CN112070718A - Method and device for determining regional quantization parameter, storage medium and terminal - Google Patents
Method and device for determining regional quantization parameter, storage medium and terminal Download PDFInfo
- Publication number
- CN112070718A CN112070718A CN202010784772.4A CN202010784772A CN112070718A CN 112070718 A CN112070718 A CN 112070718A CN 202010784772 A CN202010784772 A CN 202010784772A CN 112070718 A CN112070718 A CN 112070718A
- Authority
- CN
- China
- Prior art keywords
- quantization parameter
- determining
- rectangular
- area
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a method, a device, a storage medium and a terminal for determining regional quantization parameters, wherein the method comprises the following steps: according to the judgment result, selecting a determination method for determining regional quantization parameters, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region; according to the determination method, the corresponding regional quantization parameter is determined, so that according to the embodiment of the application, the corresponding quantization parameter determination method can be selected according to the judgment result of whether the rectangular regions in which a plurality of users are interested have overlapping regions, and therefore a simple and flexible regional quantization parameter determination method is provided.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a regional quantization parameter, a storage medium, and a terminal.
Background
At present, after determining that a user is interested in a certain picture in an image database, the existing image processing technology often determines which region is the region concerned by the user according to tracking and capturing eye motion and eye motion tracks of certain interested regions of the current picture of the user's eyes, and needs to perform sharpness processing on the definition of the region, and which region is not the region concerned by the user, may be an unrelated background color, and may perform blur processing.
The image is a two-dimensional matrix, and the identified area of interest to the user is a portion of the two-dimensional matrix, which is a rectangle. Each identified region of interest to the user has a common quantization parameter. When a plurality of regions of interest after use have a common region, different quantization parameters are respectively corresponding to the common region, so that the problem to be solved is to select the quantization parameter corresponding to which region is to be used as the quantization parameter of the common region.
The existing solution to the above problem is to perform bubble sorting on the parameters of the common area, and find the most value as the parameter of the common area, where the most value is often the minimum value. The basic idea of bubble ordering is: bubble sorting, similar to bubbling in water, with larger numbers sinking and smaller numbers slowly rising, assuming that the larger numbers are arranged slowly backwards and the smaller numbers are arranged slowly forwards. The visual expression is that, for each traversal pass, a maximum number is moved to the end of the sequence.
The bubble sort algorithm described above is briefly described as follows:
comparing adjacent elements and swapping if the previous one is larger than the next one;
the first pass sorts the 1 st and 2 nd pairs, compare and swap, followed by the 2 nd and 3 rd pair compare swap, thus moving the largest number to the last bit up to the 2 nd and last 1 st from the last;
the second pass moves the second largest number to the second to last place;
the above process is repeated, so that n-1 times are needed to determine the minimum value of all the areas which are interested by the user, and the areas which are interested by the user are assumed to be n areas, wherein n is a natural number which is more than or equal to 2. According to the above description, the existing bubble-based sorting method determines the most value as the parameter of the common region, and at least n-1 comparison processes of the quantization parameters of the regions in which all users are interested are required to finally determine the minimum value, and the minimum value is used as the parameter of the common region.
In practical application, the chip capable of efficiently processing the image needs to sort the quantization parameters of the regions of interest of a plurality of users, the sorting process is complex, a large amount of time needs to be consumed, and the region quantization parameters of the cross region can be finally determined, so that the image processing efficiency performance of the chip capable of processing the image is poor.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining regional quantization parameters, a storage medium and a terminal. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
In a first aspect, an embodiment of the present application provides a method for determining a regional quantization parameter, where the method includes:
determining a plurality of rectangular areas which are interesting to the user and correspond to the current image, and identifying each rectangular area with different identification numbers;
judging whether each rectangular area marked with different mark numbers has an overlapping area or not to obtain a judgment result;
according to the judgment result, selecting a determination method for determining regional quantization parameters, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region;
and determining the corresponding regional quantization parameter according to the determination method.
In a second aspect, an embodiment of the present application provides an apparatus for determining a regional quantization parameter, where the apparatus includes:
the determining and identifying module is used for determining a plurality of rectangular areas which are interested by the user and correspond to the current image, and identifying different identification numbers for the rectangular areas;
the judging module is used for judging whether each rectangular area marked as different identification numbers by the determining and marking module has an overlapping area or not to obtain a judging result;
a selecting module, configured to select, according to the determination result of the determining module, a determination method for determining a regional quantization parameter, where the quantization parameter determination method includes a first determination method and a second determination method, the first determination method is used to determine a first regional quantization parameter corresponding to any selected overlapping region when there is at least one overlapping region between rectangular regions, and the second determination method is used to determine a second regional quantization parameter corresponding to any selected rectangular region when there is no overlapping region between rectangular regions;
and the quantization parameter determining module is used for determining the corresponding regional quantization parameter according to the determining method selected by the selecting module. In a third aspect, embodiments of the present application provide a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the above-mentioned method steps.
In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
in the embodiment of the application, rectangular areas which correspond to a current image and are interesting to a plurality of users are determined, and different identification numbers are marked for the rectangular areas; judging whether each rectangular area marked with different mark numbers has an overlapping area or not to obtain a judgment result; according to the judgment result, selecting a determination method for determining regional quantization parameters, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region; and determining the corresponding regional quantization parameter according to the determination method. According to the method and the device for determining the quantization parameters of the regions, the corresponding quantization parameter determination method can be selected according to the judgment result of whether the overlapped regions exist among the rectangular regions which are interested by a plurality of users, so that a simple and flexible determination method for the quantization parameters of the regions is provided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic flowchart of a method for determining a regional quantization parameter according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating an overlapping area between rectangular areas of interest to a plurality of users in a specific application scenario provided by an embodiment of the present application;
fig. 3 is a schematic diagram illustrating sorting of parameters of overlapping areas according to different values of preset configurations in a specific application scenario provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for determining a regional quantization parameter according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
So far, the scheme needs to sequence the quantization parameters of the regions of interest of a plurality of users, the sequencing process is complex, and a large amount of time needs to be consumed to finally determine the region quantization parameters of the intersection region, so that the image processing efficiency performance of a chip capable of processing the image is poor. Therefore, the present application provides a method, an apparatus, a storage medium, and a terminal for determining a regional quantization parameter, so as to solve the above-mentioned problems in the related art. In the technical scheme provided by the application, a determination method for determining regional quantization parameters is selected according to a judgment result, the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between rectangular regions, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between rectangular regions; the corresponding region quantization parameter is determined according to the determination method, and since the corresponding quantization parameter determination method can be selected according to the determination result of whether there is an overlapping region between rectangular regions in which a plurality of users are interested, a simple and flexible determination method of the region quantization parameter is provided, which is described in detail below by using an exemplary embodiment.
A method for determining a regional quantization parameter according to an embodiment of the present application will be described in detail below with reference to fig. 1 to 3. The method for determining the regional quantization parameter may be implemented by a computer program, and may be executed on a device for determining the regional quantization parameter. The computer program may be integrated into the application or may run as a separate tool-like application. The determining device of the area quantization parameter in the embodiment of the present application may be a user terminal, including but not limited to: personal computers, tablet computers, handheld devices, in-vehicle devices, wearable devices, computing devices or other processing devices connected to a wireless modem, and the like. The user terminals may be called different names in different networks, for example: user equipment, access terminal, subscriber unit, subscriber station, mobile station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user equipment, cellular telephone, cordless telephone, Personal Digital Assistant (PDA), terminal equipment in a 5G network or future evolution network, and the like.
Referring to fig. 1, a flow chart of a method for determining a regional quantization parameter is provided in an embodiment of the present application. As shown in fig. 1, the method for determining a regional quantization parameter according to the embodiment of the present application may include the following steps:
s101, determining a plurality of rectangular areas which are interested by the user and correspond to the current image, and identifying each rectangular area with different identification numbers.
FIG. 2 is a schematic diagram illustrating an overlapping area between rectangular areas of interest to a plurality of users in a specific application scenario provided by an embodiment of the present application; as shown in fig. 2, it is determined that the plurality of rectangular areas of interest to the user corresponding to the current image are a rectangular area 1 of interest to the user, a rectangular area 2 of interest to the user, and a rectangular area 3 of interest to the user, respectively, and there are overlapping areas between the rectangular areas, forming a shadow area.
In one possible implementation, before determining the rectangular regions of interest to the multiple users corresponding to the current image, the method further includes the following steps:
the method comprises the steps of obtaining eye movement track information of a user, and segmenting a current image into a plurality of rectangular areas which are interesting to the user according to the eye movement track information.
For example, as shown in fig. 2, according to the eye movement trajectory information of the user, it is determined that a plurality of regions in which the user is interested are a rectangular region 1 in which the user is interested, a rectangular region 2 in which the user is interested, and a rectangular region 3 in which the user is interested, and there is an overlapping region between the rectangular regions, a shadow region is formed.
In this way, the current image is segmented into at least 3 rectangular regions of interest to the user by analyzing the eye movement trajectory information.
In practical application, the eye movement track information may include coordinate information of a starting point of the eye movement, coordinate information corresponding to each key node capable of determining the eye movement track, and coordinate information of an end point of the eye movement; thus, the eye movement locus can be determined according to the information. And analyzing the eye movement track to analyze a rectangular area of the current image concerned by the user.
In practical applications, there are various methods for determining the rectangular area, for example, knowing the coordinate information of the top left corner vertex of the current rectangular area and the coordinate information of the bottom right corner vertex of the current rectangular area, the range of the current rectangular area can be determined. The above are merely examples, and other determination methods exist, which are not described herein again.
S102, judging whether each rectangular area marked with different identification numbers has an overlapping area or not, and obtaining a judgment result.
Fig. 2 illustrates an application scenario in which there is an overlapping area between rectangular areas identified with different identification numbers, and an application scenario in which there is no overlapping area between rectangular areas identified with different identification numbers exists, which is not illustrated and described herein again.
And S103, selecting a determination method for determining regional quantization parameters according to the judgment result, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region.
In practical application, under the condition that the judgment result is that at least one overlapping area exists among the rectangular areas, a first determination method is selected to determine a first area quantization parameter corresponding to any selected overlapping area.
In addition, under the condition that the judgment result shows that no overlapping area exists between the rectangular areas, a second determination method is selected to determine a second area quantization parameter corresponding to any one selected rectangular area.
In practical applications, determining the first region quantization parameter of the current overlapping region by the first determination method includes the following steps:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
Further, determining the first region quantization parameter of the current overlap region according to the first determination method includes the steps of:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
In addition, the step of determining a second region quantization parameter corresponding to any one of the selected rectangular regions according to a second determination method includes the steps of:
and acquiring a pre-configured area quantization parameter corresponding to any selected rectangular area, and taking the pre-configured area quantization parameter as a second area quantization parameter.
And S104, determining the corresponding regional quantization parameter according to the determination method.
In one possible implementation, determining the corresponding region quantization parameter according to the determination method includes the following steps:
under the condition that the judgment result is that at least one overlapping area exists among the rectangular areas, selecting any overlapping area as a current overlapping area, and determining a first area quantization parameter of the current overlapping area according to a first determination method;
and sequentially selecting the rest of the overlapping areas, and sequentially determining the corresponding quantization parameters of the overlapping areas according to a first determination method until the quantization parameters of the overlapping areas corresponding to each overlapping area are obtained.
As shown in fig. 2, there is only one overlapping area between the rectangular areas. This is merely illustrative of one application scenario. In practical applications, there may also be multiple overlapping regions. In this way, it is necessary to sequentially traverse each overlapping region and determine the quantization parameter of the overlapping region of each overlapping region until the quantization parameter of the overlapping region corresponding to each overlapping region is obtained.
In one possible implementation, determining the first region quantization parameter of the current overlapping region according to the first determination method includes the following steps:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
In one possible implementation, before obtaining each associated rectangular region associated with the current overlap region, the method further includes the following steps:
and under the condition that the current overlapping area is a partial area of any rectangular area, determining that the current rectangular area is an associated rectangular area associated with the current overlapping area.
As shown in fig. 2, for the overlapping area shown in fig. 2, the associated rectangular areas associated with the overlapping area are a rectangular area 1 interested by the user, a rectangular area 2 interested by the user, and a rectangular area 3 interested by the user, respectively.
As shown in fig. 2, after determining that a plurality of rectangular areas which are interested by the user and correspond to the current image are a rectangular area 1 which is interested by the user, a rectangular area 2 which is interested by the user and a rectangular area 3 which is interested by the user respectively, and that there are overlapping areas among the rectangular areas, acquiring a configuration quantization parameter 1 of the rectangular area 1 which is interested by the user, a configuration quantization parameter 2 of the rectangular area 2 which is interested by the user and a configuration quantization parameter 3 of the rectangular area 3 which is interested by the user respectively.
In practical applications, the configuration quantization parameter 1 of the rectangular area 1 interested by the user, the configuration quantization parameter 2 of the rectangular area 2 interested by the user, and the configuration quantization parameter 3 of the rectangular area 3 interested by the user are configured in advance by the user. The specific configuration method can be set according to the requirements of different users. For example, in a specific application scenario, the value of the read configured quantization parameter 1 of the rectangular region 1 interested by the user is 5, the value of the read configured quantization parameter 2 of the rectangular region 2 interested by the user is 10, and the value of the read configured quantization parameter 3 of the rectangular region 3 interested by the user is 15; thus, 5 with the minimum value corresponding to the configured quantization parameter in the above values is selected as the first region quantization parameter of the current overlapping region. In this way, compared with the existing bubble sorting algorithm, the first region quantization parameter of the current overlapping region can be obtained quickly and simply by only reading and comparing the configuration quantization parameters of the rectangular region corresponding to the current overlapping region and interested by each user. In the existing bubble sorting algorithm, three calculation and comparison processes need to be performed, and in the scheme provided by the embodiment of the present disclosure, after the configuration quantization parameters preconfigured in the rectangular region associated with the current overlapping region and interested by each user are read, a comparison is performed once, so that the first region quantization parameter of the current overlapping region can be determined.
Fig. 3 is a schematic diagram illustrating sorting of parameters of overlapping areas according to different values of preset configurations in a specific application scenario provided in an embodiment of the present application.
As shown in fig. 3, it is determined that a plurality of rectangular areas of interest to the user corresponding to the current image are a rectangular area 1 of interest to the user, a rectangular area 2 of interest to the user, a rectangular area 3 of interest to the user, a rectangular area 4 of interest to the user, and up to a rectangular area N of interest to the user, where in practical applications, the value of N is often a positive integer that is equal to or less than 6 and equal to or greater than 6.
For example, in a specific application scenario, N is 6, the value of the read configured quantization parameter 1 of the rectangular region 1 interested by the user is 5, the value of the read configured quantization parameter 2 of the rectangular region 2 interested by the user is 10, the value of the read configured quantization parameter 3 of the rectangular region 3 interested by the user is 15, the value of the read configured quantization parameter 4 of the rectangular region 4 interested by the user is 20, the value of the read configured quantization parameter 5 of the rectangular region 5 interested by the user is 25, and the value of the read configured quantization parameter 6 of the rectangular region 6 interested by the user is 30; thus, 5 with the minimum value corresponding to the configured quantization parameter in the above values is selected as the first region quantization parameter of the current overlapping region. In this way, compared with the existing bubble sorting algorithm, the first region quantization parameter of the current overlapping region can be obtained quickly and simply by only reading and comparing the configuration quantization parameters of the rectangular region corresponding to the current overlapping region and interested by each user. In the existing bubble sorting algorithm, three calculation and comparison processes need to be performed, and in the scheme provided by the embodiment of the present disclosure, after the configuration quantization parameters preconfigured in the rectangular region associated with the current overlapping region and interested by each user are read, a comparison is performed once, so that the first region quantization parameter of the current overlapping region can be determined.
It should be noted that the above are merely examples. In practical application, different methods can be selected to pre-configure the configuration quantization parameters of the rectangle in which each user is interested according to different application scenarios. The specific configuration method is a conventional method, and is not described herein again.
In a possible implementation manner, determining the corresponding region quantization parameter according to the determination method further includes the following steps: and under the condition that the judgment result is that no overlapping area exists between the rectangular areas, determining a second area quantization parameter corresponding to any selected rectangular area according to a second determination method.
In a possible implementation manner, determining a second region quantization parameter corresponding to any selected rectangular region according to a second determination method includes the following steps:
and acquiring a pre-configured area quantization parameter corresponding to any selected rectangular area, and taking the pre-configured area quantization parameter as a second area quantization parameter.
For example, in a certain application scene, determining that a plurality of rectangular areas which are interested by the user and correspond to the current image are a rectangular area 4 which is interested by the user, a rectangular area 5 which is interested by the user and a rectangular area 6 which is interested by the user respectively, and the rectangular areas are not overlapped; in this way, the region quantization parameter pre-configured for the rectangular region in which the user is interested may be directly read. For example, if the configuration quantization parameter corresponding to the read rectangular area 4 that is interested by the user is 20, the second area quantization parameter corresponding to the current rectangular area is 20.
It should be noted that, in practical applications, different methods may be selected to pre-configure the quantization parameters for the rectangles that are interested in each user according to different application scenarios. The range of the configured quantization parameter is not specifically limited, and the specific configuration method is a conventional method and is not described herein again.
In the embodiment of the application, according to the judgment result, a determination method for determining the regional quantization parameter is selected, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region; according to the determination method, the corresponding regional quantization parameter is determined, so that according to the embodiment of the application, the corresponding quantization parameter determination method can be selected according to the judgment result of whether the rectangular regions in which a plurality of users are interested have overlapping regions, and therefore a simple and flexible regional quantization parameter determination method is provided.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 4, a schematic structural diagram of an apparatus for determining a regional quantization parameter according to an exemplary embodiment of the present invention is shown. The determination means of the area quantization parameter may be implemented by software, hardware or a combination of both as all or part of the terminal. The device for determining the regional quantization parameter comprises a determining and identifying module 10, a judging module 20, a selecting module 30 and a quantization parameter determining module 40.
Specifically, the determining and identifying module 10 is configured to determine a plurality of rectangular areas, which are interested by the user, corresponding to the current image, and identify different identification numbers for the rectangular areas;
a judging module 20, configured to judge whether each rectangular region identified by the determining and identifying module 10 as a different identification number has an overlapping region, so as to obtain a judgment result;
a selecting module 30, configured to select, according to a determination result of the determining module 20, a determination method for determining a quantization parameter of a region, where the quantization parameter determination method includes a first determination method and a second determination method, where the first determination method is used to determine a quantization parameter of a first region corresponding to any selected overlapping region when there is at least one overlapping region between rectangular regions, and the second determination method is used to determine a quantization parameter of a second region corresponding to any selected rectangular region when there is no overlapping region between rectangular regions;
the quantization parameter determining module 40 is configured to determine the corresponding regional quantization parameter according to the determination method selected by the selecting module 30.
Optionally, the quantization parameter determining module 40 is configured to:
under the condition that the judgment result is that at least one overlapping area exists among the rectangular areas, selecting any overlapping area as a current overlapping area, and determining a first area quantization parameter of the current overlapping area according to a first determination method;
and sequentially selecting the rest of the overlapping areas, and sequentially determining the corresponding quantization parameters of the overlapping areas according to a first determination method until the quantization parameters of the overlapping areas corresponding to each overlapping area are obtained.
Optionally, the quantization parameter determining module 40 is specifically configured to:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
Optionally, the apparatus further comprises:
and an associated rectangular region determining module (not shown in fig. 4) configured to, before the quantization parameter determining module 40 obtains each associated rectangular region associated with the current overlap region, determine that the current rectangular region is an associated rectangular region associated with the current overlap region if the current overlap region is a partial region of any rectangular region.
Optionally, the quantization parameter determining module 40 is further configured to:
and under the condition that the judgment result is that no overlapping area exists between the rectangular areas, determining a second area quantization parameter corresponding to any selected rectangular area according to a second determination method.
Optionally, the quantization parameter determining module 40 is further specifically configured to: and acquiring a pre-configured area quantization parameter corresponding to any selected rectangular area, and taking the pre-configured area quantization parameter as a second area quantization parameter.
Optionally, the apparatus further comprises:
a track information acquiring module (not shown in fig. 4) for acquiring eye movement track information of the user before the determining and identifying module 10 determines a plurality of rectangular areas which are interested by the user and correspond to the current image;
and an image segmentation module (not shown in fig. 4) for segmenting the current image into a plurality of rectangular areas of interest to the user according to the eye movement track information acquired by the track information acquisition module.
It should be noted that, when the determining apparatus for the regional quantization parameter provided in the foregoing embodiment executes the method for determining the regional quantization parameter, only the division of the functional modules is taken as an example, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules, so as to complete all or part of the functions described above. In addition, the determining apparatus of the regional quantization parameter and the determining method of the regional quantization parameter provided in the foregoing embodiments belong to the same concept, and details of the implementation process are shown in the determining method of the regional quantization parameter, which is not described herein again.
In the embodiment of the application, the selecting module selects a determining method for determining regional quantization parameters according to a judgment result judged by the judging module, the quantization parameter determining method includes a first determining method and a second determining method, the first determining method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determining method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region; and the quantization parameter determining module determines the corresponding regional quantization parameter according to the determining method selected by the selecting module. According to the method and the device, the corresponding quantization parameter determining method can be selected according to the judgment result of whether the rectangular areas which are interested by a plurality of users have the overlapped areas, so that a simple and flexible device for determining the regional quantization parameters is provided.
The present invention also provides a computer readable medium, on which program instructions are stored, which program instructions, when executed by a processor, implement the method for determining a regional quantization parameter provided by the above-mentioned method embodiments.
The present invention also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method for determining a regional quantization parameter as described in the various method embodiments above.
Please refer to fig. 5, which provides a schematic structural diagram of a terminal according to an embodiment of the present application. As shown in fig. 5, the terminal 1000 can include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.
Wherein a communication bus 1002 is used to enable connective communication between these components.
The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 5, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a determination application program of a region quantization parameter.
In the terminal 1000 shown in fig. 5, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; the processor 1001 may be configured to call the determination application of the regional quantization parameter stored in the memory 1005, and specifically perform the following operations:
determining a plurality of rectangular areas which are interesting to the user and correspond to the current image, and identifying each rectangular area with different identification numbers;
judging whether each rectangular area marked with different mark numbers has an overlapping area or not to obtain a judgment result;
according to the judgment result, selecting a determination method for determining regional quantization parameters, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region;
and determining the corresponding regional quantization parameter according to the determination method.
In one embodiment, the processor 1001, when executing the determining of the corresponding region quantization parameter according to the determining method, performs the following operations:
under the condition that the judgment result is that at least one overlapping area exists among the rectangular areas, selecting any overlapping area as a current overlapping area, and determining a first area quantization parameter of the current overlapping area according to a first determination method;
and sequentially selecting the rest of the overlapping areas, and sequentially determining the corresponding quantization parameters of the overlapping areas according to a first determination method until the quantization parameters of the overlapping areas corresponding to each overlapping area are obtained.
In an embodiment, when the processor 1001 determines the first region quantization parameter of the current overlapping region according to the first determination method, the following operations are specifically performed:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
In one embodiment, the processor 1001 further performs the following operations before acquiring each associated rectangular region associated with the current overlap region:
and under the condition that the current overlapping area is a partial area of any rectangular area, determining that the current rectangular area is an associated rectangular area associated with the current overlapping area.
In one embodiment, when the processor 1001 determines the corresponding region quantization parameter according to the determination method, the following operations are further performed:
and under the condition that the judgment result is that no overlapping area exists between the rectangular areas, determining a second area quantization parameter corresponding to any selected rectangular area according to a second determination method.
In an embodiment, when the processor 1001 determines the second region quantization parameter corresponding to any selected rectangular region according to the second determination method, the following operation is specifically performed:
and acquiring a pre-configured area quantization parameter corresponding to any selected rectangular area, and taking the pre-configured area quantization parameter as a second area quantization parameter.
In one embodiment, the processor 1001 further performs the following operations before determining the rectangular areas of interest to the plurality of users corresponding to the current image:
the method comprises the steps of obtaining eye movement track information of a user, and segmenting a current image into a plurality of rectangular areas which are interesting to the user according to the eye movement track information.
In the embodiment of the application, according to the judgment result, a determination method for determining the regional quantization parameter is selected, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region; and determining the corresponding regional quantization parameter according to the determination method. According to the method and the device for determining the quantization parameters of the regions, the corresponding quantization parameter determination method can be selected according to the judgment result of whether the overlapped regions exist among the rectangular regions which are interested by a plurality of users, so that a simple and flexible determination method for the quantization parameters of the regions is provided.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present application and is not to be construed as limiting the scope of the present application, so that the present application is not limited thereto, and all equivalent variations and modifications can be made to the present application.
Claims (10)
1. A method for determining a regional quantization parameter, the method comprising:
determining a plurality of rectangular areas which are interesting to the user and correspond to the current image, and identifying each rectangular area with different identification numbers;
judging whether each rectangular area marked with different mark numbers has an overlapping area or not to obtain a judgment result;
according to the judgment result, selecting a determination method for determining regional quantization parameters, wherein the quantization parameter determination method comprises a first determination method and a second determination method, the first determination method is used for determining a first regional quantization parameter corresponding to any selected overlapping region under the condition that at least one overlapping region exists between each rectangular region, and the second determination method is used for determining a second regional quantization parameter corresponding to any selected rectangular region under the condition that no overlapping region exists between each rectangular region;
and determining the corresponding regional quantization parameter according to the determination method.
2. The method of claim 1, wherein determining the corresponding region quantization parameter according to the determination method comprises:
under the condition that the judgment result is that at least one overlapping area exists among the rectangular areas, selecting any overlapping area as a current overlapping area, and determining the first area quantization parameter of the current overlapping area according to the first determination method;
and sequentially selecting the rest of the overlapping areas, and sequentially determining the corresponding quantization parameters of the overlapping areas according to the first determination method until the quantization parameters of the overlapping areas corresponding to each overlapping area are obtained.
3. The method of claim 2, wherein the determining the first region quantization parameter for a current overlap region according to the first determination method comprises:
acquiring each associated rectangular area associated with the current overlapping area and each associated area configuration quantization parameter corresponding to each associated rectangular area;
and selecting the area quantization parameter with the minimum value in the quantization parameters configured in each associated area as the first area quantization parameter of the current overlapping area.
4. The method of claim 3, wherein prior to said obtaining each associated rectangular region associated with a current overlap region, the method further comprises:
and under the condition that the current overlapping area is a partial area of any rectangular area, determining that the current rectangular area is an associated rectangular area associated with the current overlapping area.
5. The method of claim 1, wherein determining the corresponding region quantization parameter according to the determination method further comprises:
and under the condition that the judgment result is that no overlapping area exists between the rectangular areas, determining the second area quantization parameter corresponding to any selected rectangular area according to the second determination method.
6. The method according to claim 5, wherein the determining the second region quantization parameter corresponding to any selected rectangular region according to the second determination method comprises:
and acquiring a pre-configured region quantization parameter corresponding to any selected rectangular region, and taking the pre-configured region quantization parameter as the second region quantization parameter.
7. The method of claim 1, wherein prior to said determining the rectangular regions of interest to the plurality of users for the current image, the method further comprises:
the method comprises the steps of obtaining eye movement track information of a user, and segmenting a current image into a plurality of rectangular areas which are interesting to the user according to the eye movement track information.
8. An apparatus for determining a regional quantization parameter, the apparatus comprising:
the determining and identifying module is used for determining a plurality of rectangular areas which are interested by the user and correspond to the current image, and identifying different identification numbers for the rectangular areas;
the judging module is used for judging whether each rectangular area marked as different identification numbers by the determining and marking module has an overlapping area or not to obtain a judging result;
a selecting module, configured to select, according to the determination result of the determining module, a determination method for determining a regional quantization parameter, where the quantization parameter determination method includes a first determination method and a second determination method, the first determination method is used to determine a first regional quantization parameter corresponding to any selected overlapping region when there is at least one overlapping region between rectangular regions, and the second determination method is used to determine a second regional quantization parameter corresponding to any selected rectangular region when there is no overlapping region between rectangular regions;
and the quantization parameter determining module is used for determining the corresponding regional quantization parameter according to the determining method selected by the selecting module.
9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to carry out the method steps according to any one of claims 1 to 7.
10. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010784772.4A CN112070718A (en) | 2020-08-06 | 2020-08-06 | Method and device for determining regional quantization parameter, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010784772.4A CN112070718A (en) | 2020-08-06 | 2020-08-06 | Method and device for determining regional quantization parameter, storage medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070718A true CN112070718A (en) | 2020-12-11 |
Family
ID=73660778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010784772.4A Pending CN112070718A (en) | 2020-08-06 | 2020-08-06 | Method and device for determining regional quantization parameter, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070718A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080240250A1 (en) * | 2007-03-30 | 2008-10-02 | Microsoft Corporation | Regions of interest for quality adjustments |
| CN105049949A (en) * | 2015-06-19 | 2015-11-11 | 美国掌赢信息科技有限公司 | Coding method of instant video and electronic equipment |
| CN105744271A (en) * | 2016-02-17 | 2016-07-06 | 浙江大华技术股份有限公司 | Video coding method and device |
| CN107113429A (en) * | 2014-10-03 | 2017-08-29 | 微软技术许可有限责任公司 | The adaptive quantizing in interest region |
| CN109698957A (en) * | 2017-10-24 | 2019-04-30 | 腾讯科技（深圳）有限公司 | Image encoding method, calculates equipment and storage medium at device |
-
2020
- 2020-08-06 CN CN202010784772.4A patent/CN112070718A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080240250A1 (en) * | 2007-03-30 | 2008-10-02 | Microsoft Corporation | Regions of interest for quality adjustments |
| CN107113429A (en) * | 2014-10-03 | 2017-08-29 | 微软技术许可有限责任公司 | The adaptive quantizing in interest region |
| CN105049949A (en) * | 2015-06-19 | 2015-11-11 | 美国掌赢信息科技有限公司 | Coding method of instant video and electronic equipment |
| CN105744271A (en) * | 2016-02-17 | 2016-07-06 | 浙江大华技术股份有限公司 | Video coding method and device |
| CN109698957A (en) * | 2017-10-24 | 2019-04-30 | 腾讯科技（深圳）有限公司 | Image encoding method, calculates equipment and storage medium at device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110189246B (en) | Image stylization generation method and device and electronic equipment | |
| CN112102437B (en) | Canvas-based radar map generation method and device, storage medium and terminal | |
| CN110070551B (en) | Video image rendering method and device and electronic equipment | |
| CN110139149B (en) | Video optimization method and device, and electronic equipment | |
| CN107133909B (en) | Method and device for recombining shaders | |
| CN111507122A (en) | Graphic code identification method and device, storage medium and terminal | |
| CN113421312A (en) | Method and device for coloring black and white video, storage medium and terminal | |
| CN114003160A (en) | Data visualization display method and device, computer equipment and storage medium | |
| CN110968375B (en) | Interface control method and device, intelligent terminal and computer readable storage medium | |
| CN111179402A (en) | Target object rendering method, device and system | |
| CN112785676B (en) | Image rendering method, device, equipment and storage medium | |
| CN114119964A (en) | Network training method and device, and target detection method and device | |
| CN113486638A (en) | Table reconstruction method and device, storage medium and electronic device | |
| CN111049735B (en) | Group head portrait display method, device, equipment and storage medium | |
| CN111107264A (en) | Image processing method, image processing device, storage medium and terminal | |
| CN112070718A (en) | Method and device for determining regional quantization parameter, storage medium and terminal | |
| CN110321759B (en) | Video feature extraction method and device | |
| CN112132871B (en) | Visual feature point tracking method and device based on feature optical flow information, storage medium and terminal | |
| CN115830608A (en) | Text recognition method and device, storage medium and electronic equipment | |
| CN111325816B (en) | Feature map processing method and device, storage medium and terminal | |
| CN110941413B (en) | Display screen generation method and related device | |
| CN115700519A (en) | Text-to-image generation method and device, storage medium and terminal | |
| CN112991497A (en) | Method, device, storage medium and terminal for coloring black-and-white cartoon video | |
| CN114792283A (en) | Image processing method, device and equipment and computer readable storage medium | |
| CN111918137B (en) | Push method and device based on video characteristics, storage medium and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201211 |
|
| RJ01 | Rejection of invention patent application after publication |