CN208597123U - Pedestrian's identifying processing terminal based on raspberry pie - Google Patents
Pedestrian's identifying processing terminal based on raspberry pie Download PDFInfo
- Publication number
- CN208597123U CN208597123U CN201821438947.0U CN201821438947U CN208597123U CN 208597123 U CN208597123 U CN 208597123U CN 201821438947 U CN201821438947 U CN 201821438947U CN 208597123 U CN208597123 U CN 208597123U
- Authority
- CN
- China
- Prior art keywords
- button
- raspberry pie
- upload
- recognize
- pin
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
The utility model belongs to technical field of video monitoring, in particular a kind of pedestrian's identifying processing terminal based on raspberry pie, including raspberry pie plate, control button expansion board, camera, neural calculation rod, color LED lamp, 32G SD card and 5V/2A power supply, control button expansion board includes Recognize ON button, Recognize OFF button, Upload ON button, Upload OFF button, the periphery of the raspberry pie plate is equipped with GPIO mouthfuls, SD card mouth, Micro USB port, CAMERA mouthfuls and USB interface, and the color LED lamp is connected by GPIO mouthfuls with raspberry pie plate.The utility model is designed reasonably, it is easy to use, identification mission can be distributed to each camera, alleviated the pressure of server end, the deployment of simplified system.
Description
Technical field
The utility model relates to technical field of video monitoring more particularly to a kind of pedestrian's identifying processing based on raspberry pie are whole
End.
Background technique
At present in identification field, fingerprint recognition and recognition of face are highly developed, and large-scale application is also commonplace,
But both require the good cooperation of object, fingerprint recognition needs to compare with the finger print of the preparatory typing of user, and people
Face identification is more the need to ensure that camera can take the front photograph of user, and many identification scenes, which are difficult to make object, to be wanted
It asks, for example market monitoring is found and loses child, road monitoring identifies a suspect etc., these scenes are then needed using human bioequivalence
Means, but first problem be human bioequivalence than recognition of face difficulty because camera shooting moment may take
Multiple people, then will all detected all people, secondly the angle random of shooting is big, unlike recognition of face has to
Acquisition front is asked to shine, furthermore deep learning calculation method calculation amount used in human bioequivalence is bigger, general embedded device
It is difficult to complete calculating task, be also unable to complete identification at all only according to camera and uploads the task of data, more reliable solution
Scheme is by the data transmission of multiple cameras to a relatively large server process, but server operation pressure can be non-in this way
Chang great, and camera is more, and entire deployment can be very troublesome, for this purpose, proposing pedestrian's identifying processing terminal based on raspberry pie.
Utility model content
Purpose of the utility model is to solve disadvantages existing in the prior art, and the row based on raspberry pie proposed
People's identifying processing terminal.
To achieve the goals above, the utility model adopts the technical scheme that at pedestrian's identification based on raspberry pie
Manage terminal, including raspberry pie plate, control button expansion board, camera, neural calculation rod, color LED lamp, 32G SD card and 5V/
2A power supply, control button expansion board include Recognize ON button, Recognize OFF button, Upload ON button,
The periphery of Upload OFF button, the raspberry pie plate is equipped with GPIO mouthfuls, SD card mouth, Micro USB port, CAMERA mouthfuls and USB
Interface, the color LED lamp are connected by GPIO mouthfuls with raspberry pie plate, the Recognize ON button, Recognize
Grounding pin and digital signal output pin are equipped on OFF button, Upload ON button and Upload OFF button, it is described
Grounding pin on Recognize ON button, Recognize OFF button, Upload ON button and Upload OFF button
It is connected with the GND pin of raspberry pie plate, the Recognize ON button, Recognize OFF button, Upload ON
Digital signal output pin on button and Upload OFF button is connected by GPIO mouthfuls with raspberry pie plate, the camera shooting
Head is connected by CAMERA mouthfuls with raspberry pie plate, and the nerve calculation rod is connected by USB interface with raspberry pie plate, described
32G SD card is connected by SD card mouth with raspberry pie plate, and the 5V/2A power supply is connected by Micro USB port with raspberry pie plate
It connects.
Preferably, the color LED lamp is equipped with power input pin and three digital signal input pins, the colour
The power input pin of LED light is connected with 5V power supply, three digital signal input pins of the color LED lamp respectively with
GPIO mouthfuls of pin UART TXD, GPIO mouthfuls of pin UART RXD is connected with GPIO mouthfuls of pin PCM CLK.
Preferably, wireless network card, the model of wireless network card are as follows: MF832U, the type of camera are equipped in the raspberry pie plate
Number are as follows: WSC-580W.
Compared with prior art, the utility model has the beneficial effects that server is arranged by way of configuration file
IP, port numbers, WIFI and WIFI password can obtain video data by camera, can be pressed by Recognize ON
Button, Recognize OFF button control whether connection server, can pass through Upload ON button and Upload OFF button
It controls whether to handle original video data, real-time processing can be done to the video of shooting;
The utility model is designed reasonably, it is easy to use, identification mission can be distributed to each camera, alleviated
The pressure of server end, the deployment of simplified system.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the utility model;
Fig. 2 is the control button expansion board figure of the utility model;
Fig. 3 is GPIO mouthfuls of raspberry pie plate of the schematic diagram of the utility model;
In figure: 1, raspberry pie plate;2, control button expansion board;3, GPIO mouthfuls;4,32G SD card;5, SD card mouth;6,Micro
USB port;7,5V/2A power supply;8, CAMERA mouthfuls;9, camera;10, USB interface;11, neural calculation rod;12,Recognize
ON button;13, Recognize OFF button;14, Upload ON button;15, Upload OFF button;16, color LED lamp.
Specific embodiment
The following will be combined with the drawings in the embodiments of the present invention, carries out the technical scheme in the embodiment of the utility model
Clearly and completely describe, it is clear that the described embodiments are only a part of the embodiments of the utility model, rather than whole
Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are without making creative work
Every other embodiment obtained, fall within the protection scope of the utility model.
Fig. 1-3 is please referred to, the utility model provides a kind of technical solution: pedestrian's identifying processing terminal based on raspberry pie,
Including raspberry pie plate 1, control button expansion board 2, camera 9, neural calculation rod 11, color LED lamp 16,32G SD card 4 and 5V/
2A power supply 7, control button expansion board 2 are pressed including Recognize ON button 12, Recognize OFF button 13, Upload ON
The periphery of button 14, Upload OFF button 15, raspberry pie plate 1 is equipped with GPIO mouth 3, SD card mouth 5, Micro USB port 6, CAMERA
Mouth 8 and usb 10, color LED lamp 16 are connected by GPIO mouth 3 with raspberry pie plate 1, Recognize ON button 12,
Grounding pin and number letter are equipped on Recognize OFF button 13, Upload ON button 14 and Upload OFF button 15
Number output pin, Recognize ON button 12, Recognize OFF button 13, Upload ON button 14 and Upload OFF
Grounding pin on button 15 is connected with the GND pin of raspberry pie plate 1, Recognize ON button 12, Recognize
Digital signal output pin on OFF button 13, Upload ON button 14 and Upload OFF button 15 passes through GPIO mouth 3
It is connected with raspberry pie plate 1, camera 9 is connected by CAMERA mouth 8 with raspberry pie plate 1, and neural calculation rod 11 is connect by USB
Mouth 10 is connected with raspberry pie plate 1, and 32G SD card 4 is connected by SD card mouth 5 with raspberry pie plate 1, and 5V/2A power supply 7 passes through
Micro USB port 6 is connected with raspberry pie plate 1;
Color LED lamp 16 is equipped with power input pin and three digital signal input pins, the power supply of color LED lamp 16
Input pin is connected with 5V power supply 7, three digital signal input pins of color LED lamp 16 pin with GPIO mouth 3 respectively
The pin PCM CLK of pin UART RXD and the GPIO mouth 3 of UART TXD, GPIO mouth 3 is connected, and nothing is equipped in raspberry pie plate 1
Gauze card, the model of wireless network card are as follows: MF832U, the model of camera 9 are as follows: WSC-580W is set by way of configuration file
IP, port numbers, WIFI and the WIFI password of server are set, video data can be obtained by camera, button can be passed through
It controls whether connection server, can control whether to handle original video data by button, it can be to the view of shooting
Frequency does real-time processing, and the utility model is designed reasonably is easy to use, and identification mission can be distributed to each camera shooting
Head alleviates the pressure of server end, the deployment of simplified system.
Working principle: in use, raspberry pie plate 1 need to carry out network connection configuration, by WIFI connection network, and pass through net
Network connects remote server, and default raspberry pie plate can connect the WIFI network that entitled " recg " password is 12345678, by matching
The IP of server, port numbers, WIFI and WIFI password is arranged in the mode for setting file, and control button expansion board 2 is inserted into raspberry
It sends on the GPIO mouth 3 of plate 1,32G SD card 4 is inserted into SD card mouth 5, and the power supply 7 of 5V/2A is inserted into Micro USB port 6, and camera 9 is inserted
Enter CAMERA mouth 8, neural calculation rod 11 is inserted into usb 10, and what Recognize ON button 12 represented is to open pedestrian's identification
Function, what Recognize OFF button 13 represented is the function of closing pedestrian's identification, and what Upload ON button 14 represented is out
Video data upload is opened, what Upload OFF button 15 represented is to close video data to upload, and color LED lamp 16 is according to different
Color represents the different conditions of 1 work at present of raspberry pie plate, when control button expansion board 2 is inserted into the GPIO mouth 3 of raspberry pie plate 1
Afterwards, the digital signal output pin of Recognize ON button 12 and grounding pin should be made to connect pin 4 in GPIO mouth 3 respectively
With on pin GND1, the digital signal output pin of Recognize OFF button 13 and grounding pin connect respectively in GPIO mouth 3
On pin 17 and pin GND4, the digital signal output pin of Upload ON button 14 and grounding pin connect respectively in GPIO mouth 3
Pin 23 and pin GND2 on, the digital signal output pin and grounding pin of Upload OFF button 15 are connect respectively in GPIO
On the pin 24 and pin GND3 of mouth 3, color LED lamp 16 is RGB color LED, and three digital signals of color LED lamp 16 input
Pin is connect pin UART RXD and the GPIO mouth 3 in pin UART TXD, the GPIO mouth 3 of GPIO mouth 3 by the sequence of RGB respectively
On pin PCM CLK, program is by controlling the variation of 16 color of color LED lamp, GPIO to the different current strength of GPIO mouth 3
Mouthful 3 mouthfuls of settings are defaulted as high level, are low level from 3 mouthfuls of states got of GPIO mouth, to obtain when some button is pressed
The event that button is pressed is got, different operations is then carried out, being inserted into 5V/2A power supply 7 finally by Micro USB port 6 is
It can start to work, push button function is divided into 2 pieces, and wherein Recognize ON button 12 and Recognize OFF button 13 are controlled
Video data processed whether upload server, Upload ON button 14 and Upload OFF button 15 control whether to export video
It is uploaded again after processing, after Upload ON button 14 is pressed, 1 plug-in of raspberry pie plate starts to read in configuration file
Connection server is attempted in IP and port, determines whether server can be connected to here by TCP three-way handshake, when determination can be with
After connection, color LED lamp 16 is shown as yellow, is otherwise red, presses Recognize ON button 12, and color LED lamp 16 is
Green, raspberry pie plate 1 starts to obtain 9 video data of camera at this time, and handles each frame of video data, passes through mesh
Pedestrian in video is intercepted out by the preceding highest deep learning algorithm of discrimination, and with the pedestrian that has been downloaded in advance from server
Picture is compared, and comparison result is finally returned to server by network, there is no need to again to original graph for such server
Piece is analyzed, and the result information of directly available each camera 9 identification, is come at this time using the method for deep learning
Pedestrian's identification is carried out, the included CPU of light raspberry pie plate 1 can not accomplish real-time effect, so also needing using neural calculation rod
11 accelerate, and the principle of acceleration is to be transferred to this and accelerate to be calculated on stick, be similar to common deep learning matrix operation code
Accelerate operation using video card GPU above computer, the utility model is designed reasonably is easy to use, identification mission can be distributed to
Each camera 9, alleviates the pressure of server end, the deployment of simplified system.
The preferable specific embodiment of the above, only the utility model, but the protection scope of the utility model is not
It is confined to this, anyone skilled in the art is within the technical scope disclosed by the utility model, practical according to this
Novel technical solution and its utility model design are subject to equivalent substitution or change, should all cover the protection model in the utility model
Within enclosing.
Claims (3)
1. pedestrian's identifying processing terminal based on raspberry pie, including raspberry pie plate (1), control button expansion board (2), camera
(9), neural calculation rod (11), color LED lamp (16), 32G SD card (4) and 5V/2A power supply (7), it is characterised in that: control is pressed
Button expansion board (2) include Recognize ON button (12), Recognize OFF button (13), Upload ON button (14),
The periphery of Upload OFF button (15), the raspberry pie plate (1) is equipped with GPIO mouthfuls (3), SD card mouth (5), Micro USB port
(6), CAMERA mouthfuls (8) and USB interface (10), the color LED lamp (16) are connected by GPIO mouthfuls (3) with raspberry pie plate (1)
It connects, the Recognize ON button (12), Recognize OFF button (13), Upload ON button (14) and Upload
It is equipped with grounding pin and digital signal output pin on OFF button (15), the Recognize ON button (12),
Grounding pin on Recognize OFF button (13), Upload ON button (14) and Upload OFF button (15) with tree
The certain kind of berries sends the GND pin of plate (1) to be connected, the Recognize ON button (12), Recognize OFF button (13),
Digital signal output pin on Upload ON button (14) and Upload OFF button (15) passes through GPIO mouthfuls (3) and tree
The certain kind of berries sends plate (1) to be connected, and the camera (9) is connected by CAMERA mouthfuls (8) with raspberry pie plate (1), and the nerve calculates
Stick (11) is connected by USB interface (10) with raspberry pie plate (1), and the 32G SD card (4) passes through SD card mouth (5) and raspberry pie
Plate (1) is connected, and the 5V/2A power supply (7) is connected by Micro USB port (6) with raspberry pie plate (1).
2. pedestrian's identifying processing terminal according to claim 1 based on raspberry pie, it is characterised in that: the color LED
Lamp (16) is equipped with power input pin and three digital signal input pins, and the power input of the color LED lamp (16) is drawn
Foot is connected with 5V power supply (7), three digital signal input pins of the color LED lamp (16) respectively with GPIO mouthfuls (3)
Pin UART TXD, GPIO mouthfuls (3) of pin UART RXD is connected with GPIO mouthfuls (3) of pin PCM CLK.
3. pedestrian's identifying processing terminal according to claim 1 based on raspberry pie, it is characterised in that: the raspberry pie plate
(1) wireless network card, the model of wireless network card are as follows: MF832U, the model of camera (9) are as follows: WSC-580W are equipped in.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201821438947.0U CN208597123U (en) | 2018-09-04 | 2018-09-04 | Pedestrian's identifying processing terminal based on raspberry pie |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201821438947.0U CN208597123U (en) | 2018-09-04 | 2018-09-04 | Pedestrian's identifying processing terminal based on raspberry pie |
Publications (1)
Publication Number | Publication Date |
---|---|
CN208597123U true CN208597123U (en) | 2019-03-12 |
Family
ID=65605480
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201821438947.0U Expired - Fee Related CN208597123U (en) | 2018-09-04 | 2018-09-04 | Pedestrian's identifying processing terminal based on raspberry pie |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN208597123U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
CN111245103A (en) * | 2020-03-31 | 2020-06-05 | 贵州电网有限责任公司 | Display and storage system of power grid transformer nameplate based on neural computing rod |
CN113743242A (en) * | 2021-08-13 | 2021-12-03 | 成都理工大学 | Landslide mass detection and identification method based on raspberry pie |
-
2018
- 2018-09-04 CN CN201821438947.0U patent/CN208597123U/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
CN111245103A (en) * | 2020-03-31 | 2020-06-05 | 贵州电网有限责任公司 | Display and storage system of power grid transformer nameplate based on neural computing rod |
CN113743242A (en) * | 2021-08-13 | 2021-12-03 | 成都理工大学 | Landslide mass detection and identification method based on raspberry pie |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN208597123U (en) | Pedestrian's identifying processing terminal based on raspberry pie | |
CN205314704U (en) | Intelligence lock and system | |
CN104933344A (en) | Mobile terminal user identity authentication device and method based on multiple biological feature modals | |
CN204791017U (en) | Mobile terminal users authentication device based on many biological characteristics mode | |
CN107992794A (en) | A kind of biopsy method, device and storage medium | |
CN106445349B (en) | A kind of method, apparatus and electronic equipment adjusting mobile terminal system parameter | |
CN104361326A (en) | Method for distinguishing living human face | |
EP3610738B1 (en) | Method and system for unlocking electronic cigarette | |
CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
CN108415560A (en) | Electronic device, method of controlling operation thereof and Related product | |
CN207008639U (en) | A kind of safe bid system of authentication based on living things feature recognition | |
CN109427075A (en) | Biological information analytical equipment and its eye shadow analysis method | |
CN110347266A (en) | A kind of space gesture control device based on machine vision | |
CN109684993B (en) | Face recognition method, system and equipment based on nostril information | |
CN106887059A (en) | A kind of intelligent electronic lock system based on face recognition | |
CN102999164A (en) | E-book page turning control method and intelligent terminal | |
WO2021104128A1 (en) | Feature library update method and apparatus, inference server and storage medium | |
CN111967319A (en) | Infrared and visible light based in-vivo detection method, device, equipment and storage medium | |
CN107998670A (en) | Remote-control toy control system based on plane gesture identification | |
CN207037676U (en) | Human face image collecting device | |
CN110123289B (en) | Biological identification method based on pulse wave and related device | |
CN208689542U (en) | Gesture recognition control system towards Intelligent household scene | |
CN204102164U (en) | A kind of identity information acquisition and demo plant | |
CN202939680U (en) | Entrance guard system for iris recognition and wireless identity recognition based on DSP and CPLD | |
CN104680137B (en) | Embedded monocular iris identification device, system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190312 Termination date: 20190904 |
|
CF01 | Termination of patent right due to non-payment of annual fee |