CN105629333A - Road weather detection method based on video - Google Patents
Road weather detection method based on video Download PDFInfo
- Publication number
- CN105629333A CN105629333A CN201510987142.6A CN201510987142A CN105629333A CN 105629333 A CN105629333 A CN 105629333A CN 201510987142 A CN201510987142 A CN 201510987142A CN 105629333 A CN105629333 A CN 105629333A
- Authority
- CN
- China
- Prior art keywords
- visibility
- image
- video
- road
- range
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
Landscapes
- Environmental & Geological Engineering (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a road weather detection method based on a video. The method comprises the following steps that: the computer calibration technology is used to restore the distance information in an image; a virtual target object with a road as a background is established and the ejection of a target body with distance information at two sides of the road is avoided; a camera starts to jump a preset location; a target image block is matched; the camera reaches a preset location; a wavelet transform technique is used to remove the influence of noise on the edge of target object, and the pixels beloning to the edge are extracted; a contrast model in accordance with human vision is used to extract a target characteristic; the eye visibility curve fitting is carried out according to the characteristic information and distance information of a target object; and finally, according to an obtained eye visibility curve, combined with the eye contrast threshold 0. 05 recommended by the authority International Commission on illumination (CIE), and the fog content and haze content in the atmosphere are determined according to the visibility of the image.
Description
Technical field
The present invention relates to a kind of road weather detection method based on video, especially relate to a kind of based on the detection method of mist content and haze content in the Road Weather of video.
Background technology
China's highway mileage constantly increases in recent years, and the diastrous weather such as dense fog, heavy rain, ice and snow has become the principal element affecting traffic safety and efficiency. Owing to road Changes in weather is variable, add the various specific geological state of highway, be very easy on road regularly to produce rapidly local in short-term or long time the special weather situation such as rain, snow, group's mist, this meteorological condition is difficult to be obtained by the forecast of meteorological department, and driver runs at high speed at highway, owing to can not get early warning, road ahead situation is known nothing, corresponding preventive measure can not be taked, very easily knock into the back and collision accident. It addition, expressway speed is higher, once cause vehicle accident owing to visibility reduces, often causing chain reaction, ultimately forming the severe traffic accidents that many cars collide continuously, the dead group of group hinders, greatly have impact on the traffic safety of highway. According to statistics, the vehicle accident caused due to adverse weather conditions such as thick fogs accounts for more than the 1/4 of total number of accident.
In order to ensure the coast is clear, improve the disposal ability for accident, person can accomplish the information such as timely, accurately, intactly to collect road weather conditions (particularly visibility index), all kinds of anomalous events and issue various early warning guidance information in time just to require road management, improving trouble-saving ability, quickening processes the response speed of abnormal traffic event. Simultaneously when there is meteorology sudden change and traffic abnormity, location of accident or the regional location that is obstructed can be determined in time, and real-time release is induced and rescue information accordingly, thus farthest ensureing the safe and smooth of road.
At present, the mode that domestic and international similar highway mostly lays meteorological test point and video surveillance point by employing at roadside in Mechatronic Systems gathers weather information and video image information, and the mode of the video image and meteorological data being passed to center by perusal by the monitor of Surveillance center is monitored management, when taking treatment measures after the event of noting abnormalities and terrible weather situation, patrolled to assist discovery accident and to process along the line driving by road administration personnel timing simultaneously.
But, this mode also exists following deficiency:
1, weather information can only long-range prediction, forecast data inaccuracy, it is impossible to show the Practical Meteorological Requirements situation in each section. At present, in highway area along the line, the acquisition of weather information has been forecast mainly through the integral point of meteorological department, and meanwhile, during expressway construction, meteorological measuring station and the visibility detector laid at roadside complete the assisted acquisition of weather information. Owing to affecting the formation of the mist of visibility, process that is lasting and that dissipate is affected by multiple condition, it is carried out prediction and detection exactly and remains at many technical barriers. Simultaneously because highway is wire trend, and the forecast of the forecast of the meteorological department wide scope that is big region, be usually by square kilometre in units of, data redundancy is very big, only there is macroscopic universality and big time domain generality, and do not possess practicality and the real-time of the microcosmos area of highway. Additionally, the meteorological measuring station laid along the line and visibility detector in Expressway Electromechanical System, as: it is currently based on the traditional meteorological visibility meter of light forward/backward scattering Cleaning Principle, its detection sample space is limited, principle is to install the air regime in region in the tens of square meters of point using equipment as collection source, mainly according to the accurate measurement to atmospheric extinction coefficient (or light attenuation coefficient of air), according to Koschmider principle, between meteorological optical range MOR and extinction coefficient ��, existence function relation draws visibility data. But these data can not detect the visibility conditions outside ranges of sensors by true representations, but artificially these data are calculated in the application and to use as the visibility data of several kilometers or dozens of kilometres scope, thus arise that the data of visibility meter just can not reflect the situation beyond its sensor detection range at all if when the installation point of visibility meter and fog-zone exist larger space difference. Simultaneously because the reasons such as price much more expensive, maintenance cost is high, the complicated operation of meteorological measuring station and visibility detector, it is difficult to the intensive laying along road, the highway of usual one 100 kilometers can only be installed 2-3 and overlap visibility meter, owing to website is relatively fewer, and many observation websites is from highway farther out, the road conditions meteorology that not necessarily can represent highway is live, therefore can not fully meet the demand of expressway weather detection.
2, current monitoring system is artificial passive monitoring mode. Need to the naked eye be gone by monitoring personnel to observe monitor, judge to obtain information by the brain of people, if there is no manual observation, weather conditions will be failed to report. Being mounted with more or less a hundred CCTV road monitoring camera on road, image has also all passed to Surveillance center, but can not be equipped with same amount of monitor and same amount of monitoring personnel realize man-to-man keeping an eye on simultaneously. For a road monitoring branch center, general only 10-20 platform monitor and 1-2 name staff, it is impossible to accomplish that nearly hundred road images were monitored by artificial 24 hours simultaneously incessantly. Therefore, it is difficult to abnormal traffic event hidden danger such as finding the parking of generation in road in time, retrograde, article are dropped, and often a trickle negligent supervision and off one's guard be all likely to result in hidden trouble of traffic let alone and expand, even finally lead to freeway traffic major accident and cause immeasurable loss.
Haze, as the term suggests being mist and haze. But the difference of mist and haze is very big. What the aerosol systems of the particulate matter compositions such as dust in air, sulphuric acid, nitric acid caused visual disorder is haze. Popular, mist is exactly liquid particles, and haze is exactly solid particle. Visibility different distance is also led to owing to the liquid particles in air is different with solid content. If in air during mist too high levels, along with temperature raises, fog easily scatters naturally, and the highway traffic control time can shorten. Otherwise, during haze too high levels, the road control time is longer. So, the existing road weather detection method based on video cannot directly give mist and haze content in air, can not provide the change of highway future weather and accurately and timely predict.
Summary of the invention
The present invention devises a kind of road weather detection method based on video, it solves the technical problem that it is that (1) existing road weather detection method based on video cannot directly give mist and haze content in air, can not provide the change of highway future weather and accurately and timely predict. (2) the quantization data constantly that the visibility data that video image analysis draws are not as the change of visibility and change, it is impossible to overall visibility conditions in real reflecting video region and change.
In order to solve the technical problem of above-mentioned existence, present invention employs below scheme:
A kind of road weather detection method based on video, comprises the following steps:
Step 1: use computer calibration technique to recover the range information in image;
Step 2: set up the observed object thing with range information;
Step 3: video camera starts to redirect presetting bit;
Step 4: target image Block-matching;
Step 5: video camera arrives presetting bit;
Step 6: adopt wavelet transformation maneuver to remove the noise impact on object edge, extract the pixel belonging to edge;
Step 7: use meets human eye contrast degree model and carries out object feature extraction;
Step 8: carry out human eye visibility curve's matching according to the characteristic information of object and range information;
Step 9: finally according to obtained human eye visibility conversion curve, in conjunction with the human eye contrast degree threshold value 0.05 that International Commission on Illumination (CIE) authoritative institution is recommended, draws range of visibility;
Step 10, range of visibility according to image determine mist content and haze content in air.
Further, step 10 is step by step: step A, set up mist content and the haze data base containing numerical quantity in the air that the image of different range of visibility is corresponding; In step B, step 9, the data base in the range of visibility comparison step A of image obtains in the air of correspondence mist content and haze containing numerical quantity.
Further, when detecting next time, repeat step 3 between step 10 institute in steps.
Should based on the road weather detection method of video with traditional based on compared with the road weather detection method of video, having the advantages that
(1) present invention determines mist content and haze content in air according to the range of visibility of image, make not only can announce weather condition, and could be aware that the mist content in air and haze content, such that it is able to further following weather is carried out accurately reasonably prediction.
(2) present invention is as the change of visibility by the visibility data that video image analysis draws and the quantization data constantly that change, can overall visibility conditions in real reflecting video region and change, watching weather such as human eye, the visibility conditions in 1-2 kilometer range can be accurately reflected out, can by monitoring personnel's situation according to weather, section, arbitrarily set the threshold of visibility of zones of different, namely low visibility alerts in threshold value, thus the generation of a mist can be found rapidly in time and report to the police.
Accompanying drawing explanation
Fig. 1: the present invention is based on the flow chart of steps of the road weather detection method of video;
Fig. 2: camera calibration model schematic in the present invention.
Detailed description of the invention
Below in conjunction with Fig. 1 and Fig. 2, the present invention will be further described:
Owing to human eye is more sensitive to monochrome information comparison colouring information, so only the monochrome information of image being analyzed and processed at present, temporarily ignore colouring information. In nineteen twenty-four, Koschmieder proposes: with sky for background, and the relation observing brightness and distance of the luminous object being observed, as shown in formula (1), L is the observation brightness of object. L0For intrinsic brightness.
Formula (1)
In formula: LfFor the brightness of sky, k is the extinction coefficient of air.
The present invention is on existing video visibility Research foundation, consider detection algorithm and system availability thereof and stability, camera self-calibration technology is adopted to recover the range information in image, set up with road surface for the virtual target thing of background, it is to avoid Liao road sets up the target entity with range information on both sides of the road. Adopting wavelet transformation maneuver to remove the noise impact on object edge, extract the pixel belonging to edge, use meets human eye contrast degree model and carries out object feature extraction. Characteristic information and range information according to object carry out human eye visibility curve's matching, finally according to obtained visibility conversion curve, in conjunction with the human eye contrast degree threshold value 0.05 that the authoritative institutions such as International Commission on Illumination (CIE) are recommended, draw range of visibility.
Native system detection algorithm flow process is as shown in Figure 1: use computer calibration technique to recover the range information in image; Set up the observed object thing with range information; Eliminate the Image semantic classification of impact noise in image; Object based on SAD algorithm detects; Wavelet transformation is used to extract the pixel belonging to edge in object; The extraction of the edge feature of camera review naked eyes simulation; Gained contrast and the nonlinear fitting apart from mapping relations; The comparison threshold value that native system is chosen is recommended by authoritative institutions such as International Commission on Illumination (CIE), and when contrast is more than comparison threshold value 0.05, it is visible that target is human eye.
Specifically, including following key step:
1, image distance Information recovering.
Adopt camera self-calibration technology, set up the image coordinate mapping relations to road surface coordinate, convert image distance information to road surface range information. Its job step is as follows:
1.1, road conditions video camera imaging model is set up.
As in figure 2 it is shown, define three kinds of coordinate systems in figure, wherein earth axes Xw Yw Zw and camera coordinate system Xc Yc Zc is used for characterizing three dimensions; Plane of delineation coordinate system Xf Yf characterizes imaging plane. Setting up world coordinate system, its initial point is camera optical axis and ground intersection point. Setting up camera coordinate system, initial point is video camera photocentre position. If video camera photocentre and world coordinate system initial point distance are l, the angle of pitch of video camera is t, and drift angle is p, and swing angle is s, carrys out the express highway pavement in corresponding camera field with region between parallel lines on ground level;
1.2, based on the video camera dimensional orientation parameter of definition, desirable perspective model, the coordinate conversion relation between earth axes and two dimensional image coordinate system are set up;
1.3, the corresponding relation between the non-calibrating parameters of video camera and image features is set up with express highway pavement lines for object of reference. Choosing the parallelogram based on lines angle point on monitoring section is demarcating module. According to corresponding relation parallel between angle point, it is possible to calculate camera parameters p, t, s, f, the l of the unknown.
2, image virtual object block is set up.
Choosing 48 groups in 1.3 angle points detected from above-mentioned steps, centered by each angle point, delimiting a rectangular area is virtual target thing, and calculates the range information of virtual target thing.
3, target image Block-matching.
In order to enable the object of divided ownership exactly, adopt and be partitioned into from the nearest object of video camera, and according to it and other object relatively fixed position relation on image, it is determined that the segmentation of all objects. Object to 20m, adopts absolute difference and the algorithm SAD of the image matching method mismatch measure based on template, is split.
4, target image block edge extracting and denoising.
Marr is from neuro physiology and psychophysics, point out that the processing of vision of people is equivalent to the boundary operator having multiple resolution and image is being analyzed process, use the operator that resolution is higher in the bigger region of image pixel graded, and use the relatively low operator of resolution in the region that image pixel graded is less. Therefore the visual psychology simulating people needs lower image to be carried out small echo process multiple dimensioned.
Wherein, B-spline wavelet function has minimum possible Support length, and due to can well approximate Gaussian and be easy to computer disposal and the real-time implementation of algorithm. Cubic spline function is B-spline wavelet function conventional in wavelet transformation, its derivative is second order spline function simultaneously, is antisymmetric function, is suitable for the detection at step change type edge, therefore select cubic spline function as two dimension smooth function �� (x, y). Meanwhile, the selection of wavelet transform dimension scope to ensure that smallest dimension lower limb information is relatively more accurate, through experiment repeatedly, selects in yardstick a=2,22,23 and 24 time, image to be processed.
Difference according to the picture edge characteristic that wavelet transformation under different scale extracts, it is necessary to select different threshold value to obtain maximum point under different scale. Therefore select higher threshold value to reduce effect of noise in the metric space of large scale a=24; A=2,2 and 23 metric space in select less threshold value to keep the integrity of marginal information as far as possible.
Owing to the marginal point of detection is made up of discrete point mostly, seriality is bad, needs to adopt edge tracking and compensating to be further processed, obtain continuous print edge under each yardstick after using threshold value leaching image border.
Above in conjunction with accompanying drawing, the present invention is carried out exemplary description; the realization of the obvious present invention is not subject to the restrictions described above; as long as have employed the various improvement that the design of the method for the present invention carries out with technical scheme; or the not improved design by the present invention and technical scheme directly apply to other occasion, all in protection scope of the present invention.
Claims (3)
1., based on a road weather detection method for video, comprise the following steps:
Step 1: use computer calibration technique to recover the range information in image;
Step 2: set up the observed object thing with range information;
Step 3: video camera starts to redirect presetting bit;
Step 4: target image Block-matching;
Step 5: video camera arrives presetting bit;
Step 6: adopt wavelet transformation maneuver to remove the noise impact on object edge, extract the pixel belonging to edge;
Step 7: use meets human eye contrast degree model and carries out object feature extraction;
Step 8: carry out human eye visibility curve's matching according to the characteristic information of object and range information;
Step 9: finally according to obtained human eye visibility conversion curve, in conjunction with the human eye contrast degree threshold value 0.05 that International Commission on Illumination (CIE) authoritative institution is recommended, draws range of visibility;
Step 10, range of visibility according to image determine mist content and haze content in air.
2. according to claim 1 based on the road weather detection method of video, it is characterised in that: step 10 is step by step: step A, set up mist content and the haze data base containing numerical quantity in the air that the image of different range of visibility is corresponding; In step B, step 9, the data base in the range of visibility comparison step A of image obtains in the air of correspondence mist content and haze containing numerical quantity.
3. the road weather detection method based on video according to claim 1 or claim 2, it is characterised in that: when detecting next time, repeat step 3 between step 10 institute in steps.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510987142.6A CN105629333A (en) | 2015-12-27 | 2015-12-27 | Road weather detection method based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510987142.6A CN105629333A (en) | 2015-12-27 | 2015-12-27 | Road weather detection method based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105629333A true CN105629333A (en) | 2016-06-01 |
Family
ID=56044443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510987142.6A Pending CN105629333A (en) | 2015-12-27 | 2015-12-27 | Road weather detection method based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105629333A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109661667A (en) * | 2016-10-14 | 2019-04-19 | 富士通株式会社 | The retrograde detection device of vehicle and method, electronic equipment |
| CN110097762A (en) * | 2019-03-25 | 2019-08-06 | 南京微达电子科技有限公司 | A kind of road video image low visibility scale evaluation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006349492A (en) * | 2005-06-15 | 2006-12-28 | Denso Corp | On-vehicle fog determination device |
| CN101281142A (en) * | 2007-12-28 | 2008-10-08 | 深圳先进技术研究院 | Method for measuring atmosphere visibility |
| JP2012167983A (en) * | 2011-02-14 | 2012-09-06 | Stanley Electric Co Ltd | Fog detector |
| CN103149603A (en) * | 2013-03-07 | 2013-06-12 | 安徽皖通科技股份有限公司 | Road weather detection method based on video |
| CN103954542A (en) * | 2014-05-12 | 2014-07-30 | 中国计量学院 | PM2.5 (Particulate Matter2.5) concentration detector based on definition evaluation without reference image |
-
2015
- 2015-12-27 CN CN201510987142.6A patent/CN105629333A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006349492A (en) * | 2005-06-15 | 2006-12-28 | Denso Corp | On-vehicle fog determination device |
| CN101281142A (en) * | 2007-12-28 | 2008-10-08 | 深圳先进技术研究院 | Method for measuring atmosphere visibility |
| JP2012167983A (en) * | 2011-02-14 | 2012-09-06 | Stanley Electric Co Ltd | Fog detector |
| CN103149603A (en) * | 2013-03-07 | 2013-06-12 | 安徽皖通科技股份有限公司 | Road weather detection method based on video |
| CN103954542A (en) * | 2014-05-12 | 2014-07-30 | 中国计量学院 | PM2.5 (Particulate Matter2.5) concentration detector based on definition evaluation without reference image |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109661667A (en) * | 2016-10-14 | 2019-04-19 | 富士通株式会社 | The retrograde detection device of vehicle and method, electronic equipment |
| CN110097762A (en) * | 2019-03-25 | 2019-08-06 | 南京微达电子科技有限公司 | A kind of road video image low visibility scale evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109716108B (en) | Bituminous paving disease detecting system based on two mesh image analysis | |
| CN109377726B (en) | Expressway agglomerate fog accurate warning and inducing system and method based on Internet of vehicles | |
| CN103794056B (en) | Based on the vehicle precise classification system and method for real-time two-way video stream | |
| CN103176185B (en) | Method and system for detecting road barrier | |
| CN101382497B (en) | Visibility detecting method based on monitoring video of traffic condition | |
| CN101281142B (en) | Method for measuring atmosphere visibility | |
| CN110097762B (en) | Road video image low visibility scale estimation method and system | |
| CN101918980B (en) | Runway surveillance system and method | |
| CN103149603B (en) | Road weather detection method based on video | |
| CN103325255B (en) | The method of region transportation situation detection is carried out based on photogrammetric technology | |
| CN104613892B (en) | Merge the compound snow depth monitoring system of video detection technology and laser ranging technique | |
| CN111461088B (en) | Rail transit obstacle avoidance system based on image processing and target recognition | |
| CN105799740A (en) | Automatic detecting and early warning method for track foreign matter invasion based on Internet of Things technology | |
| CN109910872B (en) | parking scene extraction system and method based on natural driving data | |
| WO2014125248A1 (en) | A road marking analyser and a method of analysis of road markings and an apparatus and method for detecting vehicle weave | |
| CN203606954U (en) | Highway weather monitoring system | |
| CN102162788A (en) | Visibility detection method based on high-definition video | |
| CN105424655A (en) | Visibility detection method based on video images | |
| CN104240239A (en) | Method for detecting local road segment hazy weather based on road image | |
| CN105021528A (en) | Road weather detection device based on videos | |
| CN114858214B (en) | Urban road performance monitoring system | |
| Mertz et al. | City-wide road distress monitoring with smartphones | |
| CN115019514B (en) | Highway inspection system based on car networking | |
| CN113591941A (en) | Intelligent height limiting warning system and method based on multi-sensor fusion | |
| CN103134800A (en) | Road weather detection system based on video |
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 |
Application publication date: 20160601 |
|
| RJ01 | Rejection of invention patent application after publication |