CN113177917B

CN113177917B - Method, system, equipment and medium for optimizing snap shot image

Info

Publication number: CN113177917B
Application number: CN202110450382.8A
Authority: CN
Inventors: 黄超; 陈婉婉; 夏伟; 董康; 周国亚
Original assignee: Chongqing Unisinsight Technology Co Ltd
Current assignee: Chongqing Unisinsight Technology Co Ltd
Priority date: 2021-04-25
Filing date: 2021-04-25
Publication date: 2023-10-13
Anticipated expiration: 2041-04-25
Also published as: CN113177917A

Abstract

The invention provides a snapshot image optimizing method, a system, equipment and a medium, wherein the method is characterized in that a plurality of images to be selected, which are shot in a preset shooting area, are acquired, target objects in the images to be selected and identification key points of the target objects are identified, quality scoring parameters are determined, quality scores of the images to be selected are determined according to the quality scoring parameters, and optimal snapshot images are determined from the images to be selected, so that one or more optimal snapshot images can be determined in a plurality of images to be selected, the image quality of the snapshot images is improved, the problem that an intelligent algorithm cannot generate an ideal output effect due to poor quality of the snapshot images is solved, the credibility of the snapshot images is improved, good paving is made for generating the ideal effect by using the snapshot images by a follow-up intelligent algorithm, and the output result of the follow-up intelligent algorithm depending on the snapshot images is effectively improved.

Description

Method, system, equipment and medium for optimizing snap shot image

Technical Field

The present invention relates to the field of image processing, and in particular, to a method, system, device, and medium for capturing an image.

Background

With the advanced development of smart cities, more intelligent algorithms are popularized, promoted and expanded, wherein typical algorithm application examples include control alarm distribution, vehicle searching by drawing and the like. The intelligent algorithm is based on data as if the fish were in water.

Based on different algorithms, the required data types are often different, such as the police is required to take a picture by grabbing a human face, and the vehicle is required to take a picture when searching for a vehicle, so that for various algorithms, the snap shot image is often critical in determining the accuracy of the algorithm. However, in the related art, the snapshot is often photographed and selected based on a random snapshot mode, and there may be a poor output effect and an unsatisfactory output result of a subsequent intelligent algorithm due to low quality of the snapshot image.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, system, device and medium for capturing images to solve the above-mentioned technical problems.

The invention provides a snapshot image optimization method, which comprises the following steps:

acquiring a plurality of images to be selected shot in a preset shooting area;

identifying a target object in the image to be selected and identifying key points of the target object;

Determining a quality scoring parameter, wherein the quality scoring parameter comprises at least one of a correction characteristic parameter and a profile parameter, the correction characteristic parameter is determined according to the identification key point position information of the identification key point and/or the identification key point number of the identification key point, and the profile parameter is determined according to the identification key point position information of the identification key point and the identification key point influence factor of the identification key point;

and determining the quality score of the images to be selected according to the quality score parameters, and determining a preferred snap image from the images to be selected.

Optionally, the identifying key point includes a correction feature point of the target object, the identifying key point number includes a correction feature point number of the correction feature point, and the determining manner of the correction feature parameter includes:

acquiring a preset correction feature point threshold value and the number of correction feature points of the correction feature points in the image to be selected;

and determining the correction characteristic parameters according to the preset correction characteristic point threshold value and the correction characteristic point quantity.

Optionally, the identifying key point includes a correction feature point and a contour point of the target object, the correction feature point is located inside a contour formed by the contour point, the identifying key point position information includes correction feature point position information of the correction feature point and contour position information of the contour point, and the determining manner of the correction feature parameter includes:

And determining the correction characteristic parameters according to the correction characteristic point position information and the contour position information.

Optionally, the determining the correction feature parameter according to the correction feature point position information of the correction feature point and the contour position information of the contour point includes:

dividing the contour into a first region and a second region through the correction feature point;

forming a contour according to the contour position information, and determining the contour area of the contour according to the contour position information;

determining a first area of a first region and a second area of the second region according to the correction feature point position information and the contour position information;

and determining the correction characteristic parameters according to the first area, the second area and the contour area.

Optionally, the identification key point includes at least two types of correction feature points of the target object, a correction feature sub-parameter is determined according to each type of correction feature point, and the correction feature parameter is determined according to each correction feature sub-parameter.

Optionally, the identifying key point includes a contour point of the target object, the identifying key point position information includes contour point position information of the contour point, the identifying key point influence factor includes a contour point influence factor of the contour point, and the determining manner of the contour parameter includes:

Dividing the preset shooting area into at least two sub shooting areas, and determining sub shooting area influence factors of the sub shooting areas;

determining distribution information of the contour points in the sub shooting areas according to the position information of the contour points;

acquiring a preset contour point threshold value of the target object;

and determining the profile parameters according to the distribution information, the sub shooting area influence factors, the profile point influence factors and the preset profile point threshold value.

Optionally, if the quality score parameter includes the correction feature parameter and the profile parameter, the determining the quality score of the image to be selected according to the quality score parameter includes:

wherein P is a quality score, A is a contour parameter, B is a correction characteristic parameter, E is a preset correction constant, and N is a preset contour point threshold.

Optionally, the target object includes a face, the recognition key points include face contour points and at least two facial feature points, and the determining manner of the quality score includes:

dividing a face outline formed by the face outline points into a first face area and a second face area through the face feature points;

respectively determining a first face area of the first face area, a second face area of the second face area and a face contour area of the face contour;

determining distribution information of the face contour points in the sub shooting area according to the face contour point position information of the face contour points;

acquiring a preset correction constant, a preset face contour point threshold value and a face contour point influence factor of the face contour point;

wherein P is the quality score, W _Di For the i-th sub-photographing region influence factor, W _sj For the face contour point influence factor of the jth face contour point located in the ith sub-photographing region, E is a preset correction constant, sum (D _j ) For the preset face contour point threshold value, S1l is the area of the first face region, S _1r Is the area of the second face area S ₁ Is the outline area of the human face.

Optionally, the target object includes a vehicle, the identification key points include vehicle contour points and license plate identification information, and the determining manner of the quality score includes:

determining distribution information of the vehicle contour points in the sub-shooting areas according to the vehicle contour point position information of the vehicle contour points;

Acquiring the number of the identification information in the image to be selected;

acquiring a preset correction constant, a preset vehicle contour point threshold value and a vehicle contour point influence factor of the vehicle contour point;

wherein P is the quality score, W _Di For the i-th sub-photographing region influence factor, W _sj For a vehicle contour point influence factor of a jth vehicle contour point located in an ith sub-photographing region, E is a preset correction constant, sum (D _j ) For presetting a vehicle contour point threshold value, N is a preset identification information threshold value, and X is the identification information quantity.

The invention also provides a snapshot image optimization system, which comprises:

the acquisition module is used for acquiring a plurality of images to be selected, which are shot in a preset shooting area;

the identification module is used for identifying the target object in the image to be selected and identifying key points of the target object;

the quality score parameter determining module is used for determining quality score parameters, wherein the quality score parameters comprise at least one of correction characteristic parameters and profile parameters, the correction characteristic parameters are determined according to the identification key point position information of the identification key points and/or the identification key point number of the identification key points, and the profile parameters are determined according to the identification key point position information of the identification key points and identification key point influence factors of the identification key points;

And the preferred snap image determining module is used for determining the quality score of the images to be selected according to the quality score parameters and determining the preferred snap image from the images to be selected.

Optionally, the quality score parameter determining module comprises at least one of a correction feature parameter determining module and a profile parameter determining module, and the correction feature parameter determining module comprises a first correction feature parameter determining sub-module and/or a second correction feature parameter determining sub-module;

if the identification key points comprise contour points of the target object, the identification key point position information comprises contour point position information of the contour points, the identification key point influence factors comprise contour point influence factors of the contour points, the contour parameter determining module is used for dividing the preset shooting area into at least two sub shooting areas and determining sub shooting area influence factors of the sub shooting areas, determining distribution information of the contour points in the sub shooting areas according to the contour point position information, acquiring preset contour point threshold values of the target object, and determining the contour parameters according to the distribution information, the sub shooting area influence factors and the contour point influence factors;

If the identification key points comprise correction feature points of the target object, the identification key point number comprises correction feature point number of the correction feature points, the first correction feature parameter determination submodule is used for obtaining a preset correction feature point threshold value and the correction feature point number of the correction feature points in the image to be selected, and the correction feature parameters are determined according to the preset correction feature point threshold value and the correction feature point number;

if the identification key points comprise correction feature points and contour points of the target object, the correction feature points are located in the contour formed by the contour points, the identification key point position information comprises correction feature point position information of the correction feature points and contour position information of the contour points, and the second correction feature parameter determination submodule is used for determining the correction feature parameters according to the correction feature point position information and the contour position information.

The invention also provides an electronic device, which comprises a processor, a memory and a communication bus;

the communication bus is used for connecting the processor and the memory;

the processor is configured to execute a computer program stored in the memory to implement a method as in any of the embodiments described above.

The invention also provides a computer readable storage medium having stored thereon a computer program for causing the computer to perform the method according to any of the embodiments described above.

The invention has the beneficial effects that:

Drawings

Fig. 1 is a schematic flow chart of a preferred method for capturing images according to the first embodiment.

Fig. 2 is a schematic diagram of a selected preset photographing region.

Fig. 3 is a schematic diagram illustrating the division of the preset photographing region in fig. 2 into a plurality of sub-photographing regions.

Fig. 4 is a schematic diagram of a target object.

Fig. 5 is a schematic diagram of a snap shot scene.

Fig. 6 is a schematic diagram of dividing the snapshot scene in fig. 5 into a plurality of sub-shooting areas.

Fig. 7 is a schematic diagram of a face contour point.

Fig. 8 is another schematic view of a face contour point.

Fig. 9 is another schematic diagram of a snap shot scene.

Fig. 10 is a schematic diagram of dividing the snap shot scene in fig. 9 into a plurality of sub-shot areas.

Fig. 11 is a schematic view of a vehicle contour point.

Fig. 12 is another schematic view of a vehicle contour point.

Fig. 13 is a schematic flow chart of a preferred method for capturing images according to the first embodiment.

Fig. 14 is a flow chart of a method for determining a quality score according to the first embodiment.

Fig. 15 is a schematic structural diagram of a preferred system for capturing images according to the second embodiment.

Fig. 16 is a schematic hardware structure of an apparatus according to an embodiment.

Detailed Description

Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.

It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present invention, it will be apparent, however, to one skilled in the art that embodiments of the present invention may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present invention.

Example 1

As shown in fig. 1, the snapshot image prioritization method in the present embodiment includes:

s101: and acquiring a plurality of images to be selected, which are shot in a preset shooting area.

Alternatively, the preset photographing region may be any region set in advance, and the image to be selected may be an image photographed by the same photographing apparatus or may be an image photographed by a plurality of photographing apparatuses based on similar viewing angles.

Optionally, the plurality of images to be selected may be a plurality of images captured by a certain capturing machine, and since the capturing machine captures the images according to a preset instruction or randomly during capturing, the quality of the obtained images is uneven, and the images to be selected are used as the images to be selected, so that one or more images with preferable image quality can be selected from the images to be used for subsequent analysis.

Alternatively, the several images to be selected may be several video frames obtained from one video.

In some embodiments, before the image to be selected is acquired from the original image set, the original image set may be further screened, and the image with the resolution lower than the preset resolution threshold may be screened out.

S102: and identifying the target object in the image to be selected and identifying key points of the target object.

Alternatively, the identification of the target object may be implemented by related technical means in the art, which is not limited herein.

Alternatively, the identified keypoints of the target object may be a preset series of keypoints for the target object, and different target objects of different categories may have different keypoints. The target objects of the same class use the same distribution logic's key point series as the identification key point. When the categories belong to faces, taking the case that the target object comprises a face as an example, the identification key points can be a plurality of face contour points of a face image, and no matter how many faces of people are included in a plurality of images to be selected, the identification key points are a plurality of face contour points of the people, and are irrelevant to the face types such as the face, the round face, the melon seed face and the like of the person. Of course, the above description uses a face as an exemplary key point for identifying, and the classification manner of the category may also be other manners required by those skilled in the art, for example, classifying the category in a square face, a circular face, etc.

Alternatively, the recognition key point may be other correction feature points of the target object, which may be determined based on the contour of the target object, for example, when the target object is a human face, the correction feature points may be facial feature points, such as a feature point on the nose, a feature point in the middle of the lips, a feature point in the middle between two eyebrows, and the like. The correction feature points may also be determined based on a pattern within the outline of the target object, e.g., the target object is a basketball, the correction feature points are a trademark pattern on the basketball, inflation holes, etc. The correction feature point can also be identified according to an image in the outline of the target object, for example, the target object is a vehicle, the correction feature point is license plate identification information, namely a license plate number, and the license plate number comprises at least one of characters, letters and numbers, and at this time, each license plate number forms a correction feature point. The correction feature points may also be other feature points that can characterize the effect of the image to be selected on the subsequent processing, and are not limited herein.

Optionally, in this embodiment, the target objects in the images to be selected are identified as being identified as the same class of target objects, that is, the key identification points of different images to be selected or each target object in the same image to be selected are all determined based on the same dimension.

S103: a quality scoring parameter is determined.

Optionally, the quality scoring parameter includes at least one of a correction feature parameter and a profile parameter.

The correction feature parameters are determined according to the identification key point position information of the identification key points and/or the identification key point number of the identification key points. The contour parameters are determined according to the identification key point position information of the identification key point and the identification key point influence factor of the identification key point.

In some embodiments, identifying the key points includes correcting feature points of the target object, identifying the number of key points includes correcting feature points of the correcting feature points, and determining the correcting feature parameters includes:

acquiring a preset correction feature point threshold value and the number of correction feature points in an image to be selected;

and determining correction characteristic parameters according to the preset correction characteristic point threshold value and the correction characteristic point quantity.

Alternatively, the preset correction feature point threshold may be preset by those skilled in the art as needed.

Alternatively, different types of target objects may have different correction feature point thresholds, for example, when the correction feature point is a license plate number, the preset correction feature point threshold may be 7. Typically, the preset correction feature point threshold is greater than or equal to the maximum number of correction feature points that can be determined from the image to be selected.

Alternatively, the license plate number recognition may be implemented by performing semantic recognition on the image of the target object, which is not limited herein.

Alternatively, one way of determining the correction feature parameter may be:

correction feature parameter = correction feature point number/preset correction feature point threshold.

In some embodiments, the identifying key points includes correction feature points and contour points of the target object, the correction feature points are located inside a contour formed by the contour points, the identifying key point position information includes correction feature point position information of the correction feature points and contour position information of the contour points, and the determining method of the correction feature parameters includes:

and determining correction characteristic parameters according to the correction characteristic point position information and the contour position information.

Optionally, there is sometimes a certain requirement on the angle of the target object in the image to be selected, and at this time, the deflection condition of the target object can be determined as a correction characteristic parameter by collecting one or more correction characteristic point position information located inside the contour, so that the image to be selected, in which the target object with the required deflection angle is located, is selected as the preferred snap image. Alternatively, the specific manner of determining the deflection condition according to the correction feature point position information and the contour position information may be implemented in a related technical manner in the field.

In some embodiments, determining the correction feature parameter from the correction feature point location information of the correction feature point and the contour location information of the contour point includes:

dividing the contour into a first region and a second region by correcting the feature points;

respectively determining a first area of the first region and a second area of the second region according to the correction feature point position information and the contour position information;

and determining correction characteristic parameters according to the first area, the second area and the contour area.

Alternatively, the deflection condition of the current target object can be determined according to the condition that the first area and the second area respectively occupy the outline area. For example, if the correction feature point is a nose feature point, in a normal case, the nose is located at a center line position of the face (no consideration is given to the fact that there is a certain asymmetric error in the face), the face contour is divided into the first region and the second region by the nose feature point, if the face is not deflected, the ratio of the first area to the second area to the contour area should be the same, and if the face is deflected by a certain angle, the ratio of the corresponding first area to the corresponding second area to the contour area is different, based on which the correction feature parameter can be determined. And the current deflection condition of the target object can be further obtained through analysis, and a person skilled in the art can further determine a preferred snapshot image according to actual needs.

In some embodiments, the identified keypoints comprise at least two types of correction feature points of the target object, one correction feature sub-parameter is determined according to each type of correction feature point, and the correction feature parameters are determined according to each correction feature sub-parameter.

Optionally, for a certain target object, there may be multiple dimensions to determine the correction feature point, where a corresponding correction feature sub-parameter may be determined for each type of correction feature point, and then the correction feature parameter may be determined according to each correction feature sub-parameter. For example, if the target object is a vehicle, two dimensions of a license plate number and a logo of the vehicle can be extracted as correction feature points, and if the vehicle in a certain image to be selected includes both the license plate and the logo, correction feature sub-parameters are obtained for the license plate and the logo respectively, and then the average number of the correction feature sub-parameters or the weighted average determined according to the influence factors of the correction feature sub-parameters and the sum equivalent of the correction feature sub-parameters are used as correction feature parameters.

Alternatively, the correction characteristic sub-parameter is noted as C _i N correction feature sub-parameters are all used, and one determination method of the correction feature parameter B is as follows:

alternatively, the correction characteristic sub-parameter is noted as C _i N correction feature sub-parameters are added, and as the importance degree of correction feature points of different types may have differences, a correction feature influence factor M can be correspondingly set for each type of correction feature point _i The correction parameters are adjusted, that is, the correction characteristic parameters can be determined according to each correction characteristic sub-parameter and the correction characteristic influence factor corresponding to the correction characteristic sub-parameter, and the other determination mode of the correction characteristic parameters B is as follows:

alternatively, the correction feature parameter may not be divided by the correction feature point, i.e

Optionally, preset correction constants may be preset corresponding to the correction feature sub-parameters, and the preset correction constants may be the same or different, which is not limited herein, and at this time, the correction feature parameters may be determined according to the correction feature sub-parameters, the correction feature influence factors corresponding to the correction feature sub-parameters, and the preset correction constants, which may refer to the determination process about the correction feature parameters in fig. 14.

In some embodiments, the identifying key points includes contour points of the target object, the identifying key point location information includes contour point location information of the contour points, the identifying key point impact factors include contour point impact factors of the contour points, and the determining of the contour parameters includes:

Dividing a preset shooting area into at least two sub shooting areas, and determining sub shooting area influence factors of the sub shooting areas;

determining distribution information of contour points in the sub-shooting area according to the position information of the contour points;

acquiring a preset contour point threshold value of a target object;

and determining contour parameters according to the distribution information, the sub-shooting area influence factors, the contour point influence factors and the preset contour point threshold value.

Alternatively, the contour point influence factor may be preset by a person skilled in the art, for example, it is expected that the contour point influence factor corresponding to the contour point at a certain position of a target object of a certain category is set to be M, and then the contour point influence factor of the contour point at the position of each target object belonging to the category is M. Each contour point influence factor may be the same or different, and a suitable contour point influence factor is determined according to the importance of the influence of the contour point influence factor on subsequent analysis.

Similarly, the determination manner of the sub-photographing region influence factors is similar to that of the contour point influence factors, and details thereof are omitted herein.

Optionally, the contour point influence factor includes a contour point weight, and the sub-photographing region influence factor includes a sub-photographing region weight.

Alternatively, the sub-photographing region influence factor may be determined according to at least one of a moving direction of the target object, a distance between the sub-photographing region and the photographing apparatus, brightness of the sub-photographing region, the number of non-target objects of the sub-photographing region, and the like.

Alternatively, the division manner of the sub-photographing region may be set by a person skilled in the art according to need, or may be implemented in a related art manner in the art, which is not limited herein.

Alternatively, the distribution information may be determined according to the contour point position information and the sub-photographing region position information, and determining which sub-photographing region a certain contour point is located may be implemented.

Alternatively, the preset contour point threshold may be set by one skilled in the art as desired.

Optionally, the preset contour point threshold is not smaller than the maximum number of contour points that can be identified by the target object in any image to be selected.

Optionally, the contour parameters are determined by the sum of the products of the contour point influence factors and the corresponding sub-shooting area influence factors and the quotient of the preset contour point threshold value. In this way, the profile parameters can characterize the extent to which the profile points of the target object are distributed in the "key" sub-photographing region, and in general, the more profile points are distributed in the "key" sub-photographing region, the more likely the image to be selected is the preferred snap-shot image.

Optionally, a profile parameter is determined as follows:

wherein A is a profile parameter, W _Fi For the i-th sub-photographing region influence factor, W _Gj For the face contour point influence factor of the jth contour point located in the ith sub-photographing region, sum (F _j ) And presetting a contour point threshold value.

In some embodiments, after the correction feature parameters are determined, the correction feature parameters may be adjusted by a preset correction constant, and the original correction feature parameters are updated by the adjusted correction feature parameters, so as to determine quality score parameters.

Assuming that the adjusted correction characteristic parameter is marked as C, the original correction characteristic parameter is marked as B, and the preset correction constant is marked as E, wherein E is generally between 0 and 1, and according to the influence factors of the correction characteristic points, the larger the influence of the influence factors of the correction characteristic points on snapshot analysis is, the larger the E is, and the following steps are: c=b×e.

In some embodiments, if the quality score parameters include correction feature parameters and profile parameters, determining the quality score for the image to be selected based on the quality score parameters includes:

S104: and determining the quality score of the images to be selected according to the quality score parameters, and determining the preferred snap-shot image from the images to be selected.

Optionally, the profile parameter may be directly used as a quality score, the correction feature parameter may be directly used as a quality score, or the profile parameter and the correction feature parameter may be combined as quality scores to respectively determine quality scores of a plurality of images to be selected, one or more images with highest quality scores are taken as preferred snapshot images, or at least one image to be selected with a quality score greater than a preset quality score threshold is taken as the preferred snapshot image.

The existing snapshot strategy cannot ensure that the snapshot image is necessarily optimal, even part of the snapshot image cannot reach the admission standard of the algorithm, and therefore the intelligent algorithm cannot generate an ideal calculation result. The optimal strategy for capturing the images solves the problem that an intelligent algorithm cannot generate an ideal calculation effect due to poor data. The following describes an exemplary method for capturing an image according to this embodiment by using a specific embodiment, and takes a human body capturing as an example, the method includes:

S201: and selecting a snapshot machine scene.

The snap shot scene, i.e. the shot area, is a selected one of the preset shot areas as shown in fig. 2.

S202: the sub-photographing region weights are divided.

The preset photographing region is divided into several sub photographing regions for different positions where the target object may now be preset, as shown in fig. 3. It should be noted that onlyThe method adopts a simpler dividing mode, and specific dividing can adopt different modes, such as equidistant line dividing and the like, according to requirements. Obviously, the target object appears in different sub-shooting areas and has a certain influence on our snapshot, so for the different sub-shooting areas where the target object appears, we set corresponding weights for the sub-shooting areas, denoted as W _Si (weights of sub-photographing region i), specific sub-photographing region weights and sub-photographing region divisions may be set according to different snapshot scenes, and for the above scenes, we may set in advance:

W _S4 ＝W _S6 ＞W _S1 ＞W _S3 ＞W _S5 ＞W _S2 。

s203: target object model pointing.

Optionally, by acquiring a candidate capture photograph based on several capture photographs captured by the above-mentioned capture camera scene, taking the contour point of the target object in the capture photograph as one of the key factors for judging whether the capture photograph is a preferred capture photograph, the contour point is marked as Dj, and the weight of each contour point is marked as W _Dj . One such target object may be as shown in fig. 4.

S204: correction characteristic parameters are determined.

Considering the influence of other critical factors on the snapshot, such as the deflection angle of the face, whether the license plate of the vehicle is clear, etc., we define a correction characteristic parameter to determine the influence of these factors on the snapshot, which is denoted as C _i . The correction characteristic parameter may have different determination modes according to different target objects.

S205: the quality score P for each grab photo is determined.

S206: a preferred grab photo is determined.

Optionally, a quality score P of the target object at each grab photo is determined ₁ 、P ₂ 、P ₃ …P _n And comparing to obtain the optimal grab photo.

The current snapshot machine generates a snapshot based on every N frames, but in the selection of the last candidate capture (image to be selected), a better capture cannot be obtained. The preferred method for capturing images can realize the preference of candidate capturing and shooting, solves the problem that a target object has a better position but generates poor capturing under shooting equipment such as video monitoring and the like, and provides good paving for the effect generated by an algorithm for the application of follow-up data.

In some embodiments, the target object comprises a face, the identified keypoints comprise face contour points and at least two facial feature points, and the quality score determination comprises:

Dividing a face contour formed by face contour points into a first face area and a second face area through face feature points;

respectively determining a first face area of a first face area, a second face area of a second face area and a face contour area of a face contour;

determining distribution information of the face contour points in the sub shooting area according to the position information of the face contour points;

acquiring a preset correction constant, a preset face contour point threshold value and a face contour point influence factor of a face contour point;

wherein P is the quality score, W _Di For the i-th sub-photographing region influence factor, W _sj For the face contour point influence factor of the jth face contour point located in the ith sub-photographing region, E is a preset correction constant, sum (D _j ) S is a preset face contour point threshold value _1l Is the area of the first face area S _1r Is the area of the second face area S ₁ Is the outline area of the human face.

In the following, taking an example that the target object includes a human face, the method for image preference according to the present embodiment is illustrated, and the method includes:

S301: and selecting a snapshot scene and dividing sub-shooting areas.

Alternatively, a snap shot scene is shown in fig. 5, and divided sub-shot areas are shown in fig. 6.

The images shown in fig. 5 and 6 show that the setting position of the face camera is reasonable, no obvious unsuitable area exists in the capturing range, and the face can be seen clearly in each point, so that the weight gap of the sub-shooting areas is reduced as much as possible when the sub-shooting areas are divided. Considering the distance between each region and the snapshot camera, for example, setting the weight of the sub-shooting region as W _S1 ＝1，W _S2 ＝0.98，W _S3 ＝0.96。

S302: and determining the weight of the face contour points.

For the face contour, we select N face contour points, so as to ensure that the shape of the face can be roughly contoured, and as shown in fig. 7 and 8 below, the weight of each face contour point is set to 1.

S303: correction characteristic parameters are determined.

Because the angle of the target face has a larger influence on the snapshot preference, the correction variable should take the influence of the angle into consideration, and the correction characteristic parameters are given according to the characteristics, such as the nose, which can obviously distinguish the deflection angle, contained in the targetThe area formed by the extended cut contour points is shown in FIG. 8, and the left side is marked as S _l The right side is marked S _r The area formed by the entire contour point is denoted S, then the correction characteristic parameter +.>Presetting a correction constant E, wherein the correction constant E is generally between 0 and 1, and according to an influence factor, the larger the influence of the influence factor on snapshot is, the larger E is, so that correction becomesQuantity->Updating the correction characteristic parameter with the correction variable C as one of the quality scoring parameters.

S304: a quality score is determined.

Based on the above conditions, it is assumed that there is M in the first image to be selected ₁ The contour points appear in the region 1, N-M ₁ The contour points appear in region 2, the second image to be selected having M ₂ The contour points appear in the region 2, N-M ₂ The contour points of the first image to be selected are present in the region 3 with an area S ₁ The left side is marked as S _1l The right side is marked S _1r The area formed by the contour points of the second image to be selected is S ₂ The left side is marked as S _2l The right side is marked S _2r Then a first to-be-selected image quality score P1 and a second to-be-selected image quality score P2 are determined, respectively:

s305: a preferred snap shot image is determined.

Comparison P ₁ And P ₂ And obtaining the better snapshot image in the first image to be selected and the second image to be selected as the preferable snapshot image.

It will be appreciated that, in the above description, two images to be selected are taken as an example, and those skilled in the art can implement determining one or more preferred snap shots from the multiple images to be selected according to the above-described ideas.

In some embodiments, the target object comprises a vehicle, the identified keypoints comprise vehicle contour points and license plate identification information, and the determination of the quality score comprises:

determining distribution information of vehicle contour points in a sub-shooting area according to vehicle contour point position information of the vehicle contour points;

acquiring the number of identification information in an image to be selected;

acquiring a preset correction constant, a preset vehicle contour point threshold value and a vehicle contour point influence factor of a vehicle contour point;

wherein P is the quality score, W _D i is the i-th sub-shooting area influence factor, W _sj For a vehicle contour point influence factor of a jth vehicle contour point located in an ith sub-photographing region, E is a preset correction constant, sum (D _j ) For presetting a vehicle contour point threshold value, N is a preset identification information threshold value, and X is the identification information quantity.

Optionally, the license plate identification information includes a license plate number. Sometimes, due to the shielding of foreign matters, not all license plate numbers can be extracted from each snap image, for example, shielding of branches, flower bed grass blades and the like of flying birds, butterflies or branches at roadsides is achieved, and part of license plate numbers are shielded. Of course, the identification information may be other information, and the above is only exemplified by the license plate number.

The following describes an exemplary method for capturing an image according to this embodiment by using a specific embodiment, and taking vehicle capturing as an example, the method includes:

s401: and selecting a snapshot scene and dividing sub-shooting areas.

Alternatively, the snap shot scene is a preset shooting area, as shown in fig. 9, and the area shown in fig. 9 is the preset shooting area. Referring to fig. 10, fig. 10 is a method of dividing one sub-photographing region of a preset photographing region, and it can be seen that the preset photographing region is divided into four regions of 1, 2, 3, and 4.

Considering that the license plate of the motor vehicle has larger influence on the snapshot of the motor vehicle, the region can be noted when the region is divided, the region which is closer to the snapshot point position can be provided with higher weight, W _s4 ＝1，W _S3 ＝0.99，W _S2 ＝0.96，W _S2 ＝0.94。

S402: and determining the vehicle contour point and the weight of the vehicle contour point.

For motor vehicles, there are many types of vehicles, such as cars, buses, trucks, etc. Alternatively, 8 contour points are used, as shown in fig. 11 and 12. The preset 8 vehicle contour point weights are all 1, and theoretically, at most 7 vehicle contour point weights can be determined in the same image to be selected.

S403: correction characteristic parameters are determined.

Since the license plate number of a motor vehicle is one of the key factors for capturing a photograph, correction feature parameters should be defined and determined around the license plate number.

Assuming that the number of the license plate of the motor vehicle is N-bit characters, and the number of the license plate of the identified target object is X-bit, giving correction characteristic parametersA preset correction constant E, wherein the preset correction constant E is between 0 and 1, should be as close to 1 as possible, whereby the correction variable +.>Updating the correction characteristic parameter with the correction variable C as one of the quality scoring parameters.

S404: a quality score is determined.

Based on the above conditions, the same target object is captured at different moments to obtain a first vehicle captured image and a second vehicle captured image, wherein the first vehicle captured image has 5 contour points in the area 3,2 contour points in the area 1, and the second vehicle captured image has 2 contour points in the area 1, and 5 contour points in the area 2. In the first vehicle snapshot image, 6 license plate numbers are clearly visible, in the second vehicle snapshot image, 5 license plate numbers are clearly visible due to the fact that other vehicles and the like are blocked, or pedestrians pass through when in snapshot, or the situation that roadside branches, suddenly flying birds, balloons and the like are blocked, so that the following steps are achieved:

quality score of first vehicle snap-shot image:

quality score of second vehicle snap-shot image:

S405: a preferred snap shot image is determined.

Comparison P ₃ And P ₄ The better snapshot of the first vehicle snapshot image and the second vehicle snapshot image can be obtained and used as the preferable snapshot image.

It will be appreciated that, in the above description, two vehicle snap shots are taken as an example, and those skilled in the art may implement determining one or more preferred snap shots from the plurality of images to be selected according to the above-described ideas.

Optionally, the target object may also be a non-motor vehicle, and the method for determining the preferred snapshot image from the several images to be selected including the non-motor vehicle is similar to the method for determining that the target object is a non-motor vehicle, which is not described herein.

Optionally, the target object may be a human body, and the method for determining the preferred snap image from the several images to be selected including the human body is similar to the method in which the target object is a human face, which is not described herein.

In some embodiments, referring to fig. 13, fig. 13 illustrates a preferred method of capturing images, comprising:

s1301: and determining a preset shooting area.

Alternatively, the preset photographing region may be determined by determining the snapshot scene.

S1302: dividing a preset shooting area and setting sub shooting area weights.

S1303: the target object contour points and sets the contour point weights.

S1304: and acquiring a plurality of images to be selected, which are shot in a preset shooting area.

S1305: and respectively determining the quality scores of the images to be selected.

S1306: a preferred snap shot image is determined.

In step S1305, one determination manner of determining the quality scores of the images to be selected, respectively, may be refer to fig. 14, and the contour parameters may be determined by respectively obtaining the sub-capturing area weights, the contour point position information, and the contour point weights; and respectively acquiring correction characteristic sub-parameters corresponding to the correction characteristic points of multiple categories, preset correction constants corresponding to the correction characteristic sub-parameters of the categories, and influence factors corresponding to the correction characteristic parameters of the categories to determine the correction characteristic parameters, and further determining the quality scores according to the profile parameters and the correction characteristic parameters.

According to the snapshot image optimization method, the plurality of images to be selected shot in the preset shooting area are acquired, the target objects in the images to be selected and the identification key points of the target objects are identified, the quality scoring parameters are determined, the quality scores of the images to be selected are determined according to the quality scoring parameters, and the optimal snapshot images are determined from the images to be selected, so that one or more optimal snapshot images can be determined in the plurality of images to be selected, the image quality of the snapshot images is improved, the problem that an intelligent algorithm cannot generate an ideal output effect due to poor quality of the snapshot images is solved, the reliability of the snapshot images is improved, good paving is made for generating the ideal effect for a follow-up intelligent algorithm by using the snapshot images, and the output result of the intelligent algorithm which relies on the snapshot images is improved effectively.

Example two

Referring to fig. 15, an embodiment of the present invention further provides a snap-shot image preference system, including:

an acquiring module 1501, configured to acquire a plurality of images to be selected captured in a preset capturing area;

an identifying module 1502, configured to identify a target object in an image to be selected, and identify a key point of the target object;

a quality score parameter determining module 1503, configured to determine a quality score parameter, where the quality score parameter includes at least one of a correction feature parameter and a contour parameter, the correction feature parameter is determined according to identification key point position information of the identification key point and/or identification key point number of the identification key point, and the contour parameter is determined according to identification key point position information of the identification key point and identification key point influence factor of the identification key point;

the preferred snap image determining module 1504 is configured to determine a quality score of the images to be selected according to the quality score parameter, and determine a preferred snap image from the images to be selected.

In some embodiments, the quality score parameter determination module comprises at least one of a correction feature parameter determination module, a profile parameter determination module, the correction feature parameter determination module comprising a first correction feature parameter determination sub-module and/or a second correction feature parameter determination sub-module;

If the identification key point comprises a contour point of the target object, the identification key point position information comprises contour point position information of the contour point, the identification key point influence factor comprises contour point influence factors of the contour point, the contour parameter determining module is used for dividing a preset shooting area into at least two sub shooting areas and determining sub shooting area influence factors of the sub shooting areas, distribution information of the contour point in the sub shooting areas is determined according to the contour point position information, a preset contour point threshold value of the target object is obtained, and contour parameters are determined according to the distribution information, the sub shooting area influence factors and the contour point influence factors;

if the identification key point comprises correction feature points and contour points of the target object, the correction feature points are located in the contour formed by the contour points, the identification key point position information comprises correction feature point position information of the correction feature points and contour position information of the contour points, and the second correction feature parameter determination submodule is used for determining correction feature parameters according to the correction feature point position information and the contour position information.

In this embodiment, the snapshot image optimization system executes the snapshot image optimization method described in any one of the above embodiments, and specific functions and technical effects may be referred to the above embodiments and are not described herein.

Referring to fig. 16, an embodiment of the present application further provides an electronic device 1600, the electronic device 1600 including a processor 1601, a memory 1602 and a communication bus 1603;

the communication bus 1603 is used to connect the processor 1601 and the memory 1602;

the processor 1601 is configured to execute a computer program stored in the memory 1602 to implement the snap shot image preferred method according to any of the embodiments described above.

The embodiment of the application also provides a non-volatile readable storage medium, in which one or more modules (programs) are stored, where the one or more modules are applied to a device, and the device may be caused to execute instructions (instructions) of a step included in the embodiment one of the embodiment of the application.

An embodiment of the present application further provides a computer-readable storage medium having stored thereon a computer program for causing the computer to execute the snap shot image optimization method according to any one of the embodiments.

The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the appended claims.

In the corresponding figures of the above embodiments, connecting lines may represent connection relationships between various components to represent further constituent signal paths (test_signal paths) and/or one or more ends of some lines with arrows to represent primary information flow, as an indication, not as a limitation of the scheme itself, but rather the use of these lines in connection with one or more example embodiments may help to more easily connect circuits or logic units, any represented signal (as determined by design requirements or preferences) may actually comprise one or more signals that may be transmitted in either direction and may be implemented in any suitable type of signal scheme.

In the above embodiments, unless otherwise specified the description of a common object by use of a sequence number "first", "second", etc., merely indicates that it refers to a different instance of the same object, and is not intended to indicate that the described object must take a given order, whether temporally, spatially, in ranking, or in any other manner.

Reference in the specification to "this embodiment," "one embodiment," "another embodiment," or "other embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some embodiments, but not necessarily all embodiments. Multiple occurrences of "this embodiment," "one embodiment," "another embodiment," and "like" do not necessarily all refer to the same embodiment. If the specification states a component, feature, structure, or characteristic "may", "might", or "could" be included, that particular component, feature, structure, or characteristic is not required to be included. If the specification or claim refers to "a" or "an" element, that does not mean there is only one of the element. If the specification or claims refer to "an additional" element, that does not preclude there being more than one of the additional element.

In the above embodiments, while the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory structures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

Claims

1. A method of selecting a snap shot image comprising:

acquiring a plurality of images to be selected shot in a preset shooting area;

Determining the quality score of the images to be selected according to the quality score parameters, and determining a preferred snapshot image from the images to be selected;

if the target object includes a face, the quality score is determined by a method including,

the identification key points comprise face contour points and at least two face feature points, and the face contour formed by the face contour points is divided into a first face area and a second face area through the face feature points; respectively determining a first face area of the first face area, a second face area of the second face area and a face contour area of the face contour; dividing the preset shooting area into at least two sub shooting areas, and determining sub shooting area influence factors of the sub shooting areas; determining distribution information of the face contour points in the sub shooting area according to the face contour point position information of the face contour points; acquiring a preset correction constant, a preset face contour point threshold value and a face contour point influence factor of the face contour point; the quality score is determined in such a way that,

wherein P is the quality score, W _Di For the i-th sub-photographing region influence factor, W _sj For the face contour point influence factor of the jth face contour point located in the ith sub-photographing region, E is a preset correction constant, sum (D _j ) S is a preset face contour point threshold value _1l Is the area of the first face area S _1r Is the area of the second face area S ₁ Is the outline area of the human face;

if the target object comprises a vehicle, the determination mode of the quality score comprises that the identification key points comprise vehicle contour points and license plate identification information, the preset shooting area is divided into at least two sub shooting areas, and sub shooting area influence factors of the sub shooting areas are determined; determining distribution information of the vehicle contour points in the sub-shooting areas according to the vehicle contour point position information of the vehicle contour points; acquiring the number of the identification information in the image to be selected; acquiring a preset correction constant, a preset vehicle contour point threshold value and a vehicle contour point influence factor of the vehicle contour point; the quality score is determined in such a way that,

2. A snap shot image optimization method as claimed in claim 1, wherein the identified key points comprise correction feature points of the target object, the identified key point number comprises correction feature point number of the correction feature points, and the determination manner of the correction feature parameters comprises:

3. A snap shot image optimization method as claimed in claim 1, wherein the identification key points comprise correction feature points and contour points of the target object, the correction feature points are located inside a contour formed by the contour points, the identification key point position information comprises correction feature point position information of the correction feature points and contour position information of the contour points, and the determination manner of the correction feature parameters comprises:

4. A snap shot image preferred method as claimed in claim 3, wherein said determining said correction feature parameter from correction feature point position information of said correction feature point and contour position information of said contour point comprises:

5. A snap shot image optimization method as claimed in claim 1, wherein said identified keypoints comprise at least two types of correction feature points of said target object, a correction feature sub-parameter is determined according to each type of said correction feature points, and said correction feature parameter is determined according to each of said correction feature sub-parameters.

6. A snap shot image optimization method as claimed in claim 1, wherein the identified keypoints comprise contour points of the target object, the identified keypoint location information comprises contour point location information of the contour points, the identified keypoint influence factors comprise contour point influence factors of the contour points, and the contour parameters are determined in a manner comprising:

acquiring a preset contour point threshold value of the target object;

7. A snap shot image preferred method as claimed in any one of claims 1-6, wherein if said quality score parameters include said correction feature parameters and said profile parameters, said determining a quality score for said image to be selected based on said quality score parameters comprises:

8. A snap shot image optimization system comprising:

the preferred snap image determining module is used for determining the quality score of the images to be selected according to the quality score parameters and determining preferred snap images from the images to be selected;

9. A snap shot image optimization system as claimed in claim 8, wherein the quality score parameter determination module comprises at least one of a correction feature parameter determination module, a profile parameter determination module, the correction feature parameter determination module comprising a first correction feature parameter determination sub-module and/or a second correction feature parameter determination sub-module;

10. An electronic device comprising a processor, a memory, and a communication bus;

the communication bus is used for connecting the processor and the memory;

the processor is configured to execute a computer program stored in the memory to implement the method of any one of claims 1-7.

11. A computer readable storage medium, characterized in that it has stored thereon a computer program for causing the computer to perform the method according to any of claims 1-7.