CN113392714A - Crowd event detection method and system - Google Patents
Crowd event detection method and system Download PDFInfo
- Publication number
- CN113392714A CN113392714A CN202110549833.3A CN202110549833A CN113392714A CN 113392714 A CN113392714 A CN 113392714A CN 202110549833 A CN202110549833 A CN 202110549833A CN 113392714 A CN113392714 A CN 113392714A
- Authority
- CN
- China
- Prior art keywords
- camera
- thermal imaging
- crowd
- unit
- character
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000001931 thermography Methods 0.000 claims description 78
- 230000006698 induction Effects 0.000 claims description 30
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The invention relates to the technical field of image processing, and particularly discloses a crowd event detection method and system, wherein the number of character models in a target area is obtained by combining a multi-camera thermal sensing stereo shooting module to shoot a target area in multiple directions, a preset threshold value is set in an external terminal through a judgment unit, wherein the number of characters in the target area is limited, and early warning information is sent when the number of the obtained character models in the target area exceeds the preset threshold value, so that the number of crowd persons in the target area can be accurately judged.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a system for detecting a crowd event.
Background
At present, with the strong demand of the society on safety monitoring and the development of an intelligent video monitoring system, the detection of abnormal behaviors based on video monitoring is particularly important, and the street is monitored in real time through a camera at present, but when the behavior of a crowd is complex, the real-time monitoring effect under the condition of mutual shielding and coincidence is not accurate enough, and then the behavior of the crowd cannot be accurately judged.
Disclosure of Invention
The invention aims to provide a crowd event detection method and system, and aims to solve the technical problems that in the prior art, a camera is used for monitoring a street in real time, and when the crowd acts more complexly, the real-time monitoring effect is not accurate under the condition of mutual shielding and coincidence, and further the behavior action of the crowd cannot be accurately judged.
In order to achieve the purpose, the crowd event detection system comprises a multi-camera thermal induction stereo shooting module, a camera linkage control module, a crowd data processing module and a coincident pixel point data processing module;
the camera linkage control module is connected with the multiple-camera thermal induction stereo shooting module, the crowd data processing module is connected with the multiple-camera thermal induction stereo shooting module and the camera linkage control module, and the coincident pixel point data processing module is connected with the crowd data processing module;
the multi-camera thermal induction stereo shooting module is used for shooting heat-bearing organisms in street views from multiple angles through a plurality of thermal induction cameras arranged on a street;
the camera linkage control module is used for wirelessly connecting a plurality of cameras on a street, controlling the shooting angle of each camera and shooting at multiple angles towards the same position;
the crowd data processing module is used for receiving the shot images transmitted by the multi-camera thermal induction stereo shooting module and reading each thermal induction pixel point in the shot video images;
the coincident pixel point data processing module is used for carrying out multi-angle comparison on coincident thermal induction pixel points in the received shot video image, combining and analyzing the multi-angle image acquired by the multi-camera thermal induction stereo shooting module and judging the number of people gathering.
The focus data processing module comprises an information transmission unit and an arithmetic unit, the information transmission unit is connected with the multi-camera thermal induction stereo shooting module and is connected with the camera linkage control module, and the arithmetic unit is connected with the information transmission unit and is connected with the coincident pixel data processing module;
the information transmission unit is used for receiving the image information of the multi-camera thermal induction stereo shooting module and sending control information to the camera linkage control module;
and the operation unit is used for acquiring pixel points of a moving target in the shot image and constructing a character model of the target pixel points.
The overlapped pixel point data processing module comprises a model comparison unit and a judgment unit, wherein the model comparison unit is connected with the operation unit, and the judgment unit is connected with the model comparison unit;
the model comparison unit is used for comparing character models in the plurality of shot images generated by the operation unit and determining the number of character models at the superposition positions of the plurality of character models from the plurality of shot images;
and the judging unit is used for comparing the number of the character models determined in the model comparison unit with a preset threshold value and judging whether a crowd event exists at the current position.
A method for detecting a crowd event is characterized by comprising the following steps:
arranging a plurality of thermal imaging cameras on a street;
the camera linkage control module controls each thermal imaging camera to independently shoot an image of one area and transmits the image to the information transmission unit;
the operation unit generates a character model from the image shot by the thermal imaging camera;
the camera linkage control module adjusts the angles of a plurality of cameras in the character model overlapping area to obtain multi-angle shot images of the character model overlapping area;
the model comparison unit determines the number of character models of the current image;
the judging unit compares the number of the character models of the current image with a threshold value to judge whether a crowd event exists or not.
Wherein, in the "arranging a plurality of thermal imaging cameras on a street", the method further comprises,
a first thermal imaging camera is arranged at a corner of a street;
a second thermal imaging camera capable of aligning with the first thermal imaging camera is arranged on the other side of the street;
and a third thermal imaging camera in the horizontal and vertical direction is arranged between the first thermal imaging camera and the second thermal imaging camera.
Wherein, in the operation unit generates the image shot by the thermal imaging camera into the character model, the method also comprises,
acquiring thermal imaging pixel points of a moving target in a shot image;
performing combined modeling on the obtained thermal imaging pixel points;
and comparing the modeling data with the human body characteristics to judge whether the figures are overlapped.
Wherein, in the process of adjusting the angles of a plurality of cameras with character model overlapping areas by the camera linkage control module to obtain multi-angle shot images of the character model overlapping areas, the method also comprises the following steps,
shooting a target position by respectively adopting the first thermal imaging camera and the second thermal imaging camera;
shooting the target position by adopting the third thermal imaging camera;
a character model of the target location is obtained.
Wherein, in the "the model comparing unit determines the number of character models of the current image", the method further comprises,
the obtained character models are subjected to limb division, and the number of character models at the position where the plurality of character models overlap is determined from the plurality of captured images.
Wherein, in the step of comparing the number of the character models of the current image with a threshold value by the judging unit to judge whether the event of the crowd exists or not,
a people threshold for a crowd event is preset,
acquiring the number of character models at the target position;
and comparing the number of the character models at the target position with a preset threshold value, and judging whether a crowd event exists or not.
According to the crowd event detection method and system, the number of the character models in the target area is obtained by combining the multi-camera thermal sensing stereo shooting module to shoot the target area in multiple directions, the number of the characters in the target area is limited due to the fact that the preset threshold value is set in the external terminal through the judging unit, and when the number of the obtained character models in the target area exceeds the preset threshold value, early warning information is sent out, so that the number of crowd persons in the target area can be accurately judged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a system diagram of a crowd event detection system of the present invention.
FIG. 2 is a flow chart of crowd event detection of the present invention.
FIG. 3 is a flow chart of the present invention for arranging multiple thermal imaging cameras on a street.
Fig. 4 is a flowchart of the present invention in which the computing unit generates a character model from an image captured by the thermal imaging camera.
FIG. 5 is a flow chart of the present invention for obtaining multi-angle shots of overlapping regions of character models.
FIG. 6 is a flow chart of the present invention for determining whether a crowd event exists.
In the figure: the system comprises a 1-multi-camera thermal induction stereo shooting module, a 2-camera linkage control module, a 3-focus data processing module, a 4-coincident pixel point data processing module, a 31-information transmission unit, a 32-arithmetic unit, a 41-model comparison unit and a 42-judgment unit.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships illustrated in the drawings, and are used merely for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention. Further, in the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Referring to fig. 1, the present invention provides a crowd event detection system, which includes a multi-camera thermal sensing stereo camera module 1, a camera linkage control module 2, a crowd data processing module 3, and a coincident pixel point data processing module 4;
the camera linkage control module 2 is connected with the multi-camera thermal induction stereo shooting module 1, the crowd data processing module 3 is connected with the multi-camera thermal induction stereo shooting module 1 and the camera linkage control module 2, and the coincident pixel point data processing module 4 is connected with the crowd data processing module 3;
the multi-camera thermal induction stereo shooting module 1 is used for shooting heat-bearing organisms in street views from multiple angles through a plurality of thermal induction cameras arranged on a street;
the camera linkage control module 2 is used for wirelessly connecting a plurality of cameras on a street, controlling the shooting angle of each camera and shooting at multiple angles towards the same position;
the crowd data processing module 3 is configured to receive a shot image transmitted by the multi-camera thermal sensing stereo shooting module 1, and read each thermal sensing pixel point in the shot video image;
the coincident pixel point data processing module 4 is used for carrying out multi-angle comparison on coincident thermal induction pixel points in the received shot video image, combining and analyzing multi-angle images acquired by the multi-camera thermal induction stereo shooting module 1 and judging the number of people gathering.
Further, referring to fig. 1, the crowd data processing module 3 includes an information transmission unit 31 and an arithmetic unit 32, the information transmission unit 31 is connected with the multi-camera thermal sensing stereo shooting module 1 and is connected with the camera linkage control module 2, and the arithmetic unit 32 is connected with the information transmission unit 31 and is connected with the coincident pixel data processing module;
the information transmission unit 31 is configured to receive image information of the multi-camera thermal sensing stereo shooting module 1 and send control information to the camera linkage control module 2;
the operation unit 32 is configured to obtain pixel points of a moving target in the captured image, and construct a character model of the target pixel points.
Further, referring to fig. 1, the coincident pixel point data processing module 4 includes a model comparing unit 41 and a determining unit 42, the model comparing unit 41 is connected to the computing unit 32, and the determining unit 42 is connected to the model comparing unit 41;
the model comparing unit 41 is configured to compare character models in the plurality of captured images generated by the arithmetic unit 32, and determine the number of character models at positions where the plurality of character models overlap each other from the plurality of captured images;
the determining unit 42 is configured to compare the number of character models determined in the model comparing unit 41 with a predetermined threshold, and determine whether there is a crowd event at the current location.
In this embodiment, the multi-camera thermal sensing stereo camera module 1 is configured to mount a first thermal imaging camera and a second thermal imaging camera at two opposite corners of a street, the first thermal imaging camera and the second thermal imaging camera are mounted in opposite directions, and can shoot front and back sides of a target area, and a third thermal imaging camera is mounted between the first thermal imaging camera and the second thermal imaging camera and horizontally and vertically faces the first thermal imaging camera and the second thermal imaging camera, so as to shoot front, back, and side surfaces of the target area; the camera linkage control module 2 connects the multiple thermal imaging cameras through wireless signals, and transmits a control command through the wireless signals to adjust the angles of the thermal imaging cameras, and because each thermal imaging camera shoots an area independently during normal shooting, the camera linkage control module 2 can control the multiple thermal imaging cameras to shoot multiple angles towards a target area, so that when a single camera shoots a superposed thermal imaging image, a control signal is sent to the camera linkage control module 2; the information transmission unit 31 receives the thermal imaging image transmitted by the multi-camera thermal sensing stereo camera module 1 through a wireless signal, the operation unit 32 extracts the boundary of the closed region of the block mass without the hole, including determining the target point in the binarized image, acquiring a target area according to the target point, acquiring the maximum scales of the lumps along the X-axis and Y-axis directions and determining the origin of coordinates according to the target area, taking the origin of coordinates as the upper left corner, selecting a window with the size of 2 x 2 as an observation window, traversing the target area to obtain a boundary observation window, storing the number of the boundary observation window into a boundary array in a clockwise arrangement mode, sequentially reading the numbers in the boundary array, connecting the central pixel points of the observation windows corresponding to the numbers to generate a closed region boundary, and generating a character model of a target region; by the method, the number of the character models in the target area is obtained by shooting the target area in multiple directions by combining the multi-camera thermal induction stereo shooting module 1, the number of the characters in the target area is limited due to the fact that the preset threshold value is set in the external terminal through the judging unit 42, and when the number of the obtained character models in the target area exceeds the preset threshold value, the early warning information is sent out, so that the number of the crowd persons in the target area can be accurately judged.
Referring to fig. 2 to 6, a method for detecting a crowd event using the system for detecting a crowd event includes the following steps,
s401: arranging a plurality of thermal imaging cameras on a street;
s4011: a first thermal imaging camera is arranged at a corner of a street;
s4012: a second thermal imaging camera capable of aligning with the first thermal imaging camera is arranged on the other side of the street;
s4013: a third thermal imaging camera in the horizontal and vertical direction is arranged between the first thermal imaging camera and the second thermal imaging camera;
in this embodiment, the multi-camera thermal sensing stereo camera module 1 is formed by installing a first thermal imaging camera and a second thermal imaging camera at two opposite corners of a street, wherein the first thermal imaging camera and the second thermal imaging camera are installed in opposite directions, and can shoot the front side and the rear side of a target area, and a third thermal imaging camera is installed between the first thermal imaging camera and the second thermal imaging camera and horizontally and vertically faces the directions of the first thermal imaging camera and the second thermal imaging camera, so that the shooting of the front side, the rear side and the side of the target area is realized.
S402: the camera linkage control module 2 controls each thermal imaging camera to independently shoot an image of an area and transmits the image to the information transmission unit 31;
s403: the arithmetic unit 32 generates a character model from the image shot by the thermal imaging camera;
s4031: acquiring thermal imaging pixel points of a moving target in a shot image;
s4032: performing combined modeling on the obtained thermal imaging pixel points;
s4033: comparing the modeling data with the human body characteristics to judge whether the figures are overlapped;
in this embodiment, the camera linkage control module 2 connects a plurality of thermal imaging cameras through wireless signals, and transmits a control command through wireless signals, so that the thermal imaging cameras adjust angles, and since each thermal imaging camera shoots an area independently during normal shooting, the camera linkage control module 2 can control the plurality of thermal imaging cameras to shoot a plurality of angles towards a target area, so that when a single camera shoots a superposed thermal imaging image, a control signal is sent to the camera linkage control module 2; the information transmission unit 31 receives the thermal imaging image transmitted by the multi-camera thermal sensing stereo camera module 1 through a wireless signal, the operation unit 32 extracts the boundary of the closed region of the block mass without the hole, including determining the target point in the binarized image, acquiring a target area according to the target point, acquiring the maximum scales of the lumps along the X-axis and Y-axis directions and determining the origin of coordinates according to the target area, taking the origin of coordinates as the upper left corner, selecting a window with the size of 2 x 2 as an observation window, traversing the target area to obtain a boundary observation window, storing the number of the boundary observation window into a boundary array in a clockwise arrangement mode, and sequentially reading the numbers in the boundary array, connecting the central pixel points of the observation windows corresponding to the numbers to generate a closed region boundary, and thus generating a character model of the target region.
S404: the camera linkage control module 2 adjusts the angles of a plurality of cameras in the character model overlapping area to obtain multi-angle shot images of the character model overlapping area;
s4041: shooting a target position by respectively adopting the first thermal imaging camera and the second thermal imaging camera;
s4042: shooting the target position by adopting the third thermal imaging camera;
s4043: obtaining a character model of the target position;
s405: the model comparison unit 41 determines the number of character models of the current image, performs limb division on the obtained character models, and determines the number of character models at the superposition positions of a plurality of character models from a plurality of shot images;
s406: the determination unit 42 compares the number of character models of the current image with a threshold value to determine whether a crowd event exists;
s4061: a people threshold for a crowd event is preset,
s4062: acquiring the number of character models at the target position;
s4063: and comparing the number of the character models at the target position with a preset threshold value, and judging whether a crowd event exists or not.
In the present embodiment, the number of character models in the target area is obtained by shooting the target area in multiple directions in combination with the multi-camera thermal sensing stereo shooting module 1, and since a preset threshold is set in the external terminal through the determination unit 42, the number of characters in the target area is limited, and when the number of obtained character models in the target area exceeds the preset threshold, the warning information is sent out, so that the number of people gathering people in the target area can be accurately determined.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A crowd event detection system is characterized by comprising a multi-camera thermal induction stereo shooting module, a camera linkage control module, a crowd data processing module and a coincident pixel point data processing module;
the camera linkage control module is connected with the multiple-camera thermal induction stereo shooting module, the crowd data processing module is connected with the multiple-camera thermal induction stereo shooting module and the camera linkage control module, and the coincident pixel point data processing module is connected with the crowd data processing module;
the multi-camera thermal induction stereo shooting module is used for shooting heat-bearing organisms in street views from multiple angles through a plurality of thermal induction cameras arranged on a street;
the camera linkage control module is used for wirelessly connecting a plurality of cameras on a street, controlling the shooting angle of each camera and shooting at multiple angles towards the same position;
the crowd data processing module is used for receiving the shot images transmitted by the multi-camera thermal induction stereo shooting module and reading each thermal induction pixel point in the shot video images;
the coincident pixel point data processing module is used for carrying out multi-angle comparison on coincident thermal induction pixel points in the received shot video image, combining and analyzing the multi-angle image acquired by the multi-camera thermal induction stereo shooting module and judging the number of people gathering.
2. The crowd event detection system of claim 1,
the crowd data processing module comprises an information transmission unit and an operation unit, the information transmission unit is connected with the multi-camera thermal induction stereo shooting module and is connected with the camera linkage control module, and the operation unit is connected with the information transmission unit and is connected with the overlapped pixel data processing module;
the information transmission unit is used for receiving the image information of the multi-camera thermal induction stereo shooting module and sending control information to the camera linkage control module;
and the operation unit is used for acquiring pixel points of a moving target in the shot image and constructing a character model of the target pixel points.
3. The crowd event detection system of claim 2,
the coincident pixel point data processing module comprises a model comparison unit and a judgment unit, wherein the model comparison unit is connected with the operation unit, and the judgment unit is connected with the model comparison unit;
the model comparison unit is used for comparing character models in the plurality of shot images generated by the operation unit and determining the number of character models at the superposition positions of the plurality of character models from the plurality of shot images;
and the judging unit is used for comparing the number of the character models determined in the model comparison unit with a preset threshold value and judging whether a crowd event exists at the current position.
4. A crowd event detection method using the crowd event detection system according to claim 3, comprising the steps of,
arranging a plurality of thermal imaging cameras on a street;
the camera linkage control module controls each thermal imaging camera to independently shoot an image of one area and transmits the image to the information transmission unit;
the operation unit generates a character model from the image shot by the thermal imaging camera;
the camera linkage control module adjusts the angles of a plurality of cameras in the character model overlapping area to obtain multi-angle shot images of the character model overlapping area;
the model comparison unit determines the number of character models of the current image;
the judging unit compares the number of the character models of the current image with a threshold value to judge whether a crowd event exists or not.
5. The crowd event detection method of claim 4, wherein in arranging a plurality of thermal imaging cameras on a street, the method further comprises,
a first thermal imaging camera is arranged at a corner of a street;
a second thermal imaging camera capable of aligning with the first thermal imaging camera is arranged on the other side of the street;
and a third thermal imaging camera in the horizontal and vertical direction is arranged between the first thermal imaging camera and the second thermal imaging camera.
6. The crowd event detection method of claim 4, wherein in the computing unit generating a character model from images taken by a thermal imaging camera, the method further comprises,
acquiring thermal imaging pixel points of a moving target in a shot image;
performing combined modeling on the obtained thermal imaging pixel points;
and comparing the modeling data with the human body characteristics to judge whether the figures are overlapped.
7. The crowd event detecting method as claimed in claim 5, wherein in the 'the camera linkage control module adjusts angles of a plurality of cameras where the overlapping regions of the character models occur to obtain multi-angle shot images of the overlapping regions of the character models', the method further comprises,
shooting a target position by respectively adopting the first thermal imaging camera and the second thermal imaging camera;
shooting the target position by adopting the third thermal imaging camera;
a character model of the target location is obtained.
8. The crowd event detecting method as claimed in claim 4, wherein in the determining the number of character models of the current picture by the model comparing unit, the method further comprises,
the obtained character models are subjected to limb division, and the number of character models at the position where the plurality of character models overlap is determined from the plurality of captured images.
9. The crowd event detecting method according to claim 4, wherein in the determining unit comparing the number of character models of the current image with a threshold value to determine whether a crowd event exists,
a people threshold for a crowd event is preset,
acquiring the number of character models at the target position;
and comparing the number of the character models at the target position with a preset threshold value, and judging whether a crowd event exists or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110549833.3A CN113392714A (en) | 2021-05-20 | 2021-05-20 | Crowd event detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110549833.3A CN113392714A (en) | 2021-05-20 | 2021-05-20 | Crowd event detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113392714A true CN113392714A (en) | 2021-09-14 |
Family
ID=77618100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110549833.3A Pending CN113392714A (en) | 2021-05-20 | 2021-05-20 | Crowd event detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392714A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116385969A (en) * | 2023-04-07 | 2023-07-04 | 暨南大学 | Personnel gathering detection system based on multi-camera cooperation and human feedback |
| CN117156259A (en) * | 2023-10-30 | 2023-12-01 | 海信集团控股股份有限公司 | Video stream acquisition method and electronic equipment |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010077316A1 (en) * | 2008-12-17 | 2010-07-08 | Winkler Thomas D | Multiple object speed tracking system |
| US20140072170A1 (en) * | 2012-09-12 | 2014-03-13 | Objectvideo, Inc. | 3d human pose and shape modeling |
| CN103975577A (en) * | 2011-10-07 | 2014-08-06 | 菲力尔系统公司 | Smart surveillance camera systems and methods |
| CN104981377A (en) * | 2012-11-27 | 2015-10-14 | 克劳德帕克公司 | Controlling use of a single multi-vehicle parking space using multiple cameras |
| CN105184815A (en) * | 2015-07-31 | 2015-12-23 | 江苏诚创信息技术研发有限公司 | Assembly event detection method and system |
| US20170017846A1 (en) * | 2015-07-15 | 2017-01-19 | Umm Al-Qura University | Crowd and traffic monitoring apparatus and method |
| CN107995467A (en) * | 2017-12-19 | 2018-05-04 | 内江师范学院 | A kind of Active Eyes |
| CN108009488A (en) * | 2017-11-29 | 2018-05-08 | 合肥寰景信息技术有限公司 | The street security joint defense system of Behavior-based control analysis |
| CN108062809A (en) * | 2017-11-28 | 2018-05-22 | 特斯联（北京）科技有限公司 | A kind of house access control system for realizing personnel's big data collection analysis |
| CN109219836A (en) * | 2016-01-29 | 2019-01-15 | 麦墨艾斯有限责任公司 | Pass in and out limited community's monitoring system |
| CN109445315A (en) * | 2018-08-21 | 2019-03-08 | 成都理工大学 | High-voltage test hall safety guard and method of controlling security |
| CN110235188A (en) * | 2016-10-31 | 2019-09-13 | 埃施朗公司 | Video data and GIS for traffic monitoring, event detection and variation prediction map |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN111445678A (en) * | 2020-04-27 | 2020-07-24 | 南京瑞宇环保科技有限公司 | Crowd gathering monitoring and dissuading system based on Internet of things |
| CN111564022A (en) * | 2020-05-26 | 2020-08-21 | 姜培生 | Intelligent terminal for detecting panoramic display of multi-target temperature data images |
| CN211860321U (en) * | 2020-06-02 | 2020-11-03 | 重庆溢哲渝实业有限公司 | People stream gathering monitoring camera based on thermal imaging |
| CN112016518A (en) * | 2020-09-14 | 2020-12-01 | 郑州航空工业管理学院 | Crowd distribution form detection method based on unmanned aerial vehicle and artificial intelligence |
-
2021
- 2021-05-20 CN CN202110549833.3A patent/CN113392714A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010077316A1 (en) * | 2008-12-17 | 2010-07-08 | Winkler Thomas D | Multiple object speed tracking system |
| CN103975577A (en) * | 2011-10-07 | 2014-08-06 | 菲力尔系统公司 | Smart surveillance camera systems and methods |
| US20140072170A1 (en) * | 2012-09-12 | 2014-03-13 | Objectvideo, Inc. | 3d human pose and shape modeling |
| CN104981377A (en) * | 2012-11-27 | 2015-10-14 | 克劳德帕克公司 | Controlling use of a single multi-vehicle parking space using multiple cameras |
| US20170017846A1 (en) * | 2015-07-15 | 2017-01-19 | Umm Al-Qura University | Crowd and traffic monitoring apparatus and method |
| CN105184815A (en) * | 2015-07-31 | 2015-12-23 | 江苏诚创信息技术研发有限公司 | Assembly event detection method and system |
| CN109219836A (en) * | 2016-01-29 | 2019-01-15 | 麦墨艾斯有限责任公司 | Pass in and out limited community's monitoring system |
| CN110235188A (en) * | 2016-10-31 | 2019-09-13 | 埃施朗公司 | Video data and GIS for traffic monitoring, event detection and variation prediction map |
| CN108062809A (en) * | 2017-11-28 | 2018-05-22 | 特斯联（北京）科技有限公司 | A kind of house access control system for realizing personnel's big data collection analysis |
| CN108009488A (en) * | 2017-11-29 | 2018-05-08 | 合肥寰景信息技术有限公司 | The street security joint defense system of Behavior-based control analysis |
| CN107995467A (en) * | 2017-12-19 | 2018-05-04 | 内江师范学院 | A kind of Active Eyes |
| CN109445315A (en) * | 2018-08-21 | 2019-03-08 | 成都理工大学 | High-voltage test hall safety guard and method of controlling security |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN111445678A (en) * | 2020-04-27 | 2020-07-24 | 南京瑞宇环保科技有限公司 | Crowd gathering monitoring and dissuading system based on Internet of things |
| CN111564022A (en) * | 2020-05-26 | 2020-08-21 | 姜培生 | Intelligent terminal for detecting panoramic display of multi-target temperature data images |
| CN211860321U (en) * | 2020-06-02 | 2020-11-03 | 重庆溢哲渝实业有限公司 | People stream gathering monitoring camera based on thermal imaging |
| CN112016518A (en) * | 2020-09-14 | 2020-12-01 | 郑州航空工业管理学院 | Crowd distribution form detection method based on unmanned aerial vehicle and artificial intelligence |
Non-Patent Citations (4)
| Title |
|---|
| ANTOINE RIMBOUX 等: "Smart IoT Cameras for Crowd Analysis based on augmentation for automatic pedestrian detection, simulation and annotation", 《ARXIV:1906.03994》, pages 1 - 8 * |
| 张苗辉: "基于视觉系统的行人检测与跟踪方法研究", 《中国博士学位论文全文数据库 信息科技辑》, no. 2017, pages 138 - 46 * |
| 邓诗祯: "基于人脸识别的安全管理系统研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2019, pages 138 - 1009 * |
| 鲍天龙 等: "基于深度学习的监控视频中的异常事件检测和对象识别", 《中国博士学位论文全文数据库信息科技辑》, no. 2019, pages 138 - 48 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116385969A (en) * | 2023-04-07 | 2023-07-04 | 暨南大学 | Personnel gathering detection system based on multi-camera cooperation and human feedback |
| CN116385969B (en) * | 2023-04-07 | 2024-03-12 | 暨南大学 | Personnel gathering detection system based on multi-camera cooperation and human feedback |
| CN117156259A (en) * | 2023-10-30 | 2023-12-01 | 海信集团控股股份有限公司 | Video stream acquisition method and electronic equipment |
| CN117156259B (en) * | 2023-10-30 | 2024-03-22 | 海信集团控股股份有限公司 | Video stream acquisition method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104902246B (en) | Video monitoring method and device | |
| US8488001B2 (en) | Semi-automatic relative calibration method for master slave camera control | |
| KR101343975B1 (en) | System for detecting unexpected accident | |
| CN104103030A (en) | Image analysis method, camera apparatus, control apparatus and control method | |
| CN110491060B (en) | Robot, safety monitoring method and device thereof, and storage medium | |
| CN113392714A (en) | Crowd event detection method and system | |
| CN104954747B (en) | Video monitoring method and device | |
| CN105718863A (en) | Living-person face detection method, device and system | |
| CN103329518A (en) | Image capturing system, camera control device for use therein, image capturing method, camera control method, and computer program | |
| WO2021259365A1 (en) | Target temperature measurement method and apparatus, and temperature measurement system | |
| CN112711263A (en) | Storage automatic guided vehicle obstacle avoidance method and device, computer equipment and storage medium | |
| CN109784028B (en) | Face unlocking method and related device | |
| US10878228B2 (en) | Position estimation system | |
| KR100879622B1 (en) | Method for detecting objects passing through virtual paths on video | |
| KR101410985B1 (en) | monitoring system and monitoring apparatus using security camera and monitoring method thereof | |
| CN113068000B (en) | Video target monitoring method, device, equipment, system and storage medium | |
| EP4354853A1 (en) | Thermal-image-monitoring system using plurality of cameras | |
| US11166005B2 (en) | Three-dimensional information acquisition system using pitching practice, and method for calculating camera parameters | |
| CN113840137B (en) | Verification method and system for mobile detection sensitivity of network camera | |
| KR101845612B1 (en) | 3d information acquisition system using practice of pitching and method for calculation of camera parameter | |
| CN105376523A (en) | Stereoscopic vision detection method and system | |
| CN112406700B (en) | Blind area early warning system based on upper and lower binocular vision analysis range finding | |
| JPWO2018235256A1 (en) | Stereo measuring device and system | |
| CN113191197A (en) | Image restoration method and device | |
| CN111064483A (en) | Wearable monitoring device and monitoring method |
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 |