CN115209052B - Image screening method and device, electronic equipment and storage medium - Google Patents
Image screening method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115209052B CN115209052B CN202210806681.5A CN202210806681A CN115209052B CN 115209052 B CN115209052 B CN 115209052B CN 202210806681 A CN202210806681 A CN 202210806681A CN 115209052 B CN115209052 B CN 115209052B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- frames
- feature point
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72439—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for image or video messaging
Abstract
The application discloses an image screening method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring N frames of first images, wherein the N frames of first images are images including a shooting object; determining a fitting curve corresponding to the motion trail of the shooting object based on the N frames of first images; the fitting curve comprises N characteristic points corresponding to the N frames of first images; determining a second image satisfying a first condition from the N frames of first images based on a position offset between each feature point of the N feature points and the preset parabola under the condition that the fitted curve conforms to the preset parabola; wherein N is an integer greater than 5.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to an image screening method and device, electronic equipment and a storage medium.
Background
At present, when a user uses electronic equipment to capture the best moment of a motion scene, the user often needs to capture multiple times because a motion subject is too fast and wonderful, instantaneous and evanescent, so that the electronic equipment can obtain multiple frame images, and then the user can select the multiple frame images to obtain the images required by the user.
In the related art, after obtaining multiple frames of images, the electronic device may recommend an optimal motion moment according to the definition of the multiple frames of images and the facial expression of a shooting object in the multiple frames of images, so as to screen out an image required by a user.
However, in the above method, although the operation of screening images by the user is simplified, the electronic device does not meet the requirement of the user in terms of the aesthetic posture because the electronic device only recommends the optimal movement time according to the definition of the multi-frame images and the facial expression of the photographic subject in the multi-frame images, and thus the accuracy of screening images by the electronic device is low.
Disclosure of Invention
An object of the embodiments of the present application is to provide an image screening method, an image screening apparatus, an electronic device, and a storage medium, which can solve the problem of low accuracy of image screening by an electronic device.
In a first aspect, an embodiment of the present application provides an image screening method, where the image screening method includes: acquiring N frames of first images, wherein the N frames of first images comprise images of shot objects; determining a fitting curve corresponding to the motion trail of the shooting object based on the N frames of first images; the fitting curve comprises N characteristic points corresponding to N frames of first images; determining a second image satisfying a first condition from the N frames of first images based on a position offset between each feature point of the N feature points and the preset parabola under the condition that the fitted curve conforms to the preset parabola; wherein N is an integer greater than 5.
In a second aspect, an embodiment of the present application provides an image screening apparatus, including: the device comprises an acquisition module and a determination module. The acquisition module is used for acquiring N frames of first images, and the N frames of first images are images including shot objects. The determining module is used for determining a fitting curve corresponding to the motion track of the shooting object based on the N frames of first images; the fitting curve comprises N characteristic points corresponding to N frames of first images; under the condition that the fitting curve accords with a preset parabola, determining a second image meeting a first condition from the N frames of first images on the basis of the position offset between each characteristic point of the N characteristic points and the preset parabola; wherein N is an integer greater than 5.
In a third aspect, embodiments of the present application provide an electronic device, which includes a processor and a memory, where the memory stores a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implement the steps of the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the method according to the first aspect.
In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method according to the first aspect.
In a sixth aspect, embodiments of the present application provide a computer program product, stored on a storage medium, for execution by at least one processor to implement the method according to the first aspect.
In this embodiment, the electronic device may acquire N frames of first images, where the N frames of first images are images including a photographic subject, so as to determine a fitted curve corresponding to a motion trajectory of the photographic subject in the N frames of first images according to the N frames of first images, and then, in a case where the fitted curve conforms to a preset parabola, the electronic device may determine a second image satisfying a first condition from the N frames of first images based on a position offset between each feature point on the fitted curve (i.e., position information of the photographic subject in the N frames of first images) and the preset parabola. In the scheme, the electronic equipment can judge the motion behavior corresponding to the shot object according to the relation between the fitting curve and the preset parabola, and then the electronic equipment can determine the second image meeting the first condition from the N frames of first images according to the position offset between each feature point on the fitting curve of the shot object under the motion behavior and the preset parabola, and does not need to manually select the image required by the user from the multi-frame image after the multi-frame image is obtained by the electronic equipment.
Drawings
Fig. 1 is a flowchart of an image screening method according to an embodiment of the present application;
fig. 2 is a second flowchart of an image screening method according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an image screening apparatus according to an embodiment of the present application;
fig. 4 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present disclosure;
fig. 5 is a second schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.
The image screening method provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
With the development of communication technology, functions in electronic equipment are increasing day by day, for example, a user can record an optimal moment in a motion scene by capturing a plurality of frames of images, and the electronic equipment often needs to capture a plurality of frames of images by capturing the motion subject too fast and the highlight is lost instantly, so that the user can select images required by the user from the plurality of frames of images by a mobile phone, and the process is time-consuming and tedious; in the related art, the electronic device can guide the user to shoot at different shooting angles through a guiding type interactive guidance mode so as to obtain a more wonderful motion moment; or after the electronic device obtains the multiple frames of images, the electronic device may perform post-screening of the optimal motion time picture in a post-processing manner according to the image sharpness of the multiple frames of images and the facial expressions of the multiple frames of images.
However, in the two methods, the first method requires the user to shoot the shot object at different angles through a large number of preset shooting angles, so as to obtain an image with a good shooting effect, the process is time-consuming and tedious, and the second method simplifies the operation of screening the image by the user, but since the electronic device only recommends the best motion moment according to the definition of a plurality of frames of images and the facial expression of the shot object in the plurality of frames of images, the requirement of the user on the aspect of posture attractiveness cannot be met, and thus, the accuracy of screening the image by the electronic device is low.
In this embodiment, the electronic device may acquire N frames of first images, where the N frames of first images are images including a photographic subject, so as to determine a fitted curve corresponding to a motion trajectory of the photographic subject in the N frames of first images according to the N frames of first images, and then, in a case where the fitted curve conforms to a preset parabola, the electronic device may determine, from the N frames of first images, a second image that satisfies a first condition based on a position offset between each feature point on the fitted curve (i.e., position information of the photographic subject in the N frames of first images) and the preset parabola. In the scheme, the electronic equipment can judge the motion behavior corresponding to the shot object according to the relation between the fitting curve and the preset parabola, and then the electronic equipment can determine the second image meeting the first condition from the N frames of first images according to the position offset between each characteristic point on the fitting curve of the shot object under the motion behavior and the preset parabola, the electronic equipment does not need to manually select the image required by the user from the multi-frame images after obtaining the multi-frame images, in addition, the problem that the accuracy of the image screened out by the electronic equipment only according to the definition of the multi-frame images and the facial features of the shot object in the multi-frame images is lower is avoided, and therefore, the accuracy of image screening of the electronic equipment is improved while the user operation is simplified.
The execution main body of the image screening method provided by the embodiment of the application can be an image screening device, and the image screening device can be electronic equipment or a functional module in the electronic equipment. The following describes technical solutions provided in embodiments of the present application by taking an electronic device as an example.
An embodiment of the present application provides an image screening method, and fig. 1 shows a flowchart of the image screening method provided in the embodiment of the present application. As shown in fig. 1, the image screening method provided in the embodiment of the present application may include steps 201 to 203 described below.
In this embodiment of the present application, the N frames of the first image are images including a photographic subject, and N is an integer greater than 5.
Specifically, the photographic subject may include a first subject and a second subject, and the N frames of the first image may be understood as including an image acquired by the first subject controlling the second subject so that the second subject is in a moving state.
In this embodiment, the electronic device may acquire, through a motion burst mode, N consecutive frames of first images including a first object controlling movement of a second object.
Optionally, in this embodiment of the present application, the second object may be a movable object.
Illustratively, the movable object may be any one of: basketball, badminton, volleyball or tennis, etc.
Alternatively, in this embodiment, the first object may be a human or an animal.
It should be noted that the first image described in the embodiments of the present application is described in a broad sense, that is, the first image may be understood as a video frame of a picture or a video.
Optionally, in this embodiment of the application, the electronic device may receive a first input of a shooting mode control by a user in a shooting preview interface, so as to trigger the electronic device to switch the shooting mode to a motion continuous shooting mode, so that the electronic device may acquire N consecutive frames of the first image.
Optionally, in this embodiment of the application, the first input may be a click input, a long-press input, a sliding input, or a preset trajectory input of the user on the shooting mode control; or a physical key combination (e.g., power key and volume key). The method can be determined according to actual use requirements, and the embodiment of the application is not limited.
In this embodiment of the present application, the fitting curve includes N feature points corresponding to N frames of the first image. One feature point corresponds to one frame of the first image. In other words, one feature point is used to represent the position of the photographic subject in one frame of the first image.
In the embodiment of the application, after the electronic device acquires the N frames of first images, the electronic device can acquire the position information of the shooting object in each frame of first image in the N frames of first images in a first mode, so that the electronic device can acquire the motion track of the shooting object according to the position information of the shooting object in the N frames of first images, and further the electronic device can determine the fitting curve corresponding to the motion track according to the motion track of the shooting object.
Optionally, in this embodiment of the application, the first mode may be any one of the following: feature extraction algorithms, convolutional neural networks, or generative antagonistic neural networks.
In other words, the N feature points may be points corresponding to the position information of the photographic subject in the N first images.
Optionally, in this embodiment of the application, the position information may include horizontal position information and vertical position information, where the vertical position information is a vertical distance between the shooting object and the first reference point, and the horizontal position information is a horizontal distance between the shooting object and the second reference point.
For example, the first reference point and the second reference point may be preset by a user, or the electronic device may determine the first reference point according to a size of the captured first image.
Illustratively, taking the case where the user shoots a basketball using the basketball as an example, in the case where the first reference point is the ground and the second reference point is the basket, the longitudinal position information of the basketball is a vertical distance between the basketball and the ground, and the lateral position information of the basketball is a horizontal distance between the basketball and the basket.
Further illustratively, taking the first image of one frame as an example, assuming that the horizontal position of the object is the horizontal coordinate, the vertical position of the object is the vertical coordinate, assuming that the horizontal position of the object in the current frame image is 1 meter, and the vertical position of the object in the current frame image is 2 meters, the feature point corresponding to the current frame image is (1,2).
Alternatively, in this embodiment of the application, the step 202 may be specifically implemented by the step 202a described below.
Step 202a, the electronic device fits the motion track of the shooting object by using a least square method based on the N frames of the first image to obtain a fit curve corresponding to the motion track of the shooting object.
In this embodiment of the application, after obtaining the position information of the photographic object in the N frames of first images, the electronic device may determine the motion trajectory of the photographic object according to the position information of the photographic object in each frame of first images in the N frames of first images, so as to fit the motion trajectory of the photographic object by using a least square method (that is, the following formula one) to obtain a fit curve corresponding to the motion trajectory of the photographic object, where the specific formula one is:
y＝ax 1/2 +bx+cx 2 + d (formula one)
Wherein, a, b, c and d are parameters to be fitted, y is a coordinate corresponding to the longitudinal position of the shooting object, and x is a coordinate corresponding to the transverse position of the shooting object.
In the embodiment of the application, the electronic device can fit the fitting curve of the motion track of the shooting object by a least square method, so that the electronic device can determine the motion behavior of the shooting object according to the fitting curve and the preset parabola.
Optionally, in this embodiment of the present application, after the step 202, the image screening method provided in this embodiment of the present application further includes the following step 301.
Step 301, the electronic device determines whether the fitting curve conforms to a preset parabola based on a longest common subsequence trajectory similarity measurement method lcs.
It should be noted that the electronic device may determine whether the shot object is in the preset motion behavior according to whether the fitted curve conforms to the preset parabola, and the image screened by the electronic device is a second image including the preset motion behavior of the user.
Specifically, the parabolic function of the preset parabola is y 2 ＝2px。
In this embodiment of the application, after the electronic device obtains the fitted curve of the photographed object, the electronic device may input the fitted curve and the preset parabola into an lcs algorithm (for example, the following formula two), so as to determine whether the fitted curve conforms to the preset parabola, where the specific formula two is:
wherein, head (tr) 1 ) To fit the ith feature point on the curve, head (tr) 2 ) Rest (tr) is the ith characteristic point on the preset parabola 1 ) Rest (tr) as the i +1 th feature point on the fitted curve 2 ) Is the i +1 th feature point on the preset parabola and epsilon is the threshold value of the minimum distance between the fitted curve and the feature point on the preset parabola.
For example, the electronic device may traverse each feature point on the fitting curve and on the preset parabola through the lcs algorithm, so that in the case that the distance between the feature points in the two parabolas is smaller than the preset threshold, the electronic device may add 1 to obtain the number of the distances between each feature point on the fitting curve and on the preset parabola which are smaller than the preset threshold.
Exemplarily, the electronic device inputs the obtained fitted curve and the preset parabola into the lcs algorithm, through which the electronic device can obtain the number of points with the minimum distance (hereinafter, referred to as target number) in the two parabolas, and then the electronic device can determine whether the fitted curve and the preset parabola are in the same trend through the relationship between the target number and the preset threshold, that is, the electronic device can determine whether the fitted curve conforms to the preset parabola. The relationship between the target number and the preset threshold may be:
wherein, d LCSS (tr 1 ,tr 2 ) Alpha is a preset threshold value.
For example, assuming that the preset threshold is 10, if the number of the obtained targets of the electronic device is greater than the preset threshold, the electronic device may determine that the fitting curve conforms to the preset parabola, and if the number of the obtained targets of the electronic device is less than the preset threshold, the electronic device may determine that the fitting curve does not conform to the preset parabola.
In the embodiment of the application, the electronic device can input the fitting curve and the preset parabola to the LCSS algorithm, and determine whether the fitting curve meets the preset parabola or not through the relation between the target number between the fitting curve and the preset parabola and the preset threshold, so that the electronic device can determine the second image meeting the first condition from the N frames of the first images according to the position offset between the characteristic point in the fitting curve and the preset parabola, and thus, the accuracy of image screening of the electronic device is improved.
In the embodiment of the application, if the fitting curve conforms to the preset parabola, it is indicated that the behavior trend of the shooting object is consistent with the trend of the preset parabola.
In the embodiment of the present application, the position offset between any characteristic point on the fitting curve and the preset parabola is: the distance between any one characteristic point and a second characteristic point on the preset parabola. Wherein, the second characteristic point is: and the characteristic point on the preset parabola, which is closest to any characteristic point.
In an embodiment of the present application, the second image satisfying the first condition is: and the position offset amount of the characteristic points corresponding to the N frames of first images is larger than a preset offset threshold value.
In this embodiment of the application, when the fitted curve conforms to the preset parabolic curve, the electronic device may obtain a position offset between each feature point of the N feature points and the preset parabolic curve through a deviation degree algorithm (i.e., the following formula four), so that the electronic device may determine, according to the position offset corresponding to each feature point, the second image satisfying the first condition from the N frames of the first image, where the specific formula four may be:
wherein x is i For the lateral position of the object in each of the N first images, h i G longitudinal position of the object in each of the N first images xh4 And g xh3 Respectively representing a 4 th order operator and a 3 rd order operator for calculating the degree of deviation, deltah, between the photographic subject and a preset parabola i The height difference between the actual position of the photographic subject in the first image and the preset parabolic curve is calculated for each frame.
For example, the electronic device may calculate a degree of offset between the photographic object and the preset parabola through a 4-order operator and a 3-order operator, and then subtract a height difference between an actual position of the photographic object in each frame of the first image and the preset parabola curve through the 4-order operator, so as to obtain a position offset between the actual position of the photographic object in each frame of the first image and the preset parabola curve.
Optionally, in this embodiment of the application, after obtaining the position deviation amount between the photographic subject and the preset parabola (hereinafter, referred to as N position deviation amounts) in each frame of the first image, the electronic device may integrate the N position deviation amounts into one position deviation vector or position deviation array, so that the electronic device may determine the second image satisfying the first condition from the N frames of the first image according to the position deviation vector or position deviation array.
Optionally, in this embodiment of the application, the electronic device may integrate the N position deviation quantities into one position deviation degree vector or one position deviation degree array through a preset sequence (for example, a positive sequence or a reverse sequence).
Specifically, taking the example that the electronic device integrates N position offset quantities into one position offset vector, and taking the reverse order as an example, the electronic device can integrate the N position offset quantities into one position offset vector through an integration vector algorithm, and the position offset vector can be represented by the following formula five:
diff(X,H)＝(diff(x N ,h N ),diff(x N-1 ,h N-1 ),...,diff(x 1 ,h 1 ) Equation five)
Wherein, diff (x) i ,h i ) For each of the N position offset amounts.
Alternatively, in this embodiment of the application, the step 203 may be specifically implemented by the step 203a described below.
In step 203a, the electronic device starts from a first feature point of the N feature points and traverses the N feature points.
In the embodiment of the present application, each of the N feature points corresponds to one frame of the N frames of the first image. The first feature point is a feature point corresponding to a last frame image in the N frames of first images. Namely, the first image corresponding to the first feature point is the last frame of the N frames of first images.
In the embodiment of the application, in the process of traversing the N feature points, the electronic device executes the following process for each feature point:
if the position offset between the currently traversed feature point and the preset parabola is less than or equal to the preset offset threshold, the electronic equipment continues to traverse the next feature point of the currently traversed feature point;
and if the position offset between the currently traversed feature point and the preset parabola is larger than a preset offset threshold, the electronic equipment takes the first image corresponding to the next feature point of the currently traversed feature point as a second image.
In the embodiment of the application, after the electronic device obtains the position offset corresponding to the N feature points, the electronic device may traverse the N feature points, so that the electronic device may determine, according to a predetermined offset threshold, a second image that satisfies a first condition from the N frames of first images. For example, when the offset of the current frame obtained by traversal of the electronic device is smaller than the maximum offset threshold, the electronic device may traverse the offset of the first image of the next frame, and if the offset of the current frame obtained by traversal of the electronic device is larger than the maximum offset threshold (i.e., a first condition), the electronic device may determine the first image of the previous frame of the first image corresponding to the offset of the previous frame as the second image.
Optionally, in this embodiment of the application, the predetermined offset threshold may be determined by a user, or determined by the electronic device according to a maximum distance offset between the shooting object and a preset parabola.
Optionally, in this embodiment of the application, after obtaining the position offset vectors of the N position offset amounts, the electronic device may traverse each position offset amount of the N position offset amounts through a reverse traversal algorithm (e.g., the following formula six), so as to determine the second image satisfying the first condition from the N frames of the first image, where a specific formula six may be:
wherein i =1,2 … …, N; x i For the lateral position of the object in the N first images of each frame, H i Longitudinal position of each frame of first image in N frames of first image for shooting objectAnd diff (Head (X), head (H)) is the offset between the shot object in the current frame and the preset parabola, next (X), next (H) is the Next reverse dynamic search frame, and μ is the preset offset threshold.
Optionally, in this embodiment of the present application, the electronic device may add a first identifier to each frame of the N frames of first images, and establish a correspondence between N first identifiers corresponding to the N frames of first images and N position offset amounts corresponding to the N frames of first images, so that the electronic device may determine the second image from the N frames of first images according to the correspondence.
For example, after determining a target feature point (a position offset between the target feature point and a preset parabola is greater than a predetermined offset threshold), the electronic device may find a first identifier corresponding to the position offset corresponding to the target feature point based on the position offset corresponding to the target feature point and the corresponding relationship, so as to use a previous frame image of the first image corresponding to the first identifier as the second image.
Illustratively, the first identifier may include at least one of: a number mark, a letter mark, a symbol mark and an expression mark.
Optionally, in this embodiment of the application, after the electronic device determines the second image, the electronic device adds a second identifier to the second image, and returns the second image to which the second identifier is added to a target application program (for example, an album application program), so that the second image to which the second identifier is added is displayed to a user, and the user can quickly find the second image.
Illustratively, the second identifier may include at least one of: a number mark, a letter mark, a symbol mark and an expression mark.
In the image screening method provided by the embodiment of the application, the electronic device may acquire N frames of first images, where the N frames of first images are images including a photographic subject, so as to determine a fitted curve corresponding to a motion trajectory of the photographic subject in the N frames of first images according to the N frames of first images, and then, in a case that the fitted curve conforms to a preset parabola, the electronic device may determine a second image satisfying a first condition from the N frames of first images based on a position offset between each feature point on the fitted curve (i.e., position information of the photographic subject in the N frames of first images) and the preset parabola. In the scheme, the electronic equipment can judge the motion behavior corresponding to the shot object according to the relation between the fitting curve and the preset parabola, and then the electronic equipment can determine the second image meeting the first condition from the N frames of first images according to the position offset between each characteristic point on the fitting curve of the shot object under the motion behavior and the preset parabola, the electronic equipment does not need to manually select the image required by the user from the multi-frame images after obtaining the multi-frame images, in addition, the problem that the accuracy of the image screened out by the electronic equipment only according to the definition of the multi-frame images and the facial features of the shot object in the multi-frame images is lower is avoided, and therefore, the accuracy of image screening of the electronic equipment is improved while the user operation is simplified.
Optionally, in this embodiment of the application, after obtaining the fitted curve of the motion trajectory of the photographic object, the electronic device may determine the motion behavior of the photographic object according to the fitted curve and a preset parabola. If the fitted curve does not conform to the preset parabola, the best image can be determined based on the motion attitude score of the second shooting object in each frame of the first image.
In a possible embodiment, the photographic subject includes a first subject and a second subject; after step 202, the image screening method provided in the embodiment of the present application further includes step 301 described below.
Step 301, under the condition that the fitted curve does not conform to the preset parabola, the electronic device determines a third image based on the first motion attitude score of the first object in each frame of the N frames of the first images.
In an embodiment of the present application, the third image is: and the first image with the first attitude score meeting the second condition in the N frames of first images. For example, the first image satisfying the second condition may be: and the first image with the highest first posture score in the N frames of first images corresponds to the first posture score.
In an embodiment of the present application, the first motion gesture score is used to characterize a stretching degree of the first object controlling the motion gesture of the second object.
In this embodiment of the application, after obtaining a first motion attitude score (hereinafter, referred to as N first motion attitude scores) of a first object in each frame of a first image in N frames of the first images, the electronic device may establish a corresponding relationship between N first image indices and N first motion attitude scores, so that the electronic device may determine a maximum first motion attitude score (i.e., a second condition) from the N first motion attitude scores through a maximum value algorithm (i.e., the following formula seven), and further determine a third image according to the first image indices, where the specific formula seven may be:
index_best＝index(max(Score i ) (formula seven)
Wherein, score i For each of the N first motion pose scores, index is a first image index.
In the embodiment of the application, after the electronic device determines the third image, the electronic device adds the third identifier to the third image, and returns the third image to which the third identifier is added to a target application program (for example, an album application program), so that the third image to which the third identifier is added is displayed to a user, and the user can quickly find the third image.
Illustratively, the third identifier may include at least one of: a number mark, a letter mark, a symbol mark and an expression mark.
In the embodiment of the application, the electronic device can determine the image corresponding to the highest attitude score in the first motion attitude scores of each frame of first images in the N frames of first images as the third image, so that the user is prevented from manually selecting the image, and the accuracy of screening the image by the electronic device is improved while the user operation is simplified.
In a possible embodiment, before step 301, the image screening method provided in the embodiment of the present application further includes steps 401 and 402 described below.
Step 401, the electronic device obtains a second motion pose score and a corresponding pose score weight of the first object in each frame of the N frames of the first images.
In an embodiment of the present application, the pose scoring weight of each of the N first images is determined based on a distance between the first object and the second object in the first image.
It should be noted that the above-mentioned pose scoring weight is used to characterize the distance between the first object and the second object in the first image.
In the embodiment of the application, the electronic device may obtain, through a target algorithm, a second motion posture score of the first object in each frame of the first image.
Illustratively, the target algorithm may be any one of: a convolutional neural network, an Artificial Intelligence (AI) scoring algorithm, or a feature weighted scoring algorithm.
In the embodiment of the application, the electronic device may obtain a distance (hereinafter referred to as a target distance) between the first object and the second object through a distance algorithm, and then obtain a posture scoring weight in each frame of the first image in the N frames of the first image through (formula eight) according to the target distance, where the specific formula is as follows:
wherein, d ij The Euclidean distance between a first object and a second object in the first image of the ith frame; w is a ij Scoring weight, p, for the pose of the first image of the ith frame ijx Is the lateral position, h, of the first object in the first image of the ith frame ix Is the lateral position, p, of the second object in the first image of the ith frame ijy Is the longitudinal position, h, of the first object in the first image of the ith frame iy Is the longitudinal position of the second object in the first image of the ith frame.
Step 402, the electronic device calculates a first attitude score of the first object in each frame of the first image according to the second attitude score of the first object in each frame of the first image and the corresponding attitude score weight.
In this embodiment of the application, the electronic device may respectively calculate the second pose score of the first object in each frame of the first image through a scoring algorithm (that is, the following formula nine), where a specific formula nine may be:
Score i ＝w i1 *PScore i1 +w i2 *PScore i1 +…+w iN *PScore iN (formula nine)
Wherein, w i Scoring a weight, PScore, for the pose of the first image of frame i i And scoring the first pose of the first image of the ith frame.
In the embodiment of the application, the electronic device can determine the first posture score of each frame of the first image in the N frames of the first images according to the distance weight and the second posture score between the first object and the second object, and it can be understood that the electronic device can determine the posture of the first object according to the distance weight between the first object and the second object, so that the electronic device can determine the third image according to the posture of the first object, and the problem that the accuracy of the image screened out by the electronic device only according to the definition of the multiple frames of images and the facial features of the shooting objects in the multiple frames of images in the prior art is low is solved, so that the accuracy of the image screened out by the electronic device is improved.
As shown in fig. 2, the technical solution provided by the embodiment of the present application will be exemplarily described below by taking the second object as a basketball (i.e., a scene for shooting the first object a), and the image screening method in the embodiment of the present application exemplarily includes the following steps 10 to 15.
And step 10, clicking a motion snapshot continuous shooting mode in the camera by a user.
In the embodiment of the application, a user clicks a motion snapshot continuous shooting mode in a camera, so that the electronic equipment starts a continuous shooting function in the motion snapshot mode.
And step 11, the user aims the camera at a shooting object to be shot, and long-time pressing of a shutter key obtains 20 frames of motion snapshot continuous shooting images.
In the embodiment of the application, when a user obtains 20 frames of motion snapshot continuous shooting images, the internal algorithm of the camera can automatically obtain the basketball position, the face information and the human body posture information.
And step 12, judging the shooting behavior of the electronic equipment.
In the embodiment of the present application, step 13 is executed when the electronic device determines that the shooting behavior is a shooting behavior, and step 14 is executed otherwise.
The embodiment of the application provides a basketball scene shooting behavior classification method based on an LCSS algorithm, and the specific design flow is as follows:
the electronic equipment integrates and records the movement track of 20 frames of basketball by using the position of the basketball provided by the camera, and fits the movement track of the basketball by using a least square estimation curve fitting method to obtain a fitting curve, wherein the fitting curve is shown in the formula I;
then, a method for measuring the track similarity of the longest common subsequence, namely LCSS is utilized to judge whether the tracks of the fitting curve and the preset parabola are in the same trend, namely whether the fitting curve meets a parabola function y 2 =2px. Wherein, the value of the longest common subsequence method (LCSS) represents the number of points that can be regarded as the same point at most, that is, the logarithm of the point of the two parabolic tracks satisfying the minimum distance threshold limit, and the algorithm based on dynamic programming is as shown in the above formula (two);
therefore, the electronic equipment finally judges whether the basketball motion trail of a group of 20-frame pictures accords with a parabolic function expression or not, if the target number is larger than a preset threshold value, the basketball is judged to be a shooting behavior, and if the target number is smaller than the preset threshold value, the basketball is judged to be a non-shooting behavior.
It should be noted that, since the maximum number of basketball tracks is 20, the preset threshold in the application is 10 by batch verification;
and step 13, under the condition that the shooting object is judged to be a shooting behavior, the electronic equipment obtains the optimal frame image through a reverse dynamic search algorithm.
In the embodiment of the application, when the shooting object is judged to be a shooting behavior, the electronic device obtains the optimal frame index _ best for a shooting behavior scene through an optimal shooting time optimization algorithm for reverse dynamic search.
It can be understood that a conventional parabola is a parabola of forward time, and in the embodiment of the present application, a manner of reversely finding whether there is a departure parabola track in adjacent 4 basketballs is adopted, and an optimal shooting moment optimization algorithm for reverse dynamic finding is designed to obtain an optimal frame index _ best label of a shooting scene, which has the main idea that: since the last continuous frames of the basketball in the shooting behavior are always in a parabolic trend, the first image frame which does not conform to the corresponding of the basketball on the parabolic track is found through a reverse searching mode, namely the previous frame when the basketball leaves the hand of the shooting object, namely the first image frame index _ i deviating from the parabolic track needs to be found through reverse searching, and then the next frame index _ i +1 leaving the hand of the moving subject can be used as the optimal frame index _ best label. The optimal shooting time optimization algorithm mainly comprises the following steps:
the offset between each of the 20 basketballs and the parabola is first calculated by the following (formula ten), which can be specifically:
wherein x is i For the lateral position of the second object in each of the 20 first images, h i For the longitudinal position of the second object in each of the 20 first images, g xh4 And g xh3 Respectively representing an order 4 operator and an order 3 operator for calculating the degree of offset, Δ h, between the second object and a preset parabola i Is the height difference between the actual position of the second object in the first image and the preset parabolic curve per frame.
Then, the offset between the 20 basketballs and the parabola is integrated in a reverse order manner to obtain an offset vector, and the position offset vector can be represented by the following formula eleven:
diff(X,H)＝(diff(x 20 ,h 20 ),diff(x 19 ,h 19 ),...,diff(x 1 ,h 1 ) Equation eleven)
Wherein, diff (x) i ,h i ) For each of the 20 positional offset amounts.
And when the electronic equipment dynamically and reversely finds the image frame which is larger than the maximum deviation degree threshold value for the first time through the position deviation degree vector, directly returning the first image of the last frame of the first image of the frame as the optimal shooting moment optimal frame label index _ best.
And step 14, under the condition that the shooting object is judged to be a non-shooting behavior, the electronic equipment obtains the optimal frame image through a posture extension degree evaluation algorithm.
In the embodiment of the application, when the electronic equipment judges that a shooting object is a non-shooting behavior, namely the shooting object is a dribbling behavior, a passerby behavior and other behaviors, the optimal frame is preferably selected to the non-shooting scene through an optimal frame index _ best which is obtained by integrating attitude extension evaluation algorithms of all shooting objects designed in the embodiment of the application; the specific scheme design flow is as follows:
the electronic equipment scores the relaxation postures of the n shooting objects by using a posture stretching aesthetic scoring algorithm combined with human key points on the image of the ith frame (i =1,2, …) to obtain a first posture score.
Specifically, for a non-shooting scene, in the embodiment of the present application, a comprehensive pose extension evaluation algorithm covering all the shot objects is designed, and first, for an image of an i-th frame (i =1,2, …) and a weighted sum is performed by taking euclidean distances between n shot objects and a basketball as weights according to the following formula twelve, so as to obtain a second pose score of each frame image, where the specific formula (twelve) may be:
wherein d is ij The Euclidean distance between a first object and a second object in the first image of the ith frame; w is a ij Is the ithPose score weight, p, for the first image of the frame ijx Is the lateral position, h, of the first object in the first image of the ith frame ix Is the lateral position, p, of the second object in the first image of the ith frame ijy Is the longitudinal position, h, of the first object in the first image of the ith frame iy Is the longitudinal position of the second object in the first image of the ith frame.
Then, the electronic device may rank the second pose scores of each frame of the first image by using the following (formula thirteen), and use, as an optimal frame, an index _ best corresponding to a frame of picture with a highest second pose score in the second pose scores of each frame of the first image, where the specific formula may be:
Score i ＝w i1 *PScore i1 +w i2 *PScore i1 +…+w iN *PScore iN (formula thirteen)
And step 15, adding a fourth identifier to the optimal frame image by the electronic equipment, and returning the optimal frame image added with the identifier to the target application program.
In the embodiment of the application, the electronic device can return the identifier corresponding to the optimal frame image to the album end in the way of the identifier symbol, and display the picture with the preferred identifier to the user.
Illustratively, the fourth identification may include at least one of: a number mark, a letter mark, a symbol mark and an expression mark.
Therefore, after the user opens the motion snapshot mode, the electronic device firstly obtains 20 frames of images continuously shot by the motion snapshot by long pressing of a shutter key by the user, and meanwhile, the electronic device can automatically detect and obtain basketball position information, human face information and human body posture information. Then, shooting behavior judgment is carried out on the basketball position information by using the basketball scene shooting behavior classification method designed by the embodiment of the application. Aiming at a shooting scene, the optimal frame index _ best is obtained for the shooting behavior scene through an optimal shooting moment optimization algorithm for reverse dynamic search designed in the embodiment of the application. Aiming at non-shooting scenes such as people passing, dribbling and the like, the optimal frame index _ best is obtained for the non-shooting behavior scene through the comprehensive posture extension evaluation algorithm covering all shooting objects. Finally, the best frame label index _ best is returned to the album end in a mark symbol mode, and the picture with the preferred identifier is displayed to the user, so that the best movement highlight time of the basketball scene can be recommended to the user accurately in all directions, the picture is screened in an AI mode instead of the user, the hands of the user are liberated, and a simple and elegant shooting experience of the best movement time of the movement scene is brought to the user.
It should be noted that, in the image screening method provided in the embodiment of the present application, the execution subject may be an image screening apparatus, or an electronic device, or may also be a functional module or an entity in the electronic device. In the embodiment of the present application, an image screening method executed by an image screening apparatus is taken as an example, and the image screening apparatus provided in the embodiment of the present application is described.
Fig. 3 shows a schematic diagram of a possible structure of the image screening apparatus according to the embodiment of the present application. As shown in fig. 3, the image screening apparatus 70 may include: an acquisition module 71 and a determination module 72.
The acquiring module 71 is configured to acquire N frames of first images, where the N frames of first images are images including a photographic subject. A determining module 72, configured to determine a fitted curve corresponding to a motion trajectory of the photographic subject based on the N frames of first images acquired by the acquiring module 71; the fitting curve comprises N characteristic points corresponding to N frames of first images; under the condition that the fitted curve accords with a preset parabolic curve, determining a second image meeting a first condition from the N frames of first images on the basis of the position offset between each feature point of the N feature points and the preset parabolic curve; wherein N is an integer greater than 5.
In a possible implementation manner, the determining module 72 is specifically configured to traverse the N feature points from a first feature point of the N feature points, where the first feature point is a feature point corresponding to a last frame image of the N frames of first images; and in the process of traversing N feature points, executing the following process for each feature point: if the position offset between the currently traversed feature point and the preset parabola is smaller than or equal to the preset offset threshold, continuously traversing the next feature point of the currently traversed feature point; and if the position offset between the currently traversed feature point and the preset parabola is larger than a preset offset threshold, taking the first image corresponding to the last feature point of the currently traversed feature point as a second image.
In a possible implementation manner, the photographic object includes a first object and a second object; the determining module 72 is further configured to determine a third image based on the first motion pose score of the first object in each frame of the N frames of the first images, if the fitted curve does not conform to the preset parabola; wherein the third image is: and the first image with the first attitude score meeting the second condition in the N frames of first images.
In a possible implementation manner, the image screening apparatus provided in the embodiment of the present application further includes: the device comprises an acquisition module and a processing module. And an obtaining module 72, configured to obtain a second motion pose score and a corresponding pose score weight of the first object in each frame of the first images before determining the third image based on the first motion pose score of the first object in each frame of the N frames of the first images by the determining module 72. The processing module is used for respectively calculating the first attitude score of the first object in each frame of first image according to the second attitude score of the first object in each frame of first image and the corresponding attitude score weight; wherein the pose scoring weight corresponding to each frame of the first image is determined based on a distance between the first object and the second object in the first image.
In a possible implementation manner, the determining module 72 is specifically configured to fit the motion trajectory of the photographic subject based on the N frames of the first image by using a least square method, so as to obtain a fit curve corresponding to the motion trajectory of the photographic subject.
The embodiment of the application provides an image screening device, image screening device can be according to the relation between fitting curve and the predetermined parabola, thereby judge the motion behavior that the shooting object corresponds, and then image screening device can be according to the position offset between every characteristic point and the predetermined parabola of shooting object on the fitting curve under this motion behavior, confirm the second image that satisfies first condition in N frame first image, need not image screening device and need not the manual image of selecting oneself demand from this multiframe image of user after obtaining multiframe image, and, avoided image screening device only according to the definition of multiframe image and the lower problem of the accuracy of the image that the facial feature of shooting object in the multiframe image was selected, so, when simplifying user's operation, the accuracy of image screening device screening image has been promoted.
The image screening apparatus in the embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in an electronic device. The device can be mobile electronic equipment or non-mobile electronic equipment. The Mobile electronic Device may be, for example, a Mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic Device, a Mobile Internet Device (MID), an Augmented Reality (AR)/Virtual Reality (VR) Device, a robot, a wearable Device, an ultra-Mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and may also be a server, a Network Attached Storage (Storage), a personal computer (NAS), a Television (TV), a teller machine, a self-service machine, and the like, and the embodiments of the present application are not limited in particular.
The image filtering apparatus in the embodiment of the present application may be an apparatus having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiment of the present application.
The image screening apparatus provided in the embodiment of the present application can implement each process implemented in the embodiment of the method in fig. 1, and is not described here again to avoid repetition.
Optionally, as shown in fig. 4, an electronic device 90 provided in an embodiment of the present application further includes a processor 91 and a memory 92, where the memory 92 stores a program or an instruction that can be executed on the processor 91, and when the program or the instruction is executed by the processor 91, the steps of the embodiment of the image screening method are implemented, and the same technical effect can be achieved, and are not described again here to avoid repetition.
It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.
Fig. 5 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 100 includes, but is not limited to: a radio frequency unit 101, a network module 102, an audio output unit 103, an input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, and a processor 110.
Those skilled in the art will appreciate that the electronic device 100 may further comprise a power supply (e.g., a battery) for supplying power to various components, and the power supply may be logically connected to the processor 110 via a power management system, so as to implement functions of managing charging, discharging, and power consumption via the power management system. The electronic device structure shown in fig. 5 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than those shown, or combine some components, or arrange different components, and thus, the description is omitted here.
The processor 110 is configured to acquire N consecutive frames of first images, where the N frames of first images are images including a photographic subject; determining a fitting curve corresponding to the motion trail of the shooting object based on the N frames of first images; the fitting curve comprises N characteristic points corresponding to N frames of first images; under the condition that the fitting curve accords with a preset parabola, determining a second image meeting a first condition from the N frames of first images on the basis of the position offset between each feature point of the N feature points and the preset parabola; wherein N is an integer greater than 5.
The embodiment of the application provides electronic equipment, electronic equipment can be according to the relation between fitting curve and the preset parabola, thereby judge the motion behavior that the shooting object corresponds, and then electronic equipment can be according to the position offset between every characteristic point on the fitting curve of shooting object under this motion behavior and the preset parabola, confirm the second image that satisfies first condition from N frame first image, need not electronic equipment and need not the user to select the image of self demand from this multiframe image after obtaining multiframe image, and, avoided electronic equipment only according to the definition of multiframe image and the lower problem of the accuracy of the image of screening that the facial feature of shooting object in the multiframe image was only, so, when simplifying user operation, electronic equipment screening image's accuracy has been promoted.
Optionally, in this embodiment of the application, the processor 110 is specifically configured to traverse the N feature points from a first feature point in the N feature points, where the first feature point is a feature point corresponding to a last frame image in the N frames of first images; and in the process of traversing the N characteristic points, executing the following process for each characteristic point: if the position offset between the currently traversed feature point and the preset parabola is smaller than or equal to the preset offset threshold, continuously traversing the next feature point of the currently traversed feature point; and if the position offset between the currently traversed feature point and the preset parabola is larger than a preset offset threshold, taking the first image corresponding to the last feature point of the currently traversed feature point as a second image.
Optionally, in this embodiment of the present application, the shooting object includes a first object and a second object; the processor 110 is further configured to determine, based on the N frames of first images, a fitting curve corresponding to a motion trajectory of the photographic object, and determine, when the fitting curve does not conform to a preset parabola, a third image based on the first motion attitude score of the first object in each frame of the N frames of first images; wherein the third image is: and the first image with the first attitude score meeting the second condition in the N frames of first images.
Optionally, in this embodiment of the application, the processor 110 is further configured to, before determining the third image based on the first motion pose score of the first object in each of the N frames of the first images, obtain a second motion pose score and a corresponding pose score weight of the first object in each of the N frames of the first images; respectively calculating a first attitude score of the first object in each frame of the first image according to the second attitude score of the first object in each frame of the first image and the corresponding attitude score weight; wherein the pose scoring weight corresponding to each frame of the first image is determined based on a distance between the first object and the second object in the first image.
Optionally, in this embodiment of the application, the processor 110 is specifically configured to fit the motion trajectory of the target photographic object based on the N frames of the first image by using a least square method, so as to obtain a fit curve corresponding to the motion trajectory of the target photographic object.
The electronic device provided by the embodiment of the application can realize each process realized by the method embodiment, and can achieve the same technical effect, and for avoiding repetition, the details are not repeated here.
The beneficial effects of the various implementation manners in this embodiment may specifically refer to the beneficial effects of the corresponding implementation manners in the above method embodiments, and are not described herein again to avoid repetition.
It should be understood that, in the embodiment of the present application, the input Unit 104 may include a Graphics Processing Unit (GPU) 1041 and a microphone 1042, and the Graphics Processing Unit 1041 processes image data of a still picture or a video obtained by an image capturing device (such as a camera) in a video capturing mode or an image capturing mode. The display unit 106 may include a display panel 1061, and the display panel 1061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 107 includes at least one of a touch panel 1071 and other input devices 1072. The touch panel 1071 is also referred to as a touch screen. The touch panel 1071 may include two parts of a touch detection device and a touch controller. Other input devices 1072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein.
The memory 109 may be used to store software programs as well as various data. The memory 109 may mainly include a first storage area storing a program or an instruction and a second storage area storing data, wherein the first storage area may store an operating system, an application program or an instruction (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, memory 109 may include volatile memory or non-volatile memory, or memory 109 may include both volatile and non-volatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. The volatile Memory may be a Random Access Memory (RAM), a Static Random Access Memory (Static RAM, SRAM), a Dynamic Random Access Memory (Dynamic RAM, DRAM), a Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), a Double Data Rate Synchronous Dynamic Random Access Memory (Double Data Rate SDRAM, ddr SDRAM), an Enhanced Synchronous SDRAM (ESDRAM), a Synchronous Link DRAM (SLDRAM), and a Direct Memory bus RAM (DRRAM). The memory 109 in the embodiments of the subject application includes, but is not limited to, these and any other suitable types of memory.
Processor 110 may include one or more processing units; optionally, the processor 110 integrates an application processor, which mainly handles operations related to the operating system, user interface, application programs, etc., and a modem processor, which mainly handles wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 110.
The embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored, and when the program or the instruction is executed by a processor, the program or the instruction implements the processes of the foregoing method embodiments, and can achieve the same technical effects, and in order to avoid repetition, details are not repeated here.
The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read only memory ROM, a random access memory RAM, a magnetic or optical disk, and the like.
The embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to execute a program or an instruction to implement each process of the foregoing method embodiment, and the same technical effect can be achieved.
It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as system-on-chip, system-on-chip or system-on-chip, etc.
Embodiments of the present application provide a computer program product, where the program product is stored in a storage medium, and the program product is executed by at least one processor to implement the processes of the foregoing image screening method embodiments, and achieve the same technical effects, and in order to avoid repetition, details are not repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present application may be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. An image screening method, comprising:
acquiring N frames of first images, wherein the N frames of first images comprise images of shot objects;
determining a fitting curve corresponding to the motion trail of the shooting object based on the N frames of first images; the fitting curve comprises N characteristic points corresponding to the N frames of first images;
determining a second image satisfying a first condition from the N frames of first images based on a position offset between each of the N feature points and a preset parabola under the condition that the fitted curve conforms to the preset parabola;
wherein the position offset is: a distance between each feature point and a second feature point on the preset parabola, wherein the second feature point is a feature point on the preset parabola closest to any feature point in each feature point; n is an integer greater than 5.
2. The method according to claim 1, wherein the determining a second image satisfying a first condition from the N-frame first images based on a position offset between each of the N feature points and the preset parabola comprises:
traversing the N characteristic points from a first characteristic point in the N characteristic points, wherein the first characteristic point is a characteristic point corresponding to the last frame of image in the N frames of first images;
in the process of traversing the N feature points, the following process is executed for each feature point:
if the position offset between the currently traversed feature point and the preset parabola is less than or equal to a preset offset threshold, continuously traversing the next feature point of the currently traversed feature point;
and if the position offset between the currently traversed feature point and the preset parabola is larger than the preset offset threshold, taking the first image corresponding to the last feature point of the currently traversed feature point as a second image.
3. The method according to claim 1, wherein the photographic object includes a first object and a second object; after determining a fitted curve corresponding to the motion trail of the photographic object based on the N frames of first images, the method further includes:
determining a third image based on a first motion pose score of the first object in each of the N first images if the fitted curve does not conform to the preset parabola;
wherein the third image is: and the first image with the first attitude score meeting a second condition in the N frames of first images.
4. The method of claim 3, wherein prior to determining a third image based on the first motion pose score of the first object in the first image for each of the N frames of first images, the method further comprises:
acquiring a second motion attitude score and a corresponding attitude score weight of the first object in each frame of the N frames of first images;
respectively calculating a first posture score of the first object in each frame of the first image according to a second posture score of the first object in each frame of the first image and a corresponding posture score weight;
wherein the pose scoring weight for each frame of the first image is determined based on a distance between the first object and the second object in the first image.
5. The method according to any one of claims 1 to 4, wherein the determining a fitted curve corresponding to the motion trajectory of the photographic object based on the N first images comprises:
and fitting the motion track of the shot object by using a least square method based on the N frames of first images to obtain a fitting curve corresponding to the motion track of the shot object.
6. An image screening apparatus, characterized by comprising: the device comprises an acquisition module and a determination module;
the acquisition module is used for acquiring N frames of first images, wherein the N frames of first images comprise images of shot objects;
the determining module is used for determining a fitting curve corresponding to the motion trail of the shooting object based on the N frames of first images acquired by the acquiring module; the fitting curve comprises N characteristic points corresponding to the N frames of first images; under the condition that the fitting curve accords with a preset parabola, determining a second image meeting a first condition from the N frames of first images on the basis of the position offset between each feature point in the N feature points and the preset parabola; wherein the position offset is: the distance between each feature point and a second feature point on the preset parabola is the feature point on the preset parabola, which is closest to any feature point in each feature point; n is an integer greater than 5.
7. The apparatus according to claim 6, wherein the determining module is specifically configured to traverse the N feature points starting from a first feature point in the N feature points, where the first feature point is a feature point corresponding to a last image in the N first images; and in the process of traversing the N characteristic points, executing the following process for each characteristic point: if the position offset between the currently traversed feature point and the preset parabola is less than or equal to a preset offset threshold, continuously traversing the next feature point of the currently traversed feature point; and if the position offset between the currently traversed feature point and the preset parabola is larger than the preset offset threshold, taking the first image corresponding to the last feature point of the currently traversed feature point as a second image.
8. The apparatus according to claim 6, wherein the photographic subject includes a first subject and a second subject; the determining module is further configured to determine a third image based on the first motion pose score of the first object in each of the N first images if the fitted curve does not conform to the preset parabola; wherein the third image is: and the first image with the first attitude score meeting a second condition in the N frames of first images.
9. The apparatus of claim 8, wherein the image filtering apparatus further comprises: the device comprises an acquisition module and a processing module;
the obtaining module is configured to obtain a second motion pose score and a corresponding pose score weight of the first object in each of the N first images before the determining module determines the third image based on the first motion pose score of the first object in each of the N first images;
the processing module is used for respectively calculating a first posture score of the first object in each frame of the first image according to a second posture score of the first object in each frame of the first image and a corresponding posture score weight; wherein the pose scoring weight for each frame of the first image is determined based on a distance between the first object and the second object in the first image.
10. The apparatus according to any one of claims 6 to 9, wherein the determining module is specifically configured to fit the motion trajectory of the photographic object based on the N frames of the first image by using a least square method, so as to obtain a fit curve corresponding to the motion trajectory of the photographic object.
11. An electronic device comprising a processor, a memory and a program or instructions stored on the memory and executable on the processor, which program or instructions, when executed by the processor, carry out the steps of the image screening method according to any one of claims 1 to 5.
12. A readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the image screening method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210806681.5A CN115209052B (en) | 2022-07-08 | 2022-07-08 | Image screening method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210806681.5A CN115209052B (en) | 2022-07-08 | 2022-07-08 | Image screening method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115209052A CN115209052A (en) | 2022-10-18 |
| CN115209052B true CN115209052B (en) | 2023-04-18 |
Family
ID=83579586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210806681.5A Active CN115209052B (en) | 2022-07-08 | 2022-07-08 | Image screening method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115209052B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102263896A (en) * | 2010-05-31 | 2011-11-30 | 索尼公司 | image processing unit, image processing method and program |
| CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
| CN106056138A (en) * | 2016-05-25 | 2016-10-26 | 努比亚技术有限公司 | Picture processing device and method |
| CN108447109A (en) * | 2018-05-16 | 2018-08-24 | 电子科技大学中山学院 | Device for making stop-motion animation |
| CN110175579A (en) * | 2019-05-29 | 2019-08-27 | 北京百度网讯科技有限公司 | Attitude determination method, the methods of exhibiting of scene image, device, equipment and medium |
| CN110825897A (en) * | 2019-10-29 | 2020-02-21 | 维沃移动通信有限公司 | Image screening method and device and mobile terminal |
| JP2020102787A (en) * | 2018-12-25 | 2020-07-02 | キヤノン株式会社 | Image processing device |
| CN113313009A (en) * | 2021-05-26 | 2021-08-27 | Oppo广东移动通信有限公司 | Method, device and terminal for continuously shooting output image and readable storage medium |
-
2022
- 2022-07-08 CN CN202210806681.5A patent/CN115209052B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102263896A (en) * | 2010-05-31 | 2011-11-30 | 索尼公司 | image processing unit, image processing method and program |
| CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
| CN106056138A (en) * | 2016-05-25 | 2016-10-26 | 努比亚技术有限公司 | Picture processing device and method |
| CN108447109A (en) * | 2018-05-16 | 2018-08-24 | 电子科技大学中山学院 | Device for making stop-motion animation |
| JP2020102787A (en) * | 2018-12-25 | 2020-07-02 | キヤノン株式会社 | Image processing device |
| CN110175579A (en) * | 2019-05-29 | 2019-08-27 | 北京百度网讯科技有限公司 | Attitude determination method, the methods of exhibiting of scene image, device, equipment and medium |
| CN110825897A (en) * | 2019-10-29 | 2020-02-21 | 维沃移动通信有限公司 | Image screening method and device and mobile terminal |
| CN113313009A (en) * | 2021-05-26 | 2021-08-27 | Oppo广东移动通信有限公司 | Method, device and terminal for continuously shooting output image and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115209052A (en) | 2022-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654512B (en) | A kind of method for tracking target and device | |
| US8379931B2 (en) | Image processing apparatus for retrieving object from moving image and method thereof | |
| CN109343700B (en) | Eye movement control calibration data acquisition method and device | |
| CN112351185A (en) | Photographing method and mobile terminal | |
| CN109297489B (en) | Indoor navigation method based on user characteristics, electronic equipment and storage medium | |
| CN110598559B (en) | Method and device for detecting motion direction, computer equipment and storage medium | |
| CN109254662A (en) | Mobile device operation method, apparatus, computer equipment and storage medium | |
| CN110633004A (en) | Interaction method, device and system based on human body posture estimation | |
| CN113873166A (en) | Video shooting method and device, electronic equipment and readable storage medium | |
| EP3945463A1 (en) | A computing system and a computer-implemented method for sensing gameplay events and augmentation of video feed with overlay | |
| CN114140721A (en) | Archery posture evaluation method and device, edge calculation server and storage medium | |
| CN112511743B (en) | Video shooting method and device | |
| CN114037923A (en) | Target activity hotspot graph drawing method, system, equipment and storage medium | |
| CN115209052B (en) | Image screening method and device, electronic equipment and storage medium | |
| CN117152660A (en) | Image display method and device | |
| CN111258413A (en) | Control method and device of virtual object | |
| US11640713B2 (en) | Computing system and a computer-implemented method for sensing gameplay events and augmentation of video feed with overlay | |
| CN111953907B (en) | Composition method and device | |
| CN112256976B (en) | Matching method and related device | |
| CN114565777A (en) | Data processing method and device | |
| CN114466140A (en) | Image shooting method and device | |
| Liwei | Research on classification and recognition of badminton batting action based on machine learning | |
| CN111611941A (en) | Special effect processing method and related equipment | |
| CN112017179B (en) | Method, system, electronic device and storage medium for evaluating visual effect grade of picture | |
| CN117097982B (en) | Target detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |