CN110309819B - Crowd crowding estimation system - Google Patents
Crowd crowding estimation system Download PDFInfo
- Publication number
- CN110309819B CN110309819B CN201910695329.7A CN201910695329A CN110309819B CN 110309819 B CN110309819 B CN 110309819B CN 201910695329 A CN201910695329 A CN 201910695329A CN 110309819 B CN110309819 B CN 110309819B
- Authority
- CN
- China
- Prior art keywords
- radiating
- crowd
- column
- heat dissipation
- heat
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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 invention provides a crowd crowding estimation system, which comprises a spherical camera and a chip arranged in the spherical camera, wherein a radiating piece is arranged on the spherical camera and comprises a radiating part and a radiating fin, the radiating part and the radiating fin are connected through a heat conducting column, a mounting part is arranged on the heat conducting column, threads are arranged on the mounting part, a plurality of auxiliary heat radiating columns are arranged in the circumferential direction of the radiating fin, an inner layer heat radiating column is arranged in the auxiliary heat radiating column, the auxiliary heat radiating column is connected with the inner layer heat radiating column through a heat radiating body, the heat radiating body is connected with the radiating fin through a connecting part, a hexagonal screw hole is formed in the surface of the radiating fin, and the crowd crowding estimation method for the chip is provided. The heat dissipation part of the invention is directly contacted with the chip and conducts heat out through the heat conduction column. The heat dissipation effect to the spherical machine shell can be improved through the auxiliary heat dissipation column. And the crowding degree of the personnel is judged by combining the ratio of the personnel overlapping area to the pedestrian area and the residual brown value of the erection angle of the camera, so that the crowding degree of the actual crowd is judged more scientifically.
Description
Technical Field
The invention belongs to the field of image equipment, and particularly relates to a crowd crowding estimation system.
Background
The traditional way of guaranteeing crowd safety is mainly that people monitor a certain scene through the video, subjectively judge crowd state, when crowd density exceeds certain degree, carry out the early warning, inform on-the-spot staff to close the entrance that crowd is surging a large amount of people simultaneously. At present, the crowding degree can be automatically judged by utilizing images shot by video monitoring, so that quantitative scientific management of the crowd is realized. However, such camera chips have a relatively high power consumption and a high heat generation, which can reduce the life of the camera if they cannot conduct heat effectively.
Disclosure of Invention
The invention provides a crowd crowding estimation system, which adopts the following technical scheme:
the utility model provides a crowded estimation system, includes spherical camera, is equipped with the radiating piece on the spherical camera, the radiating piece includes radiating part and fin, and radiating part and fin link to each other through the heat conduction post, are equipped with the installation department on the heat conduction post, are equipped with the screw thread on the installation department, and the circumference of fin is equipped with a plurality of supplementary heat dissipation posts, and the inside of supplementary heat dissipation post is equipped with inlayer heat dissipation post, and supplementary heat dissipation post and inlayer heat dissipation post link to each other through the radiator, and the radiator passes through connecting portion and links to each other with the fin, and the surface of fin is equipped with the hexagonal screw.
Further, the outer side of the auxiliary heat dissipation column is provided with a heat dissipation ring body, the heat dissipation ring body is composed of paired arc-shaped copper plates, and each pair of arc-shaped copper plates forms a triangular structure.
Further, the installation department is used for fixing the radiating part on the opening of ball machine shell, and the opening part of ball machine shell is equipped with sealed rubber ring, and radiating part contacts with the chip surface in the ball-type camera after the radiating part is fixed.
Further, an angle of 120-150 degrees is formed between the connecting part and the radiating fin; the outside of radiator is equipped with first heat conduction silica gel, and the bottom of supplementary heat dissipation post is equipped with second heat conduction silica gel, and the bottom of supplementary heat dissipation post contacts with the ball machine shell.
Further, the heat conducting column is a hollow copper column.
Further, the method for estimating crowd crowds with built-in chips comprises the following steps:
s1, scaling a detected crowd area to 300 x 300, and then sending the crowd area to a trained pedestrian detection model to detect pedestrians in the area, wherein each pedestrian in the detection area is marked by a pixel frame, and pixels in each frame generate the same mark;
s2, counting total pedestrian area S in the area Pedestrian All of the images are calculatedThe sum of pixels of the pixel frames is used for counting the overlapping area S between pedestrians in the crowd area Overlapping of Calculating the sum of pixels with a plurality of marks in a pixel frame, calculating the ratio, S Overlapping of /S Pedestrian ;
S3, calculating crowd crowding degree evaluation: s is S Overlapping of /S Pedestrian * cosA, wherein a is the angle between the camera optical axis and the ground vertical plane.
Compared with the prior art, the invention has the beneficial effects that: the heat dissipation part comprises a heat dissipation part and an auxiliary heat dissipation column, wherein the heat dissipation part is directly contacted with a chip, and heat is conducted out through the heat conduction column. The heat dissipation effect to the spherical machine shell can be improved through the auxiliary heat dissipation column. And the crowding degree of the personnel is judged by combining the ratio of the personnel overlapping area to the pedestrian area and the residual brown value of the erection angle of the camera, so that the crowding degree of the actual crowd is judged more scientifically.
Drawings
FIG. 1 is an overall schematic of a heat sink;
FIG. 2 is a schematic diagram of an auxiliary heat dissipation post structure;
fig. 3 is a schematic diagram of a heat dissipating structure installation.
Reference numerals illustrate:
the heat dissipation device comprises a heat dissipation part-1, a heat conduction column-11, threads-12, a sealing rubber ring-13, a heat dissipation sheet-2, an auxiliary heat dissipation column-3, an inner heat dissipation column-31, a connection part-32, a heat dissipation ring body-33, a heat dissipation body-34, a first heat conduction silica gel-35, a second heat conduction silica gel-36 and a spherical shell-4.
Detailed Description
As shown in fig. 1 to 3, the crowd crowding estimation system proposed in this embodiment includes a spherical camera, a heat dissipation member is provided on the spherical camera, the heat dissipation member includes a heat dissipation portion 1 and a heat dissipation fin 2, the heat dissipation portion 1 and the heat dissipation fin 2 are connected through a heat conduction column 11, a mounting portion is provided on the heat conduction column 11, a thread 12 is provided on the mounting portion, a plurality of auxiliary heat dissipation columns 3 are provided in the circumferential direction of the heat dissipation fin 2, an inner layer heat dissipation column 31 is provided in the auxiliary heat dissipation column 3, the auxiliary heat dissipation columns 3 and the inner layer heat dissipation column 31 are connected through a heat dissipation body 34, the heat dissipation body 34 is connected with the heat dissipation fin 2 through a connecting portion 32, and a hexagonal screw hole is provided on the surface of the heat dissipation fin 2.
The outer side of the auxiliary heat dissipation column 3 is provided with a heat dissipation ring body 33, the heat dissipation ring body 33 is composed of pairs of arc-shaped copper plates, and each pair of arc-shaped copper plates forms a triangular structure. The installation department is used for fixing the radiating part on the opening of ball machine shell 4, and the opening part of ball machine shell 4 is equipped with sealed rubber ring 13, and radiating part 1 contacts with the chip surface in the ball-type camera after the radiating part is fixed. The connecting part 32 and the radiating fin 2 form an angle of 120-150 degrees; the outside of radiator 34 is equipped with first heat conduction silica gel 35, and the bottom of supplementary heat dissipation post 3 is equipped with second heat conduction silica gel 36, and the bottom of supplementary heat dissipation post 3 contacts with ball machine shell 4. The heat conductive pillars 11 are hollow copper pillars.
In the embodiment, the heat dissipation effect of the ball machine is improved through the cooperation of the heat dissipation part and the auxiliary heat dissipation column.
On the other hand, the embodiment provides a crowd crowding estimation method based on a convolutional neural network, which can automatically judge the crowding degree by utilizing images shot by video monitoring, and realize quantitative scientific management of crowds.
The detection method comprises the following steps:
a training model (mobilenet_ssd) is used for detecting whether more people exist in the video image or not through manual labeling of the crowd data set, and if so, crowd position information in the image is given;
the effect of this step on the whole algorithm: 1) Scattered pedestrians are excluded, and the algorithm detection precision is improved; 2) If no crowd exists in the current image, the algorithm does not process the current image, so that the overall efficiency of the algorithm is improved;
scaling the detected crowd area to 300 x 300 size, and then sending the crowd area to a trained pedestrian detection model (yolo_v3) to detect pedestrians in the area; each pedestrian in the area is marked by a frame of pixels, and the pixels in each frame produce the same identification.
The effect of this step on the whole algorithm: and separating and calibrating the single pedestrians in the image, and calculating the area of the pedestrians and the overlapping area between the pedestrians.
Counting the total pedestrian area S in the crowd area in the step 1 Pedestrian Calculating the pixel sum of all pixel frames in the image;
counting the overlapping area S between pedestrians in crowd area Overlapping of Namely, calculating the pixel sum with a plurality of marks in the pixel frame;
calculating the ratio S Overlapping of /S Pedestrian ;
Crowd crowding degree of the current scene is related to the erection angle of the camera, and finally crowd crowding degree is evaluated: s is S Overlapping of /S Pedestrian * cosA, where a is the angle at which the camera is erected.
According to the invention, the crowding degree of the person is judged by using the ratio of the overlapping area of the person to the pedestrian area, and the angular deviation exists between the position relation of the person shot by the picture acquired by the camera and the position relation of the actual person, so that the deviation is compensated by using the residual value of the erection angle of the camera, and the crowding degree of the actual crowd is judged more scientifically.
The technical principle of the present invention has been described above in connection with specific embodiments, which are only for the purpose of explaining the technical principle of the present invention, and should not be construed as limiting the scope of the present invention in any way. Based on this explanation, one skilled in the art will recognize that other embodiments of the present invention do not require inventive effort and will fall within the scope of the present invention.
Claims (5)
1. A crowd crowding estimation system comprising a spherical camera, characterized in that,
the spherical camera is provided with a radiating piece, the radiating piece comprises a radiating part (1) and radiating fins (2), the radiating part (1) is connected with the radiating fins (2) through heat conducting columns (11), the heat conducting columns (11) are provided with mounting parts, the mounting parts are provided with threads (12), the circumference of each radiating fin (2) is provided with a plurality of auxiliary radiating columns (3), the inside of each auxiliary radiating column (3) is provided with an inner radiating column (31), the auxiliary radiating columns (3) are connected with the inner radiating columns (31) through radiating bodies (34), the radiating bodies (34) are connected with the radiating fins (2) through connecting parts (32), and the surfaces of the radiating fins (2) are provided with hexagonal screw holes;
the crowd crowding estimation method with the built-in chip comprises the following steps:
s1, scaling a detected crowd area to 300 x 300, and then sending the crowd area to a trained pedestrian detection model to detect pedestrians in the area, wherein each pedestrian in the detection area is marked by a pixel frame, and pixels in each frame generate the same mark;
s2, counting the total area S pedestrians in the area, calculating the pixel sum of all pixel frames in the image, counting the overlapping area S overlapping among pedestrians in the crowd area, calculating the pixel sum with a plurality of marks in the pixel frames, and calculating the ratio, S overlapping/S pedestrians;
s3, calculating crowd crowding degree evaluation: s overlap/S pedestrian cosA, where a is the angle between the camera optical axis and the ground vertical plane.
2. The crowd congestion estimation system of claim 1, wherein,
the outer side of the auxiliary heat dissipation column (3) is provided with a heat dissipation ring body (33), the heat dissipation ring body (33) is composed of paired arc-shaped copper plates, and each pair of arc-shaped copper plates forms a triangular structure.
3. The crowd congestion estimation system of claim 2, wherein,
the installation department is used for fixing the radiating part on the opening of ball machine shell (4), and the opening part of ball machine shell (4) is equipped with sealed rubber ring (13), and radiating part (1) contacts with the chip surface in the ball-type camera after the radiating part is fixed.
4. The crowd congestion estimation system of claim 3, wherein,
an angle of 120-150 degrees is formed between the connecting part (32) and the radiating fin (2); the outside of radiator (34) is equipped with first heat conduction silica gel (35), and the bottom of supplementary heat dissipation post (3) is equipped with second heat conduction silica gel (36), and the bottom of supplementary heat dissipation post (3) contacts with ball machine shell (4).
5. The crowd congestion estimation system of claim 1, wherein,
the heat conduction column (11) is a hollow copper column.
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 CN110309819A (en) | 2019-10-08 |
CN110309819B true 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 |
---|
大华高清红外智能球型摄像机;浙江大华技术股份有限公司;《科技成果》;1-4 * |
节能型视频分析&自动跟踪型 SDI 高清红外球型摄像机;天津汇讯视通科技有限公司;《科技成果》;1-4 * |
Also Published As
Publication number | Publication date |
---|---|
CN110309819A (en) | 2019-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104717465B (en) | Wide-angle video monitoring equipment and video monitoring method for multiple IP cameras | |
CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
CN103345840B (en) | Road incidents video detecting method is crossed at a kind of cross channel crossing | |
CN105976368A (en) | Insulator positioning method | |
ES2569386T3 (en) | Method and system to process a video image | |
KR102358773B1 (en) | Smart guide device for guiding objects, system and method including the device | |
CN110309819B (en) | Crowd crowding estimation system | |
CN103729620A (en) | Multi-view pedestrian detection method based on multi-view Bayesian network | |
CN106454051A (en) | Multi-angle rotary portable vidicon for network security and protection | |
CN112489372A (en) | Swimming pool monitoring and alarming system | |
Shi | Object detection models and research directions | |
Wang et al. | VIMI: Vehicle-infrastructure multi-view intermediate fusion for camera-based 3D object detection | |
CN205563928U (en) | Outer broken integrated early warning system is prevented to transmission line intelligence based on pattern recognition | |
CN208691429U (en) | A repeated use of staff locating and monitoring system suitable for construction site | |
CN210645067U (en) | Camera module for identifying basketball track | |
CN210072646U (en) | Crowd estimation device | |
CN202018554U (en) | Internal heat dissipating structure of high-definition web camera | |
CN111561915A (en) | Building construction state monitoring feedback device, system and method | |
Radu et al. | Car crash detection in videos | |
Liu et al. | Automated vehicle wheelbase measurement using computer vision and view geometry | |
CN113743380B (en) | Active tracking method based on video image dynamic monitoring | |
Li et al. | A calibration and real-time object matching method for heterogeneous multi-camera system | |
Brasil et al. | Automatic detection of red light running using vehicular cameras | |
CN110032961A (en) | A kind of underground space pipeline method for detecting abnormality based on 3D convolutional neural networks | |
CN109459077A (en) | A kind of power transmission and distribution capability of anti-wind assessment 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 |