WO2020063072A1 - 图像筛选方法、系统、终端及计算机可读存储介质 - Google Patents
图像筛选方法、系统、终端及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2020063072A1 WO2020063072A1 PCT/CN2019/097353 CN2019097353W WO2020063072A1 WO 2020063072 A1 WO2020063072 A1 WO 2020063072A1 CN 2019097353 W CN2019097353 W CN 2019097353W WO 2020063072 A1 WO2020063072 A1 WO 2020063072A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- frame
- moving subject
- center
- ordered
- Prior art date
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
- H04N23/62—Control of parameters via user interfaces
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Definitions
- Embodiments of the present invention relate to the field of image processing technologies, and in particular, to an image screening method, system, terminal, and computer-readable storage medium.
- Continuously taking pictures of moving targets is one of the common life scenes of camera photography. Continuously taking pictures of moving targets can capture a series of movement states and moving positions of moving targets within a period of time, but when the moving speed of the subject is too slow, a large number of redundant images of the same position and state are often taken , Which causes trouble for users to filter photos.
- Existing photo screening methods are preferred in terms of image quality, for example: screening images with better lighting brightness and better exposure light effect parameters. This photo screening method ignores the redundancy of image content, resulting in still filtered photos. There will be redundant photos with similar or identical content.
- embodiments of the present invention provide an image screening method, system, terminal, and computer-readable storage medium to solve the above-mentioned photo screening method, which ignores the redundancy of image content, resulting in the filtered photos still existing. Issues with redundant or similar photos.
- a first aspect of an embodiment of the present invention provides an image screening method, which includes:
- the ordered image sequence is filtered according to the position coordinates of the center of the moving subject in each frame of the image, so that the separation distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset threshold.
- a second aspect of the embodiments of the present invention provides an image screening system.
- the image screening system includes:
- An image acquisition unit configured to acquire continuous multiple frames of images to be filtered, and mark the continuous multiple frames of images in order of image acquisition time to form an ordered image sequence
- a center marking unit configured to mark the center of the moving subject in each frame of the ordered image sequence, and obtain the position coordinates of the center of the moving subject in each frame of the image on a preset reference coordinate system in the image preview field of view;
- An image screening unit configured to filter the ordered image sequence according to the position coordinates of the center of the moving subject in each frame of the image, so that the distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset threshold .
- a third aspect of the embodiments of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program Steps of implementing the image screening method method described in the first aspect above.
- a fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the image according to the first aspect is implemented. Steps of a screening method.
- FIG. 1 is a schematic flowchart of an image screening method provided by Embodiment 1 of the present invention
- Embodiment 2 is a schematic flowchart of an image screening method provided by Embodiment 2 of the present invention.
- Embodiment 3 is a schematic flowchart of an image screening method provided by Embodiment 3 of the present invention.
- FIG. 4 is a schematic structural diagram of an image screening system according to a fourth embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of a terminal provided by Embodiment 5 of the present invention.
- FIG. 1 shows an implementation process of an image screening method provided by Embodiment 1 of the present invention, and an execution subject of the method is a terminal in an embodiment of the present invention.
- the implementation process of the method provided in this embodiment is detailed as follows:
- Step S101 Obtain continuous multiple frames of images to be screened, and mark the continuous multiple frames of images in order of image acquisition time to form an ordered image sequence.
- the continuous multi-frame image to be filtered may be a continuous multi-frame image captured by a camera device on the terminal in real time for a moving object, or a non-real-time continuous multi-frame image read from the memory of the terminal. It should be noted that, during the continuous multi-frame image capturing process, the image preview field of view of the camera device remains unchanged, which facilitates subsequent calculation of the separation distance between moving subjects in different frames of the image using the image preview field of view as a reference.
- the ordered image sequence may be obtained by marking consecutive multiple frames of images according to the sequence of image acquisition time, or may be obtained by marking consecutive multiple frames of image in the reverse order of the sequence of image acquisition time.
- the method may further include:
- the continuous multi-frame images are identified, and images that do not include a moving subject are filtered out.
- the continuous multi-frame images are obtained, they are further identified, the images that do not contain the moving subject are filtered, and then the filtered multiples that include the moving subject are filtered according to the image acquisition time.
- Frame images are labeled to obtain an ordered image sequence, which can improve the efficiency and accuracy of subsequent image screening.
- Step S102 Mark the center of the moving subject in each frame of the ordered image sequence, and obtain position coordinates of the center of the moving subject in each frame of the image on a preset reference coordinate system in the image preview field of view.
- the image preview field of view refers to the image preview field of view of the imaging device when the continuous multi-frame image is captured, and the image preview field of view of the camera device when the continuous multi-frame image is captured is fixed.
- the preview field of view is the reference object to calculate the distance between the centers of moving subjects in different frames of the image.
- marking the center of the moving subject in each frame of the ordered image sequence includes:
- the main body region includes, but is not limited to, the smallest circumscribed circle of the moving subject or the smallest circumscribed rectangle of the moving subject.
- step S103 the ordered image sequence is filtered according to the position coordinates of the center of the moving subject in each frame of the image, so that the separation distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset threshold.
- step S103 specifically includes:
- the found image is retained as a valid image, and the found image is set as a base frame image again.
- the previous step is executed cyclically until all valid image sequences are filtered.
- the above selection of the first frame image in the ordered image sequence as the first basic frame image is merely a preferred implementation example exemplified in the present invention and is not intended to limit the present invention, for example, in other implementation examples
- the method may further include:
- making the moving direction of the moving subject in the filtered image sequence consistent on the x-axis or y-axis of the preset reference coordinate system specifically means that the center of the moving subject in the filtered ordered image sequence is in the The coordinate values on the x-axis or y-axis in the preset reference coordinate system are increasing or decreasing. In this way, it can ensure that the moving direction of the moving subject in the filtered ordered image sequence is not reversed, and the reliability of subsequent image screening is guaranteed.
- the image filtering method provided in this embodiment first marks consecutive multi-frame images to be filtered in order of image shooting time to form an ordered image sequence; and then marks the movement within each frame of the ordered image sequence.
- the subject center obtains the position coordinates of the moving subject center in a preset reference coordinate system in the image preview field of view in each frame of the image; finally, the ordered image sequence is filtered according to the position coordinates of the moving subject center in each frame of the image, so that the screening In the subsequent effective image sequence, the separation distance between moving subjects in adjacent images is greater than a preset threshold, so that it is possible to filter out images for which the positions of moving subjects are not duplicated according to the positions of the moving subjects in the image.
- FIG. 2 is a schematic flowchart of an image screening method provided in Embodiment 2 of the present invention, and an execution body of the method is a terminal described in an embodiment of the present invention.
- the image filtering method provided in this embodiment includes the following steps:
- Step S201 Acquire a continuous multi-frame image to be screened, and mark the continuous multi-frame image according to an image acquisition time sequence to form an ordered image sequence.
- Step S202 Obtain the smallest circumscribed circle containing the moving subject in each frame of the ordered image sequence, mark the center of the smallest circumscribed circle as the moving subject center, and obtain the center of the moving subject in each frame of the image. Position coordinates on a preset reference coordinate system in the image preview field of view.
- Step S203 Calculate the average value of the minimum circumscribed circle diameter of the moving subject in all the images in the ordered image sequence.
- Step S204 Perform training according to the average value of the minimum circumscribed circle diameter and the adjustable coefficient to obtain the preset threshold.
- step S205 the ordered image sequence is filtered according to the position coordinates of the center of the moving subject in each frame of the image, so that the distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset threshold.
- the preset threshold value is a product value of the average value of the smallest circumscribed circle and the adjustable coefficient.
- the adjustable coefficient is adjusted by the user according to the image screening results, so as to obtain the optimal preset threshold value after a large amount of experimental training, and to ensure that the most comprehensive motion state of the moving subject is obtained while obtaining an effective image sequence without redundant images. information.
- the image screening method provided in this embodiment calculates the average value of the minimum circumscribed circle diameter of a moving subject in all images in the ordered image sequence, and The average value of the circle diameter and the adjustable coefficient are trained to obtain the preset threshold, so that the image screening can obtain the most comprehensive motion state information of the moving subject while obtaining an effective image sequence without redundant images.
- FIG. 3 is a schematic flowchart of an image screening method provided by Embodiment 3 of the present invention, and an execution body of the method is a terminal described in an embodiment of the present invention.
- the image filtering method provided in this embodiment includes the following steps:
- Step S301 Obtain consecutive multi-frame images to be screened, and mark the consecutive multi-frame images in order of image acquisition time to form an ordered image sequence.
- Step S302 Obtain the smallest circumscribed rectangle containing the moving subject in each frame of the ordered image sequence, mark the center of the smallest circumscribed rectangle as the moving subject center, and obtain the center of the moving subject in each frame of the image. Position coordinates on a preset reference coordinate system in the image preview field of view.
- Step S303 Calculate the average value of the diagonals of the smallest circumscribed rectangle of the moving subject in all the images in the ordered image sequence.
- step S304 the preset threshold is obtained by training according to the average value of the diagonal of the smallest circumscribed rectangle and the adjustable coefficient.
- step S305 the ordered image sequence is filtered according to the position coordinates of the center of the moving subject in each frame of the image, so that the separation distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset threshold.
- the preset threshold value is a product value of an average value of the diagonal lines of the smallest circumscribed rectangle and the adjustable coefficient.
- the adjustable coefficient is adjusted by the user according to the image screening results, so as to obtain the optimal preset threshold value after a large amount of experimental training, and to ensure that the most comprehensive motion state of the moving subject is obtained while obtaining an effective image sequence without redundant images. information.
- step S301 to S302 and step S305 are completely the same as the implementation manners of steps S101 to S103 in the previous embodiment, so they are not repeated here.
- the image screening method provided in this embodiment is based on calculating the average of the smallest circumscribed rectangular diagonals of the moving subjects in all the images in the ordered image sequence, and according to the minimum
- the average value of the bounding rectangle diagonals and the adjustable coefficients are trained to obtain the preset threshold, so that the image screening can obtain the most comprehensive motion state information of the moving subject while obtaining an effective image sequence without redundant images.
- FIG. 4 is a schematic structural diagram of an image screening system according to a fourth embodiment of the present invention. For convenience of explanation, only parts related to this embodiment are shown.
- the image screening system 4 provided in this embodiment includes:
- An image acquisition unit 41 is configured to acquire continuous multiple frames of images to be filtered, and mark the continuous multiple frames of images in order of image collection time to form an ordered image sequence;
- the center marking unit 42 is configured to mark the center of the moving subject in each frame of the ordered image sequence, and obtain position coordinates of the center of the moving subject in each frame of the image on a preset reference coordinate system in the image preview field of view;
- An image screening unit 43 is configured to filter the ordered image sequence according to the position coordinates of the center of the moving subject in each frame of the image, so that the separation distance between the moving subjects in adjacent images in the filtered effective image sequence is greater than a preset Threshold.
- the image screening unit 43 is specifically configured to:
- the found image is retained as a valid image, and the found image is set as a base frame image again.
- the previous step is executed cyclically until all valid image sequences are filtered.
- the image screening system of the embodiment of the present invention belongs to the same concept as the image screening methods of the first embodiment, the second embodiment, or the third embodiment described above, and the specific implementation process thereof is detailed in the corresponding method embodiment, and the technical features in the method embodiment are described in The embodiments of the device are applicable correspondingly, and are not repeated here.
- FIG. 5 is a schematic structural diagram of a terminal provided by Embodiment 5 of the present invention. For convenience of explanation, only the parts related to this embodiment are shown.
- the terminal 5 provided in this embodiment includes a memory 51, a processor 52, and a computer program 53 stored in the memory 51 and executable on the processor 52.
- the processor 52 executes all When the computer program 53 is described, the steps of the image screening method according to the first embodiment or the second embodiment are implemented.
- the terminal 5 may be an electronic device with a camera function, such as a smart phone, a notebook, and a palmtop computer.
- FIG. 5 is only an example of the terminal 5 and does not constitute a limitation on the terminal 5.
- the terminal 5 may include more or fewer components than shown in the figure, or some components may be combined, or different components,
- the terminal 5 may further include an input-output device, a network access device, and a bus.
- the terminal according to the embodiment of the present invention belongs to the same concept as the image screening method of the first embodiment or the second embodiment, and the specific implementation process thereof is detailed in the method embodiment, and the technical features in the method embodiment are correspondingly applicable in this device embodiment. I wo n’t repeat them here.
- Embodiment 6 of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the image screening method according to Embodiment 1 or Embodiment 2 is implemented. step.
- the computer-readable storage medium of the embodiment of the present invention belongs to the same concept as the method of Embodiment 1 or Embodiment 2.
- the specific implementation process is detailed in the corresponding method embodiment, and the technical features in the method embodiment are readable by the computer.
- the storage medium embodiments are correspondingly applicable, and are not repeated here.
- an ordered image sequence is formed; then, the center of the moving subject in each frame of the ordered image sequence is labeled to obtain the movement in each frame of the image.
- the position coordinates of the subject center in the image preview field of view are preset on the reference coordinate system; finally, the ordered image sequence is filtered according to the position coordinates of the moving subject center in each frame of the image, so that adjacent images in the filtered effective image sequence
- the distance between the moving subjects in the inner space is greater than a preset threshold, so that it is possible to filter out images for which the positions of the moving subjects do not overlap according to the positions of the moving subjects in the image.
- the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be composed of several physical The components execute cooperatively.
- Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit .
- Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).
- computer storage medium includes volatile and non-volatile implemented in any method or technology used to store information such as computer-readable instructions, data structures, program modules or other data.
- Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or may Any other medium used to store desired information and which can be accessed by a computer.
- a communication medium typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium .
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
本发明实施例适用于图像处理技术领域，提供了一种图像筛选方法、系统、终端及计算机可读存储介质，其中方法包括：获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列；标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
Description
交叉引用
本发明要求在2018年9月30日提交中国专利局、申请号为201811155565.1发明名称为“图像筛选方法、系统、终端及计算机可读存储介质”的中国专利申请的优先权，该申请的全部内容通过引用结合在本发明中。
本发明实施例涉及图像处理技术领域，尤其涉及一种图像筛选方法、系统、终端及计算机可读存储介质。
对运动目标进行连续拍照是相机拍照的常用生活场景之一。对运动目标进行连续拍照，可以抓拍到运动目标在一段时间内的一系列动作状态和运动位置，但是当被拍摄目标主体运动速度过慢时，往往会拍到大量同一位置、状态的冗余图像，给用户筛选照片造成麻烦。现有的照片筛选方式是从图像质量上优选，例如：筛选出光照亮度、曝光灯效果参数较好的图像，这种照片筛选方式忽略了图像内容的冗余性，导致筛选后的照片中仍然会存在内容相似或相同的冗余照片。
发明内容
有鉴于此，本发明实施例提供了一种图像筛选方法、系统、终端及计算机可读存储介质，以解决上述照片筛选方式忽略了图像内容的冗余性，导致筛选后的照片中仍然会存在内容相似或相同的冗余照片的问题。
本发明实施例的第一方面提供了一种图像筛选方法，该方法包括：
获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列；
标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；
根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
本发明实施例的第二方面提供了一种图像筛选系统，该图像筛选系统包括：
图像获取单元，用于获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列；
中心标记单元，用于标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；
图像筛选单元，用于根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
本发明实施例的第三方面提供了一种终端，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现如上述第一方面所述图像筛选方法方法的步骤。
本发明实施例的第四方面提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其中，所述计算机程序被处理器执行时实现如上述第一方面所述图像筛选方法的步骤。
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明实施例的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例一提供的图像筛选方法的实现流程示意图；
图2是本发明实施例二提供的图像筛选方法的实现流程示意图；
图3是本发明实施例三提供的图像筛选方法的实现流程示意图；
图4是本发明实施例四提供的图像筛选系统的结构示意图；
图5是本发明实施例五提供的终端的结构示意图。
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本发明实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本发明实施例。在其它情况中，省略对众所周知的系统、设备、电路以及方法的详细说明，以免不必要的细节妨碍本发明实施例的描述。
为了说明本发明实施例所述的技术方案，下面通过具体实施例来进行说明。
图1示出了本发明实施例一提供的图像筛选方法的实现流程，该方法的执行主体为本发明实施例中的终端。参见图1所示，本实施例提供的方法的实现流程详述如下：
步骤S101，获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列。
其中，所述待筛选的连续多帧图像可以是由终端上的摄像装置实时针对运动物体拍摄的连续多帧图像，也可以是从终端的存储器中读取的非实时拍 摄的连续多帧图像。需要说明的是，所述连续多帧图像拍摄过程中摄像装置的图像预览视野保持不变，这样方便后续以图像预览视野为参照物计算不同帧图像内运动主体之间的间隔距离。
其中，所述有序图像序列可以是按照图像采集时间的先后顺序对连续多帧图像进行标记得到的，也可以按照图像采集时间的先后顺序的逆序对连续多帧图像进行标记得到的。
可选的，在本实施例中，在获取带筛选的连续多帧图像之后还可以包括：
对所述连续多帧图像进行识别，滤除不包含运动主体的图像。
在本实施例中，由于在获取到所述连续多帧图像后，进一步对其进行识别，过滤掉不包含运动主体的图像，然后再对按照图像采集时间对过滤后的包含有运动主体的多帧图像进行标记，得到有序图像序列，这样可以提高后续图像筛选效率和精度。
步骤S102，标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标。
其中，所述图像预览视野是指拍摄所述连续多帧图像时摄像装置的图像预览视野，摄像装置在拍摄所述连续多帧图像时的图像预览视野是固定不变的，因此可以所述图像预览视野为参照物来计算不同帧图像内运动主体中心之间的间隔距离。
其中，所述标记所述有序图像序列中每帧图像内运动主体中心包括：
获取所述有序图像序列中每帧图像内包含所述运动主体的主体区域，将所述主体区域的中心标记为所述运动主体中心。
所述主体区域包括但不限于所述运动主体的最小外接圆或所述运动主体的最小外接矩形。
步骤S103，根据每帧图像内运动主体中心的位置坐标对所述有序图像序 列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
优选的，在本实施例中，步骤S103具体包括：
选取所述有序图像序列中首帧图像保留为有效图像，并将该图像设置为基础帧图像；
以所述基础帧图像作为起始帧，顺序遍历所述有序图像序列，查找首次出现的图像内运动主体中心与所述基础帧图像内运动主体中心之间的间隔距离大于所述预设阈值的图像；
将查找出的图像保留为有效图像，并重新将查找出的图像设置为基础帧图像返回上一步循环执行上述流程，直至筛选出所有有效图像序列。
应当理解的是，上述选取所述有序图像序列中的首帧图像作为首帧基础帧图像仅仅为本发明所例举的较佳实现示例，并不用于限制本发明，例如：在其他实现示例中，也可以选取位于有序图像序列中间的某帧图像作为首帧基础帧图像，然后在以该基础帧图像为起始帧，先对有序图像序列进行顺序遍历，再对有序图像序列进行倒序遍历，以筛选出所有有效图像序列；当然也可以选取位于有序序列尾部的图像作为首帧基础帧图像，然后以该基础帧图像为起始帧，倒序遍历所述有序图像序列，以筛选出所有有效图像序列。
优选的，在本实施例中，在步骤S102之后还可以包括：
根据每帧图像内运动主体中心的位置坐标，对所述连续多帧图像进行筛选，使得筛选后的图像序列内运动主体在所述预设参考坐标系的x轴或y轴上的运动方向保持一致。
其中，使得筛选后的图像序列内运动主体在所述预设参考坐标系的x轴或y轴上的运动方向保持一致具体是指：使得筛选后的有序图像序列中运动主体中心在所述预设参考坐标系中x轴或y轴上的坐标值呈递增或递减趋势。这样便可以保证筛选后的有序图像序列中运动主体的运动方向未发生反向， 保证了后续图像筛选的可靠性。
以上可以看出，本实施例提供的图像筛选方法由于首先按照图像拍摄时间顺序对待筛选的连续多帧图像进行标记，形成有序图像序列；然后标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；最后根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值，从而可以实现根据图像中运动主体的位置，为用户筛选出运动主体位置不重复的图像。
实施例二
图2是本发明实施例二提供的图像筛选方法的实现流程示意图，该方法的执行主体为本发明实施例中所述的终端。参见图2所示，本实施例提供的图像筛选方法包括以下步骤：
步骤S201，获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列。
步骤S202，获取所述有序图像序列中每帧图像内包含所述运动主体的最小外接圆，将所述最小外接圆的中心标记为所述运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标。
步骤S203，计算所述有序图像序列中所有图像内运动主体的最小外接圆直径的平均值。
步骤S204，根据所述最小外接圆直径的平均值和可调系数进行训练得到所述预设阈值。
步骤S205，根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔 距离大于预设阈值。
优选的，在本实施例中，所述预设阈值为所述最小外接圆的平均值与所述可调系数的乘积值。所述可调系数由用户根据图像筛选结果进行调节，以便经过大量实验训练得出最佳预设阈值，保证在获取无冗余图像的有效图像序列的同时，获取最全面的运动主体的运动状态信息。
需要说明的是，本实施例中，步骤S201～步骤S202以及步骤S205的实现方式由于与上一实施例中步骤S101～步骤S103的实现方式完全相同，因此，在此不再赘述。
因此，可以看出，相对于上一实施例，本实施例提供的图像筛选方法由于计算所述有序图像序列中所有图像内运动主体的最小外接圆直径的平均值，并根据所述最小外接圆直径的平均值和可调系数进行训练得到所述预设阈值，因此可以保证图像筛选在获取无冗余图像的有效图像序列的同时，获取最全面的运动主体的运动状态信息。
实施例三
图3是本发明实施例三提供的图像筛选方法的实现流程示意图，该方法的执行主体为本发明实施例中所述的终端。参见图3所示，本实施例提供的图像筛选方法包括以下步骤：
步骤S301，获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列。
步骤S302，获取所述有序图像序列中每帧图像内包含所述运动主体的最小外接矩形，将所述最小外接矩形的中心标记为所述运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标。
步骤S303，计算所述有序图像序列中所有图像内运动主体的最小外接矩 形对角线的平均值。
步骤S304，根据所述最小外接矩形对角线的平均值和可调系数进行训练得到所述预设阈值。
步骤S305，根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
优选的，在本实施例中，所述预设阈值为所述最小外接矩形对角线的平均值与所述可调系数的乘积值。所述可调系数由用户根据图像筛选结果进行调节，以便经过大量实验训练得出最佳预设阈值，保证在获取无冗余图像的有效图像序列的同时，获取最全面的运动主体的运动状态信息。
需要说明的是，本实施例中，步骤S301～步骤S302以及步骤S305的实现方式由于与上一实施例中步骤S101～步骤S103的实现方式完全相同，因此，在此不再赘述。
因此，可以看出，相对于实施例一，本实施例提供的图像筛选方法由于计算所述有序图像序列中所有图像内运动主体的最小外接矩形对角线的平均值，并根据所述最小外接矩形对角线的平均值和可调系数进行训练得到所述预设阈值，因此可以保证图像筛选在获取无冗余图像的有效图像序列的同时，获取最全面的运动主体的运动状态信息。
实施例四
图4是本发明实施例四提供的图像筛选系统的结构示意图。为了便于说明仅仅示出了与本实施例相关的部分。
参见图4所示，本实施例提供的图像筛选系统4包括：
图像获取单元41，用于获取待筛选的连续多帧图像，按照图像采集时间 顺序对所述连续多帧图像进行标记形成有序图像序列；
中心标记单元42，用于标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；
图像筛选单元43，用于根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
可选的，所述图像筛选单元43具体用于：
选取所述有序图像序列中首帧图像保留为有效图像，并将该图像设置为基础帧图像；
以所述基础帧图像作为起始帧，顺序遍历所述有序图像序列，查找首次出现的图像内运动主体中心与所述基础帧图像内运动主体中心之间的间隔距离大于所述预设阈值的图像；
将查找出的图像保留为有效图像，并重新将查找出的图像设置为基础帧图像返回上一步循环执行上述流程，直至筛选出所有有效图像序列。
本发明实施例的图像筛选系统与上述实施例一、实施例二或实施例三的图像筛选方法属于同一构思，其具体实现过程详细见对应的方法实施例，且方法实施例中的技术特征在本设备实施例中均对应适用，这里不再赘述。
本领域普通技术人员可以理解，本实施例所公开方法中的全部或某些步骤、可以被实施为软件、固件、硬件及其适当的组合。
实施例五
图5是本发明实施例五提供的终端的结构示意图。为了便于说明，仅仅示出了与本实施例相关的部分。
参见图5所示，本实施例提供的终端5包括存储器51、处理器52以及存储在所述存储器51中并可在所述处理器52上运行的计算机程序53，所述处理器52执行所述计算机程序53时实现如实施例一或实施例二所述图像筛选方法的步骤。
本领域普通技术人员可以理解，所述终端5可以是智能手机、笔记本及掌上电脑等具有拍照功能的电子设备。图5仅仅是终端5的示例，并不构成对终端5的限定，在实际应用中所述终端5可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述终端5还可以包括输入输出设备、网络接入设备、总线等。
本发明实施例的终端与上述实施例一或实施例二的图像筛选方法属于同一构思，其具体实现过程详细见方法实施例，且方法实施例中的技术特征在本设备实施例中均对应适用，这里不再赘述。
本领域普通技术人员可以理解，本实施例所公开方法中的全部或某些步骤、可以被实施为软件、固件、硬件及其适当的组合。
实施例六
本发明实施例六提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如实施例一或实施例二所述图像筛选方法的步骤。
本发明实施例的计算机可读存储介质与上述实施例一或实施例二的方法属于同一构思，其具体实现过程详细见对应的方法实施例，且方法实施例中的技术特征在本计算机可读存储介质实施例中均对应适用，这里不再赘述。
本发明实施例的有益效果是：
本发明实施例由于首先按照图像拍摄时间顺序对待筛选的连续多帧图像进行标记，形成有序图像序列；然后标记所述有序图像序列中每帧图像内运 动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；最后根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值，从而可以实现根据图像中运动主体的位置，为用户筛选出运动主体位置不重复的图像。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。
在硬件实施方式中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。
以上参照附图说明了本发明的部分实施例，并非因此局限本发明的权利范围。本领域技术人员不脱离本发明的范围和实质内所作的任何修改、等同 替换和改进，均应在本发明的权利范围之内。
Claims (10)
- 一种图像筛选方法，其特征在于，包括：获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列；标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
- 如权利要求1所述的图像筛选方法，其特征在于，所述标记所述有序图像序列中每帧图像内运动主体中心包括：获取所述有序图像序列中每帧图像内包含所述运动主体的主体区域，将所述主体区域的中心标记为所述运动主体中心。
- 如权利要求2所述的图像筛选方法，其特征在于，所述主体区域为所述运动主体的最小外接圆，所述根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选之前还包括：计算所述有序图像序列中所有图像内运动主体的最小外接圆直径的平均值；根据所述最小外接圆直径的平均值和可调系数进行训练得到所述预设阈值。
- 如权利要求2所述的图像筛选方法，其特征在于，所述最小几何区域为所述运动主体的最小外接矩形，所述根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选之前还包括：计算所述有序图像序列中所有图像内所述运动主体的最小外接矩形对角线的平均值；根据所述最小外接矩形对角线的平均值和可调系数进行训练得到所述预设阈值。
- 如权利要求3或4所述的图像筛选方法，其特征在于，所述根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值包括：选取所述有序图像序列中首帧图像保留为有效图像，并将该图像设置为基础帧图像；以所述基础帧图像作为起始帧，顺序遍历所述有序图像序列，查找首次出现的图像内运动主体中心与所述基础帧图像内运动主体中心之间的间隔距离大于所述预设阈值的图像；将查找出的图像保留为有效图像，并重新将查找出的图像设置为基础帧图像返回上一步循环执行上述流程，直至筛选出所有有效图像序列。
- 如权利要求1所述的图像筛选方法，其特征在于，所述标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标之后还包括：根据每帧图像内运动主体中心的位置坐标，对所述连续多帧图像进行筛选，使得筛选后的图像序列内运动主体在所述预设参考坐标系的x轴或y轴上的运动方向保持一致。
- 一种图像筛选系统，其特征在于，包括：图像获取单元，用于获取待筛选的连续多帧图像，按照图像采集时间顺序对所述连续多帧图像进行标记形成有序图像序列；中心标记单元，用于标记所述有序图像序列中每帧图像内运动主体中心，获取每帧图像内运动主体中心在图像预览视野内预设参考坐标系上的位置坐标；图像筛选单元，用于根据每帧图像内运动主体中心的位置坐标对所述有序图像序列进行筛选，使得筛选后的有效图像序列中相邻图像内运动主体之间的间隔距离大于预设阈值。
- 如权利要求7所述的图像筛选系统，其特征在于，所述图像筛选单元具体用于：选取所述有序图像序列中首帧图像保留为有效图像，并将该图像设置为基础帧图像；以所述基础帧图像作为起始帧，顺序遍历所述有序图像序列，查找首次出现的图像内运动主体中心与所述基础帧图像内运动主体中心之间的间隔距离大于所述预设阈值的图像；将查找出的图像保留为有效图像，并重新将查找出的图像设置为基础帧图像返回上一步循环执行上述流程，直至筛选出所有有效图像序列。
- 一种终端，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至6任一项所述图像筛选方法的步骤。
- 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述图像筛选方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811155565.1A CN110971811B (zh) | 2018-09-30 | 2018-09-30 | 图像筛选方法、系统、终端及计算机可读存储介质 |
| CN201811155565.1 | 2018-09-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020063072A1 true WO2020063072A1 (zh) | 2020-04-02 |
Family
ID=69949827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/097353 WO2020063072A1 (zh) | 2018-09-30 | 2019-07-23 | 图像筛选方法、系统、终端及计算机可读存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110971811B (zh) |
| WO (1) | WO2020063072A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462190A (zh) * | 2020-04-20 | 2020-07-28 | 海信集团有限公司 | 一种智能冰箱及食材录入方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114463988B (zh) * | 2020-11-09 | 2023-10-03 | 浙江宇视科技有限公司 | 图像获取方法、装置、电子设备及存储介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100315512A1 (en) * | 2008-03-05 | 2010-12-16 | Huawei Device Co., Ltd | Method and System for Processing Images |
| CN104767933A (zh) * | 2015-03-13 | 2015-07-08 | 北京畅游天下网络技术有限公司 | 一种具备拍照功能的便携数码设备及筛选照片的方法 |
| CN104883628A (zh) * | 2014-02-28 | 2015-09-02 | 华为软件技术有限公司 | 一种生成视频浓缩摘要的方法、装置及设备 |
| CN105138962A (zh) * | 2015-07-28 | 2015-12-09 | 小米科技有限责任公司 | 图像显示方法及装置 |
| CN106559190A (zh) * | 2015-09-29 | 2017-04-05 | 腾讯科技（深圳）有限公司 | 一种媒体资源处理方法、装置及终端 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101720044B (zh) * | 2009-12-10 | 2011-09-28 | 四川长虹电器股份有限公司 | 一种基于自适应帧结构的avs编码方法 |
| CN104104952B (zh) * | 2014-08-01 | 2017-08-25 | 武汉高德信息产业有限公司 | 一种适应于移动设备存储与播放的音视频处理方法与系统 |
| CN107371026B (zh) * | 2017-07-25 | 2019-12-10 | 西安科技大学 | 一种视频数据多重压缩及重构方法 |
-
2018
- 2018-09-30 CN CN201811155565.1A patent/CN110971811B/zh active Active
-
2019
- 2019-07-23 WO PCT/CN2019/097353 patent/WO2020063072A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100315512A1 (en) * | 2008-03-05 | 2010-12-16 | Huawei Device Co., Ltd | Method and System for Processing Images |
| CN104883628A (zh) * | 2014-02-28 | 2015-09-02 | 华为软件技术有限公司 | 一种生成视频浓缩摘要的方法、装置及设备 |
| CN104767933A (zh) * | 2015-03-13 | 2015-07-08 | 北京畅游天下网络技术有限公司 | 一种具备拍照功能的便携数码设备及筛选照片的方法 |
| CN105138962A (zh) * | 2015-07-28 | 2015-12-09 | 小米科技有限责任公司 | 图像显示方法及装置 |
| CN106559190A (zh) * | 2015-09-29 | 2017-04-05 | 腾讯科技（深圳）有限公司 | 一种媒体资源处理方法、装置及终端 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462190A (zh) * | 2020-04-20 | 2020-07-28 | 海信集团有限公司 | 一种智能冰箱及食材录入方法 |
| CN111462190B (zh) * | 2020-04-20 | 2023-11-17 | 海信集团有限公司 | 一种智能冰箱及食材录入方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110971811B (zh) | 2022-11-15 |
| CN110971811A (zh) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107690673B (zh) | 图像处理方法、装置及服务器 | |
| WO2016127478A1 (zh) | 一种图像处理方法、装置和终端 | |
| CN109495686B (zh) | 拍摄方法及设备 | |
| US20180077359A1 (en) | Image processing method and apparatus and terminal device | |
| EP3281400A1 (en) | Automated generation of panning shots | |
| JP6946564B2 (ja) | 画像処理方法および画像処理装置、コンピュータ可読記憶媒体ならびにコンピュータ機器 | |
| US20170289454A1 (en) | Method and apparatus for video content stabilization | |
| CN104506767B (zh) | 利用马达连续移动生成同一景物不同焦距的方法和终端 | |
| EP4044579A1 (en) | Main body detection method and apparatus, and electronic device and computer readable storage medium | |
| WO2020063072A1 (zh) | 图像筛选方法、系统、终端及计算机可读存储介质 | |
| CN104954659A (zh) | 一种处理图像信息的方法及装置 | |
| CN109711241B (zh) | 物体检测方法、装置与电子设备 | |
| CN105635568B (zh) | 一种移动终端中的图像处理方法和移动终端 | |
| TWI469085B (zh) | 影像處理裝置、影像處理方法及電腦可讀取記憶媒體 | |
| TWI741305B (zh) | 圖像處理方法和裝置 | |
| CN110809797B (zh) | 微视频系统、格式和生成方法 | |
| CN106488128B (zh) | 一种自动拍照的方法及装置 | |
| JP2015008385A (ja) | 画像選択装置、撮像装置および画像選択プログラム | |
| CN115082495A (zh) | 图像处理方法、装置、设备和计算机可读存储介质 | |
| CN105467741B (zh) | 一种全景拍照方法及终端 | |
| WO2023001107A1 (zh) | 摄影图像处理方法及设备 | |
| WO2022088882A1 (zh) | 拍摄方法、装置、终端及计算机可读存储介质 | |
| WO2018099128A1 (zh) | 一种应用于投影设备的方法及装置 | |
| CN111917989B (zh) | 一种视频拍摄方法及装置 | |
| WO2021022810A1 (zh) | 一种自动对焦方法、装置、电子设备及可读存储介质 |
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: 19864581 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 25/08/2021) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19864581 Country of ref document: EP Kind code of ref document: A1 |