CN103413444A - Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video - Google Patents
Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video Download PDFInfo
- Publication number
- CN103413444A CN103413444A CN2013103750043A CN201310375004A CN103413444A CN 103413444 A CN103413444 A CN 103413444A CN 2013103750043 A CN2013103750043 A CN 2013103750043A CN 201310375004 A CN201310375004 A CN 201310375004A CN 103413444 A CN103413444 A CN 103413444A
- Authority
- CN
- China
- Prior art keywords
- traffic
- image
- video
- traffic flow
- unmanned plane
- 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
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a traffic flow surveying and handling method based on an unmanned aerial vehicle high-definition video. The method comprises the steps of video capture, wherein an unmanned aerial vehicle is made to hover over a selected urban road intersection for high-definition video shooting; image stabilization and pre-processing, wherein the high-definition video is copied, stabilization and pre-processing are carried out on images, and then an image sequence is output; detection and tracking, wherein detection and tracking are carried out on moving objects with the image sequence treated with image stabilization as source data; analysis and statistics, wherein traffic flow analysis and statistics are carried out on a target ID which is tracked down and the current coordinates of motion; output, wherein traffic flow statistical data are transmitted to a client-side graphical interface for display, and then data and statements are generated. The traffic flow surveying and handling method based on the unmanned aerial vehicle high-definition video is capable of obtaining various high-accuracy traffic data, reducing the workload of field survey remarkably, preventing the traffic from being affected, obtaining statistic data of all traffic flows in twelve directions of the intersection, and providing data support for congestion control such as intersection signal timing optimization and traffic channeling improvement.
Description
Technical field
The present invention relates to a kind of traffic flow method of investigating, relate in particular to a kind of traffic flow based on unmanned plane HD video method of investigating.
Background technology
Vehicle identification and tracking are important contents in intelligent transport technology, are having broad application prospects aspect future transportation information acquisition and traffic control and management; Existing vehicle identification and tracking technique are mainly studied based on the video of fixing camera, but fixing camera is limited by mobile difficulty, and the shortcomings such as limited coverage area have restricted its effect performance in the urban transportation monitoring greatly.And the main method that the volume of traffic, the speed of a motor vehicle, density philosophy are investigated that adopts of existing traditional traffic stream characteristics investigation, not only on fact-finding process and data are processed, need a large amount of man power and materials, but also there will be to a certain extent interference traffic, the problem such as the investigation sample amount is little, fact-finding process can not reproduce.
Summary of the invention
Technical matters to be solved by this invention is need to provide a kind of not only can significantly reduce the field investigation workload, but also have, do not affect traffic, data acquisition and analyzing and processing process can repeat as required, the traffic live material traffic flow with long preservation period method of investigating.
To this, the invention provides a kind of traffic flow based on unmanned plane HD video method of investigating, comprise the following steps:
The video acquisition step, hover over selected urban road intersection top by unmanned plane, and take HD video;
Steady picture pre-treatment step, copy HD video and surely look like pre-service, exports sequence of pictures;
Detect tracing step, using surely as after sequence of pictures as coming source data to carry out detection and the tracking to moving object;
The analytic statistics step, carry out wagon flow quantitative analysis and statistics to the Target id that tracks and the current coordinates of motion; And,
The output step, be transferred to Client GUI by the statistics of vehicle flowrate and show, and generated data and form.
The invention belongs to the digital image processing techniques field, be specifically related to a kind of traffic flow based on the unmanned plane HD video by electronic steady image and visual analysis method of investigating, this traffic flow method of investigating is first carried out pre-service by the HD video of surely as device, unmanned plane being taken, then output to target acquistion software and carry out moving object detection and tracking, again result is transferred to trajectory analysis software and carries out vehicle flowrate, finally output to graphical interfaces and show, data and form are passed judgment in the quantification that generates traffic flow.
Unmanned plane (UAV) progresses into the traffic engineering field as a kind of emerging information acquisition means, unmanned plane can carry out motor-driven, flexible and large-scale traffic information collection by carrying high-resolution picture pick-up device, information acquisition in can advancing according to certain path like this, can hover again and obtain traffic video in the top, observation area.But unmanned plane (UAV) gathers transport information, its intrinsic difficulty is also arranged, as: the shake of video, due to video sensor along with the high-speed motion of unmanned plane moves, the complicacy of background and the characteristics such as diversity of moving target information in the video sequence image, these characteristics make processing target detect the problem of following the tracks of and become more difficult.
The present invention be take the traffic flow of crossing and is research object, by the mode of hovering directly over unmanned plane (UAV), gather the traffic flow video of crossing, and the video that unmanned plane (UAV) gathers is analyzed to vehicle individuality, the speed of a motor vehicle in the identification crossing and the motion process of following the tracks of vehicle; By the hover characteristics of unmanned plane (UAV) video of research crossing, design vehicle identification and the tracking processing method of adverse effects such as can overcoming video jitter, translation, rotate and fluctuate, and then realized effective extraction of transport information in the crossing.
Compared with prior art, the means that the present invention's application video frequency vehicle detects are carried out investigation and the processing to traffic stream characteristics, by the traffic fact that video camera is recorded, carry out data acquisition and analyzing and processing, can obtain the traffic data that multiple precision is very high, not only can significantly reduce the field investigation workload, but also have, do not affect traffic, data acquisition and analyzing and processing process can repeat as required, but traffic live material long preservation; On this basis, the present invention compares other similar highway section formula video analysis traffic flow investigating systems and compares, overcome unmanned plane (UAV) in the intrinsic difficulty gathered on transport information, and the statistical function with the whole magnitudes of traffic flow on the direction of 12 of crossings, can sum up the rule of blocking up and forming and dissipating, for the control measures that block up such as intersection signal timing optimization, traffic channelling improvement provide Data support.
Further improvement of the present invention is, describedly surely as pre-treatment step, comprise following sub-step: step 1, current frame image is carried out to translation, Rotation and Zoom, make itself and former frame image there is no difference, and the motion-vector of current frame image and former frame image is write to journal file; Step 2, carry out translation, Rotation and Zoom according to journal file to current frame image.Preferably, described steady step 1 as pre-treatment step is: at first, search the violent shake of current frame image and former frame image, downscaled images displacement calculating amount; Then, the image dwindled is carried out respectively to the amplification of twice and four times, the displacement size of meticulous these image blocks of adjusting is until find the motion-vector of original image.By the supporting of two field picture dwindled and amplify to search motion-vector, can eliminate quickly and accurately the shake of video.
Further improvement of the present invention is, described detection tracing step comprises following sub-step:
The noise reduction process sub-step, adopt median filtering method to carry out noise reduction process to gray level image;
The binary conversion treatment sub-step, adopt the threshold segmentation method to carry out binary conversion treatment to image;
The vehicle detection sub-step, adopt the background subtraction point-score to carry out vehicle detection; And,
The vehicle tracking sub-step, follow the tracks of vehicle by the agglomerate that comprises vehicle identifiers, position and size.
Further improvement of the present invention is, described noise reduction process sub-step is first carried out the calculating of maximal value, intermediate value and minimum value to each column data in sequence of pictures, then maximal value, intermediate value and minimum value are got to the output pixel value of mean as the filtering result.
For ease of explanation, the video in window of 3 x 3 of take is example, is P0 by each pixel definition in 3 x 3 windows, P1 ... P8; To each column count maximal value, intermediate value and the minimum value in window, and maximal value, intermediate value and minimum value are got to the output pixel value of mean as the filtering result, this median calculation only needs 17 comparisons, with traditional algorithm, compare and reduced approximately 2 times, can obtain a result rapidly, be applicable to real-time processing.
Further improvement of the present invention is, described binary conversion treatment sub-step presets threshold value T, according to
Image is divided into to two pixel groups that are greater than T and are less than T.The present invention has set a certain threshold value T(OSTU maximum variance between clusters), this threshold value T can set as the case may be and change, passing threshold T can be divided into two parts by the data of image: be greater than the pixel group of T and be less than the pixel group of T, being convenient to follow-up image be carried out to visual analysis.
Further improvement of the present invention is, described vehicle detection sub-step is first chosen the average image as a setting of piece image at least in background, then the present frame of successive image sequence and background image is subtracted each other, and carries out the background cancellation; When resulting pixel count is greater than while presetting threshold value T, judge in observed scene moving target is arranged.
At first choose a width in background or a few width image the average image as a setting, then the present frame of successive image sequence and background image are subtracted each other, carry out the background cancellation; If resulting pixel count is greater than a certain threshold value, can judge in observed scene moving target is arranged, be formulated as follows:
,
Wherein,
For present frame,
For background image.
Mixed Gaussian distribution background model is adopted in background extracting and renewal, and update rule is as follows:
.Wherein,
The threshold value that means noise; X means the current frame pixel value; α means the learning rate of model, i.e. renewal rate; Because the renewal of background model is also not exclusively depended on current pixel value, and have correlativity with front frame, after introducing α, background model can keep relative stability in long-time.
Further improvement of the present invention is, described vehicle tracking sub-step is: candidate pixel is carried out to image and cut apart, judge that this pixel of cutting apart image belongs to target, background or other zones, the pixel that will have same characteristic features assembles a zone; Use contour area to identify vehicle as characteristic quantity, the same moving target of images different in the video flowing sequence is connected, indicate by oval frame; Carry out Kalman's estimation, speed and accuracy in order to provide new image cut zone to detect, circulate according to this.
Further improvement of the present invention is, described analytic statistics step is that track generates and the track aftertreatment, comprise the analysis to target data number, event data number and timestamp, described target data number comprises ID, barycenter image coordinate, image coordinate width, image coordinate height, speed, type, track, place and the region of target; Described event data number comprises sign, Target id number, event, track, lights state, speed and event additional data.
Further improvement of the present invention is, the form that described output step is exported comprises short-term observation report and long-term observation report, and the data of described short-term observation report comprise that the 5min volume of traffic, the daytime 12h volume of traffic, peak hour traffic, peak hour flow ratio, peak hour factor, road direction distribution coefficient, the busy direction volume of traffic account for ratio and right-hand rotation, craspedodrome and the left-hand bend wagon flow ratio that adds up to the volume of traffic; The data of described long-term observation report comprise annual average daily traffic, all average daily traffic volumes, monthly average daily traffic, the annual moon volume of traffic, year the highest hourly traffic volume, the 30th maximum annual hourly volume, the 30th volume of traffic coefficient, month volume of traffic variation factor and all daily traffic volume variation factors.
Compared with prior art, beneficial effect of the present invention is, by HD video to vehicle and detect, and then realization is to investigation and the analyzing and processing of traffic flow, can obtain the traffic data that multiple precision is very high, not only can significantly reduce the field investigation workload, not affect traffic but also have, data acquisition and analyzing and processing process can repeat as required, but traffic live material long preservation; On this basis, the technical matters that the present invention has also overcome that unmanned plane (UAV) video jitter, the video sensor on gathering transport information moves along with the high-speed motion of unmanned plane, background is complicated in the video sequence image, moving target information is various etc. brings, statistical function with the whole magnitudes of traffic flow on the direction of 12 of crossings, can sum up the rule of blocking up and forming and dissipating, for the control measures that block up such as intersection signal timing optimization, traffic channelling improvement provide Data support.
The accompanying drawing explanation
Fig. 1 is the workflow schematic diagram of an embodiment of the present invention;
Fig. 2 is the workflow schematic diagram of background subtraction point-score of the vehicle detection sub-step of the another kind of embodiment of the present invention;
Fig. 3 is the renewal schematic flow sheet of background model of the vehicle detection sub-step of the another kind of embodiment of the present invention;
Fig. 4 is the previous moment of the another kind of embodiment of the present invention and variance prediction and the correction schematic diagram of current time;
Fig. 5 is the workflow schematic diagram of the vehicle tracking sub-step of the another kind of embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, preferably embodiment of the present invention is described in further detail.
Embodiment 1:
This example provides a kind of traffic flow based on unmanned plane HD video method of investigating, and comprises the following steps:
The video acquisition step, hover over selected urban road intersection top by unmanned plane, and take HD video;
Steady picture pre-treatment step, be copied to HD video on PC and surely look like pre-service, the output sequence of pictures;
Detect tracing step, using surely as after sequence of pictures as coming source data to carry out detection and the tracking to moving object;
The analytic statistics step, carry out wagon flow quantitative analysis and statistics to the Target id that tracks and the current coordinates of motion; And,
The output step, be transferred to Client GUI by the statistics of vehicle flowrate and show, and generated data and form.
This routine workflow schematic diagram as shown in Figure 1, belong to the digital image processing techniques field, be specifically related to a kind of traffic flow based on the unmanned plane HD video by electronic steady image and visual analysis method of investigating, this traffic flow method of investigating is first carried out pre-service by the HD video of surely as device, unmanned plane being taken, then output to target acquistion software and carry out moving object detection and tracking, again result is transferred to trajectory analysis software and carries out vehicle flowrate, finally output to graphical interfaces and show, data and form are passed judgment in the quantification that generates traffic flow.
Unmanned plane (UAV) progresses into the traffic engineering field as a kind of emerging information acquisition means, unmanned plane can carry out motor-driven, flexible and large-scale traffic information collection by carrying high-resolution picture pick-up device, information acquisition in can advancing according to certain path like this, can hover again and obtain traffic video in the top, observation area.But unmanned plane (UAV) gathers transport information, its intrinsic difficulty is also arranged, as: the shake of video, due to video sensor along with the high-speed motion of unmanned plane moves, the complicacy of background and the characteristics such as diversity of moving target information in the video sequence image, these characteristics make processing target detect the problem of following the tracks of and become more difficult.
This example be take the traffic flow of crossing and is research object, by the mode of hovering directly over unmanned plane (UAV), gather the traffic flow video of crossing, and the video that unmanned plane (UAV) gathers is analyzed to vehicle individuality, the speed of a motor vehicle in the identification crossing and the motion process of following the tracks of vehicle; By the hover characteristics of unmanned plane (UAV) video of research crossing, design vehicle identification and the tracking processing method of adverse effects such as can overcoming video jitter, translation, rotate and fluctuate, and then realized effective extraction of transport information in the crossing.
Compared with prior art, the means that this example application video frequency vehicle detects are carried out investigation and the processing to traffic stream characteristics, by the traffic fact that video camera is recorded, carry out data acquisition and analyzing and processing, can obtain the traffic data that multiple precision is very high, not only can significantly reduce the field investigation workload, but also have, do not affect traffic, data acquisition and analyzing and processing process can repeat as required, but traffic live material long preservation; On this basis, this example is compared other similar highway section formula video analysis traffic flow investigating systems and is compared, overcome unmanned plane (UAV) in the intrinsic difficulty gathered on transport information, and the statistical function with the whole magnitudes of traffic flow on the direction of 12 of crossings, can sum up the rule of blocking up and forming and dissipating, for the control measures that block up such as intersection signal timing optimization, traffic channelling improvement provide Data support.
Embodiment 2:
On the basis of embodiment 1, this example is described surely comprises step quickly as pre-treatment step: step 1, current frame image is carried out to translation, Rotation and Zoom, and make itself and former frame image there is no difference.At first, search violent shake, vast scale downscaled images displacement calculating amount; Then, the image dwindled is carried out to the amplification of twice and four times, the displacement size of meticulous these image blocks of adjusting until find the motion-vector (motion vectors) of original image, finally writes journal file by motion-vector.Step 2, carry out translation, Rotation and Zoom according to journal file to current frame image.
This routine described detection tracing step and analytic statistics step all belong to visual analysis, specifically comprise following double teacher.
Stage 1: adopting Fast median filtering algorithm to carry out noise reduction process to gray level image, for ease of explanation, is P0 by each pixel definition in 3 x 3 windows, P1 ... P8; To each column count maximal value, intermediate value and minimum value in window, processing procedure comprises: Max0=max[P0, P3, P6], Max1=max[P1, P4, P7], Max2=max[P2, P5, P8], Med0=med[P0, P3, P6], Med1=med[P1, P4, P7], Med2=med[P2, P5, P8], Min0=min[P0, P3, P6], Min1=min[P1, P4, P7], Min2=min[P2, P5, P8].
The processing procedure of the output pixel value Winmed of filtering result is as follows: Maxmin=min[Max0, Max1, Max2], Medmed=med[Med0, Med1, Med2], Minmax=max[Min0, Min1, Min2], Winmed=med[Maxmin, Medmed, Minmax].By above-mentioned median calculation, only need 17 comparisons, with traditional algorithm, compare and reduced approximately 2 times, be applicable to real-time processing.
Stage 2: adopt the threshold segmentation method to carry out binary conversion treatment to image.Set a certain threshold value T(OSTU maximum variance between clusters), can the data of image be divided into to two parts with this threshold value T: be greater than the pixel group and the pixel group that is less than T of T, the formula that binary conversion treatment adopts is:
.
Stage 3: adopt the background subtraction point-score to carry out vehicle detection.At first choose a width in background or a few width image the average image as a setting, then the present frame of successive image sequence and background image are subtracted each other, carry out the background cancellation; If resulting pixel count is greater than a certain threshold value, can judge in observed scene moving target is arranged, be formulated as follows:
,
Wherein,
For present frame,
For background image.This stage 2 and stage 3 belong to the detection tracing step, and Fig. 2 is the workflow schematic diagram of the background subtraction point-score of vehicle detection sub-step.
Mixed Gaussian distribution background model is adopted in background extracting and renewal, and update rule is as follows:
.
Wherein,
Mean the threshold value of noise, x means the current frame pixel value, and α means the learning rate of model, i.e. renewal rate.Because the renewal of background model is also not exclusively depended on current pixel value, and have correlativity with front frame, after introducing α, background model can keep relative stability in long-time, and Fig. 3 is the renewal schematic flow sheet of the background model of this routine vehicle detection sub-step.
Stage 4: based on the vehicle tracking of agglomerate (blob).Candidate pixel is carried out to image and cut apart, judge that this pixel belongs to target or belongs to background or belong to other zones, assembles a zone to the pixel with same characteristic features; Use contour area to identify vehicle as characteristic quantity, the same moving target of images different in the video flowing sequence is connected, indicate by oval frame; Carry out Kalman's estimation, speed and accuracy in order to provide new image cut zone to detect, circulate according to this again.Wherein, Fig. 4 be this example be applied to traffic flow investigate previous moment in system and current time the variance prediction and revise schematic diagram; Fig. 5 is the workflow schematic diagram of this routine vehicle tracking sub-step.
Stage 5: track generates and the track aftertreatment.The disposal route of real time data and picture bag can realize by following program.
typedef?struct?DetailDataHeader
{
Int nJPGLen; //jpeg picture length
Int nWidth, nHeight; // picture width, the picture height
Int nObjCnt; // target data number
Int nEvtCnt; // event data number
Int nOrient; //Jpeg image direction
ULONG ulFrames; // visual frame number
_ TIME_STAMP stamp; // timestamp
}DetailDataHeader;
Disposal route to target data can realize by following program.
typedef?struct?ObjData
{
DWORD dwFlag; // sign
Int nID; // Target id;
Int x, y; // target barycenter image coordinate
Int width, height; The image coordinate width of // target and height
Float fWidth; // target developed width, world coordinates width after namely demarcating, unit rice
Float fSpeed; // target velocity m/s
Int type; // target type, 0-vehicle, 1 pedestrian, 2 abandons, 3 bicycles
Int nPlateType; // car plate type
Int nBelieve; // recognition confidence
Char szPlate[16]; // the number-plate number
Int nRoad; Track, // target place
DWORD EvtMask; The event mask that // target once occurred
Int nArea; // target region
}ObjData;
Disposal route to event data can realize by following program.
typedef?struct?EvtData
{
DWORD dwFlag; // sign
Int nID; // Target id number
DWORD dwEvent; // event
Int nRoad; // track
DWORD dwTraficFlag; // lights state
Float dbVelocity; // speed m/s
LONGLONG llPicID; // associated 832 normal pictures
Char AppendData[16]; // event additional data
}?EvtData;
By above program, can be found out, this routine described analytic statistics step is that track generates and the track aftertreatment, comprise the analysis to target data number, event data number and timestamp, described target data number comprises ID, barycenter image coordinate, image coordinate width, image coordinate height, speed, type, track, place and the region of target; Described event data number comprises sign, Target id number, event, track, lights state, speed and event additional data.
The form that this routine described output step is exported comprises short-term observation report and long-term observation report, and the data of described short-term observation report comprise that the 5min volume of traffic, the daytime 12h volume of traffic, peak hour traffic, peak hour flow ratio, peak hour factor, road direction distribution coefficient, the busy direction volume of traffic account for ratio and right-hand rotation, craspedodrome and the left-hand bend wagon flow ratio that adds up to the volume of traffic; The data of described long-term observation report comprise annual average daily traffic, all average daily traffic volumes, monthly average daily traffic, the annual moon volume of traffic, year the highest hourly traffic volume, the 30th maximum annual hourly volume, the 30th volume of traffic coefficient, month volume of traffic variation factor and all daily traffic volume variation factors.
Compared with prior art, this routine beneficial effect is, by HD video to vehicle and detect, and then realization is to investigation and the analyzing and processing of traffic flow, can obtain the traffic data that multiple precision is very high, not only can significantly reduce the field investigation workload, not affect traffic but also have, data acquisition and analyzing and processing process can repeat as required, but traffic live material long preservation; On this basis, the technical matters that the present invention has also overcome that unmanned plane (UAV) video jitter, the video sensor on gathering transport information moves along with the high-speed motion of unmanned plane, background is complicated in the video sequence image, moving target information is various etc. brings, statistical function with the whole magnitudes of traffic flow on the direction of 12 of crossings, can sum up the rule of blocking up and forming and dissipating, for the control measures that block up such as intersection signal timing optimization, traffic channelling improvement provide Data support.
Above content is in conjunction with concrete preferred implementation further description made for the present invention, can not assert that specific embodiment of the invention is confined to these explanations.For the general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, can also make some simple deduction or replace, all should be considered as belonging to protection scope of the present invention.
Claims (10)
1. the traffic flow based on unmanned plane HD video method of investigating, is characterized in that, comprises the following steps:
The video acquisition step, hover over selected urban road intersection top by unmanned plane, and take HD video;
Steady picture pre-treatment step, copy HD video and surely look like pre-service, exports sequence of pictures;
Detect tracing step, using surely as after sequence of pictures as coming source data to carry out detection and the tracking to moving object;
The analytic statistics step, carry out wagon flow quantitative analysis and statistics to the Target id that tracks and the current coordinates of motion; And,
The output step, be transferred to Client GUI by the statistics of vehicle flowrate and show, and generated data and form.
2. the traffic flow based on the unmanned plane HD video according to claim 1 method of investigating, it is characterized in that, describedly surely as pre-treatment step, comprise following sub-step: step 1, current frame image is carried out to translation, Rotation and Zoom, make itself and former frame image there is no difference, and the motion-vector of current frame image and former frame image is write to journal file; Step 2, carry out translation, Rotation and Zoom according to journal file to current frame image.
3. the traffic flow based on the unmanned plane HD video according to claim 2 method of investigating, it is characterized in that, described steady step 1 as pre-treatment step is: at first, search the violent shake of current frame image and former frame image, downscaled images displacement calculating amount; Then, the image dwindled is carried out respectively to the amplification of twice and four times, the displacement size of meticulous these image blocks of adjusting is until find the motion-vector of original image.
4. described traffic flow based on the unmanned plane HD video method of investigating according to the claims 1 to 3 any one, is characterized in that, described detection tracing step comprises following sub-step:
The noise reduction process sub-step, adopt median filtering method to carry out noise reduction process to gray level image;
The binary conversion treatment sub-step, adopt the threshold segmentation method to carry out binary conversion treatment to image;
The vehicle detection sub-step, adopt the background subtraction point-score to carry out vehicle detection; And,
The vehicle tracking sub-step, follow the tracks of vehicle by the agglomerate that comprises vehicle identifiers, position and size.
5. the traffic flow based on the unmanned plane HD video according to claim 4 method of investigating, it is characterized in that, described noise reduction process sub-step is first carried out the calculating of maximal value, intermediate value and minimum value to each column data in sequence of pictures, then maximal value, intermediate value and minimum value are got to the output pixel value of mean as the filtering result.
6. the traffic flow based on the unmanned plane HD video according to claim 4 method of investigating, is characterized in that, described binary conversion treatment sub-step presets threshold value T, according to
Image is divided into to two pixel groups that are greater than T and are less than T.
7. the traffic flow based on the unmanned plane HD video according to claim 4 method of investigating, it is characterized in that, described vehicle detection sub-step is first chosen the average image as a setting of piece image at least in background, then the present frame of successive image sequence and background image are subtracted each other, carry out the background cancellation; When resulting pixel count is greater than while presetting threshold value T, judge in observed scene moving target is arranged.
8. the traffic flow based on the unmanned plane HD video according to claim 4 method of investigating, it is characterized in that, described vehicle tracking sub-step is: candidate pixel is carried out to image and cut apart, judge that this pixel of cutting apart image belongs to target, background or other zones, the pixel that will have same characteristic features assembles a zone; Use contour area to identify vehicle as characteristic quantity, the same moving target of images different in the video flowing sequence is connected, indicate by oval frame; Carry out Kalman's estimation, speed and accuracy in order to provide new image cut zone to detect, circulate according to this.
9. the traffic flow based on the unmanned plane HD video according to claim 4 method of investigating, it is characterized in that, described analytic statistics step is that track generates and the track aftertreatment, comprise the analysis to target data number, event data number and timestamp, described target data number comprises ID, barycenter image coordinate, image coordinate width, image coordinate height, speed, type, track, place and the region of target; Described event data number comprises sign, Target id number, event, track, lights state, speed and event additional data.
10. the traffic flow based on the unmanned plane HD video according to claim 9 method of investigating, it is characterized in that, the form that described output step is exported comprises short-term observation report and long-term observation report, and the data of described short-term observation report comprise that the 5min volume of traffic, the daytime 12h volume of traffic, peak hour traffic, peak hour flow ratio, peak hour factor, road direction distribution coefficient, the busy direction volume of traffic account for ratio and right-hand rotation, craspedodrome and the left-hand bend wagon flow ratio that adds up to the volume of traffic; The data of described long-term observation report comprise annual average daily traffic, all average daily traffic volumes, monthly average daily traffic, the annual moon volume of traffic, year the highest hourly traffic volume, the 30th maximum annual hourly volume, the 30th volume of traffic coefficient, month volume of traffic variation factor and all daily traffic volume variation factors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310375004.3A CN103413444B (en) | 2013-08-26 | 2013-08-26 | A kind of traffic flow based on unmanned plane HD video is investigated method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310375004.3A CN103413444B (en) | 2013-08-26 | 2013-08-26 | A kind of traffic flow based on unmanned plane HD video is investigated method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103413444A true CN103413444A (en) | 2013-11-27 |
| CN103413444B CN103413444B (en) | 2015-08-19 |
Family
ID=49606449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310375004.3A Active CN103413444B (en) | 2013-08-26 | 2013-08-26 | A kind of traffic flow based on unmanned plane HD video is investigated method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103413444B (en) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632535A (en) * | 2013-11-19 | 2014-03-12 | 河海大学 | Judgment method for section pedestrian crossing signal lamp arrangement |
| CN103730015A (en) * | 2013-12-27 | 2014-04-16 | 株洲南车时代电气股份有限公司 | Method and device for detecting traffic flow at intersection |
| CN103778790A (en) * | 2014-01-13 | 2014-05-07 | 杭州电子科技大学 | Traffic flow square-wave statistical method based on video sequence |
| CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN104157165A (en) * | 2014-08-11 | 2014-11-19 | 江苏恒创软件有限公司 | Unmanned helicopter-based urban area motor vehicle parking planning method |
| CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
| CN104269054A (en) * | 2014-09-20 | 2015-01-07 | 无锡北斗星通信息科技有限公司 | Road segment traffic index estimation system based on unmanned aerial vehicle measurement |
| CN105321342A (en) * | 2015-12-07 | 2016-02-10 | 北京航空航天大学 | Intersection vehicle queuing length detection method based on aerial video |
| CN105528891A (en) * | 2016-01-13 | 2016-04-27 | 深圳市中盟科技有限公司 | Traffic flow density detection method and system based on unmanned aerial vehicle monitoring |
| CN105957341A (en) * | 2016-05-30 | 2016-09-21 | 重庆大学 | Wide area traffic jam detection method based on unmanned plane airborne platform |
| CN106030666A (en) * | 2013-12-20 | 2016-10-12 | 珀肯斯公司 | Traffic monitoring and surveillance system and method, and corresponding traffic infraction recording system and unmanned air vehicle |
| CN106056624A (en) * | 2016-05-24 | 2016-10-26 | 西北工业大学 | Unmanned aerial vehicle high-definition image small target detecting and tracking system and detecting and tracking method thereof |
| US9505494B1 (en) | 2015-04-30 | 2016-11-29 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| WO2017041303A1 (en) * | 2015-09-11 | 2017-03-16 | SZ DJI Technology Co., Ltd. | Systems and methods for detecting and tracking movable objects |
| CN106791439A (en) * | 2017-01-22 | 2017-05-31 | 陕西外号信息技术有限公司 | A kind of stabilization compensation method of optical label |
| WO2017114503A1 (en) * | 2015-12-31 | 2017-07-06 | Wellen Sham | Facilitating communication with a vehicle via a uav |
| CN107005397A (en) * | 2015-11-23 | 2017-08-01 | 深圳市大疆创新科技有限公司 | The data syn-chronization of flight equipment and method, device and the flight equipment of collection |
| CN107248296A (en) * | 2017-07-13 | 2017-10-13 | 南京航空航天大学 | A kind of video traffic flow statistical method based on unmanned plane and temporal aspect |
| CN107808524A (en) * | 2017-11-30 | 2018-03-16 | 中山大学 | A kind of intersection vehicle checking method based on unmanned plane |
| CN108009494A (en) * | 2017-11-30 | 2018-05-08 | 中山大学 | A kind of intersection wireless vehicle tracking based on unmanned plane |
| CN108320510A (en) * | 2018-04-03 | 2018-07-24 | 深圳市智绘科技有限公司 | One kind being based on unmanned plane video traffic information statistical method and system |
| CN108364466A (en) * | 2018-02-11 | 2018-08-03 | 金陵科技学院 | A kind of statistical method of traffic flow based on unmanned plane traffic video |
| CN108399745A (en) * | 2018-03-01 | 2018-08-14 | 北京航空航天大学合肥创新研究院 | A kind of city road network trend prediction method at times based on unmanned plane |
| CN108564787A (en) * | 2018-05-31 | 2018-09-21 | 北京理工大学 | Traffic observation procedure, system and equipment based on Floating Car method |
| CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
| US10102586B1 (en) | 2015-04-30 | 2018-10-16 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| CN108694829A (en) * | 2018-03-27 | 2018-10-23 | 西安科技大学 | Magnitude of traffic flow identification monitoring network based on unmanned aerial vehicle group mobile platform and method |
| CN109003451A (en) * | 2018-07-04 | 2018-12-14 | 北京航空航天大学 | A kind of intersection OD matrix estimation method based on low latitude unmanned plane |
| CN109118767A (en) * | 2018-09-05 | 2019-01-01 | 盐城骏拔汽车零部件有限公司 | Intelligent transportation system based on unmanned plane |
| CN109658688A (en) * | 2017-10-11 | 2019-04-19 | 深圳市哈工大交通电子技术有限公司 | The detection method and device of access connection traffic flow based on deep learning |
| CN110278717A (en) * | 2018-01-22 | 2019-09-24 | 深圳市大疆创新科技有限公司 | Control the method and apparatus of aircraft flight |
| CN110889971A (en) * | 2019-11-08 | 2020-03-17 | 合肥宜拾惠网络科技有限公司 | Intelligent vehicle finding method and device for parking lot |
| CN111201496A (en) * | 2017-10-05 | 2020-05-26 | 图森有限公司 | System and method for aerial video traffic analysis |
| CN112037579A (en) * | 2019-06-03 | 2020-12-04 | 索尼公司 | Monitoring vehicle movement to mitigate traffic risks |
| CN112735164A (en) * | 2020-12-25 | 2021-04-30 | 北京智能车联产业创新中心有限公司 | Test data construction method and test method |
| US11140326B2 (en) | 2015-05-22 | 2021-10-05 | The United States Of America, As Represented By The Secretary Of The Navy | Aerial video based point, distance, and velocity real-time measurement system |
| CN113706932A (en) * | 2021-10-29 | 2021-11-26 | 天津云圣智能科技有限责任公司 | Road section safety warning method and device and unmanned aerial vehicle |
| CN117315934A (en) * | 2023-09-25 | 2023-12-29 | 阜阳交通能源投资有限公司 | Expressway traffic flow real-time monitoring and congestion prediction system based on unmanned aerial vehicle |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11120481A (en) * | 1997-10-17 | 1999-04-30 | Mitsubishi Heavy Ind Ltd | Traffic flow measuring device |
| CN101009021A (en) * | 2007-01-25 | 2007-08-01 | 复旦大学 | Video stabilizing method based on matching and tracking of characteristic |
| JP2009087316A (en) * | 2007-09-11 | 2009-04-23 | Hitachi Ltd | Traffic flow measurement system |
| CN101968924A (en) * | 2010-10-19 | 2011-02-09 | 北方工业大学 | High-resolution image-based real-time traffic flow detection method |
| CN102073846A (en) * | 2010-12-15 | 2011-05-25 | 同济大学 | Method for acquiring traffic information based on aerial images |
| CN102289940A (en) * | 2011-07-26 | 2011-12-21 | 西南交通大学 | Hybrid differential-based traffic flow detection method |
| CN102436738A (en) * | 2011-09-26 | 2012-05-02 | 同济大学 | Traffic monitoring device based on unmanned aerial vehicle (UAV) |
| CN102496276A (en) * | 2011-12-01 | 2012-06-13 | 青岛海信网络科技股份有限公司 | High efficiency vehicle detection method |
| CN102509287A (en) * | 2011-10-12 | 2012-06-20 | 西安理工大学 | Finding method for static target based on latitude and longitude positioning and image registration |
-
2013
- 2013-08-26 CN CN201310375004.3A patent/CN103413444B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11120481A (en) * | 1997-10-17 | 1999-04-30 | Mitsubishi Heavy Ind Ltd | Traffic flow measuring device |
| CN101009021A (en) * | 2007-01-25 | 2007-08-01 | 复旦大学 | Video stabilizing method based on matching and tracking of characteristic |
| JP2009087316A (en) * | 2007-09-11 | 2009-04-23 | Hitachi Ltd | Traffic flow measurement system |
| CN101968924A (en) * | 2010-10-19 | 2011-02-09 | 北方工业大学 | High-resolution image-based real-time traffic flow detection method |
| CN102073846A (en) * | 2010-12-15 | 2011-05-25 | 同济大学 | Method for acquiring traffic information based on aerial images |
| CN102289940A (en) * | 2011-07-26 | 2011-12-21 | 西南交通大学 | Hybrid differential-based traffic flow detection method |
| CN102436738A (en) * | 2011-09-26 | 2012-05-02 | 同济大学 | Traffic monitoring device based on unmanned aerial vehicle (UAV) |
| CN102509287A (en) * | 2011-10-12 | 2012-06-20 | 西安理工大学 | Finding method for static target based on latitude and longitude positioning and image registration |
| CN102496276A (en) * | 2011-12-01 | 2012-06-13 | 青岛海信网络科技股份有限公司 | High efficiency vehicle detection method |
Non-Patent Citations (1)
| Title |
|---|
| 詹峰群: "基于OpenCV的视频道路车辆检测与跟踪", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (60)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632535B (en) * | 2013-11-19 | 2015-06-10 | 河海大学 | Judgment method for section pedestrian crossing signal lamp arrangement |
| CN103632535A (en) * | 2013-11-19 | 2014-03-12 | 河海大学 | Judgment method for section pedestrian crossing signal lamp arrangement |
| CN106030666A (en) * | 2013-12-20 | 2016-10-12 | 珀肯斯公司 | Traffic monitoring and surveillance system and method, and corresponding traffic infraction recording system and unmanned air vehicle |
| CN106030666B (en) * | 2013-12-20 | 2019-07-23 | 珀肯斯公司 | Traffic monitoring and monitoring system and method and corresponding traffic violations record system and unmanned plane |
| CN103730015B (en) * | 2013-12-27 | 2016-01-20 | 株洲南车时代电气股份有限公司 | Intersection traffic flow detecting method and device |
| CN103730015A (en) * | 2013-12-27 | 2014-04-16 | 株洲南车时代电气股份有限公司 | Method and device for detecting traffic flow at intersection |
| CN103778790A (en) * | 2014-01-13 | 2014-05-07 | 杭州电子科技大学 | Traffic flow square-wave statistical method based on video sequence |
| CN103778790B (en) * | 2014-01-13 | 2015-08-12 | 杭州电子科技大学 | A kind of vehicle flowrate square wave statistic law based on video sequence |
| CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN104134222B (en) * | 2014-07-09 | 2017-02-15 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN104157165B (en) * | 2014-08-11 | 2016-07-06 | 江苏恒创软件有限公司 | A kind of urban area motor vehicle parking planing method based on unmanned plane |
| CN104157165A (en) * | 2014-08-11 | 2014-11-19 | 江苏恒创软件有限公司 | Unmanned helicopter-based urban area motor vehicle parking planning method |
| CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
| CN104821084A (en) * | 2014-09-20 | 2015-08-05 | 李福军 | Road section traffic index estimation system based on unmanned aerial vehicle measurement |
| CN104821084B (en) * | 2014-09-20 | 2017-01-18 | 罗普特（厦门）科技集团有限公司 | Road section traffic index estimation system based on unmanned aerial vehicle measurement |
| CN104269054A (en) * | 2014-09-20 | 2015-01-07 | 无锡北斗星通信息科技有限公司 | Road segment traffic index estimation system based on unmanned aerial vehicle measurement |
| US11869090B1 (en) | 2015-04-30 | 2024-01-09 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| US10223753B1 (en) | 2015-04-30 | 2019-03-05 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| US11010837B1 (en) | 2015-04-30 | 2021-05-18 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| US9505494B1 (en) | 2015-04-30 | 2016-11-29 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| US10102586B1 (en) | 2015-04-30 | 2018-10-16 | Allstate Insurance Company | Enhanced unmanned aerial vehicles for damage inspection |
| US11140326B2 (en) | 2015-05-22 | 2021-10-05 | The United States Of America, As Represented By The Secretary Of The Navy | Aerial video based point, distance, and velocity real-time measurement system |
| WO2017041303A1 (en) * | 2015-09-11 | 2017-03-16 | SZ DJI Technology Co., Ltd. | Systems and methods for detecting and tracking movable objects |
| CN108139757A (en) * | 2015-09-11 | 2018-06-08 | 深圳市大疆创新科技有限公司 | For the system and method for detect and track loose impediment |
| US11206123B2 (en) | 2015-11-23 | 2021-12-21 | SZ DJI Technology Co., Ltd. | Method and device of data synchronization and data collection for aerial vehicle and aerial vehicle |
| CN107005397A (en) * | 2015-11-23 | 2017-08-01 | 深圳市大疆创新科技有限公司 | The data syn-chronization of flight equipment and method, device and the flight equipment of collection |
| US10938544B2 (en) | 2015-11-23 | 2021-03-02 | SZ DJI Technology Co., Ltd. | Method and device of data synchronization and data collection for aerial vehicle and aerial vehicle |
| CN105321342A (en) * | 2015-12-07 | 2016-02-10 | 北京航空航天大学 | Intersection vehicle queuing length detection method based on aerial video |
| CN105321342B (en) * | 2015-12-07 | 2017-11-21 | 北京航空航天大学 | A kind of intersection vehicles queue length detection method based on video of taking photo by plane |
| WO2017114503A1 (en) * | 2015-12-31 | 2017-07-06 | Wellen Sham | Facilitating communication with a vehicle via a uav |
| CN105528891A (en) * | 2016-01-13 | 2016-04-27 | 深圳市中盟科技有限公司 | Traffic flow density detection method and system based on unmanned aerial vehicle monitoring |
| CN106056624A (en) * | 2016-05-24 | 2016-10-26 | 西北工业大学 | Unmanned aerial vehicle high-definition image small target detecting and tracking system and detecting and tracking method thereof |
| CN105957341A (en) * | 2016-05-30 | 2016-09-21 | 重庆大学 | Wide area traffic jam detection method based on unmanned plane airborne platform |
| CN106791439A (en) * | 2017-01-22 | 2017-05-31 | 陕西外号信息技术有限公司 | A kind of stabilization compensation method of optical label |
| CN106791439B (en) * | 2017-01-22 | 2019-09-10 | 陕西外号信息技术有限公司 | A kind of stabilization compensation method of optical label |
| CN107248296A (en) * | 2017-07-13 | 2017-10-13 | 南京航空航天大学 | A kind of video traffic flow statistical method based on unmanned plane and temporal aspect |
| CN111201496B (en) * | 2017-10-05 | 2023-06-30 | 图森有限公司 | System and method for aerial video traffic analysis |
| CN111201496A (en) * | 2017-10-05 | 2020-05-26 | 图森有限公司 | System and method for aerial video traffic analysis |
| CN109658688A (en) * | 2017-10-11 | 2019-04-19 | 深圳市哈工大交通电子技术有限公司 | The detection method and device of access connection traffic flow based on deep learning |
| CN107808524B (en) * | 2017-11-30 | 2021-09-24 | 中山大学 | Road intersection vehicle detection method based on unmanned aerial vehicle |
| CN108009494A (en) * | 2017-11-30 | 2018-05-08 | 中山大学 | A kind of intersection wireless vehicle tracking based on unmanned plane |
| CN107808524A (en) * | 2017-11-30 | 2018-03-16 | 中山大学 | A kind of intersection vehicle checking method based on unmanned plane |
| CN110278717A (en) * | 2018-01-22 | 2019-09-24 | 深圳市大疆创新科技有限公司 | Control the method and apparatus of aircraft flight |
| CN108364466B (en) * | 2018-02-11 | 2021-01-26 | 金陵科技学院 | Traffic flow statistical method based on unmanned aerial vehicle traffic video |
| CN108364466A (en) * | 2018-02-11 | 2018-08-03 | 金陵科技学院 | A kind of statistical method of traffic flow based on unmanned plane traffic video |
| CN108399745A (en) * | 2018-03-01 | 2018-08-14 | 北京航空航天大学合肥创新研究院 | A kind of city road network trend prediction method at times based on unmanned plane |
| CN108694829B (en) * | 2018-03-27 | 2021-08-13 | 西安科技大学 | Traffic flow identification monitoring network and method based on unmanned aerial vehicle group mobile platform |
| CN108694829A (en) * | 2018-03-27 | 2018-10-23 | 西安科技大学 | Magnitude of traffic flow identification monitoring network based on unmanned aerial vehicle group mobile platform and method |
| CN108320510A (en) * | 2018-04-03 | 2018-07-24 | 深圳市智绘科技有限公司 | One kind being based on unmanned plane video traffic information statistical method and system |
| CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
| CN108564787A (en) * | 2018-05-31 | 2018-09-21 | 北京理工大学 | Traffic observation procedure, system and equipment based on Floating Car method |
| CN109003451A (en) * | 2018-07-04 | 2018-12-14 | 北京航空航天大学 | A kind of intersection OD matrix estimation method based on low latitude unmanned plane |
| CN109118767A (en) * | 2018-09-05 | 2019-01-01 | 盐城骏拔汽车零部件有限公司 | Intelligent transportation system based on unmanned plane |
| US11820400B2 (en) | 2019-06-03 | 2023-11-21 | Sony Corporation | Monitoring vehicle movement for traffic risk mitigation |
| CN112037579A (en) * | 2019-06-03 | 2020-12-04 | 索尼公司 | Monitoring vehicle movement to mitigate traffic risks |
| CN110889971A (en) * | 2019-11-08 | 2020-03-17 | 合肥宜拾惠网络科技有限公司 | Intelligent vehicle finding method and device for parking lot |
| CN112735164A (en) * | 2020-12-25 | 2021-04-30 | 北京智能车联产业创新中心有限公司 | Test data construction method and test method |
| CN113706932A (en) * | 2021-10-29 | 2021-11-26 | 天津云圣智能科技有限责任公司 | Road section safety warning method and device and unmanned aerial vehicle |
| CN113706932B (en) * | 2021-10-29 | 2022-02-25 | 天津云圣智能科技有限责任公司 | Road section safety warning method and device and unmanned aerial vehicle |
| CN117315934A (en) * | 2023-09-25 | 2023-12-29 | 阜阳交通能源投资有限公司 | Expressway traffic flow real-time monitoring and congestion prediction system based on unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103413444B (en) | 2015-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103413444B (en) | A kind of traffic flow based on unmanned plane HD video is investigated method | |
| Uke et al. | Moving vehicle detection for measuring traffic count using opencv | |
| CN111899227A (en) | Automatic railway fastener defect acquisition and identification method based on unmanned aerial vehicle operation | |
| CN110633610B (en) | Student state detection method based on YOLO | |
| CN103345840B (en) | Road incidents video detecting method is crossed at a kind of cross channel crossing | |
| CN104506804A (en) | Device and method for monitoring abnormal behavior of motor vehicle on expressway | |
| CN116434159A (en) | Traffic flow statistics method based on improved YOLO V7 and Deep-Sort | |
| CN105243354B (en) | A kind of vehicle checking method based on target feature point | |
| CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
| Xu et al. | Ground plane context aggregation network for day-and-night on vehicular pedestrian detection | |
| Cheng et al. | Semantic segmentation of road profiles for efficient sensing in autonomous driving | |
| Li et al. | Intelligent transportation video tracking technology based on computer and image processing technology | |
| CN101877135A (en) | Moving target detecting method based on background reconstruction | |
| CN116152696A (en) | Intelligent security image identification method and system for industrial control system | |
| Yu et al. | LCNet: a light-weight network for object counting | |
| WO2023105800A1 (en) | Object detection device, object detection method, and object detection system | |
| Neto et al. | Computer-vision-based surveillance of intelligent transportation systems | |
| CN114694078A (en) | Traffic behavior judgment method based on multi-target tracking | |
| Glasl et al. | Video based traffic congestion prediction on an embedded system | |
| CN110427911B (en) | Road detection method, device, equipment and storage medium | |
| Bi et al. | Real-time traffic flow statistics based on dual-granularity classification | |
| Liu et al. | Research on vehicle target detection technology based on UAV aerial images | |
| Kadiķis et al. | Efficient video processing method for traffic monitoring combining motion detection and background subtraction | |
| Vujović et al. | Traffic video surveillance in different weather conditions | |
| Jehad et al. | Developing and validating a real time video based traffic counting and classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |