CN112200839A - Infant protection socket based on image processing and protection method thereof - Google Patents
Infant protection socket based on image processing and protection method thereof Download PDFInfo
- Publication number
- CN112200839A CN112200839A CN202011089987.0A CN202011089987A CN112200839A CN 112200839 A CN112200839 A CN 112200839A CN 202011089987 A CN202011089987 A CN 202011089987A CN 112200839 A CN112200839 A CN 112200839A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- socket
- single chip
- chip microcomputer
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000035772 mutation Effects 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 9
- 238000013459 approach Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000087 stabilizing effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000006641 stabilisation Effects 0.000 claims description 4
- 238000011105 stabilization Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 230000001681 protective effect Effects 0.000 description 8
- 230000014509 gene expression Effects 0.000 description 4
- 210000000697 sensory organ Anatomy 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000007920 subcutaneous administration Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000004304 visual acuity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an infant protection socket based on image processing and a protection method thereof, wherein the infant protection socket comprises a camera, a singlechip data processing system and a relay control module; the camera is electrically connected with the singlechip data processing system and the relay control module in sequence; the power supply module is respectively and electrically connected with the single chip microcomputer data processing system, the relay control module and 220V alternating current; the relay control module is connected with the jacks of the socket in an on-off manner. The invention collects the picture through the camera, the singlechip continuously detects whether the picture has a moving object, if so, the head-body ratio of the picture is compared with a preset value in the singlechip, if the head-body ratio is smaller than a predicted value, the target is judged not to be an infant, otherwise, the target is judged to be close to the infant, meanwhile, the singlechip also detects whether the target height has a large mutation, if so, the target is resculed as a non-dangerous target, and if not, the protection operation is implemented.
Description
Technical Field
The invention belongs to the technical field of sockets, and particularly relates to an infant protection socket based on image processing and a protection method thereof.
Background
Nowadays, people's life can not be cut off, and family households have many sockets distributed in all corners of a house, and the tragedy of electric shock caused by mistaken contact of a socket by an infant without resolving power is frequently generated in real life. The infant close to the socket is identified by means of identification technology, the safety of the socket can be greatly improved by timely cutting off the power supply, and the reliability of the safety socket is related to the identification method.
With the popularization of intelligent identification technology, facial recognition is widely applied to the aspects of life, a mobile phone can be unlocked through facial recognition, the facial recognition signing-in authentication is often used in office places, shopping can also be carried out through the facial recognition in supermarkets, and the facial recognition is also applied to the modern criminal investigation technology. However, it is very difficult to use facial technology to identify infants close to the outlet: first, it is difficult to ensure that the face of the infant is just in the shooting area of the camera; secondly, the common face recognition is obtained by extracting the facial features of an individual and analyzing the whole surface, the shape, the size of five sense organs and the distance between the five sense organs, and the method seems to be unreliable for infants who are difficult to manage and control the expression of the infant; at present, a more reliable face recognition method is also available, and features of a human face are extracted and the structure of a subcutaneous blood vessel of the human is analyzed through a heat drawing technology, however, the technology is extremely high in manufacturing cost and is not suitable for daily life.
The presence of protective sockets for babies or small children is at an almost preliminary stage in the market, and more socket designs are mainly made by external safeguards. For example, the socket protection covers on the market have a very simple working principle, namely, the insulation objects matched with the socket openings cover the sockets, but the objects have very big disadvantages. First it requires manual operation and iterative steps. You need to remove the protective cover when you are using and cover it when you are not using. However, in a home, the number of the socket openings is about twenty, and repeated covering and removing of the protective cover causes omission in a heavy burden. In addition, it is not guaranteed that the infant or toddler will not be removed by itself.
Disclosure of Invention
In view of the above-mentioned shortcomings in the prior art, an object of the present invention is to provide an infant protection socket and a protection method thereof based on image processing, so as to solve or improve the above-mentioned problems.
In order to achieve the purpose, the invention adopts the technical scheme that:
an image processing based infant protection outlet, comprising:
the system comprises a camera, a singlechip data processing system and a relay control module; the camera is electrically connected with the singlechip data processing system and the relay control module in sequence; the power supply module is respectively and electrically connected with the single chip microcomputer data processing system, the relay control module and 220V alternating current; the relay control module is connected with the jacks of the socket in an on-off manner.
Preferably, the singlechip data processing system mainly comprises a serial communication interface, a singlechip, a reset circuit and a power module.
Preferably, the reset circuit is an internal integrated MAX810 dedicated reset circuit; the power supply module comprises a voltage reduction part and a rectification and voltage stabilization part; the voltage stabilizing part comprises 7805 and 7905 voltage stabilizing chips.
Preferably, the camera adopts embedded camera, and the camera is installed in vertical socket top.
Preferably, the single chip microcomputer is an STC12C5A60S2 single chip microcomputer.
Preferably, the relay control module is an HH54P type relay.
The protection method of the infant protection socket based on image processing comprises the following steps:
s1, the camera collects the current environment image picture in real time and transmits the collected image picture to the singlechip;
s2, the single chip microcomputer acquires an image and processes the image;
s3, judging whether a moving object exists in the current image picture, if not, continuing to judge the next frame of image picture until the moving object is detected;
s4, comparing the proportion of the pixels of the head of the detected moving object on the vertical axis with a preset value in the single chip microcomputer, if the proportion of the pixels of the head of the detected moving object on the vertical axis is smaller than the preset value, judging that the target is a non-dangerous target, and returning to S3; if the current time is greater than the preset value, the current time is judged to be a dangerous target, and S5 is entered;
s5, judging whether the height of the image corresponding to the dangerous target has a large mutation, if so, re-dividing the current dangerous target into a non-dangerous target, and returning to S3; if the voltage does not suddenly change, the single chip microcomputer outputs low level to a control pin of the control relay to control the relay, so that contacts of the relay are switched, a live wire connected with the socket jack is disconnected with a live wire of external 220V alternating current, and the socket is automatically powered off when an infant approaches the socket.
Preferably, the single chip microcomputer in S2 acquires the image picture and processes the image picture, including;
s2.1, carrying out Gaussian filtering on the acquired image picture to remove image noise points; histogram equalization and Laplace sharpening are adopted to remove image brightness difference and enhance details;
s2.2, quickly establishing a background model of image pixel points by using a VIBE algorithm, and detecting a foreground;
and S2.3, based on OpenCV, extracting areas occupied by the head pixels and the body pixels respectively according to the position of the head in the foreground and the difference of the outlines of the head and the body.
Preferably, the step S2.2 of rapidly establishing a background model of the image by using the VIBE algorithm to detect the foreground includes:
s2.2.1, initializing a background model of each pixel point in the single frame image, assuming that the pixel values of each pixel and its neighborhood pixels have similar distribution in the spatial domain, each pixel model can be represented by the pixels in its neighborhood, when the first frame image is input, i.e. when t is 0, the background model BK of the pixel is represented by the pixel value of the first frame imageM 0Comprises the following steps:
BKM 0＝f0(xi,yi)|(xi，yi)∈NG(x,y)
wherein N isG(x, y) are spatially adjacent pixel values, f0(x, y) is the pixel value of the current point, N is the initialization process of N timesG(x, y) of pixelsi，yi) The possible number of times of selection is L ═ 1,2,3, …, N;
s2.2.2, performing foreground object segmentation operation on the subsequent image sequence, and when t is equal to k, the background model of the pixel point (x, y) is BKM k-1(x, y) pixel value of fk(x, y), and judging whether the pixel value is foreground:
fk(x,y)＝BKM k-1(xr，yr)＞T foregound
fk(x,y)＝BKM k-1(xr，yr)≤T backgound
wherein r represents random selection, T is a preset threshold value, and when f isk(x, y) satisfy background # N times, pixel point fk(x, y) is background, otherwise foreground;
s2.2.3, updating the background model by adopting a ViBe algorithm, comprising:
the random property in time is randomly extracted from N background models and is set as an image PGWhen a new frame of image P is obtainedtIf the image P is normal, if the image P is normaltPixel P corresponding to x position in (1)t(x) Is judged to beFor background, then PGIs updated;
spatially random selection of PG(x) Randomly extracts a pixel P from the eight neighborhoodsG(r) with Pt(x) By replacing PG(r)。
The infant protection socket based on image processing and the protection method thereof provided by the invention have the following beneficial effects:
compared with the socket protective covers on the market, the socket protective cover has the advantages of automation, intelligence and leak resistance, the common protective cover needs to artificially cover the jacks needing to be prevented from being touched by mistake, the operation mode is troublesome, and in the information era, the use frequency of the socket is greatly increased due to the fact that people use electronic equipment more and more times every day. If the user removes and covers the protective cover every time the user starts to use and finishes using, the trouble of the user is undoubtedly increased, and even the user probably gives up using the protective cover after a long time; and secondly, some jacks which are forgotten to be covered after being used up are easily omitted, the original purpose of the product is lost due to the situation, the camera automatically collects the shot pictures for processing, if a baby approaches, the power supply is automatically cut off, and the problem of the former is solved.
Compared with common identification, the method is more accurate; the face recognition technology is to identify various facial features of a human face in a picture, such as the size of five sense organs, the distance and the like, to judge whether a baby approaches, and the identification mode can cause two problems: (1) how to ensure that the device always captures the face of the person approaching? If the infant does not ideally climb right up against the socket camera, then a large potential device may not capture its facial picture. (2) How to solve the baby expression change condition? The expressions of the infant are quite rich and if the infant approaches the device with some special expressions, the system may miss the determination of the facial features. The recognition mode of the invention is to measure the body shape and height of the object in the picture, so that the problems are well solved.
Compared with the heat mapping technology, the device can accurately identify whether the object in the picture is a baby or not. But the cost is too high to be used in household, and the cost of the invention is far lower, so the invention can be widely used in each household.
Drawings
FIG. 1 is a hardware flow diagram of the present invention.
FIG. 2 is a software flow diagram of the present invention.
FIGS. 3 and 4 are images P of the present inventionGAnd pixels within its eight neighborhood.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
According to an embodiment of the application, referring to fig. 1, the infant protection socket based on image processing in the scheme comprises a camera, a single chip microcomputer data processing system and a relay control module; the camera is electrically connected with the singlechip data processing system and the relay control module in sequence; the power supply module is respectively and electrically connected with the singlechip data processing system and the relay control module; the relay control module is connected with the jacks of the socket in an on-off manner.
The single chip data processing system mainly comprises a serial communication interface, a single chip, a reset circuit and a power supply module. The reset circuit is a special reset circuit for an internal integrated MAX 810; the power supply module comprises a voltage reduction part, a rectification voltage stabilization part and a voltage stabilization part; the voltage stabilizing part comprises 7805 and 7905 voltage stabilizing chips.
The camera adopts embedded camera, and the camera is located vertical socket top and is convenient for shoot the infant.
The singlechip selects STC12C5A60S 2.
The relay control module adopts an HH54P type relay.
According to an embodiment of the present application, referring to fig. 2, a method for protecting an infant protection socket based on image processing includes:
s1, the camera collects the current environment image picture in real time and transmits the collected image picture to the singlechip;
s2, the single chip acquires the image picture, and processes and judges the image picture, the specific steps include:
s2.1, carrying out Gaussian filtering on the acquired image picture to remove image noise points; histogram equalization and Laplace sharpening are adopted to remove image brightness difference and enhance details;
s2.2, quickly establishing a background model of image pixel points by using a VIBE algorithm, and detecting a foreground;
and S2.3, based on OpenCV, extracting the areas occupied by the head pixels and the body pixels respectively according to the position of the head in the foreground (the head outline is more inclined to the ellipse) and the difference of the outlines of the head and the body parts.
Wherein the head to body ratio of the infant should be greater.
Gaussian filtering: the Gaussian filtering is a linear smooth filtering, is a process of carrying out weighted average on the whole image, obtains the value of each pixel point by carrying out weighted average on the value of each pixel point and other pixel values in the neighborhood, and is suitable for the noise reduction process of image processing.
Histogram equalization: this method is often used to increase the global contrast of many images, especially when the contrast of the useful data of the images is relatively close, by which the luminance can be better distributed over the histogram, which can be used to enhance the local contrast without affecting the overall contrast.
Laplacian sharpening: when the gray level of the central pixel of the neighborhood is lower than the average gray level of other pixels in the neighborhood, the gray level of the central pixel is further reduced, and when the gray level of the central pixel of the neighborhood is higher than the average gray level of other pixels in the neighborhood, the gray level of the central pixel is further improved, so that the sharpening processing of the image is realized, and the details of the image are enhanced.
VIBE foreground extraction algorithm: the algorithm uses neighborhood pixels to create a background model, and detects the foreground by comparing the background model with the current input pixel values, including:
s2.2.1, initializing a background model of each pixel point in the single frame image, assuming that the pixel values of each pixel and its neighborhood pixels have similar distribution in the spatial domain, each pixel model can be represented by the pixels in its neighborhood, when the first frame image is input, i.e. when t is 0, the background model BK of the pixel is represented by the pixel value of the first frame imageM 0Comprises the following steps:
BKM 0＝f0(xi,yi)|(xi，yi)∈NG(x,y)
wherein N isG(x, y) are spatially adjacent pixel values, f0(x, y) is the pixel value of the current point, N is the initialization process of N timesG(x, y) of pixelsi，yi) The possible number of times of selection is L ═ 1,2,3, …, N:
s2.2.2, performing foreground object segmentation operation on the subsequent image sequence, and when t is equal to k, the background model of the pixel point (x, y) is BKM k-1(x, y) pixel value of fk(x, y), and judging whether the pixel value is foreground:
fk(x,y)＝BKM k-1(xr，yr)＞T foregound
fk(x,y)＝BKM k-1(xr，yr)≤T backgound
wherein r represents random selection, T is a preset threshold value, and when f isk(x, y) satisfy background # N times, pixel point fk(x, y) is background, otherwise foreground;
s2.2.3, updating the background model by adopting a ViBe algorithm, comprising:
referring to fig. 3 and 4, the temporal randomness, which randomly extracts one of N background models, is set as an image PGWhen a new frame of image P is obtainedtIf the image P is normal, if the image P is normaltPixel P corresponding to x position in (1)t(x) Is judged as background, then PGIs updated;
follow in spaceMechanical selection at PG(x) Randomly extracts a pixel P from the eight neighborhoodsG(r) with Pt(x) By replacing PG(r)。
Namely Pt(x) And the P (x) and the eight neighborhoods thereof are updated, and ghost images and errors generated by the acquired video fine jitter (camera jitter and target micromotion) can be removed by adopting an eight neighborhood updating method, so that the target detection is more accurate.
S3, judging whether a moving object exists in the current image picture, if not, continuing to judge the next frame of image picture until the moving object is detected;
s4, comparing the proportion of the pixels of the head of the detected moving object on the vertical axis with a preset value in the single chip microcomputer, if the proportion of the pixels of the head of the detected moving object on the vertical axis is smaller than the preset value, judging that the target is a non-dangerous target, and returning to S3; if the current time is greater than the preset value, the current time is judged to be a dangerous target, and S5 is entered;
s5, judging whether the height of the image corresponding to the dangerous target has a large mutation, if so, re-dividing the current dangerous target into a non-dangerous target, and returning to S3; if the voltage does not suddenly change, the single chip microcomputer outputs low level to a control pin of the control relay to control the relay, so that contacts of the relay are switched, a live wire connected with the socket jack is disconnected with a live wire of external 220V alternating current, and the socket is automatically powered off when an infant approaches the socket.
The method for judging whether the infant approaches the socket comprises the steps that the camera collects a picture, the single chip microcomputer continuously detects whether a moving object exists in the picture, when the picture is in some cases, the head-body proportion of the moving object is compared with a preset value in the single chip microcomputer, if the picture is smaller than the predicted value, the target is judged not to be the infant, and otherwise, the infant approaches. Meanwhile, the singlechip also detects whether the height of the target has a large mutation, if so, the target is rescaled as a non-dangerous target, and if not, the protection operation is implemented.
While the embodiments of the invention have been described in detail in connection with the accompanying drawings, it is not intended to limit the scope of the invention. Various modifications and changes may be made by those skilled in the art without inventive step within the scope of the appended claims.
Claims (9)
1. An infant protects socket based on image processing its characterized in that: the system comprises a camera, a singlechip data processing system and a relay control module; the camera is sequentially electrically connected with the single chip microcomputer data processing system and the relay control module; the power supply module is respectively and electrically connected with the single chip microcomputer data processing system, the relay control module and 220V alternating current; and the relay control module is connected with the jacks of the socket in a switching-on and switching-off manner.
2. The image processing-based infant protection outlet of claim 1, wherein: the single chip microcomputer data processing system mainly comprises a serial communication interface, a single chip microcomputer, a reset circuit and a power supply module.
3. The image processing-based infant protection outlet of claim 2, wherein: the reset circuit is a special reset circuit for an internal integrated MAX 810; the power supply module comprises a voltage reduction part and a rectification and voltage stabilization part; the voltage stabilizing part comprises 7805 and 7905 voltage stabilizing chips.
4. The image processing-based infant protection outlet of claim 1, wherein: the camera adopts embedded camera, and the camera is installed in vertical socket top.
5. The image processing-based infant protection outlet of claim 1, wherein: the type of the single chip microcomputer is STC12C5A60S2 single chip microcomputer.
6. The image processing-based infant protection outlet of claim 1, wherein: the relay control module is an HH54P type relay.
7. The method of protecting an infant protection outlet based on image processing according to any one of claims 1 to 6, comprising:
s1, the camera collects the current environment image picture in real time and transmits the collected image picture to the singlechip;
s2, the single chip microcomputer acquires an image and processes the image;
s3, judging whether a moving object exists in the current image picture, if not, continuing to judge the next frame of image picture until the moving object is detected;
s4, comparing the proportion of the pixels of the head of the detected moving object on the vertical axis with a preset value in the single chip microcomputer, if the proportion of the pixels of the head of the detected moving object on the vertical axis is smaller than the preset value, judging that the target is a non-dangerous target, and returning to S3; if the current time is greater than the preset value, the current time is judged to be a dangerous target, and S5 is entered;
s5, judging whether the height of the image corresponding to the dangerous target has a large mutation, if so, re-dividing the current dangerous target into a non-dangerous target, and returning to S3; if the voltage does not suddenly change, the single chip microcomputer outputs low level to a control pin of the control relay to control the relay, so that contacts of the relay are switched, a live wire connected with the socket jack is disconnected with a live wire of external 220V alternating current, and the socket is automatically powered off when an infant approaches the socket.
8. The infant protection socket protection method based on image processing according to claim 7, wherein the single chip microcomputer in S2 acquires an image picture and processes the image picture, including;
s2.1, carrying out Gaussian filtering on the acquired image picture to remove image noise points; histogram equalization and Laplace sharpening are adopted to remove image brightness difference and enhance details;
s2.2, quickly establishing a background model of image pixel points by using a VIBE algorithm, and detecting a foreground;
and S2.3, based on OpenCV, extracting areas occupied by the head pixels and the body pixels respectively according to the position of the head in the foreground and the difference of the outlines of the head and the body.
9. The image-processing-based infant protection socket protection method according to claim 8, wherein the step of rapidly establishing a background model of the image by using a VIBE algorithm in the step S2.2 to detect a foreground includes:
s2.2.1, initializing a background model of each pixel point in the single frame image, assuming that the pixel values of each pixel and its neighborhood pixels have similar distribution in the spatial domain, each pixel model can be represented by the pixels in its neighborhood, when the first frame image is input, i.e. when t is 0, the background model BK of the pixel is represented by the pixel value of the first frame imageM 0Comprises the following steps:
BKM 0＝f0(xi,yi)|(xi，yi)∈NG(x,y)
wherein N isG(x, y) are spatially adjacent pixel values, f0(x, y) is the pixel value of the current point, N is the initialization process of N timesG(x, y) of pixelsi，yi) The possible number of times of selection is L ═ 1,2,3, …, N;
s2.2.2, performing foreground object segmentation operation on the subsequent image sequence, and when t is equal to k, the background model of the pixel point (x, y) is
Pixel value of fk(x, y), and judging whether the pixel value is foreground:
wherein r represents random selection, T is a preset threshold value, and when f isk(x, y) satisfy background # N times, pixel point fk(x, y) is background, otherwise foreground;
s2.2.3, updating the background model by adopting a ViBe algorithm, comprising:
the random property in time is randomly extracted from N background models and is set as an image PGWhen a new frame of image P is obtainedtIf the image P is normal, if the image P is normaltPixel P corresponding to x position in (1)t(x) Is judged as background, then PGIs updated;
spatially random selection of PG(x) Randomly extracts a pixel P from the eight neighborhoodsG(r) with Pt(x) By replacing PG(r)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089987.0A CN112200839A (en) | 2020-10-13 | 2020-10-13 | Infant protection socket based on image processing and protection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089987.0A CN112200839A (en) | 2020-10-13 | 2020-10-13 | Infant protection socket based on image processing and protection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112200839A true CN112200839A (en) | 2021-01-08 |
Family
ID=74010015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011089987.0A Pending CN112200839A (en) | 2020-10-13 | 2020-10-13 | Infant protection socket based on image processing and protection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200839A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0495149A1 (en) * | 1990-12-26 | 1992-07-22 | Alexander Dr. Schluttig | Safety socket with automatic cut-off of current supply to the socket contacts |
| CN107171284A (en) * | 2017-06-29 | 2017-09-15 | 合肥步瑞吉智能家居有限公司 | A kind of intelligent power off socket control system based on human bioequivalence |
| CN107976953A (en) * | 2017-11-21 | 2018-05-01 | 北京小米移动软件有限公司 | Control method, apparatus, socket and the readable storage medium storing program for executing of socket |
| CN108448343A (en) * | 2018-02-07 | 2018-08-24 | 薛依凡 | A kind of socket with power-off protection function |
| CN108876990A (en) * | 2018-05-31 | 2018-11-23 | 深圳市零度智控科技有限公司 | Intelligent door lock and its control method, device and readable storage medium storing program for executing |
| CN110673500A (en) * | 2019-09-26 | 2020-01-10 | 青岛海尔科技有限公司 | Power supply control method of socket and Internet of things operating system |
| WO2020062399A1 (en) * | 2018-09-28 | 2020-04-02 | 安徽省极索智能科技有限公司 | Smart socket control system for preventing electric shock of children |
-
2020
- 2020-10-13 CN CN202011089987.0A patent/CN112200839A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0495149A1 (en) * | 1990-12-26 | 1992-07-22 | Alexander Dr. Schluttig | Safety socket with automatic cut-off of current supply to the socket contacts |
| CN107171284A (en) * | 2017-06-29 | 2017-09-15 | 合肥步瑞吉智能家居有限公司 | A kind of intelligent power off socket control system based on human bioequivalence |
| CN107976953A (en) * | 2017-11-21 | 2018-05-01 | 北京小米移动软件有限公司 | Control method, apparatus, socket and the readable storage medium storing program for executing of socket |
| CN108448343A (en) * | 2018-02-07 | 2018-08-24 | 薛依凡 | A kind of socket with power-off protection function |
| CN108876990A (en) * | 2018-05-31 | 2018-11-23 | 深圳市零度智控科技有限公司 | Intelligent door lock and its control method, device and readable storage medium storing program for executing |
| WO2020062399A1 (en) * | 2018-09-28 | 2020-04-02 | 安徽省极索智能科技有限公司 | Smart socket control system for preventing electric shock of children |
| CN110673500A (en) * | 2019-09-26 | 2020-01-10 | 青岛海尔科技有限公司 | Power supply control method of socket and Internet of things operating system |
Non-Patent Citations (2)
| Title |
|---|
| 于为: "运动目标检测ViBe算法", 《博客园，HTTPS://WWW.CNBLOGS.COM/YWSOFTWARE/P/4434074.HTML》 * |
| 孙华魁: "《数字图像处理与识别技术研究》", 31 May 2019, 天津科学技术出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6999600B2 (en) | Video scene background maintenance using change detection and classification | |
| CN107346409B (en) | pedestrian re-identification method and device | |
| TWI686774B (en) | Human face live detection method and device | |
| Zhang et al. | Code4d: color-depth local spatio-temporal features for human activity recognition from rgb-d videos | |
| US20180046878A1 (en) | Method and apparatus for infrared thermal image contour extraction | |
| Geetha et al. | Facial expression recognition–A real time approach | |
| Huynh-Thu et al. | Skin-color extraction in images with complex background and varying illumination | |
| CN106056089B (en) | A kind of 3 d pose recognition methods and system | |
| KR20160088224A (en) | Method for recognizing an object and apparatus thereof | |
| KR102393298B1 (en) | Method and apparatus for iris recognition | |
| CN107239735A (en) | A kind of biopsy method and system based on video analysis | |
| EP1151607A1 (en) | Method and apparatus for detecting moving objects in video conferencing and other applications | |
| CN110443179B (en) | Off-post detection method and device and storage medium | |
| Pellegrini et al. | Human posture tracking and classification through stereo vision and 3d model matching | |
| CN110309709A (en) | Face identification method, device and computer readable storage medium | |
| Cheong et al. | A novel face detection algorithm using thermal imaging | |
| Lou et al. | An illumination invariant change detection algorithm | |
| US8817125B2 (en) | Gesture recognition using chroma-keying | |
| CN111080665B (en) | Image frame recognition method, device, equipment and computer storage medium | |
| CN110222647B (en) | Face in-vivo detection method based on convolutional neural network | |
| Loutas et al. | Probabilistic multiple face detection and tracking using entropy measures | |
| KR101769741B1 (en) | Method and apparatus for recognizing iris through pupil detection | |
| CN112507767A (en) | Face identification method and related computer system | |
| CN112200839A (en) | Infant protection socket based on image processing and protection method thereof | |
| CN111259757B (en) | Living body identification method, device and equipment based on image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210108 |