WO2018000699A1 - 一种电视频道识别方法、装置及电视机、服务器 - Google Patents

一种电视频道识别方法、装置及电视机、服务器 Download PDF

Info

Publication number
WO2018000699A1
WO2018000699A1 PCT/CN2016/106703 CN2016106703W WO2018000699A1 WO 2018000699 A1 WO2018000699 A1 WO 2018000699A1 CN 2016106703 W CN2016106703 W CN 2016106703W WO 2018000699 A1 WO2018000699 A1 WO 2018000699A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
channel
reference image
identified
sad value
Prior art date
Application number
PCT/CN2016/106703
Other languages
English (en)
French (fr)
Inventor
唐江杰
Original Assignee
乐视控股（北京）有限公司
乐视致新电子科技（天津）有限公司
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 乐视控股（北京）有限公司, 乐视致新电子科技（天津）有限公司 filed Critical 乐视控股（北京）有限公司
Publication of WO2018000699A1 publication Critical patent/WO2018000699A1/zh

Links

Images

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
    • H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
    • 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]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
    • H04N21/4334—Recording operations
    • 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]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • 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]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • 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]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations

Definitions

  • the invention belongs to the field of smart televisions, and in particular relates to a television channel identification method and device, and a television set and a server.
  • TV channel access methods for smart TVs.
  • One is to obtain the video channel of the TV channel through the Internet, and the other is to obtain the video source of the TV channel through the signal transmitted by the receiver's top box.
  • the signal TV input from the set-top box HDMI interface has no program list, so the smart TV cannot know the TV channel currently viewed by the user and the corresponding specific program content.
  • One of the characteristics of smart TV is to emphasize interactivity. If the smart TV cannot know the TV channel and the specific program content that the user is currently watching, the interaction will not be realized. For this reason, the smart TV needs to be able to automatically discriminate the TV channel.
  • the existing television channel is identified by intercepting the image of the current television screen, and further intercepting the logo in the image, and acquiring the channel information through the logo matching in the background.
  • the intercepted logo contains a background image. If the background image and the station logo are highly confluent, there will be cases where the logo cannot be recognized. The logo needs to be re-intercepted. Since the background image of the TV program screen as the logo is constantly changing, it is necessary to intercept the TV screen multiple times until the detection. TV channel identification can be completed after a clear and complete logo, which will take a long time and is not real-time.
  • the traditional image similarity comparison uses a relatively large amount of algorithms, such as Scale Invariant Feature Transform (SIFT), which occupies large system resources.
  • SIFT Scale Invariant Feature Transform
  • the present invention provides a television channel identification method and apparatus, and a television set and a server, so as to solve the problem that the existing television channel identification method is low in efficiency, lack of real-time performance, and the similarity calculation algorithm of the traditional picture consumes a large amount of system resources. problem.
  • the present invention provides a television channel identification method, and the method specifically includes:
  • the channel information of the corresponding reference image is read according to the absolute error of the value lower than the preset threshold and the corresponding reference image is obtained, and the channel information is the channel information of the to-be-identified channel.
  • the server further includes a segmentation module, configured to divide the to-be-identified channel image and the reference image into at least two image units.
  • the operation processing module specifically includes:
  • a data acquisition unit configured to acquire the image of the channel to be identified and the image data of the image unit in the reference image
  • a calculating unit configured to sequentially calculate, according to the image data of the image unit, a unit SAD value of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • the value unit is configured to obtain a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the reference image acquisition module stores the image of the real-time television channel according to the preset acquisition frequency as a new reference image, adds a time stamp to the new reference image, and deletes the original reference image of the time stamp.
  • the present invention further provides a television channel identification device, where the device specifically includes:
  • a channel image obtaining module to be identified configured to acquire a channel image to be identified with a time stamp
  • a reference image obtaining module configured to acquire a reference image based on the time stamp
  • An operation processing module configured to calculate a SAD value of the to-be-identified channel image and the reference image
  • a judging module configured to compare the SAD value with a preset threshold, and if the SAD value is lower than a preset threshold, acquire channel information of a reference image corresponding to the SAD value, where the channel information is a TV channel to be identified Channel information.
  • the server further includes a segmentation module, configured to divide the to-be-identified channel image and the reference image into at least two image units.
  • the operation processing module specifically includes:
  • a data acquisition unit configured to acquire the image of the channel to be identified and the image data of the image unit in the reference image
  • a calculating unit configured to sequentially calculate, according to the image data of the image unit, a unit SAD value of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • the value unit is configured to obtain a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the reference image acquisition module stores the image of the real-time television channel according to the preset acquisition frequency as a new reference image, adds a time stamp to the new reference image, and deletes the original reference image of the time stamp.
  • the present invention also provides a television set, including a television channel identification device, the television channel identification device comprising:
  • a channel image obtaining module to be identified configured to acquire a channel image to be identified with a time stamp
  • a reference image obtaining module configured to acquire a reference image based on the time stamp
  • An operation processing module configured to calculate a SAD value of the to-be-identified channel image and the reference image
  • a determining module configured to compare the SAD value with a preset threshold, and if the SAD value is lower than a preset threshold, acquire channel information of a reference image corresponding to the SAD value, where the channel information is to be recognized Do not channel information of the TV channel.
  • the server further includes a segmentation module, configured to divide the to-be-identified channel image and the reference image into at least two image units.
  • the operation processing module specifically includes:
  • a data acquisition unit configured to acquire the image of the channel to be identified and the image data of the image unit in the reference image
  • a calculating unit configured to sequentially calculate, according to the image data of the image unit, a unit SAD value of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • the value unit is configured to obtain a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the reference image acquisition module stores the image of the real-time television channel according to the preset acquisition frequency as a new reference image, adds a time stamp to the new reference image, and deletes the original reference image of the time stamp.
  • the present invention further provides a server, including a television channel identification device, where the television channel identification device includes:
  • a channel image obtaining module to be identified configured to acquire a channel image to be identified with a time stamp
  • a reference image obtaining module configured to acquire a reference image based on the time stamp
  • An operation processing module configured to calculate a SAD value of the to-be-identified channel image and the reference image
  • a judging module configured to compare the SAD value with a preset threshold, and if the SAD value is lower than a preset threshold, acquire channel information of a reference image corresponding to the SAD value, where the channel information is a TV channel to be identified Channel information.
  • the server further includes a segmentation module, configured to divide the to-be-identified channel image and the reference image into at least two image units.
  • the operation processing module specifically includes:
  • a data acquisition unit configured to acquire the image of the channel to be identified and the image data of the image unit in the reference image
  • a calculating unit configured to sequentially calculate, according to the image data of the image unit, a unit SAD value of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • the value unit is configured to obtain a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the reference image acquisition module stores the image of the real-time television channel according to the preset acquisition frequency as a new reference image, adds a time stamp to the new reference image, and deletes the original reference image of the time stamp.
  • an embodiment of the present invention provides a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores program instructions, when the terminal device executes the program instructions, to perform:
  • the method is further configured to:
  • the to-be-identified channel image and the reference image are segmented into at least two image units according to a segmentation instruction.
  • the calculating, by the operation processing instruction, the SAD value of the to-be-identified channel image and the reference image specifically for performing:
  • the largest unit SAD value is obtained according to the value command and used as the SAD value of the channel image to be identified and the reference image.
  • the terminal device executes the program instruction, it is further configured to execute:
  • the reference image is updated in real time according to the update instruction, and the image of the real-time collection TV channel is stored as a new reference image according to the preset acquisition frequency, and a time stamp is added for the new reference image, and the original reference image of the time label is deleted.
  • an embodiment of the present invention provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instruction is used by the terminal device When executed, the terminal device is caused to perform the above method.
  • the television channel identification method and device provided by the present invention compare the overall image of the program to be identified with the reference image acquired at the same time or adjacent time by calculating the absolute error sum, without the need to intercept the logo. Avoid the low matching rate caused by the unclearness of the intercepted station logo and the additional screenshot matching operation and matching delay problem, so that the current TV channel information and program information can be obtained quickly and in real time; and the absolute error is calculated simultaneously.
  • the algorithm is simple, and the comparison result can be quickly obtained. Compared with the conventional image recognition algorithm for image similarity judgment, system resources are saved.
  • FIG. 1 is a flow chart of a television channel identification method according to Embodiment 1 of the present invention.
  • FIG. 2a is a flow chart of a television channel identification method according to Embodiment 2 of the present invention.
  • FIG. 2b is a block diagram of a SAD value calculation process according to Embodiment 2 of the present invention.
  • FIG. 2c is a schematic diagram of image segmentation according to Embodiment 2 of the present invention.
  • 2d is a diagram showing a pixel distribution of an image unit according to Embodiment 2 of the present invention.
  • FIG. 3 is a schematic structural diagram of a television channel identification apparatus according to Embodiment 3 of the present invention.
  • FIG. 4a is a schematic structural diagram of a television channel identification apparatus according to Embodiment 4 of the present invention.
  • FIG. 4b is a schematic structural diagram of an operation processing module according to Embodiment 4 of the present invention.
  • FIG. 5 is a schematic structural diagram of a television set according to Embodiment 5 of the present invention.
  • FIG. 6 is a schematic structural diagram of a server according to Embodiment 6 of the present invention.
  • references to "an embodiment” herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the invention.
  • the appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive.
  • Those skilled in the art understand, explicitly and implicitly, that the embodiments described herein may be The combination of the examples.
  • FIG. 1 provides a processing flow of a television channel identification method, and the processing flow of the method specifically includes the following steps:
  • Step 01 Obtain a channel image to be identified with a time stamp.
  • the television of the embodiment of the invention preferably refers to a smart television, and the channel image to be identified is acquired from the smart television end. Specifically, the channel image currently being played is obtained from the television terminal as the channel image to be recognized based on the specific screen capture triggering operation.
  • the screen image obtained by the smart TV may be obtained by acquiring the program image.
  • the screen capture module triggers the screen capture to require the corresponding trigger operation, and the screen capture trigger operation has the following forms:
  • the timing trigger is performed by the screen capture module to intercept the channel image currently being played by the smart TV based on a certain time interval, and the time interval can be arbitrarily set.
  • the minimum value of the time interval is not lower than between two adjacent video frames.
  • the time interval depends on the frame rate of the source video of the TV program. For example, a TV with NTSC (National Television System Committee) has a video frame rate of 30 fps, and the minimum screen interval is 100/3 milliseconds, which is less than 100. The /3 millisecond screen capture will cause the screen capture module to intercept the same screen multiple times, which will waste system resources.
  • the video frame rate of the PAL (Phase Alternating Line) system is 25 fps, and the corresponding minimum screen interval is 40 ms.
  • the user operation is detected to trigger the screen capture, and when the user switches the television channel, the television may appear black screen, sound interruption or pause.
  • the screen capture action can be triggered by directly detecting the channel switching operation.
  • the user operation triggers the screen capture to have a higher priority than the timing trigger, that is, the television system performs a certain image capture based on the timing trigger, and is preset.
  • the TV system detects the channel switching operation again, then it will The screen image is directly intercepted without having to wait for a preset time interval, so that the television channel image that the user is currently watching can be obtained in real time.
  • the intercepted image and the corresponding intercepting time may be stored in the following form, wherein the file name is automatically named by the screen module of the television system, and the format of the time label is freely set, and the picture name and time label shown in the table are only one type.
  • Step 02 Acquire a reference image based on the time stamp.
  • the reference image needs to be acquired in the background, and the background information of all television channels is included in the background.
  • the acquired reference image is associated with the corresponding television channel information.
  • all the TV channels in the background also intercept the program image synchronously, and the frequency of intercepting the image in the background is not lower than the frequency of the intercepted image of the smart TV end.
  • the background screenshot frequency is equal to the video of the TV channel.
  • the frame rate allows the background to capture all video frames of all channels to ensure that the same image as the video channel image is matched in the reference image.
  • the background adds a time stamp to the captured image while the image is being captured.
  • the image captured in the background is stored as a reference image for discriminating the television channel in the background memory.
  • the system time of the television is consistent with the system time in the background, so when the television channel is discriminated, the time label according to the channel image to be identified may be used.
  • Matching the reference image with the same time label from the background storage, the matching reference image has at least one, the specific number depends on the number of TV channels connected in the background, if the current background access 168 TV channels, the corresponding one based on one The time stamp will get 168 reference images.
  • the television channel in the background can be different regions of the world, generally rooted According to the regional information
  • the television channel is initially screened to obtain the television channel within the domain of the smart television.
  • the fast screening of the television channel according to different regions can be realized by the positioning module of the smart television. Matching the reference image from the filtered TV channel will reduce the time required to match the reference image and improve matching efficiency.
  • the background image is preferably stored in the background, and the image of the real-time collection TV channel is stored as a new reference image according to the preset collection frequency. And adding a time stamp to the new reference image, and the stored reference image forms a reference image library.
  • the original reference image of the time stamp is deleted from the reference image library, and the reference image is updated in real time. Library.
  • Step 04 Calculate a SAD value of the to-be-identified channel image and the reference image.
  • Step 05 Compare the SAD value with a preset threshold, and if the SAD value is lower than the preset threshold, acquire channel information of the reference image corresponding to the SAD value, where the channel information is channel information of the channel to be identified. .
  • the SAD value indicates whether the channel image to be identified and the reference image are identical.
  • the SAD values of the two images will be zero, however there are unknown influencing factors that may cause the SAD value to be non-zero, such as image noise, in the embodiment of the present invention, if The SAD value of the two images is lower than a certain preset threshold, and the channel image to be identified can still be considered to be the same as the reference image, wherein the preset threshold can be set manually or automatically obtained through machine training. If it is determined that a certain SAD value is lower than a preset threshold, it is determined that the reference image corresponding to the SAD value is The channel image to be identified is the same. Further, the channel information associated with the reference image corresponding to the SAD value and the program information currently being played are acquired, thereby obtaining channel information of the channel to be identified and program information currently being played.
  • the embodiment of the present invention calculates the SAD value of the channel image to be identified and the reference image, and further determines the TV channel information to be identified based on the analysis of the SAD value, and on the one hand, does not need to intercept the station logo in the channel image to be identified, thereby reducing the matching. Steps to avoid the problem that the identification of the logo is low due to the background of the captured logo, which ensures the real-time recognition of the television channel; on the other hand, the algorithm used in the conventional image comparison compares the similarity of the image.
  • the discrimination of the TV channel needs to compare whether the images are the same, so the traditional image similarity comparison and the application scene of the television channel discrimination are different, and the traditional image comparison algorithm has a large amount of computation, and the traditional image comparison method In comparison, the image comparison scheme used in the embodiment of the present invention reduces the amount of computation, thereby saving system resources.
  • Step 01 Obtain a channel image to be identified with a time stamp.
  • This step is the same as the step 01 described in the first embodiment. Specifically, the channel image currently being played is acquired from the television terminal as the to-be-identified channel image based on the specific screen capture triggering operation.
  • Step 02 Acquire a reference image based on the time stamp.
  • This step is the same as the step 02 described in the first embodiment. It should be additionally noted that there is a situation in which the system time of different devices or servers is different due to the hardware or network of the terminal device. Matching the reference image having the same time stamp from the background, the obtained reference image necessarily does not contain the same reference image as the channel image to be matched, so that the television channel cannot be identified.
  • the present invention provides a preferred embodiment, that is, expanding the reference image search range, specifically, acquiring a reference image before and after the time label of the channel image to be identified, and setting a first time threshold, based on the time label, according to the first
  • the time threshold obtains a reference image within a time threshold before and after the time label, for example,
  • the first time threshold is 1 s
  • the time label of the existing to-be-identified channel image Pic2 is 2016-5-115:23:26.160
  • the corresponding background is obtained from the background 2016-5-1 15:23:25.160 to 2016-5 -115:23:27.160
  • the reference image in the time period.
  • the search can be continued by setting the second time threshold, and so on.
  • Step 03 Segment the channel image to be identified and the reference image into at least two image units.
  • the image unit is a fixed size pixel block, and the size of the pixel block includes but is not limited to 8 ⁇ 8, 16 ⁇ 16 or 32 ⁇ 16, 32 ⁇ 32, and the like.
  • Step 04 Calculate a SAD value of the to-be-identified channel image and the reference image.
  • the specific process of calculating the SAD value of the channel image to be identified and the reference image is as follows, as shown in FIG. 2b:
  • Step 041 Obtain the image of the channel to be identified and the image data of the image unit in the reference image;
  • Obtaining the image data of the unit picture specifically refers to acquiring the pixel value of each pixel in the picture.
  • the YUV value is used to represent the pixel value.
  • the RGB value may be used to represent the pixel value, the YUV value and the RGB value. Can be converted to each other.
  • Step 042 calculating, according to the image data of the image unit, unit SAD values of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • Step 043 Acquire a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the largest unit SAD value is obtained by comparing all unit SAD values.
  • Step 05 Compare the SAD value with a preset threshold, and if the SAD value is lower than the preset threshold, acquire channel information of the reference image corresponding to the SAD value, where the channel information is channel information of the channel to be identified. .
  • Solution 1 Calculate a SAD value and perform a comparison operation with the preset threshold, such as the existing The other channel image Pic000 has 168 reference images, which are Pic001, Pic002, ..., Pic167, Pic168, first calculate the SAD value of Pic000 and Pic001, record it as SAD1, compare SAD1 with the preset threshold, if SAD1 is less than the pre- Set the threshold, Pic001 is the same image as Pic000, then the SAD value of Pic000 and other reference images will not be calculated. If SAD1 is greater than the preset threshold, calculate the SAD value of Pic000 and Pic002, record it as SAD2, then SAD2 and Preset threshold comparisons, and so on, until a SAD value less than a preset threshold is obtained.
  • the preset threshold such as the existing The other channel image Pic000 has 168 reference images, which are Pic001, Pic002, ..., Pic167, Pic168, first calculate the SAD value of Pic000 and Pic001, record it as SAD1, compare SAD1 with the preset threshold,
  • Solution 2 Calculate all SAD values first, and then compare them with preset thresholds.
  • the SAD value may be compared with the preset threshold one by one until a SAD value smaller than the preset threshold is obtained, or all SAD values may be compared first, and after obtaining the minimum SAD value, the minimum SAD value is compared with the preset threshold.
  • the calculation process of the SAD value is specifically described by dividing the two pictures into squares of 16 ⁇ 16 (pixel units), as shown in FIG. 2c, the channel image and the reference to be identified are as shown in FIG. 2c.
  • the image is divided into a plurality of image units of 16 ⁇ 16 (pixel units).
  • the unit picture in this embodiment is a square containing 256 pixel points, and the unit picture P1 in FIG. 2c is enlarged to obtain a square map as shown in FIG. 2d, and each small square is one pixel point.
  • the unit SAD value is calculated by acquiring the pixel value of the image unit at the P1 position, and the formula for calculating the SAD value of the image unit is as follows:
  • A refers to the set of values of x and y. As shown in Figure 2d, the values of x and y in this embodiment are all [0, 15], and correspondingly, set A Contains 256 elements.
  • the image to be compared is divided into a plurality of image units, and the SAD value of the image unit is first acquired and then compared to avoid the misjudgment caused by the large area similarity of the two images.
  • the TV channel identification device includes the channel image acquisition module 11 to be identified, the reference image acquisition module 12, the operation processing module 14, and the discrimination module 15.
  • the to-be-identified channel image acquisition module 11 is configured to acquire a channel image to be identified with a time stamp. Specifically, the to-be-identified channel image acquiring module 11 sends the to-be-identified channel image acquisition request to the smart television end, and acquires the channel image currently being played as the to-be-identified channel image from the television end.
  • the reference image acquisition module 12 is configured to acquire at least one reference image based on the time stamp. Specifically, the reference image obtaining module 12 obtains the reference image from the storage module in the background according to the time label of the channel image to be identified, and the matched reference image has at least one, and the specific number depends on the number of TV channels connected in the background, if Currently, 168 TV channels are connected in the background, and corresponding 168 reference images will be obtained based on a time stamp.
  • the reference image obtaining module 12 may further perform preliminary screening on the television channel according to the geographic location, obtain a television channel in the domain of the smart television, and match the reference image from the filtered television channel, thereby reducing the matching reference image. The time required to improve the matching efficiency.
  • the reference image acquiring module 12 stores the image of the real-time television channel according to the preset acquisition frequency as a new reference image, adds a time label to the new reference image, deletes the original reference image of the time label, and updates the reference image in real time. Library.
  • the operation processing module 14 is configured to calculate the SAD value of the channel image to be identified and the reference image. Specifically, the operation processing module 14 acquires the image data of the to-be-identified channel image and the reference image, and sequentially calculates the SAD value of the to-be-identified channel image and the at least one reference image;
  • the determining module 15 is configured to compare the SAD value with a preset threshold, and if the SAD value is lower than the preset threshold, acquire channel information of the reference image corresponding to the SAD value, where the channel information is a TV channel to be identified. Channel information. Specifically, the SAD value is sequentially compared with a preset threshold, and the preset threshold is not negative. If the determining module 15 determines that a certain SAD value is lower than the preset threshold, determining the reference image corresponding to the SAD value and the to-be-identified The channel images are the same. Further, the channel information associated with the reference image corresponding to the SAD value is obtained, thereby obtaining channel information of the channel to be identified. It should be noted that the processing procedure of each module of the television channel identification apparatus provided in this embodiment may refer to the corresponding technical solutions in the first embodiment and the second embodiment, and details are not described herein again.
  • the television channel identification device provided by the embodiment of the present invention calculates the SAD value of the channel image to be identified and the reference image, and further determines the television channel information to be identified based on the analysis of the SAD value, and does not need to intercept the channel to be identified in the channel to be identified.
  • the station logo reduces the matching step and avoids the problem that the logo recognition efficiency is low due to the inclusion of the background of the captured logo screen, which ensures the real-time recognition of the TV channel; on the other hand, the comparison of the algorithms used in the conventional image comparison The image similarity is large, and the amount of calculation is large.
  • the television channel identification device provided by the embodiment of the present invention has less computational complexity when performing image comparison, and saves system resources.
  • the television channel identification device provided by the embodiment of the present invention further includes a segmentation module 13 for dividing the to-be-identified channel image and the reference image based on a preset size. Divided into at least two image units. Specifically, the segmentation module 13 divides the to-be-identified channel image and the reference image into a plurality of image units based on the same preset size, and the image units are adjacent but not overlapping each other, wherein the preset size is based on a pixel unit. Dividing the size, correspondingly, the image unit is a fixed size pixel block, and the size of the pixel block includes but is not limited to 8 ⁇ 8, 16 ⁇ 16 or 32 ⁇ 16, 32 ⁇ 32, etc.
  • the operation processing module 14 of the television channel identification device includes:
  • the data acquisition unit 141 is configured to acquire the image of the image to be identified and the image data of the image unit in the reference image; specifically, obtain the pixel value of each pixel in the image.
  • the calculating unit 142 is configured to sequentially calculate, according to the image data of the image unit, a unit SAD value of the image unit corresponding to the position in the channel image to be identified and the reference image;
  • A refers to the set of values of x and y.
  • the value unit 143 is configured to obtain a maximum unit SAD value and use it as the SAD value of the to-be-identified channel image and the reference image.
  • the largest unit SAD value is obtained by comparing all unit SAD values.
  • the television channel identification device provided by the embodiment of the present invention divides the image to be compared into a plurality of image units, and firstly acquires the SAD value of the image unit and then compares the purpose of avoiding the large area similarity of the two images, and in different local situations. There was a misjudgment.
  • an embodiment of the present invention provides a television set.
  • the television set 2 includes the television channel identification apparatus 1 according to the foregoing embodiment.
  • the specific structure of the television channel identification apparatus 1 is not described herein.
  • This embodiment provides an alternative, in which the television channel identification device 1 built in the television 2 acquires a reference image from the server 3 end.
  • the television provided by the embodiment of the invention can obtain the TV program viewed by the user in real time through the built-in TV channel identification device, and can be used for statistical viewing rate and pushing interactive content according to the user's viewing behavior, or advertising push, TV program derivative promotion, etc. It can not only provide a marketing platform for TV program providers, but also enrich the user's viewing experience.
  • an embodiment of the present invention provides a server.
  • the server 3 includes the television channel identification device 1 according to the foregoing embodiment.
  • the specific structure of the television channel identification device 1 is not described herein.
  • This embodiment provides an alternative, in which the TV channel identification device 1 on the server 3 side obtains the channel image to be identified from the TV 2 end.
  • the server provided by the embodiment of the present invention can obtain the TV program viewed by the user in real time through the TV channel identification device, and can be used for statistical viewing rate and pushing interactive content according to the user's viewing behavior, or advertising push, TV program derivative promotion, etc. It can provide a marketing platform for TV program providers, and at the same time enrich the user's viewing experience.
  • the embodiment of the present invention provides a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores program instructions, when the terminal device executes the program instructions, is used to execute any of the foregoing method embodiments. Methods and steps.
  • An embodiment of the present invention provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by the terminal device,
  • the terminal device performs the methods and steps in any of the foregoing method embodiments.
  • the sub-process can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules is only a logical function division.
  • multiple modules or components may be combined. Or it can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or module, and may be electrical, mechanical or otherwise.
  • the modules described as separate components may or may not be physically separated.
  • the components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .
  • ROM read-only memory
  • RAM random access memory
  • magnetic disk or an optical disk, and the like, which can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Image Analysis (AREA)

Abstract

本发明实施例属于智能电视领域，提供电视频道识别方法、装置，其中所述方法包括：获取带有时间标签的待识别频道图像；基于所述时间标签获取基准图像；计算所述待识别频道图像和所述基准图像的SAD值；将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。所述装置包括：待识别频道图像获取模块、基准图像获取模块、运算处理模块、判断模块。还提供包含电视频道识别装置的电视机、服务器。通过本发明实施例可提高电视频道识别方式效率，保证实时性，节省系统资源。

Description

一种电视频道识别方法、装置及电视机、服务器
本申请要求申请号为CN 2016104800166、申请日为2016年06月27日、发明名称为“一种电视频道识别方法、装置及电视机、服务器”的中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
【技术领域】
本发明属于智能电视领域，尤其涉及一种电视频道识别方法、装置及电视机、服务器。
【背景技术】
当前智能电视的电视频道接入方式主要有两种，一种是通过互联网获取电视频道视频源，另一种是通过接收机顶盒传输的信号来获取电视频道视频源，然而对于后一种接入方式而言，从机顶盒HDMI接口输入的信号电视没有节目单，因而智能电视无法获悉用户当前观看的电视频道以及对应的具体节目内容。
智能电视的一个特性是强调互动性，如果智能电视无法得知用户当前观看的电视频道以及具体的节目内容，将无法实现互动，为此智能电视需要能够自动判别电视频道。
在实现本发明过程中，发明人发现现有技术中至少存在如下问题：
现有一种电视频道的识别方式是通过截取当前电视屏幕的图像，并进一步地截取图像中的台标，在后台通过台标匹配获取频道信息。这种识别方式存在一个问题，即截取的台标包含背景画面。如果背景画面和台标融合度高时，会出现无法识别台标的情况，需要重新截取台标，由于电视节目画面作为台标的背景画面是不停变化的，导致需要多次截取电视画面，直到检测到清晰完整的台标后才能完成电视频道识别，此过程将耗费较长时间，且实时性不够。
另一方面，传统的图片相似比较所采用的算法运算量比较大，比如尺度不变特征变换匹配算法(Scale Invariant Feature Transform(SIFT))，占用较大系统资源。
【发明内容】
为了解决上述问题，本发明提供一种电视频道识别方法、装置及电视机、服务器，以解决现有电视频道识别方式效率低、实时性不够以及传统图片的相似比较算法运算量大占用系统资源的问题。
第一方面，本发明提供一种电视频道识别方法，方法具体包括：
获取带有时间标签的待识别频道图像；
基于所述时间标签获取至少一幅基准图像；
获取所述待识别频道图像和所述基准图像的图像数据，依次计算所述待识别频道图像和所述至少一幅基准图像的绝对误差和；
将所述绝对误差和依次与预设阈值进行比较，获得数值低于预设阈值的绝对误差和；
根据所述数值低于预设阈值的绝对误差和获得对应的基准图像，读取对应的基准图像的频道信息，所述频道信息即为所述待识别频道的频道信息。
进一步的，所述服务器还包括分割模块，用于将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
进一步的，所述运算处理模块具体包括：
数据获取单元，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
计算单元，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
取值单元，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
进一步的，基准图像获取模块根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
第二方面，本发明还提供一种电视频道识别装置，装置具体包括：
待识别频道图像获取模块，用于获取带有时间标签的待识别频道图像；
基准图像获取模块，用于基于所述时间标签获取基准图像；
运算处理模块，用于计算所述待识别频道图像和所述基准图像的SAD值；
判断模块，用于将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。
进一步的，所述服务器还包括分割模块，用于将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
进一步的，所述运算处理模块具体包括：
数据获取单元，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
计算单元，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
取值单元，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
进一步的，基准图像获取模块根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
第三方面，本发明还提供一种电视机，包括电视频道识别装置，所述电视频道识别装置包括：
待识别频道图像获取模块，用于获取带有时间标签的待识别频道图像；
基准图像获取模块，用于基于所述时间标签获取基准图像；
运算处理模块，用于计算所述待识别频道图像和所述基准图像的SAD值；
判断模块，用于将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识 别电视频道的频道信息。
进一步的，所述服务器还包括分割模块，用于将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
进一步的，所述运算处理模块具体包括：
数据获取单元，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
计算单元，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
取值单元，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
进一步的，基准图像获取模块根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
第四方面，本发明还提供一种服务器，包括电视频道识别装置，所述电视频道识别装置包括：
待识别频道图像获取模块，用于获取带有时间标签的待识别频道图像；
基准图像获取模块，用于基于所述时间标签获取基准图像；
运算处理模块，用于计算所述待识别频道图像和所述基准图像的SAD值；
判断模块，用于将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。
进一步的，所述服务器还包括分割模块，用于将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
进一步的，所述运算处理模块具体包括：
数据获取单元，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
计算单元，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
取值单元，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
进一步的，基准图像获取模块根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
第五方面，本发明实施例提供一种非暂态计算机可读存储介质，所述非暂态计算机可读存储介质存储程序指令，当终端设备执行所述程序指令时，用于执行：
根据待识别频道图像获取指令获取带有时间标签的待识别频道图像；
基于所述时间标签，根据基准图像获取指令获取基准图像；
根据运算处理指令计算所述待识别频道图像和所述基准图像的SAD值；
根据判断指令将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则根据频道信息获取指令获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。
进一步的，在根据待识别频道图像获取指令获取所述待识别频道图像和根据基准图像获取指令获取所述基准图像之前，还用于执行：
根据分割指令将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
进一步的，所述根据运算处理指令计算所述待识别频道图像和所述基准图像的SAD值，具体用于执行：
根据数据获取指令获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
根据计算指令基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
根据取值指令获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
进一步的，当终端设备执行所述程序指令时，还用于执行：
根据更新指令实时更新基准图像，根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
第六方面，本发明实施例提供一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当程序指令被终端设备执行时，使所述终端设备执行上述的方法。
通过本发明提供的电视频道识别方法和装置及电视机、服务器，通过计算绝对误差和的方式将待识别节目图像和同一时间或相邻时间获取的基准图像整体进行对比，不需要截取台标，避免因截取的台标不清楚导致的低匹配率以及由此带来的附加截图匹配操作和匹配延时问题，从而可以快速且实时地获取当前的电视频道信息以及节目信息；同时计算绝对误差和的算法简单，可快速获得对比结果，相比于常规的用于图像相似性判断的图像识别算法，节省了系统资源。
【附图说明】
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其它的附图。
图1为本发明实施例一提供的电视频道识别方法流程框图。
图2a为本发明实施例二提供的电视频道识别方法流程框图。
图2b为本发明实施例二提供的SAD值计算流程框图。
图2c为本发明实施例二提供的图像分割示意图。
图2d为本发明实施例二提供的图像单元的像素分布图。
图3为本发明实施例三提供的电视频道识别装置结构示意图。
图4a为本发明实施例四提供的电视频道识别装置结构示意图。
图4b为本发明实施例四提供的运算处理模块的结构示意图。
图5为本发明实施例五提供的电视机的结构示意图。
图6为本发明实施例六提供的服务器的结构示意图。
【具体实施方式】
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例,附图中给出了本发明的较佳实施例。本发明可以以许多不同的形式来实现，并不限于本文所描述的实施例，相反地，提供这些实施例的目的是使对本发明的公开内容的理解更加透彻全面。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实 施例相结合。
实施例一
参阅图1所示的流程图，图1提供了一种电视频道识别方法的处理流程，所述方法的处理流程具体包括如下步骤：
步骤01、获取带有时间标签的待识别频道图像。
本发明实施例的电视优选指智能电视，待识别频道图像从智能电视端获取。具体地，基于特定的截屏触发操作从电视端获取当前正在播放的频道图像作为待识别频道图像，可选的，获取节目图像可采用智能电视内置的截屏模块。其中，截屏模块触发截屏需要相应的触发操作，截屏触发操作有如下几种形式：
1、定时触发
定时触发由截屏模块基于一定的时间间隔不间断截取智能电视当前播放的频道图像，时间间隔可任意设定，在本实施例中，时间间隔的最小值不低于两相邻视频帧之间的时间间隔，具体取决于电视节目的源视频的帧率，比如采用NTSC(National Television System Committee)制式的电视，其视频帧率为30fps，那么最小的截屏时间间隔为100/3毫秒，低于100/3毫秒截屏将导致截屏模块对同一画面进行多次截取，将浪费系统资源，而采用PAL(Phase Alternating Line)制式的电视，其视频帧率为25fps，相应的最小截屏时间间隔为40ms，
2、不定时触发
具体地指检测用户操作来触发截屏，用户在切换电视频道时，相应地电视会出现黑屏、声音中断或停顿等现象。由此可通过直接检测频道切换操作以触发截屏动作。
3、混合触发
混合触发是指将检测用户操作来触发截屏和定时截屏结合，可选的，检测用户操作触发截屏的优先级高于定时触发，即电视系统基于定时触发完成某次图像截取后，在预设的时间间隔内电视系统又检测到频道切换操作，则此时将 直接截取屏幕图像，而不必等足预设的时间间隔，从而可以实时获得用户当前正在观看的电视频道图像。
截取电视频道图像后，电视系统自动存储(或者缓存)截取的图像时，为截取的图像(即待识别频道图像)添加时间标签，所述时间标签即为截取该图像的时刻。可选的，截取的图像和对应的截取时刻可按照下表形式存储，其中文件名由电视系统的截屏模块自动命名，时间标签的格式可自由设置，表中所示图片名和时间标签只是一种示例：
图片名 时间标签
Pic1 2016-5-1 15:23:26.120
Pic2 2016-5-1 15:23:26.160
Pic3 2016-5-1 15:23:26.200
步骤02、基于所述时间标签获取基准图像。
基准图像需在后台获取，后台包含所有电视频道的频道信息，相应的，获取的基准图像与对应的电视频道信息相关联。
在智能电视截取未知频道的图像时，后台的所有电视频道也在同步截取节目图像，后台截取图像的频率不低于智能电视端的截取图像的频率，优选地，后台的截图频率等于电视频道的视频帧率，则后台可截取所有频道的全部视频帧，以保证能在基准图像中匹配到与待视频频道图像相同的图像。同样地，后台在截取图像的同时，为截取图像添加时间标签。
后台截取的图像作为判别电视频道的基准图像存储在后台的存储器中，理论上电视的系统时间和后台的系统时间是一致的，因此当进行电视频道判别时，可根据待识别频道图像的时间标签从后台存储中匹配具有相同时间标签的基准图像，匹配到的基准图像至少有一个，其具体个数取决于后台接入的电视频道数量，假如当前后台接入168个电视频道，相应的基于一个时间标签将得到168个基准图像。
可选的，由于后台接入的电视频道可以是世界不同地区的，一般性地可根 据地域信息对电视频道进行初步筛选，获取该智能电视所在地域范围内的电视频道，优选地，根据不同地域快速筛选电视频道可通过智能电视的定位模块实现。从筛选后的电视频道中匹配基准图像，将减少匹配基准图像所需的时间，提高匹配效率。
可选的，由于后台截取的基准图像数量大，若全部存储将占用大量存储空间，故后台优选存储固定时长的基准图像，根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，存储的基准图像形成基准图像库，当后台添加新的基准图像至图像库时，相应的从基准图像库中删除时间标签最早的基准图像，实时更新基准图像库。
步骤04、计算所述待识别频道图像和所述基准图像的SAD值。
为获得当前电视正在播放的频道以及节目内容，需要通过对比待识别频道图像和基准图像是否相同，数学上比较A和B两个数据是否相等，我们可以用AB的绝对差值C＝|A-B|来表示，当C＝0时，可认为A和B相等。同样对于两幅图像也可以采用类似的方法，本发明实施例提供的技术方案通过获取所述待识别频道图像和所述基准图像的图像数据，并将得到的图像数据相减得到两幅图像的SAD值，以进一步判断两幅图像是否相同，其中SAD指绝对误差和(Sum of Absolute Difference)。
步骤05、将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别频道的频道信息。
通过SAD值的进一步分析可得出待识别频道图像和基准图像是否相同。优选地，如果待识别频道图像和基准图像相同，则两幅图像的SAD值将为零，然而存在可能导致SAD值不为零的未知影响因素，比如图像噪声，在本发明实施例中，如果两幅图像的SAD值低于某一预设阈值，仍然可以认为待识别频道图像和基准图像相同，其中预设阈值可人为设定，也可通过机器训练学习自动获得。如果已判定某SAD值低于预设阈值，则判定该SAD值对应的基准图像与 待识别频道图像相同，进一步地，获取该SAD值对应的基准图像所关联的频道信息以及当前正在播放的节目信息，从而得到待识别频道的频道信息以及当前正在播放的节目信息。
本发明实施例通过计算待识别频道图像和基准图像的SAD值，并进一步基于SAD值的分析判别得到待识别的电视频道信息，一方面可不需要截取待识别频道画面中的台标，减少了匹配步骤，避免因截取的台标画面包含背景而导致台标识别效率低的问题，保证了电视频道识别的实时性；另一方面，传统的图像比对所采用的算法比较的是图像的相似度，然而电视频道的判别需要比较的是图像是否相同，因此传统的图像相似比较和电视频道判别的应用场景是有差别的，且传统图像比对算法的运算量大，与传统的图像比对方法相比，本发明实施例所采用的图像比对方案运算量减少，节省了系统资源。
实施例二
如图2a所示的电视频道识别方法流程图，本发明实施例提供的电视频道识别方法具体如下：
步骤01、获取带有时间标签的待识别频道图像。
本步骤同实施例一所述的步骤01，具体地，基于特定的截屏触发操作从电视端获取当前正在播放的频道图像作为待识别频道图像。
步骤02、基于所述时间标签获取基准图像。
本步骤同实施例一所述的步骤02，需要额外说明的是，存在这样的情形，因终端设备硬件或者网络的原因，不同的设备或者服务器的系统时间有出入，此时根据标注的时间标签从后台匹配具有相同时间标签的基准图像，得到的基准图像必然不包含与待匹配频道图像相同的基准图像，从而无法识别电视频道。可选的，本发明提供一种优选实施例，即扩大基准图像搜索范围，具体的，获取待识别频道图像的时间标签前后的基准图像，可设置第一时间阈值，基于时间标签，根据第一时间阈值获取时间标签前后时间阈值内的基准图像，比如设 定第一时间阈值为1s，现有某待识别频道图像Pic2的时间标签为2016-5-115:23:26.160，则对应的从后台获取2016-5-1 15:23:25.160至2016-5-115:23:27.160时间段内的基准图像，可选的，若通过比对仍然没有相同的基准图像，则可通过设置第二时间阈值继续扩大搜索，依次类推。
步骤03、将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
基于相同的预设尺寸，将所述待识别频道图像和所述基准图像分割为多个图像单元，各个图像单元邻接但互不重叠，其中预设尺寸以像素单位为基本分割尺寸，相应的，图像单元为固定尺寸的像素块，像素块的大小包括但不限于8×8、16×16或者32×16，32×32等。
步骤04、计算所述待识别频道图像和所述基准图像的SAD值。
根据本发明提供的可选实施例，计算所述待识别频道图像和所述基准图像的SAD值的具体过程如下，如图2b所示：
步骤041、获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
获取单元图片的图像数据具体指获取图片中各像素点的像素值，在本实施例中采用YUV值来表征像素值，可选的，亦可用RGB值来表征像素值，YUV值和RGB值之间可以相互转换。
步骤042、基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
步骤043、获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。通过比较所有的单元SAD值来获得最大的单元SAD值。
步骤05、将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别频道的频道信息。
对于多个SAD值与预设阈值比较的过程，可采用如下几种方案：
方案一、计算一个SAD值就与预设阈值执行一次比较操作，比如现有待识 别频道图像Pic000,同时有168个基准图像，分别为Pic001、Pic002、……、Pic167、Pic168，先计算Pic000与Pic001的SAD值，记为SAD1，将SAD1与预设阈值比较，如果SAD1小于预设阈值，Pic001即为与Pic000相同的图像，则不再计算Pic000与其他基准图像的SAD值；如果SAD1大于预设阈值，则在计算Pic000与Pic002的SAD值，记为SAD2，再将SAD2与预设阈值比较，依次类推，直到获得小于预设阈值的SAD值为止。
方案二、先计算全部SAD值，再与预设阈值进行比较。可将SAD值逐一与预设阈值进行比较，直到得到小于预设阈值的SAD值为止，也可以先比较所有SAD值，获得最小的SAD值后，将最小的SAD值与预设阈值进行比较。
根据本发明实施例提供的技术方案，现以将两幅画面划分为16x16(像素单位)的方格为例来具体说明SAD值的计算过程，如图2c所示，将待识别频道图像和基准图像均划分成多个16×16(像素单位)的图像单元，如图2b所示一共有Pn个图像单元，其中横向Pi个,纵向Pj个，有n＝i*j，其中n、i、j均为大于1的正整数。本实施例中的单元图片为包含256个像素点的方格，取图2c中的单元图片P1放大后得到如图2d所示的方格图，每一个小方格即为一个像素点。
计算待识别频道图像和基准图像位置相对应的图像单元的SAD值，其中所述的位置相对应，具体是指在待识别频道图像和基准图像的单元图片具有相同的位置，比如计算待识别频道图像和基准图像在P1位置的图像单元SAD值。
通过获取P1位置的图像单元的像素值来计算单元SAD值，计算图像单元的SAD值公式如下：
Figure PCTCN2016106703-appb-000001
其中s[x,y]为待识别频道图像某一图像单元中的某一像素点的像素值，s’[x,y]为基准图像某一图像单元中的某一像素点的像素值，A指x和y的取值集合，如图2d所示，本实施例中的x和y取值范围均为[0,15]，相应的，集合A 包含256个元素。
根据上述公式获取所有图像单元的SAD值，并取最大的单元SAD值作为待识别频道图像和基准图像的SAD值，当最大的单元SAD值低于预设阀值时，判断为两幅图像相同。
本发明实施例将待比对的图像划分成多个图像单元，先获取图像单元的SAD值再进行比较的目的在于避免因两幅图像大面积相似，而局部不同情形下出现误判。
实施例三
请参阅图3所示电视频道识别装置结构框图，本发明实施例提供电视频道识别装置具体包括待识别频道图像获取模块11、基准图像获取模块12、运算处理模块14、判别模块15。
待识别频道图像获取模块11用于获取带有时间标签的待识别频道图像。具体的，待识别频道图像获取模块11向智能电视端发送待识别频道图像获取请求，从电视端获取当前正在播放的频道图像作为待识别频道图像。
基准图像获取模块12用于基于所述时间标签获取至少一幅基准图像。具体的，基准图像获取模块12根据待识别频道图像的时间标签从后台的存储模块中获取基准图像，匹配到的基准图像至少有一个，其具体个数取决于后台接入的电视频道数量，假如当前后台接入168个电视频道，相应的基于一个时间标签将得到168个基准图像。
可选的，基准图像获取模块12还可根据地理位置对电视频道进行初步筛选，获取该智能电视所在地域范围内的电视频道，从筛选后的电视频道中匹配基准图像，将减少匹配基准图像所需的时间，提高匹配效率。
可选的，基准图像获取模块12根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像，实时更新基准图像库。
运算处理模块14用于计算所述待识别频道图像和所述基准图像的SAD值。具体的，运算处理模块14获取所述待识别频道图像和所述基准图像的图像数据，依次计算所述待识别频道图像和所述至少一幅基准图像的SAD值；
判断模块15用于将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。具体的，将所述SAD值依次与预设阈值进行比较，所述预设阈值非负，如果判断模块15判定某SAD值低于预设阈值，则判定该SAD值对应的基准图像与待识别频道图像相同，进一步地，获取该SAD值对应的基准图像所关联的频道信息，从而得到待识别频道的频道信息。需要说明，本实施例提供的电视频道识别装置的各模块的处理过程可援引实施例一和实施例二中相应的技术方案，在此不再赘述。
本发明实施例提供的电视频道识别装置通过计算待识别频道图像和基准图像的SAD值，并进一步基于SAD值的分析判别得到待识别的电视频道信息，一方面可不需要截取待识别频道画面中的台标，减少了匹配步骤，避免因截取的台标画面包含背景而导致台标识别效率低的问题，保证了电视频道识别的实时性；另一方面，传统的图像比对所采用的算法比较的是图像的相似度，且运算量大，本发明实施例提供的电视频道识别装置在进行图片比对时运算量少，节省了系统资源。
实施例四
请参与图4a所示电视频道识别装置，本发明实施例所提供的电视频道识别装置，还包括分割模块13，分割模块13用于基于预设尺寸将所述待识别频道图像和所述基准图像划分为至少两个图像单元。具体地，分割模块13基于相同的预设尺寸，将所述待识别频道图像和所述基准图像分割为多个图像单元，各个图像单元邻接但互不重叠，其中预设尺寸以像素单位为基本分割尺寸，相应的，图像单元为固定尺寸的像素块，像素块的大小包括但不限于8×8、16×16或者 32×16，32×32等。
具体地，如图4b所示，电视频道识别装置的运算处理模块14包括：
数据获取单元141，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；具体为获取图片中各像素点的像素值。
计算单元142，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
计算每个方格的SAD值公式如下：
Figure PCTCN2016106703-appb-000002
其中s[x,y]为待识别频道图像某一图像单元中的某一像素点的像素值，s’[x,y]为基准图像某一图像单元中的某一像素点的像素值，A指x和y的取值集合。
取值单元143，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。通过比较所有的单元SAD值来获得最大的单元SAD值。
需要说明，本实施例提供的电视频道识别装置的各模块的处理过程可援引前述实施例中直接或者间接披露的技术方案，在此不再赘述。
本发明实施例提供的电视频道识别装置将待比对的图像划分成多个图像单元，先获取图像单元的SAD值再进行比较的目的在于避免因两幅图像大面积相似，而局部不同情形下出现误判。
实施例五
参阅图5，本发明实施例提供一种电视机，具体的，电视机2包括前述实施例所述的电视频道识别装置1，在此电视频道识别装置1的具体结构不再赘述。本实施例提供一种可选方案，电视机2内置的电视频道识别装置1从服务器3端获取基准图像。
本发明实施例提供的电视机通过内置电视频道识别装置，可以实时获取用户观看的电视节目，可用于统计收视率以及根据用户的观看行为来推送互动内容，或者广告推送、电视节目衍生品推广等，既能为电视节目提供方提供营销平台，同时可以丰富用户的观影体验。
实施例六
参阅图6，本发明实施例提供一种服务器，具体的，所述服务器3包括前述实施例所述的电视频道识别装置1，在此电视频道识别装置1的具体结构不再赘述。本实施例提供一种可选方案，服务器3端的电视频道识别装置1从电视机2端获取待识别频道图像。
本发明实施例提供的服务器通过电视频道识别装置，可以实时获取用户观看的电视节目，可用于统计收视率以及根据用户的观看行为来推送互动内容，或者广告推送、电视节目衍生品推广等，既能为电视节目提供方提供营销平台，同时可以丰富用户的观影体验。
实施例七
本发明实施例提供一种非暂态计算机可读存储介质，所述非暂态计算机可读存储介质存储程序指令，当终端设备执行所述程序指令时，用于执行上述任意方法实施例中的方法及步骤。
本实施例所提供的非暂态计算机可读存储介质具有的有益效果可参考上述方法实施例的有益效果。
实施例八
本发明实施例提供一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当程序指令被终端设备执行时，使所述终端设备执行上述任意方法实施例中的方法及步骤。本领域普通技术人员可以理解实现上述实施例方法中的全部或部 分流程，是可以通过计算机程序来指令相关硬件来完成，所述的程序可存储于一计算机可读存储介质中。
本实施例所提供的计算机程序产品具有的有益效果可参考上述方法实施例的有益效果。
在本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如，多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理单元中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机装置(可以是个人计算机，服务器，或者网络装置等)或处理器(Processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。以上仅为本发明的优选实施例，但并不限制本发明的专利范围，尽 管参照前述实施例对本发明进行了详细的说明，对于本领域的技术人员来而言，其依然可以对前述各具体实施方式所记载的技术方案进行修改，或者对其中部分技术特征进行等效替换。凡是利用本发明说明书及附图内容所做的等效结构，直接或间接运用在其他相关的技术领域，均同理在本发明专利保护范围之内。

Claims (12)

  1. 一种电视频道识别方法，应用于终端设备，其特征在于，所述方法包括：
    获取带有时间标签的待识别频道图像；
    基于所述时间标签获取基准图像；
    计算所述待识别频道图像和所述基准图像的SAD值；
    将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。
  2. 根据权利要求1所述的电视频道识别方法，其特征在于，在获取所述待识别频道图像和所述基准图像的图像数据步骤前还包括：
    将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
  3. 根据权利要求2所述的电视频道识别方法，其特征在于，所述计算所述待识别频道图像和所述基准图像的SAD值的具体过程如下：
    获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
    基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
    获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
  4. 根据权利要求1所述的电视频道识别方法，其特征在于，还包括实时更新基准图像，具体为：
    根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
  5. 一种电视频道识别装置，其特征在于，包括：
    待识别频道图像获取模块，用于获取带有时间标签的待识别频道图像；
    基准图像获取模块，用于基于所述时间标签获取基准图像；
    运算处理模块，用于计算所述待识别频道图像和所述基准图像的SAD值；
    判断模块，用于将所述SAD值与预设阈值进行比较，若SAD值低于预设阈值，则获取所述SAD值对应的基准图像的频道信息，所述频道信息即为待识别电视频道的频道信息。
  6. 根据权利要求5所述的电视频道识别装置，其特征在于，还包括分割模块，用于将所述待识别频道图像和所述基准图像分割为至少两个图像单元。
  7. 根据权利要求6所述的电视频道识别装置，其特征在于，所述运算处理模块具体包括：
    数据获取单元，用于获取所述待识别频道图像和所述基准图像中图像单元的图像数据；
    计算单元，用于基于所述图像单元的图像数据，依次计算所述待识别频道图像和所述基准图像中位置相对应的图像单元的单元SAD值；
    取值单元，用于获取最大的单元SAD值，并将其作为所述待识别频道图像和所述基准图像的SAD值。
  8. 根据权利要求5所述的电视频道识别装置，其特征在于，基准图像获取模块根据预设采集频率实时采集电视频道的图像存储为新的基准图像，并为新的基准图像添加时间标签，同时删除时间标签最早的基准图像。
  9. 一种电视机，其特征在于，包括权利要求5-8中任一项所述的电视频道识别装置。
  10. 一种服务器，其特征在于，包括权利要求5-8中任一项所述的电视频道识别装置。
  11. 一种非暂态计算机可读存储介质，其特征在于，所述非暂态计算机可读存储介质存储程序指令，当终端设备执行所述程序指令时，用于执行权利要求1-4任一项所述的方法。
  12. 一种计算机程序产品，其特征在于，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令， 当程序指令被终端设备执行时，使所述终端设备执行权利要求1-4任一项所述的方法。
PCT/CN2016/106703 2016-06-27 2016-11-22 一种电视频道识别方法、装置及电视机、服务器 WO2018000699A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610480016.6 2016-06-27
CN201610480016.6A CN106060584A (zh) 2016-06-27 2016-06-27 一种电视频道识别方法、装置及电视机、服务器

Publications (1)

Publication Number Publication Date
WO2018000699A1 true WO2018000699A1 (zh) 2018-01-04

Family

ID=57166503

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/106703 WO2018000699A1 (zh) 2016-06-27 2016-11-22 一种电视频道识别方法、装置及电视机、服务器

Country Status (2)

Country Link
CN (1) CN106060584A (zh)
WO (1) WO2018000699A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106060584A (zh) * 2016-06-27 2016-10-26 乐视控股（北京）有限公司 一种电视频道识别方法、装置及电视机、服务器
CN106454426B (zh) * 2016-10-27 2019-04-30 四川长虹电器股份有限公司 一种识别智能电视模拟频道的方法
EP3920541A1 (en) * 2020-06-03 2021-12-08 Top Victory Investments Limited Method for obtaining television rating points for television channels
CN113901266A (zh) * 2021-10-11 2022-01-07 深圳创维－Rgb电子有限公司 电视视频查找方法和装置、电视及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005057322A2 (en) * 2003-11-19 2005-06-23 Nielsen Media Research, Inc. Methods and apparatus for detecting a television channel change event
CN102917247A (zh) * 2012-11-05 2013-02-06 北京恒远创智信息技术有限公司 自动识别电视频道和电视节目的方法
CN104038775A (zh) * 2014-06-05 2014-09-10 Tcl集团股份有限公司 一种频道信息识别方法及装置
CN104301755A (zh) * 2013-07-19 2015-01-21 联想(北京)有限公司 一种电视信息获取方法、电视、后台服务器及系统
CN106060584A (zh) * 2016-06-27 2016-10-26 乐视控股（北京）有限公司 一种电视频道识别方法、装置及电视机、服务器
CN106131592A (zh) * 2016-07-18 2016-11-16 乐视控股（北京）有限公司 一种电视频道的确定方法和装置
CN106131611A (zh) * 2016-06-29 2016-11-16 乐视控股（北京）有限公司 一种识别节目频道的方法、终端及服务器

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102143376B (zh) * 2010-11-29 2013-05-22 北大方正集团有限公司 一种双路视频信号一致性检测的方法及装置
CN102542297A (zh) * 2010-12-16 2012-07-04 上海无戒空间信息技术有限公司 电视频道的识别方法
KR101799443B1 (ko) * 2011-05-02 2017-11-20 삼성전자주식회사 영상 컨텐츠 시청 확인 방법 및 이를 적용한 방송수신장치, 그리고 서버

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005057322A2 (en) * 2003-11-19 2005-06-23 Nielsen Media Research, Inc. Methods and apparatus for detecting a television channel change event
CN102917247A (zh) * 2012-11-05 2013-02-06 北京恒远创智信息技术有限公司 自动识别电视频道和电视节目的方法
CN104301755A (zh) * 2013-07-19 2015-01-21 联想(北京)有限公司 一种电视信息获取方法、电视、后台服务器及系统
CN104038775A (zh) * 2014-06-05 2014-09-10 Tcl集团股份有限公司 一种频道信息识别方法及装置
CN106060584A (zh) * 2016-06-27 2016-10-26 乐视控股（北京）有限公司 一种电视频道识别方法、装置及电视机、服务器
CN106131611A (zh) * 2016-06-29 2016-11-16 乐视控股（北京）有限公司 一种识别节目频道的方法、终端及服务器
CN106131592A (zh) * 2016-07-18 2016-11-16 乐视控股（北京）有限公司 一种电视频道的确定方法和装置

Also Published As

Publication number Publication date
CN106060584A (zh) 2016-10-26

Similar Documents

Publication Publication Date Title
CN110933490B (zh) 一种画质和音质的自动调整方法、智能电视机及存储介质
KR102263898B1 (ko) 동적 비디오 오버레이
WO2018000699A1 (zh) 一种电视频道识别方法、装置及电视机、服务器
US20140201773A1 (en) Systems and methods for on-screen graphics detection
US20100201871A1 (en) Temporally consistent caption detection on videos using a 3D spatiotemporal method
CN106529406B (zh) 一种获取视频摘要图像的方法和装置
JP5677229B2 (ja) 映像字幕検出装置およびそのプログラム
EP3323245A1 (en) Detection of common media segments
CN106454426B (zh) 一种识别智能电视模拟频道的方法
CN115396705B (zh) 投屏操作验证方法、平台及系统
CN103544467B (zh) 一种台标检测识别的方法及其装置
US10270872B2 (en) Information pushing method and system
CN111654747B (zh) 弹幕显示方法及装置
CA2973492C (en) Detection of solid color frames for determining transitions in video content
CN110662001B (zh) 一种视频投影显示方法、装置及存储介质
US20230119783A1 (en) Methods and apparatus to monitor a split screen media presentation
CN110198457B (zh) 视频播放方法及其设备、系统、存储介质、终端、服务器
CN107391661B (zh) 推荐词显示方法及装置
KR102487111B1 (ko) 수화 방송 품질 모니터링 방법 및 장치
Chen et al. Picture in picture detection for mobile captured digital video
Zhou et al. Research on video motion characteristics extraction and description based on human visual characteristics
RU2737346C1 (ru) Способ сравнения изображения с шаблоном
CN114331533A (zh) 基于广告设备的信息采集方法和系统
Dong et al. An Improved Video Mosaic Block Detection Method Considering the Boundary of Macroblock
Zhou An Improved Video Mosaic Block Detection Method on the Statistics of Pixel Difference across the Boundary of Macroblock and Suspected Mosaic Blocks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16907095

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16907095

Country of ref document: EP

Kind code of ref document: A1