WO2021035424A1 - Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation - Google Patents

Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation Download PDF

Info

Publication number
WO2021035424A1
WO2021035424A1 PCT/CN2019/102322 CN2019102322W WO2021035424A1 WO 2021035424 A1 WO2021035424 A1 WO 2021035424A1 CN 2019102322 W CN2019102322 W CN 2019102322W WO 2021035424 A1 WO2021035424 A1 WO 2021035424A1
Authority
WO
WIPO (PCT)
Prior art keywords
recognition
database
processor
social
central processing
Prior art date
Application number
PCT/CN2019/102322
Other languages
English (en)
Chinese (zh)
Inventor
刘浩源
郑云爽
靖建农
Original Assignee
唐山哈船科技有限公司
唐山圣因海洋科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 唐山哈船科技有限公司, 唐山圣因海洋科技有限公司 filed Critical 唐山哈船科技有限公司
Priority to PCT/CN2019/102322 priority Critical patent/WO2021035424A1/fr
Publication of WO2021035424A1 publication Critical patent/WO2021035424A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Definitions

  • the invention relates to the technical field of traffic management, and in particular to a device for identifying and detecting social idlers and a method of use thereof.
  • the present invention proposes a social idler identification and detection device and its use method, which solves the problem that the identification of idlers cannot be driven quickly when traffic is required.
  • a device for identifying and detecting social idlers includes a central processing device.
  • the central processing device is electrically connected with a back-end database and a display screen through a wire, and the central processing device is electrically connected with an input device through a wire.
  • the input device includes a protective box fixedly connected to the ground, a processor, a front-end database, and a router are fixedly connected to the protective box by bolts, and a support frame is fixedly connected to the upper side of the protective box by bolts, so The upper side of the support frame is fixedly connected with a speaker and a camera.
  • the processor adopts an AFPX0L14R model processor, and the front-end database, router, audio and camera are all electrically connected to the processor through wires.
  • the central processing device and the processor both include a recognition program.
  • the recognition program includes facial recognition and behavior recognition
  • the behavior recognition includes upper extremity motion recognition and lower extremity motion recognition.
  • the back-end database includes a public database and a record database
  • the public database is a personnel database in a public security system.
  • a method for identifying and detecting social idlers includes the following steps:
  • step S2 through the identification in step S1, there are three situations:
  • a After being identified by the recognition program in the processor, it is determined to be the person who is stored and filed in the front-end database, and then the person's information is directly sent to the back-end central processing device through the router and displayed on the display screen, while comparing the back-end In the public database in the database, inquire about the contact information or the contact information of relatives and friends, make telephone notifications, conduct dismissal, and can not receive the signal, refuse to listen to the dissuasion, or have no contact information in the public database, notify the nearby patrol, transfer, and take in;
  • the recognition program in the processor After the recognition program in the processor, the facial and behavior actions are suspected to be social idlers, but there is no data storage in the front-end data, it is processed by the processor, and then transmitted to the central processing device through the router, and passed
  • the identification program in the central processing device calls the data in the back-end database for comparison. If there are social idlers in the back-end database, the back-end staff will be notified, and the processing method in the situation will be processed. When the identification program fails again When it is confirmed, it will be transmitted to the back-end display screen for manual identification in the background. If the person is manually identified as a social idler, the central processing unit will ignore this information. If the person is manually identified as a social idler, the person will be identified The features are entered into the databases at all levels for storage, and at the same time, they are processed through the processing methods in the passing situation;
  • step S3 Perform multiple treatments through the idle persons who were taken into the house in step S3:
  • Figure 1 is a schematic diagram of the connection of the device of the present invention.
  • Figure 2 is a schematic flow diagram of the present invention.
  • 1 central processing unit 1 central processing unit, 2 display screens, 3 back-end databases, 4 cameras, 5 speakers, 6 support frames, 7 front-end databases, 8 protective boxes, 9 processors, 10 routers.
  • a device for identifying and detecting social idlers includes a central processing device 1.
  • the central processing device 1 is electrically connected with a back-end database 3 and a display screen 2 through a wire, and the central processing device 1 is electrically connected with an input device through a wire .
  • the input device includes a protective box 8 fixedly connected to the ground.
  • the protective box 8 is fixedly connected with a processor 9, a front-end database 7 and a router 10 through bolts.
  • the upper side of the protective box 8 is fixedly connected with a support frame 6 and a support frame 6 through bolts.
  • the upper side of the camera is fixedly connected with the audio 5 and the camera 4, and the camera 4 is installed on the top of the support column,
  • the processor 9 uses the AFPX0L14R model processor.
  • the front-end database 7, the router 10, the audio 5 and the camera 4 are all electrically connected to the processor 9 through wires. Through the connection of the processor 9, the various devices can be electrically connected to each other and pass through at the same time.
  • the processor 9 implements logic operations and controls various devices while completing required functions.
  • the central processing device 1 and the processor 9 both contain recognition programs.
  • the recognition programs include facial recognition and behavior recognition.
  • Behavior recognition includes upper extremity motion recognition and lower extremity motion recognition. Facial recognition technology can recognize the angle of the facial features and realize The logical operation is accurate, while the limb recognition uses the position of the limbs in a shorter period of time for comparison and recognition. After the logical operation, the trend and trajectory of the movement are initially understood.
  • the back-end database 3 includes a public database and a record database.
  • the public database adopts the personnel database in the public security system.
  • the front-end database 7 can perform preliminary real-time processing of location information, reducing the pressure of subsequent processing of huge data, and can be relatively large Discover and process the required information, carry out follow-up processing, and improve work efficiency.
  • a method for identifying and detecting social idlers includes the following steps:
  • the camera 4 collects the avatars and behaviors of people around the intersection.
  • the camera 4 converts optical signals into electrical signals, and then transmits the wires to the processor 9 in the first-level processing system of the intersection for data processing.
  • the processor 9 of the high-level processing system mainly performs data conversion and logical operations. At the same time, it performs face recognition and behavior recognition through a recognition program.
  • the processor 9 uses the data recognized in the recognition program to communicate with the front-end database 7 Compare and output the data stored in it;
  • step S2 through the identification in step S1, there are three situations:
  • a After being identified by the recognition program, it is determined to be the personnel stored in the front-end database 7 for the record, that is, the social idle personnel who often stream in the field or the region, and some personnel who have been registered.
  • the system determines that it is here
  • the person is the person in the time shooting and collection process
  • the person’s information is directly transmitted to the back-end staff through the transmission device, and at the same time, the personnel information in the public database in the back-end database is called, and at the same time, it is sent to the back-end staff for manual comparison and analysis.
  • the recognition program in the processor 9 After recognition by the recognition program in the processor 9, the facial and behavioral movements are suspected to be social idlers. After processing and calling by the processor 9, it is determined that there is no data storage in the front-end data 7, and then transmitted to the central processing device through the transmission device In 1, that is, in the back-end master control system, the identification program and the central processing device 1 are used to compare the data of the back-end database 3 after calling the data. If it is a social idle person in the back-end database 3, the information of the person The personnel information is transmitted to the staff through the transmission device, and the personnel information is sent to the back-end staff through the transmission device. At the same time, the personnel information in the public database is called, and at the same time, it is sent to the back-end personnel for manual comparison and analysis.
  • the data is transmitted to the back-end display screen 3 through the transmission device for manual final identification of the back-end.
  • the central processing device 1 Forcibly ignore this piece of information and proceed to the next collection and processing work. If manually identified as a social idler, then the characteristics of this person will be entered into the database at all levels for storage, which is convenient for subsequent automatic machine identification and reduces manual labor. Labor intensity, after being identified as a social idler, manually call the personnel information in the public database, and send it to the back-end personnel for manual comparative analysis.
  • step S3 Perform multiple treatments through the idle persons who were taken into the house in step S2:

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne un appareil de reconnaissance et de détection d'un vagabond et son procédé d'utilisation, qui se rapportent au domaine technique de la gestion du trafic. Selon l'invention, la solution suivante est proposée pour le problème existant selon lequel un vagabond sur une route à grande circulation n'est pas rapidement reconnu et chassé. L'appareil de reconnaissance et de détection comprend un appareil de traitement central (1). L'appareil de traitement central (1) est relié électriquement à une base de données principale (3) et à un écran d'affichage (2) au moyen d'un fil, et l'appareil de traitement central (1) est relié électriquement à un appareil d'enregistrement au moyen d'un fil. La solution décrite présente une structure simple et ele est facile à utiliser. Au moyen d'un traitement à différents niveaux, la pression d'utilisation dans l'arrière-plan est réduite de sorte que la vitesse de traitement augmente. La notification est réalisée de différentes manières, et les droits humains sont respectés tout en assurant l'efficacité du traitement. Le problème d'un embouteillage dû à un individu au niveau d'un carrefour est résolu à la racine, tandis qu'un risque de sécurité routière est réduit, ce qui permet de construire une meilleure ville.
PCT/CN2019/102322 2019-08-23 2019-08-23 Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation WO2021035424A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/102322 WO2021035424A1 (fr) 2019-08-23 2019-08-23 Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/102322 WO2021035424A1 (fr) 2019-08-23 2019-08-23 Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation

Publications (1)

Publication Number Publication Date
WO2021035424A1 true WO2021035424A1 (fr) 2021-03-04

Family

ID=74684812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/102322 WO2021035424A1 (fr) 2019-08-23 2019-08-23 Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation

Country Status (1)

Country Link
WO (1) WO2021035424A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103325251A (zh) * 2013-05-30 2013-09-25 安科智慧城市技术（中国）有限公司 一种基于行人闯红灯的图像快速识别方法及其系统
WO2017120714A1 (fr) * 2016-01-11 2017-07-20 汤美 Système anti-intrusion sur l'enceinte d'un campus
CN107169906A (zh) * 2017-04-16 2017-09-15 悠泊物联网科技(上海)有限公司 一种智能安防报警控制系统
CN107948597A (zh) * 2017-11-29 2018-04-20 合肥寰景信息技术有限公司 基于特定区域的行为分析及报警嵌入式设备
CN208924280U (zh) * 2018-09-17 2019-05-31 石家庄中政科技有限公司 一种社区监控管理系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103325251A (zh) * 2013-05-30 2013-09-25 安科智慧城市技术（中国）有限公司 一种基于行人闯红灯的图像快速识别方法及其系统
WO2017120714A1 (fr) * 2016-01-11 2017-07-20 汤美 Système anti-intrusion sur l'enceinte d'un campus
CN107169906A (zh) * 2017-04-16 2017-09-15 悠泊物联网科技(上海)有限公司 一种智能安防报警控制系统
CN107948597A (zh) * 2017-11-29 2018-04-20 合肥寰景信息技术有限公司 基于特定区域的行为分析及报警嵌入式设备
CN208924280U (zh) * 2018-09-17 2019-05-31 石家庄中政科技有限公司 一种社区监控管理系统

Similar Documents

Publication Publication Date Title
CN106781449A (zh) 路口行人过街综合管理控制系统
CN109571499A (zh) 一种智能导航引领机器人及其实现方法
CN209543514U (zh) 基于人脸识别的监控与报警系统
WO2020024552A1 (fr) Procédé et système de surveillance de sécurité routière, et support de stockage lisible par ordinateur
CN109741815A (zh) 一种医疗引导机器人及其实现方法
CN103268686A (zh) 基于人脸识别的防盗系统
CN112542027A (zh) 基于图像识别的施工现场人员安全告警系统
CN108416715A (zh) 一种基于智能摄像头的校园安全管理系统
WO2024124970A1 (fr) Appareil et procédé de surveillance destinés à réaliser une reconnaissance de comportement dans un environnement complexe
CN112784695A (zh) 一种基于图像及语音识别的司机异常状态检测方法
CN108776452B (zh) 一种特种设备现场维保监控方法及系统
CN109086732A (zh) 一种智能眼镜侦察终端系统及控制方法
CN116416281A (zh) 一种粮库ai视频监管分析方法及系统
WO2021035424A1 (fr) Appareil pour la reconnaissance et la détection de vagabond et son procédé d'utilisation
CN113256998A (zh) 一种特种车辆及其工作状态识别方法及设备
CN111723671A (zh) 一种智慧灯杆呼救系统及方法
CN210091231U (zh) 一种智慧园区管理系统
CN113052125A (zh) 一种施工现场违章图像识别告警方法
CN113327404A (zh) 空中交通管制员岗位疲劳状态监测告警系统
CN115331386B (zh) 一种基于计算机视觉的防垂钓检测告警系统
TWI691923B (zh) 金融交易詐騙偵測防範系統及其方法
CN115966023A (zh) 防护服规范化穿脱检测方法及相关系统
Diwan et al. Accident detection using mask R-CNN
WO2023158926A1 (fr) Systèmes et procédés de détection d'événements de sécurité dans un environnement
CN115471872A (zh) 散发广告的行为检测方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19942771

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19942771

Country of ref document: EP

Kind code of ref document: A1