CN105631446A - Method and device for determining interactive corner mark prompt - Google Patents
Method and device for determining interactive corner mark prompt Download PDFInfo
- Publication number
- CN105631446A CN105631446A CN201510956040.8A CN201510956040A CN105631446A CN 105631446 A CN105631446 A CN 105631446A CN 201510956040 A CN201510956040 A CN 201510956040A CN 105631446 A CN105631446 A CN 105631446A
- Authority
- CN
- China
- Prior art keywords
- color
- pixel value
- connected region
- pixel
- object connected
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
Abstract
The invention discloses a method and a device for determining an interactive corner mark prompt. The method comprises steps: according to a preset color template for a preset prompt corresponding to the interactive corner mark, a target color communication area matched with the preset color template in the current video frame is determined; whether the confidence between the mark in the target color communication area and the preset prompt is larger than preset confidence is judged; and when the confidence is larger than the preset confidence, the mark in the target color communication area is determined to be the preset prompt. Through the technical scheme of the invention, automatic color detection can be carried out in the current video frame, after the target color communication area in the current video frame is determined, the confidence between the mark and the preset prompt can be determined through recognizing the mark in the target color communication area, and thus when the confidence between the two is larger than the preset confidence, the mark in the target color communication area is automatically determined to be the preset prompt.
Description
Technical field
The present invention relates to interactive footmark detection technique field, particularly to defining method and the device of a kind of interactive footmark prompt.
Background technology
At present, in program interaction process, when interactive footmark occurs, it is possible to receive the interactive signal of televiewer, and in order to confirm interactive signal better, it is necessary in time the interactive footmark occurred in telescreen is carried out detection and identify. Sometimes, for interactive needs, interactive footmark there will be prompt (as: 5s falls meter) before occurring time, footmark detection is carried out again, it is possible to reduce footmark flase drop, therefore after countdown occurs, the prompt of interactive footmark is carried out detection identification there is good meaning, but the position that prompt is on the tv screen is likely to not fix, and television video is complicated, thus increases the detection difficulty of prompt.
Summary of the invention
The present invention provides defining method and the device of a kind of interactive footmark prompt, color detection can be automatically carried out in current video frame, after determining the color of object connected region in this current video frame, by identifying the mark in this color of object connected region, may determine that the confidence level of this mark and this default prompt, and then judge whether this confidence level pre-sets reliability more than this, if both pre-set reliability more than this by confidence level, then illustrate that the similarity of this mark and this default prompt identified is higher, then can automatically determine and color of object connected region is designated default prompt, this also illustrates to have occurred in that default prompt in this current video frame in current playing program, namely this current playing program will appear from interactive footmark, user is about to participate in interaction.
The present invention provides the defining method of a kind of interactive footmark prompt, including:
Pre-set color template according to default prompt corresponding to interactive footmark, it is determined that the color of object connected region matched with described pre-set color template in current video frame;
Judge that whether the confidence level of the mark in described color of object connected region and described default prompt is more than pre-seting reliability;
When described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt.
In one embodiment, described default prompt includes: at least one countdown numeral;
The described mark judged in described color of object connected region with the confidence level of described default prompt whether more than pre-seting reliability, including:
Use the convolutional neural networks pre-build, it is determined that the confidence level of the mark in described color of object connected region and each countdown numeral at least one countdown numeral described;
The target number the highest with the confidence level of described mark is selected from least one countdown numeral described;
Determine whether confidence level corresponding to described target number pre-sets reliability more than described;
Described when described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt, including:
When confidence level corresponding to described target number more than described pre-set reliability time, it is determined that described color of object connected region is designated described target number.
In one embodiment, in determining described color of object connected region be designated described target number before, described method also includes:
Second pixel value of the first pixel value of each pixel in described color of object connected region Yu the pre-set color template of described target number is compared;
According to comparative result, the pixel value of all pixels in described color of object connected region is carried out binaryzation;
Pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, it is determined that identifying whether as described target number in described color of object connected region.
In one embodiment, described according to comparative result, the pixel value of all pixels in described color of object connected region is carried out binaryzation, including:
Judge that in described color of object connected region, whether the pixel value difference of the second pixel value of the pre-set color template of the first pixel value of each pixel and described target number is more than or equal to presetted pixel threshold value;
Described color of object connected region will be set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number less than or equal to the first pixel value of the pixel of described presetted pixel threshold value;
Described color of object connected region will be set to the second target pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number more than the first pixel value of the pixel of described presetted pixel value threshold value.
In one embodiment, the described pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, determine and described color of object connected region identifies whether as described target number, including:
Determine that whether the number of target pixel points equal with the pixel value of the pixel of relevant position in described Character mother plate in the described color of object connected region after binaryzation is more than preset number;
When the number of described target pixel points is more than described preset number, it is determined that described color of object connected region is designated described target number.
The present invention also provides for the determination device of a kind of interactive footmark prompt, including:
First determines module, for the pre-set color template of the default prompt corresponding according to interactive footmark, it is determined that the color of object connected region matched with described pre-set color template in current video frame;
Whether judge module, be used for the confidence level of mark and the described default prompt judging in described color of object connected region more than pre-seting reliability;
Second determines module, for when described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt.
In one embodiment, described default prompt includes: at least one countdown numeral;
Described judge module includes:
First determines submodule, for using the convolutional neural networks pre-build, it is determined that the confidence level of the mark in described color of object connected region and each countdown numeral at least one countdown numeral described;
Select submodule, for selecting the target number the highest with the confidence level of described mark from least one countdown numeral described;
Second determines submodule, for determining whether confidence level corresponding to described target number pre-sets reliability more than described;
Described second determines that module includes:
3rd determines submodule, for when confidence level corresponding to described target number more than described pre-set reliability time, it is determined that described color of object connected region is designated described target number.
In one embodiment, described device also includes:
Comparison module, for in determining described color of object connected region be designated described target number before, the second pixel value of the first pixel value of each pixel in described color of object connected region Yu the pre-set color template of described target number is compared;
Processing module, for according to comparative result, carrying out binaryzation by the pixel value of all pixels in described color of object connected region;
3rd determines module, for the pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, it is determined that identifying whether as described target number in described color of object connected region.
In one embodiment, described processing module includes:
Judge submodule, for judging that in described color of object connected region, whether the pixel value difference of the second pixel value of the pre-set color template of the first pixel value of each pixel and described target number is more than or equal to presetted pixel threshold value;
First arranges submodule, for being set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number less than or equal to the first pixel value of the pixel of described presetted pixel threshold value in described color of object connected region;
Second arranges submodule, for being set to the second target pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number more than the first pixel value of the pixel of described presetted pixel value threshold value in described color of object connected region.
In one embodiment, the described 3rd determines that module includes:
4th determines submodule, whether is used for the number of target pixel points equal with the pixel value of the pixel of relevant position in described Character mother plate in the described color of object connected region after determining binaryzation more than preset number;
5th determines submodule, for when the number of described target pixel points is more than described preset number, it is determined that be designated described target number in described color of object connected region.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect:
Color detection can be automatically carried out in the current video frame of current playing program, after determining the color of object connected region in this current video frame, by identifying the mark in this color of object connected region, may determine that the confidence level of this mark and this default prompt, and then judge whether this confidence level pre-sets reliability more than this, if both pre-set reliability more than this by confidence level, then illustrate that the similarity of this mark and this default prompt identified is higher, then can automatically determine and color of object connected region is designated default prompt, this also illustrates to have occurred in that default prompt in this current video frame in current playing program, namely this current playing program will appear from interactive footmark, user is about to participate in interaction.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from description, or understand by implementing the present invention. The purpose of the present invention and other advantages can be realized by structure specifically noted in the description write, claims and accompanying drawing and be obtained.
Below by drawings and Examples, technical scheme is described in further detail.
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, is used for together with embodiments of the present invention explaining the present invention, is not intended that limitation of the present invention. In the accompanying drawings:
Fig. 1 is the flow chart of the defining method of a kind of interactive footmark prompt according to an exemplary embodiment.
Fig. 2 is the flow chart of the defining method of the another kind of interactive footmark prompt according to an exemplary embodiment.
Fig. 3 is the flow chart of the defining method of the interactive footmark prompt of another according to an exemplary embodiment.
Fig. 4 is the block diagram of the determination device of a kind of interactive footmark prompt according to an exemplary embodiment.
Fig. 5 is the block diagram of the determination device of the another kind of interactive footmark prompt according to an exemplary embodiment.
Fig. 6 is the block diagram of the determination device of the interactive footmark prompt of another according to an exemplary embodiment.
Fig. 7 is the block diagram of the determination device of the interactive footmark prompt of another according to an exemplary embodiment.
Fig. 8 is the block diagram of the determination device of the interactive footmark prompt of another according to an exemplary embodiment.
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is merely to illustrate and explains the present invention, is not intended to limit the present invention.
In correlation technique, in program interaction process, when interactive footmark occurs, it is possible to receive the interactive signal of televiewer, and in order to confirm interactive signal better, it is necessary in time the interactive footmark occurred in telescreen is carried out detection and identify. Sometimes, for interactive needs, interactive footmark there will be prompt (as: 5s falls meter) before occurring time, footmark detection is carried out again, it is possible to reduce footmark flase drop, therefore after countdown occurs, the prompt of interactive footmark is carried out detection identification there is good meaning, but the position that prompt is on the tv screen is likely to not fix, and television video is complicated, thus increases the detection difficulty of prompt.
In order to solve above-mentioned technical problem, disclosure embodiment provides the defining method of a kind of interactive footmark prompt, the method is suitable in the interactive determination program of footmark prompt, system or device, its executive agent can be the equipment that intelligent television, mobile phone, computer etc. can play video, as shown in Figure 1
Step S101, the pre-set color template according to default prompt corresponding to interactive footmark, it is determined that the color of object connected region matched with described pre-set color template in current video frame;
Interactive footmark can be any one program of any one television station for the interactive footmark of user interaction (if making user participate in the prize drawing footmark of prize drawing, user can be made to participate in the movable footmark of the activity of shaking), and default prompt corresponding to this interaction footmark is usually countdown numeral, such as 5,4,3,2,1 etc., can also be word, figure, letter etc. for pointing out user interaction footmark namely to will appear from, the prompt of interactive process can be entered at once.
Additionally, when automatically identifying the color in current video frame, the essentially identical region of the color with this pre-set color template that system identification goes out (i.e. the poor less region of pixel of pixel value and the pixel value of pre-set color template in current video frame) is probably multiple zone of dispersion, now, multiple zone of dispersions of close together can be connected, thus obtaining the color of object connected region matched with pre-set color template, certainly, after connecting multiple zone of dispersions, still multiple color of object connected region it is likely to be obtained, and owing to the size in the region of this default prompt is certain, thus, the bigger connected region of area and the less connected region of area can be removed, thus using the color of object connected region close with the size in the region of the default prompt candidate region as prompt.
Step S102, it is judged that the mark in described color of object connected region with the confidence level of described default prompt whether more than pre-seting reliability;
Carrying out color detection, after determining the color of object connected region in this current video frame, by identifying the mark in this color of object connected region, it may be determined that the confidence level of this mark and this default prompt, and then judge whether this confidence level pre-sets reliability more than this.
Step S103, when described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt.
If both pre-set reliability more than this by confidence level, then illustrate that the similarity of this mark and this default prompt identified is higher, then can automatically determine and described color of object connected region is designated described default prompt, this also illustrates to have occurred in that default prompt in this current video frame in current playing program, namely this current playing program will appear from interactive footmark, user is about to participate in interaction, wherein, confidence level is more high, represent that this mark is more high with the similarity of this default prompt, the determination result that mark in this color of object connected region is exactly this default prompt is more accurate.
In one embodiment, described default prompt includes: at least one countdown numeral;
This default prompt can be at least one countdown numeral.
As in figure 2 it is shown, above-mentioned steps S102 can be performed as:
Step A1, uses the convolutional neural networks pre-build, it is determined that the confidence level of the mark in described color of object connected region and each countdown numeral at least one countdown numeral described;
Convolutional neural networks is that the video flowing training using in advance and comprising this at least one countdown numeral in a large number forms, in the training process, countdown numeral has how many kinds of, which floor the output layer of convolutional neural networks just can have, so, just can use this convolutional neural networks, the mark in different target color-connected regions is identified, to determine the confidence level of this mark respectively each countdown numeral.
Step A2, selects the target number the highest with the confidence level of described mark from least one countdown numeral described;
Step A3, it is determined that whether confidence level corresponding to described target number pre-sets reliability more than described;
It is different owing to this mark is the confidence level of each countdown numeral respectively, and the countdown numeral of the more high correspondence of confidence level, more it is probably the legitimate reading of this mark, such as: this at least one countdown numeral is 5 respectively, 4, 3, 2, 1, and this mark is 5 respectively, 4, 3, 2, the confidence level of 1 respectively 94%, 2%, 2%, 1%, 1%, then this mark is most likely to be countdown numeral 5, thus, can from least one countdown numeral, select the target number the highest with the confidence level of this mark, and in order to prevent from this mark being identified as this target number by mistake, substantially ensure that the recognition correct rate of this mark, may further determine that whether confidence level corresponding to this target number (i.e. the confidence level of this target number and this mark) pre-sets reliability (such as 0.9) more than this.
Above-mentioned steps S103 can be performed as:
Step A4, when confidence level corresponding to described target number more than described pre-set reliability time, it is determined that described color of object connected region is designated described target number.
When the confidence level that this target number is corresponding pre-sets reliability more than this, can accurately determine that the mark in this color of object connected region is exactly this target number, further relate to this current video frame in this current playing program has occurred in that this default prompt, namely will appear from interactive footmark, user is about to carry out interaction.
As it is shown on figure 3, in one embodiment, determine confidence level corresponding to target number more than described pre-set reliability after, and in determining described color of object connected region be designated described target number before, described method also includes:
Step S301, compares the second pixel value of the first pixel value of each pixel in described color of object connected region Yu the pre-set color template of described target number;
Step S302, according to comparative result, carries out binaryzation by the pixel value of all pixels in described color of object connected region;
Step S303, the pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, it is determined that identifying whether as described target number in described color of object connected region.
In determining this color of object connected region be designated this target number before, in order to prevent this mark being identified as this target number further by mistake, the second pixel value in first pixel value of pixel each in the color of object connected region pre-set color template with this target number can also be compared, and then carry out binaryzation again after being normalized by the pixel value of pixels all in color of object connected region, namely the first pixel value of pixel close with the pre-set color template of target number in color of object connected region can be set to white pixel value, first pixel value of color difference pixel farther out is set to black pixel value, and then the pixel value according to the pixel value of pixel in the color of object connected region after binaryzation with the pixel in the Character mother plate of target number, accurately determine further and described color of object connected region identifies whether as described target number, wherein, the pixel value of the pixel in Character mother plate is also through binaryzation.
In one embodiment, above-mentioned steps S302 can be performed as:
Judge that in described color of object connected region, whether the pixel value difference of the second pixel value of the pre-set color template of the first pixel value of each pixel and described target number is more than or equal to presetted pixel threshold value; Wherein, presetted pixel threshold value can be 10pixels etc., even less, wherein, presetted pixel threshold value is more little, and the color of object connected region after binaryzation is more accurate, wherein, the pre-set color template of target number monochrome often, thus the second pixel value of the pre-set color template of this target number can be a fixed pixel value, it is also possible to it is that a little pixel value is interval.
Described color of object connected region will be set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number less than or equal to the first pixel value of the pixel of described presetted pixel threshold value;
Described color of object connected region will be set to the second target pixel value with the pixel value difference of the second pixel value of respective pixel point in the pre-set color template of described target number more than the first pixel value of the pixel of described presetted pixel value threshold value.
Wherein, first object pixel value can be pixel value and the 255pixels of white, and the second target pixel value can be pixel value and the 0pixels of black.
By the first pixel value of the pixel of second pixel value close (namely pixel value difference is less than or equal to presetted pixel threshold value) of pre-set color template with this target number in color of object connected region is set to first object pixel value, first pixel value of the pixel differing farther out (namely pixel value difference is more than this presetted pixel threshold value) with the second pixel value of the pre-set color template of this target number is set to the second target pixel value, the color of the pre-set color template according to this target number can be realized, this color of object connected region is carried out binary conversion treatment.
In one embodiment, above-mentioned steps S303 can be performed as:
Determine that whether the number of target pixel points equal with the pixel value of the pixel of relevant position in described Character mother plate in the described color of object connected region after binaryzation is more than preset number, wherein, Character mother plate be describe this target number template (such as: when target number is 5, the numeral that Character mother plate describes is exactly 5, when target number is 3, the numeral that Character mother plate describes is exactly 3), and the pixel of relevant position refers in the target number of this Character mother plate in described Character mother plate, the pixel identical with each pixel position in the mark of this color of object connected region,
When the number of described target pixel points is more than described preset number, it is determined that described color of object connected region is designated described target number.
After this color of object connected region is carried out binary conversion treatment, may further determine that target pixel points equal with the pixel value of the pixel of relevant position in this Character mother plate in the color of object connected region after this binaryzation, and the specific number of these target pixel points, if greater than preset number, then think that the match is successful, it is possible to accurately determine that the mark in this color of object connected region is exactly described target number.
As shown in Figure 4, the present invention also provides for the determination device of a kind of interactive footmark prompt, including:
First determines module 401, for the pre-set color template of the default prompt corresponding according to interactive footmark, it is determined that the color of object connected region matched with pre-set color template in current video frame;
Whether judge module 402, be used for the confidence level of mark and the default prompt judging in color of object connected region more than pre-seting reliability;
Second determines module 403, for when confidence level is more than when pre-seting reliability, it is determined that be designated default prompt in color of object connected region.
As it is shown in figure 5, in one embodiment, default prompt includes: at least one countdown numeral;
Judge module 402 includes:
First determines submodule 4021, for using the convolutional neural networks pre-build, it is determined that the confidence level of the mark in color of object connected region and each countdown numeral at least one countdown numeral;
Select submodule 4022, for selecting the target number the highest with the confidence level identified from least one countdown numeral;
Second determines submodule 4023, for determining that whether confidence level corresponding to target number be more than pre-seting reliability;
Second determines that module 403 includes:
3rd determines submodule 4031, for when confidence level corresponding to target number is more than when pre-seting reliability, it is determined that be designated target number in color of object connected region.
As shown in Figure 6, in one embodiment, device also includes:
Comparison module 601, in determining color of object connected region be designated target number before, the second pixel value of the first pixel value of pixel each in color of object connected region Yu the pre-set color template of target number is compared;
Processing module 602, for according to comparative result, carrying out binaryzation by the pixel value of pixels all in color of object connected region;
3rd determines module 603, for the pixel value according to the pixel value of pixel in the color of object connected region after binaryzation with the pixel in the Character mother plate of target number, it is determined that identifying whether as target number in color of object connected region.
As it is shown in fig. 7, in one embodiment, processing module 602 includes:
Judge submodule 6021, whether be used for the first pixel value judging each pixel in the color of object connected region pixel value difference with the second pixel value of the pre-set color template of target number more than or equal to presetted pixel threshold value;
First arranges submodule 6022, for being set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of target number less than or equal to the first pixel value of the pixel of presetted pixel threshold value in color of object connected region;
Second arranges submodule 6023, for being set to the second target pixel value with the pixel value difference of the second pixel value of the pre-set color template of target number more than the first pixel value of the pixel of presetted pixel value threshold value in color of object connected region.
As shown in Figure 8, in one embodiment, the 3rd determines that module 603 includes:
4th determines submodule 6031, whether is used for the number of target pixel points equal with the pixel value of the pixel of relevant position in Character mother plate in the color of object connected region after determining binaryzation more than preset number;
5th determines submodule 6032, for when the number of target pixel points is more than preset number, it is determined that be designated target number in color of object connected region.
About the device in above-described embodiment, the concrete mode that wherein modules performs to operate has been described in detail in about the embodiment of the method, and explanation will be not set forth in detail herein.
Finally, the determination device of the interactive footmark prompt in the present invention is applicable to terminal unit. For example, it may be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, armarium, body-building equipment, personal digital assistant etc.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program. Therefore, the present invention can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect. And, the present invention can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory and optical memory etc.) wherein including computer usable program code.
The present invention is that flow chart and/or block diagram with reference to method according to embodiments of the present invention, equipment (system) and computer program describe. It should be understood that can by the combination of the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame. These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device so that the instruction performed by the processor of computer or other programmable data processing device is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing device work in a specific way, the instruction making to be stored in this computer-readable memory produces to include the manufacture of command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices provides for realizing the step of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
Obviously, the present invention can be carried out various change and modification without deviating from the spirit and scope of the present invention by those skilled in the art. So, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. the defining method of an interactive footmark prompt, it is characterised in that including:
Pre-set color template according to default prompt corresponding to interactive footmark, it is determined that the color of object connected region matched with described pre-set color template in current video frame;
Judge that whether the confidence level of the mark in described color of object connected region and described default prompt is more than pre-seting reliability;
When described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt.
2. method according to claim 1, it is characterised in that
Described default prompt includes: at least one countdown numeral;
The described mark judged in described color of object connected region with the confidence level of described default prompt whether more than pre-seting reliability, including:
Use the convolutional neural networks pre-build, it is determined that the confidence level of the mark in described color of object connected region and each countdown numeral at least one countdown numeral described;
The target number the highest with the confidence level of described mark is selected from least one countdown numeral described;
Determine whether confidence level corresponding to described target number pre-sets reliability more than described;
Described when described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt, including:
When confidence level corresponding to described target number more than described pre-set reliability time, it is determined that described color of object connected region is designated described target number.
3. method according to claim 2, it is characterised in that
In determining described color of object connected region be designated described target number before, described method also includes:
Second pixel value of the first pixel value of each pixel in described color of object connected region Yu the pre-set color template of described target number is compared;
According to comparative result, the pixel value of all pixels in described color of object connected region is carried out binaryzation;
Pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, it is determined that identifying whether as described target number in described color of object connected region.
4. method according to claim 3, it is characterised in that
Described according to comparative result, the pixel value of all pixels in described color of object connected region is carried out binaryzation, including:
Judge that in described color of object connected region, whether the pixel value difference of the second pixel value of the pre-set color template of the first pixel value of each pixel and described target number is more than or equal to presetted pixel threshold value;
Described color of object connected region will be set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number less than or equal to the first pixel value of the pixel of described presetted pixel threshold value;
Described color of object connected region will be set to the second target pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number more than the first pixel value of the pixel of described presetted pixel value threshold value.
5. method according to claim 3, it is characterised in that
The described pixel value according to the pixel in the pixel value of pixel in the described color of object connected region after binaryzation and the Character mother plate of described target number, it is determined that identify whether as described target number in described color of object connected region, including:
Determine that whether the number of target pixel points equal with the pixel value of the pixel of relevant position in described Character mother plate in the described color of object connected region after binaryzation is more than preset number;
When the number of described target pixel points is more than described preset number, it is determined that described color of object connected region is designated described target number.
6. the determination device of an interactive footmark prompt, it is characterised in that including:
First determines module, for the pre-set color template of the default prompt corresponding according to interactive footmark, it is determined that the color of object connected region matched with described pre-set color template in current video frame;
Whether judge module, be used for the confidence level of mark and the described default prompt judging in described color of object connected region more than pre-seting reliability;
Second determines module, for when described confidence level more than described pre-set reliability time, it is determined that described color of object connected region is designated described default prompt.
7. device according to claim 6, it is characterised in that
Described default prompt includes: at least one countdown numeral;
Described judge module includes:
First determines submodule, for using the convolutional neural networks pre-build, it is determined that the confidence level of the mark in described color of object connected region and each countdown numeral at least one countdown numeral described;
Select submodule, for selecting the target number the highest with the confidence level of described mark from least one countdown numeral described;
Second determines submodule, for determining whether confidence level corresponding to described target number pre-sets reliability more than described;
Described second determines that module includes:
3rd determines submodule, for when confidence level corresponding to described target number more than described pre-set reliability time, it is determined that described color of object connected region is designated described target number.
8. device according to claim 7, it is characterised in that described device also includes:
Comparison module, for in determining described color of object connected region be designated described target number before, the second pixel value of the first pixel value of each pixel in described color of object connected region Yu the pre-set color template of described target number is compared;
Processing module, for according to comparative result, carrying out binaryzation by the pixel value of all pixels in described color of object connected region;
3rd determines module, for the pixel value according to the pixel value of pixel in the described color of object connected region after binaryzation with the pixel in the Character mother plate of described target number, it is determined that identifying whether as described target number in described color of object connected region.
9. device according to claim 8, it is characterised in that
Described processing module includes:
Judge submodule, for judging that in described color of object connected region, whether the pixel value difference of the second pixel value of the pre-set color template of the first pixel value of each pixel and described target number is more than or equal to presetted pixel threshold value;
First arranges submodule, for being set to first object pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number less than or equal to the first pixel value of the pixel of described presetted pixel threshold value in described color of object connected region;
Second arranges submodule, for being set to the second target pixel value with the pixel value difference of the second pixel value of the pre-set color template of described target number more than the first pixel value of the pixel of described presetted pixel value threshold value in described color of object connected region.
10. device according to claim 8, it is characterised in that
Described 3rd determines that module includes:
4th determines submodule, whether is used for the number of target pixel points equal with the pixel value of the pixel of relevant position in described Character mother plate in the described color of object connected region after determining binaryzation more than preset number;
5th determines submodule, for when the number of described target pixel points is more than described preset number, it is determined that be designated described target number in described color of object connected region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510956040.8A CN105631446B (en) | 2015-12-17 | 2015-12-17 | A kind of determination method and device interacting footmark prompt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510956040.8A CN105631446B (en) | 2015-12-17 | 2015-12-17 | A kind of determination method and device interacting footmark prompt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105631446A true CN105631446A (en) | 2016-06-01 |
| CN105631446B CN105631446B (en) | 2019-04-26 |
Family
ID=56046359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510956040.8A Expired - Fee Related CN105631446B (en) | 2015-12-17 | 2015-12-17 | A kind of determination method and device interacting footmark prompt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631446B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108235119A (en) * | 2018-03-15 | 2018-06-29 | 联想(北京)有限公司 | Method for processing video frequency and device, electronic equipment and computer-readable medium |
| CN110996094A (en) * | 2019-11-01 | 2020-04-10 | 北京奇艺世纪科技有限公司 | Method and device for detecting video jamming, computer equipment and storage medium |
| CN115225815A (en) * | 2022-06-20 | 2022-10-21 | 南方科技大学 | Target intelligent tracking shooting method, server, shooting system, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299239A (en) * | 2008-06-06 | 2008-11-05 | 北京中星微电子有限公司 | Method and device for acquiring character area image and character recognition system |
| CN102708651A (en) * | 2012-05-23 | 2012-10-03 | 无锡蓝天电子有限公司 | Image type smoke fire disaster detection method and system |
| CN104573697A (en) * | 2014-12-31 | 2015-04-29 | 西安丰树电子科技发展有限公司 | Construction hoist lift car people counting method based on multi-information fusion |
-
2015
- 2015-12-17 CN CN201510956040.8A patent/CN105631446B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299239A (en) * | 2008-06-06 | 2008-11-05 | 北京中星微电子有限公司 | Method and device for acquiring character area image and character recognition system |
| CN102708651A (en) * | 2012-05-23 | 2012-10-03 | 无锡蓝天电子有限公司 | Image type smoke fire disaster detection method and system |
| CN104573697A (en) * | 2014-12-31 | 2015-04-29 | 西安丰树电子科技发展有限公司 | Construction hoist lift car people counting method based on multi-information fusion |
Non-Patent Citations (2)
| Title |
|---|
| 杨心: "基于卷积神经网络的交通标识识别研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈国玉: "序列图像中运动目标检测算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108235119A (en) * | 2018-03-15 | 2018-06-29 | 联想(北京)有限公司 | Method for processing video frequency and device, electronic equipment and computer-readable medium |
| CN108235119B (en) * | 2018-03-15 | 2021-02-19 | 联想(北京)有限公司 | Video processing method and device, electronic equipment and computer readable medium |
| CN110996094A (en) * | 2019-11-01 | 2020-04-10 | 北京奇艺世纪科技有限公司 | Method and device for detecting video jamming, computer equipment and storage medium |
| CN115225815A (en) * | 2022-06-20 | 2022-10-21 | 南方科技大学 | Target intelligent tracking shooting method, server, shooting system, equipment and medium |
| CN115225815B (en) * | 2022-06-20 | 2023-07-25 | 南方科技大学 | Intelligent target tracking shooting method, server, shooting system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631446B (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108885699B (en) | Character recognition method, device, storage medium and electronic equipment | |
| US20210042474A1 (en) | Method for text recognition, electronic device and storage medium | |
| CN106598527B (en) | The method and apparatus of position of display unit in identification display equipment | |
| CN106559688A (en) | The upgrading test method and apparatus of remote control | |
| CN112637842B (en) | Screen projection equipment connection method, system, equipment and storage medium | |
| CN108764000B (en) | Two-dimensional code fast decoding method | |
| CN103634652A (en) | Station caption identification method, station caption identification device, TV (Television) and station caption identification system | |
| CN105631446A (en) | Method and device for determining interactive corner mark prompt | |
| CN105740010A (en) | Power-on method and terminal equipment | |
| CN104618316A (en) | Method, device and system of safety verification | |
| CN108717542B (en) | Method and device for recognizing character area and computer readable storage medium | |
| CN111126108A (en) | Training method and device of image detection model and image detection method and device | |
| CN103902875A (en) | Verification code image generating method and device and verification method and device | |
| CN110895602B (en) | Identity authentication method and device, electronic equipment and storage medium | |
| CN113190106B (en) | Gesture recognition method and device and electronic equipment | |
| CN113705389A (en) | Face recognition module testing method and device, storage medium and electronic equipment | |
| CN113112511A (en) | Method and device for correcting test paper, storage medium and electronic equipment | |
| CN106249968B (en) | Scanning method and device | |
| CN112465497A (en) | Payment method, payment device, electronic equipment and medium | |
| CN112840305B (en) | Font switching method and related product | |
| US10613622B2 (en) | Method and device for controlling virtual reality helmets | |
| CN110597593B (en) | User-guided task processing method and device, computer equipment and storage medium | |
| CN113850238B (en) | Document detection method and device, electronic equipment and storage medium | |
| CN108924614B (en) | Control method, control system and electronic equipment | |
| CN115035530A (en) | Image processing method, image text obtaining method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method and device for determining interactive corner mark prompt Effective date of registration: 20200420 Granted publication date: 20190426 Pledgee: Zhongguancun Beijing technology financing Company limited by guarantee Pledgor: Tvmining (BEIJING) Technology Co., Ltd. Registration number: Y2020990000346 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190426 Termination date: 20211217 |