CN109406521A - A kind of real-time horizontal visibility level detection method - Google Patents
A kind of real-time horizontal visibility level detection method Download PDFInfo
- Publication number
- CN109406521A CN109406521A CN201811494351.7A CN201811494351A CN109406521A CN 109406521 A CN109406521 A CN 109406521A CN 201811494351 A CN201811494351 A CN 201811494351A CN 109406521 A CN109406521 A CN 109406521A
- Authority
- CN
- China
- Prior art keywords
- visibility
- real
- image
- straight line
- detection method
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of real-time horizontal visibility level detection methods.Device is made of fixed object, image acquisition units, background process equipment, storage unit, foreground processing unit, wireless communication module and information receiving terminal, image acquisition units and storage unit are connected with background process equipment respectively, image acquisition units, storage unit and wireless communication module are connected with foreground processing unit respectively, and wireless communication module is connected with information receiving terminal by wireless signal.Processing method includes the processing method of background process equipment and the real-time processing method of foreground processing unit.It can measure accurate horizontal visibility is realized, can be applied to the fields such as airport, harbour, bridge, highway, railway, environmental protection, meteorological station.
Description
Technical field
The present invention relates to a kind of digital image processing field, specifically a kind of real-time horizontal visibility grade detection side
Method.
Background technique
The height of horizontal visibility and the production and living of people have it is inseparable contact, visibility is one by very much
The physical quantity of ingredient joint effect, its difference for being defined on application field is there is also different difference, and every country is to it
Measure also informal calibration standard and detected rule.Instantly, the quality and measurement of many visibility measurement device functions
Effect is obtained in the analysis of a large amount of scholar's quiz statistics data before.Therefore possess the unified visibility of complete set
Measuring criterion is one of difficulty urgently to be resolved at present.Nowadays visibility measurement method mainly includes ocular estimate, instrument measuring method
And the visibility detecting method based on characteristics of image, with the differentiation of intelligence life, for visibility measurement instrument instantly
High cost, the deficiencies of plant maintenance is difficult, consideration obtains corresponding picture progress from existing ambient intelligence equipment to be seen
The measurement method of degree is feasible, therefore the detection of the visibility based on image has become a Main way, but due to environment
Complexity, such as landform, building, the influence of the factors such as moving object, the detection of visibility is even also in theoretical and experiment
Stage.Major part detection algorithm is all based on the research that simple environment such as highway carries out, the scope of application ratio of the algorithm at present
It is smaller, while complexity is higher, operates complex.
Summary of the invention
The present invention provides a kind of real-time horizontal visibility level detection methods, carry out visibility using based on digital picture
Detection, by the foundation of background model, when application, is loaded directly into and calculates output, has that real-time is high, at low cost, accuracy height
The advantages that.
Technical solution used by target to realize the present invention is:
1, construction device:
By fixed object, image acquisition units, background process equipment, storage unit, foreground processing unit, wireless communication
Module and information receiving terminal form a kind of real-time horizontal visibility grade detection device, image acquisition units and storage unit point
Be not connected with background process equipment, image acquisition units, storage unit and wireless communication module respectively with foreground processing unit phase
Even, wireless communication module is connected with information receiving terminal by wireless signal；
2, detection method:
(1) under 1 grade of visibility, after image acquisition units collect the image I of fixed object, it is input to background process
Equipment is handled, and obtains straight line magnitude-set CS of the image I in scale space under 1 grade of visibility, and by straight line quantity collection
It closes CS and is stored in storage unit；
(2) image acquisition units will collect the image Ic of fixed object, is input to foreground processing equipment and carries out in real time
Processing, and be compared with the straight line magnitude-set CS in storage unit, visibility scale P is obtained, by wireless communication module
It is sent to information receiving terminal.
The fixed object is the vertical plane outdoor scene that background color is black, is respectively separated from top to bottom and draws width and be
7cm, 6cm ..., the white line segment of 2cm, 1cm；
The processing of the background process equipment, comprising the following steps:
Step 1.1: the image I of fixed object under 1 grade of visibility of input；
Step 1.2: the scale space S of construction image I；
Step 1.3: extracting image G respectively based on Straight Line Extraction1,G2,…,GnIn straight line and count the number of straight line
Amount, straight line magnitude-set CS={ C1,C2,…,CnAnd save to storage unit.
The background process equipment uses PC.
The scale space S of the step 1.2 is by image G1,G2,…,GnComposition, wherein n is the number of plies of scale space S；
...
In formula,For convolution operator, g (i, j, t) is two-dimensional convolution core,(i, j) is image
In location of pixels, t be the scale space factor.
The real-time processing of the foreground processing unit, comprising the following steps:
Step 2.1: the straight line magnitude-set CS={ C of fixed object is loaded from storage unit1,C2,…,Cn}；
Step 2.2: inputting the image Ic of fixed object；
Step 2.3: the straight line in image Ic is extracted with the Straight Line Extraction in step 1.3 and counts the quantity of straight line,
Straight line quantity is denoted as TC；
Step 2.4: calculating visibility scale, work as CP≥TC≥CP+1When, current visibility scale is determined as P grades, wherein P
∈{1,2,…,7}；
Step 2.5: calculating visibility scale, work as CP≥TC≥CP+1When, current visibility scale is determined as P grades, wherein P
∈{1,2,…,7}；Export visibility scale P.
1 grade of visibility is in accordance with can be shown in level in the People's Republic of China's standard GB/T/T 33673-2017
Spend the definition of grade.
The foreground processing unit uses dsp processor.
The beneficial effects of the present invention are: can measure accurate horizontal visibility is realized, airport, port can be applied to
The fields such as mouth, bridge, highway, railway, environmental protection, meteorological station.
Detailed description of the invention
Fig. 1 is system construction drawing of the invention；
Fig. 2 is the processing method flow chart of background process equipment of the invention；
Fig. 3 is the real-time processing method flow chart of foreground processing unit of the invention.
Specific embodiment
It describes the specific embodiments of the present invention in detail with reference to the accompanying drawing.
Fig. 1 is system construction drawing of the invention.As shown in Figure 1, system there are seven component parts, it is respectively as follows: fixed target
Object (101), image acquisition units (102), background process equipment (103), storage unit (104), foreground processing unit (105),
Wireless communication module (106) and information receiving terminal (107), image acquisition units (102) and storage unit (104) respectively with it is rear
Platform processing equipment (103) be connected, image acquisition units (102), storage unit (104) and wireless communication module (106) respectively with
Foreground processing unit (105) is connected, and wireless communication module (106) is connected with information receiving terminal (107) by wireless signal.
Fig. 2 is the processing method flow chart of background process equipment of the invention.201 be input picture step, and 202 be construction
Scale space step, 203 be to extract straight line step, and 204 be to save straight line quantity step.
Step 201: the image I of fixed object under 1 grade of visibility of input, wherein 1 grade of visibility is total in accordance with Chinese people
With the definition in state standard GB/T/T 33673-2017 to horizontal visibility grade, the background color of fixed object is black, from
It is 7cm, 6cm ..., 2cm, the white line segment of 1cm that top to bottm, which is respectively separated and draws width,.
Step 202: the scale space S of construction image I, scale space S is by image G1,G2,…,GnComposition, wherein n is ruler
Spend the number of plies of space S；
...
In formula,For convolution operator, g (i, j, t) is two-dimensional convolution core,(i, j) is image
In location of pixels, t be the scale space factor.
Step 203: extracting image G respectively based on Straight Line Extraction1,G2,…,GnIn straight line and count the number of straight line
Amount, straight line magnitude-set CS={ C1,C2,…,Cn,
Step 204: straight line magnitude-set CS obtained in step 203 is saved to the storage unit (104) into Fig. 1.
Fig. 3 is the real-time processing method flow chart of foreground processing unit of the invention.301 be load straight line quantity step,
302 be input picture step, and 303 be to extract straight line step, and 304 be to calculate visibility scale step, and 305 be output visibility etc.
Grade step.
Step 301: the straight line magnitude-set CS={ C of load fixed object from the storage unit (104) in Fig. 11,
C2,…,Cn}。
Step 302: inputting the image Ic of fixed object.
Step 303: the straight line in image Ic is extracted with the Straight Line Extraction in step 1.3 and counts the quantity of straight line,
Straight line quantity is denoted as TC。
Step 304: calculating visibility scale, work as CP≥TC≥CP+1When, current visibility scale is determined as P grades, wherein P
∈{1,2,…,7}。
Step 305: output visibility scale P.
Claims (8)
1. a kind of real-time horizontal visibility level detection method, it is characterised in that:
1) construction device:
By fixed object, image acquisition units, background process equipment, storage unit, foreground processing unit, wireless communication module
Form a kind of real-time horizontal visibility grade detection device with information receiving terminal, image acquisition units and storage unit respectively with
Background process equipment is connected, and image acquisition units, storage unit and wireless communication module are connected with foreground processing unit respectively, nothing
Line communication module is connected with information receiving terminal by wireless signal；
2) detection method:
(1) under 1 grade of visibility, after image acquisition units collect the image I of fixed object, it is input to background process equipment
It is handled, obtains straight line magnitude-set CS of the image I in scale space under 1 grade of visibility, and by straight line magnitude-set CS
It is stored in storage unit；
(2) image acquisition units will collect the image Ic of fixed object, is input to foreground processing equipment and is handled in real time,
And be compared with the straight line magnitude-set CS in storage unit, visibility scale P is obtained, module is sent to by wireless communication
Information receiving terminal.
2. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that the fixation
Object is the vertical plane outdoor scene that background color is black, and being respectively separated draw width from top to bottom is 7cm, 6cm ..., 2cm, 1cm
White line segment.
3. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that the backstage
Processing equipment uses PC.
4. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that the backstage
The processing of processing equipment, comprising the following steps:
Step 1.1: the image I of fixed object under 1 grade of visibility of input；
Step 1.2: the scale space S of construction image I；
Step 1.3: extracting image G respectively based on Straight Line Extraction1,G2,…,GnIn straight line and count the quantity of straight line, directly
Line number duration set CS={ C1,C2,…,CnAnd save to storage unit.
5. a kind of real-time horizontal visibility level detection method according to claim 4, it is characterised in that described in step 1.2
Scale space S by image G1,G2,…,GnComposition, wherein n is the number of plies of scale space S；
…
In formula,For convolution operator, g (i, j, t) is two-dimensional convolution core,(i, j) is the picture in image
Plain position, t are the scale space factor.
6. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that the foreground
The real-time processing of processing unit, comprising the following steps:
Step 2.1: the straight line magnitude-set CS={ C of fixed object is loaded from storage unit1,C2,…,Cn}；
Step 2.2: inputting the image Ic of fixed object；
Step 2.3: the straight line in image Ic is extracted with the Straight Line Extraction in step 1.3 and counts the quantity of straight line, it will be straight
Line number amount is denoted as TC；
Step 2.4: calculating visibility scale, work as CP≥TC≥CP+1When, current visibility scale is determined as P grades, wherein P ∈
{1,2,…,7}；
Step 2.5: calculating visibility scale, work as CP≥TC≥CP+1When, current visibility scale is determined as P grades, wherein P ∈
{1,2,…,7}；Export visibility scale P.
7. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that 1 grade of energy
Degree of opinion is in accordance with the definition in the People's Republic of China's standard GB/T/T 33673-2017 to horizontal visibility grade.
8. a kind of real-time horizontal visibility level detection method according to claim 1, it is characterised in that the foreground
Processing unit uses dsp processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494351.7A CN109406521A (en) | 2018-12-07 | 2018-12-07 | A kind of real-time horizontal visibility level detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811494351.7A CN109406521A (en) | 2018-12-07 | 2018-12-07 | A kind of real-time horizontal visibility level detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109406521A true CN109406521A (en) | 2019-03-01 |
Family
ID=65457814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811494351.7A Withdrawn CN109406521A (en) | 2018-12-07 | 2018-12-07 | A kind of real-time horizontal visibility level detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109406521A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063726A (en) * | 2010-12-31 | 2011-05-18 | 中国科学院计算技术研究所 | Moving target classification method and system |
| CN102254315A (en) * | 2010-05-17 | 2011-11-23 | 中国科学院城市环境研究所 | Atmospheric visibility observation method implemented by using double digital cameras |
| CN102262092A (en) * | 2011-04-29 | 2011-11-30 | 中国气象局北京城市气象研究所 | Visibility measurement system and method |
| CN102521597A (en) * | 2011-12-14 | 2012-06-27 | 武汉大学 | Hierarchical strategy-based linear feature matching method for images |
| CN204442538U (en) * | 2013-11-11 | 2015-07-01 | 山东神戎电子股份有限公司 | A kind of watch-dog with visibility acquisition function |
| CN106404720A (en) * | 2016-08-24 | 2017-02-15 | 中国气象科学研究院 | Visibility observation method |
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
-
2018
- 2018-12-07 CN CN201811494351.7A patent/CN109406521A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254315A (en) * | 2010-05-17 | 2011-11-23 | 中国科学院城市环境研究所 | Atmospheric visibility observation method implemented by using double digital cameras |
| CN102063726A (en) * | 2010-12-31 | 2011-05-18 | 中国科学院计算技术研究所 | Moving target classification method and system |
| CN102262092A (en) * | 2011-04-29 | 2011-11-30 | 中国气象局北京城市气象研究所 | Visibility measurement system and method |
| CN102521597A (en) * | 2011-12-14 | 2012-06-27 | 武汉大学 | Hierarchical strategy-based linear feature matching method for images |
| CN204442538U (en) * | 2013-11-11 | 2015-07-01 | 山东神戎电子股份有限公司 | A kind of watch-dog with visibility acquisition function |
| CN106404720A (en) * | 2016-08-24 | 2017-02-15 | 中国气象科学研究院 | Visibility observation method |
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
Non-Patent Citations (2)
| Title |
|---|
| 吕艳芬 等: ""改进的基于图像边缘的能见度反演方法"", 计算机工程与应用, no. 10, pages 170 - 173 * |
| 朱秋旭 等: ""基于梯度的红外与可见光图像直线匹配算法"", 计算机仿真, vol. 30, no. 3, pages 412 - 415 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106017320B (en) | A kind of system of scattered groceries heap volume measuring method and realization the method based on image procossing | |
| CN104020475B (en) | A kind of line of electric force based on on-board LiDAR data extracts and modeling method | |
| CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
| CN103940358B (en) | A kind of Real-time Monitoring System of Bridges | |
| CN108921165B (en) | Water level identification method based on water gauge image | |
| CN103605978A (en) | Urban illegal building identification system and method based on three-dimensional live-action data | |
| CN101033962B (en) | Measurement method for displacement of model experiment based on optics | |
| CN106295655A (en) | A kind of transmission line part extraction method patrolling and examining image for unmanned plane | |
| CN103366250A (en) | City appearance environment detection method and system based on three-dimensional live-action data | |
| CN102819765B (en) | A kind of milk somatic cell method of counting based on computer vision | |
| CN106384355B (en) | A kind of automatic calibration method in projection interactive system | |
| CN103558409B (en) | Distributed PTV flow field survey system and measuring method thereof in a kind of current | |
| CN105066877A (en) | Tree measuring method based on intelligent terminal lens | |
| CN108961330A (en) | The long measuring method of pig body and system based on image | |
| CN106504287B (en) | Monocular vision object space positioning system based on template | |
| CN105842707A (en) | Grassland above-ground biomass measuring method and grassland above-ground biomass measuring device based on remote sensing image acquired by unmanned aerial vehicle | |
| CN103389041B (en) | A kind of method of measuring grid line width | |
| CN107798720A (en) | A kind of method for drawing map and its device, mobile terminal | |
| CN104460951A (en) | Human-computer interaction method | |
| CN113469178B (en) | Power meter identification method based on deep learning | |
| KR20130133596A (en) | Method and apparatus for measuring slope of poles | |
| CN103322918B (en) | The equipment of measuring vehicle height and measuring method thereof | |
| CN203857977U (en) | Automatic calibration system of pointer type instrument | |
| Xu et al. | Water level estimation based on image of staff gauge in smart city | |
| CN204202563U (en) | Fish morphological parameters self-operated measuring unit |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190301 |
|
| WW01 | Invention patent application withdrawn after publication |