WO2022231039A1 - Système de feu de signalisation intelligent mobile - Google Patents

Système de feu de signalisation intelligent mobile Download PDF

Info

Publication number
WO2022231039A1
WO2022231039A1 PCT/KR2021/005505 KR2021005505W WO2022231039A1 WO 2022231039 A1 WO2022231039 A1 WO 2022231039A1 KR 2021005505 W KR2021005505 W KR 2021005505W WO 2022231039 A1 WO2022231039 A1 WO 2022231039A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
traffic light
vehicle
smart
entry
Prior art date
Application number
PCT/KR2021/005505
Other languages
English (en)
Korean (ko)
Inventor
조재영
박아름
이성주
전정혁
김준수
임병석
Original Assignee
원광전력주식회사
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 원광전력주식회사 filed Critical 원광전력주식회사
Publication of WO2022231039A1 publication Critical patent/WO2022231039A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • G08G1/0955—Traffic lights transportable
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/075—Ramp control

Definitions

  • the present invention relates to a mobile smart traffic light system capable of active decision control of traffic signals.
  • a road less than 9m wide such as an alley in a residential area, a small road in a commercial district, or a cement road in a rural area, is called a back road.
  • Road Traffic Space According to 2015 statistical data, the majority of traffic accidents in Korea occur on the back road, and in the case of child pedestrian accidents, the ratio of accidents on the back road reaches 70.3%. In addition, as the number of back roads is also increasing due to the increase of automobiles and shoulder parking that increases every year, the importance of traffic safety on the back road is increasing day by day.
  • An object of the present invention is to provide a field-sensitive mobile smart traffic light system capable of unmanning the number of traffic signals in a situation where only a single lane is available, such as a back road traffic control situation.
  • the present invention is to provide a mobile smart traffic light system equipped with traffic signal active determination and control software that can actively respond to traffic conditions by determining the signal demand of traffic lights through Vision AI vehicle recognition and controlling the traffic lights.
  • a mobile smart traffic light system installed in a traffic control section, comprising at least a first smart traffic light device and a second smart traffic light device,
  • any one of the first smart traffic light device and the second smart traffic light device serves as a client of the mobile smart traffic light system by being equipped with a camera, a vision AI analysis unit, a socket client, and a traffic light,
  • the other of the first smart traffic light device and the second smart traffic light device is equipped with a camera, a vision AI analysis unit, a socket client, and a traffic light to serve as the client, and at the same time, a socket server and a smart decision system are mounted. It serves as a server of the mobile smart traffic light system,
  • the first smart traffic light device and the second smart traffic light device respectively, based on the image acquired through the camera, transmit the analysis data regarding the presence or absence of an ingress vehicle analyzed by the vision AI analysis unit through the socket client. transmit to the socket server using socket communication,
  • the smart decision system is a mobile smart traffic light system, characterized in that based on the analysis data regarding the presence or absence of an incoming vehicle received through the socket server, the demand determination of the traffic signal and the active determination and control of the traffic signal are performed. This is provided
  • the present invention on at least a reciprocating two-lane road including a first lane in a first vehicle traveling direction and a second lane in a second vehicle traveling direction opposite to the first vehicle traveling direction, the In the event of a road obstruction section in which lane use is not possible in either lane of the first lane or the second lane,
  • the first smart traffic light device is disposed at a predetermined position in front of the starting point of the road obstacle section of the one lane and detects a vehicle entering in the direction of the starting point of the road obstacle section according to the vehicle driving direction,
  • the second smart traffic light device is disposed at a predetermined position behind the lane point corresponding to the end point of the road obstacle section in the other lane and detects a vehicle entering the direction of the end point of the road obstacle section according to the vehicle driving direction.
  • a mobile smart traffic light system may be provided.
  • each of the vision AI analyzer may detect and track a two-dimensional area of a vehicle in the image acquired by the camera. If the harmonic average of the change amount ( ⁇ S), the approach speed (v), and the entry angle ( ⁇ ) is greater than or equal to the pre-designed threshold (c), the vehicle is approaching the location where the smart traffic light is installed.
  • a mobile smart traffic light system may be provided, characterized in that it is recognized as an entering vehicle.
  • the smart decision system In addition, according to an embodiment of the present invention, the smart decision system, and
  • a traffic signal command to turn on all red signals at each traffic light is issued through socket communication through the socket server.
  • the traffic light of the corresponding one lane is switched to a green signal, and the red signal is maintained on the traffic light of the other lane. transmits a traffic signal command to the first smart traffic light device and the second smart traffic light device through the socket communication,
  • one traffic light alternately according to a pre-designed interval until both vehicles enter into both lanes are completed. Transmits a traffic signal command for controlling traffic flow in such a way that the signal is switched to a green signal and the other traffic light is kept lit in the red signal to the first smart traffic light device and the second smart traffic light device through the socket communication alternately can
  • the mobile smart traffic light system it is possible to unmanned the number of traffic signals in a situation where only a single lane is available, such as a back road traffic control situation, and to determine the signal demand for a traffic light through Vision AI vehicle recognition, By controlling the traffic lights, it is possible to actively determine and control traffic signals that can actively respond to traffic conditions.
  • FIG. 1 is a block diagram for explaining the system structure of a mobile smart traffic light system according to an embodiment of the present invention.
  • Figure 2 is a diagram schematically showing a road situation of an embodiment to which a mobile smart traffic light system according to an embodiment of the present invention is applied.
  • FIG 3 is an example of a traffic signal control flow in a mobile smart traffic light system according to an embodiment of the present invention.
  • Figure 4 is a reference view for explaining a vehicle detection and tracking method through a vision AI (Vision artificial intelligence).
  • vision AI Vision artificial intelligence
  • FIG. 1 is a block diagram for explaining the system structure of a mobile smart traffic light system according to an embodiment of the present invention
  • FIG. 2 is a road situation of an embodiment to which a mobile smart traffic light system according to an embodiment of the present invention is applied.
  • 3 is an example of a traffic signal control flow in a mobile smart traffic light system according to an embodiment of the present invention
  • FIG. 4 is vehicle detection and tracking through vision artificial intelligence (AI) It is a reference drawing for explaining the method.
  • AI vision artificial intelligence
  • the smart traffic light device 1 10 constituting the two smart traffic light devices will be referred to as a first smart traffic light and the smart traffic light device 2 20 will be referred to as a second smart traffic light.
  • the first smart traffic light ie, the smart traffic light device 1 ( 10 ) of FIG. 1
  • the second smart traffic light that is, the smart traffic light device 2 (10) of FIG. 1
  • the second smart traffic light also has the same configuration as the laser scanner sensor 21, the camera 22, the vision AI analysis unit 23, the socket client ( 24), a traffic light 25 may be included.
  • all the devices ie, the first smart traffic light and the second smart traffic light
  • the cameras 12 and 22 and the laser scanner sensors 11 and 21 mounted on each device receives the analysis data analyzed by the AI analysis unit 13, 23 based on the data obtained from the , transmits it to the server through socket communication, and controls the traffic lights 15 and 25 according to the command received from the server.
  • any one of the first smart traffic light and the second smart traffic light requests and receives data acquired by the client, determines the traffic signal demand, and then performs the role of a server that determines the traffic signal will do
  • the first smart traffic light operates as a client and also serves as a kind of edge server (refer to reference numeral 30 in FIG. 1), thereby receiving data from each client through the socket server 34.
  • edge server reference numeral 30 in FIG. 1
  • the vision AI analyzers 13 and 23 mounted on each device can recognize an approaching vehicle through artificial intelligence-based image recognition (ie, target object classification according to object detection and tracking, see FIG. 4 ).
  • artificial intelligence-based image recognition ie, target object classification according to object detection and tracking, see FIG. 4 .
  • various commercial image recognition techniques may be applied to the recognition of an entering vehicle (ie, vehicle recognition and entry recognition), but according to an embodiment of the present invention, YOLOv4-based object detection and deep-sort-based A method of recognizing an approaching vehicle through object tracking may be applied.
  • the method of Equation 1 below may be applied to recognizing whether a vehicle enters.
  • the vehicle is a smart vehicle.
  • a method of recognizing that the vehicle is entering in a direction close to the location where the traffic light is installed may be applied.
  • the vehicle detection distance (related to the field of view (FoV) in FIG. 2) through the vision AI analyzer 13, 23 is 50M or more in front, and the vehicle detection and tracking speed is 10 FPS or more,
  • the response speed is preferably 500 ms or less.
  • the data analyzed through the vision AI analyzer 13 and 23 is transmitted to the socket server 34 through the socket clients 14 and 24, and the smart decision system 32 is based on the received data.
  • the demand judgment of traffic signals and the active determination and control of traffic signals are performed.
  • a traffic signal control flow according to an embodiment of the present invention will be described with reference to FIG. 2 with reference to the flowchart of FIG. 3 .
  • the analysis result through the vision AI analyzer 13 and 23 based on the images obtained from the cameras 12 and 22 is centered, but in a situation such as bad weather with thick fog, the laser scanner sensor Traffic signal control, which will be described later, can be performed by using the scan data obtained by (11, 21) together.
  • the traffic signal control flow chart of FIG. 3 to be described later is basically as shown in FIG. 2 , at least one lane (hereinafter referred to as 'first lane') constituting at least two round trip lanes.
  • a lane having a vehicle driving direction in the direction (B) In the other lane (hereinafter, referred to as a 'second lane', a lane having a vehicle driving direction in the direction (B), based on FIG.
  • lane referring to the first lane, which is a lane having a vehicle driving direction in the direction (A) when referenced in FIG. 2
  • FIG. 2 when a specific section of the first lane becomes a road obstacle section).
  • the mobile smart traffic light system when either lane of either side of the lane is placed in an unavailable situation due to the corresponding road obstacle section, as shown in FIG. 2, the corresponding road obstacle
  • Traffic signal control as shown in FIG. 3 is performed.
  • each client ie, the first smart traffic light and the second smart traffic light
  • a red signal may be turned on at each of the traffic lights 15 and 25 [S125].
  • step S120 if there is an entering vehicle as a result of the determination in step S120, and when it is determined that there is an entering vehicle in only one lane according to the determination result in step S130, the traffic light of the corresponding lane is switched to a green signal, The traffic lights on the other side of the road can keep the red signal on [S135]. At this time, when the entry of several vehicles into a single lane is detected, the green signal is maintained until the last vehicle is not detected, and then the red signal is switched.
  • step S140 when it is determined that there is an entering vehicle as a result of the determination in step S120, and it is determined that there is an entering vehicle in both lanes according to the determination result of step S130, until the vehicle entry into both lanes is completed [S140], it is possible to control the traffic flow in such a way that one side of the traffic light alternately switches to a green signal and the other side of the traffic light keeps the red signal lit according to the pre-designed interval [S145].
  • a predetermined interval criterion for example, the maximum number of vehicles that can pass at one time is determined based on the counted number of vehicles, or a time interval (ex. 2 minutes)
  • the traffic signal control can be alternately performed, and when both vehicles enter into both lanes, both traffic lights are switched back to red signals.
  • traffic safety can be further strengthened by adding the traffic signal control flow in the manner described below.
  • the smart decision system 32 provides an image analysis result of the vision AI analysis unit as a case in which an entering vehicle exists in any one of the first lane and the second lane. Accordingly, when the entry speed (v) of the vehicle entering for the first time in the direction of the road obstacle section exceeds the statutory driving speed of the corresponding lane, the red signal of the traffic light may be maintained until it comes within the statutory driving speed. have.
  • the separation distance between the road obstacle section and the entering vehicle is calculated based on the area change amount ( ⁇ S) of the first entering vehicle, and the separation distance and the entry speed (v) ), traffic signal command to keep the red light on until the safe driving distance calculated on the basis of when the separation distance falls to 1/2 or less of the legal driving speed can be secured can convey
  • the smart decision system 32 is configured to, when it is determined that an entering vehicle exists in both lanes of the first lane and the second lane, the vision AI According to the image analysis result of the analysis unit, the first separation distance between the road obstacle section and the corresponding entry vehicle is calculated based on the area change ⁇ S of the first lane vehicle entering the first lane from the first lane, and the second A second separation distance between the road obstacle section and the corresponding entry vehicle may be calculated based on the area change amount ⁇ S of the second lane vehicle first entering from the lane.
  • the one-way lane It is possible to make the traffic light of the traffic light turn on with a green signal, and the traffic light on the other side of the road can keep the red signal on.
  • the entry speed v of the first-entry vehicle having a smaller separation distance among the first separation distance and the second separation distance exceeds the legal operating speed, it is the first time in a different lane. If the entry speed v of the entering vehicle complies with the statutory driving speed, the traffic light of the other lane may be turned on with a green signal, and the traffic light of the one lane may be kept on with the red signal.
  • the entry speed v of each of the vehicle in the first lane and the vehicle in the second lane is When the statutory driving speed is exceeded, the red signal light of the traffic light on one side of the first lane and the second lane with the road obstruction zone is maintained, and the traffic light of the other lane is switched to yellow light. Afterwards, when the entry speed (v) of the vehicle entering the lane complies with the legal driving speed, a traffic signal command may be transmitted such that the corresponding traffic light is switched to a green light.

Landscapes

  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Operations Research (AREA)

Abstract

La présente invention concerne un système de feu de signalisation intelligent mobile sensible au champ pour une situation telle qu'une situation de contrôle de circulation de route de campagne dans laquelle seulement une voie unique est disponible. Selon un mode de réalisation de la présente invention, en fonction d'un système de feu de signalisation intelligent mobile, dans une situation telle qu'une situation de contrôle de circulation de route de campagne dans laquelle seulement une voie unique est disponible, la signalisation de circulation peut être effectuée sans personne, et, par l'intermédiaire d'une reconnaissance de véhicule par IA de vision, par la détermination d'une demande de signal pour le feu de signalisation et la commande du feu de signalisation, la détermination et la commande actives de signaux de signalisation pouvant réagir activement à la situation de circulation est possible.
PCT/KR2021/005505 2021-04-30 2021-04-30 Système de feu de signalisation intelligent mobile WO2022231039A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020210056300A KR102498035B1 (ko) 2021-04-30 2021-04-30 이동식 스마트 신호등 시스템
KR10-2021-0056300 2021-04-30

Publications (1)

Publication Number Publication Date
WO2022231039A1 true WO2022231039A1 (fr) 2022-11-03

Family

ID=83846893

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/005505 WO2022231039A1 (fr) 2021-04-30 2021-04-30 Système de feu de signalisation intelligent mobile

Country Status (2)

Country Link
KR (1) KR102498035B1 (fr)
WO (1) WO2022231039A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116311949A (zh) * 2023-05-17 2023-06-23 山东新众通信息科技有限公司 城市交通智能控制系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190013237A (ko) * 2017-08-01 2019-02-11 (주)유앤비테크 도로공사 현장의 안전관리정보제공장치 및 그 장치의 구동방법
KR102025098B1 (ko) * 2019-05-28 2019-09-26 주식회사 아이에스앤로드테크 도로 작업구간용 신호 알림 시스템
KR20200009559A (ko) * 2018-07-19 2020-01-30 한국건설기술연구원 도로 공사구간에 따른 대기행렬 및 지체시간 정보제공 시스템 및 그 방법
KR102082944B1 (ko) * 2019-09-02 2020-02-28 한국건설기술연구원 무선통신-기반 이동식 단일통행차선 교통신호 제어 시스템
KR102181855B1 (ko) * 2020-04-29 2020-11-23 주식회사 유닉테크노스 이동식 교행 신호기

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190013237A (ko) * 2017-08-01 2019-02-11 (주)유앤비테크 도로공사 현장의 안전관리정보제공장치 및 그 장치의 구동방법
KR20200009559A (ko) * 2018-07-19 2020-01-30 한국건설기술연구원 도로 공사구간에 따른 대기행렬 및 지체시간 정보제공 시스템 및 그 방법
KR102025098B1 (ko) * 2019-05-28 2019-09-26 주식회사 아이에스앤로드테크 도로 작업구간용 신호 알림 시스템
KR102082944B1 (ko) * 2019-09-02 2020-02-28 한국건설기술연구원 무선통신-기반 이동식 단일통행차선 교통신호 제어 시스템
KR102181855B1 (ko) * 2020-04-29 2020-11-23 주식회사 유닉테크노스 이동식 교행 신호기

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116311949A (zh) * 2023-05-17 2023-06-23 山东新众通信息科技有限公司 城市交通智能控制系统
CN116311949B (zh) * 2023-05-17 2023-08-01 山东新众通信息科技有限公司 城市交通智能控制系统

Also Published As

Publication number Publication date
KR102498035B1 (ko) 2023-02-08
KR20220149102A (ko) 2022-11-08

Similar Documents

Publication Publication Date Title
WO2019103197A1 (fr) Système pour prédire un accident de la circulation sur la base de l'intelligence artificielle et procédé associé
US20200082713A1 (en) Vehicular vision and alert system
EP1993279A2 (fr) Dispositif modulé à déclenchement par la lumière pour caméras de reconnaissance de plaque d'immatriculation
CN110024010B (zh) 用于探测位于停车场内的突起对象的方法和系统
WO2020101071A1 (fr) Système de surveillance de circulation utilisant un lidar capable de fournir une notification d'obstacle routier et véhicule suivi
KR20110128685A (ko) 주정차 단속 시스템 및 그 방법
CN110114807B (zh) 用于探测位于停车场内的突起对象的方法和系统
EP3451105A1 (fr) Système de commande de vitesse automatisé
WO2022231039A1 (fr) Système de feu de signalisation intelligent mobile
EP1291808A2 (fr) Appareil de reconnaissance des marquages d'arrêt pour des systèmes d'assistance à la conduite des véhicules
CN111785030A (zh) 交通监控终端和交通监控系统
WO2021112277A1 (fr) Système de gestion de la sécurité d'un piéton au niveau d'un passage pour piétons
WO2022196928A1 (fr) Système de gestion de commande de blocage et de prévention de ferme d'élevage basé sur une technologie d'analyse d'image par apprentissage profond
WO2014054879A1 (fr) Appareil de fourniture d'images de route incurvée
KR102456869B1 (ko) 스마트 교통관제 시스템
JPH1091899A (ja) 道路監視システム
WO2022146008A1 (fr) Procédé de sélection d'image d'accident au moyen d'une analyse de profil de vitesse
KR102310845B1 (ko) 인공지능 기반의 cctv 일체형 스마트 가로등
KR100469972B1 (ko) 이동식 수배차량 검거시스템
US11989796B2 (en) Parking seeker detection system and method for updating parking spot database using same
US11443519B2 (en) Method and system for determining the digital fingerprint of vehicles in transit
WO2020116767A1 (fr) Serveur de gestion de la circulation routière, et procédé et programme informatique destinés à la gestion de la circulation routière l'utilisant
KR20220128779A (ko) 스테레오 카메라 및 레이더를 이용한 차량 감지 시스템 및 차량 감지 방법
KR101242075B1 (ko) 전용차로 단속방법 및 장치
KR102017855B1 (ko) 자동차구동정보를 이용한 돌발상황 관제시스템

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: 21939422

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: 21939422

Country of ref document: EP

Kind code of ref document: A1