CN109448397A - A kind of group's mist monitoring method based on big data - Google Patents
A kind of group's mist monitoring method based on big data Download PDFInfo
- Publication number
- CN109448397A CN109448397A CN201811380273.8A CN201811380273A CN109448397A CN 109448397 A CN109448397 A CN 109448397A CN 201811380273 A CN201811380273 A CN 201811380273A CN 109448397 A CN109448397 A CN 109448397A
- Authority
- CN
- China
- Prior art keywords
- mist
- image
- group
- background
- camera
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The present invention discloses a kind of group's mist monitoring method based on big data, massive video data (data in multiple camera continuous time periods) is handled and analyzed using big data technology, establish group's mist monitoring method based on time series, the changing rule of backdrop pels when the method takes full advantage of large nuber of images information and rolls into a ball mist burst, prepare monitoring result more, also more for engineering practicability.
Description
Technical field
Group's mist monitoring method based on big data that the present invention relates to a kind of, belongs to Traffic monitoring technical field.
Background technique
Group's mist is referred to as " killer " of traffic safety, especially on a highway, it is easier to cause serious accident.
On November 15th, 2017, the new high speed Ying upper section of Chu knocked into the back because mist causes more vehicles, caused 18 people dead altogether, 21 people are injured.2017
18 traffic accidents occur for Yongdeng on November 8 high speed Zhoukou City Taikan Duan Yintuan mist.What Ministry of Public Security's traffic control board web in 2016 was announced
Data are shown: at average annual generation 3 times or more the express highway sections 2567 of group's mist, wherein the road of generation 10 times or more group's mists every year
At section 920,120 times or more occur every year and rolls into a ball mist for Shen Hai certain section of high speed and Beijing-Hongkong Australia certain section of high speed.
The monitoring of group's mist and early warning system are broadly divided into two classes both at home and abroad: a kind of monitoring data based on visibility meter, separately
One kind is based on image data, at present based on the first kind.The U.S. state Jue great Shuo is all directed to highway mist and establishes monitoring system
System, these systems are substantially based on the data of visibility meter, if California is in 13 miles of sections of the highway of California the 99th
A set of mist early warning system has inside been disposed, has set a changeable-message sign and a visibility meter every 800 meter amperes along highway；Field
The mist early warning system of Nahsi state construction, there is 9 forward scatter-type visibility meters, 14 microwave thunders in 5 kilometers of mist detection zone
Up to wagon detector.Domestic various regions also begin trying to establish the weather monitoring system of highway, and Anhui Province is in highway cloth
If 196 weather monitoring stations, each weather station is equipped with visibility meter, and 15 kilometers are spacing.Meteorological optical range equipment monitoring distance
It is excessive, most intensive Shanghai-Nanjing freeway is laid at present also in 10km, and roll into a ball that mist occurrence scope is small, and visibility meter data are unable to satisfy group
The detection of mist.The another kind of group's mist established based on image data monitors system, and the core technology of this kind of system is based on image
The quick mist detection algorithm of processing, the current mist detection algorithm based on image (video) are and more with based on based on single image
Based on the contrast for extracting image.Chen Zhong is just equal to have studied a kind of video visibility inspection by the video camera on highway
Survey method, and test obtains good effect on a highway；Li Bo etc. is realized using the contrast of total four neighborhood of image
The visibility measurement of unlimited handmarking；The deep and clear equal interest domain ROI by extracting road surface is opened, extracts and reflects road surface brightness change
Obtain visibility monitoring method；The visibility for foggy weather that road small echo etc. has studied a kind of color of image space characteristics is examined
Survey method；Zhu Yun et al. has applied for that a kind of patent of the applications such as " road weather detection system based on video ", Feng Haixia is " a kind of
Expressway fog real-time monitoring system and method based on generalized information system ", " the group's mist based on digital camera for the applications such as sprouting
The patents such as real-time early warning system and method " be also based on single image data processing,
This kind of current many places of monitoring system do not carry out the massive video data that camera provides abundant in conceptual phase
Using what is run in production is also more rare.
Summary of the invention
Group's mist monitoring method based on big data that the technical problem to be solved in the present invention is to provide a kind of, by monitoring section
The case where video image monitoring group mist in interior multiple camera continuous time periods happens suddenly, has more engineering practicability.
In order to solve the technical problem, the technical solution adopted by the present invention is that: a kind of group's mist monitoring based on big data
Method, comprising the following steps: S01), obtain monitoring each camera in section video data, video data is pre-processed；
S02), the image data provided each camera establishes a dynamic time series, the image of graph shape at any time
At dynamic time-series image；S03), the gauss hybrid models monitored using moving target reject moving target, extract figure
The background information of picture establishes the time series models of background picture；S04), the variation of background picture is advised when the mist burst of analysis group
Rule establishes the mist monitoring model based on backdrop pels time series, and using mist monitoring model to the real-time number of thecamera head
According to being judged；S05), a camera interpretation is the group of starting immediately mist interpretation, if N1 adjacent cameras after having mist
All monitor mist, interpretation is mist, starts mist early warning；Such as there is the case where N2 or more adjacent camera monitors non-mist, sentences
Break as a mist, the flow direction of analysis prediction group mist, the mist early warning of starting group；N1, N2 are positive integer, and N1 > N2.
Further, S31), by the first frame f of time-series image1As initial background, come using K Gauss model
Characterize each pixel f in this image1The feature of (x, y), the value range of K is 3~5, by the distribution of image grey level histogram
Determine the mean μ of each Gauss modeljAnd standard deviation sigmaj, j ∈ [1, K], each pixel gray value can be expressed as K Gauss point
The superposition of cloth function, i.e.,Wherein, η (μj, σj) it is j-th of Gauss
Distribution, ω j is its weight；S32), from the second frame image fi(x, y), i > 1 start, and estimate whether each pixel belongs to background,
That is the no establishment of judgment formula 2: | fi(x,y)-μj|≤2.5σj(formula 2), if formula 2 is set up, pixel fi(x, y) is
Otherwise background dot is foreground point, new Gauss model is generated according to foreground point；S33), updated by formula 3 each in present image
Model Weight,Wherein α is learning rate, if working as
Preceding point is background, then MK,i=1, otherwise MK,i=0,For update before Model Weight,For updated model
Weight；S34), the Gauss model mean value and standard deviation of foreground point remain unchanged, and the Gauss model mean value and standard deviation of background dot are pressed
Present image is updated；S35), all Gauss models are ranked up, the model that weight is big, standard deviation is small comes front, row
Model of the sequence after K is cast out, to obtain updated background image；S36), step S32-S35 is repeated, is obtained each
The Background of frame image establishes the Dynamic Time Series image of background image,；S37), based on the time series chart of background image
Background picture is divided into 4 regions, establishes the time change change curve of 4 region contrasts by picture.
Further, the contrast that current image is comprehensively considered based on the mist monitoring model of backdrop pels time series is established
X1, the fuzziness X2 of current image, the contrast X3 of upper frame image in time series, in time series upper frame image fuzziness
X4, when group's mist burst, sharply X1 is reduced the contrast of pixel value in background image, and current image full figure has 75% area above to be
Fuzzy region, X3 and the X1 fall for having 3 areas in 4 subregions are more than 300%, there is upper frame image full figure in time series
25% following region is fuzzy region.
Further, the pretreatment carried out to video data includes: that image data is quickly examined and verified, and is deleted
Duplicate message corrects existing mistake, and the picture format of all cameras is unified.
Further, the camera in section is monitored according to specific direction and apart from arrangement, and mist is monitored according to camera
Flow direction and the speed of mist are rolled into a ball in sequencing forecast analysis.
Further, a camera interpretation is the group of starting immediately mist interpretation 5 cameras adjacent to front and back after having mist
It carries out comprehensive descision and starts mist early warning if 4 or more adjacent cameras are judged to having mist；It is such as adjacent in the presence of 2 or more
Camera the case where monitoring non-mist, be judged as a mist.
Beneficial effects of the present invention: the present invention is using big data technology to massive video data (multiple camera consecutive hourss
Between data in section) handled and analyzed, establish group's mist monitoring method based on time series, the method takes full advantage of sea
The changing rule of backdrop pels, prepares monitoring result more, also more for Practical when measuring image information and rolling into a ball mist burst
Property.
Detailed description of the invention
Fig. 1 is the flow chart of 1 the method for embodiment.
Specific embodiment
The present invention is further limited in the following with reference to the drawings and specific embodiments.
Embodiment 1
The present embodiment discloses a kind of group's mist monitoring method based on big data, as shown in Figure 1, comprising the following steps:
S01), the video data for obtaining the monitoring each camera in section, pre-processes video data；
In the present embodiment, the pretreatment carried out to video data includes: that image data is quickly examined and verified, and is deleted
Except duplicate message, image mistake caused by rejecting because of the problems such as camera spottiness is unified by the picture format of all cameras
For general jpg format；
In the present embodiment, the real time data of each camera carries out distributed storage, parallel computation.
S02), by the video image of camera every 5 seconds extraction piece images, continuous 5 width image forms a time sequence
Column；The image of graph forms dynamic time-series image at any time；
S03), the gauss hybrid models monitored using moving target are rejected moving target, extract the background information of image,
The time series models of background picture are established, specific as follows:
The first frame f1 of time-series image is characterized into this image using K Gauss model as initial background first
In each pixel f1The feature of (x, y), the value range of K are 3~5.It is determined by the distribution of image grey level histogram each high
The mean μ of this modeljAnd standard deviation sigmaj, j ∈ [1, K], each pixel gray value can be expressed as the folded of K gauss of distribution function
Add, i.e.,
Wherein, η (μj, σj) it is j-th of Gaussian Profile, ωjIt is its weight.
From the second frame image fi(x, y), i > 1 start, and estimate whether each pixel belongs to background, i.e., judgment formula 2 is no
It sets up:
|fi(x,y)-μj|≤2.5σj(formula 2),
If formula 2 is set up, pixel fi(x, y) is background dot, is otherwise foreground point.New height is generated according to foreground point
This model.
Each Model Weight in present image is updated by formula 3,
Wherein α is learning rate, if current point is background, MK,i=1, otherwise MK,i=0,Before updating
Model Weight,For updated Model Weight；
The Gauss model mean value and standard deviation of foreground point remain unchanged, and the Gauss model mean value and standard deviation of background dot are by working as
Preceding image is updated.
All Gauss models are ranked up, the model that weight is big, standard deviation is small comes front, the mould to sort after K
Type is cast out, to obtain updated background image.
It repeats above operation, obtains the Background of each frame image, establish the Dynamic Time Series image of background image.
Background picture is divided into 4 regions, establishes 4 region contrasts by the time-series image based on background image
Time change change curve.
S04), the changing rule of backdrop pels when analysis group mist happens suddenly, establishes the mist prison based on backdrop pels time series
Survey model；It establishes the mist monitoring model based on backdrop pels time series and has comprehensively considered 4 variables:
A, the contrast X1 of current image when group's mist burst, will cause the contrast of pixel value in background image sharply X1
It reduces；
B, the fuzziness X2 of current image carries out fuzziness identification to current, and when group's mist happens suddenly, full figure has 75% or more area
Domain is fuzzy region；
C, the contrast X3 of frame image is gone up in time series, when group's mist happens suddenly, is had under the X3 and X1 in 3 areas in 4 subregions
Range of decrease degree is more than 300%；
D, in time series upper frame image fuzziness X4, in fuzziness identification, when group's mist burst, full figure have 25% with
Lower region is fuzzy region.
Comprehensively consider above-mentioned 4 variables, establishes the mist monitoring model based on backdrop pels time series, and monitor using mist
Model judges the realtime graphic that camera transmits；
S05), a camera interpretation is after having mist, and the group of starting immediately mist interpretation 5 cameras adjacent to front and back carry out
Comprehensive descision starts mist early warning if 4 or more adjacent cameras are judged to having mist；Such as there are 2 or more adjacent to take the photograph
The case where monitoring non-mist as head is judged as a mist, the flow direction of analysis prediction group mist, the mist early warning of starting group.
In the present embodiment, flow direction and the speed of mist are rolled into a ball according to the sequencing forecast analysis of camera detection to mist,
Because camera is according to specific direction and apart from arrangement, if a camera detection to there is mist, southern is taken the photograph positioned at its
As head has successively detected mist, then the flow direction of the group's of can be determined that mist be from north orientation south, according to the distance between camera and
Time can the group's of calculating mist flow direction and speed.
Described above is only basic principle and preferred embodiment of the invention, and those skilled in the art do according to the present invention
Improvement and replacement out, belong to the scope of protection of the present invention.
Claims (6)
1. a kind of group's mist monitoring method based on big data, it is characterised in that: the following steps are included: S01), obtain monitoring section
The video data of each camera, pre-processes video data；S02), the image data provided each camera is built
A dynamic time series is found, the image of graph forms dynamic time-series image at any time；S03), movement mesh is utilized
The gauss hybrid models of monitoring are marked, moving target is rejected, extracts the background information of image, establish the time series mould of background picture
Type；S04), the changing rule of background picture, establishes the mist based on background picture time series and monitors mould when analysis group mist happens suddenly
Type, and judged using real time data of the mist monitoring model to thecamera head；S05), a camera interpretation is to have mist
Afterwards, the group of starting immediately mist interpretation, if N1 adjacent cameras all monitor mist, interpretation is mist, starts mist early warning；As existed
The case where N2 or more adjacent camera monitors non-mist is judged as a mist, the flow direction of analysis prediction group mist, starting group
Mist early warning；N1, N2 are positive integer, and N1 > N2.
2. group's mist monitoring method according to claim 1 based on big data, it is characterised in that: step S03 specifically:
S31), by the first frame f of time-series image1As initial background, each picture in this image is characterized using K Gauss model
Vegetarian refreshments f1The feature of (x, y), the value range of K are 3~5, determine each Gauss model by the distribution of image grey level histogram
Mean μjAnd standard deviation sigmaj, j ∈ [1, K], each pixel gray value can be expressed as the superposition of K gauss of distribution function, i.e.,Wherein, η (μj, σj) it is j-th of Gaussian Profile, ω j is its power
Weight；S32), from the second frame image fi(x, y), i > 1 start, and estimate whether each pixel belongs to background, i.e., judgment formula 2 is no
It sets up: | fi(x,y)-μj|≤2.5σj(formula 2), if formula 2 is set up, pixel fi(x, y) is background dot, otherwise
It is foreground point, new Gauss model is generated according to foreground point；S33), each Model Weight in present image is updated by formula 3,Wherein α is learning rate, if current point is background,
MK,i=1, otherwise MK,i=0,For update before Model Weight,For updated Model Weight；S34), prospect
The Gauss model mean value and standard deviation of point remain unchanged, and the Gauss model mean value and standard deviation of background dot are carried out more by present image
Newly；S35), all Gauss models are ranked up, the model that weight is big, standard deviation is small comes front, the mould to sort after K
Type is cast out, to obtain updated background image；S36), step S32-S35 is repeated, the background of each frame image is obtained
Figure, establishes the Dynamic Time Series image of background image,；S37), based on the time-series image of background image, by background picture
Change is divided into 4 regions, establishes the time change change curve of 4 region contrasts.
3. group's mist monitoring method according to claim 2 based on big data, it is characterised in that: establish and be based on backdrop pels
The mist monitoring model of time series comprehensively considers the contrast X1 of current image, the fuzziness X2 of current image, in time series
The fuzziness X4 of upper frame image in the contrast X3 of upper frame image, time series, when group's mist burst, pixel value in background image
Contrast X1 is drastically reduced, and it is fuzzy region that current image full figure, which has 75% area above, have in 4 subregions the X3 in 3 areas with
X1 fall is more than 300%, and it is fuzzy region that upper frame image full figure, which has 25% following region, in time series.
4. group's mist monitoring method according to claim 1 based on big data, it is characterised in that: carried out to video data
Processing includes: that image data is quickly examined and verified, and deletes duplicate message, existing mistake is corrected, by all camera shootings
The picture format of head is unified, carries out quick mist monitoring, group's mist judgement processing to the video data of each camera.
5. group's mist monitoring method according to claim 1 based on big data, it is characterised in that: monitor the camera in section
According to specific direction and apart from arrangement, flow direction and the speed of the sequencing forecast analysis group mist of mist are monitored according to camera
Degree.
6. group's mist monitoring method according to claim 1 based on big data, it is characterised in that: a camera interpretation is
After having mist, 5 cameras adjacent to front and back of starting group's mist interpretation immediately carry out comprehensive descision, if 4 or more adjacent is taken the photograph
As head is determined as there is mist, then start mist early warning；Such as there is the case where 2 or more adjacent cameras monitor non-mist, is judged as
Group's mist.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811380273.8A CN109448397B (en) | 2018-11-20 | 2018-11-20 | Group fog monitoring method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811380273.8A CN109448397B (en) | 2018-11-20 | 2018-11-20 | Group fog monitoring method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109448397A true CN109448397A (en) | 2019-03-08 |
| CN109448397B CN109448397B (en) | 2020-11-13 |
Family
ID=65552657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811380273.8A Active CN109448397B (en) | 2018-11-20 | 2018-11-20 | Group fog monitoring method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109448397B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309704A (en) * | 2019-04-30 | 2019-10-08 | 泸州市气象局 | A kind of extreme weather real-time detection method, system and terminal |
| CN111341118A (en) * | 2020-02-28 | 2020-06-26 | 长安大学 | System and method for early warning of mist on grand bridge |
| CN112419745A (en) * | 2020-10-20 | 2021-02-26 | 中电鸿信信息科技有限公司 | Highway group fog early warning system based on degree of depth fusion network |
| CN112668503A (en) * | 2020-12-30 | 2021-04-16 | 日照市气象局 | Method for monitoring visibility of luminous target object video group fog |
| CN113129408A (en) * | 2021-04-08 | 2021-07-16 | 重庆电子工程职业学院 | Group fog monitoring method based on big data |
| CN113706889A (en) * | 2021-08-02 | 2021-11-26 | 浪潮天元通信信息***有限公司 | Highway agglomerate fog measuring system and method based on target detection and analysis |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060101990A (en) * | 2005-03-22 | 2006-09-27 | 주식회사 화흥도로안전씨스템 | Fog preventing system |
| JP2007057331A (en) * | 2005-08-23 | 2007-03-08 | Denso Corp | In-vehicle system for determining fog |
| US20110135200A1 (en) * | 2009-12-04 | 2011-06-09 | Chao-Ho Chen | Method for determining if an input image is a foggy image, method for determining a foggy level of an input image and cleaning method for foggy images |
| CN103871251A (en) * | 2014-03-13 | 2014-06-18 | 山东交通学院 | Digital photography-based agglomerate fog real time early warning system and method |
| CN106097744A (en) * | 2016-08-15 | 2016-11-09 | 山东交通学院 | A kind of expressway fog real-time monitoring system and method based on generalized information system |
| CN106254827A (en) * | 2016-08-05 | 2016-12-21 | 安徽金赛弗信息技术有限公司 | A kind of group's mist Intelligent Recognition method for early warning and device thereof |
| CN107895379A (en) * | 2017-10-24 | 2018-04-10 | 天津大学 | The innovatory algorithm of foreground extraction in a kind of video monitoring |
| CN108765453A (en) * | 2018-05-18 | 2018-11-06 | 武汉倍特威视***有限公司 | Expressway fog recognition methods based on video stream data |
-
2018
- 2018-11-20 CN CN201811380273.8A patent/CN109448397B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060101990A (en) * | 2005-03-22 | 2006-09-27 | 주식회사 화흥도로안전씨스템 | Fog preventing system |
| JP2007057331A (en) * | 2005-08-23 | 2007-03-08 | Denso Corp | In-vehicle system for determining fog |
| US20110135200A1 (en) * | 2009-12-04 | 2011-06-09 | Chao-Ho Chen | Method for determining if an input image is a foggy image, method for determining a foggy level of an input image and cleaning method for foggy images |
| CN103871251A (en) * | 2014-03-13 | 2014-06-18 | 山东交通学院 | Digital photography-based agglomerate fog real time early warning system and method |
| CN106254827A (en) * | 2016-08-05 | 2016-12-21 | 安徽金赛弗信息技术有限公司 | A kind of group's mist Intelligent Recognition method for early warning and device thereof |
| CN106097744A (en) * | 2016-08-15 | 2016-11-09 | 山东交通学院 | A kind of expressway fog real-time monitoring system and method based on generalized information system |
| CN107895379A (en) * | 2017-10-24 | 2018-04-10 | 天津大学 | The innovatory algorithm of foreground extraction in a kind of video monitoring |
| CN108765453A (en) * | 2018-05-18 | 2018-11-06 | 武汉倍特威视***有限公司 | Expressway fog recognition methods based on video stream data |
Non-Patent Citations (1)
| Title |
|---|
| 刘建磊等: "基于视频图像对比度的团雾检测算法", 《光电子技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309704A (en) * | 2019-04-30 | 2019-10-08 | 泸州市气象局 | A kind of extreme weather real-time detection method, system and terminal |
| CN110309704B (en) * | 2019-04-30 | 2022-01-25 | 泸州市气象局 | Method, system and terminal for detecting extreme weather in real time |
| CN111341118A (en) * | 2020-02-28 | 2020-06-26 | 长安大学 | System and method for early warning of mist on grand bridge |
| CN111341118B (en) * | 2020-02-28 | 2021-07-30 | 长安大学 | System and method for early warning of mist on grand bridge |
| CN112419745A (en) * | 2020-10-20 | 2021-02-26 | 中电鸿信信息科技有限公司 | Highway group fog early warning system based on degree of depth fusion network |
| CN112668503A (en) * | 2020-12-30 | 2021-04-16 | 日照市气象局 | Method for monitoring visibility of luminous target object video group fog |
| CN112668503B (en) * | 2020-12-30 | 2022-06-28 | 日照市气象局 | Method for monitoring visibility of luminous target object video group fog |
| CN113129408A (en) * | 2021-04-08 | 2021-07-16 | 重庆电子工程职业学院 | Group fog monitoring method based on big data |
| CN113706889A (en) * | 2021-08-02 | 2021-11-26 | 浪潮天元通信信息***有限公司 | Highway agglomerate fog measuring system and method based on target detection and analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109448397B (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109448397A (en) | A kind of group's mist monitoring method based on big data | |
| CN106910203B (en) | The quick determination method of moving target in a kind of video surveillance | |
| DE112013001858B4 (en) | Multiple-hint object recognition and analysis | |
| Kaseko et al. | A neural network-based methodology for pavement crack detection and classification | |
| CN103839065B (en) | Extraction method for dynamic crowd gathering characteristics | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN106373430A (en) | Intersection pass early warning method based on computer vision | |
| CN103593678B (en) | A kind of long-span bridge vehicle dynamic load distribution detection method | |
| CN103077423B (en) | To run condition detection method based on crowd's quantity survey of video flowing, local crowd massing situation and crowd | |
| CN106204640A (en) | A kind of moving object detection system and method | |
| CN102902974B (en) | Image based method for identifying railway overhead-contact system bolt support identifying information | |
| CN111626203B (en) | Railway foreign matter identification method and system based on machine learning | |
| CN101286239A (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN102955940B (en) | A kind of transmission line of electricity object detecting system and method | |
| CN103034862A (en) | Road snow and rain state automatic identification method based on feature information classification | |
| CN104200673B (en) | A kind of road surface slippery situation detection method based on road image | |
| CN115035182B (en) | Landslide hazard early warning method and system | |
| CN103324951A (en) | Multiple isomerous water environment monitoring data evaluating and early-warning method | |
| CN109086682A (en) | A kind of intelligent video black smoke vehicle detection method based on multi-feature fusion | |
| CN110443142B (en) | Deep learning vehicle counting method based on road surface extraction and segmentation | |
| CN103268498A (en) | Method for area-of-interest blurred image semantic comprehension | |
| CN111783700A (en) | Automatic recognition early warning method and system for road foreign matters | |
| CN116184438A (en) | Data processing method for identifying bad weather based on laser radar | |
| CN109191492A (en) | A kind of intelligent video black smoke vehicle detection method based on edge analysis | |
| CN112329515B (en) | High-point video monitoring congestion event detection 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 |