CN103279943A - Target invasion detection method and device, and video monitoring system - Google Patents
Target invasion detection method and device, and video monitoring system Download PDFInfo
- Publication number
- CN103279943A CN103279943A CN2013101359394A CN201310135939A CN103279943A CN 103279943 A CN103279943 A CN 103279943A CN 2013101359394 A CN2013101359394 A CN 2013101359394A CN 201310135939 A CN201310135939 A CN 201310135939A CN 103279943 A CN103279943 A CN 103279943A
- Authority
- CN
- China
- Prior art keywords
- area
- minimum
- allows
- maximum
- target
- 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
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to a target invasion detection method, a target invasion detection device and a video monitoring system. The method comprises the following steps of initiating, namely acquiring a video image, and receiving at least one line segment drawn by an operator at an interested area of the video image and the minimum filtering area and the maximum filtering area which are set at two end points of each line segment; calculating, namely detecting a moving target, and calculating the minimum allowed area and the maximum allowed area at the position of the moving target when the at least line segment is crossed according to the set minimum filtering area and the set maximum filtering area; and judging, namely judging whether the area of the moving target is larger than the minimum allowed area and smaller than the maximum allowed area, and if so, judging that the moving target is an effective target, otherwise, judging that the moving target is an ineffective target. In the whole detection process, a specially-assigned person is not needed to mark in a scene, and also the depth of field of the sceneis not needed to be calculated, and the effectiveness of the target can be easily and quickly detected.
Description
Technical field
The application relates to technical field of video monitoring, relates in particular to a kind of target intrusion detection method and device and a kind of video monitoring system.
Background technology
Video surveillance applications is very extensive.Whether by video is carried out intellectual analysis, can judge has moving target to cross the border, invade area-of-interest.At present, the analytical technology employing of using always arranges the modes such as line and zone of stumbling and judges.When judging, because effectively the size of target is usually in certain scope, need to remove too small or excessive objects interfered, the effective target that for example needs to detect is human body, then to filter out invalid target, for example too small objects interfered such as kitten doggie and excessive objects interfered such as automobile etc.Therefore, need filter the moving target of specific size.
What adopt usually at present is the scene calibration mode.Particularly, in a kind of method, three not coordinate points of conllinear are set in the scene of image, then, allow a people stand at these three points, obtain this people respectively in the picture altitude of these three points (be unit with the pixel), and this people's true height, simultaneously, select two points on scene ground more again arbitrarily, and obtain this image distance of 2 and space actual distance, by converting, calculate in the diverse location of space, the mapping relations between target true altitude and the picture altitude, afterwards can be in scene the optional position, calculate the true area of this place's target by elemental area, thereby realize target is filtered.This method is not suitable for dangerous occasion owing to need personnel to go to the scene to demarcate, and method and the step more complicated of demarcating, and is unfavorable for that the user uses.Another kind method is virtual plane of initialization in scene, by the degree of tilt on continuous adjustment plane and the focus point of depth of field line, to reach the relation of match scene plane space, in case certain any target sizes is determined, then can be tried to achieve other local target sizes according to the variation ratio on plane.Though it is this method is fairly simple, directly perceived inadequately.
In addition, more than two kinds of methods only be suitable for the scene on plane, belong to overall filter method.If scene is not the plane, precision can be subjected to very big influence so.The scene that stage is for example arranged on the square, this moment, the demarcation on square was not suitable for stage, and for example the demarcation on ground is not suitable for the top etc. of enclosure wall again.
Summary of the invention
The target intrusion detection method that the application provides a kind of localized target to filter can be realized the filtration to the moving target of specific size quickly and easily, need not the special messenger and demarcates in scene, does not also need to calculate the depth of field of scene.
According to the application's first aspect, the application provides a kind of target intrusion detection method, comprising:
Initialization step obtains video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area;
Calculation procedure, the detected activity target, according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing described at least one line segment allows area and the maximum area that allows;
Determining step judges whether the area of described moving target allows area greater than described minimum permission area and less than described maximum, if then described moving target is effective target, otherwise described moving target is invalid target.
In one embodiment, the quantity of described lines is one; Described calculation procedure comprises:
When detected activity target, the predetermined point on the described moving target overlapped with point on the described line segment, according to set minimum filter area and maximum filtering area, the minimum of calculating described point allowed area and the maximum area that allows.
Further, an end points of the described line segment of predetermined point on described moving target distance is more near, and the described minimum area that allows is more near the minimum filter area of described end points, and the described maximum area that allows is more near the maximum filtering area of described end points.
Preferably,
The formula that the calculating of described minimum permission area is adopted is:
Spmin=D1*(S2min-S1min)/D+S1min，
Perhaps, Spmin=D2* (S1min-S2min)/D+S2min,
Wherein, Spmin is the minimum area that allows, S1min and S2min are respectively the default first minimum filter area and the second minimum filter area, D1 is the distance of first end points of the described line segment of predetermined point distance on the described moving target, D2 is the distance of second end points of the described line segment of predetermined point distance on the described moving target, and D is first end points of described line segment and the distance between second end points;
The formula that the calculating of described maximum permission area is adopted is:
Spmax=D1*(S2max-S1max)/D+S1max，
Perhaps, Spmax=D2* (S1max-S2max)/D+S2max,
Wherein, Spmax is the minimum area that allows, and S1max and S2max are respectively the default first minimum filter area and the second minimum filter area.
In another kind of embodiment, the quantity of described at least one line segment is many and constitutes a closed region;
Described calculation procedure comprises:
The detected activity target determines that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of described closed region and second intersection point of second line segment;
According to minimum filter area and the maximum filtering area of two end points of described article one line segment, the minimum of calculating described first intersection point allows area and the maximum area that allows;
According to minimum filter area and the maximum filtering area of two end points of described second line segment, the minimum of calculating described second intersection point allows area and the maximum area that allows;
Minimum according to described first intersection point allows area and the maximum minimum of area and described second intersection point that allows to allow area and the maximum area that allows, and the minimum of calculating the predetermined point position on the described moving target allows area and the maximum area that allows.
According to the application's second aspect, the application provides a kind of target invasion detecting device, comprising:
Initialization module is used for obtaining video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area;
Computing module, for detection of moving target, according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing described at least one line segment allows area and the maximum area that allows;
Judge module is used for judging whether the area of described moving target allows area greater than described minimum permission area and less than described maximum, if then described moving target is effective target, otherwise described moving target is invalid target.
In one embodiment, the quantity of described lines is one; Described computing module comprises:
Detecting unit is for detection of moving target;
Minimum calculation unit, when overlapping with point on the described line segment for the predetermined point on described moving target, according to formula S pmin=D1* (S2min-S1min)/D+S1min or formula S pmin=D2* (S1min-S2min)/D+S2min, the minimum of calculating described point allows area, wherein, Spmin is the minimum area that allows, S1min and S2min are respectively the default first minimum filter area and the second minimum filter area, D1 is the distance of first end points of the described line segment of predetermined point distance on the described moving target, D2 is the distance of second end points of the described line segment of predetermined point distance on the described moving target, and D is first end points of described line segment and the distance between second end points;
The max calculation unit, be used for according to formula S pmax=D1* (S2max-S1maz)/D+S1max or formula S pmax=D2* (S1max-S2max)/D+S2max, the maximum of calculating described point allows area, wherein, Spmax is the maximum area that allows, and S1max and S2max are respectively the default first maximum filtering area and the second maximum filtering area.
In another kind of embodiment, the quantity of described at least one line segment is many and constitutes a closed region;
Described computing module comprises:
The intersection point determining unit, the detected activity target determines that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of described closed region and second intersection point of second line segment;
The first intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of described article one line segment, the minimum of calculating described first intersection point allows area and the maximum area that allows;
The second intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of described second line segment, the minimum of calculating described second intersection point allows area and the maximum area that allows;
The target computing unit, minimum according to described first intersection point allows area and the maximum minimum of area and described second intersection point that allows to allow area and the maximum area that allows, and the minimum of calculating the predetermined point position on the described moving target allows area and the maximum area that allows.
According to the application's second aspect, the application provides a kind of video monitoring system, and it comprises aforesaid target invasion detecting device.
The application's beneficial effect is: by the line segment of drawing and minimum filter area and the maximum filtering area preset at the line segment two ends, the minimum of present position allowed area and the maximum area that allows when the computational activity target was crossed institute's draw line segments, and the area of combining movement target is determined effective target and invalid target, whole testing process need not the special messenger and demarcates in scene, do not need to calculate the depth of field of scene yet, can detect the validity of target quickly and easily.
Description of drawings
Fig. 1 is the schematic flow sheet of the target intrusion detection method of a kind of embodiment of the application;
Fig. 2 is the synoptic diagram of a line segment drawing among a kind of embodiment of the application;
Fig. 3 is the synoptic diagram of three line segments triangular in shape of drawing among a kind of embodiment of the application;
The synoptic diagram that be pentagonal five line segments of Fig. 4 for drawing among a kind of embodiment of the application
Fig. 5 is the synoptic diagram of some the line segments that are the fence shape drawn among a kind of embodiment of the application.
Embodiment
By reference to the accompanying drawings the present invention is described in further detail below by embodiment.
At first some terms or the concept of using among each embodiment of the application made an explanation.If an end points on the line segment of drawing is first end points, another end points is second end points, then the first minimum filter area and the first maximum filtering area refer to minimum area and the maximum area that first end points allows, when moving target is passed first end points, if the area of moving target is greater than this minimum area and less than this maximum area, can judge that then active area is effective target, system can carry out corresponding operation as sound the alarm and warn etc. according to judged result; Similarly, the second minimum filter area and the second maximum filtering area refer to minimum area and the maximum area that second end points allows.These areas can be user preset value or the system default value of setting.
Each embodiment of the application does not need the special messenger to demarcate in scene, does not need to calculate the depth of field of scene yet, does not need match is carried out on the plane yet.The user only need set rule, and according to the definite scope of filtering target of rule, can realize the filtration to target.Even scene is made up of a plurality of planes or curved surface, also can easily realize filtering.The rule that sets comprises the line rule-like of stumbling, regional rule-like and fence rule-like.The line rule-like of stumbling refers to that the user draws out a line segment, and minimum filter area and the maximum filtering area of two end points of this line segment are set; The zone rule-like refers to that the user draws out many line segments and these line segments constitute the closed region, and minimum filter area and the maximum filtering area of two end points of each bar line segment are set; The fence rule-like refers to that the user draws out many continuous segments, and minimum filter area and the maximum filtering area of two end points of each bar line segment are set.
Embodiment 1:
Present embodiment provides a kind of target intrusion detection method, as shown in Figure 1, comprises following processing procedure:
Initialization step obtains video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area;
In the specific implementation of this step, a kind of simple effective method is: the user uses input equipment draw line segments in scene such as mouse or paintbrush, adopt the mode of mouse drag to draw minimum target at each end points place of line segment then and filter mad and maximum target filter frame, and calculate the area of filter frame, thereby obtain maximum filtering area and the minimum filter area of each end points.During other is realized, can adopt and for example eject dialog box is treated two end points of draw line segments for user's input coordinate and two end points minimum filter area and maximum filtering area separately.
Calculation procedure, the detected activity target, according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing the line segment of drawing allows area and the maximum area that allows;
Here, the detection of moving target can be adopted technical field of video processing object detection method commonly used, for example background subtraction method, signature tracking, optical flow method etc.A kind of method commonly used is the background subtraction method, mainly is by determining background image, use current image frame subtracting background image then, obtain the difference of scene, and this difference is exactly to want the moving target that obtains.
If only draw lines in the initialization step, in calculation procedure, when the predetermined point on the moving target for example central point when a some P on the line segment of drawing overlaps, the minimum that can calculate a P according to the minimum filter area that has arranged and maximum filtering area allows area and the maximum area that allows, wherein, predetermined point on the moving target is more near apart from an end points of line segment, the minimum of this predetermined point allows area more near the minimum filter area of this end points, and the maximum area that allows is more near the maximum filtering area of this end points.
Particularly, as shown in Figure 2, if the predetermined point of the moving target for example point that intersects of central point and institute's draw line segments is a some P, it is Spmin that the minimum of some P allows area, maximum permission area is Spmax, the minimum filter area of the first end points S1 of this that draw line segment is that S1min, maximum filtering area are S1max, the minimum filter area of the second end points S2 is that S2min, maximum filtering area are S2max, point P is first distance B 1 apart from the distance of end points S1, point P is second distance D2 apart from the distance of end points S2, and the distance between end points S1 and the end points S2 is D; Then,
The minimum computing formula of area Spmin that allows is:
Spmin=D1*(S2min-S1min)/D+S1min，
Perhaps, Spmin=D2* (S1min-S2min)/D+S2min;
The maximum computing formula of area Spmax that allows is:
Spmax=D1*(S2max-S1max)/D+S1max，
Perhaps, Spmax=D2* (S1max-S2max)/D+S2max.
If drawn many line segments in the initialization step, and these line segments constitute a closed region; Calculation procedure then comprises so: detected activity target at first, determine that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of this closed region and second intersection point of second line segment; Then, according to minimum filter area and the maximum filtering area of two end points of article one line segment, the minimum of calculating first intersection point allows area and the maximum area that allows; Then, according to minimum filter area and the maximum filtering area of two end points of second line segment, the minimum of calculating second intersection point allows area and the maximum area that allows; At last, allow area and maximum to allow area according to the minimum permission area of first intersection point and the minimum of maximum permission area and second intersection point, the minimum of the predetermined point position on the computational activity target allows area and maximum permission area.
For example the closed region of Gou Chenging is triangle, be that the user has drawn three line segments, as shown in Figure 3, leg-of-mutton three end points are respectively S1, S2 and S3, if the minimum filter area of end points S1 is S1min, the maximum filtering area is S1max, the minimum filter area of end points S2 is S2min, the maximum filtering area is S2max, the minimum filter area of end points S3 is S3min, the maximum filtering area is S3max, the predetermined point that enters the moving target in the closed region for example central point is a some C, intersection point through first line segment of arbitrary straight line of a C and closed region is a some M, and the intersection point of second line segment of this straight line and closed region is for putting a N; Then, according to end points S1 and S2 maximum filtering area and minimum filter area separately, the maximum of utilizing aforementioned formula can calculate a M allows area Smmax and the minimum area Smmin that allows, similarly, according to end points S2 and S3 maximum filtering area and minimum filter area separately, the maximum of utilizing aforementioned formula can calculate a N allows area Snmax and minimum to allow area Snmin, and then the application of aforementioned formula calculates maximum permission area Spmax and the minimum area Spmin that allows of some P on a M and the some N place straight line.
The closed region that for example constitutes is pentagon again, be that the user has drawn five line segments, as shown in Figure 4, pentagonal five end points are respectively S1, S2, S3, S4 and S5, these five end points minimum filter area and maximum filtering area separately is set equally, if the predetermined point that enters the moving target in the closed region for example central point is a some P, be a some M through the intersection point of arbitrary straight line of a C and first line segment of closed region, the intersection point of second line segment of this straight line and closed region is a N; Then, similarly, the maximum that can calculate a M allows the maximum of area Smmax and the minimum area Smmin of permission and some N to allow area Snmax and minimum to allow area Snmin, and then the application of aforementioned formula calculates maximum permission area Spmax and the minimum area Spmin that allows of some P on a M and the some N place straight line.
Certainly, if drawn many line segments in the initialization step, but these line segments do not constitute a closed region, and as shown in Figure 5, then this moment, calculation procedure also adopted the way of only having drawn a line segment as the aforementioned to calculate, and no longer repeated.
Use same computing method, can calculate the maximum of certain point in quadrilateral, pentagon etc. the polygon, minimum filter value, thereby can be implemented in the closed region target is effectively filtered.
Determining step judges whether the area of moving target allows area and allow area less than maximum greater than minimum, if then moving target is effective target, otherwise moving target is invalid target.
The area of moving target can be determined by aforementioned detected activity target, specifically can not be described further with reference to existing target detection technique.
Present embodiment does not carry out goal filtering at whole scene, only need to draw some line segments at the area-of-interest place, and two end points of every line segment are arranged maximum filtering area and minimum filter area respectively, allow area and the minimum area that allows by the maximum of calculating the point in the closed region that point on the line segment or line segment surround, judge the areal extent of moving target, thereby can determine that moving target is effective target or invalid target, this method is simple and easy to use and is very flexible, do not need the special messenger in scene, to demarcate, do not need to calculate the depth of field of scene yet, do not need match is carried out on the plane yet.
Embodiment 2:
Present embodiment provides a kind of target invasion detecting device, and it comprises initialization module, computing module and judge module.Wherein, initialization module is used for obtaining video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area; Computing module is for detection of moving target, and according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing institute's draw line segments allows area and the maximum area that allows; Judge module is used for judging whether the area of moving target allows area and allow area less than maximum greater than minimum, if then moving target is effective target, otherwise moving target is invalid target.
In a kind of realization, the quantity of the lines of drawing is one; This moment, computing module specifically comprised:
Detecting unit is for detection of moving target;
Minimum calculation unit, when overlapping with point on the described line segment for the predetermined point on moving target, the minimum of calculating this point according to formula allows area;
The max calculation unit is used for allowing area according to the maximum of calculating this point.
In another kind of the realization, the quantity of the lines of drawing is many and this closed region of many line segments formations, and this moment, computing module specifically comprised:
The intersection point determining unit, the detected activity target determines that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of this closed region and second intersection point of second line segment;
The first intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of article one line segment, the minimum of calculating first intersection point allows area and the maximum area that allows;
The second intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of second line segment, the minimum of calculating second intersection point allows area and the maximum area that allows;
The target computing unit allows area and maximum to allow area according to the minimum permission area of first intersection point and the minimum of maximum permission area and second intersection point, and the minimum of the predetermined point position on the computational activity target allows area and maximum permission area.
More than each module and correlation unit can realize with reference to the method institute corresponding content of previous embodiment 1, do not do and repeat.
Embodiment 3:
Present embodiment provides a kind of video monitoring system, and it comprises the target invasion detecting device of embodiment 2.
It will be appreciated by those skilled in the art that, the all or part of step of the whole bag of tricks can instruct related hardware to finish by program in the above-mentioned embodiment, this program can be stored in the computer-readable recording medium, and storage medium can comprise: ROM (read-only memory), random access memory, disk or CD etc.
Above content be in conjunction with concrete embodiment to further describing that the present invention does, can not assert that concrete enforcement of the present invention is confined to these explanations.For the general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, can also make some simple deduction or replace.
Claims (9)
1. a target intrusion detection method is characterized in that, comprising:
Initialization step obtains video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area;
Calculation procedure, the detected activity target, according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing described at least one line segment allows area and the maximum area that allows;
Determining step judges whether the area of described moving target allows area greater than described minimum permission area and less than described maximum, if then described moving target is effective target, otherwise described moving target is invalid target.
2. target intrusion detection method as claimed in claim 1 is characterized in that, the quantity of described lines is one; Described calculation procedure comprises:
When detected activity target, the predetermined point on the described moving target overlapped with point on the described line segment, according to set minimum filter area and maximum filtering area, the minimum of calculating described point allowed area and the maximum area that allows.
3. target intrusion detection method as claimed in claim 2, it is characterized in that, an end points of the described line segment of predetermined point distance on the described moving target is more near, the described minimum area that allows is more near the minimum filter area of described end points, and the described maximum area that allows is more near the maximum filtering area of described end points.
4. target intrusion detection method as claimed in claim 3 is characterized in that,
The formula that the calculating of described minimum permission area is adopted is:
Spmin=D1*(S2min-S1min)/D+S1min，
Perhaps, Spmin=D2* (S1min-S2min)/D+S2min,
Wherein, Spmin is the minimum area that allows, S1min and S2min are respectively the default first minimum filter area and the second minimum filter area, D1 is the distance of first end points of the described line segment of predetermined point distance on the described moving target, D2 is the distance of second end points of the described line segment of predetermined point distance on the described moving target, and D is first end points of described line segment and the distance between second end points;
The formula that the calculating of described maximum permission area is adopted is:
Spmax=D1*(S2max-S1max)/D+S1max，
Perhaps, Spmax=D2* (S1max-S2max)/D+S2max,
Wherein, Spmax is the minimum area that allows, and S1max and S2max are respectively the default first minimum filter area and the second minimum filter area.
5. target intrusion detection method as claimed in claim 1 is characterized in that, the quantity of described at least one line segment is many and constitutes a closed region;
Described calculation procedure comprises:
The detected activity target determines that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of described closed region and second intersection point of second line segment;
According to minimum filter area and the maximum filtering area of two end points of described article one line segment, the minimum of calculating described first intersection point allows area and the maximum area that allows;
According to minimum filter area and the maximum filtering area of two end points of described second line segment, the minimum of calculating described second intersection point allows area and the maximum area that allows;
Minimum according to described first intersection point allows area and the maximum minimum of area and described second intersection point that allows to allow area and the maximum area that allows, and the minimum of calculating the predetermined point position on the described moving target allows area and the maximum area that allows.
6. a target invasion detecting device is characterized in that, comprising:
Initialization module is used for obtaining video image, receives the operator at least one line segment of the area-of-interest place of video image drafting and at two end points of each bar line segment set minimum filter area and maximum filtering area;
Computing module, for detection of moving target, according to set minimum filter area and maximum filtering area, the minimum of calculating moving target present position when crossing described at least one line segment allows area and the maximum area that allows;
Judge module is used for judging whether the area of described moving target allows area greater than described minimum permission area and less than described maximum, if then described moving target is effective target, otherwise described moving target is invalid target.
7. target invasion detecting device as claimed in claim 6 is characterized in that, the quantity of described lines is one; Described computing module comprises:
Detecting unit is for detection of moving target;
Minimum calculation unit, when overlapping with point on the described line segment for the predetermined point on described moving target, according to formula S pmin=D1* (S2min-S1min)/D+S1min or formula S pmin=D2* (S1min-S2min)/D+S2min, the minimum of calculating described point allows area, wherein, Spmin is the minimum area that allows, S1min and S2min are respectively the default first minimum filter area and the second minimum filter area, D1 is the distance of first end points of the described line segment of predetermined point distance on the described moving target, D2 is the distance of second end points of the described line segment of predetermined point distance on the described moving target, and D is first end points of described line segment and the distance between second end points;
The max calculation unit, be used for according to formula S pmax=D1* (S2max-S1maz)/D+S1max or formula S pmax=D2* (S1max-S2max)/D+S2max, the maximum of calculating described point allows area, wherein, Spmax is the maximum area that allows, and S1max and S2max are respectively the default first maximum filtering area and the second maximum filtering area.
8. target invasion detecting device as claimed in claim 6 is characterized in that, the quantity of described at least one line segment is many and constitutes a closed region;
Described computing module comprises:
The intersection point determining unit, the detected activity target determines that arbitrary straight line in predetermined point place on the moving target intersects at first intersection point of first line segment of described closed region and second intersection point of second line segment;
The first intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of described article one line segment, the minimum of calculating described first intersection point allows area and the maximum area that allows;
The second intersection point calculation unit, according to minimum filter area and the maximum filtering area of two end points of described second line segment, the minimum of calculating described second intersection point allows area and the maximum area that allows;
The target computing unit, minimum according to described first intersection point allows area and the maximum minimum of area and described second intersection point that allows to allow area and the maximum area that allows, and the minimum of calculating the predetermined point position on the described moving target allows area and the maximum area that allows.
9. a video monitoring system is characterized in that, comprises each described target invasion detecting device as claim 6-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310135939.4A CN103279943B (en) | 2013-04-18 | 2013-04-18 | Target invasion detection method and device, and video monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310135939.4A CN103279943B (en) | 2013-04-18 | 2013-04-18 | Target invasion detection method and device, and video monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103279943A true CN103279943A (en) | 2013-09-04 |
| CN103279943B CN103279943B (en) | 2017-01-25 |
Family
ID=49062450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310135939.4A Expired - Fee Related CN103279943B (en) | 2013-04-18 | 2013-04-18 | Target invasion detection method and device, and video monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103279943B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104007047A (en) * | 2014-06-17 | 2014-08-27 | 青岛理工大学 | Method for identifying granular system power transmission chain |
| CN104021570B (en) * | 2014-06-04 | 2016-11-09 | 电子科技大学 | Directive in a kind of video cross the border and mix line detecting method |
| CN106802789A (en) * | 2015-11-26 | 2017-06-06 | 中国电信股份有限公司 | Action scope intersects detection method and intersects the device of detection for action scope |
| CN110070606A (en) * | 2019-04-01 | 2019-07-30 | 浙江大华技术股份有限公司 | Space method for drafting, object detection method, detection device and storage medium |
| CN111739334A (en) * | 2019-03-25 | 2020-10-02 | 姚琴 | Method for identifying parking station based on geographic information and parking station judgment device |
| CN113343856A (en) * | 2021-06-09 | 2021-09-03 | 北京容联易通信息技术有限公司 | Image recognition method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090262230A1 (en) * | 2008-04-21 | 2009-10-22 | Sony Corporation | Image pickup apparatus and method for controlling ranging area |
| CN101835035A (en) * | 2010-06-04 | 2010-09-15 | 天津市亚安科技电子有限公司 | Regional invasion real-time detection method |
-
2013
- 2013-04-18 CN CN201310135939.4A patent/CN103279943B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090262230A1 (en) * | 2008-04-21 | 2009-10-22 | Sony Corporation | Image pickup apparatus and method for controlling ranging area |
| CN101835035A (en) * | 2010-06-04 | 2010-09-15 | 天津市亚安科技电子有限公司 | Regional invasion real-time detection method |
Non-Patent Citations (3)
| Title |
|---|
| J.L.CASTRO等: "Intelligent surveillance system with integration of heterogeneous information for intrusion detection", 《EXPERT SYSTEMS WITH APPLICATIONS》, vol. 38, no. 9, 30 September 2011 (2011-09-30), pages 11182 - 11192, XP028200619, DOI: doi:10.1016/j.eswa.2011.02.165 * |
| 吴文平: "在复杂场景下的入侵检测", 《中国优秀硕士学位论文全文数据库》, 15 July 2012 (2012-07-15), pages 40 - 43 * |
| 路红等: "一种自适应运动目标检测方法", 《电子测量与仪器学报》, vol. 22, no. 4, 31 August 2008 (2008-08-31), pages 7 - 11 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021570B (en) * | 2014-06-04 | 2016-11-09 | 电子科技大学 | Directive in a kind of video cross the border and mix line detecting method |
| CN104007047A (en) * | 2014-06-17 | 2014-08-27 | 青岛理工大学 | Method for identifying granular system power transmission chain |
| CN104007047B (en) * | 2014-06-17 | 2016-01-27 | 青岛理工大学 | The dynamofluidal recognition methods of a kind of granular system |
| CN106802789A (en) * | 2015-11-26 | 2017-06-06 | 中国电信股份有限公司 | Action scope intersects detection method and intersects the device of detection for action scope |
| CN111739334A (en) * | 2019-03-25 | 2020-10-02 | 姚琴 | Method for identifying parking station based on geographic information and parking station judgment device |
| CN110070606A (en) * | 2019-04-01 | 2019-07-30 | 浙江大华技术股份有限公司 | Space method for drafting, object detection method, detection device and storage medium |
| CN110070606B (en) * | 2019-04-01 | 2023-01-03 | 浙江大华技术股份有限公司 | Space rendering method, target detection method, detection device, and storage medium |
| CN113343856A (en) * | 2021-06-09 | 2021-09-03 | 北京容联易通信息技术有限公司 | Image recognition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103279943B (en) | 2017-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103279943A (en) | Target invasion detection method and device, and video monitoring system | |
| CN107194967B (en) | Human body tumbling detection method and device based on Kinect depth image | |
| CN105286871B (en) | Video processing-based body height measurement method | |
| US9875408B2 (en) | Setting apparatus, output method, and non-transitory computer-readable storage medium | |
| WO2016049493A1 (en) | Real-time warning for distracted pedestrians with smartphones | |
| CN104978751B (en) | Detection method of crossing the border based on camera angle | |
| WO2016104395A1 (en) | Crowd monitoring system | |
| JP2016201756A5 (en) | ||
| CN104902246A (en) | Video monitoring method and device | |
| CN104954747B (en) | Video monitoring method and device | |
| US20180260964A1 (en) | System and method for detecting moving object in an image | |
| KR101921610B1 (en) | Method and Apparatus for Monitoring Objects from Video | |
| US20160021309A1 (en) | Image based surveillance system | |
| WO2016203078A2 (en) | Ir or thermal image enhancement method based on background information for video analysis | |
| JP2017195552A5 (en) | ||
| RU2017131075A (en) | SYSTEMS AND METHODS FOR DETECTING AN ALARM OBJECT TRAJECTORIES | |
| KR20150115287A (en) | Camera modeling system | |
| KR20140110484A (en) | Risk behavior detection method using image information | |
| Ghilardi et al. | A new approach for automatic detection of tactile paving surfaces in sidewalks | |
| Yajai et al. | Fall detection using directional bounding box | |
| JP2009239347A5 (en) | ||
| KR101840042B1 (en) | Multi-Imaginary Fence Line Setting Method and Trespassing Sensing System | |
| KR101889051B1 (en) | Method for increasing reliability in monitoring systems | |
| JP7289198B2 (en) | Fire detection device and fire detection method | |
| KR101960741B1 (en) | Method for Setting Event Rule According to Interested Boundary and Apparatus for Monitoring Event Using The Method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170125 Termination date: 20180418 |