Summary of the invention
To solve the above-mentioned problems, the present invention provides one kind by data acquisition come adaptively selected information input mode
Method, select different smart television input patterns for the spectators of different age group.
The present invention at least has the important inventive point of following two:
(1) by controlling the adaptive switching of resolution ratio/frame per second of each image acquisition units, guaranteeing not with losing fortune
While dynamic object and guarantee imaging moving objects quality, the power consumption of acquisition unit is reduced, the wave of electric power resource is avoided
Take, has ensured the cruising ability of tracking system;
(2) by with pre-stored each visual angle still image carry out it is matched in a manner of obtain best background image, meanwhile,
Each foreground point is determined by randomization judgment model, so that solid data base has been laid in the identification for subsequent motion target
Plinth.
According to an aspect of the present invention, provide it is a kind of by data acquisition come the side of adaptively selected information input mode
Method, this method comprises: providing the adaptively selected system of information input mode being located on television set;With the operation system, institute
The system of stating includes:
Input mode switching equipment, connect with image segmentation apparatus, for receiving face pattern, and based in face pattern
Facial aging degree be that television set present communications tool selects corresponding information input mode;
The input mode switching equipment is television set present communications tool based on the facial aging degree in face pattern
Selecting corresponding information input mode includes: to select corresponding information input when facial aging degree is level-one aging degree
Mode is voice input, and when facial aging degree is second level aging degree, selecting corresponding information input mode is remote controler
Input selects corresponding information input mode for remote sensing input when facial aging degree is three-level aging degree;
Adaptive resolution acquires equipment, including mode switch element, motion detection unit and several image acquisition units,
Several image acquisition units respectively with different angle to place environment carry out image data acquiring to export several subangle images,
Each image acquisition units default mode of operation is low resolution acquisition mode, and motion detection unit is adopted with several images respectively
Collect unit connection, with the presence or absence of Moving Objects, mode in the subangle image for detecting the shooting of each image acquisition units
Switch unit is connect with motion detection unit, is also connect respectively with several image acquisition units, for receiving some figure
As acquisition unit is there are when Moving Objects, the operating mode of the image acquisition units is switched to high-resolution acquisition mode, is used
In receiving some image acquisition units there is no when Moving Objects, the operating mode of the image acquisition units is switched to
Low resolution acquisition mode;
Environment light sensing device, including luminance sensor, for detecting the real-time luminosity of ambient enviroment using as real-time ring
Border brightness output;
Brightness of display screen measuring device, for providing the flat of the current contrast of display screen and the current picture of display screen
Equal brightness;
Brightness regulation equipment is connect with environment light sensing device and brightness of display screen measuring device respectively, for based on real
When ambient brightness, the current contrast of display screen and display screen the average brightness of current picture decide whether to display screen
Brightness is adjusted in real time;
Contrast identifies equipment, connect with adaptive resolution acquisition equipment, for receiving several subangle images, and knows
Several contrasts of not several subangle images, several contrasts are compared, will be corresponding to the highest contrast of numerical value
Subangle image is as subangle reference picture;
Background obtains equipment, for receiving subangle reference picture, and subangle reference picture and each visual angle is static
Image is matched one by one, will be defeated as real-time background image with the highest visual angle still image of subangle reference picture matching degree
Out, wherein each visual angle still image is pre-stored in the storage unit that background obtains built in equipment, each visual angle is quiet
State image is the image for being shot and being obtained to the static scene under the corresponding visual angle without any Moving Objects in advance;
Image segmentation apparatus obtains equipment with background and connect, for receiving subangle reference picture and real-time background image,
The variance for determining the mean value of the pixel value of real-time background image and the pixel value of real-time background image, by subangle reference picture
In the pixel value of each pixel and the mean value of pixel value of real-time background image do difference, when difference is more than or equal to back in real time
At five times of the variance of the pixel value of scape image, which is determined as foreground point, the pixel is otherwise determined as background
Point, and all foreground points in subangle reference picture are formed into real-time foreground image, face is carried out from real-time foreground image
Detection is to obtain and export face pattern.
Specific embodiment
The embodiment of the adaptively selected system of information input mode of the invention is carried out below with reference to accompanying drawings detailed
Explanation.
In order to overcome above-mentioned deficiency, the present invention has built one kind by data acquisition come adaptively selected information input mode
Method, this method comprises: provide be located at television set on the adaptively selected system of information input mode;With the operation system
System.Fig. 1 is the structural schematic diagram according to the adaptively selected system of information input mode shown in embodiment of the present invention, the system
System includes:
Input mode switching equipment, connect with image segmentation apparatus, for receiving face pattern, and based in face pattern
Facial aging degree be that television set present communications tool selects corresponding information input mode;
The input mode switching equipment is television set present communications tool based on the facial aging degree in face pattern
Selecting corresponding information input mode includes: to select corresponding information input when facial aging degree is level-one aging degree
Mode is voice input, and when facial aging degree is second level aging degree, selecting corresponding information input mode is remote controler
Input selects corresponding information input mode for remote sensing input when facial aging degree is three-level aging degree;
As shown in Fig. 2, adaptive resolution acquires equipment, including mode switch element, motion detection unit and several figures
As acquisition unit, it is several to export that several image acquisition units carry out image data acquiring to place environment with different angle respectively
Subangle image, each image acquisition units default mode of operation are low resolution acquisition mode, motion detection unit difference
It is connect with several image acquisition units, with the presence or absence of fortune in the subangle image for detecting the shooting of each image acquisition units
Dynamic object, mode switch element connect with motion detection unit, also connect respectively with several image acquisition units, for receiving
To some image acquisition units there are when Moving Objects, the operating mode of the image acquisition units is switched to high-resolution and is adopted
Integrated mode, for when receiving some image acquisition units there is no Moving Objects, by the work of the image acquisition units
Pattern switching is low resolution acquisition mode;
Environment light sensing device, including luminance sensor, for detecting the real-time luminosity of ambient enviroment using as real-time ring
Border brightness output;
Brightness of display screen measuring device, for providing the flat of the current contrast of display screen and the current picture of display screen
Equal brightness;
Brightness regulation equipment is connect with environment light sensing device and brightness of display screen measuring device respectively, for based on real
When ambient brightness, the current contrast of display screen and display screen the average brightness of current picture decide whether to display screen
Brightness is adjusted in real time;
Contrast identifies equipment, connect with adaptive resolution acquisition equipment, for receiving several subangle images, and knows
Several contrasts of not several subangle images, several contrasts are compared, will be corresponding to the highest contrast of numerical value
Subangle image is as subangle reference picture;
Background obtains equipment, for receiving subangle reference picture, and subangle reference picture and each visual angle is static
Image is matched one by one, will be defeated as real-time background image with the highest visual angle still image of subangle reference picture matching degree
Out, wherein each visual angle still image is pre-stored in the storage unit that background obtains built in equipment, each visual angle is quiet
State image is the image for being shot and being obtained to the static scene under the corresponding visual angle without any Moving Objects in advance;
Image segmentation apparatus obtains equipment with background and connect, for receiving subangle reference picture and real-time background image,
The variance for determining the mean value of the pixel value of real-time background image and the pixel value of real-time background image, by subangle reference picture
In the pixel value of each pixel and the mean value of pixel value of real-time background image do difference, when difference is more than or equal to back in real time
At five times of the variance of the pixel value of scape image, which is determined as foreground point, the pixel is otherwise determined as background
Point, and all foreground points in subangle reference picture are formed into real-time foreground image, face is carried out from real-time foreground image
Detection is to obtain and export face pattern.
Then, continue to carry out further the specific structure of the adaptively selected system of information input mode of the invention
It is bright.
In the adaptively selected system of information input mode: the corresponding age bracket of three-level aging degree declines less than second level
The corresponding age bracket of old degree, the corresponding age bracket of second level aging degree are less than the corresponding age bracket of level-one aging degree.
In the adaptively selected system of information input mode: each image acquisition units is low point in operating mode
When resolution acquisition mode, image data acquiring is carried out with 960 × 540 resolution ratio.
In the adaptively selected system of information input mode: each image acquisition units is low point in operating mode
When resolution acquisition mode, image data acquiring is carried out with 1920 × 1080 resolution ratio.
In the adaptively selected system of information input mode: each image acquisition units is high score in operating mode
When resolution acquisition mode, image data acquiring is carried out with 3840 × 2160 resolution ratio.
In the adaptively selected system of information input mode: each image acquisition units is low point in operating mode
When resolution acquisition mode, image data acquiring is carried out with low frame per second.
In the adaptively selected system of information input mode: each image acquisition units is high score in operating mode
When resolution acquisition mode, image data acquiring is carried out with high frame per second.
In the adaptively selected system of information input mode: each image acquisition units is low point in operating mode
When resolution acquisition mode, image data acquiring is carried out with the frame per second of 10 frame per second.
In the adaptively selected system of information input mode: each image acquisition units is high score in operating mode
When resolution acquisition mode, image data acquiring is carried out with the frame per second of 50 frame per second.
In addition, can also include ZigBee communication interface in the adaptively selected system of information input mode, it be used for
Transmit wirelessly the facial aging degree in face pattern.
ZigBee is the low-power consumption LAN protocol based on IEEE802.15.4 standard.It is provided according to international standard,
ZigBee technology is the wireless communication technique of a kind of short distance, low-power consumption.This title (also known as ZigBee protocol) derives from honeybee
Eight words dance, due to honeybee (bee) be by circle in the air and " drone " (zig) shake wing " dancing " come and companion transmitting pollen
Place azimuth information, that is to say, that honeybee constitutes the communication network in group by such mode.Its main feature is that closely,
Low complex degree, self-organizing, low-power consumption, low data rate.It is mainly suitable for be embedded in for automatic control and remote control field
Various equipment.In brief, ZigBee is a kind of cheap, the near radio networking mechanics of communication of low-power consumption.ZigBee
It is a kind of wireless network protocol of low speed short-distance transmission.Zigbee protocol is respectively physical layer (PHY), media visit from top to bottom
Ask control layer (MAC), transport layer (TL), network layer (NWK), application layer (APL) etc..Wherein physical layer and MAC layer
Follow the regulation of IEEE 802.15.4 standard.
Using the adaptively selected system of information input mode of the invention, for smart television input control in the prior art
The not high technical problem of intelligent level, using input mode switching equipment, for receiving the high-precision face from scene
Pattern, and be that television set present communications tool selects corresponding information input mould based on the facial aging degree in face pattern
Formula also uses input mode switching equipment based on the facial aging degree in face pattern for the selection of television set present communications tool
Corresponding information input mode includes: to select corresponding information input mode when facial aging degree is level-one aging degree
Select corresponding information input mode for remote controler input when facial aging degree is second level aging degree for voice input,
When facial aging degree is three-level aging degree, select corresponding information input mode for remote sensing input.
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, anything that does not depart from the technical scheme of the invention are 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.