CN105760816A - Method of intelligently recognizing human body sleep gesture under strong wind cooling - Google Patents
Method of intelligently recognizing human body sleep gesture under strong wind cooling Download PDFInfo
- Publication number
- CN105760816A CN105760816A CN201610055813.XA CN201610055813A CN105760816A CN 105760816 A CN105760816 A CN 105760816A CN 201610055813 A CN201610055813 A CN 201610055813A CN 105760816 A CN105760816 A CN 105760816A
- Authority
- CN
- China
- Prior art keywords
- human body
- data
- temperature
- high wind
- sleeping position
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001816 cooling Methods 0.000 title abstract 4
- 238000004378 air conditioning Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 21
- 238000005057 refrigeration Methods 0.000 claims description 10
- 230000036760 body temperature Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000036544 posture Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
Abstract
The invention relates to the human body recognition technology and aims at solving the problem that missed recognition on human bodies is likely to happen when the human bodies are in sleep gestures under strong wind cooling of an air conditioner in the prior art. The invention provides a method of intelligently recognizing a human body sleep gesture under strong wind cooling. The method comprises the following steps: 1, when the air conditioner operates under strong wind cooling, an infrared sensor rotates to carry out step-by-step scanning and data acquisition; 2, the acquired data are arrayed into a temperature image according to a certain law, and the variance of the temperature image is solved; 3, median filter is used to perform analysis and median filter processing on data of interpolation processing; 4, the variance of the temperature image is combined, the data after filter processing are compared and processed, and temperature and quantity information of the human bodies in sleep gestures are acquired; and 5, through a relation between the temperature and the distance, the distance between the human body and the air conditioner is obtained. The method of the invention is applicable to the air conditioner.
Description
Technical field
The present invention relates to human body recognition technology, accurately know method for distinguishing particularly to human body in a kind of air conditioning applications.
Background technology
The issue of Changhong CHiQ air-conditioning, has overturned tradition, and it is based on unique body state cognition technology, changed to software definition air-conditioning by hardware definition air-conditioning on the one hand, realize working in coordination with between people and the interaction of air-conditioning, equipment, while ensureing human comfort, energy-saving and cost-reducing;On the other hand from user's request angle, meet user's request by plurality of application scenes pattern rather than pure function.Therefore, the traditional air conditioner theory of " hardware+function " overturned by Changhong CHiQ air-conditioning, has started the development new direction of " software+application scenarios pattern ".
Changhong CHiQ air-conditioning is according to the man-machine distance of perception identification, crowd's quantity, position etc., for zones of different, automatically adjusts the parameters such as air-out mode, wind speed, wind direction, dynamically adjusts the comfort level of each subregion.More marvellous is, people can set VIP people's mode of priority for ad-hoc location within the scope of air-conditioning wind-force angle of radiation, when user is when preferential comfort zone, CHiQ can carry out temperature, humidity, wind speed and direction adjustment targetedly, and old friend's body state Intelligent Identify is the function of Changhong CHiQ air-conditioning core the most.
For reducing cost, Changhong CHiQ air-conditioning adopts the low resolution non-brake method mid-infrared sensor of 4*16 to replace the infrared camera of high score ratio high cost, and realizes human body information identification under certain algorithm.Usually, human body presents three kinds of postures before air-conditioning, namely stance, sitting posture, sleeping position, although CHiQ air-conditioning room temperature refrigeration and high wind refrigeration under be easy to be identified to stance, sitting posture and sleeping position, but when high wind freezes, sleeping position is just very easy to the situation that leakage identifies occur.
Summary of the invention
The invention aims to solve in prior art, when air-conditioning high wind freezes, the problem that number leakage is known easily occurs when human body is in sleeping position.
For reaching above-mentioned purpose, the present invention provides the method for the lower Intelligent Recognition human body sleeping position of a kind of high wind refrigeration, it is characterised in that comprise the steps:
Step one, when air-conditioning high wind refrigerating operaton, infrared sensor rotate carry out progressively scanner uni data acquisition;
Step 2, the data collected are arranged in temperature pattern by according to certain rule, and obtain the variance of temperature pattern;
The data of interpolation processing are analyzed for step 3, utilization medium filtering and medium filtering processes;
Data after Filtering Processing are carried out contrast process by step 4, variance in conjunction with described temperature pattern, obtain human body temperature under sleeping position and quantity information;
Step 5, relation by temperature and distance obtain the distance between people and air-conditioning.
Specifically, in step one, the low resolution non-brake method mid-infrared sensor adopting resolution to be 4*16 carries out progressively scanner uni data acquisition.
Specifically, described infrared sensor carries out progressively scanning and data acquisition by 1 ° of-1 ° of-1 ° of-13 ° of rotation.
Specifically, to carry out the concrete grammar of medium filtering process as follows for step 3:
Pixel in plate being ranked up according to the size of pixel value, what generate monotone increasing is one-dimensional data sequence, then exports one-dimensional medium filtering:
G (x)=med{f (x-k), (k ∈ W) }
Wherein, f (x), g (x) respectively original image and image after processing, W is one-dimensional template, its in length and breadth the value respectively excursion on direction be 1*7 and 1*21 region.
The invention has the beneficial effects as follows: original image is carried out variance and middle finger Filtering Processing, utilize the difference extraction human body information of the image after asking variance and medium filtering and original image, even if under high wind freezes, ensure that human body stance and sitting posture information obtain the information of human body sleeping position when can recognize that, eliminate situation about Lou identifying, improve the human body information discrimination of air-conditioning.
Detailed description of the invention
Hereinafter technical scheme is described in further detail.
The present invention is directed in prior art, when air-conditioning high wind freezes, the problem that number leakage is known easily occurs when human body is in sleeping position, it is provided that the method for the lower Intelligent Recognition human body sleeping position of a kind of high wind refrigeration, comprise the steps:
Step one, when air-conditioning high wind refrigerating operaton, infrared sensor rotate carry out progressively scanner uni data acquisition;
Step 2, the data collected are arranged in temperature pattern by according to certain rule, and obtain the variance of former temperature pattern;
The data of interpolation processing are analyzed for step 3, utilization medium filtering and medium filtering processes;
Data after Filtering Processing are carried out contrast process by step 4, variance in conjunction with described image, obtain human body temperature under sleeping position and quantity information;
Step 5, relation by temperature and distance obtain the distance between people and air-conditioning.
Medium filtering is based on a kind of nonlinear signal processing technology that can effectively suppress noise that sequencing statistical is theoretical, the ultimate principle of medium filtering is that the Mesophyticum of each point value in a neighborhood of this point of the value of any in digital picture or Serial No. is replaced, allow the actual value that the pixel value of surrounding is close, thus eliminating isolated noise spot.Because the data in the present invention are relatively fewer in the vertical, it is contemplated that the DeGrain of process, therefore only it is filtered data transversely processing.For accelerating arithmetic speed, present invention employs a kind of one-dimensional sleiding form being continually changing, pixel in plate be ranked up according to the size of pixel value, what generate monotone increasing is one-dimensional data sequence, then exports one-dimensional medium filtering:
G (x)=med{f (x-k), (k ∈ W) }
Wherein, f (x), g (x) respectively original image and image after processing, W is one-dimensional template, its in length and breadth the value respectively excursion on direction be 1*7 and 1*21 region.
In order to eliminate the situation that Conventional median filtering method occurs that in high wind refrigeration situation leakage identifies, before underway value filtering, present invention employs the way that original image is asked variance, contrast original image and variance image thereof, being not difficult to find out there is the place of people in original image, variance yields shows relatively large, utilize this characteristic, then carry out contrast with the image of medium filtering and effectively can must fall the information of human body.
Embodiment
Under high wind freezes, respectively to when there being a people to fall asleep in the radiation scope of air-conditioning, a people falls asleep when stand with a people, when a people is sleeping, a people is seated and a people stands, after gathering data and processing, it is possible to the accurately errorless characteristic information providing human body.Through Multiple-Scan, identify checking, identify (identifying less than people) and misrecognized (being people by object or other thermal source identification) without leakage.
Claims (4)
1. the method for the lower Intelligent Recognition human body sleeping position of high wind refrigeration, it is characterised in that comprise the steps:
Step one, when air-conditioning high wind refrigerating operaton, infrared sensor rotate carry out progressively scanner uni data acquisition;
Step 2, the data collected are arranged in temperature pattern by according to certain rule, and obtain the variance of temperature pattern;
The data of interpolation processing are analyzed for step 3, utilization medium filtering and medium filtering processes;
Data after Filtering Processing are carried out contrast process by step 4, variance in conjunction with described temperature pattern, obtain human body temperature under sleeping position and quantity information;
Step 5, relation by temperature and distance obtain the distance between people and air-conditioning.
2. the method for the lower Intelligent Recognition human body sleeping position of high wind refrigeration as claimed in claim 1, it is characterised in that in step one, the low resolution non-brake method mid-infrared sensor adopting resolution to be 4*16 carries out progressively scanner uni data acquisition.
3. the method for the lower Intelligent Recognition human body sleeping position of high wind refrigeration as claimed in claim 2, it is characterised in that described infrared sensor carries out progressively scanning and data acquisition by 1 ° of-1 ° of-1 ° of-13 ° of rotation.
4. the method for the lower Intelligent Recognition human body sleeping position of high wind refrigeration as described in claim 1 or 2 or 3, it is characterised in that the concrete grammar that step 3 carries out medium filtering process is as follows:
Pixel in plate being ranked up according to the size of pixel value, what generate monotone increasing is one-dimensional data sequence, then exports one-dimensional medium filtering:
G (x)=med{f (x-k), (k ∈ W) }
Wherein, f (x), g (x) respectively original image and image after processing, W is one-dimensional template, its in length and breadth the value respectively excursion on direction be 1*7 and 1*21 region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610055813.XA CN105760816A (en) | 2016-01-27 | 2016-01-27 | Method of intelligently recognizing human body sleep gesture under strong wind cooling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610055813.XA CN105760816A (en) | 2016-01-27 | 2016-01-27 | Method of intelligently recognizing human body sleep gesture under strong wind cooling |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105760816A true CN105760816A (en) | 2016-07-13 |
Family
ID=56342622
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610055813.XA Pending CN105760816A (en) | 2016-01-27 | 2016-01-27 | Method of intelligently recognizing human body sleep gesture under strong wind cooling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105760816A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108363977A (en) * | 2018-02-11 | 2018-08-03 | 四川虹美智能科技有限公司 | A kind of human prone position state identification method and device |
CN111189102A (en) * | 2020-01-03 | 2020-05-22 | 王艳苓 | Heating pipeline opening degree adjusting platform and method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1821906A (en) * | 2006-03-08 | 2006-08-23 | 刘雪梅 | Industive controller for human comfortableness and its use in air conditioner |
CN101051223A (en) * | 2007-04-29 | 2007-10-10 | 浙江工业大学 | Air conditioner energy saving controller based on omnibearing computer vision |
CN101793562A (en) * | 2010-01-29 | 2010-08-04 | 中山大学 | Face detection and tracking algorithm of infrared thermal image sequence |
CN101957042A (en) * | 2010-09-30 | 2011-01-26 | 宇龙计算机通信科技(深圳)有限公司 | Control device, mobile terminal and method for controlling air conditioner output temperature |
KR20110020065A (en) * | 2009-08-21 | 2011-03-02 | 삼성전기주식회사 | Air-condition controlling apparatus and method using infrared camera |
CN102519088A (en) * | 2008-09-10 | 2012-06-27 | 三菱电机株式会社 | An air conditioner |
-
2016
- 2016-01-27 CN CN201610055813.XA patent/CN105760816A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1821906A (en) * | 2006-03-08 | 2006-08-23 | 刘雪梅 | Industive controller for human comfortableness and its use in air conditioner |
CN101051223A (en) * | 2007-04-29 | 2007-10-10 | 浙江工业大学 | Air conditioner energy saving controller based on omnibearing computer vision |
CN102519088A (en) * | 2008-09-10 | 2012-06-27 | 三菱电机株式会社 | An air conditioner |
KR20110020065A (en) * | 2009-08-21 | 2011-03-02 | 삼성전기주식회사 | Air-condition controlling apparatus and method using infrared camera |
CN101793562A (en) * | 2010-01-29 | 2010-08-04 | 中山大学 | Face detection and tracking algorithm of infrared thermal image sequence |
CN101957042A (en) * | 2010-09-30 | 2011-01-26 | 宇龙计算机通信科技(深圳)有限公司 | Control device, mobile terminal and method for controlling air conditioner output temperature |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108363977A (en) * | 2018-02-11 | 2018-08-03 | 四川虹美智能科技有限公司 | A kind of human prone position state identification method and device |
CN108363977B (en) * | 2018-02-11 | 2020-08-04 | 四川虹美智能科技有限公司 | Human body prone position state identification method and device |
CN111189102A (en) * | 2020-01-03 | 2020-05-22 | 王艳苓 | Heating pipeline opening degree adjusting platform and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6074143B2 (en) | Air conditioner | |
US9124812B2 (en) | Object image capture apparatus and method | |
CN105571066B (en) | Air-conditioning control method and device | |
JP2019067778A (en) | Image sensor | |
CN105141922B (en) | Security-protecting and monitoring method based on air-conditioning and air conditioner | |
CN103986871B (en) | Method and system for intelligent zoom video monitoring | |
CN100357670C (en) | Intelligent air supply air-conditioner and intelligent air supply method | |
CN105423502A (en) | Method and device for controlling air-conditioning air supply | |
CN109654676B (en) | Adjusting method, device and system of air supply device, computer equipment and storage medium | |
WO2019119470A1 (en) | Air conditioner control method and system, and air conditioner | |
CN105546748B (en) | Air-conditioning control method and device | |
JP2011137589A (en) | Air conditioner and control device of the same | |
JP6216596B2 (en) | Image processing apparatus, imaging apparatus, air conditioning system, and program | |
JP2016085739A (en) | Modification of at least one parameter used by video processing | |
CN105022999A (en) | Man code company real-time acquisition system | |
WO2022242143A1 (en) | Air conditioner control method and apparatus, and air conditioner | |
CN105760816A (en) | Method of intelligently recognizing human body sleep gesture under strong wind cooling | |
CN104266312B (en) | Air conditioner and control method and system thereof | |
JPWO2017029762A1 (en) | Air conditioner | |
JP2008051463A (en) | Automatic air-conditioning control system | |
WO2022262460A1 (en) | Wide-angle air-out head for use in air conditioner and control method therefor | |
CN112907617A (en) | Video processing method and device | |
CN105546746B (en) | Air-conditioning control method and device | |
CN105651397A (en) | Method for accurately recognizing human body temperature | |
US9596410B2 (en) | Vision systems and methods for analysing images taken by image sensors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20160713 |