存储至宠物A的配置信息中。若接收到针对宠物A的“跳”指令，可以生成宠物A的目标行为标签为tiao，并将该标签tiao存储至宠物A的配置信息中。For example, if a "run" command is received for pet A, a target behavior tag of pet A can be generated as pao, and the tag pao can be stored in the configuration information of pet A. If a "jump" command is received for pet A, a target behavior tag of pet A can be generated as tiao, and the tag tiao can be stored in the configuration information of pet A.
上述步骤202-步骤204是步骤104的下位描述，其具体实现可以参见步骤104的相关描述，本实施例在此不再赘述。The above steps 202 to 204 are subordinate descriptions of step 104. For their specific implementation, please refer to the relevant description of step 104, which will not be repeated in this embodiment.
步骤206，接收针对当前场景的图像获取任务。Step 206: receiving an image acquisition task for the current scene.
用户在玩游戏的过程中，可能会接收到游戏中的任务，该任务需要提供游戏中拍到的一些图像。即在用户玩游戏的过程中，可以接收到图像获取任务，该图像获取任务是为了获取到当前场景的场景图像。When playing a game, the user may receive a task in the game, which requires providing some images taken in the game. That is, when playing a game, the user may receive an image acquisition task, which is to acquire a scene image of the current scene.
步骤208，基于所述图像获取任务，采集当前场景的第一图像，获取所述当前场景包括的游戏对象的配置信息并添加至第一图像中。Step 208: Based on the image acquisition task, a first image of the current scene is captured, and configuration information of the game objects included in the current scene is acquired and added to the first image.
其中，所述配置信息包括所述游戏对象的目标类别标签和所述游戏对象的目标行为标签。Wherein, the configuration information includes a target category label of the game object and a target behavior label of the game object.
示例性地，假设当前场景中包括一个沙发和两只猫，接收到图像获取任务后，用户可以点击屏幕的拍照按钮，用于对屏幕上显示的当前场景进行拍摄。在此过程中，设备可以获取到当前场景中包括的一个沙发的配置信息和两只猫的配置信息，得到第一图像后，可以将该沙发的配置信息添加至第一图像中沙发对应的位置处，将两只猫的配置信息分别添加至第一图像中两只猫对应的位置处。For example, assuming that the current scene includes a sofa and two cats, after receiving the image acquisition task, the user can click the camera button on the screen to take a picture of the current scene displayed on the screen. In this process, the device can obtain the configuration information of a sofa and the configuration information of two cats included in the current scene. After obtaining the first image, the configuration information of the sofa can be added to the position corresponding to the sofa in the first image, and the configuration information of the two cats can be added to the positions corresponding to the two cats in the first image.
例如，假设一个沙发的全局标识为A，两只猫的全局标识分别为B和C，且全局标识为B的猫正在执行“跳”的指令，全局标识为C的猫正在执行“跑”的指令，则一个沙发的配置信息可以包括目标类别标签shafa，全局标识为B的猫的配置信息为目标类别标签mao和目标行为标签tiao，全局标识为C的猫的配置信息为目标类别标签mao和目标行为标签pao。即在第一图像中可以包括一个沙发和两只猫，且该沙发所在的位置处标记有目标类别标签shafa，猫B所在的位置处标记有目标类别标签mao和目标行为标签tiao，猫C所在的位置处标记有目标类别标签mao和目标行为标签pao。For example, assuming that the global identifier of a sofa is A, the global identifiers of two cats are B and C, and the cat with the global identifier B is executing the "jump" instruction, and the cat with the global identifier C is executing the "run" instruction, then the configuration information of a sofa may include the target category label shafa, the configuration information of the cat with the global identifier B is the target category label mao and the target behavior label tiao, and the configuration information of the cat with the global identifier C is the target category label mao and the target behavior label pao. That is, the first image may include a sofa and two cats, and the position of the sofa is marked with the target category label shafa, the position of cat B is marked with the target category label mao and the target behavior label tiao, and the position of cat C is marked with the target category label mao and the target behavior label pao.
需要说明的是，上述步骤208是步骤104的下位描述，其具体实现可以参见步骤104的相关描述，本实施例在此不再赘述。It should be noted that the above step 208 is a subordinate description of step 104. For its specific implementation, please refer to the relevant description of step 104, which will not be repeated in this embodiment.
步骤210，基于所述目标类别标签，确定所述游戏对象的目标类别。Step 210: Determine the target category of the game object based on the target category label.
继续上述举例，可以对第一图像进行识别，该第一图像中，全局标识为A的游戏对象的目标类别标签为shafa，全局标识分别为B和C的两个游戏对象的目标类别标签均为mao，根据目标类别标签与目标类别的对应关系，可以确定全局标识为A的游戏对象的目标类别是沙发，确定全局标识分别为B和C的两个游戏对象的目标类别均是猫。Continuing with the above example, the first image can be identified. In the first image, the target category label of the game object with the global identification A is shafa, and the target category labels of the two game objects with the global identifications B and C are both mao. According to the correspondence between the target category label and the target category, it can be determined that the target category of the game object with the global identification A is sofa, and it can be determined that the target category of the two game objects with the global identifications B and C are both cats.
步骤212，基于所述目标类别标签，确定所述游戏对象对应的目标渲染颜色。Step 212: Determine the target rendering color corresponding to the game object based on the target category label.
在实施中，可以预先确定类别标签与渲染颜色的对应关系。基于所述目标类别标签，从所述对应关系中确定与所述目标类别标签对应的渲染颜色，以所确定的渲染颜色为所述目标渲染颜色。In implementation, the correspondence between the category label and the rendering color may be predetermined. Based on the target category label, the rendering color corresponding to the target category label is determined from the correspondence, and the determined rendering color is used as the target rendering color.
例如，可以确定类别标签shafa与渲染颜色黄色对应，类别标签dianshiji与渲染颜色绿色对应，类别标签mao与渲染颜色蓝色对应，如此，可以确定多组对应关系。在确定游戏对象对应的目标渲染颜色时，可以基于游戏对象的目标类别标签，确定游戏对象对应的目标渲染颜色。For example, it can be determined that the category label shafa corresponds to the rendering color yellow, the category label dianshiji corresponds to the rendering color green, and the category label mao corresponds to the rendering color blue, and thus, multiple sets of corresponding relationships can be determined. When determining the target rendering color corresponding to the game object, the target rendering color corresponding to the game object can be determined based on the target category label of the game object.
继续上述举例，假设当前场景中包括三个游戏对象，全局标识分别为A、B、C，全局标识为A的游戏对象的目标类别标签为shafa，全局标识分别为B和C的两个游戏对象的目标类别标签均为mao。基于目标类别标签shafa，从对应关系中可以确定与shafa对应的渲染颜色为黄色，基于目标类别标签mao，从对应关系中可以确定与mao对应的渲染颜色为蓝色。Continuing with the above example, assume that the current scene includes three game objects, with global identifiers A, B, and C. The target category label of the game object with global identifier A is shafa, and the target category labels of the two game objects with global identifiers B and C are both mao. Based on the target category label shafa, it can be determined from the correspondence that the rendering color corresponding to shafa is yellow, and based on the target category label mao, it can be determined from the correspondence that the rendering color corresponding to mao is blue.
步骤214，基于所述目标渲染颜色对所述当前场景中包括的游戏对象进行渲染，得到所述包括所述游戏对象的当前场景的第二图像。Step 214: Render the game object included in the current scene based on the target rendering color to obtain a second image of the current scene including the game object.
例如，可以将全局标识A对应的游戏对象渲染成黄色，将全局标识B和C对应的游戏对象均渲染成蓝色。如此，可以清楚直观地确定当前场景中包括的三个游戏对象为两只猫和一个沙发。For example, the game object corresponding to the global identifier A can be rendered yellow, and the game objects corresponding to the global identifiers B and C can be rendered blue. In this way, it can be clearly and intuitively determined that the three game objects included in the current scene are two cats and a sofa.
步骤216，基于所述目标行为标签，确定所述游戏对象的目标行为。Step 216, determining the target behavior of the game object based on the target behavior tag.
例如，假设当前游戏场景包括的三个游戏对象中，有两个游戏对象包括目标行为标签，这两个游戏对象均为猫，且这两只猫的全局标识分别为B和C，全局标识为B的猫的目标行为标签为tiao，全局标识为C的猫的目标行为标签为pao，根据目标类别标签与目标类别的对应关系，可以确定全局标识为B的猫的目标行为为跳，全局标识为C的猫的目标行为为跑。For example, assuming that among the three game objects included in the current game scene, two game objects include target behavior labels, both of which are cats, and the global identifications of the two cats are B and C respectively, the target behavior label of the cat with the global identification B is tiao, and the target behavior label of the cat with the global identification C is pao. According to the correspondence between the target category label and the target category, it can be determined that the target behavior of the cat with the global identification B is jump, and the target behavior of the cat with the global identification C is run.
需要说明的是，步骤216与步骤212没有严格的先后执行顺序。It should be noted that there is no strict execution order between step 216 and step 212 .
步骤218，若所述目标类别为预设类别，且所述目标行为为预设行为，确定完成所述图像获取任务。Step 218: If the target category is a preset category and the target behavior is a preset behavior, determine that the image acquisition task is completed.
假设预设类别为沙发和猫，预设行为为猫的行为为跑和跳，继续上述举例，当前场景中包括的三个目标对象为一个沙发和两只猫，且两只猫的目标行为分别为跑和跳，可以确定完成图像获取任务。Assuming that the preset categories are sofa and cat, and the preset behaviors are running and jumping of cats, continuing with the above example, the three target objects included in the current scene are a sofa and two cats, and the target behaviors of the two cats are running and jumping respectively, it can be determined that the image acquisition task is completed.
需要说明的是，上述步骤210-步骤218是步骤106的下位描述，其具体实现可以参见步骤106的相关描述，本实施例在此不再赘述。It should be noted that the above steps 210 to 218 are subordinate descriptions of step 106. For their specific implementation, please refer to the relevant description of step 106, which will not be repeated in this embodiment.
本说明书提供的图像处理方法，基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。通过预先为目标对象设置目标类别标签并将目标类别标签添加至第一图像中，可以快速确定第一图像中目标对象的类别，并且，根据目标对象的目标类别标签对目标对象进行渲染，可以直观地将目标对象的类别展示出来，以便于后续进行调试。The image processing method provided in this specification, based on the image acquisition task, collects the first image of the current scene, obtains the configuration information of the target object included in the current scene and adds it to the first image, wherein the configuration information includes the target category label of the target object; based on the target category label, determines the target category of the target object, and renders the target object to obtain a second image of the current scene including the target object. By setting the target category label for the target object in advance and adding the target category label to the first image, the category of the target object in the first image can be quickly determined, and by rendering the target object according to the target category label of the target object, the category of the target object can be intuitively displayed for subsequent debugging.
与上述方法实施例相对应，本说明书还提供了图像处理装置实施例，图3示出了本说明书一实施例提供的一种图像处理装置的结构示意图。如图3所示，该装置包括：Corresponding to the above method embodiment, this specification also provides an image processing device embodiment, and FIG3 shows a schematic diagram of the structure of an image processing device provided in an embodiment of this specification. As shown in FIG3, the device includes:
接收模块302，被配置为接收针对当前场景的图像获取任务；A receiving module 302 is configured to receive an image acquisition task for a current scene;
获取模块304，被配置为基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；The acquisition module 304 is configured to acquire a first image of the current scene based on the image acquisition task, acquire configuration information of a target object included in the current scene and add the configuration information to the first image, wherein the configuration information includes a target category label of the target object;
渲染模块306，被配置为基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。The rendering module 306 is configured to determine the target category of the target object based on the target category label, and render the target object to obtain a second image of the current scene including the target object.
可选地，所述渲染模块306被配置为：Optionally, the rendering module 306 is configured to:
基于所述目标类别标签，确定所述目标对象对应的目标渲染颜色；Based on the target category label, determining a target rendering color corresponding to the target object;
基于所述目标渲染颜色对所述当前场景中包括的目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。The target object included in the current scene is rendered based on the target rendering color to obtain a second image of the current scene including the target object.
可选地，所述渲染模块306还被配置为：Optionally, the rendering module 306 is further configured to:
确定类别标签与渲染颜色的对应关系；Determine the correspondence between category labels and rendering colors;
基于所述目标类别标签，从所述对应关系中确定与所述目标类别标签对应的渲染颜色，以所确定的渲染颜色为所述目标渲染颜色。Based on the target category label, a rendering color corresponding to the target category label is determined from the corresponding relationship, and the determined rendering color is used as the target rendering color.
可选地，所述获取模块304还被配置为：Optionally, the acquisition module 304 is further configured to:
生成所述目标对象的目标类别标签；Generating a target category label of the target object;
将所述目标类别标签存储至所述目标对象的配置信息中。The target category label is stored in the configuration information of the target object.
可选地，所述获取模块304还被配置为：Optionally, the acquisition module 304 is further configured to:
基于检测到的行为指令生成所述目标对象的目标行为标签；generating a target behavior label of the target object based on the detected behavior instruction;
将所述目标行为标签存储至所述目标对象的配置信息中。The target behavior tag is stored in the configuration information of the target object.
可选地，所述渲染模块306还被配置为：Optionally, the rendering module 306 is further configured to:
若所述目标类别为预设类别，确定完成所述图像获取任务。If the target category is a preset category, it is determined that the image acquisition task is completed.
可选地，所述渲染模块306还被配置为：Optionally, the rendering module 306 is further configured to:
所述配置信息还包括目标行为标签，基于所述目标行为标签，确定所述目标对象的目标行为。The configuration information also includes a target behavior tag, based on which the target behavior of the target object is determined.
可选地，所述渲染模块306，被配置为：Optionally, the rendering module 306 is configured to:
若所述目标类别为预设类别，且所述目标行为为预设行为，确定完成所述图像获取任务。If the target category is a preset category and the target behavior is a preset behavior, it is determined that the image acquisition task is completed.
本说明书提供的图像处理方法，基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。通过预先为目标对象设置目标类别标签并将目标类别标签添加至第一图像中，可以快速确定第一图像中目标对象的类别，并且，根据目标对象的目标类别标签对目标对象进行渲染，可以直观地将目标对象的类别展示出来，以便于后续进行调试。The image processing method provided in this specification, based on the image acquisition task, collects the first image of the current scene, obtains the configuration information of the target object included in the current scene and adds it to the first image, wherein the configuration information includes the target category label of the target object; based on the target category label, determines the target category of the target object, and renders the target object to obtain a second image of the current scene including the target object. By setting the target category label for the target object in advance and adding the target category label to the first image, the category of the target object in the first image can be quickly determined, and by rendering the target object according to the target category label of the target object, the category of the target object can be intuitively displayed for subsequent debugging.
上述为本实施例的一种图像处理装置的示意性方案。需要说明的是，该图像处理装置的技术方案与上述的图像处理方法的技术方案属于同一构思，图像处理装置的技术方案未详细描述的细节内容，均可以参见上述图像处理方法的技术方案的描述。The above is a schematic scheme of an image processing device of this embodiment. It should be noted that the technical scheme of the image processing device and the technical scheme of the above-mentioned image processing method belong to the same concept, and the details not described in detail in the technical scheme of the image processing device can be referred to the description of the technical scheme of the above-mentioned image processing method.
图4示出了根据本说明书一实施例提供的一种计算设备400的结构框图。该计算设备400的部件包括但不限于存储器410和处理器420。处理器420与存储器410通过总线430相连接，数据库450用于保存数据。Fig. 4 shows a block diagram of a computing device 400 according to an embodiment of the present specification. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.
计算设备400还包括接入设备440，接入设备440使得计算设备400能够经由一个或多个网络460通信。这些网络的示例包括公用交换电话网(PSTN)、局域网(LAN)、广域网(WAN)、个域网(PAN)或诸如因特网的通信网络的组合。接入设备440可以包括有线或无线的任何类型的网络接口(例如，网络接口卡(NIC))中的一个或多个，诸如IEEE802.11无线局域网(WLAN)无线接口、全球微波互联接入(Wi-MAX)接口、以太网接口、通用串行总线(USB)接口、蜂窝网络接口、蓝牙接口、近场通信(NFC)接口，等等。The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.
在本说明书的一个实施例中，计算设备400的上述部件以及图4中未示出的其他部件也可以彼此相连接，例如通过总线。应当理解，图4所示的计算设备结构框图仅仅是出于示例的目的，而不是对本说明书范围的限制。本领域技术人员可以根据需要，增添或替换其他部件。In one embodiment of the present specification, the above components of the computing device 400 and other components not shown in FIG. 4 may also be connected to each other, for example, through a bus. It should be understood that the computing device structure block diagram shown in FIG. 4 is only for illustrative purposes and is not intended to limit the scope of the present specification. Those skilled in the art may add or replace other components as needed.
计算设备400可以是任何类型的静止或移动计算设备，包括移动计算机或移动计算设备(例如，平板计算机、个人数字助理、膝上型计算机、笔记本计算机、上网本等)、移动电话(例如，智能手机)、可佩戴的计算设备(例如，智能手表、智能眼镜等)或其他类型的移动设备，或者诸如台式计算机或PC的静止计算设备。计算设备400还可以是移动式或静止式的服务器。Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.
其中，处理器420用于执行如下计算机可执行指令：The processor 420 is used to execute the following computer executable instructions:
接收针对当前场景的图像获取任务；Receive an image acquisition task for the current scene;
基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；Based on the image acquisition task, a first image of the current scene is acquired, and configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object;
基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。Based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object.
上述为本实施例的一种计算设备的示意性方案。需要说明的是，该计算设备的技术方案与上述的图像处理方法的技术方案属于同一构思，计算设备的技术方案未详细描述的细节内容，均可以参见上述图像处理方法的技术方案的描述。The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned image processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned image processing method.
本说明书一实施例还提供一种计算机可读存储介质，其存储有计算机指令，该指令被处理器执行时以用于：An embodiment of the present specification further provides a computer-readable storage medium storing computer instructions, which are used when executed by a processor to:
接收针对当前场景的图像获取任务；Receive an image acquisition task for the current scene;
基于所述图像获取任务，采集所述当前场景的第一图像，获取所述当前场景包括的目标对象的配置信息并添加至所述第一图像中，其中，所述配置信息包括所述目标对象的目标类别标签；Based on the image acquisition task, a first image of the current scene is acquired, and configuration information of a target object included in the current scene is acquired and added to the first image, wherein the configuration information includes a target category label of the target object;
基于所述目标类别标签，确定所述目标对象的目标类别，并对所述目标对象进行渲染，得到包括所述目标对象的所述当前场景的第二图像。Based on the target category label, the target category of the target object is determined, and the target object is rendered to obtain a second image of the current scene including the target object.
上述为本实施例的一种计算机可读存储介质的示意性方案。需要说明的是，该存储介质的技术方案与上述的图像处理方法的技术方案属于同一构思，存储介质的技术方案未详细描述的细节内容，均可以参见上述图像处理方法的技术方案的描述。The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned image processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned image processing method.
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
所述计算机指令包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
需要说明的是，对于前述的各方法实施例，为了简便描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本说明书并不受所描述的动作顺序的限制，因为依据本说明书，某些步骤可以采用其它顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定都是本说明书所必须的。It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that this specification is not limited by the order of the actions described, because according to this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this specification.
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其它实施例的相关描述。In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
以上公开的本说明书优选实施例只是用于帮助阐述本说明书。可选实施例并没有详尽叙述所有的细节，也不限制该发明仅为所述的具体实施方式。显然，根据本说明书的内容，可作很多的修改和变化。本说明书选取并具体描述这些实施例，是为了更好地解释本说明书的原理和实际应用，从而使所属技术领域技术人员能很好地理解和利用本说明书。本说明书仅受权利要求书及其全部范围和等效物的限制。The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is limited only by the claims and their full scope and equivalents.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011631540.1ACN112784693B (en) | 2020-12-31 | 2020-12-31 | Image processing method and device |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011631540.1ACN112784693B (en) | 2020-12-31 | 2020-12-31 | Image processing method and device |
| Publication Number | Publication Date |
|---|---|
| CN112784693A CN112784693A (en) | 2021-05-11 |
| CN112784693Btrue CN112784693B (en) | 2024-10-22 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011631540.1AActiveCN112784693B (en) | 2020-12-31 | 2020-12-31 | Image processing method and device |
| Country | Link |
|---|---|
| CN (1) | CN112784693B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920084A (en)* | 2021-09-30 | 2022-01-11 | Oppo广东移动通信有限公司 | Image evaluation method and system |
| CN114155172A (en)* | 2021-12-14 | 2022-03-08 | 广东赛昉科技有限公司 | An image processing method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104910A (en)* | 2019-12-20 | 2020-05-05 | 上海寒武纪信息科技有限公司 | Method for monitoring garbage delivery behavior and related products |
| CN111210435A (en)* | 2019-12-24 | 2020-05-29 | 重庆邮电大学 | Image semantic segmentation method based on local and global feature enhancement module |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10390082B2 (en)* | 2016-04-01 | 2019-08-20 | Oath Inc. | Computerized system and method for automatically detecting and rendering highlights from streaming videos |
| US10929665B2 (en)* | 2018-12-21 | 2021-02-23 | Samsung Electronics Co., Ltd. | System and method for providing dominant scene classification by semantic segmentation |
| WO2020258286A1 (en)* | 2019-06-28 | 2020-12-30 | 深圳市大疆创新科技有限公司 | Image processing method and device, photographing device and movable platform |
| CN111259898B (en)* | 2020-01-08 | 2023-03-24 | 西安电子科技大学 | Crop segmentation method based on unmanned aerial vehicle aerial image |
| CN111833456A (en)* | 2020-06-30 | 2020-10-27 | 北京市商汤科技开发有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN112153400B (en)* | 2020-09-22 | 2022-12-06 | 北京达佳互联信息技术有限公司 | Live broadcast interaction method and device, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104910A (en)* | 2019-12-20 | 2020-05-05 | 上海寒武纪信息科技有限公司 | Method for monitoring garbage delivery behavior and related products |
| CN111210435A (en)* | 2019-12-24 | 2020-05-29 | 重庆邮电大学 | Image semantic segmentation method based on local and global feature enhancement module |
| Publication number | Publication date |
|---|---|
| CN112784693A (en) | 2021-05-11 |
| Publication | Publication Date | Title |
|---|---|---|
| US20210216830A1 (en) | Content tagging | |
| CN107680684B (en) | Method and device for acquiring information | |
| CN115699062A (en) | Augmented reality item set | |
| WO2020000876A1 (en) | Model generating method and device | |
| CN110472516A (en) | A kind of construction method, device, equipment and the system of character image identifying system | |
| CN108346171B (en) | Image processing method, device, equipment and computer storage medium | |
| CN112784693B (en) | Image processing method and device | |
| CN108536467B (en) | Code positioning processing method, device, terminal device and storage medium | |
| CN104917967A (en) | Photographing method and terminal | |
| CN109271929B (en) | Detection method and device | |
| CN113052025B (en) | Image fusion model training method, image fusion method and electronic device | |
| CN107368550A (en) | Information acquisition method, device, medium, electronic device, server and system | |
| CN114307153A (en) | Game asset processing method and device, computer storage medium and electronic equipment | |
| US20140198177A1 (en) | Realtime photo retouching of live video | |
| CN113297416B (en) | Video data storage method, device, electronic device and readable storage medium | |
| CN109670454B (en) | Biological information introduction method, biological information introduction device and terminal equipment | |
| WO2025002130A1 (en) | Image editing method and related device | |
| CN113518217A (en) | Object recognition method, device, server and medium | |
| CN111625101A (en) | Display control method and device | |
| CN115174893B (en) | Image simulation method and device | |
| CN117950983A (en) | User interface testing method, device, electronic device and storage medium | |
| CN110647841B (en) | Image recognition result filtering method, device, computer equipment and storage medium | |
| CN109064416B (en) | Image processing method, device, storage medium and electronic device | |
| CN107852454B (en) | Method and device for sharing and downloading light field images | |
| CN114332351B (en) | Mouse motion reconstruction method and device based on multi-view camera |
| 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information | Address after:519000 Room 102, 202, 302 and 402, No. 325, Qiandao Ring Road, Tangjiawan Town, high tech Zone, Zhuhai City, Guangdong Province, Room 102 and 202, No. 327 and Room 302, No. 329 Applicant after:Zhuhai Jinshan Digital Network Technology Co.,Ltd. Address before:519000 Room 102, 202, 302 and 402, No. 325, Qiandao Ring Road, Tangjiawan Town, high tech Zone, Zhuhai City, Guangdong Province, Room 102 and 202, No. 327 and Room 302, No. 329 Applicant before:ZHUHAI KINGSOFT ONLINE GAME TECHNOLOGY Co.,Ltd. | |
| GR01 | Patent grant | ||
| GR01 | Patent grant |