WO2018120519A1

WO2018120519A1 - Image processing method and device

Info

Publication number: WO2018120519A1
Application number: PCT/CN2017/080645
Authority: WO
Inventors: 王鹏
Original assignee: 华为技术有限公司
Priority date: 2016-12-26
Filing date: 2017-04-14
Publication date: 2018-07-05
Also published as: CN109804409A

Abstract

Disclosed in an embodiment of the present invention are an image processing method and device. The image processing method comprises: using a first resolution to perform processing on a first region of a target video image, the first region comprising a hot spot region of the target video image; using gradually changing resolutions to perform processing on a second region of the target video image, the gradually changing resolutions being lower than the first resolution, wherein the closer an image portion in the second region is to the hot spot region, the higher the corresponding resolution of the image portion, the second region is located outside the first region, and the second region and the first region constitute the target video image; and transmitting the processed target video image to a player terminal. The embodiment of the present invention enables more useful video data to be transmitted to a player terminal of a user.

Description

Image processing method and device

Technical field

The present invention relates to the field of image processing, and more particularly to a method and apparatus for image processing.

Background technique

The Content Delivery Network (CDN) is a network built on the existing transport network. The CDN relies on the edge servers deployed in various places, through the load balancing, content distribution, scheduling and other functional modules of the central platform. Users get the content they need, reduce network congestion, and improve user access response speed and hit rate. The technical architecture for transmitting video by CDN is as shown in FIG. 1. First, the network server uploads the video file to the file server, and then the file server distributes the video file to multiple content distribution networks, and finally, the user passes the playback terminal. Get or watch videos from their respective distribution networks.

Although the CDN method solves the problem of transmission and distribution of video, when the amount of data of the video is too large, in the case where the transmission bandwidth is small or limited, the user may have problems such as video jamming during the process of watching the video. Users can't get a better viewing experience.

Summary of the invention

Embodiments of the present invention provide a method and apparatus for image processing, which can process a video image of a target video with a limited transmission bandwidth, and reduce the data amount of the target video while providing a better viewing experience for the user, which is more useful. The video data is transmitted to the user's playback terminal.

A first aspect of the embodiments of the present invention provides a method for image processing, including:

Processing a first region of the target video image at a first resolution, the first region including a hotspot region of the target video image;

Processing a second region of the target video image with a gradient resolution that is less than the first resolution, wherein the second region is closer to the hotspot region The higher the resolution corresponding to the image, the second area is located outside the first area, and the second area and the first area constitute the target video image;

The processed target video image is sent to the playback terminal.

Specifically, the hotspot area of the target video image is a focused area of the user's line of sight, that is, a certain area that the user pays attention to or is interested in. The hotspot area may be, for example, a ball in a ball game, specifically, soccer, volleyball, basketball, etc. It can be a singer in a concert, specifically a singer's face, a participant in a meeting, and so on.

In the embodiment of the present invention, the target video image area may be divided into the first area and the second area according to the hotspot area, so that the hotspot area is in the first area, and then the first area is processed at the first resolution to be gradual The resolution processes the second area, and finally sends the processed target video image to the user's playing terminal, wherein the first resolution is greater than all resolutions of the second area, and the resolution of the second area follows the hotspot area The distance is increased, and the resolution is reduced. In the case of the same bandwidth, the resolution of the hotspot area is higher by processing the video image, and the resolution of other areas is lower, and the data amount of the processed video image is smaller than The amount of data of the original video image, the useful video data, that is, the video data that the user wants to watch, is transmitted to the user's playing terminal to ensure the user's viewing experience and save bandwidth costs.

In a first possible implementation manner of the first aspect, before the processing, by the first resolution, the first region of the target video image, the method further includes: determining a hotspot region of the target video image; Determining a first region and the second region of the target video image.

With reference to the first possible implementation manner of the first aspect, in a second possible implementation, the determining, by the hotspot region, the first region of the target video image includes: determining a center of the hotspot region; An area having a center of the center and a radius of the first predetermined distance is determined as the first area of the target video image.

In conjunction with the first possible implementation of the first aspect, in a third possible implementation, the determining, by the hotspot region, the first region of the target video image includes: a minimum of the hotspot region to be included The regular graphics area is determined to be the first area of the target video image. Specifically, the minimum regular pattern area includes, but is not limited to, a circular area, a rectangular area, and a diamond shaped area.

In a fourth possible implementation manner of the first aspect, before the processing, by the first resolution, the first area of the target video image, the method further includes: determining a transmission bandwidth with the play terminal; The area size of the first area, the area size of the second area, and the transmission bandwidth determine the resolution of the first resolution and the gradation. Specifically, the transmission bandwidth between the target and the playback terminal may be determined according to the target image acquisition request sent by the user through the playback terminal, for example, the bandwidth data is carried in the target image acquisition request; and the playback terminal may be determined according to the access bandwidth of the playback terminal. The transmission bandwidth of the terminal, wherein the access bandwidth of the terminal is the actual network bandwidth of the user; and the transmission bandwidth between the terminal and the playback terminal may also be determined according to the effective bandwidth that the transmission network can provide.

With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation, the determining, according to the area size of the first area, the area size of the second area, and the transmission bandwidth The resolution of the gradation includes determining a resolution of a target image position in the second region according to a distance between a target image position in the second region and a center of the hot spot region.

With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation, the determining, according to a distance between a target image location in the second region and a center of the hotspot region, The resolution of the target image position in the second region includes: obtaining a distance between the target image position in the second region and a center of the hot spot region; determining a target image position in the second region according to a gradation function The resolution, wherein the gradient function is a function that characterizes a correspondence between the resolution and the distance. Specifically, the distance may be in units of centimeters, inches, pixels, and the like.

With reference to the fifth possible implementation of the first aspect, in a seventh possible implementation, the second area includes a third area and a fourth area, where the third area and the hotspot area a shortest distance between the centers is smaller than a shortest distance between the fourth region and a center of the hotspot region; the determining is based on a distance between a target image location in the second region and a center of the hotspot region The resolution of the target image position in the second region includes: acquiring a distance between a target image position in the third region and a center of the hot spot region; determining a target in the third region according to a gradation function a resolution of an image position, wherein the gradient function is a function characterizing a correspondence between the resolution and the distance; determining a second resolution as a resolution of a target image position in the fourth region Wherein the second resolution is less than or equal to a minimum resolution of a target image location in the third region, the second resolution being a fixed resolution.

With reference to the seventh possible implementation of the first aspect, in an eighth possible implementation, the second resolution is 1/N of the first resolution, and N is an integer greater than 1; The second resolution is the target in the third region 1/P of the minimum resolution of the target image position, P is an integer greater than or equal to 1.

In a ninth possible implementation manner of the first aspect, the gradation function may be a parabolic function, an elliptic function, or a one-time decreasing function, and the like, which satisfies a gradual change function of a human visual change rule.

With reference to the fifth possible implementation manner of the first aspect, in a tenth possible implementation manner, the second area includes K sub-areas, and the resolution of the gradation is a resolution that varies discretely, The resolution corresponding to the sub-region is a fixed resolution, wherein the shortest distance between the (K-1)th sub-region and the center of the hotspot region is smaller than the shortest distance between the K-th sub-region and the center of the hotspot region And K is a positive integer greater than or equal to 2; determining the resolution of the target image position in the second region according to the distance between the target image position in the second region and the center of the hotspot region includes: Obtaining a distance between a target image position in the second area and a center of the hot spot area; determining a sub-area where the target image position is located according to the distance; and corresponding to the sub-area according to the resolution The relationship determines the resolution of the target image location. Specifically, the shape of the sub-region may be a regular shape such as a circle, a rectangle, or an equilateral triangle.

With reference to the tenth possible implementation manner of the first aspect, in an eleventh possible implementation manner, the corresponding relationship between the resolution and the sub-region includes: a first sub-region of the target video image The corresponding resolution is 1/L of the first resolution or a difference between the first resolution and the first preset value, where L is an integer greater than 1.

With reference to the eleventh possible implementation manner of the first aspect, in a twelfth possible implementation, the corresponding relationship between the resolution and the sub-region further includes: a Kth of the target video image The resolution corresponding to the sub-region is 1/M of the resolution corresponding to the (K-1)th sub-region, and M is an integer greater than 1; or the resolution corresponding to the K-th sub-region of the target video image is The difference between the resolution corresponding to the (K-1)th sub-region of the target video image and the second preset value.

In a thirteenth possible implementation manner of the first aspect, the method further includes: determining a target bandwidth required for transmitting the target video image and a transmission bandwidth with the playing terminal; In the case of being greater than the transmission bandwidth, the step of processing the first region of the target video image at the first resolution is performed. Specifically, the target video image is an original target video image, that is, a target video image before processing.

In a fourteenth possible implementation of the first aspect, the resolution of the gradation comprises a resolution that varies continuously or a resolution that varies discretely.

A second aspect of the embodiments of the present invention provides an apparatus for image processing, including:

a first area processing module, configured to process, in a first resolution, a first area of the target video image, where the first area includes a hotspot area of the target video image;

a second area processing module, configured to process the second area of the target video image with a gradual resolution, the resolution of the gradation being smaller than the first resolution, wherein the distance in the second area is The higher the resolution corresponding to the image at the position closer to the hot spot region, the second region is located outside the first region, and the second region and the first region constitute the target video image;

And a sending module, configured to send the processed target video image to the playing terminal.

The apparatus for image processing provided by the second aspect of the present invention further includes other program modules for performing the image processing method provided by the first aspect of the embodiments of the present invention, and details are not described herein again.

A third aspect of the embodiments of the present invention provides an apparatus for image processing, including a processor, a memory, and a communication interface, wherein the processor, the memory, and the communication interface are connected to each other, wherein the communication interface is configured to receive And transmitting data for storing an application code supporting the image processing apparatus for performing the above method, the processor being configured to perform the various methods of the first aspect described above.

A fourth aspect of the embodiments of the present invention provides a computer storage medium for storing computer program instructions for use in the apparatus for image processing described above, comprising a program for performing the above first aspect.

A fifth aspect of the embodiments of the present invention provides a computer program for performing the various methods provided by the above first aspect.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the drawings to be used in the embodiments of the present invention or the background art will be described below.

1 is a technical architecture diagram of content distribution using a CDN in the prior art;

2 is a schematic structural diagram of a system for performing live video broadcast according to an embodiment of the present invention;

3 is a schematic flowchart of a method for image processing according to an embodiment of the present invention;

4a is a target video image of an undistinguished hotspot area and a non-hotspot area provided by an embodiment of the present invention;

FIG. 4b is a target video image after distinguishing a hot spot area according to an embodiment of the present invention; FIG.

FIG. 5 is a schematic diagram of a relationship between a hot spot area, a first area, and a second area according to an embodiment of the present invention;

FIG. 5b is a schematic diagram of another hotspot area, a first area, and a second area according to an embodiment of the present invention;

FIG. 5c is a schematic diagram of another relationship between a hot spot area, a first area, and a second area according to an embodiment of the present invention;

6 is a distribution diagram of a first area and a second area according to an embodiment of the present invention;

FIG. 7a is still another distribution diagram of a first area and a second area according to an embodiment of the present invention; FIG.

FIG. 7b is still another distribution diagram of the first area and the second area provided by the embodiment of the present invention; FIG.

FIG. 8a is still another distribution diagram of a first area and a second area according to an embodiment of the present invention; FIG.

FIG. 8b is still another distribution diagram of the first area and the second area provided by the embodiment of the present invention; FIG.

FIG. 9a is a target video image before processing according to an embodiment of the present invention; FIG.

FIG. 9b is a processed target video image according to an embodiment of the present invention; FIG.

FIG. 10 is a schematic structural diagram of an apparatus for image processing according to an embodiment of the present invention; FIG.

FIG. 11 is a schematic structural diagram of another apparatus for image processing according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

The solution of the embodiment of the present invention is applicable to a system structure for performing video collection, production, and transmission. For example, a system structure for performing live video broadcast, as shown in FIG. 2, includes a video collection end 101 and a video splicing server 102. The network server 103, the transmission distribution network 104, and the playback terminal 105. In the system structure diagram shown in FIG. 2, in the video live broadcast process, the video collection end 101 is configured to capture various initial video images, such as live video images, and send the collected video images to the video splicing server 102. The video capture end 101 can be, for example, a camera, a camera, etc.; the video splicing server 102 is used to capture the video image collected by the video capture end 101. Perform editing processing such as editing, encoding, etc. to generate a target video, and send the target video to the web server 103; the web server 103 is a background server of the video website, the background server may also be called a cloud server, and the web server 103 distributes the target video to the transmission distribution network. The transmission distribution network 104 includes a plurality of cache servers/streaming servers, and the transmission distribution network 104 distributes the target video to the respective playback terminals 105. The transmission distribution network 104 can be, for example, a CDN, and the playback terminal can be, for example, a mobile phone or a virtual reality. (English: Virtual Reality, VR) Devices, tablets, etc. that can be used to play video.

Specifically, the video may be a VR video or a normal video.

The system structure shown in FIG. 2 can transmit the original target video to the user's play terminal. Based on the system structure shown in FIG. 2, the image processing method provided by the embodiment of the present invention can be implemented, where the video stitching server can be executed. The step of processing the original target video image, wherein the original target video image may be any one of the target video images, the step specifically comprising: performing the first region of the target video image at the first resolution. Processing, processing the second area of the target video image with a gradual resolution, or performing the processing of the target video image by a cache server/streaming server in the transmission distribution network, and also in the system Adding an image processing node to the structure to perform the step of processing the target video image, for example, adding an image processing server to perform processing on the target video image in the transmission distribution network; and then processing by the transmission distribution network After the target video image is sent to the user's end of play Thus data amount of each frame of video decreases the target video image, saving transmission bandwidth, the terminal displays the video data useful to the user.

It should be noted that the image processing method provided by the embodiment of the present invention may also be performed by two or more servers in the foregoing system structure, and no further enumeration is made herein.

In a possible implementation manner, the system structure shown in FIG. 2 may also be a schematic structural diagram of a system for performing video on demand. At this time, the video splicing server 102 sends the target video to the network server 103, and the network server 103 After the target video is distributed to the plurality of transmission distribution networks 104, the target video may be cached or stored in the cache server/streaming server for a period of time, and when the user needs to view the target video, then the playback terminal is used to the network server. Initiating a target video acquisition request, and then the network server returns the address of the cache server/streaming server closest to the playing terminal to the playing terminal, and the playing terminal accesses the cache server/streaming server closest to the playing terminal according to the address to view the target. Video, at this time, the step of processing the target video image may be performed by a cache server/streaming server in the transmission distribution network, or an image processing server may be added to the transmission distribution network to perform the target video image. The steps of processing.

It should be understood that the image processing method provided by the embodiment of the present invention is applicable to other system structures related to video image transmission, in addition to the system structure shown in FIG.

Referring to FIG. 3, FIG. 3 is a schematic flowchart diagram of a method for image processing according to an embodiment of the present invention. The method of the present invention may be implemented on the server mentioned above, where the server specifically includes a video splicing server and a cache server/flow. At least one of a media server and an image processing server, the method including but not limited to the following steps:

Step S201: processing a first area of the target video image with a first resolution, where the first area includes a hotspot area of the target video image.

The hotspot area is the focus area of the user's line of sight, that is, compared with other areas of the target video image, the hotspot area is an area where the user is more concerned or interested, and the area that the user desires to see more clearly.

Optionally, before performing step S201, a hotspot area of the target video image may also be determined and according to the hotspot The region determines a first region and a second region of the target video image.

Specifically, for example, if the target video image is a video image of a soccer game live video, the area where the soccer ball is located may be determined as a hot spot area or a face area of a certain player may be determined as a hot spot area; and the target video image is sung A video image of a live video can be used to determine the area where the singer's face is located as a hotspot area or the area where the singer's body is located as a hotspot area; and if the target video image is a large conference, such as a target The video image is a video image of a national conference, and the face of the speaker or the area where the body is located can be determined as the hotspot area.

For example, referring to FIG. 4a and FIG. 4b, FIG. 4a is a target video image that does not distinguish between a hot spot area and a non-hot spot area, and FIG. 4b is a target video image after distinguishing the hot spot area, wherein FIG. 4a is a video image of a basketball game video. In the image, there are images such as players, stadiums, basketball baskets, basketballs, etc. In Figure 4b, the image images defined by the white areas, that is, the image images corresponding to the basketballs are hotspots, and the image images of the black areas are corresponding to the areas outside the basketball. The image image is a non-hot spot area.

Optionally, the hot spot region of the target video image may be determined according to the image-based target recognition method, wherein the image-based target recognition method may be a feature-based target detection method or a texture-based and boundary feature-based target Detection method.

Optionally, when a class-based feature detection method is adopted, a Haar-like feature can be adopted, and the Haar-like feature is a simple rectangular feature, which is named after a Haar wavelet (English: Haar wavelet). A grayscale change that reflects the local features of the detected object. For example, by extracting the Haar-like feature of the to-be-identified region of the target video image, wherein the to-be-identified region includes the hotspot region and the non-hotspot region, and then obtaining the feature values of the to-be-identified region, and then using the AdaBoost (English: Adaptive Boosting) algorithm to perform these features. The values are categorized to determine the hotspot area.

Optionally, when the target detection method based on texture and boundary features is adopted, the features of the pixel points are extracted by using a Harris operator, a Forstner operator, a Moravic operator, etc., and then clustering operations are performed to form different categories. Characteristics.

In an optional manner, when determining the first area and the second area according to the hot spot area, the center of the first area may coincide with the center of the hot spot area, so that the hot spot area is located at an intermediate position of the first area.

In a possible implementation manner, in a case where the shape of the hot spot area is irregular, the first area and the second area may be determined in at least two manners: 1) the center of the hot spot area may be determined, and the center is to be Determining, as a first region of the target video image, a region having a radius of a center and a first predetermined distance, wherein the first predetermined distance radius is greater than a maximum distance between a center of the hot spot region and an edge of the hot spot region, and correspondingly The area outside the first area is the second area; 2) the minimum regular graphic area including the hot spot area may be determined as the first area of the target video image, wherein the minimum rule graphic may be a circle or a rectangle A shape area such as a triangle, a diamond, or the like, and correspondingly, a region outside the first area is the second area.

Specifically, the unit of the first preset distance may be an image distance unit of centimeters, inches, pixels, etc., and the first preset distance may be set according to the length and width of the total area of the target video image, for example, the length of the total area is 1 /2, 1/3, etc.; may also be set according to the longest distance between the center of the hot spot area and the edge of the hot spot area, for example, the sum of the longest distance and a preset threshold, specifically, a preset threshold, for example The distance is 1 unit.

Optionally, the size of the first area may be a fixed setting, or may be set by the user, for example, the user will The first predetermined distance is set to 2 cm, and it is determined that the first area is a circular area with a center of the hot spot area as a center and a radius of 2 cm, and the area of the first area is 4π square centimeter.

In another possible implementation manner, in a case where the shape of the hot spot area is a regular figure, in addition to determining the first area and the second area by using the above two manners, the hot spot area may be directly determined as the first area. Correspondingly, the area outside the first area is the second area.

The following example illustrates how the first region and the second region are determined according to the hotspot region. Referring to Figures 5a-5c, it is assumed that the target video image of the hotspot region is determined as shown in Figure 4b. FIG. 5a is a schematic diagram of a relationship between a hot spot area, a first area, and a second area according to an embodiment of the present invention. In FIG. 5a, the first area is centered on the center of the hot spot area, and the first preset distance is a circular area of a radius, the hotspot area is in the first area, and the area outside the first area is the second area; FIG. 5b is another hotspot area, the first area, and the second area provided by the embodiment of the present invention. A schematic diagram of the relationship, in FIG. 5b, the first area is the smallest square area including the hotspot area, the center of the first area and the center of the hot spot area coincide, and the area outside the first area is the second area; FIG. 5c is provided by the embodiment of the present invention. Another schematic diagram of the relationship between the hot spot area, the first area, and the second area; in FIG. 5c, the first area and the hot spot area coincide, and the area outside the hot spot area is the second area.

Optionally, before the step S201 is performed, the transmission bandwidth between the playback terminal and the target bandwidth required for transmitting the target video image may be determined. If the target bandwidth is greater than the transmission bandwidth, step S201 is performed; and the target bandwidth is smaller than the transmission. In the case of bandwidth, the target video image is not processed, and the unprocessed/original target video image is directly transmitted to the playback terminal.

Optionally, the transmission bandwidth can be determined in at least the following ways:

1) In the case that the bandwidth resource of the server is not limited, the access bandwidth of the playback terminal is determined as the transmission bandwidth, that is, the actual bandwidth of the user is determined as the transmission bandwidth;

2) In the case that the bandwidth resource of the server is not limited, the bandwidth indication sent by the user through the playing terminal is received, and the transmission bandwidth is determined according to the bandwidth indication, that is, the bandwidth specified by the user is determined as the transmission bandwidth; for example, the current connection of the user is assumed. The inbound bandwidth is 20M, but the user does not want all the bandwidth to be used to transmit the target video image. The user only wants to use 10M bandwidth to transmit the target video image. The user can set the playback bandwidth to 10M on the playable terminal, and the playback terminal will bandwidth. The indication is set to 10M, and after receiving the bandwidth indication, the server determines 10M as the transmission bandwidth.

3) In the case that the bandwidth resource of the server is limited, the current free bandwidth of the server is determined according to the bandwidth resource allocation of the server, and then part of the bandwidth of the idle bandwidth is determined to be between the playback terminal and the terminal according to a certain bandwidth allocation rule. Transmission bandwidth, in which case the transmission bandwidth is less than or equal to the access bandwidth of the playback terminal.

Step S202: processing a second region of the target video image with a gradient resolution, the resolution of the gradient being smaller than the first resolution, wherein the second region is closer to the hotspot region The higher the resolution corresponding to the image at the location, the second region is outside the first region, and the second region and the first region constitute the target video image.

Specifically, the resolution of the first resolution and the gradation may be determined according to a transmission bandwidth with the playback terminal.

In a possible implementation, the first resolution may be determined according to the transmission bandwidth, the size of the area of the first area, and the size of the area of the second area, according to the location between the target image location in the second area and the center of the hotspot area. The correspondence between the distance and the resolution determines the resolution of the target image position.

Specifically, the size of the area of the first area and the second area may be measured by area or by area The total number of pixels is measured.

Wherein, the resolution in the second region satisfies the condition that the closer the image position is to the hot spot region, the higher the resolution is, the at least the following resolution change rules may be set for the second region: 1) The resolution of the two regions changes continuously, and there is a function correspondence between the resolution and the distance, wherein the distance refers to the distance between the target image position of the second region and the center of the hot spot region, and the distance is larger. The smaller the function value is; 2) the resolution of the second region varies discretely, wherein the second region is divided into a plurality of sub-regions, the resolution in the sub-region is fixed, and the different sub-regions correspond to different resolutions. The farther the sub-area from the center of the hot spot area, the lower the corresponding resolution; 3) the resolution of the second area changes continuously in a part of the second area, and the other part of the second area is discrete Variety.

Specifically, the gradation function between the resolution and the distance may be a functional relationship such as a parabolic function, an elliptic function, or a decremental function that conforms to changes in the human visual.

Several variations of the resolution of the gradation in the second region are specifically described below, and a method of determining the resolution of the first resolution and the gradation is introduced in conjunction with the variation rule of the resolution of the second region.

It should be noted that the resolution of the first resolution and the gradation determined in the following scenarios refers to the resolution per unit area. If it is necessary to determine the total resolution of a certain area of the target video image, the resolution on a unit area is determined. The rate is multiplied by the corresponding area to get the total resolution of a certain area.

It should be noted that, in the following scenarios, the center of the first area is the center of the hotspot area. In the alternative, the center of the first area may not be consistent with the center of the hotspot area.

Implementation scenario 1: The resolution of the second region changes continuously, wherein there is a function correspondence between the resolution and the distance.

In this implementation scenario, the distance can be used as the argument of the gradual function, the resolution is used as the dependent variable of the gradual function, and the dependent variable and the independent variable satisfy the decreasing correspondence, that is, the dependent variable increases with the independent variable. If you decrease, you can use the decreasing function as the gradient function between resolution and distance.

Specifically, the size of the first area may be first determined, and the maximum radius of the second area is determined, where the maximum radius refers to the maximum distance between the center of the hot spot area and the edge of the second area, and then the transmission bandwidth is determined according to the transmission bandwidth. The resolution determines the first resolution according to the principle that the total number of pixels is consistent and the gradient function, and determines the resolution at each distance according to the gradient function of the distance and the resolution, wherein the total number of pixels is consistent, the pointer is the same as the size of the region. The target video image, the target video image before the resolution change contains a total amount of pixels equal to the total number of pixels included in the target video image after the resolution change.

Let's take a function as a decrement function as an example to introduce the specific process.

For example, the distribution of the first area and the second area is as shown in FIG. 6. FIG. 6 is a distribution diagram of the first area and the second area, wherein the shape of the first area is circular, the radius is d1, and the first resolution is The rate is R1, the second area is a gray area outside the first area, the resolution function of the second area is R2=R1-(x-d1), and the resolution corresponding to the transmission bandwidth is R0. It should be noted that the present invention The resolution R0 described in the embodiment refers to the resolution corresponding to the transmission bandwidth, that is, the transmission bandwidth can support the resolution of the transmitted target video image per unit area when the playback is not stuck, and at the same time, In the case of explicit explanation, R1, R0, and R2 all refer to the resolution per unit area.

First, the second area is placed in a ring composed of two concentric circles centered on the center of the hot spot area, as shown in FIG. 6, in which case the radius of the circle 1 is the center of the hot spot area and the second area. Minimum distance of the boundary, circle 1 Coincident with the first region, the radius of the circle 1 is d1, the circle 2 is the smallest circle containing the second region, and the radius d2 of the circle 2 is the maximum distance between the center of the hot spot region and the boundary of the second region, according to the total pixel point The principle of quantity constant, in this case, the principle that the total number of pixels is constant is that the sum of the total number of pixels of circle 1 and the total number of pixels of the ring is equal to the total number of pixels of circle 2, and the formula is obtained:

Where (πd1 ² )*R1 is the total number of pixels of circle 1,

The total number of pixels of the circle, R0*(πd2 ² ) is the total number of pixels of the circle 2.

Then push back to get R1, R1=(R0*d2 ² +1/3d1 ³ -2/3d2 ³ -d2 ² d1)/d2 ²

According to the above formula, according to R0, d1 and d2, the first resolution R1 can be determined, and then the resolution function of the second region is obtained according to the formula R2=R1-(x-d1) is R2=(R0*d2 ² +1/ 3d1 ³ -2/3d2 ³ -d2 ² d1)/d2 ² -x+d1, obtain the distance x between the target position image on the second area and the center of the hot spot area, and take the value of x to determine the target position image Resolution.

Specifically, d1, d2 may be obtained after determining the first area and the second area.

Specifically, R0 can be obtained according to the transmission bandwidth, assuming that the area of the target video image is 5 inches, and the resolution corresponding to the transmission bandwidth is 1080P, wherein 1080P includes 1280*720 pixels, then R0=1280*720/5, R0 The unit is pixels/inch.

It should be understood that the above examples are only used to explain the embodiments of the invention, and should not be construed as limiting. The resolution function of the second region may also be other functions, wherein the resolution function is a linear function (R2=kx+b, k and When b is a constant), the value of k is not limited to 1, and the shape of the first region may be other shapes.

Implementation scenario 2: the resolution of the second region varies discretely, and the second region has K sub-regions, wherein the shortest distance between the (K-1)th sub-region and the center of the hotspot region is smaller than the K-th sub-region The shortest distance from the center of the hot spot area, that is, visually, the Kth sub-area is outside of the (K-1)th sub-area or surrounds the (K-1)th sub-area.

In a possible implementation manner, in a possible implementation manner, in order to facilitate determining the resolution of each sub-region, the resolutions of the respective sub-regions may be correlated, so that the resolution between the sub-regions is regular. The change, for example, the resolution of the (K-1)th sub-region of the Kth sub-region is 1/M, M is an integer greater than 1, and the resolution of the K-th sub-region is the resolution of the (K-1)th sub-region. The rate is subtracted from the second preset value; then the resolution of the sub-region closest to the center of the hot spot region among the K sub-regions is determined, that is, the resolution of the first sub-region is determined.

In an alternative, the resolution of the first sub-region is 1/L of the first resolution or the first resolution minus the first preset value, where L is an integer greater than 1.

Optionally, L and M may be set equal or different; the first preset value and the second preset value may be set equal to each other, or may be unequal.

In another possible implementation manner, the resolutions of the sub-areas may not be associated, that is, the resolution of each sub-area is irregular, and each sub-area may be associated with the first resolution. For example, the resolution of the first sub-region is the first resolution minus the first preset value, the resolution of the second sub-region is the second resolution minus the second preset value, and the resolution of the third sub-region is The resolution of the first resolution is 1/L...the Kth sub-region is the first resolution 1/M, here only as an example, in addition, each sub-region needs to satisfy the condition that "the farther away from the hot spot region, the lower the corresponding resolution is."

Alternatively, the first resolution may also be replaced with a preset fixed resolution smaller than the first resolution.

The resolution relationship between the above two sub-regions and the resolution of each region are determined by referring to the respective sub-regions of the first region and the second region.

For example, the distribution of the first area and the second area is as shown in FIG. 7a, and FIG. 7a is another distribution diagram of the first area and the second area, wherein the first area has a circular shape with a radius of d1; A resolution is R1, the second area is a gray area outside the first area, and the second area has three sub-areas, and the first sub-area is closest to the first area, and is a ring having an inner ring radius of d1. The ring radius is d2; the second sub-region is adjacent to the first sub-region, and is also a ring, the inner ring radius is d2, the outer ring radius is d3; the third sub-region is outside the second sub-region, the target video image is The area is S, and the resolution corresponding to the transmission bandwidth is R0.

In the case where the resolution of the first sub-region is 1/L of the first resolution and the resolution of the K-th sub-region is 1/M of the resolution of the (K-1)th sub-region, both L and M are assumed The value is 2, according to the principle that the total number of pixels is constant, in this case, the principle that the total number of pixels does not change is that the sum of the total number of pixels of the first region and the second region is equal to the total pixel of the video image. The amount, the sum of the total number of pixels in each sub-area is equal to the total number of pixels in the second area, and the formula is obtained:

(πd1 ² )*R1+1/2(πd2 ² -πd1 ² )*R1+1/4(πd3 ² -πd2 ² )*R1+1/8(S-πd3 ² )*R1=R0*S

Where (πd1 ² )*R1 is the total number of pixel points in the first region, 1/2(πd2 ² -πd1 ² )*R1 is the total number of pixel points in the first sub-region, 1/4 (πd2 ² -πd1 ² *R1 is the total number of pixels in the second sub-region, 1/8 (S-πd3 ² )*R1 is the total number of pixels in the third sub-region, and R0*S is the total number of pixels in the entire target video image.

Then push back to get R1, R1=(R0*S)/(1/2πd1 ² +1/4πd2 ² +1/8πd3 ² +1/8S)

According to the above formula, the first resolution R1 can be determined according to R0, d1, d2, d3, and S, and the resolution of each sub-area is determined according to the relationship between each sub-area and R1, and the resolution of the first sub-area is 1/1 2R1, the resolution of the second sub-area is 1/4R1, and the resolution of the third sub-area is 1/8R1.

Specifically, d1, d2, and d3 may be default distances, or may be set by the user, and d1, d2, and d3 may change regularly, such as d1=1/2d2, d2=1/2d3, and d3 is the target. Half the width of the video image, etc.

The resolution of the first sub-region is the first resolution minus the first preset value, and the resolution of the K-th sub-region is the resolution of the (K-1)th sub-region minus the second preset value. Assuming that the first preset value and the second preset value are both r, according to the principle that the total number of pixel points does not change, in this case, the principle that the total number of pixel points does not change is the pixel points of the first region and the second region. The sum of the total amounts is equal to the total number of pixels of the video image, and the sum of the total number of pixels of each sub-area is equal to the total number of pixels of the second area, and the formula is obtained:

(πd1 ² )*R1+(πd2 ² -πd1 ² )*(R1-r)+(πd3 ² -πd2 ² )*(R1-2r)+(S-πd3 ² )*(R1-3r)=R0*S

Where (πd1 ² )*R1 is the total number of pixel points in the first region, and (πd2 ^{2 -} πd1 ² )*(R1-r) is the total number of pixel points in the first sub-region, (πd3 ^{2 -} πd2 ² )* (R1-2r) is the total number of pixel points in the second sub-region, (S-πd3 ² )*(R1-3r) is the total number of pixel points in the third sub-region, and R0*S is the pixel point of the entire target video image. Total amount.

Then, R1 is obtained, and R1=(R0*S+3r*S-πd1 ² *r-πd2 ² *r-πd3 ² *r)/S.

According to the above formula, the first resolution R1 can be determined according to R0, d1, d2, d3, S, and r, and the resolution of each sub-area is determined according to the relationship between each sub-area and R1, and the resolution of the first sub-area is R1-r, 2nd The resolution of the sub-area is R1-2r, and the resolution of the third sub-area is R1-3r.

For another example, the distribution of the first area and the second area is as shown in FIG. 7b, and FIG. 7b is another distribution diagram of the first area and the second area, wherein the first area has a rectangular shape and the area is S1, the first The resolution is R1, the second area is a gray area outside the first area, the second area has three sub-areas, and the distance between the first sub-area and the second area is the closest, which is a rectangle, the area is S2, and the second sub-area The first sub-region is adjacent to each other, and has a rectangular shape, the area is S3, and the third sub-region is outside the second sub-region, the area of the target video image is S, and the resolution corresponding to the transmission bandwidth is R0.

It is assumed that the resolution of the first sub-area is 1/2 of the first resolution, the resolution of the second sub-area is 1/3 of the first resolution, and the resolution of the third sub-area is 1/ of the first resolution. 4. According to the principle that the total number of pixel points does not change, in this case, the principle that the total amount of pixel points does not change is that the sum of the total number of pixel points of the first area and the second area is equal to the total number of pixel points of the entire video image, and each The sum of the total number of pixels in the sub-area is equal to the total number of pixels in the second area, and the formula is obtained:

S1*R1+S2*1/2R1+S3*1/3R1+(S-S3-S2-S1)*1/4R1=R0*S.

Where S1*R1 is the total number of pixels in the first region, S2*1/2R1 is the total number of pixels in the first sub-region, and S3*1/3R1 is the total number of pixels in the second sub-region, (S- S3-S2-S1)*1/4R1 is the total number of pixels of the third sub-region, and R0*S is the total number of pixels of the entire target video image.

Then push back R1, R1=(R0*S)/(3/4S1+1/4S2+1/12S3+1/4S)

According to the above formula, the first resolution R1 can be determined according to R0, S1, S2, S3, S4, and S, and further the resolution 1/2R1 of the first sub-region and the resolution 1/3R1 of the second sub-region are determined. The resolution of the 3 sub-regions is 1/4R1.

Specifically, S1, S2, S3, and S4 may be set as defaults, or may be set by a user, and will not be discussed here.

It should be understood that the above examples are only used to explain the embodiments of the invention, and should not be construed as limiting. The second area may further include a plurality of sub-areas, for example, the second area includes 4 sub-areas, 5 sub-areas, etc., and the shape of each sub-area It is not limited to the above-mentioned circular and rectangular shapes, and the resolution of each sub-area may have other variations.

In this implementation scenario, the distance between the target image location of the second region China and the center of the hotspot region may be first obtained, and the sub-region where the target image location is located is determined according to the distance, and then according to the resolution and the sub-region The correspondence between the target image positions is determined, for example, determining that the target image position is located in the first sub-region, and the resolution of the first sub-region is the resolution of the target image position.

Implementation scenario 3: The resolution of the second region changes continuously in a portion of the target video image, and varies discretely in another portion of the target video image.

In this implementation scenario, for the region that changes continuously, the resolution of each target image location may be determined by referring to the solution in the foregoing implementation scenario 1. For the region that varies discretely, refer to the scenario of the foregoing embodiment. The scheme determines the resolution of each sub-region, and further determines the resolution of the target image location. Specifically, in which sub-region the target image location is located, the resolution of the target image location is the resolution of the current sub-region.

The following describes an example of implementing the scenario 3, as shown in FIG. 8a. FIG. 8a is another distribution diagram of the first region and the second region, wherein the first region has a circular shape and a radius of d1. One resolution is R1, the second area is a gray area outside the first area, the second area has two areas, and the second area includes a third area and a fourth area, wherein the third area is a ring, the inner ring The radius is d1 and the outer ring radius is d2. The resolution of the third region changes continuously. The resolution function of the third region is R2=R1-(x-d1), and the fourth region is outside the third region. The area includes two sub-areas, A area and B area respectively. The A area is adjacent to the third area. The radius of the ring in the A area is d2, the radius of the outer ring is d3, and the area B is outside the area A. The resolution of the A area is assumed. 1/2 of the minimum resolution of the third region, The resolution of the B area is 1/3 of the minimum resolution of the third area, the area of the target video image is S, and the resolution corresponding to the transmission bandwidth is R0.

According to the principle that the total number of pixel points does not change, in this case, the principle that the total number of pixel points does not change is that the sum of the total number of pixel points of the first region, the third region, and the fourth region is equal to the total number of pixels of the entire video image. The sum of the total number of pixels in the A area and the B area is equal to the total number of pixel points in the fourth area, and the formula is obtained:

Where (πd1 ² )*R1 is the total number of pixels in the first region,

For the total number of pixels in the third region, (πd3 ² -πd2 ² )*1/2(R1-d2+d1) is the total number of pixel points in the A region, (S-πd3 ² )*1/3 (R1- D2+d1) is the total number of pixels in the B region, and R0*S is the total number of pixels of the entire target video image.

Then inversely get R1, R1=(R0*S+1/6πd2 ³ +1/3πd1 ³ -1/2πd2 ² d1-(1/6πd3 ² +1/3S)(d1-d2))/(1/2πd2 ² +1/6πd3 ³ +1/3S-πd1 ² )

According to the above formula, the first resolution R1 can be determined according to R0, d1, d2, d3, and S, thereby determining the resolution function of the third region, the resolution of the A region, and the resolution of the B region.

In an alternative embodiment, the profile of FIG. 8b can also be changed as shown in FIG. 8b, and FIG. 8b is another distribution diagram of the first region and the second region, wherein the shape of the first region is a circle and a radius For d1, the first resolution is R1, the second area is a gray area outside the first area, the second area has two areas, and the second area includes a fifth area and a sixth area, wherein the fifth area includes two sub- The area is A area and B area respectively. The inner ring radius of area A is d1, the outer ring radius is d2, the inner ring radius of B area is d2, the outer ring radius is d3, and the resolution of the fifth area is discrete. The resolution of the A area is 1/2 of the minimum resolution of the fifth area, the resolution of the B area is 1/3 of the minimum resolution of the fifth area; the sixth area is outside the fifth area, and the sixth area is The resolution function is R2=1/3*R1-(x-d1), the area of the target video image is S, and the resolution corresponding to the transmission bandwidth is R0.

For the method of calculating R1, refer to the above-mentioned scheme, and R2 can be further obtained after calculating R1, and details are not described herein again.

It should be understood that the above examples are only used to explain the embodiments of the invention, and should not be construed as limiting. The resolution function of the second region may also be other functions. The shape of the first region may also be other shapes, and the second region has other The way of division.

It should be noted that the foregoing implementation scenarios are only partially reflected in the resolution change rule of the second region. In the alternative, other resolution change rules may also be used, for example, in the foregoing implementation scenario III. The sub-areas are refined to have a continuous or discrete change in resolution, which is not enumerated here.

According to the solution mentioned above, the corresponding resolution can be determined by the transmission bandwidth, and the correspondence between the resolution of the first resolution and the gradient and the distance can be obtained according to the principle of the total number of pixels, thereby determining the second region. The position of the image at various distances.

After determining the resolution at each distance, the distance between the target image position and the center of the hot spot region can be obtained, the target resolution at the distance is determined, and the image image of the target image position is processed at the target resolution.

Step S203: Send the processed target video image to the playing terminal.

Specifically, the processed target video image is visually different from the original target video image, the original target The sharpness of the image of each region of the target video image is the same, the sharpness of the image of the first region of the processed target video image is higher than the sharpness of the image of the second region, and the image of the second region The image image that is farther away from the first region has a lower resolution.

Specifically, according to different resolution change rules adopted in the process, the clear changes of the target video image are different, and the visual representation thereof is also different, and the image image closer to the center of the hot spot region has higher definition.

The following is an example of the target video image before processing and the processed target video image.

See Figures 9a-9b. Fig. 9a is a target video image before processing, and the sharpness of the image screen at each position of the target video image before processing is the same. FIG. 9b is a processed target video image. If the adopted resolution change rule corresponds to the implementation scenario 2 in the above step S203, for example, the processed target video image has four levels, wherein the innermost layer is the image of the first region. The picture is the clearest, the image of the second layer, that is, the image of the first sub-area is lower than the resolution of the image of the innermost layer, and the image of the third layer, that is, the image of the second sub-area, is lower than that of the second layer. The sharpness of the image picture, the sharpness of the image image of the outermost layer, that is, the third sub-area, is lower than the sharpness of the image picture of the third layer.

Specifically, for the target video, if the transmission bandwidth is limited, the above-mentioned processing may be performed on each frame of the target video image of the target video image, so that the image of the user's attention or interest is sufficiently clear and the resolution of the transmission bandwidth is satisfied. Rate demand.

In the method described in FIG. 3, the target video image area is divided into the first area and the second area according to the hotspot area of the target video image such that the hotspot area is in the first area, and then the first area is compared with the first area. Processing, processing the second area with a gradual resolution, and finally transmitting the processed target video image to the user's playing terminal, wherein the first resolution is greater than all resolutions of the second area, and the resolution of the second area The rate decreases with the distance from the hotspot area. In the case of the same transmission bandwidth, the resolution of the hotspot area is higher by processing the video image, while the resolution of other areas is lower, and at the same time, after processing The data amount of the video image is smaller than the data amount of the original video image, so that the useful video data, that is, the video data that the user wants to watch, can be transmitted to the user's playing terminal, thereby ensuring the user's viewing experience and saving bandwidth cost.

The above describes the method of the embodiment of the present invention in detail, and the apparatus of the embodiment of the present invention is provided below.

Referring to FIG. 10, FIG. 10 is a schematic structural diagram of an apparatus for image processing according to an embodiment of the present invention. The apparatus includes at least a first area processing module 310, a second area processing module 320, and a sending module 330. The detailed description is as follows:

a first area processing module 310, configured to process, in a first resolution, a first area of the target video image, where the first area includes a hotspot area of the target video image;

a second area processing module 320, configured to process the second area of the target video image with a gradual resolution, the resolution of the gradation being smaller than the first resolution, wherein the distance in the second area The image area corresponding to the hotspot area corresponds to a higher resolution, the second area is located outside the first area, and the second area and the first area constitute the target video image;

The sending module 330 is configured to send the processed target video image to the playing terminal.

Optionally, the device further includes:

a hotspot area determining module 340, configured to determine a hotspot area of the target video image;

The area dividing module 350 is configured to determine the first area and the second area of the target video image according to the hot spot area.

Optionally, the area dividing module 350 includes:

a central determination sub-module 351, configured to determine a center of the hotspot area;

The first area determining sub-module 352 is configured to determine an area having a center of the center and a radius of the first preset distance as the first area of the target video image.

Optionally, the area dividing module 350 is specifically configured to:

A minimum regular graphics area containing the hotspot area is determined as the first area of the target video image.

Optionally, the device further includes:

a transmission bandwidth determining module 360, configured to determine a transmission bandwidth with the playing terminal;

The resolution determining module 370 is configured to determine the resolution of the first resolution and the gradation according to an area size of the first area, an area size of the second area, and the transmission bandwidth.

Optionally, the resolution determining module 370 includes:

a first resolution determining submodule 370, configured to determine the first resolution according to an area size of the first area, an area size of the second area, and the transmission bandwidth;

The gradient resolution determining sub-module 371 is configured to determine a resolution of the target image position in the second region according to a distance between a target image position in the second region and a center of the hot spot region.

Optionally, the gradient resolution determining submodule 371 includes:

a first distance obtaining unit 3711, configured to acquire a distance between a target image location in the second region and a center of the hotspot region;

a first resolution determining unit 3712, configured to determine a resolution of a target image position in the second region according to a gradation function, wherein the gradation function is to represent a correspondence between the resolution and the distance function.

Optionally, the second area includes a third area and a fourth area, wherein a shortest distance between the third area and a center of the hotspot area is smaller than a center of the fourth area and the hotspot area The shortest distance between the shortest distances; the gradient resolution determining sub-module 371 includes:

a second distance acquiring unit 3713, configured to acquire a distance between a target image location in the third region and a center of the hotspot region;

a second resolution determining unit 3714, configured to determine a resolution of a target image position in the third region according to a gradation function, wherein the gradation function is to represent a correspondence between the resolution and the distance function;

a third resolution determining unit 3715, configured to determine the second resolution as a resolution of a target image position in the fourth region, wherein the second resolution is less than or equal to a target image in the third region The minimum resolution of the location, the second resolution being a fixed resolution.

Optionally, the second resolution is 1/N of the first resolution, N is an integer greater than 1; or the second resolution is a minimum resolution of a target image location in the third region. 1/P, P is an integer greater than or equal to 1.

Optionally, the gradation function comprises: a parabolic function, an elliptic function, and a declining function.

Optionally, the second area includes K sub-areas, the resolution of the gradation is a resolution that varies discretely, and the resolution corresponding to the sub-area is a fixed resolution, where the (K-1) The shortest distance between the sub-region and the center of the hot spot region is smaller than the shortest distance between the K-th sub-region and the center of the hot-spot region, and K is a positive integer greater than or equal to 2; the gradient resolution determination sub-module 371 include:

a third distance obtaining unit 3716, configured to acquire a target image location and the hotspot area in the second area The distance between the centers;

a sub-area determining unit 3717, configured to determine, according to the distance, a sub-area where the target image position is located;

The fourth resolution determining unit 3718 is configured to determine a resolution of the target image position according to a correspondence between the resolution and the sub-region.

Optionally, the correspondence between the resolution and the sub-region includes: a resolution corresponding to the first sub-region of the target video image is 1/L of the first resolution or the first The difference between the resolution and the first preset value, where L is an integer greater than or equal to 1.

Optionally, the mapping between the resolution and the sub-region further includes: a resolution corresponding to a Kth sub-region of the target video image is a resolution corresponding to the (K-1)th sub-region 1/M, M is an integer greater than 1; or the resolution corresponding to the Kth sub-region of the target video image is the resolution corresponding to the (K-1)th sub-region of the target video image and the second pre- Set the difference in value.

It should be noted that the implementation of each module may also correspond to the corresponding description of the method embodiment shown in FIG. 3 .

In the embodiment described in FIG. 10, the image processing server may divide the target video image area into the first area and the second area according to the hotspot area of the target video image, such that the hotspot area is in the first area, and then the first The resolution processes the first area, processes the second area with a gradual resolution, and finally sends the processed target video image to the user's playing terminal, wherein the first resolution is greater than all resolutions of the second area The resolution of the second region decreases with increasing distance from the hotspot region. In the case of the same bandwidth, the resolution of the hotspot region is higher by processing the video image, and the resolution of other regions is lower. The data amount of the processed video image is smaller than the data amount of the original video image, and the useful video data, that is, the video data that the user wants to watch, is transmitted to the user's playing terminal, thereby ensuring the user's viewing experience and saving bandwidth cost.

Referring to FIG. 11, FIG. 11 is a schematic structural diagram of another apparatus for image processing according to an embodiment of the present invention. The apparatus includes a processor 41, a memory 42, and a communication interface 43. The processor 41 is connected to the memory 42 and the communication interface 43, for example, the processor 41 can be connected to the memory 42 and the communication interface 43 via a bus.

The processor 41 is configured to support a corresponding function in the method of image processing performed by the apparatus of the image processing described in FIG. The processor 41 can be a central processing unit (CPU), a network processor (in English: network processor, NP), a hardware chip, or any combination thereof. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), and a general array logic (GAL). Or any combination thereof.

The memory 42 is used to store program codes and the like. The memory 42 may include a volatile memory (English: volatile memory), such as a random access memory (English: random access memory, abbreviation: RAM); the memory 72 may also include a non-volatile memory (English: non-volatile memory) For example, read-only memory (English: read-only memory, abbreviation: ROM), flash memory (English: flash memory), hard disk (English: hard disk drive, abbreviation: HDD) or solid state drive (English: solid-state drive , abbreviation: SSD); the memory 42 may also include a combination of the above types of memories.

Communication interface 43 is used to receive and transmit data.

The processor 41 can invoke the program code to perform the following operations:

Processing a second region of the target video image with a gradient resolution that is less than the first resolution, wherein an image location in the second region that is closer to the hotspot region The higher the corresponding resolution, the second area is located outside the first area, and the second area and the first area constitute the target video image;

The processed target video image is transmitted to the playback terminal through the communication interface 43.

Optionally, before processing, by the processor 41, the first area of the target video image at a first resolution, the processor 41 is further configured to:

Determining a hot spot area of the target video image;

Determining a first region and the second region of the target video image based on the hotspot region.

Optionally, the determining, by the processor 41, the first area of the target video image according to the hotspot area, specifically:

Determining a center of the hot spot area;

An area having a center of the center and a radius of the first predetermined distance is determined as the first area of the target video image.

Optionally, before the processor 41 processes the first area of the target video image with the first resolution, the processor 41 is further configured to:

Determining a transmission bandwidth with the playing terminal;

Determining the resolution of the first resolution and the gradation according to an area size of the first area, an area size of the second area, and the transmission bandwidth.

Optionally, the processor 41 determines the resolution of the first resolution and the gradation according to the area size of the first area, the area size of the second area, and the transmission bandwidth, and specifically includes:

Determining the first resolution according to an area size of the first area, an area size of the second area, and the transmission bandwidth;

A resolution of a target image position in the second region is determined according to a distance between a target image position in the second region and a center of the hot spot region.

Optionally, the determining, by the processor 41, the resolution of the target image location in the second region according to the distance between the target image location in the second region and the center of the hotspot region, specifically including:

Obtaining a distance between a target image location in the second region and a center of the hotspot region;

A resolution of a target image position in the second region is determined according to a gradation function, wherein the gradation function is a function that characterizes a correspondence between the resolution and the distance.

Optionally, the second area includes a third area and a fourth area, wherein a shortest distance between the third area and a center of the hotspot area is smaller than a center of the fourth area and the hotspot area The resolution of the target image position in the second region is determined by the processor 41 according to the distance between the target image location in the second region and the center of the hotspot region, and specifically includes:

Obtaining a distance between a target image location in the third region and a center of the hotspot region;

Determining a resolution of a target image position in the third region according to a gradation function, wherein the gradation function is a function characterizing a correspondence between the resolution and the distance;

Determining a second resolution as a resolution of a target image position in the fourth region, wherein the second resolution is less than or equal to a minimum resolution of a target image position in the third region, the second resolution For fixed resolution.

Optionally, the second area includes K sub-areas, the resolution of the gradation is a resolution that varies discretely, and the resolution corresponding to the sub-area is a fixed resolution, where the (K-1) The shortest distance between the sub-area and the center of the hot spot area is smaller than the shortest distance between the K-th sub-area and the center of the hot-spot area, K is a positive integer greater than or equal to 2; the processor 41 is based on the second area The distance between the target image location and the center of the hotspot region determines the resolution of the target image location in the second region, and specifically includes:

Determining, according to the distance, a sub-area where the target image position is located;

A resolution of the target image position is determined according to a correspondence between the resolution and the sub-region.

Optionally, the correspondence between the resolution and the sub-region includes: a resolution corresponding to the first sub-region of the target video image is 1/L of the first resolution or the first The difference between the resolution and the first preset value, where L is an integer greater than one.

Optionally, the processor 41 is further configured to:

Determining a target bandwidth required for transmitting the target video image and a transmission bandwidth with the playback terminal;

In the case that the target bandwidth is greater than the transmission bandwidth, the step of processing the first region of the target video image at the first resolution is performed.

It should be noted that the implementation of each operation may also correspond to the corresponding description of the method embodiment shown in FIG. 3 .

The embodiment of the present invention further provides a computer storage medium storing a computer program, the computer program comprising program instructions, when the image processing device performs the image processing The apparatus performs the method as described in the previous embodiments.

The embodiment of the present invention further provides a computer program, including program instructions, which are used to execute the method as described in the foregoing embodiments when executed by an image processing apparatus.

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Claims

A method of image processing, comprising:

Processing a first region of the target video image at a first resolution, the first region including a hotspot region of the target video image;

Processing a second region of the target video image with a gradient resolution that is less than the first resolution, wherein the second region is closer to the hotspot region The higher the resolution corresponding to the image, the second area is located outside the first area, and the second area and the first area constitute the target video image;

The processed target video image is sent to the playback terminal.
The method according to claim 1, wherein the processing of the first area at the first resolution further comprises:

Determining a hot spot area of the target video image;

Determining a first region and the second region of the target video image based on the hotspot region.
The method of claim 2, wherein the determining the first region of the target video image according to the hotspot region comprises:

Determining a center of the hot spot area;

An area having a center of the center and a radius of the first predetermined distance is determined as the first area of the target video image.
The method of claim 2, wherein the determining the first region of the target video image according to the hotspot region comprises:

A minimum regular graphics area containing the hotspot area is determined as the first area of the target video image.
A method according to any one of claims 1 to 4, wherein the resolution of the gradation comprises a resolution that varies continuously or a resolution that varies discretely.
The method according to any one of claims 1 to 5, wherein the processing of the first region of the target video image at the first resolution further comprises:

Determining a transmission bandwidth with the playing terminal;

Determining the resolution of the first resolution and the gradation according to an area size of the first area, an area size of the second area, and the transmission bandwidth.
The method according to claim 6, wherein the determining the resolution of the gradation according to the size of the area of the first area, the size of the area of the second area, and the transmission bandwidth comprises:

Determining the number according to a distance between a target image position in the second region and a center of the hot spot region The resolution of the target image position in the two regions.
The method according to claim 7, wherein said determining a resolution of a target image position in said second region based on a distance between a target image position in said second region and a center of said hot spot region Rates include:

Obtaining a distance between a target image location in the second region and a center of the hotspot region;

A resolution of a target image position in the second region is determined according to a gradation function, wherein the gradation function is a function that characterizes a correspondence between the resolution and the distance.
The method of claim 7 wherein said second region comprises a third region and a fourth region, wherein a shortest distance between said third region and a center of said hot spot region is less than said The shortest distance between the four regions and the center of the hotspot region;

Determining the resolution of the target image location in the second region according to the distance between the target image location in the second region and the center of the hotspot region includes:

Obtaining a distance between a target image location in the third region and a center of the hotspot region;

Determining a resolution of a target image position in the third region according to a gradation function, wherein the gradation function is a function characterizing a correspondence between the resolution and the distance;

Determining a second resolution as a resolution of a target image position in the fourth region, wherein the second resolution is less than or equal to a minimum resolution of a target image position in the third region, the second resolution For fixed resolution.
The method of claim 9, wherein the second resolution is 1/N of the first resolution, and N is an integer greater than 1; or

The second resolution is 1/P of the minimum resolution of the target image position in the third region, and P is an integer greater than or equal to 1.
The method of any of claims 8-10, wherein the gradation function comprises:

A parabolic function, an elliptic function, or a declining function.
The method of claim 7, wherein the second region comprises K sub-regions, the resolution of the gradation is a resolution that varies discretely, and the resolution corresponding to the sub-region is a fixed resolution Wherein the shortest distance between the (K-1)th sub-region and the center of the hotspot region is smaller than the shortest distance between the Kth sub-region and the center of the hotspot region, and K is a positive integer greater than or equal to 2;

Determining the resolution of the target image location in the second region according to the distance between the target image location in the second region and the center of the hotspot region includes:

Obtaining a distance between a target image location in the second region and a center of the hotspot region;

Determining, according to the distance, a sub-area where the target image position is located;

A resolution of the target image position is determined according to a correspondence between the resolution and the sub-region.
The method of claim 12, wherein the resolution corresponds to a correspondence between the sub-regions Relationships include:

The resolution corresponding to the first sub-region of the target video image is 1/L of the first resolution or a difference between the first resolution and a first preset value, where L is an integer greater than 1. .
The method according to claim 13, wherein the correspondence between the resolution and the sub-region further comprises:

The resolution corresponding to the Kth sub-region of the target video image is 1/M of the resolution corresponding to the (K-1)th sub-region, and M is an integer greater than 1; or

The resolution corresponding to the Kth sub-region of the target video image is a difference between a resolution corresponding to the (K-1)th sub-region of the target video image and a second preset value.
The method of any of claims 1 to 14, wherein the method further comprises:

Determining a target bandwidth required for transmitting the target video image and a transmission bandwidth with the playback terminal;

In the case that the target bandwidth is greater than the transmission bandwidth, the step of processing the first region of the target video image at the first resolution is performed.
An apparatus for image processing, comprising:

a first area processing module, configured to process, in a first resolution, a first area of the target video image, where the first area includes a hotspot area of the target video image;

a second area processing module, configured to process the second area of the target video image with a gradual resolution, the resolution of the gradation being smaller than the first resolution, wherein the distance in the second area is The higher the resolution corresponding to the image at the position closer to the hot spot region, the second region is located outside the first region, and the second region and the first region constitute the target video image;

And a sending module, configured to send the processed target video image to the playing terminal.
An apparatus for image processing, comprising: a processor, a memory, and a communication interface, wherein the processor, the memory, and the communication interface are connected to each other, wherein the communication interface is for receiving and transmitting data, and the memory is used for The program code is stored, and the processor is configured to invoke the program code to perform the following operations:

Processing a first region of the target video image at a first resolution, the first region including a hotspot region of the target video image;

Processing a second region of the target video image with a gradient resolution that is less than the first resolution, wherein the second region is closer to the hotspot region The higher the resolution corresponding to the image, the second area is located outside the first area, and the second area and the first area constitute the target video image;

The processed target video image is sent to the playback terminal.
A computer storage medium, characterized in that the computer storage medium stores a computer program, the computer program comprising program instructions, the program instructions causing the image processing when executed by an image processing device The apparatus performs the method of any of claims 1-15.
A computer program, comprising program instructions for performing the method of any of claims 1-15 when executed by an image processing device.