CN202422420U - Illegal parking detection system based on video monitoring - Google Patents

Abstract

The utility model discloses an illegal parking detection system based on video monitoring. The illegal parking detection system comprises an image collector, an image processor, an alarm system and a display, wherein the image collector is used for collecting a video image and outputting a video sequence; the image processor is used for carrying out background modeling on the video sequence collected by the image collector by utilizing a codebook model, obtaining a foreground likelihood information image by adopting a background subtraction method, filtering interference of other moving targets to a vehicle to be monitored in the foreground likelihood information image, and carrying out intelligent judgment on the vehicle to be monitored in the foreground likelihood information image by utilizing an illegal parking judgment algorithm; the alarm system is used for giving an alarm when the vehicle to be monitored has the illegal parking phenomenon; and the display is used for displaying the video image processed by the image collector. By utilizing the illegal parking detection system, other types of moving targets which can have impact on the vehicle to be monitored are filtered, the accuracy of the alarm is improved, the illegal parking detection system has the characteristics of good instantaneity, strong robustness, high accuracy, and the like, thereby providing an effective technological means for intelligent management of urban traffic.

Description

A kind of parking offense detection system based on video monitoring

Technical field

The utility model belongs to image processing field, particularly a kind of parking offense detection system based on video monitoring.

Background technology

Along with the progress and development of society, the automobile pollution in city is increasing, has meanwhile also brought a lot of problems.Parking offense has caused the attention of vehicle supervision department as one of problem demanding prompt solution.It mainly is to fix a point to implement artificial supervision through the traffic police that traditional parking offense detects, and efficient is low, can't realize real-time monitoring, has greatly wasted the manpower and financial resources of relevant departments.In recent years, received the attention of more and more scholars and relevant departments based on the parking offense detection method of video monitoring, this method has the accuracy rate height, and real-time is good, and cost is low, advantage such as collect evidence easily.

At present; Generally be based on the mixed Gauss model algorithm or utilize method of difference to realize treating the extraction of monitoring objective based on the parking offense detection system of video monitoring; Because it does not carry out filtering to targets such as pedestrian or other non power driven vehicles, causes the increase of rate of false alarm to a great extent.In addition, existing systems is not made careful classification to being in the separated type of vehicle that stops the zone, must influence the validity of monitoring.

The utility model content

The problems referred to above that the utility model exists to the present parking offense detection system based on video monitoring, and a kind of parking offense detection system based on video monitoring has been proposed.The technological means that the utility model adopts is following:

A kind of parking offense detection system based on video monitoring is characterized in that comprising:

The image acquisition device of output video sequence behind the collection video image;

Connect image acquisition device, utilize the code book model that the video sequence of image acquisition device collection is carried out background modeling, adopts the background subtraction method to obtain behind the prospect likelihood information image in the filtering prospect likelihood information image other moving target to treat the interference of monitoring vehicle, utilize the parking offense decision algorithm vehicle to be monitored in the prospect likelihood information image to be carried out the image processor of intelligent decision afterwards;

Connect image processor, send the alarm of warning when stopping phenomenon when disobeying appears in vehicle to be monitored;

Connect image processor, show the display of the video image of handling through image acquisition device.

The utility model effectively overcome the shortcoming of traditional manual detection parking offense based on the parking offense detection system of video monitoring, can monitor in real time monitoring scene, find to disobey to stop and in time report to the police.This system is with respect to existing parking offense detection system based on video monitoring; Filtering possibly treat other kinds of athletic target that there is influence in monitoring vehicle; Improved the accuracy of reporting to the police, and this system to have a real-time good, strong robustness; Characteristics such as accuracy rate height are for the intelligent management of urban transportation provides effective technical means.

Description of drawings

Fig. 1 is the structural drawing based on the parking offense detection system of video monitoring of the utility model.

Fig. 2 A is the existing prospect likelihood illustrated example that adopts the mixed Gaussian algorithm to generate.

The prospect likelihood illustrated example of Fig. 2 B for adopting the code book model method to generate.

Fig. 3 A is the prospect likelihood illustrated example before other moving target of filtering.

Fig. 3 B is the prospect likelihood illustrated example behind other moving target of filtering.

Embodiment

For the purpose, technical scheme and the advantage that make the utility model is clearer,, the utility model is further elaborated below in conjunction with accompanying drawing and embodiment.

As shown in Figure 1, the parking offense detection system based on video monitoring of the utility model comprises:

The image acquisition device 1 of output video sequence behind the collection video image; Connect image acquisition device 1, the video sequence that utilizes the code book model that image acquisition device 1 is gathered carries out background modeling, adopt the background subtraction method to obtain behind the prospect likelihood information image in the filtering prospect likelihood information image other moving target treats the interference of monitoring vehicle, utilizes the parking offense decision algorithm vehicle to be monitored in the prospect likelihood information image to be carried out the image processor 2 of intelligent decision afterwards; Connect image processor 2, send the alarm 4 of warning when stopping phenomenon when disobeying appears in vehicle to be monitored; Connect image processor 2, show the display 3 of the video image of handling through image acquisition device 1.

The existing mixed Gauss model that is adopted based on the parking offense detection method of video monitoring is on the time scale of pixel domain, pixel to be classified; Be difficult to its learning efficiency both had been controlled at the also perfect condition of not omission of only inspection; Cause erroneous judgement easily; Can't solve the too much problem of shade, cavity and noise of treating monitoring objective, the accuracy that follow the tracks of the influence location.To this problem, image processor 2 is to adopt the code book model that video sequence is carried out background modeling.Particularly, image processor 2 video sequence that utilizes the code book model that image acquisition device 1 is gathered carries out background modeling, the process that adopts the background subtraction method to obtain prospect likelihood information image comprises:

Step 11: video sequence is learnt, generated a code book for each pixel, suppose that current pixel point is that (B), its corresponding code book is M to x=for R, G according to the color distance of each pixel continuous sampling value and brightness range.

Step 12: calculate the brightness I=R+G+B of current pixel point, definition Boolean variable match=0.

Step 13: from code book M, find the code word C that matees with current pixel according to imposing a condition _mIf can find code word C _m, match=1 then, otherwise match=0.Imposing a condition wherein comprises condition A and condition B, and condition A is expressed as:

$\mathrm{colordist}(x,v_m)=\frac{{\left|\right|x\left|\right|}^2{\left|\right|v_m\left|\right|}^2-{<x,v_m>}^2}{{\left|\right|v_m\left|\right|}^2}\&le;\mathrm{\&epsiv;}$

Wherein, || x|| ²=R ²+ G ²+ B ², ${\left|\right|v_m\left|\right|}^2={\stackrel{\&OverBar;}{R}}_m^2+{\stackrel{\&OverBar;}{G}}_m^2+{\stackrel{\&OverBar;}{B}}_m^2,$ ${<x,v_m>}^2={({\stackrel{\&OverBar;}{R}}_{m}R+{\stackrel{\&OverBar;}{G}}_{m}G+{\stackrel{\&OverBar;}{B}}_{m}B)}^2;$

Condition B is expressed as:

And work as I _Low≤|| x||≤I _HiThe time,

Wherein, I _LowBe the brightness range minimum value of code word, I _HiBrightness range maximal value for this code word.

Step 14: with the pixel of match=0 foreground pixel, with the pixel of match=1 background pixel as current video image as current video image.

Step 15: generate about pixel m in the current video image _iForeground likelihood function L _i(m _i), and then generate corresponding prospect likelihood figure, shown in Fig. 2 B.Foreground likelihood function L wherein _i(m _i) be expressed as:

Generally speaking, foreground area areas such as pedestrian, bicycle, noise are regional littler than vehicle to be monitored, and therefore, the process that other moving target is treated the interference of monitoring vehicle in the image processor 2 filtering prospect likelihood information images comprises:

Step 21: calculate in the prospect likelihood information image connected region area of each moving target.

Step 22: choose the connected region area more than or equal to the moving target of a threshold value as vehicle to be monitored, shown in Fig. 3 B, think that follow-up tracking and judgement violating the regulations provide necessary guarantee.

If vehicle to be monitored is divided into non-concern vehicle, pays close attention to vehicle and disobey and stop.Wherein, non-concern vehicle is disobeyed the vehicle that stops the zone for not getting into; Pay close attention to vehicle and disobey the vehicle that stops the zone, but berthing time is less than given time threshold for getting into; Disobey to stop and to stop in the zone and berthing time surpasses the vehicle of given threshold value for being in to disobey.Then image processor 2 utilizes the parking offense decision algorithm that the process that the vehicle to be monitored in the prospect likelihood information image carries out intelligent decision is comprised:

Step 31: calculate to disobey and stop regional center C _NPCoordinate (x _NP, y _NP).

Step 32: calculating vehicle i (i=1,2 ..., barycenter C N) _i, be expressed as:

$x_{C_i}=\frac{1}{A_i}\underset{(x,y)\&Element;R_i}{\mathrm{\&Sigma;}}x$

$y_{C_i}=\frac{1}{A_i}\underset{(x,y)\&Element;R_i}{\mathrm{\&Sigma;}}y$

Wherein, R _iBe the corresponding foreground area of vehicle i; A _iBe R _iArea; X, y is for belonging to R _iThe coordinate figure of pixel.

Step 33: calculate barycenter C _iWith the separated regional center C that stops _NPBetween apart from dist (C _i, C _NP), be expressed as:

$\mathrm{dist}(C_i,C_{\mathrm{NP}})=\mathrm{sqrt}({(x_{C_i}-x_{\mathrm{NP}})}^2+{(y_{C_i}-y_{\mathrm{NP}})}^2)$

Step 34: judging distance dist (C _i, C _NP) whether less than threshold value Th _d, be then vehicle i to be labeled as the concern vehicle, otherwise return step 32.

Step 35: calculate in the t frame video image and to pay close attention to vehicle i and be in and disobey the time span of stopping in the zone

Wherein, F _sFrame per second for video image.

Step 36: judge Whether greater than threshold value Th _τ, be then vehicle i to be labeled as disobey to stop, and get into and disobey the processing stage of the parking; Otherwise, return step 35.

Further, disobey and to stop the zone and comprise two types again: one type is to forbid all vehicle parkings zones (such as first-aid station, construction site, crossing etc.); Another kind of be forbid parking when long but allows temporary parking regional (such as: the interim bus stop of taxi etc.).Then can different distances threshold value and time threshold be set and realize an intelligent monitoring of stopping disobeying according to different requirement.Preferably, for forbidding all vehicle parking zones, satisfy: Th _d∈ (0.6～0.8) * L, Th _τ∈ (5～30) s; For forbidding parking when long but allows the temporary parking zone, satisfied: Th _d∈ (0.15～0.2) * L, Th _τ∈ (30～60) s is with the separated incident of stopping in the monitoring specialized range.Wherein, L is the length of no-parking zone in monitor video.

The utility model effectively overcome the shortcoming of traditional manual detection parking offense based on the parking offense detection system of video monitoring, can monitor in real time monitoring scene, find to disobey to stop and in time report to the police.This system is with respect to existing parking offense detection system based on video monitoring; Filtering possibly treat other kinds of athletic target that there is influence in monitoring vehicle; Improved the accuracy of reporting to the police, and this system to have a real-time good, strong robustness; Characteristics such as accuracy rate height are for the intelligent management of urban transportation provides effective technical means.

The above; Be merely the preferable embodiment of the utility model; But the protection domain of the utility model is not limited thereto; Any technician who is familiar with the present technique field is equal to replacement or changes according to the technical scheme of the utility model and utility model design thereof in the technical scope that the utility model discloses, and all should be encompassed within the protection domain of the utility model.

Claims (1)

1. parking offense detection system based on video monitoring is characterized in that comprising:

The image acquisition device of output video sequence behind the collection video image;

Connect image acquisition device, utilize the code book model that the video sequence of image acquisition device collection is carried out background modeling, adopts the background subtraction method to obtain behind the prospect likelihood information image in the filtering prospect likelihood information image other moving target to treat the interference of monitoring vehicle, utilize the parking offense decision algorithm vehicle to be monitored in the prospect likelihood information image to be carried out the image processor of intelligent decision afterwards;

Connect image processor, send the alarm of warning when stopping phenomenon when disobeying appears in vehicle to be monitored;

Connect image processor, show the display of the video image of handling through image acquisition device.

Images