CN109903503A - A kind of detection method in video monitoring object intrusion detection region - Google Patents
A kind of detection method in video monitoring object intrusion detection region Download PDFInfo
- Publication number
- CN109903503A CN109903503A CN201910303233.1A CN201910303233A CN109903503A CN 109903503 A CN109903503 A CN 109903503A CN 201910303233 A CN201910303233 A CN 201910303233A CN 109903503 A CN109903503 A CN 109903503A
- Authority
- CN
- China
- Prior art keywords
- video monitoring
- vertex
- cross
- rectangle
- detection
- 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.)
- Pending
Links
Landscapes
- Burglar Alarm Systems (AREA)
Abstract
The invention discloses a kind of detection methods in video monitoring object intrusion detection region, squaring restriction is carried out by object area in the video frame by video monitoring, and the shape in optimizing detection region is convex polygon, by the overlapping cases judgment object between the rectangle of judgment object image and the convex polygon of detection zone whether intrusion detection region, judge precision height, real-time is good.Therefore, a kind of detection method in video monitoring object intrusion detection region of the invention, which has, judges precision height, the good advantage of real-time.
Description
Technical field
The present invention relates to image identification technical field more particularly to a kind of judgement precision height, the good video monitorings of real-time
The detection method in object intrusion detection region.
Background technique
With the development of intellectual technology, the concept of intelligence community is constantly implemented in practice by theory, especially AI intelligence
The application scenarios of the alarm video analysis in object analysis intrusion detection region, i.e., by whether having in AI intellectual analysis video monitoring
Object intrusion detection region, the detection zone are the identification region marked.Currently, major part AI judges whether there is object invasion
Treatment mechanism used by detection zone is by the methods of trajectory analysis, but there are the lag that event occurs for this method
Property, or even when the central point of object detection area continues when boundary is hovered, the event of may cause can not be triggered and can not be reported
And so on, such case is not very practical in the region detections such as some illegal parkings, anti-climbing.
Therefore, it is necessary to a kind of improvement be proposed, to overcome the deficiencies of existing technologies.
Summary of the invention
Present invention aim to address the problems of the prior art, provide a kind of judgement precision height, the good video of real-time
Monitor the detection method in object intrusion detection region.
The technical scheme is that
A kind of detection method in video monitoring object intrusion detection region, comprising the following steps: S1, obtained from video monitoring
Take video frame fram；S2, object detection is carried out on the video frame fram, obtain object category, object similarity and object
Region B；It is rectangle that the object area B, which is arranged, the framework coordinate of the object area B be rbboxes=[[xmin, ymin],
[xmax,ymax]]；S3, setting detection zone are S, and the detection zone S is convex polygon, have n side and n vertex；
S4, judge whether the object area B and the detection zone S are overlapped；Alert event is triggered if having overlapping；If non-overlapping
It returns to S1 and carries out lower whorl video detection task.
As a kind of perferred technical scheme, it includes three that object area B described in step S4 is Chong Die with the detection zone S
Kind situation: a, B include that S or S have vertex in B；B, S includes that B or B have vertex in S；C, S does not have vertex in B, and S has at least
A line intersects at least one diagonal line of B；The establishment of situation a, b, c either case can determine whether that B is Chong Die with S, trigger alert event.
As a kind of further preferred technical solution, the judgment method of situation a in the step S4 are as follows: judge the institute of S
Have the relationship of apex coordinate Yu the region rectangle B, if the coordinate (x, y) at least one vertex S meet xmin < x < xmax and
Ymin < y < ymax then can determine whether that situation a is set up, and B is Chong Die with S, triggers alert event.
As another further preferred technical solution, the judgment method of situation b in the step S4 are as follows: S4b1, by S
N vertex be sequentially placed into array a [n]；S4b2, each side, that is, edge (i, j) for obtaining S, i is by 0 to n, j=(i+
1) %n；Four vertex P for successively obtaining B, calculate separately the cross product cross of i-j and i-P vector；If there is cross < 0, there is B
Vertex in S, can determine whether situation b set up, B is Chong Die with S, triggering alert event.
As a kind of technical solution still more preferably, in the step S4b1, by the n vertex of S according to counterclockwise
Sequence is sequentially placed into array a [n].
The technical solution further preferred as another, the judgment method of situation c in the step S4 are as follows: S4c1, vacation
If the diagonal line segment of two lines of rectangle B is L1 and L2；S4c2, the n vertex of S is sequentially placed into array a [n]；S4c3, S is obtained
N each in while, i.e. edge (i, j), i determine two diagonal Ls 1 and L2 of B by 0 to n, j=(i+1) %n
Whether any one intersect with certain side of S；If intersection, it can determine whether that situation c is set up, B is Chong Die with S, triggers alert event.
As a kind of technical solution still more preferably, in the step S4c2, by the n vertex of S according to counterclockwise
Sequence is sequentially placed into array a [n].
As a kind of another technical solution still more preferably, two 1 Hes of diagonal L of B are determined in the step S4c3
The method whether any one of L2 intersects with certain side of S are as follows: S4c3a, the diagonal L 1 (P1, P2) for setting B, the side M1 of S
(P3, P4)；S4c3b, two rectangles R1 and R2 are established respectively using L1 and M1 as diagonal line, judge whether rectangle R1 and R2 intersect,
If R1 is non-intersecting with R2, L1 and M1 are non-intersecting, if R1 and R2 intersection, carries out step S4c3c；S4c3c, 1 direction of label L to
It measures W=(P1, P2), the direction vector of the endpoint P1 of the endpoint P3 and L1 of M1 are that Q=(P1, P3) is then marked according to cross product formula
Cross (P1, P2, P3)=(P2 [0]-P1 [0]) * (P3 [1]-P1 [1])-(P3 [0]-P1 [0]) * (P2 [1]-P1 [1])；Similarly
Cross (P1, P2, P4), cross (P3, P4, P1) and cross (P3, P4, P2) can be obtained；S4c3d, cross if (P1, P2, P3) *
Cross (P1, P2, P4)≤0 and cross (P3, P4, P1) * cross (P3, P4, P2)≤0, then determine that L1 intersects with M1；
Otherwise non-intersecting.
As a kind of perferred technical scheme, the rectangle size of the object area B in the video frame fram and the object
Body classification, the association of object similarity；Object category is identical, the rectangle size of the region B of the higher object of similarity is identical.
As a kind of perferred technical scheme, when the setting object area B in told step S2 is rectangle, rectangle B
For the circumscribed rectangle of the exterior contour of object.
The detection method in a kind of video monitoring object intrusion detection region of the invention, by by the video frame of video monitoring
Middle object area carries out squaring restriction, and the shape in optimizing detection region is convex polygon, in a creative way regards intelligent decision
Whether there is the judgment method in object intrusion detection region to be optimized for the rectangle and detection zone of judgment object image in frequency monitoring
Overlapping cases between convex polygon, so as to by rectangle determine and intersect determine judgment object whether intrusion detection region,
Judge precision height, real-time is good.Therefore, a kind of detection method in video monitoring object intrusion detection region of the invention has and sentences
Disconnected precision is high, the good advantage of real-time.
Detailed description of the invention
Fig. 1 is a kind of detection method specific embodiment flow chart in video monitoring object intrusion detection region of the present invention；
Fig. 2 is object areas in a kind of detection method specific embodiment in video monitoring object intrusion detection region of the present invention
Domain B and the detection zone S overlapping cases a schematic diagram；
Fig. 3 is object areas in a kind of detection method specific embodiment in video monitoring object intrusion detection region of the present invention
Domain B and the detection zone S overlapping cases b schematic diagram；
Fig. 4 is object areas in a kind of detection method specific embodiment in video monitoring object intrusion detection region of the present invention
Domain B and the detection zone S overlapping cases c schematic diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning, " a variety of " generally comprise at least two, but not
It excludes to include at least one situation.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
Depending on context, word as used in this " if ", " if " can be construed to " ... when " or
" when ... " or " in response to determination " or " in response to detection ".Similarly, context is depended on, phrase " if it is determined that " or " such as
Fruit detection (condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when detection (statement
Condition or event) when " or " in response to detection (condition or event of statement) ".
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Include, so that commodity or system including a series of elements not only include those elements, but also including not clear
The other element listed, or further include for this commodity or the intrinsic element of system.In the feelings not limited more
Under condition, the element that is limited by sentence "including a ...", it is not excluded that in the commodity or system for including the element also
There are other identical elements.
As shown in Figure 1 it is a kind of detection method in video monitoring object intrusion detection region of the invention, including once walks
It is rapid: video frame fram S1, is obtained from video monitoring；S2, object detection is carried out on the video frame fram, obtain object type
Not, object similarity and object area B；It is rectangle that the object area B, which is arranged, and the framework coordinate of the object area B is
Rbboxes=[[xmin, ymin], [xmax, ymax]]；S3, setting detection zone are S, and the detection zone S is convex polygon
Shape has n side and n vertex；S4, judge whether the object area B and the detection zone S are overlapped；If having overlapping
Trigger alert event；S1 is returned if non-overlapping carries out lower whorl video detection task.A kind of video monitoring object of the invention enters
Object area is carried out squaring restriction by the detection method for invading detection zone, and the shape in optimizing detection region is convex polygon, is led to
It crosses rectangle and determines and intersect resolution principle, each side to the convex polygon detection zone on monitor video picture can be recycled
Determined with the rectangular area of detection object, then intelligent analysis can determine that the event in object intrusion detection region.
As shown in Figures 2 to 4, as an example, the detection zone S of the present embodiment is convex pentagon, has 5 sides and 5 tops
Point.
When object area B is Chong Die with detection zone S, there are three types of situations:
As shown in Fig. 2, it includes that S or S have vertex in B that situation a, which is B,.
As shown in figure 3, it includes that B or B have vertex in S that situation b, which is S,.
As shown in figure 4, S does not have vertex in B and B does not have vertex in S, but S has at least one side and B at least one right
Linea angulata intersection.
Three cases above a, b, c either case is set up, then can determine whether that B is Chong Die with S, triggers alert event.
The judgment method of situation a shown in Fig. 2 are as follows: judge all apex coordinates of S and the relationship of the region rectangle B,
If the coordinate (x, y) at least one vertex S meets xmin < x < xmax and ymin < y < ymax, it can determine whether that situation a is set up, B
It is Chong Die with S, trigger alert event.
The judgment method of situation b shown in Fig. 3 are as follows:
S4b1, the n vertex of S is sequentially placed into array a [n]；
S4b2, each side, that is, edge (i, j) for obtaining S, i is by 0 to n, j=(i+1) %n；Successively obtain four tops of B
Point P calculates separately the cross product cross of i-j and i-P vector；If there is cross < 0, there is the vertex of B in S, can determine whether situation b
It sets up, B is Chong Die with S, triggers alert event.
In the present embodiment, S is convex pentagon, therefore n is 5.
In order to guarantee that all vertex of S are put into an orderly manner in array a [n], preferably, by the n vertex of S according to the inverse time
Needle sequence is sequentially placed into, and certainly, in practical applications, can also be put into according to clockwise sequence.
The judgment method of situation c shown in Fig. 4 are as follows:
S4c1, the diagonal line segment of two lines for assuming rectangle B are L1 and L2；
S4c2, the n vertex of S is sequentially placed into array a [n]；
S4c3, when obtaining n of the S each in, i.e. edge (i, j), i determine B's by 0 to n, j=(i+1) %n
Whether any one of two diagonal Ls 1 and L2 intersects with certain side of S；If intersection, it can determine whether that situation c is set up, B and S weight
It is folded, trigger alert event.
In the present embodiment, S is convex pentagon, therefore n is 5.
In order to guarantee that all vertex of S are put into an orderly manner in array a [n], preferably, by the n vertex of S according to the inverse time
Needle sequence is sequentially placed into, and certainly, in practical applications, can also be put into according to clockwise sequence.
In the present embodiment, determine in above-mentioned steps S4c3 B two diagonal Ls 1 and any one of L2 whether with S certain
The method of side intersection are as follows:
S4c3a, such as Fig. 4, if the diagonal L 1 (P1, P2) of B, the side M1 (P3, P4) of S；
S4c3b, two rectangles R1 and R2 are established respectively using L1 and M1 as diagonal line, judge whether rectangle R1 and R2 intersect,
If R1 is non-intersecting with R2, L1 and M1 are non-intersecting, if R1 and R2 intersection, carries out step S4c3c；Wherein, judge rectangle R1 and
The method whether R2 intersects are as follows: judge following two condition whether and meanwhile meet: the right end of any rectangle of R1 and R2 is both greater than
The left end of another rectangle, and any rectangle most significant end of R1 and R2 is greater than the least significant end of another rectangle；As long as any condition
It is unsatisfactory for, then two rectangles are non-intersecting namely two line segments are non-intersecting；If two conditions are all satisfied, R1 intersects with R2, carries out step
S4c3c；
S4c3c, label L 1 direction vector W=(P1, P2), the endpoint P1 of the endpoint P3 and L1 of M1 direction vector be Q=
(P1, P3) then marks cross (P1, P2, P3)=(P2 [0]-P1 [0]) * (P3 [1]-P1 [1])-(P3 [0]-according to cross product formula
P1[0])*(P2[1]-P1[1])；Can similarly obtain cross (P1, P2, P4), cross (P3, P4, P1) and cross (P3, P4,
P2)；
If S4c3d, cross (P1, P2, P3) * cross (P1, P2, P4)≤0 and cross (P3, P4, P1) * cross
(P3, P4, P2)≤0 then determines that L1 intersects with M1；Otherwise non-intersecting.
In order to further accurately identify the classification of object in video monitoring, while quickly determining the rectangle region of object
Domain B, preferably, the rectangle size of the object area B in the video frame fram are similar to the object category, object
Degree association；Object category is identical, the rectangle size of the region B of the higher object of similarity is identical.It will likely can invade in advance
Object carry out classification statistics and size statistics, corresponding rectangular area is established according to object category, size similarity, when
Recognized from the picture frame of video monitoring object category is identical, similarity higher object when, the square of its region of Auto-matching B
Shape size.The determination efficiency of object rectangular area B is improved, to improve the detection efficiency of whole detection method, guarantees detection
Real-time.
Certainly, in order to improve the accuracy of detection, guarantee that object rectangular area B can reflect the size of object conscientiously, it can
To set the rectangle of object area B in the circumscribed rectangle of the exterior contour of object.To make the rectangular shape of object area B with
Contour of object is close to for subsequent detection object area B, whether the judgment accuracy of intrusion detection region S is provided safeguard, and improves inspection
Survey precision.
The detection method in a kind of video monitoring object intrusion detection region of the invention, by by the video frame of video monitoring
Middle object area carries out squaring restriction, and the shape in optimizing detection region is convex polygon, in a creative way regards intelligent decision
Whether there is the judgment method in object intrusion detection region to be optimized for the rectangle and detection zone of judgment object image in frequency monitoring
Overlapping cases between convex polygon, so as to by rectangle determine and intersect determine judgment object whether intrusion detection region,
Judge precision height, real-time is good.Therefore, a kind of detection method in video monitoring object intrusion detection region of the invention has and sentences
Disconnected precision is high, the good advantage of real-time.
A kind of detection method in video monitoring object intrusion detection region of the invention can be applied in intelligent Community
Illegal parking, the recognition detection for forbidding climbing region climbing, detection accuracy is high, and real-time is good, and detection is accurate.
It is in summary only preferred embodiments of the present invention, practical range not for the purpose of limiting the invention.That is Fan Yiben
Equivalence changes made by the content of patent application the scope of the patents and modification all should belong to technology scope of the invention.
Claims (10)
1. a kind of detection method in video monitoring object intrusion detection region, it is characterised in that: the following steps are included:
S1, video frame fram is obtained from video monitoring；
S2, object detection is carried out on the video frame fram, obtain object category, object similarity and object area B；Setting
The object area B is rectangle, the framework coordinate of the object area B be rbboxes=[[xmin, ymin], [xmax,
ymax]]；
S3, setting detection zone are S, and the detection zone S is convex polygon, have n side and n vertex；
S4, judge whether the object area B and the detection zone S are overlapped；Alert event is triggered if having overlapping；If without weight
It is folded then return S1 carry out lower whorl video detection task.
2. a kind of detection method in video monitoring object intrusion detection region according to claim 1, it is characterised in that: step
Object area B described in rapid S4 Chong Die with the detection zone S includes three kinds of situations:
A, B includes that S or S have vertex in B；
B, S includes that B or B have vertex in S；
C, S does not have vertex in B, and S has at least one side to intersect at least one diagonal line of B；
The establishment of situation a, b, c either case can determine whether that B is Chong Die with S, trigger alert event.
3. a kind of detection method in video monitoring object intrusion detection region according to claim 2, it is characterised in that: institute
State the judgment method of situation a in step S4 are as follows: all apex coordinates of S and the relationship of the region rectangle B are judged, if S is at least
There is the coordinate (x, y) on a vertex to meet xmin < x < xmax and ymin < y < ymax, then can determine whether that situation a is set up, B is Chong Die with S,
Trigger alert event.
4. a kind of detection method in video monitoring object intrusion detection region according to claim 2, it is characterised in that: institute
State the judgment method of situation b in step S4 are as follows:
S4b1, the n vertex of S is sequentially placed into array a [n]；
S4b2, each side, that is, edge (i, j) for obtaining S, i is by 0 to n, j=(i+1) %n；Four vertex P of B are successively obtained,
Calculate separately the cross product cross of i-j and i-P vector；If there is cross < 0, there is the vertex of B in S, can determine whether that situation b is set up,
B is Chong Die with S, triggers alert event.
5. a kind of detection method in video monitoring object intrusion detection region according to claim 4, it is characterised in that: institute
It states in step S4b1, the n vertex of S is sequentially placed into array a [n] according to sequence counter-clockwise.
6. a kind of detection method in video monitoring object intrusion detection region according to claim 2, it is characterised in that: institute
State the judgment method of situation c in step S4 are as follows:
S4c1, the diagonal line segment of two lines for assuming rectangle B are L1 and L2；
S4c2, the n vertex of S is sequentially placed into array a [n]；
S4c3, when obtaining n of the S each in, i.e. edge (i, j), i determine two of B by 0 to n, j=(i+1) %n
Whether any one of diagonal L 1 and L2 intersects with certain side of S；If intersection, can determine whether that situation c is set up, B is Chong Die with S,
Trigger alert event.
7. a kind of detection method in video monitoring object intrusion detection region according to claim 6, which is characterized in that institute
It states in step S4c2, the n vertex of S is sequentially placed into array a [n] according to sequence counter-clockwise.
8. a kind of detection method in video monitoring object intrusion detection region according to claim 6, it is characterised in that: institute
It states and determines two diagonal Ls 1 of B and any one method whether intersected with certain side of S of L2 in step S4c3 are as follows:
S4c3a, the diagonal L 1 (P1, P2) for setting B, the side M1 (P3, P4) of S；
S4c3b, two rectangles R1 and R2 are established respectively using L1 and M1 as diagonal line, judges whether rectangle R1 and R2 intersect, if R1
Non-intersecting with R2, then L1 and M1 are non-intersecting, if R1 and R2 intersection, carries out step S4c3c；
S4c3c, label L 1 direction vector W=(P1, P2), the endpoint P1 of the endpoint P3 and L1 of M1 direction vector be Q=(P1,
P3 cross (P1, P2, P3)=(P2 [0]-P1 [0]) * (P3 [1]-P1 [1])-(P3 [0]-P1 then) is marked according to cross product formula
[0])*(P2[1]-P1[1])；Cross (P1, P2, P4), cross (P3, P4, P1) and cross (P3, P4, P2) can similarly be obtained；
If S4c3d, cross (P1, P2, P3) * cross (P1, P2, P4)≤0 and cross (P3, P4, P1) * cross (P3,
P4, P2)≤0, then determine that L1 intersects with M1；Otherwise non-intersecting.
9. a kind of detection method in video monitoring object intrusion detection region according to claim 1, it is characterised in that: institute
The rectangle size for stating the object area B in video frame fram is associated with the object category, object similarity；Object category phase
It is identical with, the rectangle size of region B of the higher object of similarity.
10. a kind of detection method in video monitoring object intrusion detection region according to claim 1, it is characterised in that:
When the setting object area B in told step S2 is rectangle, rectangle B is the circumscribed rectangle of the exterior contour of object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910303233.1A CN109903503A (en) | 2019-04-16 | 2019-04-16 | A kind of detection method in video monitoring object intrusion detection region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910303233.1A CN109903503A (en) | 2019-04-16 | 2019-04-16 | A kind of detection method in video monitoring object intrusion detection region |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109903503A true CN109903503A (en) | 2019-06-18 |
Family
ID=66954833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910303233.1A Pending CN109903503A (en) | 2019-04-16 | 2019-04-16 | A kind of detection method in video monitoring object intrusion detection region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903503A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427942A (en) * | 2019-08-09 | 2019-11-08 | 上海天诚比集科技有限公司 | A kind of detection zone determines method |
| CN111080952A (en) * | 2020-01-13 | 2020-04-28 | 贵州安防工程技术研究中心有限公司 | Feedback type regional intrusion detection method and system based on real-time video and rules |
| CN111144291A (en) * | 2019-12-25 | 2020-05-12 | 中铁信(北京)网络技术研究院有限公司 | Method and device for distinguishing personnel invasion in video monitoring area based on target detection |
| CN111223260A (en) * | 2020-01-19 | 2020-06-02 | 上海智勘科技有限公司 | Method and system for intelligently monitoring goods theft prevention in warehousing management |
| CN111488838A (en) * | 2020-04-14 | 2020-08-04 | 上海天诚比集科技有限公司 | Video detection area object intrusion detection method |
| CN113379984A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Electronic nursing fence system |
| CN113379985A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Nursing electronic fence alarm device |
| CN113379987A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Design method of nursing electronic fence module |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0913800A1 (en) * | 1997-10-29 | 1999-05-06 | Endusis Limited | Monitoring system |
| CN102045544A (en) * | 2010-11-10 | 2011-05-04 | 无锡中星微电子有限公司 | Video monitoring system and video data transmission method thereof |
| CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
| CN104680557A (en) * | 2015-03-10 | 2015-06-03 | 重庆邮电大学 | Intelligent detection method for abnormal behavior in video sequence image |
| CN109257569A (en) * | 2018-10-24 | 2019-01-22 | 广东佳鸿达科技股份有限公司 | Security protection video monitoring analysis method |
-
2019
- 2019-04-16 CN CN201910303233.1A patent/CN109903503A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0913800A1 (en) * | 1997-10-29 | 1999-05-06 | Endusis Limited | Monitoring system |
| CN102045544A (en) * | 2010-11-10 | 2011-05-04 | 无锡中星微电子有限公司 | Video monitoring system and video data transmission method thereof |
| CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
| CN104680557A (en) * | 2015-03-10 | 2015-06-03 | 重庆邮电大学 | Intelligent detection method for abnormal behavior in video sequence image |
| CN109257569A (en) * | 2018-10-24 | 2019-01-22 | 广东佳鸿达科技股份有限公司 | Security protection video monitoring analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 王瑞: "智能视频监控系统的研究与开发", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427942A (en) * | 2019-08-09 | 2019-11-08 | 上海天诚比集科技有限公司 | A kind of detection zone determines method |
| CN111144291A (en) * | 2019-12-25 | 2020-05-12 | 中铁信(北京)网络技术研究院有限公司 | Method and device for distinguishing personnel invasion in video monitoring area based on target detection |
| CN111144291B (en) * | 2019-12-25 | 2023-06-09 | 中铁信(北京)网络技术研究院有限公司 | Video monitoring area personnel intrusion discrimination method and device based on target detection |
| CN111080952A (en) * | 2020-01-13 | 2020-04-28 | 贵州安防工程技术研究中心有限公司 | Feedback type regional intrusion detection method and system based on real-time video and rules |
| CN111223260A (en) * | 2020-01-19 | 2020-06-02 | 上海智勘科技有限公司 | Method and system for intelligently monitoring goods theft prevention in warehousing management |
| CN113379985A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Nursing electronic fence alarm device |
| CN113379984A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Electronic nursing fence system |
| CN113379987A (en) * | 2020-02-25 | 2021-09-10 | 北京君正集成电路股份有限公司 | Design method of nursing electronic fence module |
| CN113379984B (en) * | 2020-02-25 | 2022-09-23 | 北京君正集成电路股份有限公司 | Electronic nursing fence system |
| CN113379985B (en) * | 2020-02-25 | 2022-09-27 | 北京君正集成电路股份有限公司 | Nursing electronic fence alarm device |
| CN113379987B (en) * | 2020-02-25 | 2022-10-21 | 北京君正集成电路股份有限公司 | Design method of nursing electronic fence module |
| CN111488838A (en) * | 2020-04-14 | 2020-08-04 | 上海天诚比集科技有限公司 | Video detection area object intrusion detection method |
| CN111488838B (en) * | 2020-04-14 | 2023-09-01 | 上海天诚比集科技有限公司 | Method for detecting intrusion of object in video detection area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109903503A (en) | A kind of detection method in video monitoring object intrusion detection region | |
| WO2020215552A1 (en) | Multi-target tracking method, apparatus, computer device, and storage medium | |
| CN103871078B (en) | A kind of billiard ball batting key message detection method and system | |
| CN101577812B (en) | Method and system for post monitoring | |
| CN101794385B (en) | Multi-angle multi-target fast human face tracking method used in video sequence | |
| CN103971380B (en) | Pedestrian based on RGB-D trails detection method | |
| Stalder et al. | Cascaded confidence filtering for improved tracking-by-detection | |
| CN107527009A (en) | A kind of remnant object detection method based on YOLO target detections | |
| US20080212099A1 (en) | Method for counting people passing through a gate | |
| CN110569772A (en) | Method for detecting state of personnel in swimming pool | |
| CN108921873A (en) | The online multi-object tracking method of Markovian decision of filtering optimization is closed based on nuclear phase | |
| CN108564069A (en) | A kind of industry safe wearing cap video detecting method | |
| CN102214359B (en) | Target tracking device and method based on hierarchic type feature matching | |
| CN104616006B (en) | A kind of beard method for detecting human face towards monitor video | |
| CN109002801A (en) | A kind of face occlusion detection method and system based on video monitoring | |
| CN114782897A (en) | Dangerous behavior detection method and system based on machine vision and deep learning | |
| CN106778540B (en) | Parking detection is accurately based on the parking event detecting method of background double layer | |
| CN111339901B (en) | Image-based intrusion detection method and device, electronic equipment and storage medium | |
| CN112464797B (en) | Smoking behavior detection method and device, storage medium and electronic equipment | |
| CN113223046A (en) | Method and system for identifying prisoner behaviors | |
| CN109685009A (en) | A kind of method of region crowd density video detection | |
| CN112651371A (en) | Dressing security detection method and device, storage medium and computer equipment | |
| CN109583339A (en) | A kind of ATM video brainpower watch and control method based on image procossing | |
| CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
| CN108830204A (en) | The method for detecting abnormality in the monitor video of target |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190618 |
|
| RJ01 | Rejection of invention patent application after publication |