CN110779567A - Indoor and outdoor scene recognition method based on multi-module fusion - Google Patents
Indoor and outdoor scene recognition method based on multi-module fusion Download PDFInfo
- Publication number
- CN110779567A CN110779567A CN201911066345.6A CN201911066345A CN110779567A CN 110779567 A CN110779567 A CN 110779567A CN 201911066345 A CN201911066345 A CN 201911066345A CN 110779567 A CN110779567 A CN 110779567A
- Authority
- CN
- China
- Prior art keywords
- indoor
- module
- sequence
- calculating
- calculation formula
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Abstract
An indoor and outdoor scene recognition method based on multi-module fusion comprises the following steps: step 1, calculating indoor confidence of each detection module, and step 2, judging indoor and outdoor scenes according to the indoor confidence. The invention ensures the accuracy of indoor and outdoor scene identification and also ensures the strong universality. Firstly, calculating corresponding indoor confidence coefficient through information such as light intensity, temperature, humidity, geomagnetism and the like acquired by a sensor; then, calculating the indoor and outdoor ticket number through a function according to the indoor confidence coefficient calculated by each module; and finally, judging whether the current environment is indoor or outdoor according to the ticket number obtained indoors and outdoors.
Description
Technical Field
The invention relates to an indoor and outdoor scene recognition method.
Background
The wearable mobile environment monitoring system can provide information of the air quality of the surrounding environment for people in real time due to the portability of the wearable mobile environment monitoring system. However, the air quality of indoor environment is different from that of outdoor environment, such as indoor detection of formaldehyde and outdoor detection of PM 2.5. Therefore, it is a challenge how to accurately distinguish indoor and outdoor scenes.
Most of the indoor and outdoor scene recognition algorithms which are common at present are realized based on image recognition, environmental information characteristics and equipment pre-deployment. The algorithms can accurately distinguish indoor scenes from outdoor scenes according to the environment of characteristics, but when the environment is particularly complex, the accuracy of the algorithms is sharply reduced. The invention can weaken the influence of complex environment on indoor and outdoor scene discrimination, can accurately discriminate indoor and outdoor scenes, and has stronger universality.
Disclosure of Invention
The invention provides a multi-module fusion indoor and outdoor scene recognition method, which aims to overcome the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a multi-module fusion indoor and outdoor scene recognition method comprises the following steps:
step 1: calculating indoor confidence degrees of the light intensity module, the temperature module, the humidity module and the geomagnetic module;
step 2: and judging indoor and outdoor scenes according to the calculated indoor confidence of each module.
The step 1 specifically comprises the following steps:
1) and (4) light intensity module indoor confidence calculation. Calculating a corresponding time zone according to the longitude of the current area, wherein the difference between the longitudes of the time zones is 15 degrees, and the calculation formula is as follows:
where Z is the current time zone and l is the current longitude.
Calculating the local noon time according to the difference between the local longitude and the local time zone longitude, wherein the calculation formula is as follows:
N=12-(l/15-Z) (2-2)
wherein N is noon time.
Judging between two of the four solar terms, and calculating the solar incident angle β of the current date according to a certain weight, wherein the calculation formula is as follows:
where x is the current date, d
1And d
2For two solar terms, α and γ are the solar angles of incidence for the two solar terms, and day is a function of the number of days between which the difference between the two dates was calculated.
And D, calculating the daytime time D according to the following calculation formula:
where β is the angle of incidence of the sun and q is the dimension of the current location.
Dividing the daytime time equally by the midday time to obtain sunrise time R and sunset time S, wherein the calculation formula is as follows:
R=N-D/2 (2-5)
S=N+D/2 (2-6)
finally, calculating the indoor confidence of the light intensity according to the light intensity L and the light intensity threshold value T
C
LThe calculation formula is as follows:
wherein, T
12000-10 × H, H is the current humidity, and T2 is 200.
2) Temperature module indoor confidence calculation. According to the temperature sequence [ T
1,T
2,…,T
n]N is the length of the temperature sequence, and the average value A of the temperature sequence is calculated
TThe calculation formula is as follows:
according to the calculated temperature sequenceMean value A
TAnd a current temperature t, calculating the variance of the temperature sequence: the calculation formula is as follows:
wherein V
TRepresenting the variance of the temperature sequence.
Mean value A according to the temperature sequence
TVariance V of sum temperature sequence
TCalculating the indoor confidence C based on the temperature
TThe calculation formula is as follows:
where σ denotes a threshold value, σ
0Is set to 4, σ
1Set to 0.03.
3) Humidity module indoor confidence calculation. According to the humidity sequence [ H
1,H
2,…,H
p]P is the length of the humidity sequence, the average A of the humidity sequence is calculated
HThe calculation formula is as follows:
from the calculated average A of the humidity series
HAnd current humidity h, calculating the variance of the humidity sequence: the calculation formula is as follows:
wherein V
HRepresenting the variance of the humidity sequence.
Mean value A from humidity series
HVariance V of sum humidity sequence
HCalculating the indoor confidence C based on humidity
HThe calculation formula is as follows:
where σ represents a threshold value,σ
2Is set to 5, σ
3Is set to 1.
4) And calculating indoor confidence of the geomagnetic module. According to the sequence of geomagnetic intensity [ M ]
1,M
2,…,M
q]Q is the length of the geomagnetic intensity sequence, and a geomagnetic variance sequence [ V ] is calculated
1,V
2,…,V
m]And m is the length of the variance of the geomagnetic intensity, and the calculation formula is shown as (2-14).
Wherein V
uThe value of the u-th geomagnetic variance in the geomagnetic variance sequence is from 1 to m, k is the size of a sliding window for calculating the geomagnetic variance, and the value is
Is 20, A
MuThe calculation formula is shown as (2-15) for the average value of the geomagnetic intensity under the sliding window.
After calculating geomagnetic variance sequence [ V ]
1,V
2,…,V
m]Then, the maximum geomagnetic variance V in the sequence is calculated
maxThe calculation formula is shown as (2-16).
V
max=max([V
1,V
2,...,V
m]) (2-16)
Where max is a function that calculates the maximum value in the sequence of the geomagnetic variances.
After calculating the maximum variance V of the earth magnetism
maxThen, compare V
maxAnd V
tSize of (V)
tSet to 14. If V
maxGreater than V
tIf the current scene is judged to be indoor, otherwise, the current scene is judged to be outdoor, and the indoor confidence coefficient C based on the geomagnetism
MCan be calculated from the equations (2-17).
The step 2 specifically comprises the following steps:
1) obtaining indoor confidence C of temperature module
TIndoor confidence C of optical module
LIndoor confidence C of humidity module
HAnd indoor confidence C of geomagnetic module
MThen, voting is carried out according to the confidence coefficient of each module, and the number of votes which are judged to be indoor is calculated and counted
iAnd the outdoor ticket count
oThe calculation formulas are shown in (2-18) and (2-19).
count
i=class(C
L)+class(C
T)+class(C
H)+class(C
M) (2-18)
count
o=class(1-C
L)+class(1-C
T)+class(1-C
H)+class(1-C
M)
(2-19)
The class function is used for judging whether the confidence of the current module is greater than a threshold value, the threshold value is set to be 0.5, if the confidence of the current module is greater than the threshold value, the result is 1, otherwise, the result is 0, and the formula is shown as (2-20).
2) In calculating count
iAnd count
oAfter the value of (1), the count is compared
iAnd count
oThe size of (2). If count
iGreater than count
oJudging that the current scene is indoor; if count
iLess than count
oJudging that the current scene is outdoor; if count
iIs equal to count
oThen, calculating the indoor confidence C of indoor multi-module fusion
FThe calculation formula of (2) to (21) is shown.
Calculating the indoor confidence coefficient C of multi-module fusion
FAfter the value of (1), compare C
FAnd the size of threshold. If C is present
FIf the current scene is greater than threshold, judging that the current scene is indoor; if C is present
FIf the current scene is smaller than threshold, judging that the current scene is outdoor; if C is present
FIf the threshold is equal, the category of the current scene cannot be judged.
Preferably, n is set to 20; m is set to 5.
The general indoor and outdoor scene identification method identifies the indoor and outdoor scenes through image identification and environmental information characteristics, and the methods can accurately identify the indoor and outdoor scenes. However, when the environment is complicated, the accuracy of these methods is reduced, which causes difficulty in recognizing indoor and outdoor scenes.
The invention has the advantages that: the indoor and outdoor scene recognition accuracy is guaranteed, and meanwhile, the strong universality is also guaranteed. Firstly, calculating corresponding indoor confidence coefficient through information such as light intensity, temperature, humidity, geomagnetism and the like acquired by a sensor; then, calculating the indoor and outdoor ticket number through a function according to the indoor confidence coefficient calculated by each module; and finally, judging whether the current environment is indoor or outdoor according to the ticket number obtained indoors and outdoors.
Drawings
FIG. 1 is a general flow diagram of the present invention.
FIG. 2 is a block diagram of the detection module of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
An indoor and outdoor scene recognition method based on multi-module fusion comprises the following steps:
1. an indoor and outdoor scene recognition method based on multi-module fusion comprises the following steps:
step 1: calculate the indoor confidence of light intensity module, temperature module, humidity module and earth magnetism module, specifically include:
11) and (4) light intensity module indoor confidence calculation. Calculating a corresponding time zone according to the longitude of the current area, wherein the difference between the longitudes of the time zones is 15 degrees, and the calculation formula is as follows:
where Z is the current time zone and l is the current longitude.
Calculating the local noon time N according to the difference between the local longitude and the local time zone longitude, wherein the calculation formula is as follows:
N=12-(l/15-Z) (2-2)
judging between two of the four solar terms, and calculating the solar incident angle β of the current date according to a certain weight, wherein the calculation formula is as follows:
where x is the current date, d
1And d
2For two solar terms, α and γ are the solar angles of incidence for the two solar terms, and day is a function of the number of days between which the difference between the two dates was calculated.
And D, calculating the daytime time D according to the following calculation formula:
where β is the angle of incidence of the sun and q is the dimension of the current location.
Dividing the daytime time equally by the midday time to obtain sunrise time R and sunset time S, wherein the calculation formula is as follows:
R=N-D/2 (2-5)
S=N+D/2 (2-6)
finally, calculating the indoor confidence coefficient C of the light intensity according to the light intensity L and the light intensity threshold value T
LThe calculation formula is as follows:
wherein, T
12000-10 × H, H is the current humidity, and T2 is 200.
12) Temperature module indoor confidence calculation. According to the temperature sequence [ T
1,T
2,…,T
n]N is the length of the temperature sequence, and the average value A of the temperature sequence is calculated
TThe calculation formula is as follows:
from the calculated average A of the temperature series
TAnd a current temperature t, calculating the variance of the temperature sequence: the calculation formula is as follows:
wherein V
TRepresenting the variance of the temperature sequence.
Mean value A according to the temperature sequence
TVariance V of sum temperature sequence
TCalculating the indoor confidence C based on the temperature
TThe calculation formula is as follows:
where σ denotes a threshold value, σ
0Is set to 4, σ
1Set to 0.03.
13) Humidity module indoor confidence calculation. According to the humidity sequence [ H
1,H
2,…,H
p]P is the length of the humidity sequence, the average A of the humidity sequence is calculated
HThe calculation formula is as follows:
from the calculated average A of the humidity series
HAnd current humidity h, calculating the variance of the humidity sequence: the calculation formula is as follows:
wherein V
HRepresenting the variance of the humidity sequence.
Mean value A from humidity series
HVariance V of sum humidity sequence
HCalculating the indoor confidence C based on humidity
HThe calculation formula is as follows:
where σ denotes a threshold value, σ
2Is set to 5, σ
3Is set to 1.
14) And calculating indoor confidence of the geomagnetic module. According to the sequence of geomagnetic intensity [ M ]
1,M
2,…,M
q]Q is the length of the geomagnetic intensity sequence, and a geomagnetic variance sequence [ V ] is calculated
1,V
2,…,V
m]And m is the length of the variance of the geomagnetic intensity, and the calculation formula is shown as (2-14).
Wherein V
uThe value of the u-th geomagnetic variance in the geomagnetic variance sequence is from 1 to m, k is the size of a sliding window for calculating the geomagnetic variance, and the value is
Is 20, A
MuThe calculation formula is shown as (2-15) for the average value of the geomagnetic intensity under the sliding window.
After calculating geomagnetic variance sequence [ V ]
1,V
2,…,V
m]Then, the maximum geomagnetic variance V in the sequence is calculated
maxThe calculation formula is shown as (2-16).
V
max=max([V
1,V
2,...,V
m]) (2-16)
Where max is a function that calculates the maximum value in the sequence of the geomagnetic variances.
After calculating the maximum variance V of the earth magnetism
maxThen, compare V
maxAnd V
tSize of (V)
tSet to 14. If V
maxGreater than V
tIf the current scene is judged to be indoor, otherwise, the current scene is judged to be outdoor, and the indoor confidence coefficient C based on the geomagnetism
MCan be calculated from the equations (2-17).
Step 2: according to the calculated indoor confidence of each module, the indoor and outdoor scenes are judged, and the method specifically comprises the following steps:
21) obtaining indoor confidence C of temperature module
TIndoor confidence C of optical module
LIndoor confidence C of humidity module
HAnd indoor confidence C of geomagnetic module
MThen, voting is carried out according to the confidence coefficient of each module, and the number of votes which are judged to be indoor is calculated and counted
iAnd the outdoor ticket count
oThe calculation formulas are shown in (2-18) and (2-19).
count
i=class(C
L)+class(C
T)+class(C
H)+class(C
M) (2-18)
count
o=class(1-C
L)+class(1-C
T)+class(1-C
H)+class(1-C
M)
(2-19)
The class function is used for judging whether the confidence of the current module is greater than a threshold value, the threshold value is set to be 0.5, if the confidence of the current module is greater than the threshold value, the result is 1, otherwise, the result is 0, and the formula is shown as (2-20).
22) In calculating count
iAnd count
oAfter the value of (1), the count is compared
iAnd count
oThe size of (2). If count
iGreater than count
oJudging that the current scene is indoor; if count
iLess than count
oJudging that the current scene is outdoor; if count
iIs equal to count
oThen, calculating the indoor confidence C of indoor multi-module fusion
FThe calculation formula of (2) to (21) is shown.
Calculating the indoor confidence coefficient C of multi-module fusion
FAfter the value of (1), compare C
FAnd the size of threshold. If C is present
FIf the current scene is greater than threshold, judging that the current scene is indoor; if C is present
FIf the current scene is smaller than threshold, judging that the current scene is outdoor; if C is present
FIf the threshold is equal, the category of the current scene cannot be judged.
n is set to 20; m is set to 5.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (2)
1. An indoor and outdoor scene recognition method based on multi-module fusion comprises the following steps:
step 1: calculate the indoor confidence of light intensity module, temperature module, humidity module and earth magnetism module, specifically include:
11) and (4) light intensity module indoor confidence calculation. Calculating a corresponding time zone according to the longitude of the current area, wherein the difference between the longitudes of the time zones is 15 degrees, and the calculation formula is as follows:
where Z is the current time zone and l is the current longitude.
Calculating the local noon time N according to the difference between the local longitude and the local time zone longitude, wherein the calculation formula is as follows:
N=12-(l/15-Z) (2-2)
judging between two of the four solar terms, and calculating the solar incident angle β of the current date according to a certain weight, wherein the calculation formula is as follows:
where x is the current date, d
1And d
2For two solar terms, α and γ are the solar angles of incidence for the two solar terms, and day is a function of the number of days between which the difference between the two dates was calculated.
And D, calculating the daytime time D according to the following calculation formula:
where β is the angle of incidence of the sun and q is the dimension of the current location.
Dividing the daytime time equally by the midday time to obtain sunrise time R and sunset time S, wherein the calculation formula is as follows:
R=N-D/2 (2-5)
S=N+D/2 (2-6)
finally, calculating the indoor confidence coefficient C of the light intensity according to the light intensity L and the light intensity threshold value T
LThe calculation formula is as follows:
wherein, T
12000-10 × H, H is the current humidity, and T2 is 200.
12) Temperature module indoor confidence calculation. According to the temperature sequence [ T
1,T
2,…,T
n]N is the length of the temperature sequence, and the average value A of the temperature sequence is calculated
TThe calculation formula is as follows:
from the calculated average A of the temperature series
TAnd a current temperature t, calculating the variance of the temperature sequence: the calculation formula is as follows:
wherein V
TRepresenting the variance of the temperature sequence.
Mean value A according to the temperature sequence
TVariance V of sum temperature sequence
TCalculating the indoor confidence C based on the temperature
TThe calculation formula is as follows:
where σ denotes a threshold value, σ
0Is set to 4, σ
1Set to 0.03.
13) Humidity module indoor confidence calculation. According to the humidity sequence [ H
1,H
2,…,H
p]P is the length of the humidity sequence, the average A of the humidity sequence is calculated
HThe calculation formula is as follows:
from the calculated average A of the humidity series
HAnd current humidity h, calculating the variance of the humidity sequence: the calculation formula is as follows:
wherein V
HRepresenting the variance of the humidity sequence.
Mean value A from humidity series
HVariance V of sum humidity sequence
HCalculating the basis humidityIndoor confidence coefficient C of
HThe calculation formula is as follows:
where σ denotes a threshold value, σ
2Is set to 5, σ
3Is set to 1.
14) And calculating indoor confidence of the geomagnetic module. According to the sequence of geomagnetic intensity [ M ]
1,M
2,…,M
q]Q is the length of the geomagnetic intensity sequence, and a geomagnetic variance sequence [ V ] is calculated
1,V
2,…,V
m]And m is the length of the variance of the geomagnetic intensity, and the calculation formula is shown as (2-14).
Wherein V
uThe value of the u-th geomagnetic variance in the geomagnetic variance sequence is from 1 to m, k is the size of a sliding window for calculating the geomagnetic variance, and the value is
Namely the number of 20, the number of the channels,
the calculation formula is shown as (2-15) for the average value of the geomagnetic intensity under the sliding window.
After calculating geomagnetic variance sequence [ V ]
1,V
2,…,V
m]Then, the maximum geomagnetic variance V in the sequence is calculated
maxThe calculation formula is shown as (2-16).
V
max=max([V
1,V
2,...,V
m]) (2-16)
Where max is a function that calculates the maximum value in the sequence of the geomagnetic variances.
After calculating the maximum variance V of the earth magnetism
maxThen, compare V
maxAnd V
tSize of (V)
tSet to 14. If V
maxGreater than V
tIf the current scene is judged to be indoor, otherwise, the current scene is judged to be outdoor, and the indoor confidence coefficient C based on the geomagnetism
MCan be calculated from the equations (2-17).
Step 2: according to the calculated indoor confidence of each module, the indoor and outdoor scenes are judged, and the method specifically comprises the following steps:
21) obtaining indoor confidence C of temperature module
TIndoor confidence C of optical module
LIndoor confidence C of humidity module
HAnd indoor confidence C of geomagnetic module
MThen, voting is carried out according to the confidence coefficient of each module, and the number of votes which are judged to be indoor is calculated and counted
iAnd the outdoor ticket count
oThe calculation formulas are shown in (2-18) and (2-19).
count
i=class(C
L)+class(C
T)+class(C
H)+class(C
M) (2-18)
count
o=class(1-C
L)+class(1-C
T)+class(1-C
H)+class(1-C
M) (2-19)
The class function is used for judging whether the confidence of the current module is greater than a threshold value, the threshold value is set to be 0.5, if the confidence of the current module is greater than the threshold value, the result is 1, otherwise, the result is 0, and the formula is shown as (2-20).
22) In calculating count
iAnd count
oAfter the value of (1), the count is compared
iAnd count
oThe size of (2). If count
iGreater than count
oJudging that the current scene is indoor; if count
iLess than count
oJudging that the current scene is outdoor; if count
iIs equal to count
oThen, calculating the indoor confidence C of indoor multi-module fusion
FThe calculation formula of (2) to (21) is shown.
Calculating the indoor confidence coefficient C of multi-module fusion
FAfter the value of (1), compare C
FAnd the size of threshold. If C is present
FIf the current scene is greater than threshold, judging that the current scene is indoor; if C is present
FIf the current scene is smaller than threshold, judging that the current scene is outdoor; if C is present
FIf the threshold is equal, the category of the current scene cannot be judged.
2. The indoor and outdoor scene recognition method based on multi-module fusion as claimed in claim 1, characterized in that: n is set to 20; m is set to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911066345.6A CN110779567B (en) | 2019-11-04 | 2019-11-04 | Indoor and outdoor scene recognition method based on multi-module fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911066345.6A CN110779567B (en) | 2019-11-04 | 2019-11-04 | Indoor and outdoor scene recognition method based on multi-module fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110779567A true CN110779567A (en) | 2020-02-11 |
CN110779567B CN110779567B (en) | 2021-07-27 |
Family
ID=69388876
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911066345.6A Active CN110779567B (en) | 2019-11-04 | 2019-11-04 | Indoor and outdoor scene recognition method based on multi-module fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110779567B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114200988A (en) * | 2021-12-06 | 2022-03-18 | 深圳市时誉高精科技有限公司 | Indoor thermostat management system based on big data |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050006763A (en) * | 2003-07-10 | 2005-01-17 | 엘지전자 주식회사 | An image display device having function for displaying environmental information and system thereof |
CN102859990A (en) * | 2010-04-29 | 2013-01-02 | 伊斯曼柯达公司 | Indoor/outdoor scene detection using GPS |
CN104457751A (en) * | 2014-11-19 | 2015-03-25 | 中国科学院计算技术研究所 | Method and system for recognizing indoor and outdoor scenes |
CN105025440A (en) * | 2015-07-09 | 2015-11-04 | 深圳天珑无线科技有限公司 | Indoor/outdoor scene detection method and device |
CN107076561A (en) * | 2014-09-16 | 2017-08-18 | 微软技术许可有限责任公司 | Indoor and outdoor transition is considered during position is determined |
CN107655564A (en) * | 2017-05-11 | 2018-02-02 | 南京邮电大学 | A kind of indoor and outdoor surroundingses detection method of the multiple technologies fusion based on intelligent terminal |
CN108268821A (en) * | 2016-12-30 | 2018-07-10 | 中国移动通信集团黑龙江有限公司 | A kind of indoor and outdoor scene recognition method and device |
CN109871641A (en) * | 2019-03-07 | 2019-06-11 | 浙江工业大学 | A method of the indoor and outdoor scene Recognition based on multidimensional heat transfer agent time series |
CN110220550A (en) * | 2018-03-02 | 2019-09-10 | 罗伯特·博世有限公司 | Method and apparatus, control unit and portable equipment for indoor/outdoor detection |
-
2019
- 2019-11-04 CN CN201911066345.6A patent/CN110779567B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050006763A (en) * | 2003-07-10 | 2005-01-17 | 엘지전자 주식회사 | An image display device having function for displaying environmental information and system thereof |
CN102859990A (en) * | 2010-04-29 | 2013-01-02 | 伊斯曼柯达公司 | Indoor/outdoor scene detection using GPS |
CN107076561A (en) * | 2014-09-16 | 2017-08-18 | 微软技术许可有限责任公司 | Indoor and outdoor transition is considered during position is determined |
CN104457751A (en) * | 2014-11-19 | 2015-03-25 | 中国科学院计算技术研究所 | Method and system for recognizing indoor and outdoor scenes |
CN104457751B (en) * | 2014-11-19 | 2017-10-10 | 中国科学院计算技术研究所 | Indoor and outdoor scene recognition method and system |
CN105025440A (en) * | 2015-07-09 | 2015-11-04 | 深圳天珑无线科技有限公司 | Indoor/outdoor scene detection method and device |
CN108268821A (en) * | 2016-12-30 | 2018-07-10 | 中国移动通信集团黑龙江有限公司 | A kind of indoor and outdoor scene recognition method and device |
CN107655564A (en) * | 2017-05-11 | 2018-02-02 | 南京邮电大学 | A kind of indoor and outdoor surroundingses detection method of the multiple technologies fusion based on intelligent terminal |
CN110220550A (en) * | 2018-03-02 | 2019-09-10 | 罗伯特·博世有限公司 | Method and apparatus, control unit and portable equipment for indoor/outdoor detection |
CN109871641A (en) * | 2019-03-07 | 2019-06-11 | 浙江工业大学 | A method of the indoor and outdoor scene Recognition based on multidimensional heat transfer agent time series |
Non-Patent Citations (5)
Title |
---|
S.AUST等: "Seamless Indoor/Outdoor Location Cognition with Confidence in Wireless Systems", 《4TH IEEE WORKSHOP ON USER MOBILITY AND VEHICULAR NETWORKS》 * |
ZHANG YANG等: "A pervasive indoor and outdoor scenario identification algorithm based on the sensing data and human activity", 《IEEE UPINLBS 2016》 * |
张扬: "面向智能终端的高性能室内外场景检测技术研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
苏帅: "基于多模态融合的高精度室内外场景识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
蒋超: "基于用户行为模式的室内外场景识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114200988A (en) * | 2021-12-06 | 2022-03-18 | 深圳市时誉高精科技有限公司 | Indoor thermostat management system based on big data |
CN114200988B (en) * | 2021-12-06 | 2023-01-10 | 深圳市时誉高精科技有限公司 | Indoor thermostat management system based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN110779567B (en) | 2021-07-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10565955B2 (en) | Display status adjustment method, display status adjustment device and display device | |
CN104457751B (en) | Indoor and outdoor scene recognition method and system | |
CN108921068B (en) | Automobile appearance automatic damage assessment method and system based on deep neural network | |
CN107131883B (en) | Full-automatic mobile terminal indoor positioning system based on vision | |
CN110110642A (en) | A kind of pedestrian's recognition methods again based on multichannel attention feature | |
CN111461053A (en) | System for identifying multiple growth period wheat lodging regions based on transfer learning | |
CN112560547A (en) | Abnormal behavior judgment method and device, terminal and readable storage medium | |
CN104394588B (en) | Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling | |
CN108960145A (en) | Facial image detection method, device, storage medium and electronic equipment | |
CN107655564A (en) | A kind of indoor and outdoor surroundingses detection method of the multiple technologies fusion based on intelligent terminal | |
CN107133685B (en) | Method and system for predicting power generation capacity of photovoltaic power generation system | |
CN110779567B (en) | Indoor and outdoor scene recognition method based on multi-module fusion | |
US20220148292A1 (en) | Method for glass detection in real scenes | |
US20190114333A1 (en) | System and method for species and object recognition | |
US20200196268A1 (en) | System and method for positioning a gateway of an architecture | |
CN109143408A (en) | Combine short-term precipitation forecasting procedure in dynamic area based on MLP | |
CN112784740A (en) | Gait data acquisition and labeling method and application | |
CN112183287A (en) | People counting method of mobile robot under complex background | |
CN108985131A (en) | A kind of target identification method and image processing equipment | |
CN109982239A (en) | Store floor positioning system and method based on machine vision | |
CN109815773A (en) | A kind of low slow small aircraft detection method of view-based access control model | |
US20040013300A1 (en) | Algorithm selector | |
CN114674317A (en) | Self-correcting dead reckoning system and method based on activity recognition and fusion filtering | |
CN111860331A (en) | Unmanned aerial vehicle is at face identification system in unknown territory of security protection | |
CN112784703A (en) | Multispectral-based personnel action track determination method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |