CN102436739A - Traffic jam discrimination method in expressway toll plaza based on video detection technology - Google Patents

Traffic jam discrimination method in expressway toll plaza based on video detection technology Download PDF

Info

Publication number
CN102436739A
CN102436739A CN2011102895309A CN201110289530A CN102436739A CN 102436739 A CN102436739 A CN 102436739A CN 2011102895309 A CN2011102895309 A CN 2011102895309A CN 201110289530 A CN201110289530 A CN 201110289530A CN 102436739 A CN102436739 A CN 102436739A
Authority
CN
China
Prior art keywords
frame
congestion
toll plaza
image
energy value
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
Application number
CN2011102895309A
Other languages
Chinese (zh)
Other versions
CN102436739B (en
Inventor
赵敏
孙棣华
刘卫宁
唐毅
廖孝勇
郑林江
陈虹颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Kunshan Silaimu Energy Saving Technology Co ltd
Original Assignee
Chongqing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University filed Critical Chongqing University
Priority to CN 201110289530 priority Critical patent/CN102436739B/en
Publication of CN102436739A publication Critical patent/CN102436739A/en
Application granted granted Critical
Publication of CN102436739B publication Critical patent/CN102436739B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Traffic Control Systems (AREA)
  • Devices For Checking Fares Or Tickets At Control Points (AREA)

Abstract

本发明涉及道路交通状态检测技术领域，具体公开了一种基于视频检测技术的高速公路收费广场交通拥堵判别方法，包括如下步骤：1)摄取收费广场道路视频；2)从视频中提取收费广场道路的图片；3)建立并更新图片的背景模型；4)从图片中提取前景图像；5)获取前景图像的能量值及能量值变化量绝对值，判断收费广场道路是否拥堵。本发明仅用获取道路能量值参数，构建拥堵判别模型，便完成了对高速公路收费广场拥堵状态的判断，算法简单，运算开销小，实时性强，可准确、高效地解决高速公路收费广场交通拥堵的判别问题，并在拥堵时刻输出拥堵警告，从而为管理者及时把握现场状况、做出管理决策提供有力的信息支撑，进而减少交通通行安全隐患。

Figure 201110289530

The present invention relates to the technical field of road traffic state detection, and specifically discloses a method for distinguishing traffic congestion in a highway toll plaza based on video detection technology, comprising the following steps: 1) capturing a video of a toll plaza road; 2) extracting a picture of the toll plaza road from the video; 3) establishing and updating a background model of the picture; 4) extracting a foreground image from the picture; 5) obtaining the energy value of the foreground image and the absolute value of the energy value change, and judging whether the toll plaza road is congested. The present invention only needs to obtain road energy value parameters and construct a congestion discrimination model to complete the judgment of the congestion state of the highway toll plaza. The algorithm is simple, the computational overhead is small, and the real-time performance is strong. The problem of distinguishing traffic congestion in the highway toll plaza can be accurately and efficiently solved, and a congestion warning can be output at the time of congestion, thereby providing strong information support for managers to grasp the on-site conditions in a timely manner and make management decisions, thereby reducing traffic safety hazards.

Figure 201110289530

Description

Expressway tol lcollection square traffic jam judging method based on video detection technology
Technical field
The present invention relates to road traffic state detection technique field, be specifically related to a kind of expressway tol lcollection square traffic jam judging method based on video detection technology.
Background technology
Along with the fast development of China's economic construction, highway operation mileage increases fast, and current vehicle on highway quantity sharply increases, and the potential safety hazard of freeway toll station also increases thereupon.The special road section that assemble as vehicle on the expressway tol lcollection square, traffic safety problem is particularly outstanding.Particularly in the peak traffic period, vehicle is prone to stand in a long queue in the toll plaza and occurs blocking up, and has influenced the driving behavior of driver in the toll plaza, and it selects the behavior in short track service time to cause traffic conflict aggravation between the vehicle, causes traffic hazard then.Therefore, the incident of blocking up on very first time monitoring expressway tol lcollection square and the on-the-spot supervision of reinforcement charge have great significance to the traffic safety of safeguarding the toll plaza.Simultaneously, often there are many enchancement factors in the generation of incident because the toll plaza blocks up, and therefore can not rely on the time period to delimit the vehicle peak period merely, and should come to monitor out in real time the congestion status on expressway tol lcollection square through scientific and technical means.
At present, utilize the video monitoring system of toll plaza, realized real time record toll plaza vehicle turnover situation, type of vehicle etc.But to the block up discovery of incident of toll plaza, remain by the staff and observe sequence of video images, realize, the block up automatic detection of incident of the toll plaza of being unrealized through manual supervisory mode.Therefore, how to utilize video detection technology to detect the congestion status of toll plaza in real time automatically, make management decision in real time, improve charge station's service level and have great significance for the traffic operation and management person.
Existing road traffic based on video detection technology blocks up event detecting method through obtaining a large amount of traffic behavior parameters; As: flow, roadway occupancy, speed, following distance, queue length etc., choose a plurality of parameters then and utilize traditional blocking up to differentiate the detection of algorithm realization the road traffic congestion incident.This method requires to utilize image processing techniques to calculate a plurality of parameters, realizes complicatedly, and expense is bigger, is unfavorable for realizing that the carrying out to the congestion in road incident monitor in real time.And in the disclosed document, find to have toll plaza based on the video detection technology event detecting method that blocks up as yet at home and abroad.
Therefore; Need the method for a kind of automatic detection toll plaza congestion event badly; Realization to the toll plaza block up incident in time, reliable detection, for the supvr in time holds field conditions, makes management decision strong information support is provided, and then reduce the current potential safety hazard of traffic.
Summary of the invention
In view of this, it is little, real-time to the invention provides a kind of computing expense, based on the expressway tol lcollection square traffic jam judging method of video detection technology.
The objective of the invention is to realize through following technical scheme: the expressway tol lcollection square traffic jam judging method based on video detection technology comprises the steps:
1) picked-up toll plaza road video;
2) picture of extraction toll plaza road from video;
3) background model of foundation and renewal picture;
4) from picture, extract foreground image;
5) obtain the energy value and the energy value variable quantity absolute value of foreground image, judge that whether current frame image is the toll plaza image that blocks up.
Further, said step 3) specifically comprises the steps:
31) pass through N 0Open the picture of toll plaza road, ask for initial background with averaging method, N 0＞20;
32) setting threshold, passing threshold is judged, from initial background, is extracted background;
33) with step 32) background extracted sets up and update background module.
Further, in the said step 4),, utilize method of difference from picture, to extract foreground image according to the background model that step 3) obtains.
Further, step 5) specifically comprises the steps:
51) obtain the energy value Energy (k) of the foreground image of present frame k frame;
52) obtain the absolute value delta Energy (k) of difference of energy value of foreground image of foreground image and the former frame k-1 frame of present frame k frame, in like manner obtain Δ Energy (k-1), Δ Energy (k-2);
53) judge that Energy (k) whether greater than threshold value T1, in this way, then carries out next step; As not, judge that then the k frame is the non-frame that blocks up;
54) whether the absolute value delta Energy (k) of difference of energy value of foreground image of foreground image and former frame k-1 frame that judges present frame k frame in this way, then carries out next step less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up;
55) whether the absolute value delta Energy (k-1) of difference of energy value of foreground image of foreground image and former frame k-2 frame that judges the k-1 frame in this way, then carries out next step less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up;
56) whether the absolute value delta Energy (k-2) of difference of energy value of foreground image of foreground image and former frame k-3 frame that judges the k-2 frame in this way, then judges k frame for block up frame less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up.
Further, T1=0.48, T2=0.076.
Further, comprise also said step 2) that the picture with the toll plaza road that extracts is converted into the step of gray scale picture by colour picture.
Further, in the said step 4), also comprise the step of the foreground image that is extracted being carried out the morphological method denoising.
Further, in the step 5), the method for energy value of obtaining foreground image is following: the definition image sequence does K is a frame number, and N is the totalframes of video, and then difference image is dif k(x, y)=fr k(x, y)-fr K-1(x, y); For k frame difference image dif k(x y), calculates its global threshold level, again this difference image is carried out binary conversion treatment, forces to convert into bianry image; Difference image after the binaryzation that obtains does
Figure BDA0000094560530000032
It has m * n pixel; Energy through the difference image after this binaryzation of computes:
E ( DB ( k , i , j ) i = 1 , j = 1 m × n ) = 1 m × n ( Σ i = 1 m Σ j = 1 n b ( i , j ) )
Wherein (i is that (i, value j) are the energy value of this point to pixel j) to b.
Further, also have the following steps after the step 5):
6) whether according to the differentiation result that blocks up of k two field picture in the step 5), differentiating the current detection cycle is that the toll plaza blocks up the cycle, and concrete steps are following:
With 10 seconds be a sense cycle, in this sense cycle, surpass 90% picture frame and be the frame that blocks up, then mark should be the cycle of blocking up in the cycle, otherwise, then be labeled as non-blocking up the cycle.
Further, also comprise the steps:
7), judge whether current toll plaza road blocks up, and correspondingly export or the releasing warning information that it specifically comprises the steps: according to the differentiation result that blocks up in current detection cycle in the step 6)
71) set up moving window ballot model, with 10 seconds be a sense cycle, the capacity of definition moving window is 6 cycles, when there being 3 and above cycle judgement toll plaza when blocking up the cycle to block up in the moving window, otherwise is non-congestion status.
72) voting results of comparison current period and the voting results of last one-period, if the voting results of last one-period are non-congestion status, and the voting results of current period are congestion status, then export the warning of blocking up; If the voting results of last one-period are congestion status, and the voting results of current period are non-congestion status, then removed the warning of blocking up.
The invention has the beneficial effects as follows: the differentiation problem that can solve expressway tol lcollection square traffic congestion accurately and efficiently; And in the output constantly of the blocking up warning of blocking up; Thereby in time hold field conditions for the supvr, make management decision strong information support is provided, and then reduce the current potential safety hazard of traffic.The present invention is directed to traditional road traffic method of discrimination that blocks up and need obtain a large amount of traffic behavior parameters, the computing expense is big, the shortcoming that real-time is not strong; The present invention is only with obtaining road energy value parameter; The structure discrimination model that blocks up has just been accomplished the judgement to expressway tol lcollection square congestion status, and algorithm is simple; The computing expense is little, and is real-time.
Other advantages of the present invention, target and characteristic will be set forth in instructions subsequently to a certain extent; And to a certain extent; Based on being conspicuous to those skilled in the art, perhaps can from practice of the present invention, obtain instruction to investigating of hereinafter.Target of the present invention and other advantages can realize and obtain through following instructions and claims.
Description of drawings
Fig. 1 shows the software processes schematic flow sheet based on the expressway tol lcollection square traffic jam judging method of video detection technology;
Fig. 2 shows step 5), 6), 7) schematic flow sheet, i.e. traffic jam judging process flow diagram;
Fig. 3 shows the sequential chart of energy value variable quantity absolute value;
Fig. 4 shows the sequential chart of energy value;
Fig. 5 shows actual congestion status output.
Embodiment
Below will carry out detailed description to the preferred embodiments of the present invention.Should be appreciated that preferred embodiment has been merely explanation the present invention, rather than in order to limit protection scope of the present invention.
Referring to Fig. 1, the expressway tol lcollection square traffic jam judging method based on video detection technology comprises the steps:
1) picked-up toll plaza road video;
2) from video, extract the picture of toll plaza road, and convert it into gray scale picture by colour picture;
3) background model of foundation and renewal picture; Specifically comprise the steps:
31) pass through N 0Open the picture of toll plaza road, ask for initial background with averaging method;
32) setting threshold, passing threshold is judged, from initial background, is extracted background;
33) with step 32) background extracted sets up and update background module.
4) from picture, extract foreground image, utilize method of difference from picture, to extract foreground image, and the foreground image that is extracted is carried out the step of morphological method denoising;
5) obtain the energy value and the energy value variable quantity absolute value of foreground image, judge that whether current frame image is the toll plaza image that blocks up.Specifically comprise the steps:
51) obtain the energy value Energy (k) of the foreground image of present frame k frame.The method of energy value Energy (k) of obtaining foreground image is following: the definition image sequence does
Figure BDA0000094560530000051
K is a frame number, and N is the totalframes of video, and then difference image is dif k(x, y)=fr k(x, y)-fr K-1(x, y); For k frame difference image dif k(x y), calculates its global threshold level, again this difference image is carried out binary conversion treatment, forces to convert into bianry image; Difference image after the binaryzation that obtains does
Figure BDA0000094560530000061
It has m * n pixel; Energy through the difference image after this binaryzation of computes:
E ( DB ( k , i , j ) i = 1 , j = 1 m × n ) = 1 m × n ( Σ i = 1 m Σ j = 1 n b ( i , j ) )
Wherein (i is that (i, value j) are the energy value of this point to pixel j) to b.
52) obtain the absolute value delta Energy (k) of difference of energy value of foreground image of foreground image and the former frame k-1 frame of present frame k frame, in like manner obtain Δ Energy (k-1), Δ Energy (k-2);
53) judge that Energy (k) whether greater than threshold value T1, in this way, then carries out next step; As not, judge that then the k frame is the non-frame that blocks up;
54) whether the absolute value delta Energy (k) of difference of energy value of foreground image of foreground image and former frame k-1 frame that judges present frame k frame in this way, then carries out next step less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up;
55) whether the absolute value delta Energy (k-1) of difference of energy value of foreground image of foreground image and former frame k-2 frame that judges the k-1 frame in this way, then carries out next step less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up;
56) whether the absolute value delta Energy (k-2) of difference of energy value of foreground image of foreground image and former frame k-3 frame that judges the k-2 frame in this way, then judges k frame for block up frame less than threshold value T2; As not, judge that then the k frame is the non-frame that blocks up.
6) whether according to the differentiation result that blocks up of k two field picture in the step 5), differentiating the current detection cycle is that the toll plaza blocks up the cycle, and concrete steps are following:
With 10 seconds be a sense cycle, in this sense cycle, surpass 90% picture frame and be the frame that blocks up, then mark should be the cycle of blocking up in the cycle, otherwise, then be labeled as non-blocking up the cycle.
Further, also comprise the steps:
7), judge whether current toll plaza road blocks up, and correspondingly export or the releasing warning information that it specifically comprises the steps: according to the differentiation result that blocks up in current detection cycle in the step 6)
71) set up moving window ballot model, with 10 seconds be a sense cycle, the capacity of definition moving window is 6 cycles, when there being 3 and above cycle judgement toll plaza when blocking up the cycle to block up in the moving window, otherwise is non-congestion status.
72) voting results of comparison current period and the voting results of last one-period, if the voting results of last one-period are non-congestion status, and the voting results of current period are congestion status, then export the warning of blocking up; If the voting results of last one-period are congestion status, and the voting results of current period are non-congestion status, then removed the warning of blocking up.
T1 and T2 obtain through experiment, T1=0.48 in the present embodiment, T2=0.076.
Above-mentioned steps 5), schematic flow sheet 6), 7) (being the traffic jam judging process flow diagram) is referring to Fig. 2.
In Fig. 2, as Energy (k)＞T 1, Δ Energy (k)＜T 2, Δ Energy (k-1)＜T 2, Δ Energy (k-2)＜T 2When these four conditions are set up simultaneously, represent that the energy value of k frame is higher, and three consecutive frame k-1 before it, k-2, the energy value variable quantity absolute value of k-3 is less.Then the k frame is for blocking up frame, and the corresponding energy value of this frame of mark is red.
Further whether according to the differentiation result of two field picture jam situation in the cycle, differentiating the current detection cycle is that the toll plaza blocks up the cycle.Concrete rule is: with 10 seconds be a sense cycle, in this sense cycle, be not less than 9/10 picture frame and be the frame that blocks up, then mark should be the cycle of blocking up in the cycle, otherwise, then be labeled as non-blocking up the cycle.
But judge whether current toll plaza road blocks up, also need combine moving window ballot model, whether block up to confirm current toll plaza road, and whether should correspondingly export or remove warning information.
In this model, with 10 seconds be a sense cycle, the capacity of definition moving window is 6 cycles, in moving window, has 3 and above cycle be the cycle of blocking up, the then output warning of blocking up, and mark this to play corresponding energy value line segment constantly be redness; Otherwise it is non-blocking up the cycle that 4 and above cycle are arranged in moving window, then removes warning, and mark this constantly corresponding energy value be blueness.
Fig. 3 representes that when congestion event occurring, the variation of energy value is very slow, very little, maintains a less numerical value at the absolute value of 64 frame to 160 frame energy value variable quantities always, and this period, traffic congestion took place.Relation through analysing energy value-energy value variable quantity absolute value; Finally obtain decision rule: when energy value is in a high numerical value; Its energy value variable quantity absolute value remains in a period of time in the smaller value, and congestion status appears in the toll plaza.
Explanation is at last; Above embodiment is only unrestricted in order to technical scheme of the present invention to be described; Although with reference to preferred embodiment the present invention is specified, those of ordinary skill in the art should be appreciated that and can make amendment or be equal to replacement technical scheme of the present invention; And not breaking away from the aim and the scope of present technique scheme, it all should be encompassed in the middle of the claim scope of the present invention.

Claims (10)

1.基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：包括如下步骤：1. the method for judging traffic congestion in expressway toll plaza based on video detection technology, is characterized in that: comprise the steps: 1)摄取收费广场道路视频；1) Capture the road video of the toll plaza; 2)从视频中提取收费广场道路的图片；2) Extract the picture of the toll plaza road from the video; 3)建立并更新图片的背景模型；3) Establish and update the background model of the picture; 4)从图片中提取前景图像；4) extract the foreground image from the picture; 5)获取前景图像的能量值及能量值变化量绝对值，判断当前帧图像是否为拥堵图像。5) Obtain the energy value of the foreground image and the absolute value of the energy value change, and judge whether the current frame image is a congestion image. 2.根据权利要求1所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：所述步骤3)具体包括如下步骤：2. the highway toll plaza traffic jam discrimination method based on video detection technology according to claim 1, is characterized in that: described step 3) specifically comprises the steps: 31)通过对N0张收费广场道路的图片，用均值法求取初始背景，N0＞20；31) Calculate the initial background by using the average value method for N 0 pictures of toll plaza roads, N 0 >20; 32)设定阈值，通过阈值判断，从初始背景中提取背景；32) Setting the threshold, and extracting the background from the initial background through threshold judgment; 33)用步骤32)提取的背景建立并更新背景模型。33) Use the background extracted in step 32) to establish and update the background model. 3.根据权利要求2所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：所述步骤4)中，根据步骤3)获得的背景模型，利用差分法从图片中提取前景图像。3. the method for discriminating traffic jams in expressway toll plazas based on video detection technology according to claim 2, characterized in that: in the step 4), according to the background model obtained in step 3), the differential method is used to extract from the picture foreground image. 4.根据权利要求1所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：步骤5)具体包括如下步骤：4. the highway toll plaza traffic jam discrimination method based on video detection technology according to claim 1, is characterized in that: step 5) specifically comprises the steps: 51)获取当前帧第k帧的前景图像的能量值Energy(k)；51) Obtain the energy value Energy(k) of the foreground image of the kth frame of the current frame; 52)获取当前帧第k帧的前景图像与前一帧第k-1帧的前景图像的能量值之差的绝对值ΔEnergy(k)，同理获取ΔEnergy(k-1)、ΔEnergy(k-2)；52) Obtain the absolute value ΔEnergy(k) of the energy value difference between the foreground image of the kth frame of the current frame and the energy value of the foreground image of the k-1th frame of the previous frame, and obtain ΔEnergy(k-1), ΔEnergy(k-1) in the same way 2); 53)判断Energy(k)是否大于阈值T1，如是，则执行下一步；如否，则判定第k帧为非拥堵帧；53) judge whether Energy (k) is greater than threshold value T1, if yes, then perform the next step; if not, then determine that the kth frame is a non-congested frame; 54)判断当前帧第k帧的前景图像与前一帧第k-1帧的前景图像的能量值之差的绝对值ΔEnergy(k)是否小于阈值T2，如是，则执行下一步；如否，则判定第k帧为非拥堵帧；54) Determine whether the absolute value ΔEnergy(k) of the energy value difference between the energy value of the foreground image of the kth frame of the current frame and the k-1th frame of the previous frame is less than the threshold T2, if yes, then perform the next step; if not, Then it is determined that the kth frame is a non-congested frame; 55)判断第k-1帧的前景图像与前一帧第k-2帧的前景图像的能量值之差的绝对值ΔEnergy(k-1)是否小于阈值T2，如是，则执行下一步；如否，则判定第k帧为非拥堵帧；55) Determine whether the absolute value ΔEnergy(k-1) of the energy value difference between the foreground image of the k-1th frame and the energy value of the foreground image of the k-2th frame of the previous frame is less than the threshold T2, if so, then perform the next step; If not, it is determined that the kth frame is a non-congested frame; 56)判断第k-2帧的前景图像与前一帧第k-3帧的前景图像的能量值之差的绝对值ΔEnergy(k-2)是否小于阈值T2，如是，则判定第k帧为拥堵帧；如否，则判定第k帧为非拥堵帧。56) Determine whether the absolute value ΔEnergy(k-2) of the energy value difference between the foreground image of the k-2th frame and the energy value of the foreground image of the k-3th frame of the previous frame is less than the threshold T2, and if so, then determine that the kth frame is congestion frame; if not, then determine the kth frame as a non-congestion frame. 5.根据权利要求4所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：步骤5)中，获取前景图像的能量值的方法如下：定义图像序列为
Figure FDA0000094560520000021
k为帧号，N为视频的总帧数，则差分图像为difk(x，y)＝frk(x，y)-frk-1(x，y)；对于第k帧差分图像difk(x，y)，计算其全局阈值level，再对该差分图像进行二值化处理，强制转换为二值图像；得到的二值化后的差分图像为
Figure FDA0000094560520000022
其有m×n个像素点；通过下式计算该二值化后的差分图像的能量：5. the method for judging traffic congestion in expressway toll plaza based on video detection technology according to claim 4, is characterized in that: in step 5), the method for obtaining the energy value of foreground image is as follows: define image sequence as
Figure FDA0000094560520000021
k is the frame number, and N is the total frame number of the video, then the difference image is dif k (x, y)=fr k (x, y)-fr k-1 (x, y); for the kth frame difference image dif k (x, y), calculate its global threshold level, and then perform binarization processing on the difference image, and force it to be converted into a binary image; the obtained binarized difference image is
Figure FDA0000094560520000022
It has m×n pixels; the energy of the binarized difference image is calculated by the following formula: EE. (( DBDB (( kk ,, ii ,, jj )) ii == 11 ,, jj == 11 mm ×× nno )) == 11 mm ×× nno (( ΣΣ ii == 11 mm ΣΣ jj == 11 nno bb (( ii ,, jj )) )) 其中b(i，j)为像素点(i，j)的值，即为该点的能量值。Where b(i, j) is the value of the pixel point (i, j), that is, the energy value of the point. 6.根据权利要求4所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：T1＝0.48，T2＝0.076。6. The method for judging traffic congestion in expressway toll plazas based on video detection technology according to claim 4, characterized in that: T1=0.48, T2=0.076. 7.根据权利要求1至6中任一项所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：所述步骤2)中还包括将提取的收费广场道路的图片由彩色图片转换为灰度图片的步骤。7. according to the highway toll plaza traffic jam discrimination method based on video detection technology described in any one in claim 1 to 6, it is characterized in that: described step 2) also includes the picture of the toll plaza road of extraction by Steps to convert a color image to a grayscale image. 8.根据权利要求7所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：所述步骤4)中，还包括对所提取的前景图像进行形态学方法去噪的步骤。8. the highway toll plaza traffic congestion discrimination method based on video detection technology according to claim 7, is characterized in that: in described step 4), also comprises the step that the foreground image that is extracted is carried out morphological method denoising . 9.根据权利要求1至8中任一项所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：步骤5)之后还有如下步骤：9. according to any one of claim 1 to 8 based on the highway toll plaza traffic congestion discrimination method based on video detection technology, it is characterized in that: step 5) also has the following steps after: 6)根据步骤5)中第k帧图像的拥堵判别结果，判别当前检测周期是否为收费广场拥堵周期，具体步骤如下：6) According to the congestion discrimination result of the kth frame image in step 5), it is judged whether the current detection cycle is a toll plaza congestion cycle, and the specific steps are as follows: 以10秒为一个检测周期，当该检测周期中超过90％的图像帧为拥堵帧，则标记该周期为拥堵周期，反之，则标记为非拥堵周期。Taking 10 seconds as a detection period, when more than 90% of the image frames in the detection period are congested frames, this period is marked as a congested period, otherwise, it is marked as a non-congested period. 10.根据权利要求9所述的基于视频检测技术的高速公路收费广场交通拥堵判别方法，其特征在于：还包括如下步骤：10. the highway toll plaza traffic jam discrimination method based on video detection technology according to claim 9, is characterized in that: also comprise the steps: 7)根据步骤6)中当前检测周期的拥堵判别结果，判断当前收费广场道路是否拥堵，并相应地输出或解除告警信息，其具体包括如下步骤：7) According to the congestion discrimination result of the current detection period in step 6), judge whether the current toll plaza road is congested, and output or remove the alarm information accordingly, which specifically includes the following steps: 71)建立滑动窗口投票模型，以10秒为一个检测周期，定义滑动窗口的容量为6个周期，当滑动窗口中有3个及以上的周期为拥堵周期时判定收费广场拥堵，否则为非拥堵状态。71) Establish a sliding window voting model, with 10 seconds as a detection period, define the capacity of the sliding window as 6 periods, when there are 3 or more periods in the sliding window as congestion periods, it is determined that the toll plaza is congested, otherwise it is non-congested state. 72)比对当前周期的投票结果与上一周期的投票结果，如果上一周期的投票结果为非拥堵状态，而当前周期的投票结果为拥堵状态，则输出拥堵警告；如果上一周期的投票结果为拥堵状态，而当前周期的投票结果为非拥堵状态，则解除拥堵警告。72) Compare the voting result of the current cycle with the voting result of the previous cycle, if the voting result of the previous cycle is non-congested state, and the voting result of the current cycle is congested state, then output congestion warning; if the voting result of the previous cycle If the result is a congestion state, and the voting result of the current cycle is a non-congestion state, the congestion warning will be released.
CN 201110289530 2011-09-27 2011-09-27 Traffic jam discrimination method in expressway toll plaza based on video detection technology Active CN102436739B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110289530 CN102436739B (en) 2011-09-27 2011-09-27 Traffic jam discrimination method in expressway toll plaza based on video detection technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201110289530 CN102436739B (en) 2011-09-27 2011-09-27 Traffic jam discrimination method in expressway toll plaza based on video detection technology

Publications (2)

Publication Number Publication Date
CN102436739A true CN102436739A (en) 2012-05-02
CN102436739B CN102436739B (en) 2013-10-23

Family

ID=45984772

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110289530 Active CN102436739B (en) 2011-09-27 2011-09-27 Traffic jam discrimination method in expressway toll plaza based on video detection technology

Country Status (1)

Country Link
CN (1) CN102436739B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103258425A (en) * 2013-01-29 2013-08-21 中山大学 Method for detecting vehicle queuing length at road crossing
US9424748B2 (en) 2014-09-09 2016-08-23 Here Global B.V. Reporting traffic conditions on road segments containing a bottleneck
CN107293127A (en) * 2017-06-26 2017-10-24 武汉大学 A kind of toll plaza congestion monitoring system based on multi-beam wide area microwave sounding
CN110942642A (en) * 2019-11-20 2020-03-31 中科视元科技(杭州)有限公司 Video-based traffic slow-driving detection method and system
CN111383444A (en) * 2018-12-28 2020-07-07 腾讯大地通途（北京）科技有限公司 Method, device, server and storage medium for predicting road condition state
CN112991719A (en) * 2021-01-28 2021-06-18 北京奥泽尔科技发展有限公司 Traffic congestion prediction method and system based on congestion portrait

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102867415B (en) * 2012-09-12 2015-05-13 重庆大学 Video detection technology-based road jam judgement method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050190975A1 (en) * 2004-02-26 2005-09-01 Porikli Fatih M. Traffic event detection in compressed videos
JP2006031645A (en) * 2004-07-12 2006-02-02 Nariyuki Mitachi Real-time estimation method for dynamic crowd density and crowd accident prevention system
CN101710448A (en) * 2009-12-29 2010-05-19 浙江工业大学 Road traffic state detecting device based on omnibearing computer vision
CN101807345A (en) * 2010-03-26 2010-08-18 重庆大学 Traffic jam judging method based on video detection technology
CN102136194A (en) * 2011-03-22 2011-07-27 浙江工业大学 Road traffic condition detection device based on panorama computer vision

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050190975A1 (en) * 2004-02-26 2005-09-01 Porikli Fatih M. Traffic event detection in compressed videos
JP2006031645A (en) * 2004-07-12 2006-02-02 Nariyuki Mitachi Real-time estimation method for dynamic crowd density and crowd accident prevention system
CN101710448A (en) * 2009-12-29 2010-05-19 浙江工业大学 Road traffic state detecting device based on omnibearing computer vision
CN101807345A (en) * 2010-03-26 2010-08-18 重庆大学 Traffic jam judging method based on video detection technology
CN102136194A (en) * 2011-03-22 2011-07-27 浙江工业大学 Road traffic condition detection device based on panorama computer vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘卫宁，曾恒，孙棣华，赵敏: "基于视频检测技术的交通拥挤判别模型", 《计算机应用研究》, vol. 27, no. 8, 15 August 2010 (2010-08-15), pages 3006 - 3008 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103258425A (en) * 2013-01-29 2013-08-21 中山大学 Method for detecting vehicle queuing length at road crossing
CN103258425B (en) * 2013-01-29 2015-07-01 中山大学 Method for detecting vehicle queuing length at road crossing
US9424748B2 (en) 2014-09-09 2016-08-23 Here Global B.V. Reporting traffic conditions on road segments containing a bottleneck
CN107293127A (en) * 2017-06-26 2017-10-24 武汉大学 A kind of toll plaza congestion monitoring system based on multi-beam wide area microwave sounding
CN107293127B (en) * 2017-06-26 2020-03-10 武汉大学 Charging square congestion monitoring system based on multi-beam wide-area microwave detection
CN111383444A (en) * 2018-12-28 2020-07-07 腾讯大地通途（北京）科技有限公司 Method, device, server and storage medium for predicting road condition state
CN111383444B (en) * 2018-12-28 2021-08-17 腾讯大地通途（北京）科技有限公司 Method, device, server and storage medium for predicting road condition state
CN110942642A (en) * 2019-11-20 2020-03-31 中科视元科技(杭州)有限公司 Video-based traffic slow-driving detection method and system
CN110942642B (en) * 2019-11-20 2021-01-19 中科视元科技(杭州)有限公司 Video-based traffic slow-driving detection method and system
CN112991719A (en) * 2021-01-28 2021-06-18 北京奥泽尔科技发展有限公司 Traffic congestion prediction method and system based on congestion portrait
CN112991719B (en) * 2021-01-28 2022-05-24 北京奥泽尔科技发展有限公司 Traffic congestion prediction method and system based on congestion portrait

Also Published As

Publication number Publication date
CN102436739B (en) 2013-10-23

Similar Documents

Publication Publication Date Title
CN102436739A (en) Traffic jam discrimination method in expressway toll plaza based on video detection technology
CN103258430B (en) Road traveling time calculating and traffic road condition judging method and road traveling time calculating and traffic road condition judging device
CN106874863B (en) Vehicle illegal parking and reverse running detection method based on deep convolutional neural network
CN101923778A (en) A Video-Based Detection Method of Expressway Traffic Congestion State
KR101748121B1 (en) System and method for detecting image in real-time based on object recognition
CN101807345B (en) Traffic jam judging method based on video detection technology
CN106373430B (en) Intersection traffic early warning method based on computer vision
CN102005120A (en) Traffic intersection monitoring technology and system based on video image analysis
CN101799985B (en) Highway tunnel traffic identification method
CN109191830A (en) A kind of congestion in road detection method based on video image processing
CN106571037A (en) Station detection technology-based expressway real-time road condition monitoring method
CN105513371B (en) A kind of highway parking offense detection method based on Density Estimator
CN104376554A (en) Illegal parking detection method based on image texture
CN110688922A (en) Deep learning-based traffic jam detection system and detection method
CN104680794A (en) Vehicle-mounted monitoring terminal as well as bus lane monitoring method and system based on terminal
CN206133931U (en) A Rapid Evacuation Control System for Tunnel Traffic Congestion
CN104392610A (en) Distributed video based highway traffic incident influence range dynamic monitoring method
CN104282154A (en) Vehicle overload monitoring system and method
CN113055649A (en) Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium
CN111754786A (en) System for identifying traffic vehicle passing events on highway
CN102110366B (en) Block-based accumulated expressway vehicle parking event detecting method
CN112749630A (en) Intelligent video monitoring method and system for road conditions
CN104301697A (en) An automatic detection system and method for violent incidents in public places
CN202422420U (en) Illegal parking detection system based on video monitoring
CN104268548A (en) Accumulated snow detection method based on road images

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
TR01 Transfer of patent right

Effective date of registration: 20201216

Address after: 402460 station No.14, no.6, 10th floor, innovation and development center, No.19 Lingfang Avenue, Changzhou street, Rongchang District, Chongqing

Patentee after: Chongqing kezhiyuan Technology Co.,Ltd.

Address before: 400044 No. 174 Sha Jie street, Shapingba District, Chongqing

Patentee before: Chongqing University

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20210106

Address after: 215400 No.2, 4th floor, building a, No.88, Beijing East Road, Taicang Development Zone, Suzhou City, Jiangsu Province

Patentee after: Suzhou Yunshou Software Technology Co.,Ltd.

Address before: 402460 station No.14, no.6, 10th floor, innovation and development center, No.19 Lingfang Avenue, Changzhou street, Rongchang District, Chongqing

Patentee before: Chongqing kezhiyuan Technology Co.,Ltd.

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20250415

Address after: 215300 room 605, science and Technology Plaza, Qianjin East Road, Kunshan Development Zone, Suzhou, Jiangsu.

Patentee after: KUNSHAN SILAIMU ENERGY-SAVING TECHNOLOGY Co.,Ltd.

Country or region after: China

Address before: 215400 No.2, 4th floor, building a, No.88, Beijing East Road, Taicang Development Zone, Suzhou City, Jiangsu Province

Patentee before: Suzhou Yunshou Software Technology Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right