CN101339688B - Intrusion checking method and system - Google Patents
Intrusion checking method and system Download PDFInfo
- Publication number
- CN101339688B CN101339688B CN2008101189956A CN200810118995A CN101339688B CN 101339688 B CN101339688 B CN 101339688B CN 2008101189956 A CN2008101189956 A CN 2008101189956A CN 200810118995 A CN200810118995 A CN 200810118995A CN 101339688 B CN101339688 B CN 101339688B
- Authority
- CN
- China
- Prior art keywords
- moving target
- limit
- prohibited area
- human body
- unit
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 32
- 238000001514 detection method Methods 0.000 claims abstract description 58
- 238000012544 monitoring process Methods 0.000 claims description 38
- 230000009545 invasion Effects 0.000 claims description 31
- 238000012360 testing method Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000007789 sealing Methods 0.000 claims description 13
- 239000004744 fabric Substances 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 3
- 230000007123 defense Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009017 pursuit movement Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention discloses an intrusion detection method and a system thereof, wherein, the intrusion detection method comprises the following steps: an video image of a monitored scene is acquired; then the video image is analyzed to acquire a moving area in the monitored scene; a forbidden zone is detected to judge whether a moving target exists in the forbidden zone according to the moving area and a preset forbidden zone in the monitored scene; and the detection result is adopted to determine where intrusion exists. The technical proposal, namely, the intrusion detection method and the system thereof disclosed by the invention can improve the effectiveness of the intrusion detection.
Description
Technical field
The present invention relates to video processing technique, relate in particular to a kind of intrusion detection method and system based on video.
Background technology
Intrusion detection is an important application direction in intelligent video monitoring field; Common application comprise warning line leap detection, frontier defense line cross that swarming into of detection, military base detected and dangerous area be strayed into detection etc., have great significance for frontier defense safety and military base warning etc.
Present intrusion detection normally utilizes sensor (like infrared sensor etc.) to detect or manpower detects, but because the induction region of sensor is limited, therefore can only among a small circle, use; And manpower detects owing to receive the restriction of human factor and attacked by the invador, therefore has unreliability and insecurity.Thus it is clear that, still do not have a kind of more effective intrusion detection method in the prior art.
Summary of the invention
In view of this, on the one hand a kind of intrusion detection method is provided among the present invention, a kind of intruding detection system is provided on the other hand, so that improve the validity of intrusion detection.
Intrusion detection method provided by the present invention comprises:
Obtain the video image of monitoring scene;
Said video image is analyzed, obtained the moving region in the monitoring scene;
Limit of the prohibited area according to demarcating in advance in said moving region and the monitoring scene detects whether there is moving target in the said limit of the prohibited area;
According to testing result, determine whether to exist invasion;
Wherein, said according to the limit of the prohibited area of demarcating in advance in moving region in the monitoring scene and the monitoring scene, detect and whether exist moving target to comprise in the said limit of the prohibited area:
In monitoring scene, demarcate limit of the prohibited area in advance with sealing outer edge;
With any point in the said moving region is that starting point is made a ray to any direction;
If the sealing outer edge of said ray and said limit of the prohibited area has the odd number intersection point, then confirm to have moving target in the said limit of the prohibited area; Otherwise, confirm not exist in the said limit of the prohibited area moving target.
Preferably, said according to testing result, determine whether that the appearance invasion is: when in detecting said limit of the prohibited area, having moving target, confirm to exist invasion.
Preferably, said in detecting said limit of the prohibited area, have moving target after, confirm to exist before the invasion, whether this method: detecting said moving target is human body if further comprising, if be human body, then confirm to exist to invade.
Preferably, whether the said moving target of said detection is that human body comprises:
Obtain N width of cloth human body image;
Calculate the gradient orientation histogram of every width of cloth human body image respectively, obtain N gradient orientation histogram;
Calculate the average Hista of a said N gradient orientation histogram;
Calculate the gradient orientation histogram Hist of said moving target;
Calculate the difference of said Hist and said Hista, if the absolute value of said difference, confirms then that said moving target is a human body less than preset threshold value.
Preferably, in detecting said limit of the prohibited area, have moving target after, confirm to exist before the invasion, this method further comprises: said moving target is followed the tracks of, when in definite continuous N frame, all said moving target occurring, confirmed to exist and invade.
Intruding detection system provided by the present invention comprises:
Image acquisition units is used to obtain the video image of monitoring scene;
Motion detection unit is used for said video image is analyzed, and obtains the moving region in the monitoring scene;
The regional analysis unit is used for the limit of the prohibited area demarcated in advance according to said moving region and monitoring scene, detects whether there is moving target in the said limit of the prohibited area;
The result confirms the unit, is used for according to testing result, determines whether to exist invasion;
Wherein, said regional analysis unit comprises:
Demarcate the record subelement, be used for being recorded in the limit of the prohibited area that monitoring scene is demarcated in advance with sealing outer edge;
Ray is handled subelement, and any point that is used for said moving region is that starting point is made a ray to any direction;
The intersection point detection sub-unit is used to detect the intersection point number of the sealing outer edge of said ray and said limit of the prohibited area;
The target judgment sub-unit is used for when said intersection point number is odd number, confirming to have moving target in the said limit of the prohibited area; Otherwise, confirm not exist in the said limit of the prohibited area moving target.
Preferably, this system further comprises: the human detection unit, be used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit, and whether be human body, and testing result is offered the result confirm the unit if detecting said moving target;
Said result confirms the unit when said moving target is human body, confirms to exist invasion.
Preferably, said human detection unit comprises:
The histogram calculation subelement is used for calculating respectively the gradient orientation histogram of N width of cloth human body image, obtains N gradient orientation histogram, and calculates the gradient orientation histogram Hist of said moving target;
The mean value computation subelement is used to calculate the average Hista of the pairing N of a said N width of cloth human body image gradient orientation histogram;
The difference computation subunit is used to calculate the difference of said Hist and said Hista;
Human body is analyzed subelement, when being used for absolute value in said difference less than preset threshold value, confirms that said moving target is a human body.
Preferably; This system further comprises: the interframe analytic unit; Be used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit; Said moving target is followed the tracks of, whether detected and said moving target all occurs in the continuous N frame, and testing result is offered the result confirm the unit;
When said result confirms that the unit all said moving target occurs in the continuous N frame, confirm to exist invasion.
Can find out from such scheme; Through obtaining the video image of monitoring scene, and the video image that is obtained is analyzed among the present invention, obtained the moving region in the monitoring scene; The position relation of the limit of the prohibited area of demarcating in advance in said then moving region and the monitoring scene; Confirm whether there is moving target in the limit of the prohibited area, and, judge whether to exist invasion according to definite result.It is thus clear that the technical scheme among the present invention need not to use sensor, therefore do not receive the distance restraint of sensor, enlarged sensing range; Replace the detection of manpower in addition again, improved the reliability and the security that detect, therefore improved the validity that detects.
Description of drawings
Fig. 1 is the exemplary process diagram of intrusion detection method in the embodiment of the invention.
Fig. 2 is an exemplary block diagram of intruding detection system in the embodiment of the invention.
Fig. 3 is the inner structure synoptic diagram of regional analysis unit in the system shown in Figure 2.
Fig. 4 is another exemplary block diagram of intruding detection system in the embodiment of the invention.
Fig. 5 is the inner structure synoptic diagram of human detection unit in the system shown in Figure 4.
Fig. 6 is another exemplary block diagram of intruding detection system in the embodiment of the invention.
Fig. 7 a and Fig. 7 b are two exemplary block diagram again of intruding detection system in the embodiment of the invention.
Embodiment
A kind of Intrusion Detection Technique based on video is proposed in the present embodiment; Promptly through obtaining the video image of monitoring scene; And said video image analyzed, obtain the moving region in the monitoring scene, then according to the position relation of the limit of the prohibited area of demarcating in advance in said moving region and the monitoring scene; Detect in the limit of the prohibited area whether have moving target, determine whether to exist invasion according to testing result afterwards.
For making the object of the invention, technical scheme and advantage clearer, below in conjunction with embodiment and accompanying drawing, to further explain of the present invention.
Fig. 1 is the exemplary process diagram of intrusion detection method in the embodiment of the invention.As shown in Figure 1, this flow process comprises the steps:
In this step, can come to take in real time and catch the video image of monitoring scene through IP Camera or traditional camera or the special-purpose high-resolution first-class image capture device of making a video recording.
In this step, the method for obtaining the moving region has a lot, specifically can adopt multiple implementation of the prior art, for example, can adopt motion detection technique such as optical flow method, frame-to-frame differences point-score, background subtraction point-score to detect the moving region in the monitoring scene.
In the present embodiment, can at first carry out initialization, promptly in the monitoring scene of video image, calibrate limit of the prohibited area in advance limit of the prohibited area.
Concrete implementation procedure in this step can adopt accomplished in many ways of the prior art.For example, can at first calculate the positional information of moving region, like center position, width and height etc., position and the pairing boundary position of limit of the prohibited area with the moving region compares then, judges whether the moving region is within the limit of the prohibited area.
In addition, a kind of simple effective method also is provided in the present embodiment.This method based on judge in how much a point whether the method in certain closed region realize, as follows:
At first, when demarcating limit of the prohibited area, limit of the prohibited area is expressed as a geometric configuration with sealing outer edge.Wherein, this sealing outer edge can be an arbitrary polygon, also can be shapes of any curves, like circular, oval, irregular curve shape.
Then; With any point in the detected moving region (like central point) is that starting point is made a ray to any direction; Judge the intersection point number of the sealing outer edge of this ray and said limit of the prohibited area then,, prove that then this is within limit of the prohibited area if the intersection point number is an odd number; And then can confirm this moving region in limit of the prohibited area, thereby can confirm to exist in the limit of the prohibited area moving target.If the intersection point number is an even number, perhaps be 0, then proof this no longer within the limit of the prohibited area, and then can confirm this moving region not in limit of the prohibited area, thereby can confirm not exist in the limit of the prohibited area moving target.
Whether because intrusion detection is generally in order to prevent that unauthorized person from getting into the forbidden zone, so comprises step 104 in the present embodiment, detecting said moving target is human body, if be human body, then execution in step 105; Otherwise, return execution in step 102.
In this step; The method that detects moving target and whether be human body can have multiple; The most effective human body detecting method is based on the detection method of gradient orientation histogram and Adaboost at present, but the operand of this method is bigger, the application that influence is handled in real time; Therefore a kind of human body monitoring method of simplification has been proposed in the present embodiment, as follows:
At first obtain N width of cloth human body image, and calculate the gradient orientation histogram of every width of cloth human body image respectively, obtain N gradient orientation histogram { Hist
1, Hist
2..., Hist
N, and calculate the average of this N gradient orientation histogram
Wherein, N is the integer greater than 1.
Then; Calculate the gradient orientation histogram Hist of moving target; And the difference
of calculating Hist and said Hista as if the absolute value of this difference less than preset threshold value T; Promptly
sets up; Can confirm that then this moving target is a human body, otherwise be non-human body.Wherein, threshold value T can adopt the whole bag of tricks setting according to actual needs.
For fear of owing to the flase drop to moving target in the single-frame images causes false-alarm, after having judged moving target entering limit of the prohibited area on the single-frame images, come the generation of verification invasion through multiframe pursuit movement target in the present embodiment.Promptly comprise step 105, said moving target is followed the tracks of, determine whether all to occur in the continuous N frame said moving target, if then execution in step 106; Otherwise, return execution in step 102.
In this step, can use various method for tracking target commonly used that moving target is followed the tracks of (when specifically realizing, can follow the tracks of the moving region), such as mean shift method, particle filter or the like.In tracing process,, confirm that then invasion takes place if find certain continuous N frame invasion forbidden zone, moving region.Wherein, M is the integer greater than 1.
Step 106 confirms to exist invasion.At this moment, warning such as can report to the police is handled.
In the above-mentioned flow process, step 104 and step 105 do not have absolute precedence relationship, also can first execution in step 105 in the promptly above-mentioned flow process, and execution in step 104 again.After confirming earlier that promptly same moving target appears in the continuous N frame, judge again whether this moving target is human body.In concrete the application, also can not comprise step 104 and step 105, promptly in step 103, detect have moving target in the limit of the prohibited area after, can execution in step 106, confirm to exist and invade.
More than the intrusion detection method in the embodiment of the invention is described in detail, again the intruding detection system in the embodiment of the invention is described in detail below.
Fig. 2 is the exemplary block diagram of intruding detection system in the embodiment of the invention.As shown in Figure 2, this system comprises: image acquisition units, motion detection unit, regional analysis unit and result confirm the unit.
Wherein, image acquisition units is used to obtain the video image of monitoring scene.
Motion detection unit is used for said video image is analyzed, and obtains the moving region in the monitoring scene.
The position relation of the limit of the prohibited area that the regional analysis unit is used for demarcating in advance according to said moving region and monitoring scene detects in the limit of the prohibited area whether have moving target.
The result confirms that the unit is used for according to testing result, determines whether to exist invasion.
During concrete the realization, the inner structure of regional analysis unit can have multiple way of realization, and Fig. 3 illustrates a kind of way of realization wherein, comprising: demarcate record subelement, ray processing subelement, intersection point detection sub-unit and target judgment sub-unit.
Wherein, demarcate the record subelement and be used for being recorded in the limit of the prohibited area that monitoring scene is demarcated in advance with sealing outer edge.
Any point that ray processing subelement is used for said moving region is that starting point is made a ray to any direction.
The intersection point detection sub-unit is used to detect the intersection point number of the sealing outer edge of said ray and said limit of the prohibited area.
The target judgment sub-unit is used for when said intersection point number is odd number, confirming to have moving target in the said limit of the prohibited area; Otherwise, confirm not exist in the said limit of the prohibited area moving target.
Consistent with method shown in Figure 1; System in the present embodiment can be as shown in Figure 4, on the basis of system shown in Figure 2, further comprises: the human detection unit is used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit; Whether detect said moving target is human body; And testing result is offered the result confirm the unit, the result confirms the unit when said moving target is human body, confirms to exist invasion; Otherwise, can confirm not exist invasion.
During concrete the realization, the inner structure of human detection unit can be as shown in Figure 5, comprising: histogram calculation subelement, mean value computation subelement, difference computation subunit and human body are analyzed subelement.
Wherein, the histogram calculation subelement is used for calculating respectively the gradient orientation histogram of N width of cloth human body image, obtains N gradient orientation histogram, and calculates the gradient orientation histogram Hist of said moving target.
The mean value computation subelement is used to calculate the average Hista of the pairing N of a said N width of cloth human body image gradient orientation histogram.
The difference computation subunit is used to calculate the difference of said Hist and said Hista.
When human body is analyzed subelement and is used for absolute value in said difference less than preset threshold value, confirm that said moving target is a human body.
In addition, the system in the present embodiment also can be as shown in Figure 6, on the basis of system shown in Figure 2, further comprises: the interframe analytic unit; Be used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit; Said moving target is followed the tracks of, whether detected and said moving target all occurs in the continuous N frame, and testing result is offered the result confirm the unit; When the result confirms that the unit all said moving target occurs in the continuous N frame, confirm to exist invasion; Otherwise, can confirm not exist invasion.
In addition, the system in the present embodiment also can further comprise on the basis of system shown in Figure 2: human detection unit and interframe analytic unit.
During concrete the realization, can shown in Fig. 7 a, on the basis of system shown in Figure 4, confirm to be provided with between the unit interframe analytic unit in human detection unit and result.At this moment; The executor of system elder generation health check-up measurement unit, the human detection unit is after detecting moving target and being human body, and system continues to carry out the interframe analytic unit; The interframe analytic unit determines whether in the continuous N frame, all to occur same moving target; And result notification confirmed the unit to the result, when the result confirms that the unit all said moving target occurs in the continuous N frame, confirm to exist invasion.
Perhaps, also can shown in Fig. 7 b, confirm to be provided with between the unit human detection unit at interframe analytic unit shown in Figure 6 and result.At this moment; System carries out earlier the interframe analytic unit, if when confirming in the continuous N frame, all same moving target to occur, system continues executor's health check-up measurement unit; After whether human detection unit detection moving target is human body; Testing result notified to the result confirm the unit, the result confirms the unit when moving target is human body, confirms to exist invasion.
The specific operation process of each unit in the embodiment of the invention system can be in the embodiment of the invention corresponding specific operation process in the intrusion detection method consistent, give unnecessary details no longer one by one here.
Above-described specific embodiment; The object of the invention, technical scheme and beneficial effect have been carried out further explain, and institute it should be understood that the above is merely preferred embodiment of the present invention; Be not to be used to limit protection scope of the present invention; All within spirit of the present invention and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. an intrusion detection method is characterized in that, this method comprises:
Obtain the video image of monitoring scene;
Said video image is analyzed, obtained the moving region in the monitoring scene;
Limit of the prohibited area according to demarcating in advance in said moving region and the monitoring scene detects whether there is moving target in the said limit of the prohibited area;
According to testing result, determine whether to exist invasion;
Wherein, said according to the limit of the prohibited area of demarcating in advance in moving region in the monitoring scene and the monitoring scene, detect and whether exist moving target to comprise in the said limit of the prohibited area:
In monitoring scene, demarcate limit of the prohibited area in advance with sealing outer edge;
With any point in the said moving region is that starting point is made a ray to any direction;
If the sealing outer edge of said ray and said limit of the prohibited area has the odd number intersection point, then confirm to have moving target in the said limit of the prohibited area; Otherwise, confirm not exist in the said limit of the prohibited area moving target.
2. the method for claim 1 is characterized in that, and is said according to testing result, determines whether to occur invasion to be: when in detecting said limit of the prohibited area, having moving target, confirm to exist invasion.
3. method as claimed in claim 2 is characterized in that, said in detecting said limit of the prohibited area, have moving target after; Confirm to exist before the invasion; Whether this method: detecting said moving target is human body if further comprising, if be human body, then confirm to exist invasion.
4. method as claimed in claim 3 is characterized in that, whether the said moving target of said detection is that human body comprises:
Obtain N width of cloth human body image;
Calculate the gradient orientation histogram of every width of cloth human body image respectively, obtain N gradient orientation histogram;
Calculate the average Hista of a said N gradient orientation histogram;
Calculate the gradient orientation histogram Hist of said moving target;
Calculate the difference of said Hist and said Hista, if the absolute value of said difference, confirms then that said moving target is a human body less than preset threshold value.
5. method as claimed in claim 2; It is characterized in that; After in detecting said limit of the prohibited area, having moving target, confirm to exist before the invasion, this method further comprises: said moving target is followed the tracks of; When in definite continuous N frame, all said moving target occurring, confirm to exist invasion.
6. an intruding detection system is characterized in that, this system comprises:
Image acquisition units is used to obtain the video image of monitoring scene;
Motion detection unit is used for said video image is analyzed, and obtains the moving region in the monitoring scene;
The regional analysis unit is used for the limit of the prohibited area demarcated in advance according to said moving region and monitoring scene, detects whether there is moving target in the said limit of the prohibited area;
The result confirms the unit, is used for according to testing result, determines whether to exist invasion;
Wherein, said regional analysis unit comprises:
Demarcate the record subelement, be used for being recorded in the limit of the prohibited area that monitoring scene is demarcated in advance with sealing outer edge;
Ray is handled subelement, and any point that is used for said moving region is that starting point is made a ray to any direction;
The intersection point detection sub-unit is used to detect the intersection point number of the sealing outer edge of said ray and said limit of the prohibited area;
The target judgment sub-unit is used for when said intersection point number is odd number, confirming to have moving target in the said limit of the prohibited area; Otherwise, confirm not exist in the said limit of the prohibited area moving target.
7. system as claimed in claim 6; It is characterized in that; This system further comprises: the human detection unit; Whether be used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit, detecting said moving target is human body, and testing result is offered the result confirms the unit;
Said result confirms the unit when said moving target is human body, confirms to exist invasion.
8. system as claimed in claim 7 is characterized in that, said human detection unit comprises:
The histogram calculation subelement is used for calculating respectively the gradient orientation histogram of N width of cloth human body image, obtains N gradient orientation histogram, and calculates the gradient orientation histogram Hist of said moving target;
The mean value computation subelement is used to calculate the average Hista of the pairing N of a said N width of cloth human body image gradient orientation histogram;
The difference computation subunit is used to calculate the difference of said Hist and said Hista;
Human body is analyzed subelement, when being used for absolute value in said difference less than preset threshold value, confirms that said moving target is a human body.
9. system as claimed in claim 6; It is characterized in that; This system further comprises: the interframe analytic unit, be used for detecting when having moving target in the said limit of the prohibited area in said regional analysis unit, and said moving target is followed the tracks of; Whether detect and said moving target all occurs in the continuous N frame, and testing result is offered the result confirm the unit;
When said result confirms that the unit all said moving target occurs in the continuous N frame, confirm to exist invasion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101189956A CN101339688B (en) | 2008-08-27 | 2008-08-27 | Intrusion checking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101189956A CN101339688B (en) | 2008-08-27 | 2008-08-27 | Intrusion checking method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101339688A CN101339688A (en) | 2009-01-07 |
| CN101339688B true CN101339688B (en) | 2012-01-11 |
Family
ID=40213747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008101189956A Active CN101339688B (en) | 2008-08-27 | 2008-08-27 | Intrusion checking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101339688B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835035B (en) * | 2010-06-04 | 2014-02-26 | 天津市亚安科技股份有限公司 | Regional invasion real-time detection method |
| CN102457657A (en) * | 2010-10-19 | 2012-05-16 | 鸿富锦精密工业（深圳）有限公司 | Camera device and method for carrying out human type detection by using the same |
| CN103177453B (en) * | 2011-12-22 | 2016-01-27 | 中国电信股份有限公司 | A kind of affair analytical method based on moving object edge characteristics and device |
| CN103369004A (en) * | 2012-03-30 | 2013-10-23 | 罗宁 | Method for carrying out security monitoring and resource management on building by using human sensors |
| CN106297129B (en) * | 2016-08-31 | 2019-07-16 | 浙江宇视科技有限公司 | A kind of implementation method and monitoring device of video monitoring |
| CN107705326A (en) * | 2017-09-15 | 2018-02-16 | 温州大学 | A kind of intrusion detection method that crosses the border in security sensitive region |
| CN107944883A (en) * | 2017-11-28 | 2018-04-20 | 蒙家革 | Honeybee shares cultural method and device |
| CN109905643A (en) * | 2017-12-08 | 2019-06-18 | 神讯电脑(昆山)有限公司 | The control method of monitoring system |
| CN109063566A (en) * | 2018-07-02 | 2018-12-21 | 天津煋鸟科技有限公司 | A kind of optical detecting method for human testing |
| CN109583396A (en) * | 2018-12-05 | 2019-04-05 | 广东亿迅科技有限公司 | A kind of region prevention method, system and terminal based on CNN two stages human testing |
| CN111435165A (en) * | 2018-12-26 | 2020-07-21 | 保定市天河电子技术有限公司 | Transport vehicle obstacle detection method and system based on laser radar |
| CN112084813B (en) * | 2019-06-12 | 2024-06-04 | 杭州萤石软件有限公司 | Abnormal target detection method, device and storage medium |
| CN110598670B (en) * | 2019-09-20 | 2022-03-25 | 腾讯科技（深圳）有限公司 | Method and device for setting monitoring area forbidden zone, storage medium and computer equipment |
| CN111639765A (en) * | 2020-05-15 | 2020-09-08 | 视若飞信息科技(上海)有限公司 | Interaction method for using point track and detection domain |
| CN111814587B (en) * | 2020-06-18 | 2024-09-03 | 浙江大华技术股份有限公司 | Human behavior detection method, teacher behavior detection method, and related systems and devices |
| CN115278159A (en) * | 2022-06-16 | 2022-11-01 | 宁夏金信光伏电力有限公司 | Person monitoring and alarming method and system |
| CN117593703B (en) * | 2024-01-19 | 2024-04-16 | 深圳市创达电子有限公司 | Control management method and system for parking lot barrier gate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2643415Y (en) * | 2003-07-09 | 2004-09-22 | 江国栋 | Video moving target inbreak alarmer |
| CN1568619A (en) * | 2001-11-15 | 2005-01-19 | 韩唯逻辑公司 | Security system and warning method using edge detection of image signal |
| JP2005328236A (en) * | 2004-05-13 | 2005-11-24 | Nippon Telegr & Teleph Corp <Ntt> | Video monitoring method, device, and program |
| CN101090483A (en) * | 2006-06-13 | 2007-12-19 | 声宝股份有限公司 | Computer mainframe structure of modular configuration |
| CN101106700A (en) * | 2007-08-01 | 2008-01-16 | 大连海事大学 | Intelligent target detail capturing device and method in video monitoring system |
-
2008
- 2008-08-27 CN CN2008101189956A patent/CN101339688B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1568619A (en) * | 2001-11-15 | 2005-01-19 | 韩唯逻辑公司 | Security system and warning method using edge detection of image signal |
| CN2643415Y (en) * | 2003-07-09 | 2004-09-22 | 江国栋 | Video moving target inbreak alarmer |
| JP2005328236A (en) * | 2004-05-13 | 2005-11-24 | Nippon Telegr & Teleph Corp <Ntt> | Video monitoring method, device, and program |
| CN101090483A (en) * | 2006-06-13 | 2007-12-19 | 声宝股份有限公司 | Computer mainframe structure of modular configuration |
| CN101106700A (en) * | 2007-08-01 | 2008-01-16 | 大连海事大学 | Intelligent target detail capturing device and method in video monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101339688A (en) | 2009-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101339688B (en) | Intrusion checking method and system | |
| US10032283B2 (en) | Modification of at least one parameter used by a video processing algorithm for monitoring of a scene | |
| US9928707B2 (en) | Surveillance system | |
| TWI537842B (en) | People counting system | |
| US9948906B2 (en) | Monitoring device and interference detection method | |
| US20110234749A1 (en) | System and method for detecting and recording traffic law violation events | |
| CN104966062B (en) | Video monitoring method and device | |
| KR101858396B1 (en) | Intelligent intrusion detection system | |
| KR101921610B1 (en) | Method and Apparatus for Monitoring Objects from Video | |
| JP5904069B2 (en) | Image processing apparatus, object detection method, and object detection program | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| JP2007233919A (en) | Intruder detection apparatus by imaging processing | |
| JP5771039B2 (en) | Abandoned person detection device | |
| CN106558224A (en) | A kind of traffic intelligent monitoring and managing method based on computer vision | |
| JP5170731B2 (en) | Traffic monitoring system | |
| CN101587619A (en) | Detection method for intrusion object based on video monitoring | |
| JP4993281B2 (en) | Monitoring area setting device | |
| JP2012088861A (en) | Intrusion object detection device | |
| JP4888707B2 (en) | Suspicious person detection device | |
| CN113239772A (en) | Personnel gathering early warning method and system in self-service bank or ATM environment | |
| KR101425658B1 (en) | Detection method of hacking and malfunction for surveillance camera system | |
| EP3506217A2 (en) | Systems and methods for intrusion detection using selective masking | |
| JP2011227614A (en) | Image monitoring device | |
| KR101077934B1 (en) | System for recognizing unlawful entry | |
| JP2009294974A (en) | Intruder detection device by image processing |
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 | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160518 Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -478 Patentee after: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Address before: 100083, Haidian District, Xueyuan Road, Beijing No. 35, Nanjing Ning building, 15 Floor Patentee before: Beijing Vimicro Corporation |