CN102426785A - Traffic flow information perception method based on contour and local characteristic point and system thereof - Google Patents
Traffic flow information perception method based on contour and local characteristic point and system thereof Download PDFInfo
- Publication number
- CN102426785A CN102426785A CN201110367452XA CN201110367452A CN102426785A CN 102426785 A CN102426785 A CN 102426785A CN 201110367452X A CN201110367452X A CN 201110367452XA CN 201110367452 A CN201110367452 A CN 201110367452A CN 102426785 A CN102426785 A CN 102426785A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- frame
- trail
- car
- information
- 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, which belongs to the intelligent transport field, discloses a traffic flow information perception method based on a contour and a local characteristic point and a system thereof. In the invention, through remote control, a parameter of an analytic algorithm can be configured. According to a concrete scene, the various kinds of parameters of the analytic algorithm can be set or adjusted at any time, which gives great convenience to use a traffic flow information perception apparatus. In the invention, for tracking a vehicle, rough tracking based on contour information and evaluation are used, and the tracking based on the local characteristic point is selectively performed. A tracking strategy, which is from coarse to minute, can be adaptive to the different traffic scenes and an execution efficiency is high. The traffic flow information perception method and the apparatus in the invention can be directly used in an intelligent transport system (ITS).
Description
Technical field
The invention belongs to intelligent transportation field; Relate to transport information flow awareness technology, relate in particular to the transport information flow awareness method and system of the tracking of a kind of location, tracking and target local feature point based on the image object contour area based on Long-distance Control, video signal.
Background technology
Along with the develop rapidly of national economy, the mobile vehicle fleet size in the whole nation is increasing, and traffic system also faces great pressure.Intelligent transportation system has obtained development at a high speed in recent years under such background, especially in freeway facility.Intelligent transportation system (Intelligent Transport System; Be called for short ITS) be to apply to whole traffic management system with infotech, data communication transmission technology, electronic sensor technology, electron controls technology and Computer Processing technology etc. are integrated effectively; And set up a kind of on a large scale in, comprehensive playing a role, in real time, comprehensive transportation and management system accurately and efficiently.
At present nationwide highway and relevant highway infrastructure, control measures are all very sound.Most highway deploy omnidistance supervisory system, this makes supervision department more comprehensive to the grasp of the car flow information of highway, highway operation situation, has also guaranteed high speed, safety, the operation management economically of highway.
But all there is the problem of a general character in these systems, and that is exactly that their detection means mainly relies on annular magnetic test coil, video frequency pick-up head, equipment such as transmission cable even microwave detector, radar.Wherein, annular magnetic test coil is used to detect quantity, size and the speed of a motor vehicle etc. of vehicular traffic, generally need be embedded in undergroundly, and the whole cross section of highway is laid, and it is very high to lay cost, rapid wear and troublesome maintenance; Video frequency pick-up head is used to take the real-time traffic scene, and transfers to Surveillance center's demonstration through transmission cable.These expensive equipment are all inapplicable to China's Class I highway, Class II highway, because one-level, Class II highway coverage are big, do not have the economic return source, and lay and safeguard that the cost of checkout equipment and web-transporting device is too big.
Poverty-stricken in the face of traffic pressure and the traditional solution of weightening finish day by day, Class I highway, Class II highway need the one-tenth of effective checkout equipment, while equipment should be low as far as possible.In recent years, rise gradually based on the traffic flow detection method of video, it is low to lay cost on the one hand based on the detection method of video, is easy to maintenance and repair; In addition, sensing range is big, and a general check point only needs a camera just can cover.On the other hand, through the video image of video analysis Algorithm Analysis camera collection, thereby can obtain telecommunication flow information equally.
In order to address this problem, make full use of ripe video processnig algorithms based on the traffic flow detection method of video analysis, accurately detect, analyze the motion conditions of each vehicle.Traditional analytical algorithm based on video generally comprises based on the vehicle detection of motion detection with based on the car speed of virtual detection line and detects, and wherein motion detection generally includes background subtraction method and frame-to-frame differences method.But these methods can't adapt to scene complicated and changeable, and accuracy of detection is not high.
Summary of the invention
Given this; Primary and foremost purpose of the present invention is to a kind of telecommunication flow information cognitive method based on profile and local unique point is provided; This method combines multiple common video analysis algorithm; The thought that employing is learnt from other's strong points to offset one's weaknesses and the strategy of multilevel policy decision can have higher execution efficient and robustness according to the adjustment of traffic scene self-adaptation.This method specifically may further comprise the steps:
The systematic parameter of Remote configuration telecommunication flow information sensory perceptual system comprises on region of interest ROI (region of interest writes a Chinese character in simplified form ROI) and the video image of video analysis the transformational relation F between the space length on the pixel distance and real road;
Vision signal is carried out frame-to-frame differences operation, the frame-to-frame differences image is carried out shape filtering, and on this basis the position of each car is positioned;
According to the positional information of vehicle, each car is followed the trail of the dynamical state of each car of design point storage organization Memory record respectively;
Estimate following the trail of the result;
Based on evaluation result, if follow the trail of the good inadequately characteristic point of then extracting the vehicle of following the trail of failure of result, characteristic point is followed the trail of based on the characteristic point tracing algorithm, and based on the state of following the trail of each car in the update mode storage organization as a result; If follow the trail of the state of each car in the enough good then direct update mode storage organization of result;
Calculate information of vehicles;
Information of vehicles to gathering in a period of time gathers, generates the transport information stream file, and regularly sends the transport information stream file to server.
Another object of the present invention is to provide a kind of telecommunication flow information sensory perceptual system, it is characterized in that said system comprises based on profile and local unique point:
Far-end server 2000: the systematic parameter to long-range telecommunication flow information sensory perceptual system is configured, and generates parameter configuration files at node, and the video data of gathering after video also will be gathered outputs to video analytics subsystem 2100;
Video analytics subsystem 2100: through video data is carried out sequence of operations, calculate information of vehicles, and the information of vehicles of gathering in a period of time is gathered, generates the transport information stream file, regularly send the transport information stream file to far-end server;
Wherein, video analytics subsystem 2100 comprises:
Inter-frame difference, morphological filter 2110: vision signal is carried out the frame-to-frame differences operation, the frame-to-frame differences image is carried out binaryzation, carry out shape filtering then;
Vehicle ' s contour zone location device 2120: the position to each car on the basis of filtered image positions;
Tracking performance decision device 2140: estimate to following the trail of the result;
Vehicle local feature point extraction apparatus 2150: the unique point of extracting the vehicle of following the trail of failure;
Beneficial effect: the telecommunication flow information cognitive method of following the trail of based on image object contour area and local unique point of the present invention and system adjust the camera posture, confirm the area-of-interest of video analysis through Long-distance Control; Adopt the rough position of traditional frame difference method and shape filtering detection vehicle, and carry out rough car tracing according to the position; Through a vital Evaluation Mechanism, rough tracking result is done Performance Evaluation after this; Algorithm after optionally carrying out according to assessment result again based on local feature point.The present invention is configured through the parameter of Long-distance Control to analytical algorithm, can be provided with or adjust the various parameters of analytical algorithm according to concrete scene at any time, and this is very easy to the use of telecommunication flow information sensing device.Among the present invention the rough tracking based on profile information, evaluation are at first adopted in the tracking of vehicle; And optionally carry out tracking based on local feature point; The different traffic scene of this pursive strategy from coarse to fine ability self-adaptation, and improved execution efficient.
Description of drawings
Fig. 1 is the telecommunication flow information cognitive method process flow diagram based on profile and local unique point of the present invention;
Fig. 2 realizes the process flow diagram of Remote configuration systematic parameter for the present invention;
Fig. 3 realizes vision signal is carried out the frame-to-frame differences operation, the frame-to-frame differences image is carried out shape filtering for the present invention, and the process flow diagram that on this basis position of each car is positioned;
Fig. 4 follows the trail of respectively each car for the present invention realizes the positional information according to vehicle, the process flow diagram of the dynamical state of each car of design point storage organization record;
Fig. 5 realizes estimating following the trail of the result for the present invention, and based on the flow chart of the state of each car in the evaluation result update mode storage organization;
Fig. 6 realizes the information of vehicles of gathering in a period of time is gathered, generates the transport information stream file for the present invention, and regularly sends the process flow diagram of transport information stream file to server;
Fig. 7 is the block scheme of the telecommunication flow information sensory perceptual system of following the trail of based on image object contour area and local unique point of the present invention, and each mark meaning is following among the figure: far-end server 2000, video analytics subsystem 2100, inter-frame difference, morphological filter 2110, vehicle ' s contour zone location device 2120, the tracker 2130 based on the vehicle ' s contour zone, tracking performance decision device 2140, vehicle local feature point extraction apparatus 2150, based on the tracker 2160 of vehicle local feature.
Embodiment
As shown in Figure 1, comprise the steps: based on the telecommunication flow information cognitive method of profile and local unique point
The systematic parameter of Remote configuration telecommunication flow information sensory perceptual system comprises on region of interest ROI and the video image of video analysis the transformational relation F between the space length on the pixel distance and real road;
Vision signal is carried out frame-to-frame differences operation, the frame-to-frame differences image is carried out binaryzation, carry out shape filtering then, and on this basis the position of each car is positioned;
According to the positional information of vehicle, each car is followed the trail of the dynamical state of each car of design point storage organization Memory record respectively;
Estimate following the trail of the result;
Based on evaluation result, if follow the trail of the good inadequately characteristic point of then extracting the vehicle of following the trail of failure of result, characteristic point is followed the trail of based on the characteristic point tracing algorithm, and based on the state of following the trail of each car in the update mode storage organization as a result; If follow the trail of the state of each car in the enough good then direct update mode storage organization of result;
The information of vehicles that comprises information such as vehicle size, the speed of a motor vehicle according to calculating such as following the trail of the information that vehicle obtains, the systematic parameter of Remote configuration;
Information of vehicles to gathering in a period of time gathers, generates the transport information stream file, and regularly sends the transport information stream file to server.
The realization flow of Remote configuration systematic parameter is as shown in Figure 2, comprising:
Step 101:, but make viewing area reach best through the posture of Long-distance Control adjustment video signal collective camera;
Step 102: after the fixing camera posture, the telecommunication flow information sensory perceptual system sends a video pictures to server end;
Step 103:, confirm the region of interest ROI of video analysis through the mode of manual work intervention at far-end server;
Step 104: at far-end server, the mode that gets involved through manual work is calculated on the video image transformational relation F between the space length on the pixel distance and real road;
Step 105: ROI information and transformational relation F are sent to telecommunication flow information perception and apparatus system as the systematic parameter of perception and apparatus system.
The present invention realizes vision signal is carried out the frame-to-frame differences operation, the frame-to-frame differences image is carried out shape filtering, and the flow process that on this basis position of each car is positioned is as shown in Figure 3, comprising:
Step 201: video analytic system obtains image sequence from vision signal; To image sequence do following frame-to-frame differences operation: dI (t)=| I (t)-I (t-1) |, the time label of t representative graph picture frame wherein, I (t) expression t image constantly; It is present image; I (t-1) is the former frame image, and dI (t) is the frame-to-frame differences image, is specially the image of the absolute value formation of two frame differences;
Step 202: the frame-to-frame differences result is carried out binaryzation: with the threshold value T of image binaryzation
1=20 is example, and if dI (t, i, j)＞20, dI (t, i then; J) ← 0, otherwise dI (t, i, j) ← 255, wherein; I presentation video pixel column number, j presentation video pixel column number, I (t, i, j) expression t time chart picture in the position (i; J) pixel value, dI (t, i, j) be t frame-to-frame differences image constantly in the position (i, the pixel value on j);
Step 203: on 202 basis as a result, dI (t) is carried out shape filtering, promptly traditional opening operation and closed operation;
Step 204: on 203 basis as a result, confirm the position of each car, the steps include:
(1) in 203 results, seeking pixel value is 0 connected region, and goes out each together with the zone with circumscribed rectangle frame, and these rectangles are designated as { S
1..., S
n, n is the number of connected region;
(2) with threshold value T
2=10, T
2'=100 are example, remove { S
1..., S
nIn area less than 100 and greater than 10 rectangle, that is, think that the corresponding rectangle size of vehicle is moderate, remove excessive or too small rectangle;
(3) with threshold value T
3=10 is example, on the basis of (2) will between distance merge into same rectangle less than two rectangles of 10, that is, think that the distance between the vehicle is bigger, two rectangles that lean on nearerly in fact corresponding same car;
The rectangle that (4) will finally stay is as the existence zone { V of vehicle
1..., V
k, k is the quantity of detected vehicle.
According to the positional information of vehicle, each car to be followed the trail of respectively, the flow process of the dynamical state of each car of design point storage organization record is as shown in Figure 4, comprises the steps:
Step 301: set up state storage structure Memory; For example comprise 50 mnemons among the Memory, be designated as mem_cell_1 ...; Mem_cell_50}; Storage unit is used to be stored in the dynamical state of the car in the ROI scope, comprises the position in picture of vehicle, the records such as size in picture, thinks that here the number that is in the vehicle in the ROI scope is less than 50;
Step 302: the position of at first expecting appearance according to historic state prediction vehicle in present frame of the vehicle in each mnemon; For example adopt linear prediction method: the two frame historical position (10 of supposing a car of record among the mem_cell_1; 20) and (11; 30), then the position that can calculate roughly this vehicle of present frame of the method through linear prediction is (12,40);
Step 303: the position of detected vehicle is { V in the present frame
1..., V
K (t), the number of detected vehicle in k (t) the expression present frame is mated the predicted position of vehicle in each mnemon of these zones and Memory, and for example mate according to Euclidean distance: supposing has vehicle registration among current mem_cell_1 and the mem_cell_2; And predicted position is respectively (12,40) and (22,70); The position of the vehicle that current detection arrives is (11,42) and (22,68); Then can judge (11,42) and (12,40) coupling according to Euclidean distance; And (22,68) are complementary with (22,70);
Fig. 5 realizes estimating following the trail of the result for the present invention; And according to evaluation result; If follow the trail of the good inadequately unique point of then extracting the vehicle of following the trail of failure of result, according to the unique point tracing algorithm unique point is followed the trail of, and according to the state of following the trail of each car in the update mode storage organization as a result; If follow the trail of the process flow diagram of the state of each car in the enough good then direct update mode storage organization of result, comprise the steps:
Step 403. is if M '=k (t) representes that the vehicle number does not change among the ROI, and each car is all followed the trail of;
Step 404. is as if M '＞k (t), and the vehicle that expressed possibility does not detect, and perhaps has vehicle to leave the ROI zone.This does further judgement through following step 410.
Step 406: extract the Harris unique point { Pf that follows the trail of the vehicle of failure among the Memory
1 1..., Pf
N1 1..., { Pf
1 L..., Pf
NL L, wherein L representes to follow the trail of the number of the vehicle of failure, { Pf
1 i..., Pf
Ni iI the unique point of vehicle in previous frame of following the trail of failure of expression;
Step 407: utilize unique point tracing algorithm KLT (Kanade-Lucas-Tomasi) algorithm, at { P
1... P
N (t)Middle unique point of following the trail of the vehicle of each tracking failure;
Step 408: for { Pf
1 i..., Pf
Ni i, the number of establishing the unique point that successfully tracks in the step 407 is s
i, s
i≤N
1, with threshold value T
4=0.6 is example, if s
i/ N
i＞0.6, think that then i car followed the trail of successfully through local feature point tracking method among the Memory, otherwise tracking is failed;
Step 409: based on the characteristic point of following the trail of successful vehicle in the step 408; And the change in location situation of the characteristic point that is complementary with it; Infer the motion conditions of this vehicle; Construct the state of vehicle in present frame on this basis, and the structure result is added in the corresponding stored unit among the Memory;
Step 410: up to the present,,, judge that then this vehicle left the ROI zone, simultaneously this information of vehicles is moved to cache file if the predicted position of vehicle is in the boundary vicinity of ROI to above two kinds of vehicles that method for tracing all lost efficacy among the Memory; Otherwise thinking has vehicle to fail correctly to track;
On this basis, calculate the information of vehicle, comprise comprising the steps: vehicle size, the speed of a motor vehicle etc. according to following the trail of the information that vehicle obtains, the systematic parameter of Remote configuration etc.
According to size and the picture position that in abovementioned steps 104, obtains and the transformation relation F between the physical location of the rectangular area of the vehicle that writes down in the cache file, calculate the actual size of vehicle;
According to the situation of change of the vehicle that writes down in cache file position in ROI, the transformation relation F between combining image position and the physical location calculates the movement velocity of vehicle.
The present invention realizes the information of vehicles of gathering in a period of time is gathered, generates the transport information stream file, and regularly as shown in Figure 6 to the flow process of server transmission transport information stream file, comprising:
Step 501. pair information of vehicles cache file is put in order, and adds additional information, like system label, zero-time etc., forms the transport information stream file;
Step 502. is sent to server end through network with this transport information stream file.
Telecommunication flow information sensory perceptual system block diagram based on image object contour area and the tracking of local unique point of the present invention is as shown in Figure 7, and this system comprises
Far-end server 2000: the systematic parameter to long-range telecommunication flow information sensory perceptual system is configured, and generates parameter configuration files at node, and the video data of gathering after video also will be gathered outputs to video analytics subsystem 2100;
Video analytics subsystem 2100: through video data being carried out operations such as inter-frame difference, shape filtering, vehicle ' s contour location, tracking performance judgement, the extraction of vehicle local feature and the tracking of vehicle local feature; Calculate information of vehicles; Comprise vehicle size, the speed of a motor vehicle etc.; And the information of vehicles of gathering in a period of time gathered, generates the transport information stream file, regularly send the transport information stream file to far-end server;
Wherein, video analytics subsystem 2100 comprises:
Inter-frame difference, morphological filter 2110: vision signal is carried out the frame-to-frame differences operation, the frame-to-frame differences image is carried out binaryzation, carry out shape filtering then;
Vehicle ' s contour zone location device 2120: the position to each car on the basis of filtered image positions;
Tracking performance decision device 2140: estimate to following the trail of the result;
Vehicle local feature point extraction apparatus 2150: the unique point of extracting the vehicle of following the trail of failure;
Above content is to combine optimum implementation to the further explain that the present invention did, and can not assert that practical implementation of the present invention is confined to these explanations.It should be appreciated by those skilled in the art, under the situation that does not break away from the spirit and scope of the present invention that limit appended claims, can also carry out the various modifications on form and the details, all should be regarded as belonging to protection scope of the present invention it.
Claims (9)
1. telecommunication flow information cognitive method based on profile and local unique point is characterized in that may further comprise the steps:
The systematic parameter of Remote configuration telecommunication flow information sensory perceptual system comprises on region of interest ROI and the video image of video analysis the transformational relation between the space length on the pixel distance and real road
F
Vision signal is carried out frame-to-frame differences operation, the frame-to-frame differences image is carried out binaryzation, carry out shape filtering then, and on this basis the position of each car is positioned;
According to the positional information of vehicle, each car is followed the trail of the dynamical state of each car of design point storage organization Memory record respectively;
Estimate following the trail of the result;
Based on evaluation result, if follow the trail of the good inadequately characteristic point of then extracting the vehicle of following the trail of failure of result, characteristic point is followed the trail of based on the characteristic point tracing algorithm, and based on the state of following the trail of each car in the update mode storage organization as a result; If follow the trail of the state of each car in the enough good then direct update mode storage organization of result;
Calculate information of vehicles;
Information of vehicles to gathering in a period of time gathers, generates the transport information stream file, and regularly sends the transport information stream file to server.
2. method according to claim 1 is characterized in that, the method for the systematic parameter of Remote configuration telecommunication flow information sensory perceptual system is:
101:, but make viewing area reach best through the posture of Long-distance Control adjustment video signal collective camera;
102: after the fixing camera posture, system sends a video pictures to server end;
103:, confirm the region of interest ROI of video analysis through the mode of manual work intervention at far-end server;
104: at far-end server, the mode that gets involved through manual work is calculated on the video image transformational relation between the space length on the pixel distance and real road
F
105: with ROI information and transformational relation
FBe sent to system as systematic parameter.
3. method according to claim 1 is characterized in that, vision signal is carried out frame-to-frame differences operation, the frame-to-frame differences image is carried out binaryzation, carries out shape filtering then, and the method that on this basis position of each car is positioned is:
201: from vision signal, obtain image sequence, image sequence is made following frame-to-frame differences operation: d
I(
t)=|
I(
t) –
I(
t-1) |, wherein
tThe time label of representative graph picture frame,
I(
t) expression
tImage constantly, i.e. present image,
I(
t-1) is the former frame image, d
I(
t) be the frame-to-frame differences image, be specially the image of the absolute value formation of two frame-to-frame differencess;
202: the frame-to-frame differences result is carried out binaryzation: if d
I(
t;
i,
j)>
T 1, d then
I(
t;
i,
j) ← 0, otherwise d
I(
t;
i,
j) ← 255, wherein,
iPresentation video pixel column number,
jPresentation video pixel column number,
I(
t;
i,
J)Expression
tThe time chart picture in the position (
i,
j) pixel value, d
I(
t;
i,
j) do
tFrame-to-frame differences image constantly in the position (
i,
j) on pixel value;
T 1Threshold value for image binaryzation;
203: on 202 basis as a result, to frame-to-frame differences image d
I(
t) carry out shape filtering, promptly traditional opening operation and closed operation;
204: on 203 basis as a result, confirm the position of each car, the steps include:
(1) in 203 results, seeking pixel value is 0 connected region, and goes out each connected region with circumscribed rectangle frame, these rectangles are designated as
S 1...,
S n ,
nNumber for connected region;
(2) remove
S 1...,
S n In area less than
T 2 ' And greater than
T 2Rectangle, wherein
T 2, T 2 ' Be setting
The area threshold of rectangular area,
T 2 ' It is bigger,
T 2Less
(3) on the basis of (2) will between the distance less than
T 3Two rectangles merge into same rectangle, its
Middle T
3Distance threshold for the center, two rectangular areas that is provided with;
The rectangle that (4) will finally stay as the existence zone of vehicle be vehicle the position
V 1...,
V k ,
k
Quantity for detected vehicle.
4. method according to claim 1 is characterized in that, according to the positional information of vehicle, each car is followed the trail of respectively, and the method for the dynamical state of each car of design point storage organization record is:
301: set up state storage structure Memory, comprise M storage unit among the Memory, be designated as { mem_cell_1;, mem_cell_M}, storage unit is used to be stored in the dynamical state of the car in the ROI scope; The M here is a constant, and greater than the number that is in the vehicle in the ROI scope;
302: the position of at first expecting appearance according to historic state prediction vehicle in present frame of the vehicle in each storage unit;
303: in the present frame position of detected vehicle do
V 1...,
V k(
t)
,
k(
t) quantity of detected vehicle in the expression present frame, the predicted position of vehicle in each storage unit of these zones and Memory is mated;
304., the successful information of vehicles of coupling in its present frame is added among the Memory in the storage unit of correspondence and goes according to matching result.
5. method according to claim 1 is characterized in that, the method that the tracking result is estimated is:
401. current vehicle quantity does
k(
t), suppose that it is M ' that the storage unit number of record is arranged in Memory, M '<m, M are the contained storage unit number of Memory, if M '≤
k(
t), then be evaluated as " enough good ", otherwise be evaluated as " good inadequately ";
402. if M '＜
k(
t), expression has new vehicle or noise to appear among the ROI this moment, then emerging vehicle is added in the new storage unit among the Memory;
403. if M '=
k(
t), the vehicle number does not change among the expression ROI, and each car is all followed the trail of;
404. if M '＞
k(
t), the vehicle that expressed possibility does not detect, and perhaps has vehicle to leave the ROI zone.
6. method according to claim 1; It is characterized in that, according to evaluation result, if it is good inadequately to follow the trail of the result; Then extract the unique point of following the trail of the vehicle of failure among the Memory; Utilize unique point tracing algorithm tracking feature point in the ROI of present frame scope, and according to the state of following the trail of each car in the update mode storage organization as a result, its method is:
405: the Harris unique point in the ROI zone of extraction present frame
P 1,
P N(
t)
,
N(
t) be the number of unique point among the ROI;
406: the Harris unique point of the vehicle of tracking failure among the extraction Memory
Pf 1 1...,
Pf N1
1..., {
Pf 1 L...,
Pf NL
L,
Pf 1 i...,
Pf Ni
iI the unique point of vehicle in previous frame of following the trail of failure of expression, wherein i=1 ... L, L represent to follow the trail of the number of the vehicle of failure;
407: utilize unique point tracing algorithm KLT algorithm,
P 1,
P N(
t)
Middle unique point of following the trail of the vehicle of each tracking failure;
408: for
Pf 1 i...,
Pf Ni
i, the number of establishing the unique point that successfully tracks in 407 is s
i, s
i≤
NIf i is s
i/
NI>
T 4Think that then i car followed the trail of successfully through local feature point tracking method among the Memory, otherwise tracking fails, wherein
NI is the unique point number of i car, T
4Be the unique point that successfully tracks and the ratio of unique point number;
409: based on the characteristic point of following the trail of successful vehicle in the step 408; And the change in location situation of the characteristic point that is complementary with it; Infer the motion conditions of this vehicle, construct the state of vehicle in present frame on this basis, and the structure result is added in the corresponding stored unit among the Memory;
410: up to the present, the vehicle that above-mentioned method for tracing among the Memory was all lost efficacy if the predicted position of vehicle is in the boundary vicinity of ROI, judges that then this vehicle left the ROI zone, simultaneously this information of vehicles is moved to cache file; Otherwise thinking has vehicle to fail correctly to track.
7. method according to claim 1 is characterized in that, the method for calculating information of vehicles is:
According to the size of the rectangular area of the vehicle that writes down in the cache file and the transformation relation F between picture position and the physical location, calculate the actual size of vehicle;
According to the situation of change of the vehicle that writes down in cache file position in ROI, the transformation relation F between combining image position and the physical location calculates the movement velocity of vehicle.
8. method according to claim 1; It is characterized in that; System puts, adds additional information in order to the information of vehicles cache file in a period of time and forms the transport information stream file in a period of time, and timing to the process that server sends the transport information stream file is:
501. the information of vehicles cache file is put in order, and is added additional information, form the transport information stream file;
502. this transport information stream file is sent to server end through network.
9. telecommunication flow information sensory perceptual system based on profile and local unique point is characterized in that said system comprises:
Far-end server (2000): the systematic parameter to long-range telecommunication flow information sensory perceptual system is configured, and generates parameter configuration files at node, and the video data of gathering after video also will be gathered outputs to video analytics subsystem (2100);
Video analytics subsystem (2100): through video data is carried out sequence of operations, calculate information of vehicles, and the information of vehicles of gathering in a period of time is gathered, generates the transport information stream file, regularly send the transport information stream file to far-end server;
Wherein, video analytics subsystem (2100) comprising:
Inter-frame difference, morphological filter (2110): vision signal is carried out the frame-to-frame differences operation,, carry out shape filtering then to the frame-to-frame differences image binaryzation;
Vehicle ' s contour zone location device (2120): the position to each car on the basis of filtered image positions;
Tracker (2130) based on the vehicle ' s contour zone:, each car is followed the trail of the dynamical state of each car of design point storage organization record respectively according to the positional information of vehicle;
Tracking performance decision device (2140): estimate to following the trail of the result;
Vehicle local feature point extraction apparatus (2150): the unique point of extracting the vehicle of following the trail of failure;
Tracker (2160) based on the vehicle local feature: according to the unique point tracing algorithm unique point is followed the trail of, and according to the state of following the trail of each car in the update mode storage organization as a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110367452XA CN102426785B (en) | 2011-11-18 | 2011-11-18 | Traffic flow information perception method based on contour and local characteristic point and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110367452XA CN102426785B (en) | 2011-11-18 | 2011-11-18 | Traffic flow information perception method based on contour and local characteristic point and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102426785A true CN102426785A (en) | 2012-04-25 |
| CN102426785B CN102426785B (en) | 2013-11-27 |
Family
ID=45960762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110367452XA Expired - Fee Related CN102426785B (en) | 2011-11-18 | 2011-11-18 | Traffic flow information perception method based on contour and local characteristic point and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102426785B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093528A (en) * | 2012-12-28 | 2013-05-08 | 中山大学 | Intelligent system for monitoring vehicles and people in community |
| CN103295015A (en) * | 2013-06-25 | 2013-09-11 | 中国人民解放军国防科学技术大学 | Method for extracting local feature points of partially-occluded object |
| CN103297754A (en) * | 2013-05-02 | 2013-09-11 | 上海交通大学 | Monitoring video self-adaption interesting area coding system |
| CN104702982A (en) * | 2013-12-20 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and system for configuring algorithms for video analysis equipment |
| CN106446790A (en) * | 2016-08-30 | 2017-02-22 | 上海交通大学 | Method for tracking and analyzing traffic video flow of fixed camera |
| CN107909032A (en) * | 2017-11-15 | 2018-04-13 | 重庆邮电大学 | A kind of behavioral value and recognition methods based on single sample |
| CN108337486A (en) * | 2018-04-19 | 2018-07-27 | 北京软通智城科技有限公司 | A kind of device and method of the video analysis of the algorithm configuration based on scene |
| CN108571928A (en) * | 2018-04-13 | 2018-09-25 | 桂林电子科技大学 | A kind of intermediate plate anchorage dimensional defects detection method based on machine vision |
| CN108758728A (en) * | 2018-03-29 | 2018-11-06 | 青岛海尔智能技术研发有限公司 | A kind of range hood control method and range hood based on impetus |
| CN110718061A (en) * | 2019-10-17 | 2020-01-21 | 长沙理工大学 | Traffic intersection vehicle flow statistical method and device, storage medium and electronic equipment |
| CN111126261A (en) * | 2019-12-23 | 2020-05-08 | 珠海深圳清华大学研究院创新中心 | Video data analysis method and device, raspberry group device and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308607A (en) * | 2008-06-25 | 2008-11-19 | 河海大学 | Moving target tracking method by multiple features integration under traffic environment based on video |
| CN101800890A (en) * | 2010-04-08 | 2010-08-11 | 北京航空航天大学 | Multiple vehicle video tracking method in expressway monitoring scene |
| CN102034355A (en) * | 2010-12-28 | 2011-04-27 | 丁天 | Feature point matching-based vehicle detecting and tracking method |
-
2011
- 2011-11-18 CN CN201110367452XA patent/CN102426785B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308607A (en) * | 2008-06-25 | 2008-11-19 | 河海大学 | Moving target tracking method by multiple features integration under traffic environment based on video |
| CN101800890A (en) * | 2010-04-08 | 2010-08-11 | 北京航空航天大学 | Multiple vehicle video tracking method in expressway monitoring scene |
| CN102034355A (en) * | 2010-12-28 | 2011-04-27 | 丁天 | Feature point matching-based vehicle detecting and tracking method |
Non-Patent Citations (3)
| Title |
|---|
| 唐宜清等: "视频监控中一种完整提取运动目标的检测算法", 《计算技术与自动化》 * |
| 张娟等: "运动目标跟踪算法研究", 《计算机应用研究》 * |
| 翟海涛: "基于交通视频的车辆检测跟踪及分类技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093528A (en) * | 2012-12-28 | 2013-05-08 | 中山大学 | Intelligent system for monitoring vehicles and people in community |
| CN103297754A (en) * | 2013-05-02 | 2013-09-11 | 上海交通大学 | Monitoring video self-adaption interesting area coding system |
| CN103297754B (en) * | 2013-05-02 | 2016-06-01 | 上海交通大学 | A kind of monitor video self-adaptation encoding region of interest system |
| CN103295015B (en) * | 2013-06-25 | 2016-02-03 | 中国人民解放军国防科学技术大学 | The local feature point extracting method of partial occlusion target |
| CN103295015A (en) * | 2013-06-25 | 2013-09-11 | 中国人民解放军国防科学技术大学 | Method for extracting local feature points of partially-occluded object |
| CN104702982B (en) * | 2013-12-20 | 2018-01-05 | 杭州海康威视数字技术股份有限公司 | A kind of algorithm configuration method and system of video analysis equipment |
| WO2015090099A1 (en) * | 2013-12-20 | 2015-06-25 | 杭州海康威视数字技术股份有限公司 | Algorithm configuration method and system |
| CN104702982A (en) * | 2013-12-20 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and system for configuring algorithms for video analysis equipment |
| CN106446790A (en) * | 2016-08-30 | 2017-02-22 | 上海交通大学 | Method for tracking and analyzing traffic video flow of fixed camera |
| CN107909032A (en) * | 2017-11-15 | 2018-04-13 | 重庆邮电大学 | A kind of behavioral value and recognition methods based on single sample |
| CN108758728A (en) * | 2018-03-29 | 2018-11-06 | 青岛海尔智能技术研发有限公司 | A kind of range hood control method and range hood based on impetus |
| CN108758728B (en) * | 2018-03-29 | 2023-02-17 | 青岛海尔智能技术研发有限公司 | Head gesture-based range hood control method and range hood |
| CN108571928A (en) * | 2018-04-13 | 2018-09-25 | 桂林电子科技大学 | A kind of intermediate plate anchorage dimensional defects detection method based on machine vision |
| CN108337486A (en) * | 2018-04-19 | 2018-07-27 | 北京软通智城科技有限公司 | A kind of device and method of the video analysis of the algorithm configuration based on scene |
| CN110718061A (en) * | 2019-10-17 | 2020-01-21 | 长沙理工大学 | Traffic intersection vehicle flow statistical method and device, storage medium and electronic equipment |
| CN111126261A (en) * | 2019-12-23 | 2020-05-08 | 珠海深圳清华大学研究院创新中心 | Video data analysis method and device, raspberry group device and readable storage medium |
| CN111126261B (en) * | 2019-12-23 | 2023-05-26 | 珠海深圳清华大学研究院创新中心 | Video data analysis method and device, raspberry group device and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102426785B (en) | 2013-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
| Mukojima et al. | Moving camera background-subtraction for obstacle detection on railway tracks | |
| CN102622895B (en) | Video-based vehicle speed detecting method | |
| CN103927878B (en) | A kind of automatic shooting device for parking offense and automatically grasp shoot method | |
| CN102622886B (en) | Video-based method for detecting violation lane-changing incident of vehicle | |
| CN101458871B (en) | Intelligent traffic analysis system and application system thereof | |
| KR101375583B1 (en) | Object Density Estimation in Video | |
| CN101510356B (en) | Video detection system and data processing device thereof, video detection method | |
| CN103366569B (en) | The method and system of real-time grasp shoot traffic violation vehicle | |
| CN102324183B (en) | Method for detecting and shooting vehicle based on composite virtual coil | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
| Pan et al. | Traffic surveillance system for vehicle flow detection | |
| CN103208190B (en) | Traffic flow detection method based on object detection | |
| CN102496281B (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| CN102393901B (en) | Traffic flow information perception method based on hybrid characteristic and system thereof | |
| CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
| CN105513342A (en) | Video-tracking-based vehicle queuing length calculating method | |
| CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
| Kulkarni et al. | Real time vehicle detection, tracking and counting using Raspberry-Pi | |
| CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
| CN107480653A (en) | passenger flow volume detection method based on computer vision | |
| CN103150908A (en) | Average vehicle speed detecting method based on video | |
| CN104134067A (en) | Road vehicle monitoring system based on intelligent visual Internet of Things |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131127 Termination date: 20161118 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |