CN104822069A - Image information detection method and apparatus - Google Patents

Image information detection method and apparatus Download PDF

Info

Publication number
CN104822069A
CN104822069A CN201510219862.8A CN201510219862A CN104822069A CN 104822069 A CN104822069 A CN 104822069A CN 201510219862 A CN201510219862 A CN 201510219862A CN 104822069 A CN104822069 A CN 104822069A
Authority
CN
China
Prior art keywords
line segment
region
information
edge
determined
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.)
Granted
Application number
CN201510219862.8A
Other languages
Chinese (zh)
Other versions
CN104822069B (en
Inventor
王涛
杨琛
张彦刚
许�鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing IQIYI Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201510219862.8A priority Critical patent/CN104822069B/en
Publication of CN104822069A publication Critical patent/CN104822069A/en
Application granted granted Critical
Publication of CN104822069B publication Critical patent/CN104822069B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences

Abstract

The embodiment of the invention, which relates to the technical field of image processing, discloses an image information detection method and apparatus. The method comprises: according to a preset image edge detection algorithm, edge detection is carried out on a target video frame to obtain edge points of the target video frame; an alternative line segment is determined according to the obtained edge points; on the basis of the determined alternative line segment, a horizontal edge line segment zone and a vertical edge line segment zone are determined; a horizontal-edge straight line is determined based on the determined horizontal edge line segment zone and a vertical-edge straight line is determined based on the determined vertical edge line segment zone; and in a determined rectangular zone based on the determined horizontal-edge straight line and vertical-edge straight line, a rectangular area meeting a preset paster information embedding rule is selected and is used as one where embedded paster information of the target video frame is located. On the basis of the technical scheme, under the circumstances that no manual intervention is needed, the area of the embedded paster information in the video frame can be detected automatically, thereby improving the work efficiency.

Description

A kind of image information detecting method and device
Technical field
The present invention relates to technical field of image processing, particularly a kind of image information detecting method and device.
Background technology
Along with the quickening of people's rhythm of life; increasing user cannot watch TV platform on time just at the video frequency program of hot broadcast; Virtual network operator is in order to attract user; usually can obtain the right of broadcasting of TV station's hot broadcast video frequency program, with make user can at one's leisure between watch this video frequency program by network.TV station, when displaying video programs, considers reasons such as increasing income, usually can product placement information in video.The advertising message that TV station implants is generally with rectangular patch message form displaying ad-hoc location in the video frame, and such as, rectangular patch advertising message is illustrated in the zone line, the 2 D code information lower right field being illustrated in frame of video etc. of frame of video.But although these paster information that TV station implants can bring commercial value for TV station, for Virtual network operator, these paster information cannot bring commercial value for it.
Therefore, from the angle of Virtual network operator, the paster information need implanted TV station in frame of video detects, so that can process the paster information that TV station implants according to testing result in later stage operation, and then brings commercial value for it.
Concrete, paster information can be understood as the information directly overlaying frame of video respective regions, along with the broadcasting of video is play together, is positioned at beginning or the latter end of video under normal circumstances.
In prior art, Virtual network operator, after acquisition video playback power, is generally determined the paster information in each frame of video, is processed afterwards according to the information manually determined to the paster information implanted in frame of video again by manual type.Although this mode can determine the paster information implanted in each frame of video, operating efficiency is low.
Summary of the invention
The embodiment of the invention discloses a kind of image information detecting method and device, to improve the efficiency detecting paster information in video.
For achieving the above object, the embodiment of the invention discloses a kind of image information detecting method, described method comprises:
Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, obtains the marginal point of described target video frame;
Alternative line segment is determined according to obtained marginal point, wherein, described alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on described target video frame, position is adjacent;
According to determined alternative line segment, determine horizontal edge line segment region and vertical edge line segment region, wherein, horizontal edge line segment region meets: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region meets: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment;
Determine horizontal edge straight line according to determined horizontal edge line segment region, determine vertical edge straight line according to determined vertical edge line segment region;
By in determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in described target video frame.
In a kind of specific implementation of the present invention, at least one in the following manner, determine horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding.
In a kind of specific implementation of the present invention, described default paster Information Embedding rule is relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
The identification characteristics information preset comprised in rectangular area.
In a kind of specific implementation of the present invention, described method also comprises:
Obtain information to be pushed;
The image information of the paster information region of having implanted in described target video frame is replaced with obtained information to be pushed.
In a kind of specific implementation of the present invention, described image information detecting method also comprises:
Before show described target video frame to user, obtain information to be pushed;
When showing described target video frame to user, obtained information to be pushed is covered on the paster information region of having implanted in described target video, show to user.
In a kind of specific implementation of the present invention, described acquisition information to be pushed, comprising:
Obtain the historical viewings recorded information of user;
According to obtained historical viewings recorded information, determine information to be pushed.
For achieving the above object, the embodiment of the invention discloses a kind of image information detecting device, described device comprises:
Marginal point obtains module, for carrying out rim detection according to the Edge-Detection Algorithm preset to target video frame, obtains the marginal point of described target video frame;
Alternative line segment determination module, for determining alternative line segment according to obtained marginal point, wherein, described alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on described target video frame, position is adjacent;
Edge line segment area determination module, for according to determined alternative line segment, determines horizontal edge line segment region and vertical edge line segment region, and wherein, horizontal edge line segment region meets: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region meets: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment;
Edge line determination module, for determining horizontal edge straight line according to determined horizontal edge line segment region, determines vertical edge straight line according to determined vertical edge line segment region;
Module is selected in rectangular area, for by determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in described target video frame.
In a kind of specific implementation of the present invention, described edge line segment area determination module, comprising: horizontal edge line segment region determines that submodule is determined in submodule and vertical edge line segment region;
Wherein, submodule is determined in described horizontal edge line segment region, at least one in the following manner, determines horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
Submodule is determined in described vertical edge line segment region, for according to determined alternative line segment, determines vertical edge line segment region.
In a kind of specific implementation of the present invention, described default paster Information Embedding rule is relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
The identification characteristics information preset comprised in rectangular area.
In a kind of specific implementation of the present invention, described image information detecting device also comprises:
First pushed information obtains module, for obtaining information to be pushed;
Image information replacement module, for replacing with obtained information to be pushed by the image information of the paster information implanted in described target video frame region.
In a kind of specific implementation of the present invention, described image information detecting device also comprises:
Second pushed information obtains module, for before show described target video frame to user, obtains information to be pushed;
Region overlay module, for when showing described target video frame to user, covers obtained information to be pushed on the paster information region of having implanted in described target video, shows to user.
In a kind of specific implementation of the present invention, described second pushed information obtains module, comprising:
Historical viewings record obtains submodule, for obtaining the historical viewings recorded information of user;
Pushed information determination submodule, for according to obtained historical viewings recorded information, determines information to be pushed.
As seen from the above, in the scheme that the embodiment of the present invention provides, Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, after obtaining the marginal point of target video frame, alternative line segment is determined according to obtained marginal point, again according to determined alternative line segment determination horizontal edge line segment region and vertical edge line segment region, because horizontal edge line segment region and vertical edge line segment region can relate to multiple pixel column, multiple pixel column, so need in practical application to determine horizontal edge straight line according to determined horizontal edge line segment region, vertical edge straight line is determined according to vertical edge line segment region, rectangular area is determined again according to determined edge line, select the rectangular area wherein meeting default paster Information Embedding rule, as the paster information region of having implanted in target video frame.Due under normal circumstances, the paster information implanted in video is generally rectangle, so, the scheme that the application embodiment of the present invention provides, when without the need to manual intervention, can automatically detect the region of having implanted paster information in frame of video, can increase work efficiency.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The first schematic flow sheet of the image information detecting method that Fig. 1 provides for the embodiment of the present invention;
Fig. 2 a is the first schematic diagram of the neighbor pixel of a pixel;
Fig. 2 b is the second schematic diagram of the neighbor pixel of a pixel;
Fig. 3 a is the first the distribution figure being in marginal point corresponding to the image border of level;
Fig. 3 b is the second distribution figure being in marginal point corresponding to the image border of level;
Fig. 3 c is the third the distribution figure being in marginal point corresponding to the image border of level;
Fig. 3 d is the 4th kind of distribution figure being in marginal point corresponding to the image border of level;
The second schematic flow sheet of the image information detecting method that Fig. 4 provides for the embodiment of the present invention;
The third schematic flow sheet of the image information detecting method that Fig. 5 provides for the embodiment of the present invention;
The schematic diagram of the first aim frame of video that Fig. 6 a provides for the embodiment of the present invention;
Fig. 6 b carries out to first aim frame of video the schematic diagram that edge extracting obtains marginal point;
Fig. 6 c identifies the schematic diagram implanting paster information in first aim frame of video;
Fig. 6 d blocks with information to be pushed the schematic diagram having implanted paster information in first aim frame of video;
The schematic diagram of the second target frame of video that Fig. 7 a provides for the embodiment of the present invention;
Fig. 7 b carries out to second target frame of video the schematic diagram that edge extracting obtains marginal point;
Fig. 7 c identifies the schematic diagram implanting paster information in second target frame of video;
Fig. 7 d blocks with information to be pushed the schematic diagram having implanted paster information in second target frame of video;
The structural representation of a kind of image information detecting device that Fig. 8 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The first schematic flow sheet of the image information detecting method that Fig. 1 provides for the embodiment of the present invention, the method comprises:
S101: the Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, obtains the marginal point of target video frame.
Image Edge-Detection is a kind of common image procossing mode, its objective is that in identification image, color value changes obvious pixel, these points can be called the marginal point of image, and in addition, Image Edge-Detection also can be understood as the edge of each object in detected image.Various Edge-Detection Algorithm can be understood as: detect according to corresponding Image Edge-Detection operator, determines each marginal point of image.
Wherein, conventional Image Edge-Detection operator comprises: Canny Image Edge-Detection operator, Laplacian Image Edge-Detection operator, Sobel Image Edge-Detection operator, Prewitt Image Edge-Detection operator etc., also there is multiple conventional Image Edge-Detection operator in practical application, will not enumerate here.
S102: determine alternative line segment according to obtained marginal point.
Wherein, alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on target video frame, position is adjacent.
The neighbor pixel of a pixel in the video frame, can only comprise in the horizontal direction with the pixel adjacent with this pixel in vertical direction, that is, the distance between this pixel and its each neighbor pixel is 1.See Fig. 2 a, the pixel of four " x " type positions is the neighbor pixel of the pixel of ". " type position.
In addition, the neighbor pixel of a pixel in frame of video, except comprising each above-mentioned pixel, the pixel adjacent in non-horizontal directions and non-vertical direction with this pixel can also be comprised, according to the arrangement feature of each pixel in image, these pixels can be the pixels in this pixel upper left corner, the lower left corner, the upper right corner and the lower right corner, and that is can also comprise with the spacing of this pixel is the pixel of 2.See Fig. 2 b, the pixel of eight " x " type positions is the neighbor pixel of the pixel of ". " type position.
Based on above-mentioned two kinds of situations, according to the alternative line segment that obtained marginal point is determined, its place straight line can be the straight line of horizontal direction, the straight line of vertical direction or be the straight line of 45 degree with horizontal direction angle.
S103: according to determined alternative line segment, determines horizontal edge line segment region and vertical edge line segment region.
Be understandable that, in practical application, when carrying out Edge extraction, by the impact of following several respects factor, may there is certain error in the marginal point extracted,
The arithmetic accuracy of the Edge extraction algorithm adopted;
The hardware performance of image capture device;
The color data error of pixel between foreground object and background object;
Shooting angle of image etc.
Certainly, the factor affecting Edge extraction is not limited in above-mentioned several.
Below to be in the image border of level, illustrate after Edge extraction, the distribution situation of the marginal point that this image border is corresponding:
When extracted marginal point does not exist error, marginal point human eye vision effect being in the image border of level corresponding is usually located at same pixel column, and each pixel arranged adjacent successively on this pixel column;
When extracted marginal point exists error, may there is following several distribution situation in marginal point human eye vision effect being in the image border of level corresponding, wherein " x " represents a pixel:
See Fig. 3 a, marginal point corresponding to image border is positioned at same pixel column, but these marginal points are not arranged adjacent successively, and some middle marginal points are not successfully detected out;
See Fig. 3 b and Fig. 3 c, marginal point corresponding to image border is positioned at two adjacent pixel columns;
See Fig. 3 d, marginal point corresponding to image border is positioned at three adjacent successively pixel columns.
It should be noted that, the application is just described for above-mentioned, the distribution situation being in marginal point corresponding to the image border of level in practical application is not limited only to above-mentioned several, those skilled in the art can learn other multiple analogues according to the thinking of above-mentioned several situation, in addition, the distribution situation being in marginal point corresponding to the image border of other states can be similar with above-mentioned several situations, such as, plumbness etc., repeats no more here.
More than comprehensive, above-mentioned horizontal edge line segment region need meet: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region need meet: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment.
Wherein, the value of the Second Threshold preset and the 3rd default threshold value is nonnegative integer, and the value of both can be equal, also can be unequal, and the application does not limit this.
Preferably, when above-mentioned default Second Threshold and the 3rd threshold value preset are zero, only include the alternative line segment being positioned at same pixel column in horizontal edge line segment region, in vertical edge line segment region, only include the alternative line segment being positioned at same pixel column.
Illustrate below by a specific embodiment, how according to determined alternative line segment, determine horizontal edge line segment region.
Concrete, from determined alternative line segment, select an alternative line segment as initial segment;
Whether the right side detecting above-mentioned initial segment exists the marginal point contiguous with the right side end points of this initial segment;
If there is not neighboring edge point, end edge point is searched;
If there is neighboring edge point, judge whether above-mentioned neighboring edge point is positioned on a determined alternative line segment;
If be positioned on a determined alternative line segment, initial segment is updated to this alternative line segment, performs each step above-mentioned, until there is not the right side neighboring edge point of alternative line segment right endpoint, or there is not marginal point adjacent thereto in the right side of neighboring edge point;
If be not positioned on a determined alternative line segment, judge whether the right side of this neighboring edge point exists marginal point adjacent thereto, if exist, return to perform and above-mentioned judge whether above-mentioned neighboring edge point is positioned on a determined alternative line segment, until there is not the right side neighboring edge point of alternative line segment right endpoint, or there is not marginal point adjacent thereto in the right side of neighboring edge point;
The alternative line segment related in each step above-mentioned and marginal point composition horizontal edge line segment region.
Concrete, can in the following manner at least one judge whether the right side of a marginal point P exists marginal point adjacent thereto:
On the pixel column of P place, judge whether right pixel point that is adjacent with P, P is edge pixel point;
On a upper pixel column of P place pixel column, judge whether upper right side pixel that is adjacent with P, P is edge pixel point;
On next pixel column of P place pixel column, judge whether lower right side pixel that is adjacent with P, P is edge pixel point;
On the pixel column of P place, judge the right side of P, and the pixel of a P interval predetermined number pixel whether be edge pixel point.
Judge that whether the right pixel point of P is that the mode of edge pixel point is not limited in above-mentioned several, the application does not limit this.
In addition, can find out and be according to sequence detection marginal point from left to right and determine horizontal edge line segment region above, in practical application, horizontal edge line segment region can also be determined according to the sequence detection marginal point of turning left from the right side.
According to determined alternative line segment, determine with above-mentioned, the method in vertical edge line segment region can determine that the method in horizontal edge line segment region is similar, no longer repeat here.
According to the method in the determination horizontal edge line segment region provided in above-mentioned specific embodiment, can determine that the horizontal edge line segment region that Fig. 3 a is corresponding comprises four alternative line segments, the horizontal edge line segment region that Fig. 3 b is corresponding comprises three alternative line segments, the horizontal edge line segment region that Fig. 3 c is corresponding comprises three alternative line segments, and the horizontal edge line segment region that Fig. 3 d is corresponding comprises five alternative line segments.
S104: determine horizontal edge straight line according to determined horizontal edge line segment region, determines vertical edge straight line according to determined vertical edge line segment region.
Concrete, can in the following manner at least one, determine horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding.
For above-mentioned Fig. 3 a, Fig. 3 b, Fig. 3 c, Fig. 3 d, wherein, pixel column place straight line corresponding for marginal point can be defined as horizontal edge straight line corresponding to this horizontal edge line segment region in Fig. 3 a;
In two pixel column place straight lines in figure one can be defined as horizontal edge straight line corresponding to horizontal edge line segment region in Fig. 3 b and Fig. 3 c;
In three pixel column place straight lines in figure one can be defined as horizontal edge straight line corresponding to horizontal edge line segment region in Fig. 3 d.
Similar with the mode of above-mentioned determination horizontal edge straight line, can in the following manner at least one, determine vertical edge straight line according to determined vertical edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target vertical edge, be defined as the vertical edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target vertical edge, be defined as the vertical edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target vertical edge, be defined as the vertical edge straight line that this region is corresponding.
It should be noted that, the application is just described for above-mentioned, determines that the mode of horizontal edge straight line and vertical edge straight line is not limited in above-mentioned several in practical application.
S105: by determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in target video frame.
Because the horizontal edge straight line determining to obtain through above-mentioned steps and vertical edge straight line all may be many, so, multiple rectangular area can be determined according to these straight lines, and these rectangles are not the paster information region of having implanted entirely under normal circumstances, therefore, need screen these rectangular areas.
The paster Information Embedding preset rule for screening rectangular area can be relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
Identification characteristics information preset comprised in rectangular area etc.
Wherein, the width of rectangular area, highly, the ratio of width to height, position in the video frame etc. is mainly from the viewpoint of the size in the video frame of paster information under normal circumstances and position, such as, the paster information implanted in the video frame is positioned at the central area of frame of video, lower right field, size are 150x100, size is 50x50 etc.In addition, identification characteristics information may be comprised in the paster information implanted in the video frame, such as, the paster information implanted in the video frame is the Quick Response Code of micro-letter, the upper left of Quick Response Code, upper right, drift angle place, three, lower-left are respectively arranged with a blockage, these three blockages as the identification characteristics information of paster information, after determining rectangular area, can determine whether it is the Quick Response Code paster information of implantation by whether comprising this identification characteristics in rectangular area.
Be understandable that, determine that a rectangle needs four straight lines, two horizontal linears, two vertical line, but in some cases, determine that the horizontal edge straight line that obtains and vertical edge straight line possibly cannot meet above-mentioned requirements.
In a preferred embodiment of the present invention, if during through determining that the horizontal edge straight line that obtains and vertical edge straight line comprise two parallel lines and a perpendicular straight line, obviously through determining that these straight lines obtained directly cannot determine a rectangle, in this case, first can determine Article 4 straight line according to these three straight lines and default paster Information Embedding rule, then determine rectangular area.Such as, detect in the region that these three straight lines determine whether comprise default identification characteristics information, if comprise, Article 4 straight line is determined in the position according to wherein identification characteristics information.In addition, position residing for above-mentioned three straight lines can also be mated with the paster Information Embedding rule preset, the ratio of width to height of rectangle when determining that the region determined at above-mentioned three straight lines is under normal circumstances implanted into paster information, due to the width of rectangle that can determine according to these three straight lines or height, so the ratio of width to height in conjunction with rectangle can determine Article 4 straight line.
As seen from the above, in the scheme that the present embodiment provides, Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, after obtaining the marginal point of target video frame, alternative line segment is determined according to obtained marginal point, again according to determined alternative line segment determination horizontal edge line segment region and vertical edge line segment region, because horizontal edge line segment region and vertical edge line segment region can relate to multiple pixel column, multiple pixel column, so need in practical application to determine horizontal edge straight line according to determined horizontal edge line segment region, vertical edge straight line is determined according to vertical edge line segment region, rectangular area is determined again according to determined edge line, select the rectangular area wherein meeting default paster Information Embedding rule, as the paster information region of having implanted in target video frame.Due under normal circumstances, the paster information implanted in video is generally rectangle, so, the scheme that application the present embodiment provides, when without the need to manual intervention, can automatically detect the region of having implanted paster information in frame of video, can increase work efficiency.
In one particular embodiment of the present invention, see Fig. 4, provide the second schematic flow sheet of image information detecting method, compared with embodiment illustrated in fig. 1, in the present embodiment, also comprise:
S106: obtain information to be pushed.
S107: the image information of the paster information region of having implanted in target video frame is replaced with obtained information to be pushed.
In the scheme that the present embodiment provides, the paster information implanted in target video frame can be replaced with the information oneself wanting to push to user by Virtual network operator, thus bring commercial value for it, in addition, the mode that Virtual network operator is replaced with information realizes information pushing, can online under complete information replacement work, when such user selects to watch video, direct viewing is to the video completing information replacement, in the process of displaying video, carry out other operations again without the need to client, newly-increased requirement can not be produced to the performance of user terminal.
In another specific embodiment of the present invention, see Fig. 5, provide the third schematic flow sheet of image information detecting method, compared with embodiment illustrated in fig. 1, in the present embodiment, also comprise:
S108: before showing target video frame to user, obtains information to be pushed.
Concrete, first can obtain the historical viewings recorded information of user, then according to obtained historical viewings recorded information, determine information to be pushed.
Hobby, sex, age etc. the information learning user can be analyzed according to the historical viewings recorded information of user, pushed information can be selected for each user targetedly according to these information, and identical pushed information can not be selected for all users, lay the foundation for realizing personalized information push.
Such as, the historical viewings recorded information analysis according to user learns that user likes sport category program, then the information to be pushed determined can be sport category articles for use series advertisements information etc.;
Historical viewings recorded information analysis according to user learns that user is women, then the information to be pushed determined can be toiletries advertising message etc.;
Historical viewings recorded information analysis according to user learns that user is the elderly, then the information to be pushed determined can be tonic advertising message etc.
S109: when showing target video frame to user, covers obtained information to be pushed on the paster information region of having implanted in target video, shows to user.
In the scheme that the present embodiment provides, when showing target video frame to user, the mode covered by information realizes information pushing, thus brings commercial value for it.In addition, the mode that Virtual network operator covers with information realizes information pushing, and this mode can realize information and cover when client terminal playing video, thus without the need to generating the video comprising information to be pushed in advance.
It should be noted that, in Fig. 4 and the scheme provided embodiment illustrated in fig. 5, in order to reach the effect of better showing target video frame to user, the width of information to be pushed should be not less than the width having implanted paster information, the height of information to be pushed should be not less than the height having implanted paster information, such information to be pushed can shelter from completely and implant paster information, brings preferably Consumer's Experience to user.
Again the present invention is described in detail below by several concrete legend.
Fig. 6 a, for implanting the target video frame that paster information is micro-letter Quick Response Code, this Quick Response Code is positioned at the lower right corner of frame of video;
Fig. 6 b is the marginal point image obtained after carrying out Edge extraction to Fig. 6 a;
Fig. 6 c, for determining the image of the micro-letter two-dimension code area implanted according to the marginal point of Fig. 6 b, wherein, micro-letter two-dimension code area is known with grey rectangle collimation mark;
Fig. 6 d, for the image after the micro-letter Quick Response Code implanted in McDonald's advertisement replacement or coverage diagram 6a.
Fig. 7 a, for implanting the target video frame that paster information is down jackets advertisement, this advertising message is positioned at the central area of frame of video;
Fig. 7 b is the marginal point image obtained after carrying out Edge extraction to Fig. 7 a;
Fig. 7 c, for determining the image of the down jackets advertising area implanted according to the marginal point of Fig. 7 b, wherein, down jackets advertising area is known with grey rectangle collimation mark;
Fig. 7 d, for the image after the down jackets advertisement of having implanted in advertisement for cosmetics replacement or coverage diagram 7a.
Corresponding with above-mentioned image information detecting method, the embodiment of the present invention additionally provides a kind of image information detecting device.
The first structural representation of the image information detecting device that Fig. 8 provides for the embodiment of the present invention, this device comprises: marginal point obtains module 801, alternative line segment determination module 802, edge line segment area determination module 803, edge line determination module 804 and rectangular area and selects module 805.
Wherein, marginal point obtains module 801, for carrying out rim detection according to the Edge-Detection Algorithm preset to target video frame, obtains the marginal point of described target video frame;
Alternative line segment determination module 802, for determining alternative line segment according to obtained marginal point, wherein, described alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on described target video frame, position is adjacent;
Edge line segment area determination module 803, for according to determined alternative line segment, determines horizontal edge line segment region and vertical edge line segment region, and wherein, horizontal edge line segment region meets: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region meets: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment;
Edge line determination module 804, for determining horizontal edge straight line according to determined horizontal edge line segment region, determines vertical edge straight line according to determined vertical edge line segment region;
Module 805 is selected in rectangular area, for by determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in described target video frame.
Concrete, described edge line segment area determination module 803 can comprise: horizontal edge line segment region determines that submodule is determined in submodule and vertical edge line segment region;
Wherein, submodule is determined in described horizontal edge line segment region, at least one in the following manner, determines horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
Submodule is determined in described vertical edge line segment region, for according to determined alternative line segment, determines vertical edge line segment region.
Concrete, described default paster Information Embedding rule can be relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
The identification characteristics information preset comprised in rectangular area.
As seen from the above, in the scheme that the present embodiment provides, Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, after obtaining the marginal point of target video frame, alternative line segment is determined according to obtained marginal point, again according to determined alternative line segment determination horizontal edge line segment region and vertical edge line segment region, because horizontal edge line segment region and vertical edge line segment region can relate to multiple pixel column, multiple pixel column, so need in practical application to determine horizontal edge straight line according to determined horizontal edge line segment region, vertical edge straight line is determined according to vertical edge line segment region, rectangular area is determined again according to determined edge line, select the rectangular area wherein meeting default paster Information Embedding rule, as the paster information region of having implanted in target video frame.Due under normal circumstances, the paster information implanted in video is generally rectangle, so, the scheme that application the present embodiment provides, when without the need to manual intervention, can automatically detect the region of having implanted paster information in frame of video, can increase work efficiency.
In one particular embodiment of the present invention, described image information detecting device can also comprise: the first pushed information obtains module and image information replacement module (not shown).
Wherein, the first pushed information obtains module, for obtaining information to be pushed;
Image information replacement module, for replacing with obtained information to be pushed by the image information of the paster information implanted in described target video frame region.
In the scheme that the present embodiment provides, the paster information implanted in target video frame can be replaced with the information oneself wanting to push to user by Virtual network operator, thus bring commercial value for it, in addition, the mode that Virtual network operator is replaced with information realizes information pushing, can online under complete information replacement work, when such user selects to watch video, direct viewing is to the video completing information replacement, in the process of displaying video, carry out other operations again without the need to client, newly-increased requirement can not be produced to the performance of user terminal.
In another specific embodiment of the present invention, described image information detecting device can also comprise: the second pushed information obtains module and region overlay module (not shown).
Wherein, the second pushed information obtains module, for before show described target video frame to user, obtains information to be pushed;
Region overlay module, for when showing described target video frame to user, covers obtained information to be pushed on the paster information region of having implanted in described target video, shows to user.
Preferably, described second pushed information obtains module, comprising:
Historical viewings record obtains submodule, for obtaining the historical viewings recorded information of user;
Pushed information determination submodule, for according to obtained historical viewings recorded information, determines information to be pushed.
In the scheme that the present embodiment provides, when showing target video frame to user, the mode covered by information realizes information pushing, thus brings commercial value for it.In addition, the mode that Virtual network operator covers with information realizes information pushing, and this mode can realize information and cover when client terminal playing video, thus without the need to generating the video comprising information to be pushed in advance.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
One of ordinary skill in the art will appreciate that all or part of step realized in said method execution mode is that the hardware that can carry out instruction relevant by program has come, described program can be stored in computer read/write memory medium, here the alleged storage medium obtained, as: ROM/RAM, magnetic disc, CD etc.
The foregoing is only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., be all included in protection scope of the present invention.

Claims (12)

1. an image information detecting method, is characterized in that, described method comprises:
Edge-Detection Algorithm according to presetting carries out rim detection to target video frame, obtains the marginal point of described target video frame;
Alternative line segment is determined according to obtained marginal point, wherein, described alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on described target video frame, position is adjacent;
According to determined alternative line segment, determine horizontal edge line segment region and vertical edge line segment region, wherein, horizontal edge line segment region meets: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region meets: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment;
Determine horizontal edge straight line according to determined horizontal edge line segment region, determine vertical edge straight line according to determined vertical edge line segment region;
By in determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in described target video frame.
2. method according to claim 1, is characterized in that, at least one in the following manner, determines horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding.
3. method according to claim 1, is characterized in that, described default paster Information Embedding rule is relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
The identification characteristics information preset comprised in rectangular area.
4. the method according to any one of claim 1-3, is characterized in that, described method also comprises:
Obtain information to be pushed;
The image information of the paster information region of having implanted in described target video frame is replaced with obtained information to be pushed.
5. the method according to any one of claim 1-3, is characterized in that, described method also comprises:
Before show described target video frame to user, obtain information to be pushed;
When showing described target video frame to user, obtained information to be pushed is covered on the paster information region of having implanted in described target video, show to user.
6. method according to claim 5, is characterized in that, described acquisition information to be pushed, comprising:
Obtain the historical viewings recorded information of user;
According to obtained historical viewings recorded information, determine information to be pushed.
7. an image information detecting device, is characterized in that, described device comprises:
Marginal point obtains module, for carrying out rim detection according to the Edge-Detection Algorithm preset to target video frame, obtains the marginal point of described target video frame;
Alternative line segment determination module, for determining alternative line segment according to obtained marginal point, wherein, described alternative line segment is through at least two marginal points, and the marginal point on alternative line segment meets: if some A and some B is in adjacent position on alternative line segment, then some A and some B is the pixel that on described target video frame, position is adjacent;
Edge line segment area determination module, for according to determined alternative line segment, determines horizontal edge line segment region and vertical edge line segment region, and wherein, horizontal edge line segment region meets: | x max_h-x min_hthe first threshold of |>=preset, | y max_h-y min_hthe Second Threshold of |≤preset, x max_h, x min_hfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_h, y min_hfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment, vertical edge line segment region meets: | x max_v-x min_v3rd threshold value of |≤preset, | y max_v-y min_v4th threshold value of |>=preset, x max_v, x min_vfor in this region comprise maximum, the minimum value of pixel horizontal direction coordinate on alternative line segment, y max_v, y min_vfor in this region comprise maximum, the minimum value of pixel vertical direction coordinate on alternative line segment;
Edge line determination module, for determining horizontal edge straight line according to determined horizontal edge line segment region, determines vertical edge straight line according to determined vertical edge line segment region;
Module is selected in rectangular area, for by determined horizontal edge straight line and the determined rectangular area of vertical edge straight line, select the rectangular area meeting default paster Information Embedding rule, as the paster information region of having implanted in described target video frame.
8. device according to claim 7, is characterized in that, described edge line segment area determination module, comprising: horizontal edge line segment region determines that submodule is determined in submodule and vertical edge line segment region;
Wherein, submodule is determined in described horizontal edge line segment region, at least one in the following manner, determines horizontal edge straight line according to determined horizontal edge line segment region:
By pixel column place straight lines maximum for marginal point quantity in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at the pixel column place straight line in this centre position, region in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
By being positioned at this region pixel column place straight line or bottom pixel column place straight line topmost in line segment region, target level edge, be defined as the horizontal edge straight line that this region is corresponding;
Submodule is determined in described vertical edge line segment region, for according to determined alternative line segment, determines vertical edge line segment region.
9. device according to claim 7, is characterized in that, described default paster Information Embedding rule is relevant at least one in following information:
The width of rectangular area and height;
The ratio of width to height of rectangular area;
Position in the video frame, rectangular area;
The identification characteristics information preset comprised in rectangular area.
10. the device according to any one of claim 7-9, is characterized in that, described device also comprises:
First pushed information obtains module, for obtaining information to be pushed;
Image information replacement module, for replacing with obtained information to be pushed by the image information of the paster information implanted in described target video frame region.
11. devices according to any one of claim 7-9, it is characterized in that, described device also comprises:
Second pushed information obtains module, for before show described target video frame to user, obtains information to be pushed;
Region overlay module, for when showing described target video frame to user, covers obtained information to be pushed on the paster information region of having implanted in described target video, shows to user.
12. devices according to claim 11, is characterized in that, described second pushed information obtains module, comprising:
Historical viewings record obtains submodule, for obtaining the historical viewings recorded information of user;
Pushed information determination submodule, for according to obtained historical viewings recorded information, determines information to be pushed.
CN201510219862.8A 2015-04-30 2015-04-30 A kind of image information detecting method and device Active CN104822069B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510219862.8A CN104822069B (en) 2015-04-30 2015-04-30 A kind of image information detecting method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510219862.8A CN104822069B (en) 2015-04-30 2015-04-30 A kind of image information detecting method and device

Publications (2)

Publication Number Publication Date
CN104822069A true CN104822069A (en) 2015-08-05
CN104822069B CN104822069B (en) 2018-09-28

Family

ID=53732216

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510219862.8A Active CN104822069B (en) 2015-04-30 2015-04-30 A kind of image information detecting method and device

Country Status (1)

Country Link
CN (1) CN104822069B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105704557A (en) * 2016-01-26 2016-06-22 天脉聚源（北京）科技有限公司 A method and apparatus for identifying icons in programs
CN108475430A (en) * 2017-04-10 2018-08-31 深圳市柔宇科技有限公司 picture quality evaluation method and device
CN110427942A (en) * 2019-08-09 2019-11-08 上海天诚比集科技有限公司 A kind of detection zone determines method
CN111556336A (en) * 2020-05-12 2020-08-18 腾讯科技（深圳）有限公司 Multimedia file processing method, device, terminal equipment and medium
CN113259713A (en) * 2021-04-23 2021-08-13 深圳信息职业技术学院 Video processing method and device, terminal equipment and storage medium
US11928863B2 (en) 2019-07-19 2024-03-12 Tencent Technology (Shenzhen) Company Limited Method, apparatus, device, and storage medium for determining implantation location of recommendation information

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101183425A (en) * 2007-12-20 2008-05-21 四川川大智胜软件股份有限公司 Guangdong and Hong Kong license plate locating method
CN101248454A (en) * 2005-08-25 2008-08-20 株式会社理光 Image processing method and image processor, digital camera equipment, and recording medium with image processing program stored thereon
US20130121595A1 (en) * 2011-11-11 2013-05-16 Hirokazu Kawatani Image processing apparatus, rectangle detection method, and computer-readable, non-transitory medium
CN103258198A (en) * 2013-04-26 2013-08-21 四川大学 Extraction method for characters in form document image

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101248454A (en) * 2005-08-25 2008-08-20 株式会社理光 Image processing method and image processor, digital camera equipment, and recording medium with image processing program stored thereon
CN101183425A (en) * 2007-12-20 2008-05-21 四川川大智胜软件股份有限公司 Guangdong and Hong Kong license plate locating method
US20130121595A1 (en) * 2011-11-11 2013-05-16 Hirokazu Kawatani Image processing apparatus, rectangle detection method, and computer-readable, non-transitory medium
CN103258198A (en) * 2013-04-26 2013-08-21 四川大学 Extraction method for characters in form document image

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
程广旭: "足球视频中的广告牌检测与替换算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑，2014年第6期》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105704557A (en) * 2016-01-26 2016-06-22 天脉聚源（北京）科技有限公司 A method and apparatus for identifying icons in programs
CN105704557B (en) * 2016-01-26 2018-06-19 天脉聚源（北京）科技有限公司 The method and device of icon in a kind of identification program
CN108475430A (en) * 2017-04-10 2018-08-31 深圳市柔宇科技有限公司 picture quality evaluation method and device
US11928863B2 (en) 2019-07-19 2024-03-12 Tencent Technology (Shenzhen) Company Limited Method, apparatus, device, and storage medium for determining implantation location of recommendation information
CN110427942A (en) * 2019-08-09 2019-11-08 上海天诚比集科技有限公司 A kind of detection zone determines method
CN110427942B (en) * 2019-08-09 2023-04-07 上海天诚比集科技有限公司 Detection area determining method
CN111556336A (en) * 2020-05-12 2020-08-18 腾讯科技（深圳）有限公司 Multimedia file processing method, device, terminal equipment and medium
CN113259713A (en) * 2021-04-23 2021-08-13 深圳信息职业技术学院 Video processing method and device, terminal equipment and storage medium

Also Published As

Publication number Publication date
CN104822069B (en) 2018-09-28

Similar Documents

Publication Publication Date Title
CN104822069A (en) Image information detection method and apparatus
EP2380358B1 (en) Creation of depth maps from images
CN100568281C (en) Create depth map
CN103069430B (en) Two-dimensional code reader and program
CN110300316B (en) Method and device for implanting push information into video, electronic equipment and storage medium
US11568644B2 (en) Methods and systems for scoreboard region detection
US11805283B2 (en) Methods and systems for extracting sport-related information from digital video frames
US20070291134A1 (en) Image editing method and apparatus
CN103080950A (en) Two-dimensional code reader and program
US11830261B2 (en) Methods and systems for determining accuracy of sport-related information extracted from digital video frames
US20210224547A1 (en) Methods and Systems for Sport Data Extraction
US11792441B2 (en) Methods and systems for scoreboard text region detection
CN113516696A (en) Video advertisement implanting method and device, electronic equipment and storage medium
JP6924932B2 (en) Mobile tracking methods, mobile tracking devices, and programs
CN104735521A (en) Method and device for detecting rolling captions
KR20100003233A (en) Method for detecting layout areas in a video image and method for generating an image of reduced size using the detection method
CN103946894A (en) Method and apparatus for dynamic placement of a graphics display window within an image
KR20010025404A (en) System and Method for Virtual Advertisement Insertion Using Camera Motion Analysis
KR100808395B1 (en) Method, system and apparatus
US20240137584A1 (en) Methods and Systems for Extracting Sport-Related Information from Digital Video Frames
KR20050008246A (en) An apparatus and method for inserting graphic images using camera motion parameters in sports video
UA154986U (en) A METHOD OF AUTOMATED DETECTION OF OBJECTS AND INFORMATIONAL AREAS ON COLOR Raster IMAGES OF THE EARTH'S SURFACE
JP2010146282A (en) Advertisement effect measuring apparatus
Kieß Adaptation of Images and Videos for Different Screen Sizes

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
C41 Transfer of patent application or patent right or utility model
TA01 Transfer of patent application right

Effective date of registration: 20151013

Address after: 100080 11, 2 North First Street, 1101 Beijing, Haidian District, Haidian

Applicant after: Beijing iQIYI Technology Co., Ltd.

Address before: A 100080 street Beijing city Haidian District North No. 2, building 10, 11 layers of Goldtron expand

Applicant before: Beijing Qiyi Century Technology Co., Ltd.

GR01 Patent grant
GR01 Patent grant