CN115706860A

CN115706860A - Image light supplementing method, device, equipment and storage medium

Info

Publication number: CN115706860A
Application number: CN202110809483.XA
Authority: CN
Inventors: 闵恒
Original assignee: Qiku Software Shenzhen Co Ltd
Current assignee: Qiku Software Shenzhen Co Ltd
Priority date: 2021-07-16
Filing date: 2021-07-16
Publication date: 2023-02-17

Abstract

The invention belongs to the technical field of computers, and discloses a method, a device, equipment and a storage medium for image light supplement. According to the method, brightness statistics is carried out on the image to be supplemented with light, so that image brightness information is obtained; acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type; determining the light supplement intensity information of the light region to be supplemented according to the image brightness information; and performing light supplement on the light region to be supplemented with light according to the light supplement intensity information. The method comprises the steps of determining a light supplementing area according to a light supplementing type corresponding to the image to be supplemented, determining light supplementing intensity information of the light supplementing area according to image brightness information of the image to be supplemented, and finally supplementing light to the light supplementing area in the image to be supplemented according to the light supplementing intensity information.

Description

Image light supplementing method, device, equipment and storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for supplementing light for an image.

Background

At present, the fields of short videos, live broadcasts and the like are exploded, and when a main broadcast carries out live broadcast or shoots short videos, hardware light supplement equipment is gradually lost to ensure the shooting effect of images, but professional hardware light supplement equipment (such as a light supplement lamp) is high in price, a plurality of main broadcasts are difficult to bear, the light supplement equipment is complex in arrangement, needs to be arranged and debugged in advance, and is difficult to apply in a plurality of scenes.

The above is only for the purpose of assisting understanding of the technical solution of the present invention, and does not represent an admission that the above is the prior art.

Disclosure of Invention

The invention mainly aims to provide an image light supplement method, device, equipment and storage medium, and aims to solve the technical problem that in the prior art, light supplement of an image depends on hardware light supplement equipment.

In order to achieve the above object, the present invention provides a method for supplementing light to an image, the method comprising the following steps:

performing brightness statistics on an image to be supplemented with light to obtain image brightness information;

acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type;

determining the light supplement intensity information of the light region to be supplemented according to the image brightness information;

and performing light supplement on the light region to be supplemented with light according to the light supplement intensity information.

Optionally, the supplementary lighting type includes global supplementary lighting;

the step of determining the light region to be compensated of the light image to be compensated according to the light compensation type includes:

and when the supplementary light type is global supplementary light, taking the whole image area of the image to be supplemented as the area to be supplemented.

Optionally, the light supplement type further includes regional light supplement;

when the light supplement type is regional light supplement, human body recognition is carried out on the image to be supplemented with light through a preset portrait segmentation model, and a human body region in the image to be supplemented with light is determined;

and taking the human body area as an area to be supplemented with light.

Optionally, the image brightness information includes image brightness of each pixel point in the image to be supplemented with light;

the step of determining fill-in light intensity information of the light area to be filled in according to the image brightness information includes:

determining a scene light intensity value corresponding to the light image to be compensated according to the image brightness information;

and determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

Optionally, the step of determining the scene light intensity value corresponding to the light image to be compensated according to the image brightness information includes:

acquiring the total number of pixel points of the light image to be compensated;

determining an image brightness median value corresponding to the image to be compensated according to the image brightness information;

determining the number of pixel points of which the image brightness is greater than the image brightness median in the image to be compensated according to the image brightness information and the image brightness median;

and determining the scene light intensity value corresponding to the image to be compensated according to the number of the pixel points and the total number of the pixel points.

Optionally, the step of determining the image brightness median corresponding to the image to be compensated according to the image brightness information includes:

determining the maximum value and the minimum value of the image brightness of each pixel point in the image to be supplemented with light according to the image brightness information;

and calculating the average value of the maximum image brightness value and the minimum image brightness value, and taking the average value as the image brightness median value corresponding to the image to be supplemented with light.

Optionally, before the step of determining fill-in light intensity information of the light area to be filled in according to the scene light intensity value and the image brightness information, the method further includes:

acquiring a manual adjustment intensity value corresponding to the light image to be compensated;

correspondingly, the step of determining fill-in light intensity information of the light area to be filled in according to the scene light intensity value and the image brightness information includes:

determining the light supplement intensity corresponding to each pixel point in the region to be supplemented according to the scene light intensity value, the image brightness information and the manual adjustment intensity value;

and determining the light supplement intensity information of the light region to be supplemented according to the light supplement intensity corresponding to each pixel point in the light region to be supplemented.

Optionally, the step of determining the fill-in light intensity corresponding to each pixel point in the region to be filled according to the scene light intensity value, the image brightness information, and the manual adjustment intensity value includes:

calculating through a light supplement intensity formula according to the scene light intensity value, the image brightness information and the manual adjustment intensity value to determine light supplement intensity corresponding to each pixel point in the region to be compensated;

the fill light intensity formula is as follows:

S _i ＝[(1-G _n )+G _h ]*L _i

wherein S is _i The fill light intensity G corresponding to the ith pixel point in the region to be filled with light _n A scene light intensity value G corresponding to the light image to be compensated _h Manually adjusting intensity value L corresponding to the light image to be compensated _i The image brightness of the ith pixel point in the region to be compensated is determined according to the image brightness information.

Optionally, before the step of determining fill-in light intensity information of the light area to be filled in according to the scene light intensity value and the image brightness information, the method includes:

obtaining a historical scene light intensity value corresponding to the light image to be compensated;

determining a light intensity change rate according to the historical scene light intensity value and the scene light intensity value;

and when the light intensity change rate is smaller than or equal to a preset change rate threshold value, executing the step of determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

Optionally, the step of performing light supplement on the light region to be supplemented with light according to the light supplement intensity information includes:

determining a light supplement direction and light source power according to the light supplement intensity information;

setting an analog light source according to the light supplementing direction and the light source power;

and supplementing light to the light region to be supplemented with light based on the analog light source.

Optionally, the step of obtaining a fill-in light type corresponding to the light image to be filled in includes:

detecting the number of people in the image to be supplemented with light;

and determining the light supplement type corresponding to the image to be supplemented with light according to the number of the people.

Optionally, the step of determining the fill-in type corresponding to the image to be filled with light according to the number of the people includes:

when the number of the people is larger than or equal to a first preset number and smaller than or equal to a second preset number, judging that the light supplement type corresponding to the image to be supplemented is regional light supplement;

and when the number of the characters is smaller than a first preset number or larger than a second preset number, judging that the light supplement type corresponding to the image to be supplemented is global light supplement.

In addition, to achieve the above object, the present invention further provides an image light supplement device, which includes the following modules:

the luminance statistic module is used for carrying out luminance statistics on the image to be supplemented with light to obtain image luminance information;

the region determining module is used for acquiring a light supplement type corresponding to the light image to be supplemented, and determining the light region to be supplemented of the light image to be supplemented according to the light supplement type;

the intensity calculation module is used for determining the fill light intensity information of the light area to be filled according to the image brightness information;

and the image adjusting module is used for supplementing light to the light area to be supplemented according to the light supplementing intensity information.

Optionally, the supplementary lighting type includes global supplementary lighting; the region determining module is further configured to, when the fill light type is global fill light, use the entire image region of the image to be filled as a region to be filled.

Optionally, the light supplement type further includes regional light supplement; the region determining module is further configured to perform human body recognition on the image to be supplemented with light through a preset portrait segmentation model when the light supplementation type is regional light supplementation, and determine a human body region in the image to be supplemented with light; and taking the human body area as an area to be supplemented with light.

Optionally, the image brightness information includes image brightness of each pixel point in the image to be supplemented with light; the intensity calculation module is further configured to determine a scene light intensity value corresponding to the light image to be compensated according to the image brightness information; and determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

Optionally, the intensity calculating module is further configured to obtain a total number of pixels of the image to be compensated; determining an image brightness median value corresponding to the image to be compensated according to the image brightness information; determining the number of pixel points of which the image brightness is greater than the image brightness median in the image to be compensated according to the image brightness information and the image brightness median; and determining the scene light intensity value corresponding to the light image to be compensated according to the number of the pixel points and the total number of the pixel points.

Optionally, the intensity calculation module is further configured to determine, according to the image brightness information, an image brightness maximum value and an image brightness minimum value of each pixel point in the image to be light-supplemented; and calculating the average value of the maximum image brightness value and the minimum image brightness value, and taking the average value as the image brightness median value corresponding to the image to be supplemented with light.

In addition, to achieve the above object, the present invention further provides an image light supplement device, including: the image light supplement method comprises a processor, a memory and an image light supplement program which is stored on the memory and can run on the processor, wherein the image light supplement program is executed by the processor to realize the steps of the image light supplement method.

In addition, in order to achieve the above object, the present invention further provides a computer-readable storage medium, where an image fill-in light program is stored, and when the image fill-in light program is executed, the steps of the image fill-in light method are implemented.

According to the method, brightness statistics is carried out on the image to be supplemented with light, so that image brightness information is obtained; acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type; determining the light supplement intensity information of the light supplement area to be supplemented according to the image brightness information; and performing light supplement on the light region to be supplemented with light according to the light supplement intensity information. The method comprises the steps of determining a light supplementing area according to a light supplementing type corresponding to the image to be supplemented, determining light supplementing intensity information of the light supplementing area according to image brightness information of the image to be supplemented, and finally supplementing light to the light supplementing area in the image to be supplemented according to the light supplementing intensity information.

Drawings

Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating an image fill-in light method according to a first embodiment of the present invention;

FIG. 3 is a flowchart illustrating a second embodiment of a method for supplementing light according to the present invention;

FIG. 4 is a flowchart illustrating a light supplement method according to a third embodiment of the present invention;

fig. 5 is a block diagram of an image fill-in light device according to a first embodiment of the invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of an image fill-in light device in a hardware operating environment according to an embodiment of the present invention.

As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.

Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

As shown in fig. 1, a memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and an image fill-in program.

In the electronic apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the electronic device according to the present invention may be disposed in an image fill-in device, and the electronic device calls an image fill-in program stored in the memory 1005 through the processor 1001 and executes the image fill-in method according to the embodiment of the present invention.

An embodiment of the present invention provides a method for supplementing light for an image, and referring to fig. 2, fig. 2 is a schematic flowchart of a first embodiment of the method for supplementing light for an image according to the present invention.

In this embodiment, the method for supplementing light to an image includes the following steps:

step S10: and carrying out brightness statistics on the image to be supplemented with light to obtain image brightness information.

It should be noted that the execution main body of this embodiment may be the image light supplement device, and the image light supplement device may be an electronic device such as a mobile phone, a tablet computer, a personal computer, or a server, or other devices with the same or similar functions.

It should be noted that the image to be compensated may be an image recorded while live broadcasting or shooting a short video. The image brightness information includes the image brightness of each pixel point in the image to be supplemented with light. The luminance statistics of the image to be supplemented with light can be performed by performing color space conversion on the image to be supplemented with light so as to extract the image luminance of each pixel point in the image to be supplemented with light, and performing luminance histogram distribution statistics based on the image luminance so as to obtain image luminance information. In order to facilitate the statistical processing, the image brightness may be represented by a brightness level during the statistical processing.

Step S20: and acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type.

It should be noted that the light supplement type may include two types, that is, a global light supplement type and a regional light supplement type, different light supplement types divide the region to be compensated differently, the light supplement type corresponding to the image to be compensated may be set by a user in advance according to actual needs, and this embodiment is not limited to this. The user may be a main broadcaster who shoots an image to be supplemented with light, or a director who manages a live broadcast picture for the main broadcaster.

It can be understood that a user may set a fill-in type corresponding to an image to be filled in according to actual needs, for example: when a user carries out common live broadcasting, the whole live broadcasting image needs to be supplemented with light, and the light supplementing type corresponding to the image to be supplemented with light can be set as global light supplementing; when the user is in dance live broadcast, the background needs to be faded, and only the images of dancers in live broadcast images need to be supplemented with light, so that the light supplement type corresponding to the images to be supplemented with light can be set as regional light supplement.

In actual use, if the fill-in type corresponding to the image to be filled in is global fill-in, it indicates that the user wishes to fill in the entire image to be filled in, and therefore, when the fill-in type is global fill-in, the entire image area of the image to be filled in is used as the area to be filled in.

In actual use, if the light supplement type corresponding to the light image to be supplemented is regional light supplement, it indicates that the user only needs to supplement light to a partial region in the light image to be supplemented, where the partial region may be a region where a human body is located in the light image to be supplemented or a region where a special object specified by the user is located.

Step S30: and determining the light supplement intensity information of the light supplement area to be supplemented according to the image brightness information.

It should be noted that the fill-in light intensity information of the to-be-filled light region may include fill-in light intensities corresponding to the pixel points in the to-be-filled light region. The light supplement intensity information of the light region to be supplemented with light according to the image brightness information may be obtained by determining scene illumination intensity corresponding to the image to be supplemented with light according to the image brightness information, and determining light supplement intensity of each pixel point in the light region to be supplemented with light according to the image brightness information and the scene illumination intensity.

Step S40: and performing light supplement on the light region to be supplemented with light according to the light supplement intensity information.

The light supplement intensity information may include light supplement intensities corresponding to the pixels in the light region to be supplemented, and performing light supplement on the light region to be supplemented according to the light supplement intensity information may be adjusting image brightness of the pixels in the light region to be supplemented according to the light supplement intensities corresponding to the pixels in the light region to be supplemented, so as to implement light supplement on the light region to be supplemented.

Further, in order to make the effect of supplementing light to the image more natural, step S40 in this embodiment may include:

determining a light supplement direction and light source power according to the light supplement intensity information; setting an analog light source according to the light supplement direction and the light source power; and supplementing light to the light region to be supplemented with light based on the analog light source.

It can be understood that the light supplement intensity information includes light supplement intensity of each pixel point in the region to be supplemented with light, the light supplement direction and the light source power which need to be supplemented with light can be determined according to the light supplement intensity distribution of each pixel point, then a simulation light source can be set according to the light supplement direction and the light source power, and light supplement is performed on the region to be supplemented with light by simulating real light supplement equipment through the simulation light source.

In practical use, the setting of the analog light source according to the fill-in light direction and the light source power may be performed by using an Open Graphics Library (OPENGL) frame to set the analog light source according to the fill-in light direction and the light source power.

It can be understood that, various abnormal phenomena may be inevitably generated in the actual operation of the image light supplement device, and in order to facilitate troubleshooting of the abnormal phenomena, after step S40 in this embodiment, an image light supplement record may be generated according to an image to be compensated, image brightness information, a light supplement type, a light supplement area, and light supplement intensity information, and then the image light supplement record is stored, and when a manager of a subsequent image light supplement device is abnormal in the image light supplement device, a reason for the abnormality may be quickly troubleshot according to the stored image light supplement record, and the abnormality may be handled.

In actual use, the storing of the image supplementary lighting record may be storing the image supplementary lighting record in a storage space of the image supplementary lighting device, or sending the image supplementary lighting record to a record storage server for storage. Wherein, the record storage server may be a server set in advance for storing the record.

In the embodiment, brightness statistics is performed on an image to be supplemented with light to obtain image brightness information; acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type; determining the light supplement intensity information of the light region to be supplemented according to the image brightness information; and performing light supplement on the light region to be supplemented with light according to the light supplement intensity information. The light supplementing method and the device have the advantages that the light region to be supplemented is determined according to the light supplementing type corresponding to the image to be supplemented, the light supplementing intensity information of the light region to be supplemented is determined according to the image brightness information of the image to be supplemented, finally the light supplementing is carried out on the light region to be supplemented in the image to be supplemented according to the light supplementing intensity information, the whole process is operated in software, the image light supplementing can be realized without depending on hardware light supplementing equipment, the use is convenient, and the cost is low.

Referring to fig. 3, fig. 3 is a flowchart illustrating a method for supplementing light to an image according to a second embodiment of the present invention.

Based on the first embodiment, before the step S30, the image light supplement method of this embodiment includes:

step S301: and determining the scene light intensity value corresponding to the light image to be compensated according to the image brightness information.

It should be noted that the scene light intensity value is a numerical value used for representing the scene illumination intensity in the shot light-to-be-supplemented image, and a higher scene light intensity value indicates a stronger scene illumination intensity.

Further, in order to reasonably determine the scene light intensity value, step S301 of this embodiment may include:

acquiring the total number of pixel points of the light image to be compensated; determining an image brightness median value corresponding to the image to be compensated according to the image brightness information; determining the number of pixel points of which the image brightness is greater than the image brightness median in the image to be compensated according to the image brightness information and the image brightness median; and determining the scene light intensity value corresponding to the image to be compensated according to the number of the pixel points and the total number of the pixel points.

It should be noted that, the total number of the pixels for obtaining the light image to be compensated may be the total number of the pixels in the light image to be compensated, and the total number of the pixels is obtained. The image brightness median corresponding to the image to be light-supplemented may be the median of the image brightness of each pixel point in the image to be light-supplemented.

It can be understood that, if more pixel points are included in the light image to be compensated, the more the pixel points have a luminance greater than the median of the luminance of the image, the more the distribution of the pixel points in the light image to be compensated is concentrated in the high-luminance level region, that is, the higher the light intensity of the scene corresponding to the light image to be compensated is.

In actual use, the determining of the scene light intensity corresponding to the image to be compensated may be, according to the number of the pixels and the total number of the pixels, obtaining a ratio of the number of the pixels to the total number of the pixels, and taking the ratio as the scene light intensity value corresponding to the image to be compensated.

Further, in order to quickly determine an image brightness median of a light-to-be-compensated image, the step of determining the image brightness median corresponding to the light-to-be-compensated image according to the image brightness information in this embodiment may include:

determining the maximum value and the minimum value of the image brightness of each pixel point in the image to be supplemented with light according to the image brightness information; and calculating the average value of the maximum image brightness value and the minimum image brightness value, and taking the average value as the image brightness median value corresponding to the image to be supplemented with light.

It should be noted that the maximum value of the image brightness may be the maximum value of the image brightness of each pixel in the light-to-be-compensated image, and the minimum value of the image brightness may be the minimum value of the image brightness of each pixel in the light-to-be-compensated image.

It can be understood that the image brightness information includes the image brightness of each pixel point in the image to be light supplemented, and the maximum value of the image metric and the minimum value of the image brightness can be quickly determined by comparing the image brightness of each pixel point.

For example: assuming that there are 5 pixels in the image to be supplemented with light, and the image brightness of each pixel is 1, 3, 5, 2, and 2, respectively, the maximum value of the image brightness is 5, the minimum value of the image brightness is 1, and the median value of the image brightness is (5 + 1)/2 =3.

Step S302: and determining the light supplement intensity information of the light region to be compensated according to the scene light intensity value and the image brightness information.

It should be noted that the fill-in light intensity information of the to-be-filled light region may include fill-in light intensities corresponding to the pixel points in the to-be-filled light region. The light supplement intensity information of the light region to be supplemented is determined according to the scene light intensity value and the image brightness information, and the light supplement intensity of each pixel point in the light region to be supplemented is determined through an intensity calculation formula according to the scene light intensity value and the image brightness information, so that the light supplement intensity information of the light region to be supplemented is obtained.

Wherein, the intensity calculation formula may be:

S _i ＝(1-G _n )*L _i

wherein S is _i The fill light intensity G corresponding to the ith pixel point in the region to be filled with light _n Is the scene light intensity value, L, corresponding to the light image to be compensated _i The image brightness of the ith pixel point in the region to be compensated is determined according to the image brightness information.

Further, a user may have a special light supplement requirement sometimes, which is different from the light supplement requirement under a normal condition, and if the light supplement intensity of the light region to be compensated is directly calculated in a normal manner, the special light supplement requirement of the user may not be met, which may result in poor user experience, and in order to avoid this, before step S302, the method may further include:

correspondingly, step S302 in this embodiment may include:

determining light supplement intensity corresponding to each pixel point in the region to be compensated according to the scene light intensity value, the image brightness information and the manual adjustment intensity value; and determining the light supplement intensity information of the light region to be supplemented according to the light supplement intensity corresponding to each pixel point in the light region to be supplemented.

It should be noted that the manually adjusted intensity value corresponding to the light-supplement image may be a light-supplement intensity adjustment parameter manually set by a user, and the user may set the manually adjusted intensity value according to actual needs. Determining the fill-in light intensity information of the light region to be filled according to the fill-in light intensity corresponding to each pixel point in the light region to be filled may be to aggregate the fill-in light intensities corresponding to each pixel point in the light region to be filled, construct a set, and use the constructed set as the fill-in light intensity information of the light region to be filled.

In actual use, the fill-in light intensity corresponding to each pixel in the light area to be filled is determined according to the scene light intensity value, the image brightness information and the manual adjustment intensity value, and the fill-in light intensity corresponding to each pixel in the light area to be filled is determined by calculating according to the scene light intensity value, the image brightness information and the manual adjustment intensity value through a fill-in light intensity formula;

the fill light intensity formula may be:

S _i ＝[(1-G _n )+G _h ]*L _i

Further, in the shooting process, a sudden situation may occur due to various reasons, which may cause a sudden and severe change in brightness of the image, and at this time, if the fill-in light intensity is calculated according to the sudden image for adjustment, the effect may be poor, the fill-in light effect is not ideal, and in order to overcome the above defect, before step S302 in this embodiment, the method may further include:

obtaining a historical scene light intensity value corresponding to the light image to be compensated; determining a light intensity change rate according to the historical scene light intensity value and the scene light intensity value; and when the light intensity change rate is smaller than or equal to a preset change rate threshold value, executing the step of determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

It should be noted that the historical scene light intensity value may be a scene light intensity value calculated according to the historical light image to be compensated, and the historical light image to be compensated may be a light image to be compensated acquired within a preset time before the current light image to be compensated, for example: and taking the light image to be compensated acquired within 5 seconds before the current light image to be compensated as a historical light image to be compensated. The preset time may be set according to actual needs, which is not limited in this embodiment. The preset change rate threshold value can be set by a manager of the image light supplement device according to actual needs.

In practical use, the determining the light intensity change rate according to the historical scene light intensity value and the scene light intensity value may be subtracting the historical scene light intensity value and the scene light intensity value to obtain a light intensity change difference, and taking the light intensity change difference as the light intensity change rate. For example: the historical light intensity value corresponding to the image to be supplemented with light is 50, the scene light intensity value is 80, the light intensity change difference value is 30, and at this time, the light intensity change difference value can be used as the light intensity change rate.

Of course, the determination of the light intensity change rate according to the historical scene light intensity value and the scene light intensity value may also be performed by subtracting the historical scene light intensity and the scene light intensity to obtain a light intensity change difference, and then taking a ratio of the light intensity change difference to the historical light intensity value as the light intensity change rate. For example: if the historical light intensity value corresponding to the light-supplement image is 60 and the scene light intensity value is 100, the light intensity variation difference is 100-60=40, and the light intensity variation rate is 40/60=66.67%.

It can be understood that, if the light intensity change rate is less than or equal to the preset change rate threshold, it may be indicated that no abnormal condition occurs and the brightness of the image is changed dramatically, and therefore, the subsequent steps may be continued.

According to the embodiment, when the light supplement intensity information of the light supplement area to be supplemented is calculated, the scene light intensity value of the scene where the image to be supplemented is shot is determined by analyzing according to the image brightness information, and then the light supplement intensity of each pixel point in the light supplement area to be supplemented is calculated according to the scene light intensity value and the image brightness information, so that the light supplement intensity information of the light supplement area to be supplemented is obtained. In addition, the special light supplement requirement possibly existing in the user is considered when the light supplement intensity information is specifically calculated, and the intensity value is manually adjusted when the light supplement intensity information is calculated, so that the user can adjust the intensity value according to the actual requirement of the user, and the application range of the image light supplement method is expanded.

Referring to fig. 4, fig. 4 is a flowchart illustrating a method for supplementing light to an image according to a third embodiment of the present invention.

Based on the first embodiment, in the step S20, the method for supplementing light to an image in this embodiment includes:

step S201: and detecting the number of people in the image to be supplemented with light.

It should be noted that, in the present day, when live broadcasting or recording special short videos, users may use various special objects (such as dolls, hands, etc.). The number of the persons can be the sum of the number of the faces in the image to be supplemented with light and the number of the special objects. The step of detecting the number of the figures in the image to be subjected to light supplement can be that the image to be subjected to light supplement is subjected to face recognition, the number of the faces in the image to be subjected to light supplement is determined, then the special objects in the image to be subjected to light supplement are detected, the number of the special objects is determined, and the number of the faces and the number of the special objects are added, so that the number of the figures in the image to be subjected to light supplement is obtained.

Step S202: and determining the light supplement type corresponding to the image to be supplemented with light according to the number of the people.

It should be noted that determining the light supplement type corresponding to the image to be supplemented with light according to the number of the characters may be determining whether the number of the characters satisfies a condition corresponding to light supplement for the area, if the number of the characters satisfies the condition corresponding to light supplement for the area, it may be determined that the light supplement type corresponding to the image to be supplemented with light is area light supplement, and if the number of the characters does not satisfy the condition corresponding to light supplement for the area, it may be determined that the light supplement type corresponding to the image to be supplemented with light is global light supplement.

Further, to illustrate how to determine the fill-in type corresponding to the image to be filled in according to the number of people, step S202 in this embodiment may include:

when the number of the characters is larger than or equal to a first preset number and smaller than or equal to a second preset number, judging that the light supplement type corresponding to the image to be supplemented is regional light supplement; and when the number of the figures is smaller than a first preset number or larger than a second preset number, judging that the light supplement type corresponding to the image to be subjected to light supplement is global light supplement.

It should be noted that the first preset number and the second preset number may be preset by a manager of the image light supplement device, where the first preset number and the second preset number are positive integers, and the first preset number is smaller than or equal to the second preset number. The first preset number and the second preset number are used for judging whether the number of the figures meets the condition of light supplement in the area.

In actual use, if the number of the persons is greater than or equal to the first preset number and less than or equal to the second preset number, it can be determined that the number of the persons meets the condition of regional supplementary lighting, and it can be determined that the type of supplementary lighting corresponding to the image to be supplemented is regional supplementary lighting. If the number of the characters is smaller than the first preset number or larger than the second preset number, it can be determined that the number of the characters does not meet the condition of regional supplementary lighting, and it can be determined that the type of supplementary lighting corresponding to the image to be supplemented with light is global supplementary lighting. For example: if the first preset number is set to 1 and the second preset number is set to 3, it can be determined that the light supplement type corresponding to the image to be light supplemented is regional light supplement when the number of characters is greater than or equal to 1 and less than or equal to 3, and it can be determined that the light supplement type corresponding to the image to be light supplemented is global light supplement when the number of characters is less than 1 or greater than 3.

Step S203: and determining a light supplementing area to be supplemented with the light image according to the light supplementing type.

It can be understood that, when the fill-in type corresponding to the light image to be filled in is global fill-in, the entire image area of the light image to be filled in may be used as the light area to be filled in.

It should be noted that when the light supplement type corresponding to the light supplement image is regional light supplement, a user may only want to supplement light to a region where a human body is located, and at this time, human body recognition may be performed on the light supplement image to be supplemented through a preset portrait segmentation model, so as to determine a human body region in the light supplement image; and taking the human body region as a light-to-be-compensated region, wherein the human body region can be a region where a human body is located in the light-to-be-compensated image. Of course, the user may also want to fill in the light of the used special object, and at this time, the user preset image in the light-to-be-filled image may also be identified, and the area where the user preset image in the light-to-be-filled image is located is used as the light-to-be-filled area. The user preset image may be an image preset by a user, for example: images of dolls or hands.

It should be noted that the preset portrait segmentation model may be a deep learning model obtained by training in advance using a large number of data samples, for example: the method is based on a deep learning model obtained by training a large number of data samples by using a MNN framework which is a lightweight deep learning reasoning engine. The preset portrait segmentation model can be used for identifying the region where the human body is located in the light image to be compensated.

The embodiment detects the number of people in the image to be supplemented with light; determining a light supplement type corresponding to the light image to be supplemented according to the number of the people; and determining a light region to be compensated of the light image to be compensated according to the light compensation type. The light supplementing type corresponding to the image to be supplemented with light is determined according to the number of the figures in the image to be supplemented with light when the image to be supplemented with light is supplemented with light, then the light region to be supplemented with light is determined according to the light supplementing type, so that the user does not need to specify the light region to be supplemented with light, the corresponding light supplementing type is set according to the actual image content, the intelligence of the image light supplementing method is improved, and the use by the user is simpler and more convenient.

In addition, an embodiment of the present invention further provides a storage medium, where an image light supplement program is stored on the storage medium, and when the image light supplement program is executed by a processor, the steps of the image light supplement method described above are implemented.

Referring to fig. 5, fig. 5 is a block diagram of an image fill-in light device according to a first embodiment of the present invention.

As shown in fig. 5, the apparatus for supplementing light for an image according to an embodiment of the present invention includes:

the luminance statistics module 10 is configured to perform luminance statistics on an image to be light supplemented to obtain image luminance information;

the region determining module 20 is configured to obtain a light supplement type corresponding to the light image to be supplemented, and determine the light region to be supplemented of the light image to be supplemented according to the light supplement type;

the intensity calculating module 30 is configured to determine fill light intensity information of the light region to be filled according to the image brightness information;

and the image adjusting module 40 is configured to perform light supplement on the light region to be supplemented with light according to the light supplement intensity information.

Further, the fill light type includes global fill light;

the region determining module 20 is further configured to, when the light supplement type is global light supplement, use the entire image region of the image to be supplemented as the light supplement region.

Further, the supplementary lighting type also comprises regional supplementary lighting;

the region determining module 20 is further configured to perform human body recognition on the image to be light-supplemented through a preset portrait segmentation model when the light-supplementing type is regional light supplementation, and determine a human body region in the image to be light-supplemented; and taking the human body area as an area to be supplemented with light.

Further, the image brightness information includes image brightness of each pixel point in the image to be supplemented with light;

the intensity calculating module 30 is further configured to determine a scene light intensity value corresponding to the light image to be compensated according to the image brightness information; and determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

Further, the intensity calculating module 30 is further configured to obtain a total number of pixel points of the light image to be compensated; determining an image brightness median value corresponding to the image to be compensated according to the image brightness information; determining the number of pixel points of which the image brightness is greater than the image brightness median in the image to be compensated according to the image brightness information and the image brightness median; and determining the scene light intensity value corresponding to the light image to be compensated according to the number of the pixel points and the total number of the pixel points.

Further, the intensity calculating module 30 is further configured to determine, according to the image brightness information, an image brightness maximum value and an image brightness minimum value of each pixel point in the image to be supplemented with light; and calculating the average value of the maximum image brightness value and the minimum image brightness value, and taking the average value as the image brightness median value corresponding to the image to be supplemented with light.

Further, the intensity calculating module 30 is further configured to obtain a manually adjusted intensity value corresponding to the light image to be compensated;

the intensity calculating module 30 is further configured to determine, according to the scene light intensity value, the image brightness information, and the manual adjustment intensity value, light supplement intensity corresponding to each pixel point in the region to be light supplemented; and determining the light supplement intensity information of the light region to be supplemented according to the light supplement intensity corresponding to each pixel point in the light region to be supplemented.

Further, the intensity calculating module 30 is further configured to calculate, according to the scene light intensity value, the image brightness information, and the manual adjustment intensity value, a fill light intensity formula to determine fill light intensity corresponding to each pixel point in the region to be filled;

the fill light intensity formula is as follows:

S _i ＝[(1-G _n )+G _h ]*L _i

wherein S is _i The fill light intensity G corresponding to the ith pixel point in the region to be filled with light _n The scene light intensity value corresponding to the light image to be compensated is obtained,G _h manually adjusting intensity value L corresponding to the light image to be compensated _i The image brightness of the ith pixel point in the region to be compensated is determined according to the image brightness information.

Further, the intensity calculating module 30 is further configured to obtain a historical scene light intensity value corresponding to the light image to be compensated; determining a light intensity change rate according to the historical scene light intensity value and the scene light intensity value; and when the light intensity change rate is smaller than or equal to a preset change rate threshold, determining the light supplement intensity information of the light region to be compensated according to the scene light intensity value and the image brightness information.

Further, the image adjusting module 40 is further configured to determine a fill-in light direction and a light source power according to the fill-in light intensity information; setting an analog light source according to the light supplementing direction and the light source power; and supplementing light to the light region to be supplemented with light based on the analog light source.

Further, the region determining module 20 is further configured to detect the number of people in the image to be supplemented with light; and determining the light supplement type corresponding to the image to be supplemented with light according to the number of the people.

Further, the region determining module 20 is further configured to determine that a light supplement type corresponding to the light image to be supplemented is regional light supplement when the number of people is greater than or equal to a first preset number and less than or equal to a second preset number; and when the number of the figures is smaller than a first preset number or larger than a second preset number, judging that the light supplement type corresponding to the image to be subjected to light supplement is global light supplement.

It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.

It should be noted that the above-mentioned work flows are only illustrative and do not limit the scope of the present invention, and in practical applications, those skilled in the art may select some or all of them according to actual needs to implement the purpose of the solution of the present embodiment, and the present invention is not limited herein.

In addition, the technical details that are not described in detail in this embodiment may refer to the image fill-in light method provided in any embodiment of the present invention, and are not described herein again.

Further, it is to 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 system 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 system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.

The invention discloses A1 and an image light supplementing method, wherein the image light supplementing method comprises the following steps:

A2, the image supplementary lighting method according to A1, wherein the supplementary lighting type comprises global supplementary lighting;

and when the supplementary lighting type is global supplementary lighting, taking the whole image area of the image to be subjected to supplementary lighting as a light area to be subjected to supplementary lighting.

A3, according to the image light supplement method in the A2, the light supplement type further comprises regional light supplement;

when the supplementary lighting type is regional supplementary lighting, human body recognition is carried out on the image to be supplemented with light through a preset portrait segmentation model, and a human body region in the image to be supplemented with light is determined;

and taking the human body area as a light supplementing area.

A4, according to the image light supplementing method in the A1, the image brightness information includes the image brightness of each pixel point in the image to be supplemented with light;

and determining the light supplement intensity information of the light region to be compensated according to the scene light intensity value and the image brightness information.

The image light supplement method according to the above A5 and A4, wherein the step of determining the scene light intensity value corresponding to the image to be supplemented according to the image brightness information includes:

The image light supplement method according to the above A6, in which the step of determining the image brightness median corresponding to the image to be supplemented according to the image brightness information includes:

A7, the image light supplement method according to A4, before the step of determining the light supplement intensity information of the to-be-supplemented region according to the scene light intensity value and the image brightness information, further includes:

determining light supplement intensity corresponding to each pixel point in the region to be compensated according to the scene light intensity value, the image brightness information and the manual adjustment intensity value;

The image light supplement method according to the aspect of A7, where the step of determining the light supplement intensity corresponding to each pixel point in the region to be supplemented according to the scene light intensity value, the image brightness information, and the manual adjustment intensity value includes:

the fill light intensity formula is as follows:

S _i ＝[(1-G _n )+G _h ]*L _i

A9, the image fill-in light method according to A4, before the step of determining fill-in light intensity information of the light area to be filled in according to the scene light intensity value and the image brightness information, the method includes:

A10, the method for supplementing light to an image according to any one of A1 to A9, where the step of supplementing light to the region to be supplemented with light according to the light supplementing intensity information includes:

A11, the image light supplement method according to any one of A1 to A9, where the step of obtaining a light supplement type corresponding to the image to be compensated includes:

detecting the number of people in the image to be supplemented with light;

and determining the light supplement type corresponding to the light image to be supplemented according to the number of the people.

The image light supplement method according to the aspect of a11, where the step of determining the light supplement type corresponding to the image to be supplemented according to the number of the people includes:

The invention discloses a B13 image light supplementing device, which comprises the following modules:

the region determining module is used for acquiring a light supplement type corresponding to the light image to be supplemented, and determining a light region to be supplemented of the light image to be supplemented according to the light supplement type;

B14, the image supplementary lighting device according to B13, wherein the supplementary lighting type includes global supplementary lighting; the region determining module is further configured to, when the fill light type is global fill light, use the entire image region of the image to be filled as a region to be filled.

B15, the image light supplement device as in B14, wherein the light supplement type further comprises regional light supplement; the region determining module is further configured to perform human body recognition on the image to be supplemented with light through a preset portrait segmentation model when the light supplementation type is regional light supplementation, and determine a human body region in the image to be supplemented with light; and taking the human body area as a light supplementing area.

B16, in the image light supplement device according to B13, the image brightness information includes image brightness of each pixel point in the image to be supplemented with light; the intensity calculation module is further configured to determine a scene light intensity value corresponding to the light image to be compensated according to the image brightness information; and determining the light supplement intensity information of the light area to be supplemented according to the scene light intensity value and the image brightness information.

The intensity calculation module is further configured to obtain a total number of pixels of the image to be compensated according to the image compensation apparatus described in B17 and B16; determining an image brightness median value corresponding to the image to be compensated according to the image brightness information; determining the number of pixel points of which the image brightness is greater than the image brightness median in the image to be compensated according to the image brightness information and the image brightness median; and determining the scene light intensity value corresponding to the image to be compensated according to the number of the pixel points and the total number of the pixel points.

The image light supplementing device according to B18, the intensity calculating module, and the processing module are further configured to determine an image brightness maximum value and an image brightness minimum value of each pixel point in the image to be supplemented with light according to the image brightness information; and calculating the average value of the maximum image brightness value and the minimum image brightness value, and taking the average value as the image brightness median value corresponding to the image to be supplemented with light.

The invention discloses a C19 and an image light supplement device, wherein the image light supplement device comprises: the image light supplement method comprises a processor, a memory and an image light supplement program which is stored on the memory and can run on the processor, wherein the image light supplement program is executed by the processor to realize the steps of the image light supplement method.

The invention discloses a D20 and a computer readable storage medium, wherein an image light supplementing program is stored on the computer readable storage medium, and the steps of the image light supplementing method are realized when the image light supplementing program is executed.

Claims

1. An image light supplement method, comprising:

2. A method for supplementing image light according to claim 1, wherein the type of light supplement comprises global light supplement;

3. A method for supplementing image light as claimed in claim 2, wherein the light supplementing type further comprises regional light supplementing;

and taking the human body area as an area to be supplemented with light.

4. The method for supplementing light into an image according to claim 1, wherein the image luminance information includes image luminance of each pixel in the image to be supplemented with light;

the step of determining fill light intensity information of the light region to be filled according to the image brightness information includes:

5. The method for supplementing light to an image according to claim 4, wherein the step of determining the scene light intensity value corresponding to the image to be supplemented according to the image brightness information includes:

determining an image brightness median value corresponding to the light image to be compensated according to the image brightness information;

and determining the scene light intensity value corresponding to the light image to be compensated according to the number of the pixel points and the total number of the pixel points.

6. The method for supplementing light to an image according to claim 5, wherein the step of determining the median value of the image brightness corresponding to the image to be supplemented according to the image brightness information comprises:

7. The method for supplementing light to an image of claim 4, wherein before the step of determining the supplemental light intensity information of the light region to be supplemented according to the scene light intensity value and the image brightness information, the method further comprises:

8. An image light supplement device, comprising:

9. An image fill-in light device, comprising: a processor, a memory and an image fill-in program stored on the memory and executable on the processor, the image fill-in program when executed by the processor implementing the steps of the image fill-in method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, wherein an image fill-in program is stored on the computer-readable storage medium, and when executed, the image fill-in program implements the steps of the image fill-in method according to any one of claims 1 to 7.