[go: up one dir, main page]

WO2019161559A1 - 一种图像采集方法、系统、电子设备及计算机程序产品 - Google Patents

一种图像采集方法、系统、电子设备及计算机程序产品 Download PDF

Info

Publication number
WO2019161559A1
WO2019161559A1 PCT/CN2018/077195 CN2018077195W WO2019161559A1 WO 2019161559 A1 WO2019161559 A1 WO 2019161559A1 CN 2018077195 W CN2018077195 W CN 2018077195W WO 2019161559 A1 WO2019161559 A1 WO 2019161559A1
Authority
WO
WIPO (PCT)
Prior art keywords
image acquisition
image
focal length
acquisition module
modules
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/077195
Other languages
English (en)
French (fr)
Inventor
王敏
刘兆祥
廉士国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cloudminds Shenzhen Robotics Systems Co Ltd
Original Assignee
Cloudminds Shenzhen Robotics Systems Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Cloudminds Shenzhen Robotics Systems Co Ltd filed Critical Cloudminds Shenzhen Robotics Systems Co Ltd
Priority to CN201880000155.1A priority Critical patent/CN108401496A/zh
Priority to PCT/CN2018/077195 priority patent/WO2019161559A1/zh
Publication of WO2019161559A1 publication Critical patent/WO2019161559A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/67—Focus control based on electronic image sensor signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
    • H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes

Definitions

  • the present application relates to the field of image acquisition, and in particular, to an image acquisition method, system, electronic device, and computer program product.
  • the cloud robot is an intelligent robot that puts the cognitive system in the cloud, the body, the drive and the sensor are placed on the robot body, and connects the two through mobile communication; the cloud robot is the development direction of the intelligent humanoid robot.
  • the equipment for solving blind people's information is mainly based on equipment such as eyes, helmets and blinds.
  • the information provided by the blind cane is limited; the helmet can be integrated with many functions including navigation obstacle avoidance, but it is slightly cumbersome for information accessibility.
  • Existing smart glasses devices generally only have a single function of telephoto or short focus, and the image capture module capable of fast zooming is relatively expensive, relatively large in size, and not portable enough. And in the process of far and near focus conversion, it is easy to cause the captured image to be blurred.
  • the embodiments of the present application are intended to provide an image acquisition method, system, electronic device, and computer program product, so as to solve the problem that the image acquisition process existing in the prior art cannot fully adapt to the near-far scene.
  • a first aspect of the embodiments of the present application provides an image collection method, where the method includes:
  • each image acquisition module corresponds to a different focal length
  • Images are acquired by the selected image acquisition module.
  • a second aspect of the embodiments of the present application provides an electronic device, including: a display, a memory, one or more processors; and one or more modules, the one or more modules being stored in the And in the memory, configured to be executed by the one or more processors, the one or more modules comprising instructions for performing the various steps in the image acquisition method of the first aspect of the embodiments of the present application.
  • a third aspect of embodiments of the present application provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions When executed by a computer, the computer is caused to perform various steps in the image acquisition method according to the first aspect of the embodiments of the present application.
  • a fourth aspect of the present application provides an image acquisition system, where the system includes an image acquisition device and a selection acquisition device.
  • the image collection device is provided with a plurality of image acquisition modules, and each image acquisition module corresponds to a different image. Focal length, the selection acquisition device is used to select an image acquisition module, and collect images through the selected image acquisition module.
  • the application acquires the user instruction and selects the corresponding focal length according to the user instruction to collect the image, thereby intelligently realizing image collection of different scenes in the near and far, which is universal, flexible and convenient, and is beneficial to the blind person's perception of the surrounding world.
  • FIG. 1 is a flowchart of an image collection method according to an embodiment of the present application.
  • FIG. 2 is a schematic diagram of an image acquisition system according to an embodiment of the present application.
  • FIG. 3 is a flowchart of the operation of the image collection system according to the embodiment of the present application.
  • this embodiment provides an image collection method, where the method includes:
  • S101 Receive a user instruction, and select one of the plurality of image acquisition modules according to the user instruction.
  • the image collection method described in this embodiment is applicable to a background server or a cloud server, or a combination of a server and an intelligent terminal.
  • the actual needs of the user for image acquisition can be known.
  • the corresponding image acquisition module is selected to perform targeted image acquisition, thereby ensuring adaptation to the near and far scenes.
  • the embodiment provides the user with a plurality of alternative instructions, including an image acquisition mode instruction and an identification object selection instruction.
  • the conventional telephoto and short focus acquisition modes respectively receive and acquire the two instructions.
  • the image acquisition mode instruction includes a distant view mode or a close-up mode; matching the focal length of the acquired image according to the image acquisition mode instruction, and selecting a corresponding image acquisition module according to the matched focal length.
  • the process described in this manner is a process of mainly interacting with the smart terminal, that is, the user may input an image acquisition mode instruction according to an APP application associated with the physical device in the smart terminal, where the image acquisition mode includes a distant view mode or a close-range mode. .
  • the image acquisition is performed by controlling the corresponding focal length after receiving the distant mode or the close-up mode.
  • the telephoto mode corresponds to the telephoto image acquisition module; the close-up mode corresponds to the short-focus image acquisition module.
  • it can be displayed to the user by comparing the display modes in the conventional existing APP application, and the user can directly select the image collection mode to be selected by hand touch.
  • the command can be selected by voice or other means.
  • the significance of the near view mode and the distant view mode is not only that the targeted image acquisition can be realized, but also the cloud server can only control the telephoto image acquisition module or the short focus image acquisition module when the user selects the close view mode or the distant view mode. Perform image acquisition to reduce the power consumption of physical devices.
  • the identification object selection includes face recognition, character recognition, graphic recognition or identification recognition; matching the focal length of the collected image according to the identification object selection instruction, and selecting corresponding according to the matched focal length Image acquisition module.
  • the process described in mode (1) is mainly introduced from the selection image acquisition mode, and the process described in mode (2) is from the perspective of image acquisition function.
  • the method (2) can be directly used as a means for specifying recognition of a specific object in an image in practical applications.
  • the identification object selection includes one or more of face recognition, character recognition, graphic recognition, or logo recognition.
  • the presentation of the selection of the recognition object is the same as the presentation of the image collection mode in the mode (2), and the selection process is also substantially the same.
  • the selection of the identification object may be selected by voice or other means, so that the cloud server selects the focal length corresponding to the identification object to collect the image, and performs targeted recognition on the image to avoid other interference items. It can alleviate the complicated recognition process of the cloud server to some extent.
  • the above two methods can realize the process of selecting the image acquisition module corresponding to the focal length for acquisition, and at the same time, in order to utilize the resources more rationally and meet the actual needs of the user, the camera of the smart terminal can be used as the short-focus camera.
  • step S101 the corresponding focal length has been selected by the user to perform image collection, and then the entity device responsible for acquiring the image sends the collected image to the cloud server for identification.
  • the blind person If the blind person needs to perceive distant information such as shop name and traffic signal, the blind person will send the command of the remote mode and select the object to be identified.
  • the cloud server will automatically assume that the user wants to collect the distant image, then it will control
  • the telephoto image acquisition module in the physical device performs image acquisition on the distant scene, and then sends the collected image to the cloud server, and then the cloud server identifies the collected image and accurately identifies the object to be recognized by the user.
  • the blind person if the blind person needs to collect close-up images such as menus, books, coins, etc., the blind person will send the instructions of the close-up mode and select the object to be identified, and the cloud server will automatically assume that the user wants to collect the near-image. Then, the short-focus image acquisition module in the physical device is controlled to perform image acquisition on the near scene, and then the collected image is sent to the cloud server, and then the collected image is recognized by the cloud server, and the user is identified. Object.
  • the image recognition process is set in the background server or the cloud server.
  • the background server or the cloud server receives the identification object selection instruction sent by the user, the collected image is identified according to the specific object to be identified by the instruction.
  • the image information is recognized, it can be directly notified in the form of text or voice, but for the blind person, the text does not work, and the transmission of the Braille is difficult to implement. Therefore, in this embodiment, the recognized image information is converted into non-visual notification information, and then the blind person is notified, and the non-visualized notification information may be voice or bone conduction information or the like.
  • the embodiment provides an electronic device, the electronic device comprising: a display, a memory, one or more processors; and one or more modules, the one or more modules being stored in the memory, and It is configured to be executed by the one or more processors, the one or more modules comprising instructions for performing the various steps in the method of embodiment 1.
  • the present embodiment provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer
  • the computer is caused to perform the various steps in the method described in embodiment 1.
  • the embodiment provides an image acquisition system, where the system includes an image acquisition device and a selection acquisition device, and the image acquisition device is provided with a plurality of image acquisition modules, and each image acquisition module corresponds to The different focus distances, the selection acquisition device is used to select an image acquisition module, and the image is acquired by the selected image acquisition module.
  • the selection collection device described in this embodiment can obtain the actual requirement of the user for image collection by acquiring a user instruction. Because the distance between the image to be collected and the distance between the people is different, the corresponding image acquisition module is selected to perform targeted image acquisition, thereby ensuring adaptation to the near and far scenes.
  • the image capturing device includes an image capturing device, and the image capturing device is provided with a plurality of image capturing modules, and each of the image capturing modules corresponds to a different focal length.
  • the selection collection device includes an application module and a cloud server disposed in the smart terminal, where the application module is configured to receive a user instruction, and send the user instruction to a cloud server, where the cloud server is implemented as the present application.
  • the embodiment provides the user with a plurality of alternative instructions, including an image acquisition mode instruction and an identification object selection instruction.
  • image acquisition mode instruction an image acquisition mode instruction
  • identification object selection instruction an identification object selection instruction.
  • the image acquisition mode instruction includes a distant view mode or a close-up mode; matching the focal length of the acquired image according to the image acquisition mode instruction, and selecting a corresponding image acquisition module according to the matched focal length.
  • the process described in this manner is a process of mainly interacting with the smart terminal, that is, the user may input an image acquisition mode instruction according to an APP application associated with the physical device in the smart terminal, where the image acquisition mode includes a distant view mode or a close-range mode. .
  • the image acquisition is performed by controlling the corresponding focal length after receiving the distant mode or the close-up mode.
  • the telephoto mode corresponds to the telephoto image acquisition module; the close-up mode corresponds to the short-focus image acquisition module.
  • it can be displayed to the user by comparing the display modes in the conventional existing APP application, and the user can directly select the image collection mode to be selected by hand touch.
  • the commands can be selected by voice or other means.
  • the significance of the near view mode and the distant view mode is not only that the targeted image acquisition can be realized, but also the cloud server can only control the telephoto image acquisition module or the short focus image acquisition module when the user selects the close view mode or the distant view mode. Perform image acquisition to reduce the power consumption of physical devices.
  • the identification object selection includes face recognition, character recognition, graphic recognition or identification recognition; matching the focal length of the collected image according to the identification object selection instruction, and selecting corresponding according to the matched focal length Image acquisition module.
  • the process described in mode (1) is mainly introduced from the selection image acquisition mode, and the process described in mode (2) is from the perspective of image acquisition function.
  • the method (2) can be directly used as a means for specifying recognition of a specific object in an image in practical applications.
  • the identification object selection includes one or more of face recognition, character recognition, graphic recognition, or logo recognition.
  • the presentation of the selection of the recognition object is the same as the presentation of the image collection mode in the mode (2), and the selection process is also substantially the same.
  • the selection of the identification object may be selected by voice or other means, so that the cloud server selects the focal length corresponding to the identification object to collect the image, and performs targeted recognition on the image to avoid other interference items. It can alleviate the complicated recognition process of the cloud server to some extent.
  • the above two methods can realize the process of selecting the image acquisition module corresponding to the focal length for acquisition, and at the same time, in order to utilize the resources more rationally and meet the actual needs of the user, the camera of the smart terminal can be used as the short-focus camera.
  • the blind person If the blind person needs to perceive distant information such as shop name and traffic signal, the blind person will send the command of the remote mode and select the object to be identified.
  • the cloud server will automatically assume that the user wants to collect the distant image, then it will control
  • the telephoto image acquisition module in the physical device performs image acquisition on the distant scene, and then sends the collected image to the cloud server, and then the cloud server identifies the collected image and accurately identifies the object to be recognized by the user.
  • the blind person if the blind person needs to collect close-up images such as menus, books, coins, etc., the blind person will send the instructions of the close-up mode and select the object to be identified, and the cloud server automatically assumes that the user wants to collect the near-image. Then, the short-focus image acquisition module in the physical device is controlled to perform image acquisition on the near scene, and then the collected image is sent to the cloud server, and then the collected image is recognized by the cloud server, and the user is identified. Object.
  • the image information is recognized, it can be directly notified by text or voice, but for blind people, the text does not work, and the transmission of Braille is difficult to achieve. Therefore, in this embodiment, the recognized image information is converted into non-visual notification information, and then the blind person is notified, and the non-visualized notification information may be voice or bone conduction information or the like.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种图像采集方法、系统、电子设备及计算机程序产品，所述方法包括：接收用户指令；根据所述用户指令从多个图像采集模块中选择一个，其中，每个图像采集模块对应不同的焦距；通过选择的图像采集模块采集图像。本申请通过获取用户指令，并根据用户指令选择对应的焦距对图像进行采集，从而智能的实现对远近不同场景的图像采集，普适性强，灵活方便，有利于盲人对周围世界的认知。

Description

一种图像采集方法、系统、电子设备及计算机程序产品 技术领域
本申请涉及图像采集领域，尤其涉及一种图像采集方法、系统、电子设备及计算机程序产品。
背景技术
云端机器人是将认知系统放在云里，身体、驱动、传感器放在机器人本体上，通过移动通信将二者连接起来的智能机器人；云端机器人是智能仿人机器人发展的方向。
在当今信息时代，盲人对于周围信息的认知需求也越来越强。目前解决盲人信息无障碍的设备主要以眼睛、头盔和盲杖等设备为主。但是，盲杖所能够提供的图像信息有限；而头盔可以集成包括导航避障等众多功能，然而仅对于信息无障碍来说，稍显笨重。现有已有的智能眼镜设备一般只具备长焦或者短焦的单一功能，而可快速变焦的图像采集模块，相对而言，价格比较昂贵，体型较大，不够便携。并且在远近焦变换过程中，容易造成截取到的图像模糊。
申请内容
有鉴于此，本申请实施例期望提供一种图像采集方法、系统、电子设备及计算机程序产品，以解决现有技术中存在的图像采集过程无法完全适应远近场景的问题。
为达到上述目的，本申请实施例的技术方案是这样实现的：
本申请实施例第一方面提供了一种图像采集方法，所述方法包括：
接收用户指令；
根据所述用户指令从多个图像采集模块中选择一个，其中，每个图像采集模块对应不同的焦距；
通过选择的图像采集模块采集图像。
本申请实施例第二方面提供了一种电子设备，所述电子设备包括：显示器，存储器，一个或多个处理器；以及一个或多个模块，所述一个或多个模块被存储在所述存储器中，并被配置成由所述一个或多个处理器执行，所述一个或多个模块包括用于执行如本申请实施例第一方面所述图像采集方法中各个步骤的指令。
本申请实施例第三方面提供了一种计算机程序产品，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行如本申请实施例第一方面所述图像采集方法中各个步骤。
本申请实施例第四方面提供了一种图像采集系统，所述系统包括图像采集设备和选择采集设备，所述图像采集设备上设置有多个图像采集模块，且每个图像采集模块对应不同的焦距，所述选择采集设备，用于选择一个图像采集模块，并通过选择的图像采集模块采集图像。
本申请通过获取用户指令，并根据用户指令选择对应的焦距对图像进行采集，从而智能的实现对远近不同场景的图像采集，普适性强，灵活方便，有利于盲人对周围世界的认知。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1为本申请实施例所述的图像采集方法的流程图；
图2为本申请实施例所述的图像采集系统的原理图；
图3为本申请实施例所述的图像采集系统的工作流程图。
具体实施方式
为了使本申请实施例中的技术方案及优点更加清楚明白，以下结合附图对本申请的示例性实施例进行进一步详细的说明，显然，所描述的实施例仅是本申请的一部分实施例，而不是所有实施例的穷举。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
实施例1
如图1所示，本实施例提出了一种图像采集方法，所述方法包括：
S101，接收用户指令，根据所述用户指令从多个图像采集模块中选择一个。
具体的，本实施例所述的图像采集方法适用于后台服务器或云服务器中，或者服务器与智能终端相结合的方式。通过获取用户指令，可以获知用户对于图像采集的实际需求。由于所要采集图像与人之间的距离远近的不同，选择对应的图像采集模块进行针对性的图像采集，从而保证了对远近景象的适应。
对于常人而言，由于具有正常的感官，可以采用手机、平板电脑、手表等常规的实体设备直接通过感官对前方的图像进行采集。而对于特殊人群，比如盲人而言，由于其身体结构所限，无法直接获知前方场景，需要借助其他的工具或设备进行拍照或图像采集。这就要求能够辅助盲人寻找方向的设备。而头部的转动则可以直接认为是盲人对于前方环境所要了解的方向，因此，对于盲人而言，可以以便携式的眼睛、帽子、头盔等等设备作为图像采集的实体设备。另外在所述实体设备上设置多个图像采集模块，且每个图像采集模块对应不同的焦距。以便对不同距离的图像进行针对性的采集。
进一步的，本实施例为用户提供了多种可供选择的指令，包括图像采集模式指令和识别对象选择指令，下面以常规的长焦和短焦的采集方式对两种指令的接收和采集分别进行介绍：
(1)接收图像采集模式指令，所述图像采集模式指令包括远景模式或近景模式；根据所述图像采集模式指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
该方式所述的过程是主要与智能终端相交互的过程，即，用户可以根据智能终端中与实体设备相关联的APP应用程序输入图像采集模式指令，所述图像采集模式包括远景模式或近景模式。当接收到所述远景模式或近景模式之后控制相对应的焦距进行图像采集。远景模式对应长焦图像采集模块；近景模式对应短焦图像采集模块。对于正常用户而言，可以通过比较常规的现有的APP应用程序中的展示方式展示给用户，用户可直接通过手触的方式直接选择所要选择的图像采集模式。而对于盲人用户而言，则可通过语音或其他方式来选择指令。本实施例提供近景模式和远景模式的意义不仅仅在于能够实现针对性的图像采集，同时，在用户选择近景模式或远景模式时，云端服务器只能控制长焦图像采集模块或短焦图像采集模块进行图像采集，降低实体设备的功耗。
(2)接收识别对象选择指令，所述识别对象选择包括人脸识别、文字识别、图形识别或标识识别；根据所述识别对象选择指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
方式(1)中所述的过程主要是从选择图像采集模式上进行介绍的，而方式(2)所述的过程则是从图像采集功能的角度出发的。方式(2)在实际应用中可以直接作为对图像中特定的对象进行指定识别的手段。所述识别对象选择包括人脸识别、文字识别、图形识别或标识识别中的一种或几种。其中所述识别对象选择的展现如方式(2)中图像采集模式的展现是相同的，选择过程也基本相同。对于盲人用户可通过语音或其他方式对识别 对象选择进行选取，使云端服务器选择与所述识别对象相对应的焦距对图像进行采集，并对图像进行针对性的识别，避免其他的干扰项，也能够在一定程度上缓解云端服务器的复杂的识别过程。
以上两种方式都能够实现选择对应焦距的图像采集模块进行采集的过程，同时，为了更加合理化的利用资源，以及满足用户的实际需求，可以以智能终端自有的摄像头作为短焦摄像头进行使用。
S102，通过选择的图像采集模块采集图像。
具体的，在步骤S101中已经通过用户指令选取对应的焦距进行图像采集，然后，负责采集图像的实体设备将采集到的图像发送至云端服务器中进行识别。
如果盲人需要对商铺名、交通信号灯等远处信息进行感知时，盲人会发送远景模式的指令，并选择所要识别的对象，云端服务器则会自动认为用户所要采集的是远方图像，那么就会控制实体设备中的长焦图像采集模块对远处景象进行图像采集，然后将采集到的图像发送至云端服务器，然后由云端服务器对采集的图像进行识别，并精确识别出用户所要识别的对象。
相应的，如果盲人需要对眼前如菜单、书本、钱币等近景图像采集时，盲人会发送近景模式的指令，并选择所要识别的对象，云端服务器则会自动认为用户所要采集的是近处图像，那么就会控制实体设备中的短焦图像采集模块对近处景象进行图像采集，然后将采集到的图像发送至云端服务器，然后由云端服务器对采集的图像进行识别，并精确识别出用户所要识别的对象。
S103，对采集的图像进行识别。
本实施例所述图像采集方法中没有对图像采集的过程做出任何的改进。图像的识别过程设置在后台服务器或者云端服务器中，当后台服务器或者云端服务器接收到用户发送的识别对象选择指令，然后根据所述指令所要 识别的具体对象对采集的图像进行识别。
另外，对于正常人而言，如果识别到了图像信息之后直接以文字或者语音的形式告知即可，但是对于盲人而言，文字是行不通的，而盲文的传输又难以实现。因此，本实施例将识别到的图像信息转换为非可视化的通报信息，然后再告知盲人，所述非可视化的通报信息可以为语音或者骨传导信息等。
实施例2
本实施例提出了一种电子设备，所述电子设备包括：显示器，存储器，一个或多个处理器；以及一个或多个模块，所述一个或多个模块被存储在所述存储器中，并被配置成由所述一个或多个处理器执行，所述一个或多个模块包括用于执行实施例1所述方法中各个步骤的指令。
实施例3
本实施例提供了一种计算机程序产品，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行实施例1所述的方法中各个步骤。
实施例4
如图2所示，本实施例提出了一种图像采集系统，所述系统包括图像采集设备和选择采集设备，所述图像采集设备上设置有多个图像采集模块，且每个图像采集模块对应不同的焦距，所述选择采集设备，用于选择一个图像采集模块，并通过选择的图像采集模块采集图像。
具体的，本实施例所述的选择采集设备通过获取用户指令，可以获知用户对于图像采集的实际需求。由于所要采集图像与人之间的距离远近的不同，选择对应的图像采集模块进行针对性的图像采集，从而保证了对远近景象的适应。
进一步的，所述图像采集设备包括图像采集装置，所述图像采集装置 上设置有多个图像采集模块，且所述每个图像采集模块对应不同的焦距。
所述选择采集设备包括设置在智能终端中的应用程序模块和云端服务器，所述应用程序模块用于接收用户指令，并将所述用户指令发送至云端服务器，所述云端服务器为如本申请实施例2所述的电子设备。
对于常人而言，由于具有正常的感官，可以采用手机、平板电脑、手表等常规的实体设备直接通过感官对前方的图像进行采集。而对于特殊人群，比如盲人而言，由于其身体结构所限，无法直接获知前方场景，需要借助其他的工具或设备进行拍照或图像采集。这就要求能够辅助盲人寻找方向的设备。而头部的转动则可以直接认为是盲人对于前方环境所要了解的方向，因此，对于盲人而言，可以以便携式的眼睛、帽子、头盔等等设备作为图像采集的实体设备。另外在所述实体设备上设置多个图像采集模块，且每个图像采集模块对应不同的焦距。以便对不同距离的图像进行针对性的采集。
更进一步的，如图3所示，本实施例为用户提供了多种可供选择的指令，包括图像采集模式指令和识别对象选择指令，下面以常规的长焦和短焦的采集方式对两种指令的接收和采集分别进行介绍：
(1)接收图像采集模式指令，所述图像采集模式指令包括远景模式或近景模式；根据所述图像采集模式指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
该方式所述的过程是主要与智能终端相交互的过程，即，用户可以根据智能终端中与实体设备相关联的APP应用程序输入图像采集模式指令，所述图像采集模式包括远景模式或近景模式。当接收到所述远景模式或近景模式之后控制相对应的焦距进行图像采集。远景模式对应长焦图像采集模块；近景模式对应短焦图像采集模块。对于正常用户而言，可以通过比较常规的现有的APP应用程序中的展示方式展示给用户，用户可直接通过手触的方式直接选择所要选择的图像采集模式。而对于盲人用户而言，则 可通过语音或其他方式来选择指令。本实施例提供近景模式和远景模式的意义不仅仅在于能够实现针对性的图像采集，同时，在用户选择近景模式或远景模式时，云端服务器只能控制长焦图像采集模块或短焦图像采集模块进行图像采集，降低实体设备的功耗。
(2)接收识别对象选择指令，所述识别对象选择包括人脸识别、文字识别、图形识别或标识识别；根据所述识别对象选择指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
方式(1)中所述的过程主要是从选择图像采集模式上进行介绍的，而方式(2)所述的过程则是从图像采集功能的角度出发的。方式(2)在实际应用中可以直接作为对图像中特定的对象进行指定识别的手段。所述识别对象选择包括人脸识别、文字识别、图形识别或标识识别中的一种或几种。其中所述识别对象选择的展现如方式(2)中图像采集模式的展现是相同的，选择过程也基本相同。对于盲人用户可通过语音或其他方式对识别对象选择进行选取，使云端服务器选择与所述识别对象相对应的焦距对图像进行采集，并对图像进行针对性的识别，避免其他的干扰项，也能够在一定程度上缓解云端服务器的复杂的识别过程。
以上两种方式都能够实现选择对应焦距的图像采集模块进行采集的过程，同时，为了更加合理化的利用资源，以及满足用户的实际需求，可以以智能终端自有的摄像头作为短焦摄像头进行使用。
如果盲人需要对商铺名、交通信号灯等远处信息进行感知时，盲人会发送远景模式的指令，并选择所要识别的对象，云端服务器则会自动认为用户所要采集的是远方图像，那么就会控制实体设备中的长焦图像采集模块对远处景象进行图像采集，然后将采集到的图像发送至云端服务器，然后由云端服务器对采集的图像进行识别，并精确识别出用户所要识别的对象。
相应的，如果盲人需要对眼前如菜单、书本、钱币等近景图像采集时， 盲人会发送近景模式的指令，并选择所要识别的对象，云端服务器则会自动认为用户所要采集的是近处图像，那么就会控制实体设备中的短焦图像采集模块对近处景象进行图像采集，然后将采集到的图像发送至云端服务器，然后由云端服务器对采集的图像进行识别，并精确识别出用户所要识别的对象。
除此之外，对于正常人而言，如果识别到了图像信息之后直接以文字或者语音的形式告知即可，但是对于盲人而言，文字是行不通的，而盲文的传输又难以实现。因此，本实施例将识别到的图像信息转换为非可视化的通报信息，然后再告知盲人，所述非可视化的通报信息可以为语音或者骨传导信息等。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存 储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (11)

  1. 一种图像采集方法，其特征在于，所述方法包括：
    接收用户指令；
    根据所述用户指令从多个图像采集模块中选择一个，其中，每个图像采集模块对应不同的焦距；
    通过选择的图像采集模块采集图像。
  2. 根据权利要求1所述的方法，其特征在于，所述接收用户指令，根据所述用户指令从多个图像采集模块中选择一个的过程包括：
    接收图像采集模式指令，所述图像采集模式指令包括远景模式或近景模式；
    根据所述图像采集模式指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
  3. 根据权利要求1或2所述的方法，其特征在于，所述接收用户指令，根据所述用户指令从多个图像采集模块中选择一个的过程包括：
    接收识别对象选择指令，所述识别对象选择包括人脸识别、文字识别、图形识别或标识识别；
    根据所述识别对象选择指令匹配采集图像的焦距，并根据所述匹配的焦距选择对应的图像采集模块。
  4. 根据权利要求1至3任一项所述的方法，其特征在于，所述图像采集模块包括智能设备自有摄像头。
  5. 一种电子设备，其特征在于，所述电子设备包括：显示器，存储器，一个或多个处理器；以及一个或多个模块，所述一个或多个模块被存储在所述存储器中，并被配置成由所述一个或多个处理器执行，所述一个或多个模块包括用于执行权利要求1至3中任一所述方法中各个步骤的指令。
  6. 一种计算机程序产品，其特征在于，所述计算机程序产品包括存储 在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行如权利要求1至3任一项所述的方法中各个步骤。
  7. 一种图像采集系统，其特征在于，所述系统包括图像采集设备和选择采集设备，所述图像采集设备上设置有多个图像采集模块，且每个图像采集模块对应不同的焦距，所述选择采集设备，用于选择一个图像采集模块，并通过选择的图像采集模块采集图像。
  8. 根据权利要求7所述的系统，其特征在于，所述图像采集设备包括图像采集装置，所述图像采集装置上设置有多个图像采集模块，且所述每个图像采集模块对应不同的焦距。
  9. 根据权利要求7所述的系统，其特征在于，所述图像采集设备包括图像采集装置和智能终端，所述图像采集装置上设置有至少一个图像采集模块，所述智能终端上设置有一个图像采集模块，且所述图像采集装置上设置的图像采集模块的焦距与所述智能终端上设置的图像采集模块的焦距不同。
  10. 根据权利要求7至9任一项所述的系统，所述选择采集设备为如权利要求6所述的电子设备。
  11. 根据权利要求7所述的系统，所述选择采集设备包括设置在智能终端中的应用程序模块和云端服务器，所述应用程序模块用于接收用户指令，并将所述用户指令发送至云端服务器，所述云端服务器为如权利要求6所述的电子设备。
PCT/CN2018/077195 2018-02-26 2018-02-26 一种图像采集方法、系统、电子设备及计算机程序产品 Ceased WO2019161559A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880000155.1A CN108401496A (zh) 2018-02-26 2018-02-26 一种图像采集方法、系统、电子设备及计算机程序产品
PCT/CN2018/077195 WO2019161559A1 (zh) 2018-02-26 2018-02-26 一种图像采集方法、系统、电子设备及计算机程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/077195 WO2019161559A1 (zh) 2018-02-26 2018-02-26 一种图像采集方法、系统、电子设备及计算机程序产品

Publications (1)

Publication Number Publication Date
WO2019161559A1 true WO2019161559A1 (zh) 2019-08-29

Family

ID=63093388

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077195 Ceased WO2019161559A1 (zh) 2018-02-26 2018-02-26 一种图像采集方法、系统、电子设备及计算机程序产品

Country Status (2)

Country Link
CN (1) CN108401496A (zh)
WO (1) WO2019161559A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113536945A (zh) * 2021-06-21 2021-10-22 清华大学 一种面向盲人的物体寻找系统及方法
CN115022707A (zh) * 2022-06-21 2022-09-06 杭州海康威视数字技术股份有限公司 计算机设备及录屏装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108401496A (zh) * 2018-02-26 2018-08-14 深圳前海达闼云端智能科技有限公司 一种图像采集方法、系统、电子设备及计算机程序产品
CN109271892A (zh) * 2018-08-30 2019-01-25 百度在线网络技术（北京）有限公司 一种物体识别方法、装置、设备、车辆和介质
CN111432126A (zh) * 2020-03-31 2020-07-17 浙江大华技术股份有限公司 一种智能识别方法，装置、摄像机及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104168418A (zh) * 2014-06-30 2014-11-26 宇龙计算机通信科技(深圳)有限公司 一种图像获取装置、图像获取方法及终端
CN104539836A (zh) * 2014-11-25 2015-04-22 深圳市金立通信设备有限公司 一种终端
CN105007431A (zh) * 2015-07-03 2015-10-28 广东欧珀移动通信有限公司 一种基于多种拍摄场景的图片拍摄方法及终端
CN105554390A (zh) * 2015-12-29 2016-05-04 广东欧珀移动通信有限公司 一种拍照方法和装置、自拍杆、拍照系统及移动终端
CN108401496A (zh) * 2018-02-26 2018-08-14 深圳前海达闼云端智能科技有限公司 一种图像采集方法、系统、电子设备及计算机程序产品

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102722321A (zh) * 2012-05-22 2012-10-10 中兴通讯股份有限公司 双摄像头切换的方法及装置
CN107302632A (zh) * 2017-06-28 2017-10-27 努比亚技术有限公司 一种移动终端拍摄方法、移动终端及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104168418A (zh) * 2014-06-30 2014-11-26 宇龙计算机通信科技(深圳)有限公司 一种图像获取装置、图像获取方法及终端
CN104539836A (zh) * 2014-11-25 2015-04-22 深圳市金立通信设备有限公司 一种终端
CN105007431A (zh) * 2015-07-03 2015-10-28 广东欧珀移动通信有限公司 一种基于多种拍摄场景的图片拍摄方法及终端
CN105554390A (zh) * 2015-12-29 2016-05-04 广东欧珀移动通信有限公司 一种拍照方法和装置、自拍杆、拍照系统及移动终端
CN108401496A (zh) * 2018-02-26 2018-08-14 深圳前海达闼云端智能科技有限公司 一种图像采集方法、系统、电子设备及计算机程序产品

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113536945A (zh) * 2021-06-21 2021-10-22 清华大学 一种面向盲人的物体寻找系统及方法
CN113536945B (zh) * 2021-06-21 2024-04-12 清华大学 一种面向盲人的物体寻找系统及方法
CN115022707A (zh) * 2022-06-21 2022-09-06 杭州海康威视数字技术股份有限公司 计算机设备及录屏装置
CN115022707B (zh) * 2022-06-21 2024-06-07 杭州海康威视数字技术股份有限公司 计算机设备及录屏装置

Also Published As

Publication number Publication date
CN108401496A (zh) 2018-08-14

Similar Documents

Publication Publication Date Title
KR102458344B1 (ko) 카메라의 초점을 변경하는 방법 및 장치
WO2019161559A1 (zh) 一种图像采集方法、系统、电子设备及计算机程序产品
KR101876655B1 (ko) 스크린 제어 방법 및 장치
US9317113B1 (en) Gaze assisted object recognition
JP6205072B2 (ja) 撮像制御装置、撮像制御方法、カメラ、カメラシステム及びプログラム
US10587847B2 (en) Content capture and transmission of data of a subject to a target device
KR102056221B1 (ko) 시선인식을 이용한 장치 연결 방법 및 장치
EP2980548A1 (en) Apparatus and method for enhancing accuracy of a contactless body temperature measurement
WO2016194844A1 (ja) ウェアラブル装置
KR20150082841A (ko) 이동 단말기 및 그 제어 방법
WO2021013230A1 (zh) 机器人的控制方法、机器人、终端、服务器及控制系统
US10514755B2 (en) Glasses-type terminal and control method therefor
EP4184321B1 (en) Method for interaction between devices based on pointing operation, and electronic device
CN110604579A (zh) 一种数据采集方法、装置、终端及存储介质
CN105430250B (zh) 移动终端及其控制方法
CN208689558U (zh) 一种辅助用户的智能系统
KR101672268B1 (ko) 전시공간 제어 시스템 및 전시공간 제어방법
WO2022022722A1 (zh) 配件主题自适应方法、装置和系统
KR20150111199A (ko) 이동 단말기 및 그것의 제어방법
JP2015162822A (ja) 電子機器、撮像装置及び通信装置
CN114564162B (zh) 一种数据传输方法、电子设备、系统及存储介质
KR101612863B1 (ko) 이동 단말기 및 제어 시스템
CN107526439A (zh) 一种界面返回方法及装置
JP2015192362A (ja) 画像再生装置，画像再生方法およびその制御プログラム
KR20160005529A (ko) 글래스 타입의 이동 단말기 및 그 제어방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18906846

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26.01.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18906846

Country of ref document: EP

Kind code of ref document: A1