CN103414870A - Multiple-mode alert analysis method - Google Patents

Abstract

The invention discloses a multi-mode alert analysis method. The multi-mode alert analysis method comprises the following steps that: monitoring videos, a large-scale map and a high-definition remote sensing image in an area are obtained, and mutual mapping of the monitor videos and two-dimensional geographic space data can be realized; according to alert requirements, linear and planar alert graphics which are drawn in a GIS form an alert area set, and allowed direction, velocity and time parameter are set, and therefore, an alert rule base can be formed, and the alert rule base is mapped to each related monitoring video; the position and direction of a dynamic target and actual movement parameters of the dynamic target under GIS mapping are obtained by means of foreground detection and target tracking; whether the movement state of the dynamic target violates the multi-mode alert rule base or not can be judged in a real-time manner; and when events violating alert rules occur, real-time alarm can be performed with highlighted graphics or alert audios in the GIS. With the method of the invention adopted, shortcomings of singleness in settings, the lack of geographic space reference, inconvenience in regional alert analysis of a traditional alter method can be eliminated; and the flexibility and integrity of regional alert can be greatly improved.

Description

A kind of multi-mode warning analytical method

Technical field

The present invention relates to a kind of multi-mode warning analytical method, specifically, be a kind ofly can in single video camera, set flexibly multiple warning rule, realize the multi-mode warning analytical method of warning as required, overcome unicity that current warning sets and without the shortcoming of geographical space reference.

Background technology

Along with socioeconomic fast development, mankind's activity is day by day frequent, because the security protection disappearance causes any property loss, the accident of casualties is of common occurrence.Therefore, lay video monitoring equipment at important place, the warning rule is set and carries out the important means that real-time warning is the region security management, real-time, various, warning method flexibly has important practical significance.

Current, the warning analytical method is relatively single, lacks flexibility.The corresponding a kind of warning analytical method of a common video camera, just need to set up another monitoring probe if carry out simultaneously another kind warning analysis.Each monitoring probe division of labor is clear and definite, moves detection, hovers and detect 4 modules separately independently as intrusion detection, abandon detection, article.And in actual video monitoring, the warning demand has flexibility, need in single monitoring scene to set multiple warning rule, and As time goes on change flexibly, thereby reach " a tractor serves several purposes ".So, existing all vigilance performance modules are carried out abstract, directly provide unified rule flexibly to set interface and will meet user flexibility, various warning demand.

Simultaneously, monitor video lacks geographical georeferencing, and under large scene, the warning rule is set relatively loaded down with trivial details.When in the face of several monitoring probe warning rules, arranging, the security protection personnel can complete fast.Yet along with socioeconomic development, monitoring probe presents the feature of densification.The warning rule is still set in a traditional way one by one will be very loaded down with trivial details, if the understanding lacked whole regional geography environment just is easy to make mistakes.GIS gives spatial data clear and definite georeferencing, geomorphological features detailed in large scene can be represented in map.Therefore, GIS is incorporated in the warning analysis, realizes the fusion of monitor video and 2D geographical spatial data, will make to guard against regular setting facilitation.

Summary of the invention

Key issue to be solved by this invention is to overcome the unicity that in video monitoring, the warning rule is set, build the mutual mapping model of geographical spatial data and monitor video, realize multi-mode warning analysis, thereby make to guard against to analyze, from traditional single warning be set the stage and move towards flexible, multimodal warning the stage is set, from without geographical space, moving towards the warning rule that be suitable for large scene, densification video monitoring of GIS under leading with reference to the stage, be set the stage.Therefore, the present invention proposes multi-mode warning analytical method.

Basic ideas of the present invention: realize the mutual mapping of geographical spatial data and monitor video, make monitor video have clear and definite geographical space reference; Take geographical spatial data as main, set the warning rule, and it is mapped in each associated monitoring video; Each associated camera performance objective detects, target following, according to the warning in real time of warning rule.

The basic step of a kind of multi-mode warning of the present invention analytical method is:

The first step, obtain monitor video, large-scale map and high definition remote sensing image in zone, according to mapping matrix, realize the mutual mapping of monitor video and 2D geographical spatial data;

Under second step, GIS, warning region is set: according to the warning demand, map-based and remote sensing image are drawn warning line and face in the GIS platform, form the warning region set;

Under the 3rd step, GIS, the warning rule is set: based on the warning region set of drawing in second step, set flexibly the direction of motion, speed and time parameter, thereby the structure multi-mode is built the warning rule base; Wherein, if the user specifies one to allow direction, need to set the direction that forms broken line and polygonal each selections when warning, according to allowing direction and warning region to draw the direction of all line segments of direction calculating; After the warning rule sets, based on the mapping matrix of the first step, these warning rules are mapped in each relevant monitor video;

The 4th step, in real time warning: by foreground detection, target following, obtain the actual motion parameter under position, direction and the GIS mapping of dynamic object; Whether real-time judge dynamic object motion state violates multi-mode warning rule base; When having the regular event of the warning of violating to occur, with figure or the alarm audio frequency of giving prominence to, carry out Realtime Alerts in generalized information system.

In the described first step, realize the mutual mapping of monitor video and 2D geographical spatial data, its concrete steps are:

(a) obtain height, inclination angle, horizontal view angle and the azimuth of each video camera, based on the ground monitoring zone of these 4 each monitoring probes of calculation of parameter, i.e. trapezoidal guarded region corresponding to each monitoring probe;

(b) according to the position of video camera, by the coordinate of the Coordinate Conversion of each trapezoidal guarded region to 2D map of living in or remote sensing image, and form guarded region figure layer;

(c) according to trapezoidal geographical coordinate and the corresponding image coordinate of trapezoidal each point, resolve homography matrix, thereby realize the mutual mapping of monitor video image and 2D geographical spatial data.

A kind of multi-mode warning analytical method of the present invention is based on the mutual mapping method of monitor video and geographical spatial data, the user draws warning line and the standby clear and definite georeferencing of mask, warning arranges and can under unified interface, complete, overcome traditional warning arrange single, lack geographical georeferencing, be not easy to the shortcoming that area outlook is analyzed, greatly improved flexibility, the globality of area outlook.

The accompanying drawing explanation

Fig. 1 is camera supervised area schematic, is (a) camera supervised area schematic in local coordinate system; (b) be camera supervised area schematic in projected coordinate system;

Fig. 2 is trapezoidal guarded region figure layer schematic diagram;

Fig. 3 monitors the ken and image coordinate corresponding relation schematic diagram;

Fig. 4 (a) draws warning line and allows the direction schematic diagram on remote sensing image; (b) be on remote sensing image, to draw warning polygon schematic diagram;

Fig. 5 (a) is that warning allows direction setting procedure figure; (b) be that warning line allows direction setting method and each line segment to allow the direction schematic diagram;

In Fig. 6 (a) map, ray mode warning rule maps to the video schematic diagram; (b) in map, polygon Mode warning rule maps to the video schematic diagram;

Fig. 7 guards against flow chart in real time.

Embodiment

Below in conjunction with drawings and Examples, the present invention is described in further detail.

The first step, monitor video and geographical spatial data are shone upon mutually concrete steps and are:

(1) obtain photo centre's geographical coordinate of each video monitoring probe, highly, inclination angle, horizontal view angle, azimuth, and obtain the detailed 2D geographical spatial data in zone, comprise map and remote sensing image; According to the relevant parameter of video camera, calculate its ground monitoring zone, i.e. trapezoid area, its coordinate is projection coordinate's system, as Fig. 1;

(2) in GIS, create guarded region figure layer, the corresponding ground monitoring of each monitoring probe zone polygon is added in this figure layer, as Fig. 2.

(3) according to coordinate and the corresponding image coordinate thereof of trapezoidal each point, calculate homography matrix, this matrix is the core of monitor video and the mutual mapping of 2D spatial data.

Second step, under GIS, warning region setting concrete steps are:

(1) in the GIS platform, create the figure layer of line and Noodles type;

(2) with remote sensing image, draw warning line and polygon according to the map.According to the warning demand, in map, draw warning line and face, form the warning region set, as Fig. 4.System provides warning line and face that interface is set, can setpoint color, line style, filling type.

The 3rd step, under GIS, warning rule setting concrete steps are:

(1) according to the warning demand, the warning region set of take is basis, specifies and allows direction, speed, time parameter.For common warning analytical method, concrete setting means is as follows:

Intrusion detection: specify the figure in the warning region set; Direction initialization in GIS (unidirectional, two-way).

The detection of hovering: specify the zone of hovering in the warning region set; Setting is hovered the time.

Abandon detects: specify the surveyed area in the warning region set; Specify the abandon time of staying.

Other warning rules are set, and the rest may be inferred.

Wherein, if the user specifies one to allow direction, need to set the direction that forms broken line and polygonal each selections, detailed process such as Fig. 5 when warning.The concrete steps of each line segment direction assignment are as follows:

At first, broken line and the judgement of polygonal drafting direction.Mainly according to two initial line segments, form vector herein, can judge broken line and polygonal drafting direction by vectorial multiplication cross.

Then, the judgement user draws the position relationship of direction and broken line.Set the user and draw the vectorial V that is ₁, the corresponding vector of line segment intersected with it is V ₂, judgement V ₁With V ₂Relation, make V ₂To V ₁Direction rotation 90 degree of vector, form vectorial V ₃, V ₃Be V ₂The permission vector of vector.According to said method, obtain the permission vector that each line segment vector is corresponding.

(2) according to the homography matrix resolved in the first step, the warning rule is mapped in the monitor video of each video camera, as Fig. 6;

The 4th step, guard against in real time concrete steps and be:

(1) in each monitor video, carry out foreground detection, fresh target detection, target following operation, obtain position and the direction of dynamic object.Foreground detection has adopted the mixed Gauss model background subtraction, and tracking adopts Mean shift algorithm.

(2) according to the kinematic parameter of dynamic object and the warning rule of the 3rd step mapping, guard against in real time.

(3) dynamic object is presented in generalized information system in real time, and when there being target to violate the warning rule, generalized information system to be to highlight and auditory tone cues security protection personnel, simultaneously to time, the place of event, break the rules and carry out record.

Embodiment:

The first step: relevant device is prepared.Prepare a monitor video server, some video cameras, high accuracy map and remote sensing image.

Second step: monitor video and 2D geographical spatial data shine upon mutually.

(1) in GIS software, open high accuracy map and remote sensing image, these data have clear and definite geographical space reference, and the WGS84UTM projected coordinate system is adopted in suggestion.The figure layer of newly-built vertex type is for managing each video camera, and positional information comprises the X under projected coordinate system and the Y of video camera, and attribute field comprises height, inclination angle, azimuth and the horizontal field of view angle of video camera.

(2), according to camera height, inclination angle, azimuth and horizontal field of view angle, calculate the corresponding guarded region of ground level, as Fig. 1.Specific formula for calculation, as follows:

In Fig. 1, the coordinate of c point in local coordinate system calculates, as formula 1, (x _c, y _c) being the coordinate in local coordinate system corresponding to c point, H is camera height, Pitch is inclination angle.

$\left\{\begin{array}{c}{x}_c=H*\tan (\mathrm{Pitch}*\frac{\mathrm{pi}}{180})\\ y_c=0\end{array}\right.---\left(1\right)$

The coordinate of c point in projected coordinate system, as formula 2, (X _c, Y _c) being the coordinate of c point under projected coordinate system, Azimuth is azimuth.

$\left\{\begin{array}{c}{X}_c=X_s+x_c*\cos (\mathrm{Azimuth}*\frac{\mathrm{pi}}{180})\\ Y_c=Y_s+x_c*\sin (\mathrm{Azimuth}*\frac{\mathrm{pi}}{180})\end{array}\right.---\left(2\right)$

Trapezoidal other each points, according to the method that is similar to c and orders, calculate respectively local coordinate, and then calculate geographical coordinate, thereby get the geographical coordinate of those trapezoidal and middle points, amounts to 9 points.

(3) calculate homography matrix.Trapezoid area is corresponding with whole image-region, therefore according to respective point, just can calculate homography matrix.In application, choosing of trapezoidal point can be selected flexibly according to the distribution of ground level in image.Homograph can be realized based on the OpenCV open source software.

The 3rd step: under GIS, warning region is drawn and the setting of warning rule.

Draw warning line and face, specify and allow direction, speed, time parameter, and it is mapped in each monitor video.Regular setting and the computer expression of multi-mode warning can be according to the described realization of Fig. 5, and core is vectorial related operation.The mapping of warning rule in geographical spatial data and monitor video, the homography matrix mainly calculated based on second step.

The 4th step: warning in real time.

(1) dynamic object is carried out to real-time tracking, and based on it mapping target in map, obtain its actual kinematic parameter.The algorithm of following the tracks of can call the OpenCV correlation function, and the mapping of target and track thereof realizes by homography matrix, actual parameter obtain mapping target and the time acquisition of information in main map-based.Dynamic object is expressed in GIS, newly-built dynamic layer receives relevant information in real time.

(2) warning: according to the kinematic parameter of dynamic object, comprise position, speed, track, in real-time judge itself and rule base, the dependency rule of defined, comprise position, direction, time.

Claims (2)

1. a multi-mode warning analytical method, the steps include:

The first step, obtain monitor video, large-scale map and high definition remote sensing image in zone, according to mapping matrix, realize the mutual mapping of monitor video and 2D geographical spatial data;

Under second step, GIS, warning region is set: according to the warning demand, map-based and remote sensing image are drawn warning line and face in the GIS platform, form the warning region set;

Under the 3rd step, GIS, the warning rule is set: based on the warning region set of drawing in second step, set flexibly the direction of motion, speed and time parameter, thereby build multi-mode warning rule base; Wherein, if the user specifies one to allow direction, need to set the direction that forms broken line and polygonal each selections when warning, according to allowing direction and warning region to draw the direction of all line segments of direction calculating; After the warning rule sets, based on the mapping matrix of the first step, these warning rules are mapped in each relevant monitor video;

The 4th step, in real time warning: by foreground detection, target following, obtain the actual motion parameter under position, direction and the GIS mapping of dynamic object; Whether real-time judge dynamic object motion state violates multi-mode warning rule base; When having the regular event of the warning of violating to occur, with figure or the alarm audio frequency of giving prominence to, carry out Realtime Alerts in generalized information system.

2. a kind of multi-mode warning analytical method according to claim 1, is characterized in that, in the described first step, realize the mutual mapping of monitor video and 2D geographical spatial data, its concrete steps are:

(a) obtain height, inclination angle, horizontal view angle and the azimuth of each video camera, based on the ground monitoring zone of these 4 each monitoring probes of calculation of parameter, i.e. trapezoidal guarded region corresponding to each monitoring probe;

(b) according to the position of video camera, by the coordinate of the Coordinate Conversion of each trapezoidal guarded region to 2D map of living in or remote sensing image, and form guarded region figure layer;

(c) according to trapezoidal geographical coordinate and the corresponding image coordinate of trapezoidal each point, resolve homography matrix, thereby realize the mutual mapping of monitor video image and 2D geographical spatial data.

Images