Invention content
Current smart television lack targetedly children's testing mechanism and corresponding TV watching overlong time and
Cause the scheme of myopia, to solve the above-mentioned problems, the present invention provides a kind of devices preventing child myopia.
According to an aspect of the present invention, a kind of device preventing child myopia is provided, which includes that smart television is opened
Control platform is closed, the platform includes:
The pre- measurement equipment of power consumption, connect with TF storage chips, by the video flowing of broadcasting after being used to read, and predicts to meet
Image quality requires to need the electricity expended to export as prediction electricity the video flowing of broadcasting after playing;
Power consumption measuring apparatus, connect with display panel, the average power consumption per minute for counting and determining display panel;
Electric power distribution facility is connect with the pre- measurement equipment of power consumption and power consumption measuring apparatus respectively, for based on prediction electricity and
Average power consumption determination per minute is distributed to the electric power of the video flowing of broadcasting after display panel is used to play;Electric power distribution is set
It is standby to be distributed to the video flowing of broadcasting after display panel is used to play based on prediction electricity and average power consumption per minute determination
Electric power include:By the duration of the video flowing of broadcasting to obtain assigned references electricity after average power consumption per minute is multiplied by,
It takes assigned references electricity and predicts the median of electricity as distributing to the video flowing of broadcasting after display panel is used to play
Electric power;
TF storage chips, by the video flowing of broadcasting after being used to store;
More mesh cameras, including multiple imaging units, each imaging unit be used for the scene in its areas imaging into
Row real time imagery operates, each imaging unit includes Analysis signal-to-noise ratio (SNR) device, quality comparator and N number of imaging sensor, noise
It is connect respectively with N number of imaging sensor than analyzer, Analysis signal-to-noise ratio (SNR) is carried out for the image to N number of imaging sensor,
Quality comparator is connect with Analysis signal-to-noise ratio (SNR) device, the signal-to-noise ratio of the image for receiving N number of imaging sensor, and selects to believe
The output image made an uproar than highest image as corresponding imaging unit;Data linkage is also carried out between N number of imaging sensor,
To ensure that the average brightness of multiple output images of N number of imaging sensor output is consistent, and ensure N number of imaging sensor output
The dynamic ranges of multiple output images be consistent.
The present invention at least has important inventive point at following two:
(1) imaging unit of more mesh cameras is subjected to complicated structure, with the figure of the wide field-of-view image after improving duplicate removal
While image quality amount, ensure the width in the visual field of image;
(2) deep neural network for establishing the non-linear mapping from target geometric properties to target type, to need to only obtain
Obtain target geometric properties, you can obtain target type, on the one hand simplify operation, on the other hand improve target type point
The accuracy of analysis.
Specific implementation mode
Embodiment of the present invention is described in detail below with reference to accompanying drawings.
Generally speaking, smart television is an open platform, and developer can develop many applications, and it is " unlimited to load
Content, unlimited application ", its development prospect is still more wide.
The arrival of smart television, complied with television set " high Qinghua ", " networking ", " intelligence " trend.When PC already
Intelligence, mobile phone and tablet are also intelligentized in large area, and TV this parts screen will not escape from the Buddha's Dharma-eye of IT giant, and one
It is fixed also to move towards intelligent.So-called real smart television, it should which having can obtain from multiple channels such as network, AV equipment, PC
Programme content, by integrated operation interface easy to use, the content that ease of Use needs most consumer is on large screen
Clearly show.
Smart television will realize web search, Internet Protocol Television, BBTV netviews, video on demand (VOD), digital music, network
The various application services such as news, network video telephone.Television set is becoming the visit of the third information after computer, mobile phone
Ask that terminal, user can access the information of oneself needs at any time;Television set will also become a kind of smart machine, realize TV, network
The cross-platform search between program;Smart television will also be one " recreation center ".
In order to overcome above-mentioned deficiency, the present invention, which has been built, provides a kind of device preventing child myopia, which includes
Smart television switchs control platform.Smart television switch control platform be used for recognize children's viewing time it is long when,
Smart television is automatically closed, to avoid causing myopia because observing time is long.
Fig. 1 is the structural schematic diagram that control platform is switched according to the smart television shown in embodiment of the present invention, described flat
Platform includes:
The pre- measurement equipment of power consumption, connect with TF storage chips, by the video flowing of broadcasting after being used to read, and predicts to meet
Image quality requires to need the electricity expended to export as prediction electricity the video flowing of broadcasting after playing;
Power consumption measuring apparatus, connect with display panel, the average power consumption per minute for counting and determining display panel;
Electric power distribution facility is connect with the pre- measurement equipment of power consumption and power consumption measuring apparatus respectively, for based on prediction electricity and
Average power consumption determination per minute is distributed to the electric power of the video flowing of broadcasting after display panel is used to play;Electric power distribution is set
It is standby to be distributed to the video flowing of broadcasting after display panel is used to play based on prediction electricity and average power consumption per minute determination
Electric power include:By the duration of the video flowing of broadcasting to obtain assigned references electricity after average power consumption per minute is multiplied by,
It takes assigned references electricity and predicts the median of electricity as distributing to the video flowing of broadcasting after display panel is used to play
Electric power;
TF storage chips, by the video flowing of broadcasting after being used to store.
Then, the concrete structure for continuing to switch the smart television of the present invention control platform is further detailed.
Can also include in the smart television switch control platform:
As shown in Fig. 2, more mesh cameras, including multiple imaging units, each imaging unit are used for its areas imaging
Interior scene carries out real time imagery operation, each imaging unit includes that Analysis signal-to-noise ratio (SNR) device, quality comparator and N number of image pass
Sensor, Analysis signal-to-noise ratio (SNR) device are connect with N number of imaging sensor respectively, and letter is carried out for the image to N number of imaging sensor
It makes an uproar than analysis, quality comparator is connect with Analysis signal-to-noise ratio (SNR) device, the noise of the image for receiving N number of imaging sensor
Than, and select the highest image of signal-to-noise ratio as the output image of corresponding imaging unit;Between N number of imaging sensor also into
Row data linkage to ensure that the average brightness of multiple output images of N number of imaging sensor output is consistent, and ensures N number of figure
As the dynamic range for multiple output images that sensor exports is consistent;
Content mergence equipment is connect with multiple imaging units respectively, multiple output figures for receiving multiple imaging units
Picture, and go out corresponding three-dimensional scene images based on multiple output image simulations.
Can also include in the smart television switch control platform:
Enhance processing equipment, for receiving three-dimensional scene images, and adaptive enhancing executed to three-dimensional scene images and is handled,
To obtain adaptive enhancing image, wherein executing adaptive enhancing processing to three-dimensional scene images includes:According to three-dimensional scene
As the contrast of each region establishs and enforces corresponding enhancing strength disposal, wherein contrast is lower, corresponding enhancing processing
Dynamics is bigger;
Dilation erosion equipment is connect with enhancing processing equipment, for receiving adaptive enhancing image, to adaptively enhancing figure
As executing Image erosion processing again after executing image expansion processing, to obtain morphological images;
Parameter analysis equipment is connect with dilation erosion equipment, for receiving morphological images, and is obtained in morphological images
The area of each object pattern, using volume close to body size threshold value object pattern as pending subgraph, to pending
Subgraph carries out shape analysis to obtain multiple geometric properties of wherein object, and place is normalized in multiple geometric properties respectively
Reason forms one-dimensional vector to obtain multiple normalization characteristics based on multiple normalization characteristics;
Objective extraction equipment is connect with Parameter analysis equipment, is inputted in advance for receiving one-dimensional vector, and by one-dimensional vector
The deep neural network for having trained the multiple input single output being completed, to obtain the object type of output;
Automatic control switch is connect with Objective extraction equipment, is children's class for the object type in the output received
Type and when lasting up to preset time threshold, is automatically closed smart television;
Wherein, positions of the quantity i.e. N based on imaging unit for the imaging sensor that each imaging unit includes is set
Fixed, for imaging unit closer to the middle position of more mesh cameras, the numerical value of corresponding N is bigger, and imaging unit more deviates more mesh
The numerical value of the middle position of camera, corresponding N is smaller.
In the smart television switchs control platform:The quantity of multiple normalization characteristics and deep neural network it is defeated
The quantity of the parameter entered is identical.
In the smart television switchs control platform:Electric power distribution facility by adjust display panel parameters come
Realize the electric power distribution to display panel.
And in the smart television switchs control platform:The TF storage chips also connect with the automatic control switch
It connects, for storing preset time threshold.
In addition, described image sensor can type selecting be cmos image sensor.Cmos image sensor has following
Advantage:1), random window reading capability.Random window read operation is that cmos image sensor is functionally better than the one of CCD
A aspect, also referred to as area-of-interest are chosen.In addition, the highly integrated characteristic of cmos image sensor makes it be easily achieved together
When open the functions of multiple tracking windows.2), capability of resistance to radiation.Generally speaking, the potential radiation resistance of cmos image sensor
There is important enhancing relative to CCD performances.3), system complexity and reliability.It can be greatly using cmos image sensor
Simplify system hardware structure.4), non-destructive data playback mode.5), the spectrum assignment optimized.Significantly, since
The reason of multiple functional transistors are integrated in pixel structure, there is also several disadvantages for cmos image sensor, mainly
Noise and filling rate two indices.In view of the relatively superior performance of cmos image sensor so that cmos image sensor is each
A field is widely used.
Smart television using the present invention switchs control platform, believes for can not accurately obtain spectators children in the prior art
The technical issues of breath, by building high-precision Image Acquisition mechanism and spectators' type-collection mechanism based on neural network,
The object type of audience is obtained, and uses automatic control switch, is children for the object type in the output received
Type and when lasting up to preset time threshold, is automatically closed smart television.
It is understood that although the present invention has been disclosed in the preferred embodiments as above, above-described embodiment not to
Limit the present invention.For any person skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications all are made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of variation.Therefore, every content without departing from technical solution of the present invention is right according to the technical essence of the invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments still fall within the range of technical solution of the present invention protection
It is interior.