CN102004537B - System power-on and power-off control device and method - Google Patents
System power-on and power-off control device and method Download PDFInfo
- Publication number
- CN102004537B CN102004537B CN201010531966.XA CN201010531966A CN102004537B CN 102004537 B CN102004537 B CN 102004537B CN 201010531966 A CN201010531966 A CN 201010531966A CN 102004537 B CN102004537 B CN 102004537B
- Authority
- CN
- China
- Prior art keywords
- environmental parameter
- processing block
- image
- main processing
- symbol
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of system power-on and power-off control device and method, wherein, this system power-on and power-off control device comprises: main processing block, for obtaining the environmental parameter value of system current place environment, and judges environmental parameter value whether outside predetermined environmental parameter scope; Control module, for when the judged result of main processing block is for being, control system power-off.Present invention achieves the intellectuality realizing system power-on and power-off and control, alleviate labour intensity and the workload of manpower monitoring.
Description
Technical field
The present invention relates to the communications field, in particular to a kind of system power-on and power-off control device and method.
Background technology
Generally, the index of environmental parameter may the serviceability of influential system, and such as: temperature and humidity exceedes certain upper and lower bound, system cannot normally work even destroyed.In this case, be necessary to carry out power-on and power-off control to system, namely when environmental parameter exceedes the threshold value of regulation, and when keeping stable or have the trend more worsened, just carry out power-off by main frame to system to control, when environmental parameter returns within set quota scope, and during the trend repeatedly do not worsened, main frame just carries out energising to system and controls.
Generally can comprise one can be carried out Measurement accuracy environment measurement equipment to environmental parameter in system, measured value can be presented on the display device such as charactron or liquid crystal display by this equipment usually in real time, distinguishes for human eye.At present, usually adopt manual supervisory mode to carry out environmentally parameter and system is carried out to the control of power-on and power-off.That is, within 24 hours, monitored the environmental parameter on above-mentioned display device by special messenger in real time, by main frame, power-on and power-off control is carried out to system thus.Obviously, adopt the not only waste of manpower of manual supervisory mode, and add workload.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of system power-on and power-off control device and method, at least to solve the manual supervisory mode waste of manpower of above-mentioned employing, and adds the problem of workload.
According to an aspect of the present invention, providing a kind of system power-on and power-off control device, comprising: main processing block, for obtaining the environmental parameter value of system current place environment, and judging environmental parameter value whether outside predetermined environmental parameter scope; Control module, for when the judged result of main processing block is for being, control system power-off.
According to a further aspect in the invention, provide a kind of system power-on and power-off control method, comprising: main processing block obtains the environmental parameter value of system current place environment, and judge environmental parameter value whether outside predetermined environmental parameter scope; Control module when the judged result of main processing block is for being, control system power-off.
Pass through the present invention, the environmental parameter value of system current place environment is obtained by arranging main processing block and control module, and in the environmental parameter value determining to obtain when predetermined environmental parameter scope is outer, control system power-off, thus achieve the automatic control of system power-on and power-off, without the need to manual monitoring, solve and adopt manual supervisory mode waste of manpower, and add the problem of workload, achieve the intellectuality realizing system power-on and power-off and control, alleviate labour intensity and the workload of manpower monitoring.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the structural representation of the system power-on and power-off control device according to the embodiment of the present invention;
Fig. 2 is the structural representation of the system power-on and power-off control device according to the preferred embodiment of the present invention one;
Fig. 3 is the structural representation of the system power-on and power-off control device according to the preferred embodiment of the present invention two;
Fig. 4 is the signal wiring schematic diagram of system power-on and power-off control device according to the preferred embodiment of the invention;
Fig. 5 is the process flow diagram of the system power-on and power-off control method according to the embodiment of the present invention;
Fig. 6 is the process flow diagram of extraction environment parameter value according to the preferred embodiment of the invention.
Embodiment
Hereinafter also describe the present invention in detail with reference to accompanying drawing in conjunction with the embodiments.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
Fig. 1 is the schematic diagram of the system power-on and power-off control device according to the embodiment of the present invention, comprise with lower module: main processing block 10, for obtaining the environmental parameter value of system current place environment, and judge that the environmental parameter value obtained is whether outside predetermined environmental parameter scope; Control module 20, for when the judged result of main processing block 10 is for being, control system power-off.
The present embodiment obtains the environmental parameter value of system current place environment by arranging main processing block and control module, and in the environmental parameter value determining to obtain when predetermined environmental parameter scope is outer, control system power-off, thus achieve the automatic control of system power-on and power-off, without the need to manual monitoring, solve and adopt manual supervisory mode waste of manpower, and add the problem of workload, achieve the intellectuality realizing system power-on and power-off and control, alleviate labour intensity and the workload of manpower monitoring.
In order to make full use of the existing equipment in system, when practical application, above-mentioned main processing block 10 can be realized by the main frame in system.A kind of embodiment that main processing block 10 obtains the environmental parameter value of system current place environment can be on the main frame of system, develop the environmental parameter value that independently environmental parameter measurement module carrys out measuring system current place environment, and sends main processing block 10 to.The another kind of embodiment that main processing block 10 obtains the environmental parameter value of system current place environment can also be that the environment measurement equipment in requirement system provides external data communication interface and sends the environmental parameter value of measurement to main processing block 10 by this data communication interface.
In another preferred implementation of the embodiment of the present invention, main processing block 10 can adopt following preferred implementation to obtain the environmental parameter value of system current place environment, in the system power-on and power-off control device of preferred embodiment as shown in Figure 2, can also comprise: image collection module 30, send the image of acquisition to main processing block 10 for the image shown by the display device in acquisition system, wherein, this display device is used for the environmental parameter value of the environment at the current place of display system; Then, main processing block 10 obtains the environmental parameter value of system current place environment with regard to the image that may be used for getting according to image collection module 30.
In actual applications, image collection module 30 can be the first-class camera head of shooting.Obviously, it is front to catch the image including environmental parameter value that display device shows that the camera head in the preferred embodiment needs to be fixed on display device, then passes to main processing block 10.
Along with the development of computer vision technique, simple camera head can be utilized to obtain the image including environmental parameter value of display device display, main processing block 10 such as can use the special algorithm of Computer Vision Recognition, just can extract the environmental parameter value in image, then notified the power-on and power-off of control module 20 control system by main processing block 10 according to these environmental parameter values, thus carry out robotization and the intelligentized control method of system power-on and power-off.
To obtain the function of the environmental parameter value of system current place environment according to the image that image collection module 30 gets in order to realize main processing block 10, as shown in Figure 3, main processing block 10 can comprise: pretreatment module 102, segmentation extraction module 104 and matching module 106, be described below in detail the function of each module.
Pretreatment module 102, carries out pre-service for the image got image collection module 30, obtains the gray-scale map (i.e. the gray-scale map of edge enhancing) suppressed through peak value; The methods such as gaussian filtering can be adopted to carry out pre-service to the image got, thus strengthen marginal information, be conducive to improving matching performance.
Wherein, in order to realize the pre-service to image, pretreatment module 102 can also comprise following four modules:
(1) modular converter, for being converted to gray-scale map by the image of colour;
Such as, coloured image can be converted to gray-scale map according to following formula (1):
I(x，y)＝0.299*R(x，y)+0.587*G(x，y)+0.114*B(x，y)(1)
Wherein, x and y denotation coordination, R (x, y), G (x, and the trichromatic value of colour at B (x, y) denotation coordination (x, y) place y), I (x, y) represents the gray-scale value at coordinate (x, the y) place calculated.
(2) filtering processing module, for carrying out gaussian filtering process to the gray-scale map converted to, obtains filtered gray-scale map;
Such as, in order to strengthen the edge of symbol, gaussian filtering process can be carried out according to following formula (2) to the gray-scale map converted to:
Wherein, * represents convolution algorithm, G
1, G
2represent two different two-dimensional Gaussian functions respectively, their parameter is σ respectively
1and σ
2.That is, the H that the gray-scale map I (x, y) converted to by modular converter is multiplied by as shown in formula (2) namely obtains filtered gray-scale map.
(3) intensity normalized module, for carrying out intensity normalized to filtered gray-scale map, obtains the normalized gray-scale map of intensity;
Such as, intensity normalized can be carried out according to following formula (3) for filtered image:
Wherein,
for positive maximum of intensity,
for negative minimum of intensity, I ' (x, y) for the gray-scale map (also referred to as intensity map) after intensity normalization, I (x, y) be filtered gray-scale map.
(4) peak value suppresses processing module, suppresses process, obtain the gray-scale map suppressed through peak value for carrying out peak value to the normalized gray-scale map of intensity.
Such as, peak value can be carried out according to following formula (4) and suppress process:
Wherein, " (x, y) is the gray-scale map (also referred to as intensity map) suppressed through peak value to I, and 0 < t≤1 is suppression threshold; I ' (x, y) is the gray-scale map (also referred to as intensity map) after intensity normalization.
Through the process of above-mentioned four modules, just obtain the gray-scale map suppressed through peak value, enhance the marginal information of image, therefore, also namely obtain the gray-scale map that edge strengthens, retain this gray-scale map, to use below.
Segmentation extraction module 104, for being partitioned into the image of each symbol from the above-mentioned gray-scale map suppressed through peak value, and extracts the proper vector of each symbol;
Such as, can comprise from the above-mentioned method being partitioned into the image of each symbol through the gray-scale map that peak value suppresses: the gray-scale map (i.e. the above-mentioned gray-scale map suppressed through peak value) after edge strengthens carries out binary conversion treatment, use morphologic opening operation filtering noise, and then carry out closed operation filling crack, the following utilization algorithm that floods is filled, mark connects component, thus obtains the area coordinate of single symbol, is partitioned into single symbol.
Such as, after being partitioned into each symbol, SIFT (Scale invariant features transform) algorithm can be used to extract the proper vector splitting each symbol obtained.SIFT algorithm mainly carries out different collections to image and forms image pyramid hierarchy, then with Gaussian kernel function, the gaussian pyramid hierarchy that convolution algorithm generates metric space is carried out to each tomographic image in image pyramid hierarchy, then difference of Gaussian image is formed to adjacent gaussian filtering image subtraction.Extreme point (comprising maximum value or minimum value) is found in difference of Gaussian image, mainly by each 9 unique points in more each unique point and 8 unique points around it and neighbouring layer, the extreme point found out alternatively point, then remove low contrast in candidate feature point and marginal point and finally obtain stable unique point.Finally calculate the descriptor of unique point, descriptor includes the information such as position, yardstick, direction of unique point, makes each unique point have very high uniqueness, for coupling below provides good parameter by the expression of descriptor.
Matching module 106, for searching the proper vector sample mated with the proper vector of each symbol be partitioned into respectively in the proper vector Sample Storehouse that prestores, for each symbol, the value of this symbol is obtained according to the proper vector sample with this Symbol matching, wherein, the value of each symbol be partitioned into forms above-mentioned environmental parameter value.
Wherein, matching module 106 searches the proper vector sample mated with the proper vector of each symbol be partitioned into respectively in the proper vector Sample Storehouse prestored, for each symbol, the value obtaining this symbol according to the proper vector sample with this Symbol matching comprises: travel through each proper vector sample in proper vector Sample Storehouse successively, calculates the current nearest neighbor distance and time nearest neighbor distance that carry out the proper vector of the symbol mated and the proper vector sample of current traversal; Judge that whether the ratio of nearest neighbor distance and time nearest neighbor distance calculated is lower than predetermined ratio threshold value; When judged result be lower than time, determine currently to carry out the proper vector of the symbol mated and the proper vector sample matches of current traversal, and determine that current value of carrying out the symbol mated is the value of symbol that the proper vector sample of current traversal is corresponding.The method is NN (arest neighbors) method.
Such as, after obtaining the proper vector of single symbol, use the proper vector sample preserved in NN method traversal proper vector sample database, carry out mating of unique point with the proper vector of the symbol extracted.NN (arest neighbors) method is adopted to mate proper vector.Whether NN method is mainly come to mate between judging characteristic vector according to the nearest neighbor distance between proper vector and the ratio of secondary nearest neighbor distance, that is, get a threshold value (i.e. fractional threshold), if ratio is lower than this threshold value, thinks and mate between proper vector.The key of NN method is arest neighbors and time neighbour of search characteristics point, and only choosing arest neighbors and secondary nearest neighbor distance ratio, to be less than mating of a certain thresholding right.A kind of method BBF (the best case mode of priority) improved on k-d tree method for fast searching basis can be adopted when searching for arest neighbors and secondary neighbour.BBF method mainly limits the most high reps of search to k-d tree, and the order utilizing a priority query that search order is increased progressively with distance sample unique point is searched for, thus can find required arest neighbors and time Neighbor Points efficiently.
Wherein, when practical application, after finding the proper vector sample (namely obtaining matching relationship) mated with the proper vector of the symbol be partitioned in the proper vector Sample Storehouse prestored, a kind of broad sense Hough of improvement (Hough) can also be first used to convert the process of carrying out removing wrong coupling in conjunction with Least-squares minimization algorithm.Particularly, Generalized Hough Transform is carried out to SIFT feature vector (proper vector comprising the current symbol mated and the proper vector sample mated with it), because the predictive transformation after Hough transform has very large error boundary, so just need to use least square method to solve affine transformation parameter between two images to be matched (the current proper vector of carrying out the symbol mated namely after Generalized Hough Transform and the proper vector sample mated with it).After trying to achieve least square solution, see and mate each coupling in set whether all meeting the affine transformation parameter solving and obtain between two images to be matched, right to removing the coupling not meeting affine transformation parameter set from original coupling, obtain new coupling to set.In new coupling is to set, again solves affine transformation parameter, repeatedly processes like this, iteration stopping after coupling is to set no longer change.In above-mentioned iterative process, if coupling is less than threshold value to remaining number of pairs in set, then judge that current proper vector of carrying out the symbol mated and the proper vector sample mated with it are erroneous matching.After stopping iteration, if coupling meets threshold requirement to the number of pairs in set, then judge that current proper vector of carrying out the symbol mated and the proper vector sample mated with it are correct couplings.
Because environmental parameter value is generally only positioned at a position of the image shown by display device, therefore main processing block can also comprise: segmentation module 40, for the position of environmental parameter value in the image obtained that basis marks in advance, from the image of this acquisition, be partitioned into the image being positioned at this position, the image be partitioned into exported to pretreatment module and carries out pre-service.Like this, can computation complexity be reduced, improve processing speed.
Generally, can not in environmental parameter value once in predetermined environmental parameter scope (it is generally acknowledged namely belong to normal range within the scope of environmental parameter) outward, i.e. control system power on/off, but obtain repeatedly environmental parameter value, judge the variation tendency of environmental parameter value according to this, when environmental parameter value is in outer and just control system power-off when keeping stable or have the trend of deterioration of environmental parameter scope, when environmental parameter value to return within the scope of environmental parameter and keeps stablize, just control system is energized again.Therefore, as shown in Figure 3, main processing block 10 can also comprise: environmental parameter judge module 108, for carrying out linear fit to the multiple environmental parameter values repeatedly obtained, judges the variation tendency of environmental parameter value; Issue module 109, outer and keep stable or have the trend of deterioration in described environmental parameter scope for determining that at described environmental parameter judge module the variation tendency of described environmental parameter value is described environmental parameter value, and described system is when being in "on" position, issue down power control commands to described control module; Determine that described environmental parameter value keeps stable within the scope of described environmental parameter at described environmental parameter judge module, and when described system is in described off-position, issue described energising control command to described control module.Thus control module can perform according to issuing the control command that module issues the power on/off that corresponding operation realizes system.
As shown in Figure 3, in order to perform according to issuing the control command that module issues the power on/off that corresponding operation realizes system, control module 20 can comprise: micro treatmenting device 202, for according to issuing the down power control commands that module 109 issues, controlling relay system 204 and opening; And according to the energising control command issuing module 109 and issue, control relay system 204 and close; Relay system 204, its one end is connected to the power supply of system, and the other end is connected to system.Therefore, when relay system 204 closes, the power supply of system and system connectivity, achieve the energising of system; When relay system 204 is opened, the power supply of system and system break, achieve the power-off of system.
When practical application, above-mentioned micro treatmenting device 202 can be microprocessor (MCU), and relay system 204 can be relay.
The said apparatus connection diagram in actual applications that Fig. 4 provides for the embodiment of the present invention, as shown in Figure 4, when practical application, existing equipment in system can be utilized to realize the modules in said system power-on and power-off control device, above-mentioned main processing block 10 can be realized by the main frame in system as far as possible.In addition, camera head can be utilized to realize above-mentioned image collection module 30, realize above-mentioned micro treatmenting device 202 by microprocessor, realize above-mentioned relay system 204 by relay.In the diagram, the video data (passing through data communication interface) obtained also is sent to main frame by the image (i.e. the image of shooting shown by display device) shown by display device in camera head acquisition system, then main frame to this video data carry out pre-service obtain through peak value suppress gray-scale map, from the above-mentioned image being partitioned into each symbol through the gray-scale map of peak value suppression, and use SIFT algorithm to extract the proper vector of each symbol, and use NN method to search the proper vector sample mated with the proper vector of each symbol be partitioned into respectively in the proper vector Sample Storehouse prestored, for each symbol, the value of this symbol is obtained according to the proper vector sample with this Symbol matching, finally obtain the environmental parameter value got, after main frame uses said method to get multiple environmental parameter value, linear fit is carried out to these environmental parameter values, determine the variation tendency of environmental parameter value and the state (reporting main frame by the timing microprocessor in control module) in conjunction with current control module repeat circuit issues control command to microprocessor, microprocessor is opened according to the control command pilot relay received or is closed, thus realizes the automatic control of system power-on and power-off.
In conjunction with system power-on and power-off control device as shown in Figure 3, the method that this device controls system power-on and power-off as shown in Figure 5, comprises the following steps:
Step S502, main processing block obtains the environmental parameter value of system current place environment, and judges environmental parameter value whether outside predetermined environmental parameter scope;
Step S504, control module when the judged result of main processing block is for being, control system power-off.
Wherein, before step S502, also comprise: the image shown by display device in image collection module acquisition system also sends the image of acquisition to main processing block, wherein, display device is used for display environment parameter value; Then, step S502 comprises: main processing block is according to Image Acquisition environmental parameter value.Image collection module is fixed on the front of display device, guarantees to catch shown environmental parameter steady and audiblely.
Such as, main processing block can obtain the environmental parameter value of the environment at the current place of system according to following steps:
Step 1, main processing block carries out pre-service to the image that image collection module obtains, and obtains the gray-scale map suppressed through peak value;
Step 2, main processing block is partitioned into the image of each symbol from the gray-scale map suppressed through peak value, and extracts the proper vector of each symbol;
Step 3, main processing block searches the proper vector sample mated with the proper vector of each symbol respectively in the proper vector Sample Storehouse prestored, for each symbol, the value of this symbol is obtained according to the proper vector sample with this Symbol matching, wherein, the value composition environment parameter value of each symbol.
Wherein, main processing block searches the proper vector sample mated with the proper vector of each symbol respectively in the proper vector Sample Storehouse prestored, for each symbol, the value obtaining this symbol according to the proper vector sample with this Symbol matching comprises: main processing block travels through each proper vector sample in proper vector Sample Storehouse successively, calculates the current nearest neighbor distance and time nearest neighbor distance that carry out the proper vector of the symbol mated and the proper vector sample of current traversal; Then, main processing block judges that whether the ratio of nearest neighbor distance and time nearest neighbor distance is lower than predetermined ratio threshold value; When judged result be lower than time, main processing block is determined currently to carry out the proper vector of the symbol mated and the proper vector sample matches of current traversal, and determines that current value of carrying out the symbol mated is the value of symbol that the proper vector sample of current traversal is corresponding.
In order to reduce computation complexity and calculated amount further, before the image obtained image collection module at main processing block carries out pre-service, step can also be comprised: main processing block, according to the position of the environmental parameter value marked in advance in the image obtained, is partitioned into the image being positioned at position from the image obtained; Then main processing block carries out pre-service to the image that image collection module obtains and comprises: main processing block only need carry out pre-service to the image be partitioned into.
Below in conjunction with the preferred embodiment shown in Fig. 4, system power-on and power-off control method is according to the preferred embodiment of the invention described in detail, specifically comprises the following steps as shown in Figure 6:
Step S602, system electrification, main frame correctly can receive the video data that camera head is sent here, and the microprocesser initialization in control module is normal with main-machine communication;
Step S604, the artificial mark region of environmental parameter value in video image;
Step S606, main frame, according to the time interval t of setting, extracts a two field picture, carries out pre-service to the image of the tab area in the image extracted from the video flowing of catching; Due to camera head fixing after, the position of environmental parameter value in ken image generally can not change, the position of an environmental parameter value artificially can be marked in mainframe program, follow-up image is all partitioned into pending image according to marking the coordinate obtained for the first time, thus reduce the complexity of program, improve processing speed.
Such as, pre-service is carried out to image and comprises the following steps 1-4:
Step 1: according to following formula (1), convert coloured image to gray-scale map:
I(x，y)＝0.299*R(x，y)+0.587*G(x，y)+0.114*B(x，y)(1)
Wherein, x and y denotation coordination, R (x, y), G (x, and the trichromatic value of colour at B (x, y) denotation coordination (x, y) place y), I (x, y) represents the gray-scale value at coordinate (x, the y) place calculated.
Step 2: in order to strengthen the edge of symbol, gaussian filtering process can be carried out according to following formula (2) to gray-scale map:
Wherein, * represents convolution algorithm, G
1, G
2represent two different two-dimensional Gaussian functions respectively, their parameter is σ respectively
1and σ
2.That is, the H that the gray-scale map I (x, y) converted to by modular converter is multiplied by as shown in formula (2) namely obtains filtered gray-scale map.
Step 3: according to following formula (3), intensity normalized is carried out for filtered image:
Wherein,
for positive maximum of intensity,
for negative minimum of intensity, I ' (x, y) for the gray-scale map (also referred to as intensity map) after intensity normalization, I (x, y) be filtered gray-scale map.
Step 4: according to following formula (4), peak value is carried out to the gray-scale map after intensity normalization and suppress process:
Wherein, " (x, y) is the gray-scale map (also referred to as intensity map) suppressed through peak value to I, and 0 < t≤1 is suppression threshold; I ' (x, y) is the gray-scale map (also referred to as intensity map) after intensity normalization.
Through the process of above-mentioned steps, just obtain the gray-scale map that edge strengthens, retain this gray-scale map, to use below.
Step S608, is partitioned into single symbol from pretreated image.Gray-scale map after edge strengthens carries out binary conversion treatment, uses morphologic opening operation filtering noise, is then carrying out closed operation filling crack.The following utilization algorithm that floods is filled, and mark connects component, thus obtains the area coordinate of single symbol, according to the area coordinate of the single symbol obtained, is partitioned into the image of single symbol from the gray-scale map after strengthening.
Step S610, extracts single symbolic feature vector by SIFT method.SIFT method is mainly carried out different collections to image and is formed image pyramid hierarchy, then with Gaussian kernel function, the gaussian pyramid hierarchy that convolution algorithm generates metric space is carried out to each tomographic image in image pyramid hierarchy, then difference of Gaussian image is formed to adjacent gaussian filtering image subtraction.Extreme point (comprising maximum value or minimum value) is found in difference of Gaussian image, mainly by each 9 unique points in more each unique point and 8 unique points around it and neighbouring layer, the extreme point found out alternatively point, then remove low contrast in candidate feature point and marginal point and finally obtain stable unique point.Finally calculate the descriptor of unique point, descriptor includes the information such as position, yardstick, direction of unique point, makes each unique point have very high uniqueness, for coupling below provides good parameter by the expression of descriptor.
Step S612, judges according to pre-conditioned, if using the coupling benchmark of the proper vector of extraction as corresponding symbol, then perform step S614.If carry out matching operation, then perform step S616.
Step S614, before mainframe program uses, makes the proper vector Sample Storehouse of glossary of symbols, as coupling benchmark.
Step S616, after obtaining the proper vector of single symbol, the proper vector Sample Storehouse of traversal glossary of symbols.NN method (arest neighbors method) is adopted to mate unique point.Whether NN method is mainly come to mate between judging characteristic point with the ratio of secondary nearest neighbor distance according to the nearest neighbor distance of unique point, gets a threshold value, if lower than this threshold value, thinks and mate between unique point.The key of NN method is arest neighbors and time neighbour of search characteristics point, and only choosing arest neighbors and secondary nearest neighbor distance ratio, to be less than mating of a certain thresholding right.A kind of method BBF (the best case mode of priority) improved on k-d tree method for fast searching basis is have employed when searching for arest neighbors and secondary neighbour.BBF method mainly limits the most high reps of search to k-d tree, and the order utilizing a priority query that search order is increased progressively with distance sample unique point is searched for, thus can find required arest neighbors and time Neighbor Points efficiently.Generalized Hough Transform is carried out to SIFT feature vector (proper vector comprising the current symbol mated and the proper vector sample mated with it), because the predictive transformation after Hough transform has very large error boundary, so just need to use least square method to solve affine transformation parameter between two images to be matched.After trying to achieve least square solution, see and mate each coupling in set whether all meeting the affine transformation parameter solving and obtain between two images to be matched, right to removing the coupling not meeting affine transformation parameter set from original coupling, obtain new coupling to set.In new coupling is to set, again solves affine transformation parameter, repeatedly processes like this, iteration stopping after coupling is to set no longer change.In above-mentioned iterative process, if coupling is less than threshold value to remaining number of pairs in set, then judge that current proper vector of carrying out the symbol mated and the proper vector sample mated with it are erroneous matching.After stopping iteration, if coupling meets threshold requirement to the number of pairs in set, then judge that current proper vector of carrying out the symbol mated and the proper vector sample mated with it are correct couplings.
Step S618, if the matching operation in step S616 does not obtain correct coupling, then performs step S620, if the match is successful, then performs step S622.
Step S620, if certain Symbol matching is unsuccessful, all results that so current environmental parameter is extracted are invalid, not to subsequent module output environment parameter value.
Step S622, if the success of single Symbol matching, preserves matching result.
Step S624, has judged whether the coupling of all symbols in the ken of mark, if do not completed, then performs step S608, if all completed, then performs step S626.
Step S626, carries out linear fit for up-to-date some groups of environmental parameter values of catching, obtains the variation tendency of environmental parameter value, then exports control command according to the environmental parameter scope of setting; Control module is periodically to the current state of telegraph relay on main frame.The current state of the variation tendency of main frame combining environmental parameter value, environmental parameter scope and relay, judges whether to need to export control command to control module.
Step S628, the control command that control module is sent here according to main frame, pilot relay carries out being energized and power operation.
As can be seen from the above description, present invention achieves following technique effect:
(1) by adopting computer vision technique extraction environment parameter value, realizing the intelligentized control method to system power-on and power-off, alleviating labour intensity and the workload of manpower monitoring.
(2) owing to uninterruptedly can monitor environmental parameter value, therefore, it is possible to effectively improve the safety coefficient of system reply abnormal environment.
(3) adopt the common hardware configuration of low cost, farthest can utilize existing equipment, for different display devices and display mode, only need upgrade software, there is dirigibility and adaptability.
Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on network that multiple calculation element forms, alternatively, they can realize with the executable program code of calculation element, thus, they can be stored and be performed by calculation element in the storage device, and in some cases, step shown or described by can performing with the order be different from herein, or they are made into each integrated circuit modules respectively, or the multiple module in them or step are made into single integrated circuit module to realize.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. a system power-on and power-off control device, is characterized in that, comprising:
Main processing block, for obtaining the environmental parameter value of described system current place environment, and judges described environmental parameter value whether outside predetermined environmental parameter scope;
Control module, for when the judged result of described main processing block is for being, controls described system cut-off;
Image collection module, for obtaining image shown by the display device in described system and sending the described image obtained to described main processing block, wherein, described display device is for showing described environmental parameter value;
Described main processing block is used for environmental parameter value according to described Image Acquisition;
Wherein,
Described main processing block also comprises:
Environmental parameter judge module, for carrying out linear fit to the multiple described environmental parameter value repeatedly obtained, judges the variation tendency of described environmental parameter value;
Issue module, outer and keep stable or have the trend of deterioration in described environmental parameter scope for determining that at described environmental parameter judge module the variation tendency of described environmental parameter value is described environmental parameter value, and described system is when being in "on" position, issue down power control commands to described control module; Determine that described environmental parameter value keeps stable within the scope of described environmental parameter at described environmental parameter judge module, and when described system is in off-position, issue energising control command to described control module.
2. device according to claim 1, is characterized in that, described main processing block comprises:
Pretreatment module, carries out pre-service for the image obtained described image collection module, obtains the gray-scale map suppressed through peak value;
Segmentation extraction module, for being partitioned into the image of each symbol from described gray-scale map, and extracts the proper vector of each described symbol;
Matching module, for searching the proper vector sample mated with the proper vector of symbol described in each respectively in the proper vector Sample Storehouse that prestores, for each described symbol, the value of this symbol is obtained according to the proper vector sample with this Symbol matching, wherein, the value of symbol described in each forms described environmental parameter value.
3. device according to claim 2, is characterized in that, described pretreatment module comprises:
Modular converter, for being converted to gray-scale map by the image of colour;
Filtering processing module, for carrying out gaussian filtering process to the gray-scale map converted to, obtains filtered gray-scale map;
Intensity normalized module, for carrying out intensity normalized to described filtered gray-scale map, obtains the normalized gray-scale map of intensity;
Peak value suppresses processing module, suppresses process, obtain the described gray-scale map suppressed through peak value for carrying out peak value to the normalized gray-scale map of described intensity.
4. device according to claim 2, is characterized in that, described main processing block also comprises:
Segmentation module, for according to the position of described environmental parameter value in the image of described acquisition marked in advance, is partitioned into the image being positioned at described position, the image be partitioned into is exported to described pretreatment module and carries out pre-service from the image of described acquisition.
5. device according to claim 1, is characterized in that, described control module comprises:
Micro treatmenting device, for issuing the described down power control commands that module issues described in basis, controlling relay system and opening; And according to the described described energising control command issuing module and issue, control relay system and close;
Described relay system, its one end is connected to the power supply of described system, and the other end is connected to described system.
6. a system power-on and power-off control method, is characterized in that, comprising:
Main processing block obtains the environmental parameter value of described system current place environment, and judges described environmental parameter value whether outside predetermined environmental parameter scope;
Control module, when the judged result of described main processing block is for being, controls described system cut-off;
Obtain the environmental parameter value of described system current place environment at main processing block before, also comprise: image collection module obtains the image shown by the display device in described system and sends the described image obtained to described main processing block, wherein, described display device is for showing described environmental parameter value;
The environmental parameter value that main processing block obtains described system current place environment comprises: described main processing block is environmental parameter value according to described Image Acquisition; Wherein, described main processing block also comprises environmental parameter judge module and issues module;
Wherein, described environmental parameter judge module, carries out linear fit to the multiple described environmental parameter value repeatedly obtained, judges the variation tendency of described environmental parameter value;
Describedly issue module, determine that the variation tendency of described environmental parameter value is described environmental parameter value at described environmental parameter judge module outer and keep stable or have the trend of deterioration in described environmental parameter scope, and described system is when being in "on" position, issue down power control commands to described control module; Determine that described environmental parameter value keeps stable within the scope of described environmental parameter at described environmental parameter judge module, and when described system is in off-position, issue energising control command to described control module.
7. method according to claim 6, is characterized in that, described main processing block environmental parameter value according to described Image Acquisition comprises:
Described main processing block carries out pre-service to the image that described image collection module obtains, and obtains the gray-scale map suppressed through peak value;
Described main processing block is partitioned into the image of each symbol from described gray-scale map, and extracts the proper vector of each described symbol;
Described main processing block searches the proper vector sample mated with the proper vector of symbol described in each respectively in the proper vector Sample Storehouse prestored, for each described symbol, the value of this symbol is obtained according to the proper vector sample with this Symbol matching, wherein, the value of symbol described in each forms described environmental parameter value.
8. method according to claim 7, it is characterized in that, described main processing block searches the proper vector sample mated with the proper vector of symbol described in each respectively in the proper vector Sample Storehouse prestored, for each described symbol, the value obtaining this symbol according to the proper vector sample with this Symbol matching comprises:
Described main processing block travels through each proper vector sample in described proper vector Sample Storehouse successively, calculates the current nearest neighbor distance and time nearest neighbor distance that carry out the proper vector of the symbol mated and the proper vector sample of current traversal;
Described main processing block judges that whether the ratio of described nearest neighbor distance and described nearest neighbor distance is lower than predetermined ratio threshold value;
When judged result be lower than time, described main processing block is determined describedly currently to carry out the proper vector of the symbol mated and the proper vector sample matches of described current traversal, and determines that described current value of carrying out the symbol mated is the value of symbol that the proper vector sample of described current traversal is corresponding.
9. method according to claim 7, is characterized in that,
Before the image obtained described image collection module at described main processing block carries out pre-service, also comprise: described main processing block, according to the position of described environmental parameter value in the image of described acquisition marked in advance, is partitioned into the image being positioned at described position from the image of described acquisition;
Described main processing block carries out pre-service to the image that described image collection module obtains and comprises: described main processing block carries out pre-service to the image be partitioned into.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010531966.XA CN102004537B (en) | 2010-11-04 | 2010-11-04 | System power-on and power-off control device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010531966.XA CN102004537B (en) | 2010-11-04 | 2010-11-04 | System power-on and power-off control device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102004537A CN102004537A (en) | 2011-04-06 |
| CN102004537B true CN102004537B (en) | 2016-03-02 |
Family
ID=43811946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010531966.XA Active CN102004537B (en) | 2010-11-04 | 2010-11-04 | System power-on and power-off control device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102004537B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930779A (en) * | 2016-04-14 | 2016-09-07 | 吴本刚 | Image scene mode generation device |
| CN108806334A (en) * | 2018-04-27 | 2018-11-13 | 中船重工鹏力（南京）大气海洋信息系统有限公司 | A kind of intelligent ship personal identification method based on image |
| CN112825011A (en) * | 2019-11-20 | 2021-05-21 | 中兴通讯股份有限公司 | Power-on and power-off control method and system of PCIe device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101651335A (en) * | 2009-09-23 | 2010-02-17 | 福建星网锐捷网络有限公司 | Electronic equipment protection device and electronic equipment |
| CN101666645A (en) * | 2009-09-08 | 2010-03-10 | 深圳市克莱沃电子有限公司 | Machine room minute environment monitoring system |
| CN101751019A (en) * | 2008-12-18 | 2010-06-23 | 珠海格力电器股份有限公司 | Monitoring system for environment simulation |
-
2010
- 2010-11-04 CN CN201010531966.XA patent/CN102004537B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751019A (en) * | 2008-12-18 | 2010-06-23 | 珠海格力电器股份有限公司 | Monitoring system for environment simulation |
| CN101666645A (en) * | 2009-09-08 | 2010-03-10 | 深圳市克莱沃电子有限公司 | Machine room minute environment monitoring system |
| CN101651335A (en) * | 2009-09-23 | 2010-02-17 | 福建星网锐捷网络有限公司 | Electronic equipment protection device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102004537A (en) | 2011-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163236B (en) | Model training method and device, storage medium and electronic device | |
| EP4116867A1 (en) | Vehicle tracking method and apparatus, and electronic device | |
| CN109919002B (en) | Yellow stop line identification method and device, computer equipment and storage medium | |
| US20170061252A1 (en) | Method and device for classifying an object of an image and corresponding computer program product and computer-readable medium | |
| CN112233124A (en) | Point cloud semantic segmentation method and system based on countermeasure learning and multi-modal learning | |
| CN104680510A (en) | RADAR parallax image optimization method and stereo matching parallax image optimization method and system | |
| CN109145742A (en) | A kind of pedestrian recognition method and system | |
| CN105701467A (en) | Many-people abnormal behavior identification method based on human body shape characteristic | |
| CN107067595B (en) | State identification method and device of indicator light and electronic equipment | |
| CN103164693B (en) | A kind of monitor video pedestrian detection matching process | |
| CN105844205A (en) | Character information identification method based on image processing | |
| CN109447036A (en) | A kind of segmentation of image digitization and recognition methods and system | |
| CN106952293A (en) | A kind of method for tracking target based on nonparametric on-line talking | |
| CN102004537B (en) | System power-on and power-off control device and method | |
| CN110796135A (en) | Target positioning method and device, computer equipment and computer storage medium | |
| Wang et al. | Combining semantic scene priors and haze removal for single image depth estimation | |
| Zhang et al. | New mixed adaptive detection algorithm for moving target with big data | |
| CN104700105A (en) | Global detection method of unstructured outdoor terrains | |
| CN103049747B (en) | The human body image utilizing the colour of skin knows method for distinguishing again | |
| CN204256521U (en) | A kind of information fusion positioning system based on RFID and vision | |
| CN115862055A (en) | Pedestrian re-identification method and device based on comparison learning and confrontation training | |
| CN107274382B (en) | State identification method and device of hard pressing plate and electronic equipment | |
| CN111815689B (en) | Semi-automatic labeling method, equipment, medium and device | |
| CN108537843A (en) | The method and device of depth of field distance is obtained according to depth image | |
| CN110148105B (en) | Video analysis method based on transfer learning and video frame association learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |