CN110309819A - A kind of crowded estimating system - Google Patents
A kind of crowded estimating system Download PDFInfo
- Publication number
- CN110309819A CN110309819A CN201910695329.7A CN201910695329A CN110309819A CN 110309819 A CN110309819 A CN 110309819A CN 201910695329 A CN201910695329 A CN 201910695329A CN 110309819 A CN110309819 A CN 110309819A
- Authority
- CN
- China
- Prior art keywords
- heat dissipation
- column
- cooling fin
- crowded
- pedestrian
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B17/00—Details of cameras or camera bodies; Accessories therefor
- G03B17/55—Details of cameras or camera bodies; Accessories therefor with provision for heating or cooling, e.g. in aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/52—Elements optimising image sensor operation, e.g. for electromagnetic interference [EMI] protection or temperature control by heat transfer or cooling elements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes a kind of crowded estimating system, including spherical camera and the chip being arranged in spherical camera, ball-shaped camera is equipped with radiating piece, radiating piece includes radiating part and cooling fin, radiating part is connected with cooling fin by heating column, heating column is equipped with mounting portion, mounting portion is equipped with screw thread, cooling fin is circumferentially with several auxiliary heat dissipation columns, the inside of auxiliary heat dissipation column is equipped with internal layer thermal column, auxiliary heat dissipation column is connected with internal layer thermal column by radiator, radiator is connected by interconnecting piece with cooling fin, the surface of cooling fin is equipped with hexagonal screw hole, the crowded estimation method of built-in chip type.Radiating part of the invention is directly contacted with chip, and passes through heating column for heat derives.The heat dissipation effect for ball machine shell can be improved by auxiliary heat dissipation column.Using personnel's overlapping area, video camera sets up profound value judgement personnel's degree of crowding more than angle, the degree of crowding of the more scientific practical crowd of judge in conjunction with the ratio of pedestrian's area.
Description
Technical field
The invention belongs to vision facilities field, especially a kind of crowded estimating system.
Background technique
The approach of traditional guarantee crowd's safety mainly manually passes through a certain scene of video monitoring, subjective judgement crowd's shape
State carries out early warning when crowd density is more than to a certain degree, while field personnel being notified to close crowd and largely gush people
Entrance.The image that can use video monitoring shooting at present judges the degree of crowding that crowd is determined in realization automatically
The scientific management of amount.But this kind of camera chip power consumption is larger, and calorific value is high, if effectively thermally conductive cannot can reduce video camera
Service life.
Summary of the invention
The present invention proposes a kind of crowded estimating system, the technical solution adopted is as follows:
A kind of crowded estimating system, including spherical camera, ball-shaped camera are equipped with radiating piece, the radiating piece
Including radiating part and cooling fin, radiating part is connected with cooling fin by heating column, and heating column is equipped with mounting portion, is set on mounting portion
There is screw thread, cooling fin is circumferentially with several auxiliary heat dissipation columns, and the inside of auxiliary heat dissipation column is equipped with internal layer thermal column, auxiliary heat dissipation
Column is connected with internal layer thermal column by radiator, and radiator is connected by interconnecting piece with cooling fin, and the surface of cooling fin is equipped with six
Angle screw hole.
Further, the outside of auxiliary heat dissipation column is equipped with heat dissipation ring body, and heat dissipation ring body is made of pairs of arc copper sheet, often
Three-legged structure is constituted to arc copper sheet.
Further, mounting portion is used to for radiating piece being fixed on the opening of ball machine shell, and the opening of ball machine shell is set
There is sealing rubber ring, radiating part is in contact with the chip surface in ball-shaped camera after fixing radiating piece.
It further, is in 120 °~150 ° angles between interconnecting piece and cooling fin;The outside of radiator is equipped with the first thermal conductive silicon
The bottom end of glue, auxiliary heat dissipation column is equipped with the second heat conductive silica gel, and the bottom end of auxiliary heat dissipation column is in contact with ball machine shell.
Further, heating column is hollow copper post.
Further, the crowded estimation method of the built-in chip type, step include:
S1. the crowd's area zoom that will test is then fed into 300*300 size to trained pedestrian detection model
The pedestrian detection in the region is carried out, each pedestrian detected in time domain can be demarcated by pixel frame, the pixel in each frame
Generate an identical mark;
S2. pedestrian's gross area S in statistical regionsPedestrian, the pixel summation of all pixels frame in image is calculated, people is counted
Overlapping area S between pedestrian in group regionOverlapping, the pixel summation in pixel frame with multiple marks is calculated, ratio is sought,
SOverlapping/SPedestrian;
S3. crowded degree evaluation: S is calculatedOverlapping/SPedestrian* cosA, wherein A is camera optical axis plane perpendicular to the ground
Angle.
It compared with prior art, the beneficial effects of the present invention are: radiating piece proposed by the present invention include radiating part and auxiliary
Thermal column is helped, wherein radiating part is directly contacted with chip, and passes through heating column for heat derives.It can be mentioned by auxiliary heat dissipation column
Heat dissipation effect of the principle of readjustment, restructuring, consolidation and improvement to ball machine shell.Using personnel's overlapping area, video camera sets up angle in conjunction with the ratio of pedestrian's area
Yu Xuan value judges personnel's degree of crowding, the degree of crowding of the more scientific practical crowd of judge.
Detailed description of the invention
Fig. 1 is radiating piece overall schematic;
Fig. 2 is auxiliary heat dissipation rod structure schematic diagram;
Fig. 3 is radiator structure scheme of installation.
Description of symbols:
Radiating part -1, heating column -11, screw thread -12, sealing rubber ring -13, cooling fin -2, auxiliary heat dissipation column -3, internal layer heat dissipation
Column -31, interconnecting piece -32, radiate ring body -33, radiator -34, the first heat conductive silica gel -35, the second heat conductive silica gel -36, outside ball machine
Shell -4.
Specific embodiment
As shown in Figure 1 to Figure 3, the crowded estimating system proposed in the present embodiment, including spherical camera, ball-type are taken the photograph
Camera is equipped with radiating piece, and the radiating piece includes radiating part 1 and cooling fin 2, and radiating part 1 and cooling fin 2 pass through heating column 11
It is connected, heating column 11 is equipped with mounting portion, and mounting portion is equipped with screw thread 12, and cooling fin 2 is circumferentially with several auxiliary heat dissipation columns
3, the inside of auxiliary heat dissipation column 3 is equipped with internal layer thermal column 31, and auxiliary heat dissipation column 3 and internal layer thermal column 31 pass through 34 phase of radiator
Even, radiator 34 is connected by interconnecting piece 32 with cooling fin 2, and the surface of cooling fin 2 is equipped with hexagonal screw hole.
Wherein, the outside of auxiliary heat dissipation column 3 is equipped with heat dissipation ring body 33, and heat dissipation ring body 33 is made of pairs of arc copper sheet,
Each pair of arc copper sheet constitutes three-legged structure.Mounting portion is used to for radiating piece being fixed on the opening of ball machine shell 4, ball machine shell 4
Opening be equipped with sealing rubber ring 13, radiating part 1 is in contact with the chip surface in ball-shaped camera after fixing radiating piece.Even
It is in 120 °~150 ° angles between socket part 32 and cooling fin 2;The outside of radiator 34 is equipped with the first heat conductive silica gel 35, auxiliary heat dissipation column
3 bottom end is equipped with the second heat conductive silica gel 36, and the bottom end of auxiliary heat dissipation column 3 is in contact with ball machine shell 4.Heating column 11 is hollow
Copper post.
In the present embodiment, the heat dissipation effect of ball machine is improved by the cooperation of both radiating part and auxiliary heat dissipation column.
The another aspect of the present embodiment proposes a kind of crowded estimation method based on convolutional neural networks, can utilize
The image of video monitoring shooting judges the degree of crowding that realization carries out quantitative scientific management to crowd automatically.
Detection method includes the following steps:
By marking demographic data collection manually, training pattern (mobileNet_ssd), for detect in video image whether
There are more crowds, then provide crowd's location information in image if it exists;
Effect of the step to entire algorithm: 1) foreclosing scattered pedestrian, improves algorithm detection accuracy;If 2) current
Without crowd, algorithm is subsequent to be not processed image, improves algorithm whole efficiency;
The crowd's area zoom that will test is then fed into 300*300 size to trained pedestrian detection model
(YOLO_v3), the pedestrian detection in the region is carried out;Each pedestrian in region can be demarcated by pixel frame, the picture in each frame
Element all generates an identical mark.
Effect of the step to entire algorithm: separating the single pedestrian in image and demarcate, for pedestrian's area,
Overlapping area calculates between pedestrian.
Pedestrian's gross area S in statistic procedure 1 in crowd regionPedestrian, that is, the pixel for calculating all pixels frame in image is total
With;
Overlapping area S between pedestrian in statistics crowd regionOverlapping, that is, calculate the pixel in pixel frame with multiple marks
Summation;
Seek ratio, SOverlapping/SPedestrian;
The crowded degree of current scene and the erection angle of video camera are related, final crowded degree evaluation:
SOverlapping/SPedestrian* cosA, wherein A is the erection angle of camera.
The present invention utilizes ratio in judgement personnel's degree of crowding of personnel's overlapping area and pedestrian's area, the picture of video camera acquisition
There are angular deviations for the personnel positions relationship and actual person positional relationship of face shooting, therefore set up the remaining of angle using video camera
Profound value makes up deviation, the degree of crowding of the more scientific practical crowd of judge.
The technical principle of the invention is described above in combination with a specific embodiment, these descriptions are intended merely to explain of the invention
Technical principle, and shall not be construed in any way as a limitation of the scope of protection of the invention.Based on this explanation, skill in the art
Art personnel do not need to pay for creative labor and can associate other specific embodiments of the invention and fall within the present invention
Protection scope in.
Claims (6)
1. a kind of crowded estimating system, including spherical camera, which is characterized in that ball-shaped camera is equipped with radiating piece,
The radiating piece includes radiating part (1) and cooling fin (2), and radiating part (1) is connected by heating column (11) with cooling fin (2), is led
Plume (11) is equipped with mounting portion, and mounting portion is equipped with screw thread (12), and cooling fin (2) is circumferentially with several auxiliary heat dissipation columns
(3), the inside of auxiliary heat dissipation column (3) is equipped with internal layer thermal column (31), and auxiliary heat dissipation column (3) and internal layer thermal column (31) are by dissipating
Hot body (34) is connected, and radiator (34) is connected by interconnecting piece (32) with cooling fin (2), and the surface of cooling fin (2) is equipped with hexagonal
Screw hole.
2. a kind of crowded estimating system as described in claim 1, which is characterized in that the outside of auxiliary heat dissipation column (3) is equipped with
It radiates ring body (33), heat dissipation ring body (33) is made of pairs of arc copper sheet, and each pair of arc copper sheet constitutes three-legged structure.
3. a kind of crowded estimating system as claimed in claim 2, which is characterized in that mounting portion is for radiating piece to be fixed on
In the opening of ball machine shell (4), the opening of ball machine shell (4) is equipped with sealing rubber ring (13), fixes radiating part after radiating piece
(1) it is in contact with the chip surface in ball-shaped camera.
4. a kind of crowded estimating system as claimed in claim 3, which is characterized in that interconnecting piece (32) and cooling fin (2) it
Between be in 120 °~150 ° angles;The outside of radiator (34) is equipped with the first heat conductive silica gel (35), and the bottom end of auxiliary heat dissipation column (3) is equipped with
The bottom end of second heat conductive silica gel (36), auxiliary heat dissipation column (3) is in contact with ball machine shell (4).
5. a kind of crowded estimating system as described in claim 1, which is characterized in that heating column (11) is hollow copper post.
6. a kind of crowded estimating system as claimed in claim 3, which is characterized in that the crowded estimation of built-in chip type
Method, step include:
S1. the crowd's area zoom that will test is then fed into trained pedestrian detection model and carries out to 300*300 size
The pedestrian detection in the region, each pedestrian detected in time domain can be demarcated by pixel frame, and the pixel in each frame generates
One identical mark;
S2. pedestrian's gross area S in statistical regionsPedestrian, the pixel summation of all pixels frame in image is calculated, crowd area is counted
Overlapping area S between pedestrian in domainOverlapping, the pixel summation in pixel frame with multiple marks is calculated, ratio, S are soughtOverlapping/
SPedestrian;
S3. crowded degree evaluation: S is calculatedOverlapping/SPedestrian* cosA, wherein A is the folder of camera optical axis plane perpendicular to the ground
Angle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910695329.7A CN110309819B (en) | 2019-07-30 | 2019-07-30 | Crowd crowding estimation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910695329.7A CN110309819B (en) | 2019-07-30 | 2019-07-30 | Crowd crowding estimation system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110309819A true CN110309819A (en) | 2019-10-08 |
CN110309819B CN110309819B (en) | 2023-10-13 |
Family
ID=68082616
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910695329.7A Active CN110309819B (en) | 2019-07-30 | 2019-07-30 | Crowd crowding estimation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110309819B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200635489A (en) * | 2005-03-25 | 2006-10-01 | Hon Hai Prec Ind Co Ltd | Thermal module |
CN201876649U (en) * | 2010-11-11 | 2011-06-22 | 徐象贤 | Infrared ball of integrated video camera |
CN201937726U (en) * | 2010-11-25 | 2011-08-17 | 天津市天下数码视频有限公司 | Indoor intelligent ball cover |
CN202362568U (en) * | 2011-09-20 | 2012-08-01 | 江久金 | Novel infrared intelligent ball-type holder |
CN103093214A (en) * | 2013-02-01 | 2013-05-08 | 浙江捷尚视觉科技有限公司 | Pedestrian detection method based on on-board infrared camera |
CN203708743U (en) * | 2014-01-26 | 2014-07-09 | 天津天地伟业数码科技有限公司 | Heating and heat dissipation apparatus of integrated camera core |
CN104048278A (en) * | 2014-06-19 | 2014-09-17 | 江苏华兴电子有限公司 | Radiator with high cooling capability and LED floodlight |
CN104504377A (en) * | 2014-12-25 | 2015-04-08 | 中邮科通信技术股份有限公司 | Bus passenger crowding degree identification system and method |
CN104900794A (en) * | 2015-06-18 | 2015-09-09 | 东莞市闻誉实业有限公司 | LED lamp heat radiation structure |
CN205249329U (en) * | 2015-11-20 | 2016-05-18 | 天津市贝斯特防爆电器有限公司 | Novel spherical camera of explosion -proof high speed |
CN206313873U (en) * | 2016-12-16 | 2017-07-07 | 清华大学苏州汽车研究院(吴江) | A kind of removable seal camera for being easy to radiate |
CN208128405U (en) * | 2018-05-15 | 2018-11-20 | 广州嘉特电子科技有限公司 | integrated network spherical camera |
CN108881821A (en) * | 2018-05-28 | 2018-11-23 | 西南交通大学 | It is a kind of to utilize the self-powered subway carriage degree of crowding display system of subway station wind-force and its method |
CN109272487A (en) * | 2018-08-16 | 2019-01-25 | 北京此时此地信息科技有限公司 | The quantity statistics method of crowd in a kind of public domain based on video |
CN208836234U (en) * | 2018-08-07 | 2019-05-07 | 浙江大华技术股份有限公司 | A kind of heat dissipation protection integrated structure and video camera |
CN210072646U (en) * | 2019-07-30 | 2020-02-14 | 天津艾思科尔科技有限公司 | Crowd estimation device |
-
2019
- 2019-07-30 CN CN201910695329.7A patent/CN110309819B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200635489A (en) * | 2005-03-25 | 2006-10-01 | Hon Hai Prec Ind Co Ltd | Thermal module |
CN201876649U (en) * | 2010-11-11 | 2011-06-22 | 徐象贤 | Infrared ball of integrated video camera |
CN201937726U (en) * | 2010-11-25 | 2011-08-17 | 天津市天下数码视频有限公司 | Indoor intelligent ball cover |
CN202362568U (en) * | 2011-09-20 | 2012-08-01 | 江久金 | Novel infrared intelligent ball-type holder |
CN103093214A (en) * | 2013-02-01 | 2013-05-08 | 浙江捷尚视觉科技有限公司 | Pedestrian detection method based on on-board infrared camera |
CN203708743U (en) * | 2014-01-26 | 2014-07-09 | 天津天地伟业数码科技有限公司 | Heating and heat dissipation apparatus of integrated camera core |
CN104048278A (en) * | 2014-06-19 | 2014-09-17 | 江苏华兴电子有限公司 | Radiator with high cooling capability and LED floodlight |
CN104504377A (en) * | 2014-12-25 | 2015-04-08 | 中邮科通信技术股份有限公司 | Bus passenger crowding degree identification system and method |
CN104900794A (en) * | 2015-06-18 | 2015-09-09 | 东莞市闻誉实业有限公司 | LED lamp heat radiation structure |
CN205249329U (en) * | 2015-11-20 | 2016-05-18 | 天津市贝斯特防爆电器有限公司 | Novel spherical camera of explosion -proof high speed |
CN206313873U (en) * | 2016-12-16 | 2017-07-07 | 清华大学苏州汽车研究院(吴江) | A kind of removable seal camera for being easy to radiate |
CN208128405U (en) * | 2018-05-15 | 2018-11-20 | 广州嘉特电子科技有限公司 | integrated network spherical camera |
CN108881821A (en) * | 2018-05-28 | 2018-11-23 | 西南交通大学 | It is a kind of to utilize the self-powered subway carriage degree of crowding display system of subway station wind-force and its method |
CN208836234U (en) * | 2018-08-07 | 2019-05-07 | 浙江大华技术股份有限公司 | A kind of heat dissipation protection integrated structure and video camera |
CN109272487A (en) * | 2018-08-16 | 2019-01-25 | 北京此时此地信息科技有限公司 | The quantity statistics method of crowd in a kind of public domain based on video |
CN210072646U (en) * | 2019-07-30 | 2020-02-14 | 天津艾思科尔科技有限公司 | Crowd estimation device |
Non-Patent Citations (2)
Title |
---|
天津汇讯视通科技有限公司: "节能型视频分析&自动跟踪型 SDI 高清红外球型摄像机", 《科技成果》, pages 1 - 4 * |
浙江大华技术股份有限公司: "大华高清红外智能球型摄像机", 《科技成果》, pages 1 - 4 * |
Also Published As
Publication number | Publication date |
---|---|
CN110309819B (en) | 2023-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107478340B (en) | A kind of converter valve monitoring method and system based on image co-registration | |
Veena et al. | Smart street light system based on image processing | |
CN204334815U (en) | The wide-angle video watch-dog of multiple IP camera | |
CN109580109A (en) | A kind of method that soft straight converter valve tower cooler water leak monitors automatically | |
CN107576269B (en) | Power transmission line forest fire positioning method | |
Badgelwar et al. | Survey on energy efficient smart street light system | |
CN110173627A (en) | A kind of solar energy system | |
CN110767411A (en) | Transformer cooling device and operation monitoring system | |
CN108153084A (en) | Refrigeration camera with antifogging function and reduction noise | |
CN110309819A (en) | A kind of crowded estimating system | |
CN110059592B (en) | Multi-camera-based mirror field cloud blocking detection method and device | |
CN204031291U (en) | A kind of digital motion cameras fore shell radiator structure | |
CN109974311A (en) | A kind of solar energy system | |
CN205681530U (en) | A kind of camera utilizing metallic support to dispel the heat | |
CN212541537U (en) | Oil level and temperature infrared thermal imaging double-light monitoring device for oil filling equipment of transformer substation | |
CN109443325A (en) | Utilize the space positioning system of floor-mounted camera | |
CN202256983U (en) | Infrared module, infrared imaging device and monitoring system | |
CN210072646U (en) | Crowd estimation device | |
CN213544959U (en) | Subminiature helmet thermal imaging detector | |
CN112903100A (en) | Brightness detector | |
CN108263439A (en) | A kind of safe train operation monitors system | |
CN209184687U (en) | Convenient for the monitor camera device of heat dissipation | |
CN204437938U (en) | A kind of Multifunctional LED high light polling lamp | |
CN208820878U (en) | A kind of far distance automatic demisting WirelessHD video camera | |
CN207283701U (en) | A kind of target center adjusting apparatus and intelligent monitor system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |