WO2021139372A1 - 图像的处理方法、装置、可读介质和电子设备 - Google Patents
图像的处理方法、装置、可读介质和电子设备 Download PDFInfo
- Publication number
- WO2021139372A1 WO2021139372A1 PCT/CN2020/126255 CN2020126255W WO2021139372A1 WO 2021139372 A1 WO2021139372 A1 WO 2021139372A1 CN 2020126255 W CN2020126255 W CN 2020126255W WO 2021139372 A1 WO2021139372 A1 WO 2021139372A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- contour
- color
- pixel
- line segment
- point
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Definitions
- the present disclosure relates to the field of image processing technology, and in particular, to an image processing method, device, readable medium, and electronic equipment.
- the terminal device can identify the outline of a designated object (for example, a person, a cat, a dog, etc.) in an image, wherein the outline identification method is relatively fixed, and the outline of the object can only be displayed according to a prescribed color or rule.
- the state of the object in each frame of the image may change, and the outline of the object is displayed in the same way in each frame of the image, which cannot be associated with the dynamically changing object, and cannot be satisfied.
- the purpose of the present disclosure is to provide an image processing method, device, readable medium and electronic equipment, which are used to solve the problem that the existing image processing method has a relatively fixed way of identifying contours, and can only display objects according to prescribed colors or rules. Contours lead to technical problems that cannot be associated with dynamically changing objects and cannot meet the needs of users.
- the present disclosure provides an image processing method, the method including:
- the starting contour point corresponding to the starting contour position is determined .
- the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current time, and the first time is a time before the current time;
- the line segment composed of the contour points between the starting contour point and the divided contour point in the target contour is taken as the first line segment, and the line segment in the target contour except the first line segment is taken as Second line segment
- the present disclosure provides an image processing device, the device including:
- the recognition module is used to recognize the target contour of the target object in the target image collected at the current moment, and the target contour includes a plurality of contour points;
- the first determining module is configured to determine the starting contour in the target contour according to the time difference between the current time and the first time, and the starting contour position and the ending contour position determined at the first time The starting contour point corresponding to the position, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current time, the first time being a time before the current time;
- the second determining module is configured to use the line segment composed of the contour points between the starting contour point and the divided contour point in the target contour as the first line segment, and divide the first line segment from the target contour
- the line segment outside the line segment is regarded as the second line segment;
- a rendering module configured to render the first line segment according to a first color, and render the second line segment according to a second color, where the first color is different from the second color;
- the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in the first aspect of the present disclosure are implemented.
- an electronic device including:
- a storage device on which a computer program is stored
- the processing device is configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect of the present disclosure.
- the present disclosure first identifies the target contour of the target object from the target image collected at the current moment, and then determines the starting contour corresponding to the starting contour position in the target contour according to the time difference between the current moment and the first moment.
- Point, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, and then the line segment composed of the contour points from the starting contour point to the segmented contour point is taken as the first line segment, and the target contour is divided by The line segment outside the one line segment is used as the second line segment, and finally the first line segment is rendered according to the first color, and the second line segment is rendered according to the second color.
- the present disclosure can realize the effect of dynamic stroke on the contour of the target object within a certain range indicated by the starting contour position and the ending contour position.
- Fig. 1 is a flowchart showing an image processing method according to an exemplary embodiment
- Fig. 2 is a schematic diagram showing a target contour according to an exemplary embodiment
- Fig. 3 is a flowchart showing another image processing method according to an exemplary embodiment
- Fig. 4 is a flowchart showing another image processing method according to an exemplary embodiment
- Fig. 5 is a flowchart showing another image processing method according to an exemplary embodiment
- Fig. 6 is a flowchart showing another image processing method according to an exemplary embodiment
- Fig. 7 is a rendered target image according to an exemplary embodiment
- Fig. 8 is a flowchart showing another image processing method according to an exemplary embodiment
- Fig. 9 is a rendered target image according to an exemplary embodiment
- Fig. 10 is a block diagram showing an image processing device according to an exemplary embodiment
- Fig. 11 is a block diagram showing another image processing device according to an exemplary embodiment
- Fig. 12 is a block diagram showing another image processing device according to an exemplary embodiment
- Fig. 13 is a block diagram showing another image processing device according to an exemplary embodiment
- Fig. 14 is a block diagram showing another image processing device according to an exemplary embodiment
- Fig. 15 is a block diagram showing another image processing device according to an exemplary embodiment
- Fig. 16 is a block diagram showing a device according to an exemplary embodiment.
- Fig. 1 is a flowchart showing an image processing method according to an exemplary embodiment. As shown in Fig. 1, the method includes:
- Step 101 Identify a target contour of a target object in a target image collected at the current moment, and the target contour includes a plurality of contour points.
- the target image collected at the current moment may be, for example, a frame of the image containing the target object collected at the current moment in the video captured by the user through the terminal device, or it may be the current image in the video played by the user on the display interface of the terminal device.
- a frame that is played at all times contains the image of the target object.
- the target object can be specified by the user, or it can be a pre-set object on the terminal device, for example: it can be a living object such as a person, a cat, a dog, or a doll, a robot, a car, a computer, a table, and chairs.
- An object is a living object such as a person, a cat, a dog, or a doll
- the target contour of the target object in the target image can be recognized, and the target contour includes multiple contour points.
- the contour point can be understood as dividing the target contour indicating the target object into multiple segments according to the preset interval.
- the endpoint of each segment is a contour point, and each contour point has a serial number.
- the serial number is used to indicate that the contour point is in the target.
- the recognition algorithm may be, for example, any image matting (English: Image Matting) algorithm, and the target contour output by the recognition algorithm may have multiple representation forms.
- the target contour can be a line segment that can represent the target contour (line segments connected end to end), as shown in Figure 2 (a), then the target contour is divided into multiple line segments according to a preset interval, and the gap between each line segment
- the endpoints are contour points, that is, the contour points marked by (a) No. 0, 1, 2, 3, ..., 267 in Fig. 2.
- the target contour can also be an area that can represent the target contour (it can be understood as the middle area between the two line segments of the inner contour and the outer contour of the target object), as shown in Figure 2 (b), then the target contour is set according to the preset Suppose the interval is divided into multiple rectangular areas.
- the four vertices of each rectangular area are contour points, that is, the contour points marked by (b) sequence numbers 0, 1, 2, 3,..., 535 in Figure 2, where 0, 1, 2, 3 form a rectangular area, and so on.
- the following embodiment uses the target contour shown in (a) in FIG. 2 as an example, which is not limited in the present disclosure.
- Step 102 According to the time difference between the current moment and the first moment, and the starting contour position and the ending contour position determined at the first moment, in the target contour, determine the starting contour point corresponding to the starting contour position, and the ending contour position corresponding The ending contour point of, and the segmentation contour point corresponding to the current moment, the first moment is the moment before the current moment.
- the setting instruction may include the start key point and the end key point set by the user, and may also include The first color set by the user.
- the start key point and the end key point are used to identify the area range that needs to be stroked in the initial image, and the first color is used to indicate the color that needs to be rendered in the area range that needs to be stroked.
- the display color of the target contour may be the second color.
- the target object is a person.
- the starting key point is the top of the head
- the ending key point is the left hand
- the first color is purple.
- the outline of the person is green (ie, the second color).
- the dynamic stroke effect that needs to be achieved is: from head to left hand (from head to left hand in a clockwise direction, or from head to left hand in a counterclockwise direction) rendered as purple, the other in the target outline Part of it is rendered in green.
- the starting contour position corresponding to the starting key point and the ending contour position corresponding to the ending key point can be determined according to the correspondence between different key points and contour points.
- the contour position (including: the starting contour position, the ending contour position and the segmented contour position mentioned later) can be understood as reflecting a contour point in the entire contour (including the target contour and the initial contour mentioned later). State contour). Since the posture, distance and other states of the target object in the images collected at different times will change, the corresponding contour contains different number of contour points. Only the serial number of the contour point cannot accurately describe the specified part of the target object, so you can change The ratio of the number of contour points to the number of contour points contained in the contour is used as the contour position.
- the contour position can be 0.04. Then, at the current moment, according to the contour position (including the starting contour position and the ending contour position) and the number of contour points contained in the target contour, the corresponding starting contour point and the ending contour point are determined.
- the starting contour point is the contour point corresponding to the starting key point in the target image.
- the ending contour point is the contour point corresponding to the ending key point in the target image.
- the rendering time of dynamic stroke can also be set, which can be set by the user at the first moment or a default value preset in the terminal device.
- Rendering time can be understood as the length of time that it takes to gradually render the line segment from the start key point to the end key point into the first color from the start key point to the end key point. It can also be understood as the start key How many frames of images need to pass through when the line segment from the point to the end key point is gradually rendered into the first color. Therefore, the segmentation contour points corresponding to the current time can be determined according to the time difference between the current time and the first time (or the number of frames between the target image and the initial image).
- the segmentation contour points can be understood as The line segment from the initial contour point to the divided contour point is rendered in the first color, and the other contour points are rendered in the second color.
- Step 103 Use a line segment composed of contour points between the starting contour point and the divided contour point in the target contour as the first line segment, and use the line segment in the target contour except the first line segment as the second line segment.
- Step 104 Render the first line segment according to the first color, and render the second line segment according to the second color.
- the first color and the second color are different.
- the target contour can be divided into a first line segment and a second line segment according to the starting contour point and the dividing contour point.
- the first line segment is a line segment composed of contour points from the initial contour point to the divided contour point according to a preset direction (for example: clockwise or counterclockwise), and the second line segment is divided by the target contour.
- the first line segment is rendered according to the first color
- the second line segment is rendered according to the second color.
- Step 101 to step 104 are repeatedly executed until the line segment composed of the contour points between the starting contour point and the ending contour point in the target contour is rendered as the first color.
- the sequence number of the starting contour point is 1, and the sequence number of the ending contour point is 100, there are 100 contour points between the starting contour point and the ending contour point. It takes 5s to render the line segment composed of these 100 contour points into the first color step by step. Then in the first second, the contour points of 1-20 are rendered according to the first color, and in the second second, the contour of 1-40 is rendered The points are rendered according to the first color, and so on, until the 5th second, the contour points from 1-100 (that is, all the contour points between the starting contour point and the ending contour point) are rendered according to the first color, with Realize the effect of dynamic stroke.
- the sequence number of the starting contour point is 1, and the sequence number of the ending contour point is 100, there are 100 contour points between the starting contour point and the ending contour point. It takes 100 frames to gradually render the line segment composed of these 100 contour points into the first color. Then in the first frame, the contour points of 1-2 are rendered according to the first color, and in the second frame, the contour points of 1-3 are rendered. The contour points are rendered according to the first color, and so on, until the 100th frame, the contour points from 1-100 (that is, all the contour points between the starting contour point and the ending contour point) are rendered according to the first color. To achieve the effect of dynamic stroke.
- the target image can be Displayed on the display interface of the terminal device, the target image can also be stored in a designated storage path, and the target image can also be sent to a designated server for sharing, etc.
- the present disclosure does not specifically limit this.
- the present disclosure first identifies the target contour of the target object from the target image collected at the current moment, and then determines the starting contour corresponding to the starting contour position in the target contour according to the time difference between the current moment and the first moment.
- Point, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, and then the line segment composed of the contour points from the starting contour point to the segmented contour point is taken as the first line segment, and the target contour is divided by The line segment outside the one line segment is used as the second line segment, and finally the first line segment is rendered according to the first color, and the second line segment is rendered according to the second color.
- the present disclosure can realize the effect of dynamic stroke on the contour of the target object within a certain range indicated by the starting contour position and the ending contour position.
- Fig. 3 is a flowchart showing another image processing method according to an exemplary embodiment. As shown in Fig. 3, step 102 includes:
- Step 1021 Determine the segmented contour position corresponding to the current time according to the time difference between the current time and the first time, and the starting contour position and the ending contour position.
- Step 1022 According to the target number of contour points included in the target contour, in the target contour, determine the starting contour point, the ending contour point, and the segmented contour point corresponding to the segmented contour position.
- the segmentation contour position corresponding to the current time can be determined first.
- the segmented contour position is used to indicate which part of the line segment indicated by the starting contour position and the ending contour position needs to be rendered as the first color at the current moment, that is, the line segment indicated by the starting contour position to the segmented contour position is rendered as the first color .
- segmented contour position start contour position+(end contour position-start contour position)*(time difference/rendering duration).
- the rendering time is 5s
- the time difference between the current moment and the first moment is 2s
- the target number of contour points included in the target contour is 700
- Fig. 4 is a flowchart showing another image processing method according to an exemplary embodiment. As shown in Fig. 4, before step 101, the method further includes:
- Step 105 Identify the initial contour and key point sequence of the target object in the initial image collected at the first moment.
- the image collected by the terminal device at the first moment is the initial image, and then the initial state contour and key point sequence of the target object in the initial image are identified through the same recognition algorithm as in step 101.
- the key point sequence includes one or more key points, and the key points included in the key point sequence may be different for different target objects.
- the key point sequence can include: top of head, right shoulder, left shoulder, left elbow, right elbow, left shoulder-inner, right shoulder-inner, left elbow-inner, right elbow-inner, left hand, right hand, Key points such as left hip, right hip, left knee, right knee, left foot, right foot, left knee-inner, right knee-inner, and thigh-inner.
- the key point sequence can include: front, left front light, right front light, left rear light, right rear light, left front door, right front door, left rear door, right rear door, left front wheel, right front wheel , Left rear wheel, right rear wheel, rear end, roof and other key points.
- Step 106 Determine the correspondence between the key points included in the key point sequence and the contour points included in the initial state contour according to the nearest neighbor algorithm.
- Step 107 Determine the starting contour position corresponding to the designated starting key point in the key point sequence and the ending contour position corresponding to the designated ending key point according to the corresponding relationship.
- the corresponding relationship between the key points included in the key point sequence and the contour points included in the initial state contour can be obtained according to the nearest neighbor algorithm and the prior knowledge of the target object.
- the nearest neighbor algorithm may be the K nearest neighbor algorithm (English: k-Nearest Neighbor, abbreviation: kNN).
- the corresponding relationship may include multiple relationship records, and each relationship record includes a key point corresponding to a contour point in the initial state contour.
- Fig. 5 is a flowchart showing another image processing method according to an exemplary embodiment. As shown in Fig. 5, the implementation of step 107 may include:
- Step 1071 According to the corresponding relationship, in the initial state contour, the first contour point corresponding to the starting key point and the second contour point corresponding to the ending key point are determined.
- Step 1072 Determine the initial state number of contour points included in the initial state contour.
- Step 1073 Use the ratio of the sequence number of the first contour point to the initial state number as the starting contour position, and use the ratio of the sequence number of the second contour point to the initial state quantity as the ending contour position.
- the first contour point is the contour point corresponding to the starting key point in the initial image, and corresponds to the starting contour point determined in step 102, that is, the position of the target object identified by the first contour point in the initial image, and
- the starting contour point is the same as the part of the target object identified in the target image.
- the second contour point is the contour point corresponding to the termination key point in the initial image, and corresponds to the termination contour point determined in step 102, that is, the position of the target object identified by the second contour point in the initial image, and the termination The contour points have the same position of the target object identified in the target image.
- Fig. 6 is a flowchart showing another image processing method according to an exemplary embodiment. As shown in Fig. 6, step 104 can be implemented by the following steps:
- Step 1041a Render each pixel in the first line segment as a first color, and render a pixel with a distance less than a distance threshold from the pixel as the first color. and / or,
- Step 1041b Render each pixel in the second line segment as a second color, and render a pixel with a distance less than the distance threshold from the pixel as the second color.
- each pixel in the first line segment can be combined with the pixel point located near the pixel point (that is, the distance from the pixel point is less than the distance threshold Pixels of) are rendered as the first color, and each pixel in the second line segment and the pixels located near the pixel are rendered as the second line color.
- the target contour is included and located in a certain area near the target contour and rendered into the first color and the second color respectively, which can make the rendered target contour more obvious and the effect of dynamic stroke more prominent.
- point A is the starting contour point
- point B is the ending contour point
- point C is the segmented contour point.
- line segment AC is the first line segment
- line segment CB is combined with line segment BA to form the first line segment.
- the line segment AC and the area near the line segment AC are rendered as the first color
- the line segment CB and the line segment BA, and the area near the line segment CB and the line segment BA are rendered as the second color.
- Fig. 8 is a flowchart showing another image processing method according to an exemplary embodiment. As shown in Fig. 8, another implementation of step 104 may include:
- Step 1042a Render the first pixel to the first color, and render the pixel whose distance from the first pixel is less than the first distance threshold to the first color, and the first pixel is any pixel on the first line segment point.
- step 1043a a pixel whose distance from the first pixel is greater than or equal to the first distance threshold and less than the second distance threshold is taken as the first edge pixel.
- Step 1044a Determine the first edge color according to the distance between the first edge pixel point and the first pixel point and the first color, and render the first edge pixel point into the first edge color.
- Step 1042b Render the second pixel to the second color, and render the pixel whose distance from the second pixel is less than the first distance threshold to the second color, and the second pixel is any pixel on the second line segment .
- step 1043b a pixel whose distance from the second pixel point is greater than or equal to the first distance threshold and less than the second distance threshold is taken as the second edge pixel.
- Step 1044b Determine the second edge color according to the distance between the second edge pixel point and the second pixel point and the second color, and render the second edge pixel point into the second edge color.
- the first line segment when rendering the first line segment, may be rendered as the first color first. Then, according to the distance from the first line segment, different colors are selected to render the pixels near the first line segment to achieve different dynamic stroke effects. Taking the first pixel as an example, the pixel whose distance from the first pixel is less than the first distance threshold is rendered as the first color, that is, the same color as the first line segment is rendered. Then, the pixel points whose distance from the first pixel point is greater than or equal to the first distance threshold value and less than the second distance threshold value are regarded as the first edge pixel point.
- the first edge color is determined according to the distance between the first edge pixel point and the first pixel point and the first color, and the first edge pixel point is rendered into the first edge color.
- the first edge pixel with a different distance from the first pixel corresponds to the first edge pixel.
- the color of one edge is different.
- the execution steps of rendering the second line segment according to the second color are the same as the execution steps of rendering the first line segment according to the first color, and will not be repeated here.
- step 1044a may be:
- the transparency of the first edge color, the transparency of the first edge color, and the distance between the first edge pixel and the first pixel are positively correlated.
- the distance between the first pixel and the first pixel is zero, then the transparency of the first color is 0% (that is, the sum of the first pixel, and the pixel whose distance from the first pixel is less than the first distance threshold is rendered as the first One color).
- the transparency of the first edge color may be 1.5 times the power of the distance between the first edge pixel and the first pixel, multiplied by a preset scale factor k.
- the upper limit value of the transparency is 100%.
- the chromaticity of the first color is used as the chromaticity of the first edge color.
- the first edge pixels are rendered into the first edge color. It can be understood that the chromaticity of the first edge color is the same as the chromaticity of the first color, and the transparency of the first edge color is higher than that of the first color. In this way, as the distance from the first pixel becomes larger and larger, The transparency of the first edge pixel is getting higher and higher, and the effect is shown in Figure 9. So as to form a gradual, neon light effect.
- step 1044b can be as follows: firstly, according to the distance between the second edge pixel and the second pixel, the transparency of the second edge color, the transparency of the second edge color, and the second edge pixel and the second edge pixel are determined. The distance between two pixels is positively correlated. After that, the chromaticity of the second color is used as the chromaticity of the second edge color. Finally, the second edge pixels are rendered into the second edge color.
- the first line can be rendered as the first color.
- the transparency becomes higher and higher
- the second line can also be rendered as the second line. Color, the area near the second line, as the distance from the second line increases, the transparency becomes higher and higher, thus forming a gradual, neon light effect.
- the present disclosure first identifies the target contour of the target object from the target image collected at the current moment, and then determines the starting contour corresponding to the starting contour position in the target contour according to the time difference between the current moment and the first moment.
- Point, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, and then the line segment composed of the contour points from the starting contour point to the segmented contour point is taken as the first line segment, and the target contour is divided by The line segment outside the one line segment is used as the second line segment, and finally the first line segment is rendered according to the first color, and the second line segment is rendered according to the second color.
- the present disclosure can realize the effect of dynamic stroke on the contour of the target object within a certain range indicated by the starting contour position and the ending contour position.
- Fig. 10 is a block diagram showing an image processing apparatus according to an exemplary embodiment. As shown in Fig. 10, the apparatus 200 includes:
- the recognition module 201 is used to recognize the target contour of the target object in the target image collected at the current moment, and the target contour includes a plurality of contour points.
- the first determining module 202 is used for determining the starting contour point corresponding to the starting contour position in the target contour according to the time difference between the current time and the first time, and the starting contour position and the ending contour position determined at the first time ,
- the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, the first moment is the moment before the current moment.
- the second determining module 203 is configured to use the line segment composed of the contour points between the starting contour point and the divided contour point in the target contour as the first line segment, and the line segment except the first line segment in the target contour as the second line segment. Line segment.
- the rendering module 204 is configured to render the first line segment according to the first color, and render the second line segment according to the second color, and the first color and the second color are different.
- Fig. 11 is a block diagram showing another image processing apparatus according to an exemplary embodiment.
- the first determining module 202 includes:
- the first determining sub-module 2021 is configured to determine the segmented contour position corresponding to the current time according to the time difference between the current time and the first time, and the starting contour position and the ending contour position.
- the second determining sub-module 2022 is used to determine the starting contour point, the ending contour point, and the segmented contour point corresponding to the segmented contour position in the target contour according to the target number of contour points included in the target contour.
- Fig. 12 is a block diagram showing another image processing apparatus according to an exemplary embodiment. As shown in Fig. 12, the apparatus 200 further includes:
- the recognition module 201 is further configured to recognize the initial state contour and key point sequence of the target object in the initial image collected at the first moment before recognizing the target contour of the target object in the target image collected at the current moment.
- the third determining module 205 is configured to determine the correspondence between the key points included in the key point sequence and the contour points included in the initial state contour according to the nearest neighbor algorithm.
- the fourth determining module 206 is configured to determine the starting contour position corresponding to the designated starting key point in the key point sequence and the ending contour position corresponding to the designated ending key point according to the corresponding relationship.
- Fig. 13 is a block diagram showing another image processing device according to an exemplary embodiment. As shown in Fig. 13, the fourth determining module 206 includes:
- the contour point determination sub-module 2061 is used for determining the first contour point corresponding to the starting key point and the second contour point corresponding to the ending key point in the initial state contour according to the corresponding relationship.
- the quantity determination sub-module 2062 is used to determine the initial state quantity of the contour points included in the initial state contour.
- the position determination sub-module 2063 is configured to use the ratio of the sequence number of the first contour point to the initial state number as the starting contour position, and the ratio of the sequence number of the second contour point to the initial state quantity as the ending contour position.
- Fig. 14 is a block diagram showing another image processing device according to an exemplary embodiment.
- the rendering module 204 includes:
- the first rendering sub-module 2041 is configured to render each pixel in the first line segment into a first color, and render a pixel whose distance from the pixel is less than a distance threshold into the first color. and / or,
- the second rendering sub-module 2042 is configured to render each pixel in the second line segment into a second color, and render a pixel with a distance less than the distance threshold from the pixel into the second color.
- Fig. 15 is a block diagram showing another image processing device according to an exemplary embodiment.
- the rendering module 204 includes:
- the third rendering sub-module 2043 is used to render the first pixel into the first color, and render the pixel whose distance from the first pixel is less than the first distance threshold into the first color, and the first pixel is the first line Any pixel on the segment.
- the third rendering sub-module 2043 is further configured to use the pixels whose distance from the first pixel is greater than or equal to the first distance threshold and less than the second distance threshold as the first edge pixel.
- the third rendering sub-module 2043 is further configured to determine the first edge color according to the distance between the first edge pixel and the first pixel and the first color, and render the first edge pixel into the first edge color.
- the fourth rendering sub-module 2044 is used to render the second pixel into the second color, and render the pixel whose distance from the second pixel is less than the first distance threshold into the second color, and the second pixel is the second line segment Any pixel on the top.
- the fourth rendering sub-module 2044 is further configured to use pixels whose distance from the second pixel point is greater than or equal to the first distance threshold and less than the second distance threshold as the second edge pixel.
- the fourth rendering submodule 2044 is further configured to determine the second edge color according to the distance between the second edge pixel and the second pixel, and the second color, and render the second edge pixel into the second edge color.
- the third rendering sub-module 2043 is configured to perform the following steps:
- Step 1) According to the distance between the first edge pixel and the first pixel, determine the transparency of the first edge color, the transparency of the first edge color, and the distance between the first edge pixel and the first pixel are positively correlated.
- Step 2) Use the chromaticity of the first color as the chromaticity of the first edge color.
- Step 3 Render the first edge pixels into the first edge color.
- the fourth rendering sub-module 2044 is used to perform the following steps:
- Step 4 According to the distance between the second edge pixel and the second pixel, determine the transparency of the second edge color, the transparency of the second edge color, and the distance between the second edge pixel and the second pixel are positively correlated.
- Step 5 Use the chromaticity of the second color as the chromaticity of the second edge color.
- Step 6 Render the second edge pixels into the second edge color.
- the present disclosure first identifies the target contour of the target object from the target image collected at the current moment, and then determines the starting contour corresponding to the starting contour position in the target contour according to the time difference between the current moment and the first moment.
- Point, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, and then the line segment composed of the contour points from the starting contour point to the segmented contour point is taken as the first line segment, and the target contour is divided by The line segment outside the one line segment is used as the second line segment, and finally the first line segment is rendered according to the first color, and the second line segment is rendered according to the second color.
- the present disclosure can realize the effect of dynamic stroke on the contour of the target object within a certain range indicated by the starting contour position and the ending contour position.
- FIG. 16 shows a schematic structural diagram of an electronic device (for example, the terminal device or the server in FIG. 1) 300 suitable for implementing the embodiments of the present disclosure.
- the electronic device in the embodiment of the present disclosure may be a server, which may be a local server or a cloud server, or a terminal device, and the terminal device may include, but is not limited to, mobile Phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), mobile terminals such as car navigation terminals, and mobile terminals such as digital TVs, desktops Fixed terminals for computers, etc.
- the user can upload the target image or the initial image by logging in to the server, or directly upload the target image or the initial image through the terminal device, or collect the target image or the initial image through the terminal device.
- the electronic device shown in FIG. 16 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
- the electronic device 300 may include a processing device (such as a central processing unit, a graphics processor, etc.) 301, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 302 or from a storage device 308
- the program in the memory (RAM) 303 executes various appropriate actions and processing.
- various programs and data required for the operation of the electronic device 300 are also stored.
- the processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304.
- An input/output (I/O) interface 305 is also connected to the bus 304.
- the following devices can be connected to the I/O interface 305: including input devices 306 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibrations
- input devices 306 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.
- LCD liquid crystal displays
- An output device 307 such as a device
- a storage device 308 such as a magnetic tape, a hard disk, etc.
- the communication device 309 may allow the electronic device 300 to perform wireless or wired communication with other devices to exchange data.
- FIG. 16 shows an electronic device 300 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.
- an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart.
- the computer program may be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302.
- the processing device 301 When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
- the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
- the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above.
- Computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
- a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
- a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein.
- This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
- the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
- the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
- the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
- the terminal device and the server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
- Communication e.g., communication network
- Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
- the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
- the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: recognizes the target contour of the target object in the target image collected at the current moment, and the target contour Includes a plurality of contour points; according to the time difference between the current time and the first time, and the starting contour position and the ending contour position determined at the first time, in the target contour, the starting contour is determined The starting contour point corresponding to the position, the ending contour point corresponding to the ending contour position, and the segmentation contour point corresponding to the current time, the first time being the time before the current time; and the target contour
- the line segment composed of the contour points between the starting contour point and the divided contour point is taken as the first line segment, and the line segment in the target contour except the first line segment is taken as the second line segment; Render the first line segment with one color, and render the second line segment with a second color, where the first color is different from the second color; repeat the recognition of the target image collected
- the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
- the above-mentioned programming languages include but are not limited to object-oriented programming languages such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
- the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
- the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).
- LAN local area network
- WAN wide area network
- each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions.
- the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
- each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
- the modules involved in the embodiments described in the present disclosure can be implemented in software or hardware. Among them, the name of the module does not constitute a limitation on the module itself under certain circumstances.
- the first determining module can also be described as a “module for obtaining contour points”.
- exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
- FPGA Field Programmable Gate Array
- ASIC Application Specific Integrated Circuit
- ASSP Application Specific Standard Product
- SOC System on Chip
- CPLD Complex Programmable Logical device
- a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
- the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
- the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
- machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
- RAM random access memory
- ROM read-only memory
- EPROM or flash memory erasable programmable read-only memory
- CD-ROM compact disk read only memory
- magnetic storage device or any suitable combination of the foregoing.
- Example 1 provides an image processing method, including identifying a target contour of a target object in a target image collected at the current moment, the target contour including a plurality of contour points; The time difference between the current moment and the first moment, and the starting contour position and the ending contour position determined at the first moment, in the target contour, the starting contour point corresponding to the starting contour position is determined, so The ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current time, the first time is the time before the current time; the starting contour point in the target contour is changed to the The line segment formed by the contour points between the divided contour points is taken as the first line segment, and the line segment in the target contour except the first line segment is taken as the second line segment; the first line segment is divided according to the first color Perform rendering, render the second line segment according to the second color, the first color is not the same as the second color; repeat the recognition of the target contour of the target object in the target image collected at the current moment, until all The
- Example 2 provides the method of Example 1, which is based on the time difference between the current moment and the first moment, and the starting contour position and the ending contour determined at the first moment.
- Position, in the target contour determining the starting contour point corresponding to the starting contour position, the ending contour point corresponding to the ending contour position, and the segmentation contour point corresponding to the current moment, including: The time difference between the current time and the first time, and the starting contour position and the ending contour position, determine the segmented contour position corresponding to the current time; according to the target number of contour points included in the target contour, In the target contour, the starting contour point, the ending contour point, and the segmented contour point corresponding to the position of the segmented contour are determined.
- Example 3 provides the method of Example 1. Before the recognizing the target contour of the target object in the target image collected at the current moment, the method further includes: recognizing the first moment In the acquired initial image, the initial state contour and key point sequence of the target object; determine the key points included in the key point sequence according to the nearest neighbor algorithm, and the corresponding relationship between the key points included in the initial state contour and the contour points included in the initial state contour; According to the corresponding relationship, the starting contour position corresponding to the designated starting key point in the key point sequence and the ending contour position corresponding to the designated ending key point are determined.
- Example 4 provides the method of Example 3, which determines the starting contour position corresponding to the specified starting key point in the key point sequence according to the corresponding relationship,
- the termination contour position corresponding to the designated termination key point includes: determining a first contour point corresponding to the starting key point in the initial state contour according to the corresponding relationship, and the termination key point Corresponding second contour point; determine the initial state number of contour points included in the initial state contour; use the ratio of the serial number of the first contour point to the initial state quantity as the initial contour position, and set the The ratio of the sequence number of the second contour point to the number of the initial state is used as the end contour position.
- Example 5 provides the method of any one of Examples 1 to 4, wherein the first line segment is rendered according to a first color, and the first line segment is rendered according to a second color.
- Rendering the second line segment includes: rendering each pixel in the first line segment as the first color, and rendering the pixel points whose distance from the pixel point is less than a distance threshold value as the first color; And/or, rendering each pixel point in the second line segment as the second color, and rendering a pixel point whose distance from the pixel point is less than the distance threshold value as the second color.
- Example 6 provides the method of any one of Examples 1 to 4, wherein the first line segment is rendered according to a first color, and the first line segment is rendered according to a second color.
- Rendering the second line segment includes: rendering a first pixel point into the first color, and rendering a pixel point whose distance from the first pixel point is less than a first distance threshold into the first color; A pixel point is any pixel point on the first line segment; a pixel point whose distance from the first pixel point is greater than or equal to the first distance threshold and less than the second distance threshold is regarded as the first edge Pixel; according to the distance between the first edge pixel and the first pixel, and the first color, determine a first edge color, and render the first edge pixel as the first edge Color; and/or, rendering a second pixel into the second color, and rendering a pixel whose distance from the second pixel is less than the first distance threshold into the second color, and Two pixels are any pixel on the second line segment;
- Example 7 provides the method of Example 6, wherein the first edge pixel is determined according to the distance between the first edge pixel and the first pixel and the first color.
- Edge color, and rendering the first edge pixel point into the first edge color includes: determining the transparency of the first edge color according to the distance between the first edge pixel point and the first pixel point , The transparency of the first edge color is positively correlated with the distance between the first edge pixel and the first pixel; the chromaticity of the first color is used as the chromaticity of the first edge color; Rendering the first edge pixel into the first edge color; said determining a second edge color according to the distance between the second edge pixel and the second pixel and the second color, And rendering the second edge pixel into the second edge color includes: determining the transparency of the second edge color according to the distance between the second edge pixel and the second pixel, and The transparency of the second edge color is positively related to the distance between the second edge pixel and the second pixel; the chromati
- Example 8 provides an image processing device, the device includes: a recognition module for recognizing the target contour of the target object in the target image collected at the current moment, the target contour Includes a plurality of contour points; a first determining module, used to determine the starting contour position and ending contour position at the first time according to the time difference between the current time and the first time, in the target contour , Determine the starting contour point corresponding to the starting contour position, the ending contour point corresponding to the ending contour position, and the segmented contour point corresponding to the current moment, and the first moment is a moment before the current moment
- the second determining module is used to take the line segment composed of the contour points between the initial contour point and the divided contour point in the target contour as the first line segment, and divide the target contour by the first
- a line segment other than a line segment is used as a second line segment
- the rendering module is configured to render the first line segment according to a first color, and render the second line segment according to a second color, where the first color is the same as
- Example 9 provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the methods described in Examples 1 to 7 are implemented.
- Example 10 provides an electronic device, including: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to Implement the steps of the methods described in Example 1 to Example 7.
- Example 11 provides a computer program having a computer program stored thereon, and when the program is executed by a processing device, the steps of the methods described in Examples 1 to 7 are implemented.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (11)
- 一种图像的处理方法,其特征在于,所述方法包括:识别当前时刻采集的目标图像中目标对象的目标轮廓,所述目标轮廓中包括多个轮廓点;根据所述当前时刻与第一时刻的时间差,和在所述第一时刻确定的起始轮廓位置、终止轮廓位置,在所述目标轮廓中,确定所述起始轮廓位置对应的起始轮廓点,所述终止轮廓位置对应的终止轮廓点,和所述当前时刻对应的分割轮廓点,所述第一时刻为所述当前时刻之前的时刻;将所述目标轮廓中所述起始轮廓点至所述分割轮廓点之间的轮廓点组成的线段作为第一线段,将所述目标轮廓中除所述第一线段之外的线段作为第二线段;按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染,所述第一颜色与所述第二颜色不相同;重复执行所述识别当前时刻采集的目标图像中目标对象的目标轮廓,至所述按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染的步骤,直至所述目标轮廓中,所述起始轮廓点至所述终止轮廓点之间的轮廓点组成的线段被渲染为所述第一颜色。
- 根据权利要求1所述的方法,其特征在于,所述根据所述当前时刻与第一时刻的时间差,和在所述第一时刻确定的起始轮廓位置、终止轮廓位置,在所述目标轮廓中,确定所述起始轮廓位置对应的起始轮廓点,所述终止轮廓位置对应的终止轮廓点,和所述当前时刻对应的分割轮廓点,包括:根据所述当前时刻与所述第一时刻的时间差,和所述起始轮廓位置、所述终止轮廓位置,确定所述当前时刻对应的分割轮廓位置;根据所述目标轮廓包括的轮廓点的目标数量,在所述目标轮廓中,确定所述起始轮廓点、所述终止轮廓点,和所述分割轮廓位置对应的所述分割轮廓点。
- 根据权利要求1或2所述的方法,其特征在于,在所述识别当前时刻采集的目标图像中目标对象的目标轮廓之前,所述方法还包括:识别所述第一时刻采集的初始图像中,所述目标对象的初态轮廓和关键点序列;按照最近邻算法确定所述关键点序列中包括的关键点,与所述初态轮廓中包括的轮廓点的对应关系;根据所述对应关系,确定所述关键点序列中指定的起始关键点对应的所述起始轮廓位置,和指定的终止关键点对应的所述终止轮廓位置。
- 根据权利要求3所述的方法,其特征在于,所述根据所述对应关系,确定所述关键点序列中指定的起始关键点对应的所述起始轮廓位置,和指定的终止关键点对应的所述终止轮廓位置,包括:根据所述对应关系,在所述初态轮廓中,确定所述起始关键点对应的第一轮廓点,和所述终止关键点对应的第二轮廓点;确定所述初态轮廓包括的轮廓点的初态数量;将所述第一轮廓点的序号与所述初态数量的比值作为所述起始轮廓位置,将所述第二轮廓点的序号与所述初态数量的比值作为所述终止轮廓位置。
- 根据权利要求1-4中任一项所述的方法,其特征在于,所述按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染,包括:将所述第一线段中的每个像素点渲染为所述第一颜色,并将与该像素点距离小于距离阈值的像素点渲染为所述第一颜色;和/或,将所述第二线段中的每个像素点渲染为所述第二颜色,并将与该像素点距离小于所述距离阈值的像素点渲染为所述第二颜色。
- 根据权利要求1-4中任一项所述的方法,其特征在于,所述按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染,包括:将第一像素点渲染为所述第一颜色,并将与所述第一像素点距离小于第一距离阈值的像素点渲染为所述第一颜色,所述第一像素点为所述第一线段上的任一像素点;将与所述第一像素点距离大于或等于所述第一距离阈值,且小于第二距离阈值的像素点,作为第一边缘像素点;根据所述第一边缘像素点与所述第一像素点的距离,和所述第一颜色,确定第一边缘颜色,并将所述第一边缘像素点渲染为所述第一边缘颜色;和/或,将第二像素点渲染为所述第二颜色,并将与所述第二像素点距离小于所述第一距离阈值的像素点渲染为所述第二颜色,所述第二像素点为所述第二线段上的任一像素点;将与所述第二像素点距离大于或等于所述第一距离阈值,且小于所述第二距离阈值的像素点,作为第二边缘像素点;根据所述第二边缘像素点与所述第二像素点的距离,和所述第二颜色,确定第二边缘颜色,并将所述第二边缘像素点渲染为所述第二边缘颜色。
- 根据权利要求6所述的方法,其特征在于,所述根据所述第一边缘像素点与所述第一像素点的距离,和所述第一颜色,确定第一边缘颜色,并将所述第一边缘像素点渲染为所述第一边缘颜色,包括:根据所述第一边缘像素点与所述第一像素点的距离,确定所述第一边缘颜色的透明度,所述第一边缘颜色的透明度,和所述第一边缘像素点与所述第一像素点的距离正相关;将所述第一颜色的色度作为所述第一边缘颜色的色度;将所述第一边缘像素点渲染为所述第一边缘颜色;所述根据所述第二边缘像素点与所述第二像素点的距离,和所述第二颜色,确定第二边缘颜色,并将所述第二边缘像素点渲染为所述第二边缘颜色,包括:根据所述第二边缘像素点与所述第二像素点的距离,确定所述第二边缘颜色的透明度,所述第二边缘颜色的透明度,和所述第二边缘像素点与所述第二像素点的距离正相关;将所述第二颜色的色度作为所述第二边缘颜色的色度;将所述第二边缘像素点渲染为所述第二边缘颜色。
- 一种图像的处理装置,其特征在于,所述装置包括:识别模块,用于识别当前时刻采集的目标图像中目标对象的目标轮廓,所述目标轮廓中包括多个轮廓点;第一确定模块,用于根据所述当前时刻与第一时刻的时间差,和在所述第一时刻 确定的起始轮廓位置、终止轮廓位置,在所述目标轮廓中,确定所述起始轮廓位置对应的起始轮廓点,所述终止轮廓位置对应的终止轮廓点,和所述当前时刻对应的分割轮廓点,所述第一时刻为所述当前时刻之前的时刻;第二确定模块,用于将所述目标轮廓中所述起始轮廓点至所述分割轮廓点之间的轮廓点组成的线段作为第一线段,将所述目标轮廓中除所述第一线段之外的线段作为第二线段;渲染模块,用于按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染,所述第一颜色与所述第二颜色不相同;重复执行所述识别当前时刻采集的目标图像中目标对象的目标轮廓,至所述按照第一颜色对所述第一线段进行渲染,按照第二颜色对所述第二线段进行渲染的步骤,直至所述目标轮廓中,所述起始轮廓点至所述终止轮廓点之间的轮廓点组成的线段被渲染为所述第一颜色。
- 一种计算机可读介质,其上存储有计算机程序,其特征在于,该程序被处理装置执行时实现权利要求1-7中任一项所述方法的步骤。
- 一种电子设备,其特征在于,包括:存储装置,其上存储有计算机程序;处理装置,用于执行所述存储装置中的所述计算机程序,以实现权利要求1-7中任一项所述方法的步骤。
- 一种计算机程序,其特征在于,包括程序代码,当计算机运行所述计算机程序时,所述程序代码执行如权利要求1-7中任一项所述方法的步骤。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/782,985 US12062116B2 (en) | 2020-01-06 | 2020-11-03 | Image processing method and apparatus, readable medium and electronic device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010010816.8 | 2020-01-06 | ||
CN202010010816.8A CN111210485B (zh) | 2020-01-06 | 2020-01-06 | 图像的处理方法、装置、可读介质和电子设备 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021139372A1 true WO2021139372A1 (zh) | 2021-07-15 |
Family
ID=70789689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/126255 WO2021139372A1 (zh) | 2020-01-06 | 2020-11-03 | 图像的处理方法、装置、可读介质和电子设备 |
Country Status (3)
Country | Link |
---|---|
US (1) | US12062116B2 (zh) |
CN (1) | CN111210485B (zh) |
WO (1) | WO2021139372A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024027820A1 (zh) * | 2022-08-05 | 2024-02-08 | 北京字跳网络技术有限公司 | 基于图像的动画生成方法、装置、设备及存储介质 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210485B (zh) | 2020-01-06 | 2023-03-28 | 北京字节跳动网络技术有限公司 | 图像的处理方法、装置、可读介质和电子设备 |
CN117435110B (zh) * | 2023-10-11 | 2024-06-18 | 书行科技(北京)有限公司 | 一种图片处理方法、装置、电子设备和存储介质 |
CN117115194B (zh) * | 2023-10-20 | 2024-01-30 | 华芯程(杭州)科技有限公司 | 基于电子显微镜图像的轮廓提取方法、装置、设备及介质 |
CN117197171B (zh) * | 2023-11-06 | 2024-01-30 | 苏州培风图南半导体有限公司 | 一种图形轮廓检测方法、装置及存储介质 |
CN117274366B (zh) * | 2023-11-22 | 2024-02-20 | 合肥晶合集成电路股份有限公司 | 线条边距确定方法和装置 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268918A (zh) * | 2014-10-09 | 2015-01-07 | 佛山精鹰传媒股份有限公司 | 一种二维动画与三维立体动画融合的处理方法 |
CN107123077A (zh) * | 2017-03-30 | 2017-09-01 | 腾讯科技(深圳)有限公司 | 对象的渲染方法和装置 |
US20180211400A1 (en) * | 2017-01-26 | 2018-07-26 | Samsung Electronics Co., Ltd. | Stereo matching method and apparatus |
CN110288670A (zh) * | 2019-06-19 | 2019-09-27 | 杭州绝地科技股份有限公司 | 一种ui描边特效的高性能渲染方法 |
CN111210485A (zh) * | 2020-01-06 | 2020-05-29 | 北京字节跳动网络技术有限公司 | 图像的处理方法、装置、可读介质和电子设备 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7656408B1 (en) * | 2006-02-10 | 2010-02-02 | Adobe Systems, Incorporated | Method and system for animating a border |
US8130226B2 (en) * | 2006-08-04 | 2012-03-06 | Apple Inc. | Framework for graphics animation and compositing operations |
US10395401B2 (en) * | 2015-08-07 | 2019-08-27 | Zhejiang University | Method for efficient parallel visualizing vector graphic |
CN105654531B (zh) * | 2015-12-30 | 2019-01-08 | 北京金山安全软件有限公司 | 一种图像轮廓的绘制方法及装置 |
CN108805957B (zh) * | 2018-06-07 | 2022-06-24 | 青岛九维华盾科技研究院有限公司 | 一种基于位图图像自适应分割的矢量图生成方法及系统 |
CN110058685B (zh) * | 2019-03-20 | 2021-07-09 | 北京字节跳动网络技术有限公司 | 虚拟对象的显示方法、装置、电子设备和计算机可读存储介质 |
CN110610453B (zh) * | 2019-09-02 | 2021-07-06 | 腾讯科技(深圳)有限公司 | 一种图像处理方法、装置及计算机可读存储介质 |
-
2020
- 2020-01-06 CN CN202010010816.8A patent/CN111210485B/zh active Active
- 2020-11-03 US US17/782,985 patent/US12062116B2/en active Active
- 2020-11-03 WO PCT/CN2020/126255 patent/WO2021139372A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268918A (zh) * | 2014-10-09 | 2015-01-07 | 佛山精鹰传媒股份有限公司 | 一种二维动画与三维立体动画融合的处理方法 |
US20180211400A1 (en) * | 2017-01-26 | 2018-07-26 | Samsung Electronics Co., Ltd. | Stereo matching method and apparatus |
CN107123077A (zh) * | 2017-03-30 | 2017-09-01 | 腾讯科技(深圳)有限公司 | 对象的渲染方法和装置 |
CN110288670A (zh) * | 2019-06-19 | 2019-09-27 | 杭州绝地科技股份有限公司 | 一种ui描边特效的高性能渲染方法 |
CN111210485A (zh) * | 2020-01-06 | 2020-05-29 | 北京字节跳动网络技术有限公司 | 图像的处理方法、装置、可读介质和电子设备 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024027820A1 (zh) * | 2022-08-05 | 2024-02-08 | 北京字跳网络技术有限公司 | 基于图像的动画生成方法、装置、设备及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN111210485B (zh) | 2023-03-28 |
US20230005194A1 (en) | 2023-01-05 |
CN111210485A (zh) | 2020-05-29 |
US12062116B2 (en) | 2024-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021139372A1 (zh) | 图像的处理方法、装置、可读介质和电子设备 | |
WO2021139408A1 (zh) | 显示特效的方法、装置、存储介质及电子设备 | |
JP7199527B2 (ja) | 画像処理方法、装置、ハードウェア装置 | |
US10181203B2 (en) | Method for processing image data and apparatus for the same | |
WO2024012251A1 (zh) | 语义分割模型训练方法、装置、电子设备及存储介质 | |
US20240305860A1 (en) | Method and apparatus for playing back video at multiple-speed, electronic device and storage medium | |
WO2021254502A1 (zh) | 目标对象显示方法、装置及电子设备 | |
WO2020253453A1 (zh) | 图像切换方法、装置、电子设备及存储介质 | |
WO2021027631A1 (zh) | 图像特效处理方法、装置、电子设备和计算机可读存储介质 | |
JP7553582B2 (ja) | 画像特殊効果の処理方法及び装置 | |
JP2023509429A (ja) | 画像処理方法及び装置 | |
US11818491B2 (en) | Image special effect configuration method, image recognition method, apparatus and electronic device | |
WO2023138441A1 (zh) | 视频生成方法、装置、设备及存储介质 | |
WO2024037556A1 (zh) | 图像处理方法、装置、设备及存储介质 | |
WO2023179310A1 (zh) | 图像修复方法、装置、设备、介质及产品 | |
WO2022247630A1 (zh) | 图像处理方法、装置、电子设备及存储介质 | |
WO2020077912A1 (zh) | 图像处理方法、装置、硬件装置 | |
CN112257598B (zh) | 图像中四边形的识别方法、装置、可读介质和电子设备 | |
JP2023538825A (ja) | ピクチャのビデオへの変換の方法、装置、機器および記憶媒体 | |
WO2023231918A1 (zh) | 图像处理方法、装置、电子设备及存储介质 | |
WO2023035973A1 (zh) | 视频处理方法、装置、设备及介质 | |
WO2023273621A1 (zh) | 脚本生成方法、装置、设备及介质 | |
WO2021233379A1 (zh) | 配置视频特效方法、装置、设备及存储介质 | |
JP2023550970A (ja) | 画面の中の背景を変更する方法、機器、記憶媒体、及びプログラム製品 | |
WO2021073204A1 (zh) | 对象的显示方法、装置、电子设备及计算机可读存储介质 |
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: 20912616 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20912616 Country of ref document: EP Kind code of ref document: A1 |
|
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 14.02.2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20912616 Country of ref document: EP Kind code of ref document: A1 |