WO2020132990A1 - 一种识别交叉路口的方法和系统 - Google Patents

一种识别交叉路口的方法和系统 Download PDF

Info

Publication number
WO2020132990A1
WO2020132990A1 PCT/CN2018/124048 CN2018124048W WO2020132990A1 WO 2020132990 A1 WO2020132990 A1 WO 2020132990A1 CN 2018124048 W CN2018124048 W CN 2018124048W WO 2020132990 A1 WO2020132990 A1 WO 2020132990A1
Authority
WO
WIPO (PCT)
Prior art keywords
intersection
lane
traffic
turn
target
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.)
Ceased
Application number
PCT/CN2018/124048
Other languages
English (en)
French (fr)
Inventor
孙伟力
徐琪琪
赵越
伊峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
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 Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Publication of WO2020132990A1 publication Critical patent/WO2020132990A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Definitions

  • This application relates to the field of road traffic control, and in particular to a method and system for identifying intersections.
  • the method for identifying intersections may include sequentially identifying a first candidate intersection and a second candidate intersection, and marking both the first candidate intersection and the second candidate intersection as target intersections.
  • the method for identifying an intersection includes: obtaining the phase sequence of the traffic signal at the intersection. When the phase sequence of the traffic signal at the intersection is that the left-turn light precedes the straight-through light, the intersection is regarded as the first candidate intersection ; You can set a section of the opposite lane of the intersection to the left-turn lane, and calculate the left-turn radius of the left-turn lane. When the left-turn radius is greater than the first threshold, use the intersection as the first Two candidate intersections; the intersections that belong to both the first candidate intersection and the second candidate intersection can be marked as target intersections.
  • the method for identifying an intersection further includes: it can be determined whether the saturation of the left-turn lane of the intersection is greater than a second threshold; it can be determined when the saturation of the left-turn lane of the intersection is greater than a second threshold At this time, the intersection is marked as a target intersection.
  • the method for identifying an intersection further includes: obtaining traffic trajectory information of the intersection; based on the traffic trajectory information, determining the traffic volume of the left-turning lane of the intersection; According to the traffic flow, it is determined whether the saturation of the left-turn lane at the intersection is greater than the second threshold.
  • the method for identifying an intersection further includes: it can be determined whether the intersection is a cross intersection or a T-shaped intersection; when the intersection is a cross intersection or a T-shaped intersection, the The intersection is marked as the target intersection.
  • the method for identifying an intersection further includes: obtaining traffic trajectory information of the intersection; based on the traffic trajectory information, determining whether the intersection is a cross intersection or a T-junction.
  • the method for identifying an intersection further includes: it can be determined whether the traffic volume of the intersection is less than a third threshold; and when the traffic volume of the intersection is less than the third threshold, the intersection The intersection is marked as the target intersection.
  • the method for identifying an intersection further includes: obtaining traffic trajectory information of the intersection; based on the traffic trajectory information, determining the traffic volume of the intersection.
  • the method for identifying intersections further includes: obtaining traffic trajectory information of the intersections; determining geometric conditions of the intersections based on the traffic trajectory information; and based on the geometric conditions To calculate the left turning radius of the left turning lane.
  • intersection identification system includes: a first candidate intersection determination module, a second candidate intersection determination module, and a target intersection determination module.
  • the first candidate intersection determination module is used to obtain the phase sequence of the traffic signal lights at the intersection.
  • the intersection is used as the first A candidate intersection;
  • the second candidate intersection determination module is used to set a section of the oncoming traffic lane of the intersection as a left-turning lane, and calculate the left-turning radius of the left-turning lane, when the left-turning radius is greater than
  • the intersection is regarded as a second candidate intersection;
  • the target intersection determination module is used to mark an intersection that belongs to both the first candidate intersection and the second candidate intersection as a target intersection.
  • the intersection identification system further includes: it can be determined whether the saturation of the left-turn lane of the intersection is greater than a second threshold; when the saturation of the left-turn lane of the intersection is greater than a second threshold , Mark the intersection as the target intersection.
  • the intersection identification system further includes: the traffic trajectory information of the intersection can be obtained; the traffic flow of the left-turning lane of the intersection can be determined based on the traffic trajectory information; According to the traffic flow, it is determined whether the saturation of the left-turn lane at the intersection is greater than the second threshold.
  • the intersection identification system further includes: it can be determined whether the intersection is a cross intersection or a T-shaped intersection; when the intersection is a cross intersection or a T-shaped intersection, the The intersection is marked as the target intersection.
  • the intersection identification system further includes: obtaining traffic trajectory information of the intersection; based on the traffic trajectory information, it can be determined whether the intersection is a cross intersection or a T-junction.
  • the intersection identification system further includes: it is possible to determine whether the traffic volume at the intersection is less than a third threshold; and when the traffic volume at the intersection is less than the third threshold, the intersection Mark as the target intersection.
  • the intersection identification system further includes: the traffic trajectory information of the intersection can be obtained; the traffic volume of the intersection can be determined based on the traffic trajectory information.
  • the intersection identification system further includes: the traffic trajectory information of the intersection can be obtained; the geometric condition of the intersection can be determined based on the traffic trajectory information; the geometric condition can be based on the geometric condition, Calculate the left turn radius of the left turn lane.
  • the device for identifying intersections includes at least one processor and at least one memory, where the memory is used to store computer instructions; and the processor is used to execute the computer instructions to implement a method for identifying intersections.
  • One of the embodiments of the present application provides a computer-readable storage medium.
  • the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, a method of identifying intersections is implemented.
  • FIG. 1 is a schematic diagram of an application scenario of an intersection identification system according to some embodiments of the present application.
  • FIG. 2 is a block diagram of an intersection identification system according to some embodiments of the present application.
  • FIG. 3 is an exemplary flowchart of a method for identifying a target intersection according to some embodiments of the present application
  • FIG. 4 is a schematic diagram of a method for identifying a target intersection according to some embodiments of the present application.
  • FIG. 5 is a flowchart of a method for identifying a target intersection according to some embodiments of the present application.
  • FIG. 6 is a flowchart of a method for identifying a target intersection according to some embodiments of the present application.
  • FIG. 7 is a flowchart of calculating a left turning radius of a left turning lane according to some embodiments of the present application.
  • FIG. 8 is a schematic diagram of a target intersection provided with a variable left-turn lane according to some embodiments of the present application.
  • FIG. 9 is a schematic diagram of an intersection for determining a turning radius of a variable left-turning lane of an intersection according to some embodiments of the present application.
  • system is a method for distinguishing different components, elements, parts, parts or assemblies at different levels.
  • the words can be replaced by other expressions.
  • the embodiments of the present application can be applied to different transportation service systems, and different transportation systems include, but are not limited to, one or a combination of land, ocean, aviation, and aerospace.
  • transportation systems that need to identify intersections such as taxis, special cars, tailwinds, buses, drones, trains, trains, high-speed rails, driverless vehicles, and pick-up/delivery services.
  • the application scenarios of different embodiments of the present application include, but are not limited to, one or a combination of several types of web pages, browser plug-ins, clients, customized systems, enterprise internal analysis systems, artificial intelligence robots, and the like. It should be understood that the application scenarios of the system and method of the present application are only some examples or embodiments of the present application. For those of ordinary skill in the art, without paying any creative labor, they can also refer to these drawings Apply this application to other similar scenarios. For example, other similar systems that need to identify intersections.
  • FIG. 1 is a schematic diagram of an application scenario of an intersection identification system according to some embodiments of the present application.
  • the intersection identification system 100 can identify intersections, which is convenient for effectively controlling the passing capacity of the left-turn lane of the road.
  • the intersection identification system 100 may be an online service platform for Internet services.
  • the intersection identification system 100 can be used as an online transportation service platform for transportation services.
  • the intersection identification system 100 can be applied to online car-hailing services, such as taxi calls, express calls, private car calls, minibus calls, carpooling, bus services, driver hire, and pick-up services.
  • the intersection recognition system 100 may include a server 110, a network 120, a traffic signal device 130, a vehicle terminal 140, and a memory 150.
  • the server 110 may include a processing device 112.
  • the server 110 may be used to process information and/or data related to identifying intersections.
  • the server 110 may be an independent server or a server group.
  • the server group may be centralized or distributed (eg, the server 110 may be a distributed system).
  • the server 110 may be regional or remote.
  • the server 110 may access information and/or materials stored in the vehicle terminal 140 and the memory 150 through the network 120.
  • the server 110 may directly connect with the vehicle terminal 140 and the memory 150 to access the information and/or materials stored therein.
  • the server 110 may execute on a cloud platform.
  • the cloud platform may include one or any combination of private cloud, public cloud, hybrid cloud, community cloud, decentralized cloud, internal cloud, and the like.
  • the server 110 may include a processing device 112.
  • the processing device 112 may process data and/or information related to transportation to perform one or more functions described in this application. For example, the processing device 112 may identify the target intersection based on traffic-related data and/or information.
  • the processing device 112 may include one or more sub-processing devices (eg, single-core processing devices or multi-core multi-core processing devices).
  • the processing device 112 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processor (GPU), a physical processor (PPU), and a digital signal processor ( DSP), field programmable gate array (FPGA), editable logic circuit (PLD), controller, microcontroller unit, reduced instruction set computer (RISC), microprocessor, etc. or any combination of the above.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • ASIP application specific instruction processor
  • GPU graphics processor
  • PPU physical processor
  • DSP digital signal processor
  • FPGA field programmable gate array
  • PLD field programmable gate array
  • controller microcontroller unit
  • RISC reduced instruction set computer
  • the network 120 may facilitate the exchange of data and/or information.
  • one or more components in the intersection identification system 100 eg, the server 110, the traffic signal device 130, the vehicle terminal 140, the memory 150
  • the network 120 may be any type of wired or wireless network.
  • the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an internal network, an internet network, a regional network (LAN), a wide area network (WAN), a wireless regional network (WLAN), and a metropolitan area network (MAN) , Public switched telephone network (PSTN), Bluetooth network, ZigBee network, near field communication (NFC) network, etc. or any combination of the above.
  • the network 120 may include one or more network access points.
  • the network 120 may include wired or wireless network access points, such as base stations and/or Internet switching points 120-1, 120-2, ..., through which access points one or more components of the intersection identification system 100 may be connected Go to the network 120 to exchange data and/or information.
  • wired or wireless network access points such as base stations and/or Internet switching points 120-1, 120-2, ..., through which access points one or more components of the intersection identification system 100 may be connected Go to the network 120 to exchange data and/or information.
  • the vehicle terminal 140 may acquire transportation data and/or information.
  • the vehicle terminal 140 may include one or any combination of a taxi terminal 140-1, a private car terminal 140-2, a bus terminal 140-3, and the like.
  • the vehicle terminal 140 may be a terminal device independent of the vehicle such as a mobile device, a tablet computer, a notebook computer, or may be a built-in device of the vehicle.
  • the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, etc., or any combination thereof.
  • the smart furniture device may include a smart lighting device, a control device for smart appliances, a smart monitoring device, a smart TV, a smart camera, a walkie-talkie, etc., or any combination thereof.
  • the wearable device may include a smart bracelet, smart footwear, smart glasses, smart helmet, smart watch, smart clothing, smart backpack, smart accessories, etc., or any combination thereof.
  • the smart mobile device may include a smart phone, personal digital assistant (PDA), game device, navigation device, POS device, etc., or any combination thereof.
  • PDA personal digital assistant
  • the virtual reality device and/or augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality eye mask, augmented reality helmet, augmented reality glasses, augmented reality eye mask, etc. or Any combination of the above.
  • the vehicle terminal 140 may have a positioning function to determine the location of the user and/or the vehicle terminal 140.
  • the vehicle terminal 140 may have a sensor that can detect the driving state of the vehicle, including but not limited to driving direction, speed, acceleration, angular velocity, angular acceleration, and the like.
  • the memory 150 may store data and/or instructions. In some embodiments, the memory 150 may store materials acquired from the vehicle terminal 140. In some embodiments, the memory 150 may store information and/or instructions for execution or use by the server 110 to perform the exemplary methods described in this application. In some embodiments, the memory 150 may include mass storage, removable memory, volatile read-write memory (eg, random access memory RAM), read-only memory (ROM), etc., or any combination thereof. In some embodiments, the memory 150 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc., or any combination thereof.
  • the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc., or any combination thereof.
  • the memory 150 may be connected to the network 120 to communicate with one or more components of the intersection identification system 100 (eg, server 110, vehicle terminal 140, etc.). One or more components of the intersection identification system 100 can access data or instructions stored in the memory 150 through the network 120. In some embodiments, the memory 150 may directly connect or communicate with one or more components in the intersection identification system 100 (eg, the server 110, the vehicle terminal 140). In some embodiments, the storage 150 may be part of the server 110.
  • the information source 160 is a source that provides other information to the intersection identification system 100.
  • the information source 160 may be used to provide traffic trajectory data and traffic image data for the system.
  • the information source 160 may exist in the form of a single central server, or in the form of multiple servers connected through a network, or may exist in the form of a large number of personal devices.
  • these devices can use a user-generated content (user-generated contents) method, such as uploading text, voice, images, and video to the cloud server, so that the cloud server is connected to Many connected personal devices together constitute the information source 160.
  • FIG. 2 is an exemplary flowchart of a method for identifying a target intersection according to some embodiments of the present application. Specifically, the method 200 of identifying a target intersection may be performed by the server 110.
  • the same road is composed of different lanes and has two-way traffic capacity, which allows vehicles to travel in opposite directions.
  • a certain road that constitutes an intersection may have both a lane allowing vehicles to drive to the intersection and a lane allowing vehicles to leave the intersection.
  • the lane where the vehicle travels to the intersection and turns left at the intersection is called a fixed left-turn lane; the lane where the vehicle driving direction beside the fixed left turn lane is away from the intersection is called the opposite direction Car driveway.
  • the left-most lane L1 of the entrance 1 is a fixed left-turn lane
  • the three lanes L2, L3, and L4 on the exit 3 are opposite lanes.
  • a section of the oncoming vehicle lane can be set as a variable left-turn lane.
  • a section of at least one oncoming vehicle lane near the intersection can be set as a variable left-turn lane.
  • the section of the lane L2 on the exit lane 3 near the intersection can be set as a variable left turn lane, or the section of the middle lane L3 on the exit lane 3 near the intersection can also be set as a variable left turn Lane.
  • the length of the variable left-turn lane can be set manually or automatically by the server 110.
  • the length may be, for example, 200 meters, 150 meters, 100 meters, 80 meters, 50 meters, and so on.
  • the vehicle may enter the variable left-turn lane through a variable left-turn lane entrance (eg, 820 in FIG. 8).
  • a prompt device (such as a signage, etc.) may be provided at the entrance of the variable left-turn lane to prompt the driver to enter the variable left-turn lane to turn left.
  • the turning radius of the variable left-turning lane is smaller than the turning radius of the fixed left-turning lane. If the turning radius is too small, it is easy to cause discomfort and even traffic accidents in the vehicle. According to the relevant national road engineering design specifications, the turning radius must meet certain standards, so it is necessary to identify intersections where the left turning radius meets certain conditions.
  • the method 200 for identifying a target intersection may include:
  • Step 210 Obtain the phase sequence of the traffic signal lights at the intersection.
  • the phase sequence of the traffic signal lights at the intersection is that the left-turn light precedes the straight-going light, use the intersection as the first candidate intersection.
  • Intersections may include, but are not limited to, planar intersections, roundabout intersections, three-dimensional intersections, and the like.
  • a plane intersection may represent an intersection formed by intersecting on the same plane.
  • plane intersections may include intersections, T-shaped intersections, Y-shaped intersections, X-shaped intersections, Wucha intersections, Liucha intersections, and so on.
  • a roundabout can mean that a roundabout with a large area is set in the middle of the intersection, and vehicles travel around the island in one direction.
  • a three-way intersection may refer to a three-way intersection formed by not crossing on the same plane.
  • the three-dimensional intersection may be composed of overpasses, approach roads and ramps. Traffic lights can be composed of red, green, and yellow lights.
  • Traffic lights may include, but are not limited to, one or any combination of motor vehicle signal lights, non-motor vehicle signal lights, crosswalk signal lights, lane signal lights, direction indicator lights, road and railroad intersection signal lights, and the like.
  • the phase sequence of the traffic lights can indicate the order of the direction of the vehicles at the intersection within a signal period.
  • the phase sequence of traffic lights can be straight ahead and then left.
  • the phase sequence of the traffic lights may be left-turning and then straight-forwarding.
  • the phase sequence of the traffic signal lights may be synchronous straight and left.
  • the phase sequence of the traffic signal light is that the left-turning light precedes the straight-going light. It can be understood that when the traffic light is a direction-indicating light, the left-turning green light turns on earlier than the straight-going light within a signal period Green light on time.
  • the server 110 may obtain the phase sequence of the cross-road traffic signal from the traffic signal device 130. Specifically, the traffic signal device 130 sets the phase sequence of each signal light, and the server 110 can acquire the phase sequence setting information. In some embodiments, the server 110 may determine the phase sequence of the traffic lights based on the image data (eg, video) of the intersection. Specifically, the image data of the intersection can be obtained by an image acquisition device (for example, a camera), and the image data can reflect the actual traffic condition of the intersection, including the release order of each lane, and the server 110 can determine the phase of the signal lights according to the release order in the image sequence. In some embodiments, the server 110 may determine the phase sequence of the traffic lights at the intersection based on the trajectory of the vehicle.
  • the image data eg, video
  • the image data of the intersection can be obtained by an image acquisition device (for example, a camera), and the image data can reflect the actual traffic condition of the intersection, including the release order of each lane, and the server 110 can determine the phase of the signal lights according to
  • the running trajectory of the vehicle may be obtained by a positioning device, and the running trajectory of the vehicle at the intersection may include a left-turn traffic flow trajectory or a straight-travel traffic flow trajectory.
  • the server 110 may determine the phase sequence of the traffic lights at the intersection based on the left-turn traffic flow trajectory or the straight-through traffic flow trajectory of the intersection at a certain time (such as a signal cycle, 3 minutes, 10 minutes, 1 hour, etc.) , The phase sequence of the traffic lights at the intersection is selected as the intersection that turns left first and then goes straight.
  • the server 110 may determine an intersection where the phase sequence of the traffic signal is first to turn left and then go straight as the first candidate intersection.
  • the determined first candidate intersection information may be stored in the memory 150 through the network 120.
  • Step 220 Set a section of the opposite lane of the intersection to the left-turn lane, and calculate the left-turn radius of the left-turn lane. When the left-turn radius is greater than the first threshold, the intersection is regarded as the second candidate intersection.
  • the server 110 may calculate the left turn radius of the variable left turn lane based on the geometric conditions of the intersection.
  • the geometric conditions of the intersection include, but are not limited to, the width of the road, the shape and size of the arc, and so on.
  • the road width may include the width of the exit road and/or the width of the entrance road.
  • the road width may also include the width of each lane.
  • the arc refers to the arc part at the junction of the road and the intersection (as shown in Figure 9 ).
  • the geometric conditions of the intersection can be determined by manual measurement.
  • the server 110 may determine the geometric condition of the intersection based on the image data of the intersection.
  • the server 110 may determine the geometric conditions of the intersection based on the traffic trajectory information. For other descriptions of calculating the left-turning radius of the left-turning lane using the traffic trajectory information, refer to FIG. 7 and its description, and details are not described herein again.
  • the server 110 may compare the left turning radius of the variable left turning lane with the first threshold to determine whether the left turning radius of the variable left turning lane is greater than the first threshold.
  • the first threshold may be a preset first threshold, or may be a first threshold dynamically set according to actual needs. For example, the preset first threshold is 30m, and when the calculated left turning radius is 35m, the server 110 may determine that the left turning radius is greater than the first threshold.
  • the first threshold may be calculated according to relevant industry specifications or standards.
  • the minimum radius of the circular curve can be calculated as the first threshold.
  • the minimum radius of the circular curve is determined according to the conditions required for the vehicle to travel safely or smoothly in the curve part, that is, the lateral force such as the centrifugal force generated by the vehicle traveling in the curve part of the road does not exceed the allowable frictional resistance of the tire and the road surface limit.
  • the minimum radius of the circular curve can be calculated by equation (1):
  • R is the minimum radius of the circular curve
  • V is the design speed
  • ⁇ is the lateral force coefficient, taking the lateral friction coefficient between the tire and the road surface
  • i is the road surface slope or ultra-high transverse slope, expressed as a decimal, when the ultra-high Use negative values.
  • the radius of the circular curve may include a limit minimum radius, a general minimum radius, and/or a minimum radius without super height.
  • the minimum minimum radius refers to the minimum radius to ensure the safe driving of the vehicle.
  • the general minimum radius refers to the minimum radius to ensure the safe and comfortable driving of the vehicle at the designed speed.
  • it can be calculated by taking the comfortable values of the road surface slope or super high cross slope i and the lateral force coefficient ⁇ .
  • the minimum radius without ultra-high refers to the minimum radius to ensure the driving stability of the vehicle.
  • setting a section of the oncoming vehicle lane at the intersection as a variable left-turn lane described in step 220 is not to set a real variable left-turn lane at the intersection, but It is a simulation setting, for example, it can be simulated by a computer. Only after determining that the intersection is a target intersection suitable for setting a variable left-turn lane, then consider setting a real variable left-turn lane at the intersection.
  • Step 230 Mark the intersection that belongs to both the first candidate intersection and the second candidate intersection as the target intersection.
  • the target intersection refers to an intersection that satisfies the condition of setting a variable left-turn lane in the opposite lane.
  • the target intersection may be marked in various ways such as machine marking, manual marking, or a combination of machine marking and manual marking.
  • step 210 may follow step 220, or both steps may be performed simultaneously.
  • step 230 a step of setting a truly variable left-turn lane at the target intersection may be added.
  • FIG. 3 is a block diagram of an intersection identification system according to some embodiments of the present application.
  • the intersection identification system 300 may include a first candidate intersection determination module 310, a second candidate intersection determination module 320, and a target intersection determination module 330.
  • the first candidate intersection determination module 310 may be used to determine the first candidate intersection.
  • the first candidate intersection determination module 310 may obtain the phase sequence of the traffic signal at the intersection. When the phase sequence of the traffic signal at the intersection is that the left-turn light precedes the straight-through light, the intersection is determined as the first Candidate intersection.
  • the first candidate intersection For a detailed description of determining the first candidate intersection, refer to step 210 and its description shown in FIG. 3, and details are not described herein again.
  • the second candidate intersection determination module 320 may be used to determine a second candidate intersection.
  • the second candidate intersection determination module 320 may set a section of the oncoming lane of the intersection as a left-turn lane, and calculate the left-turn radius of the left-turn lane. When the left-turn radius is greater than the first threshold, the intersection The intersection serves as the second candidate intersection.
  • the second candidate intersection determination module 320 may calculate the left turn radius of the left turn lane based on the road width.
  • the second candidate intersection determination module 320 may determine the road width of the intersection based on the traffic trajectory information.
  • the second candidate intersection determination module 320 may obtain traffic trajectory information. For a detailed description of determining the second candidate intersection, reference may be made to step 220, which will not be repeated here.
  • the target intersection determination module 330 may be used to determine the target intersection. In some embodiments, the target intersection determination module 330 marks an intersection that belongs to both the first candidate intersection and the second candidate intersection as the target intersection. In some embodiments, the target intersection determination module 330 may mark an intersection that simultaneously belongs to the first candidate intersection, the second candidate intersection, and the left-turn lane whose saturation is greater than the second threshold as a target intersection. Lane saturation can be expressed as the ratio of the traffic volume of the lane to the capacity of the lane. For a detailed description of marking the intersection where the saturation of the left-turning lane of the intersection is greater than the second threshold as the target intersection, refer to FIG. 4 and its description, which will not be repeated here.
  • the target intersection determination module 330 may mark an intersection that simultaneously belongs to the first candidate intersection, the second candidate intersection, and the intersection or T-junction as the target intersection. For a detailed description of marking a crossroad intersection or a T-junction intersection as a target intersection, refer to FIG. 5 and its description, and no more details are provided here. In some embodiments, the target intersection determination module 330 may mark an intersection that simultaneously belongs to the first candidate intersection, the second candidate intersection, and the pedestrian flow volume is less than the third threshold as the target intersection. For a detailed description of marking an intersection with a flow of people less than the third threshold as a target intersection, refer to FIG. 6 and its description, which will not be repeated here.
  • the target intersection determination module 330 may mark an intersection that simultaneously belongs to a first candidate intersection, a second candidate intersection, a cross intersection or a T-junction intersection, and a left-turn lane whose saturation is greater than a second threshold Target intersection. In some embodiments, the target intersection determination module 330 may mark the intersections that belong to the first candidate intersection, the second candidate intersection, the cross intersection or the T-junction as well as the intersection with the pedestrian flow less than the third threshold as the target intersection intersection.
  • the target intersection determination module 330 may combine intersections that belong to a first candidate intersection, a second candidate intersection, a cross intersection, or a T-junction, a left-turn lane whose saturation is greater than a second threshold, and a person Intersections whose flow volume is less than the third threshold are marked as target intersections.
  • system and its modules shown in FIG. 3 can be implemented in various ways.
  • the system and its modules may be implemented by hardware, software, or a combination of software and hardware.
  • the hardware part can be implemented with dedicated logic;
  • the software part can be stored in the memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware.
  • an appropriate instruction execution system such as a microprocessor or dedicated design hardware.
  • the above methods and systems can be implemented using computer-executable instructions and/or included in the processor control code, for example, on a carrier medium such as a magnetic disk, CD or DVD-ROM, such as a read-only memory (firmware Such codes are provided on programmable memories or data carriers such as optical or electronic signal carriers.
  • the system and its modules of the present application can be implemented by not only hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. It can also be implemented by, for example, software executed by various types of processors, or by a combination of the above hardware circuits and software (for example, firmware).
  • intersection identification system and its modules is only for the convenience of description, and it cannot limit the application to the scope of the cited embodiments. It can be understood that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine various modules or form a subsystem to connect with other modules without departing from this principle.
  • the first candidate intersection determination module 310, the second candidate intersection determination module 320, and the target intersection determination module 330 disclosed in FIG. 3 may be different modules in a system, or may be one The module realizes the functions of the above two or more modules.
  • the first candidate intersection determination module 310 and the second candidate intersection determination module 320 may be two modules, or one module may have the function of determining the first candidate intersection and the second candidate intersection at the same time.
  • each module may share a storage module, or each module may have its own storage module. Such deformations are within the scope of protection of this application.
  • FIG. 4 is an exemplary flowchart of a method for identifying a target intersection according to some embodiments of the present application. As shown in FIG. 4, the method 400 for identifying a target intersection may include:
  • Step 410 Determine whether the saturation of the left-turn lane at the intersection is greater than the second threshold.
  • Lane saturation can be expressed as the ratio of the traffic volume of the lane to the capacity of the lane.
  • Lane capacity refers to the maximum number of vehicles that can pass through the lane per unit time
  • the traffic capacity of the lane may be calculated according to one or any combination of the width of the left-turn lane, the duration of the left-turn release, and the duration of the signal light cycle.
  • the saturation of the left-turn lane exceeds the second threshold, it indicates that the traffic volume on the left-turn lane is large, and there may be a backlog of congestion in the left-turn vehicle.
  • the second threshold may be a value preset by the server 110 or manually based on historical traffic data of the left-turn lane of the intersection.
  • the second threshold may be updated by the server 110 or manually based on the latest traffic data at intervals (e.g., one day, one month, two months, half a year).
  • the server 110 may acquire image data (eg, video) of the intersection, and determine the traffic volume of the left-turning lane of the intersection based on the image data.
  • the traffic volume data of the left-turn lane at the intersection can be obtained by manual statistical methods.
  • the traffic volume data of the left-turn lane at the intersection may be obtained by a sensor (eg, a coil detector) provided at the left-turn lane at the intersection.
  • the saturation of the left-turn lane may be determined according to the running trajectory of the vehicle. For example, the duration of a left-turning vehicle passing through an intersection can be determined according to the vehicle running trajectory. The longer the duration, the higher the saturation of the left-turning lane. In particular, if the time for a left-turning vehicle to cross an intersection exceeds the signal cycle duration (also known as the delay time), it means that the left-turning vehicle failed to pass the intersection within a signal cycle, so the longer the signal cycle period, the left The higher the lane saturation. Specifically, the average length of the left-turning vehicle passing through the intersection can be calculated.
  • the longer the average length, the higher the saturation of the left-turning lane; or, the average delay of the left-turning vehicle passing through the intersection over the signal period can be calculated.
  • the number of times that a left-turning vehicle stops at an intersection can be determined according to the running trajectory of the vehicle. If it is greater than one, it means that the vehicle failed to pass the intersection within a signal light cycle. Specifically, the average value of the number of times that the left-turn vehicle stops at the intersection can be calculated. The larger the value, the higher the left-turn lane saturation.
  • the server 110 may determine whether the saturation of the left-turn lane at the intersection is greater than the second threshold based on the lane saturation prediction model.
  • the input characteristics of the lane saturation prediction model may include one or any combination of the width of the left-turn lane, the period of the signal light, the length of the left-turn release, the traffic volume, and the trajectory of the vehicle.
  • the server 110 compares the left-turn lane of the intersection with the preset second threshold based on the saturation of the left-turn lane of the intersection to determine whether the saturation of the left-turn lane of the intersection is greater than the preset second threshold. For example, when the saturation of the left-turn lane at the intersection is 0.9 and the preset second threshold is set to 0.8, the server 110 may determine that the saturation of the left-turn lane at the intersection is greater than the preset second threshold. For another example, when the saturation of the left-turn lane at the intersection is 0.75 and the preset second threshold is set to 0.8, the server 110 may determine that the saturation of the left-turn lane at the intersection is less than the preset second threshold.
  • Step 420 when the saturation of the left-turn lane at the intersection is greater than the second threshold, the intersection is marked as the target intersection.
  • the server 110 may store the target intersection information in the memory 150 or send the target intersection information to the corresponding traffic signal device 130 of the target intersection. In some embodiments, the server 110 may update the target intersection information based on the updated saturation of the left-turn lane of the intersection or the updated second threshold value at intervals. For example, the server 110 may update the saturation of the left-turn lane at the intersection every signal period, and compare with the preset second threshold to dynamically update the target intersection.
  • the method for identifying target intersections shown in FIG. 4 is to further filter the target intersections identified by the method shown in FIG. 3, that is, the target intersections identified by the method shown in FIG.
  • the phase sequence of the signal lights is that the left-turn light is ahead of the straight-through light, and a section of the oncoming lane is the left-turn lane when the left-turn radius is greater than the first threshold, and satisfies that the saturation of the left-turn lane is greater than the second threshold.
  • the left-turning traffic pressure can be relieved by setting a section of the oncoming lane to the left-turning lane.
  • FIG. 5 is an exemplary flowchart of a method for identifying a target intersection according to some embodiments of the present application. As shown in FIG. 5, the method 500 for identifying a target intersection may include:
  • Step 510 Determine the type of intersection.
  • Types of intersections may include, but are not limited to, planar intersections, roundabout intersections, three-dimensional intersections, and so on.
  • the plane intersection may include one or any combination of intersections, T-shaped intersections, Y-shaped intersections, X-shaped intersections, Wucha intersections, Liucha intersections, or irregular-shaped intersections.
  • intersections such as intersections or T-junctions
  • the left-turn traffic can be effectively alleviated by setting a section of oncoming traffic lanes to the left; for some other types of intersections, some are not Including oncoming traffic lanes (such as roundabouts), some of which can not effectively relieve left-turning traffic pressure by setting a section of oncoming traffic lanes as left-turning lanes (such as complex intersections such as Wucha intersection and Liucha intersection),
  • the type of intersection may be determined based on the trajectory of the vehicle. For example, if the vehicle running trajectory shows that there are four cross-shaped roads with vehicles running on them, and these four roads form an intersection, the type of the intersection is a cross intersection. For another example, if the running trajectory of the vehicle is in the shape of a one-way ring, the intersection can be determined as a roundabout. For another example, if the vehicle running trajectory shows that the conflicting trajectory in the direction of the intersecting roads can pass through the intersection at the same time, and the average speed of the intersection is high, the intersection may be an intersection.
  • the intersection may be an intersection controlled by no signal lights.
  • the vehicle running trajectory can be obtained by the positioning device.
  • the processor 110 may obtain the vehicle running trajectory from the information source 160 through the network 120.
  • the information source 160 may be, for example, a third-party database such as a database of a traffic management department or a database of a map company.
  • map data (for example, from a third-party map company) may be obtained, and the map data contains information about the type of intersection, so the type of intersection may be directly determined based on the map data.
  • the type of intersection may also be determined by image data (eg, video) of the intersection.
  • the image data of the intersection may include a traffic sign image, and there may be a traffic sign indicating the type of the intersection.
  • the server 110 may determine the type of the intersection through image recognition technology.
  • the image data at the intersection reflects the traveling direction of the vehicle, and can be used to determine the type of intersection.
  • the server 110 may recognize the traffic sign about the intersection in the image data through image recognition technology, determine its meaning, and thus determine the type of the intersection.
  • the type of intersection may be determined manually or automatically by the server 110.
  • the server 110 may employ a machine learning model to determine the type of intersection.
  • the input of the machine learning model may include the vehicle running trajectory, the image data of the intersection, etc., and the output is the type of the intersection.
  • Step 520 When the intersection is a cross intersection or a T-shaped intersection, mark the intersection as a target intersection.
  • the server 110 may store the target intersection information in the memory 150 or send the target intersection information to the corresponding traffic signal device 130 of the target intersection. In some embodiments, the server 110 may periodically or irregularly update the target intersection information.
  • the method for identifying target intersections shown in FIG. 5 is to further filter the target intersections identified by the method shown in FIG. 3, that is, the target intersections identified by the method shown in FIG.
  • the phase sequence of the signal lights is that the left-turn light is ahead of the straight-going light, and the section of the oncoming vehicle lane is the left-turn radius when the left-turn radius is greater than the first threshold, and also satisfies the type of intersection as a crossroad or a T-junction.
  • the left-turning traffic pressure can be relieved by setting a section of the oncoming lane to the left-turning lane.
  • FIG. 6 is an exemplary flowchart of a method for identifying a target intersection according to some embodiments of the present application. As shown in FIG. 6, the method 600 for identifying a target intersection may include:
  • Step 610 Determine whether the traffic volume at the intersection is less than the third threshold.
  • the flow of people may be the number of people passing through the intersection per unit time.
  • the server 110 may determine the flow of people at the intersection based on the traffic trajectory information.
  • the server 110 may determine the flow of people based on the image data (eg, video) of the intersection.
  • sensors may be provided at intersections, such as infrared sensors, cameras, radars, lidars, etc., to obtain pedestrian flow data at intersections.
  • human traffic data at intersections can be obtained through manual statistical methods.
  • the server 110 may compare the determined traffic volume of the intersection with the third threshold to determine whether the traffic volume is less than the third threshold.
  • the third threshold may be a preset fixed value, or may be updated at intervals according to actual needs (peak morning period, off-peak period, etc.).
  • Step 620 when the traffic volume of the intersection is less than the third threshold, mark the intersection as the target intersection.
  • the server 110 may store the target intersection information in the memory 150 or send the target intersection information to the corresponding traffic signal device 130 of the target intersection. In some embodiments, the server 110 may periodically or irregularly update the target intersection information.
  • the target intersection may be determined based on historical car orders. For example, you can analyze the pick-up location and/or next location of the historical car order. If the intersection and surrounding areas are frequently used as the pick-up location and/or next location (if the number of times exceeds the set number of times threshold), then determine the intersection The intersection has a large flow of people and is not suitable as a target intersection.
  • the target intersection may also be determined according to the location information around the intersection. For example, if there are hospitals, schools, large shopping malls and other places near the intersection, it is not suitable as a target intersection.
  • the server 110 may obtain the location information around the intersection from the information source 160.
  • the information source 160 may be a third-party database such as a database of a traffic management department or a database of a map company.
  • the method for identifying target intersections shown in FIG. 6 is to further filter the target intersections identified by the method shown in FIG. 3, that is, the target intersections identified by the method shown in FIG.
  • the phase sequence of the signal lights is that when the left-turning light is ahead of the straight-going light and the section of the oncoming vehicle lane is the left-turning lane, the left-turning radius is greater than the first threshold, and the pedestrian flow is less than the third threshold.
  • the left-turning traffic pressure can be relieved by setting a section of the oncoming lane to the left-turning lane.
  • FIG. 7 is a flowchart of calculating a left turning radius of a left-turn lane according to some embodiments of the present application. As shown in FIG. 7, the method 700 for calculating the left turning radius of the left turning lane may include:
  • Step 710 Obtain traffic trajectory information at the intersection.
  • the traffic trajectory information may be obtained by the positioning device using positioning technology.
  • Positioning technologies include but are not limited to GPS satellite positioning, Bluetooth positioning, WIFI network positioning, Beidou positioning, mobile communication technology positioning, etc.
  • the traffic trajectory may be composed of the trajectories of multiple vehicles. Each vehicle's driving trajectory is composed of a large number of trajectory points. Each track point data includes information such as the position (e.g. latitude and longitude) and time of the track point.
  • the position of the vehicle may be acquired once every period (eg, 10 seconds, 5 seconds, 2 seconds, etc.), and the acquired time and position information form a trajectory point.
  • Step 720 based on the traffic trajectory information, determine the geometric conditions of the intersection.
  • the geometric conditions of the intersection include, but are not limited to, the width of the road, the shape and size of the arc, and so on.
  • the road width may include the width of the exit road and/or the width of the entrance road.
  • the road width may also include the width of each lane.
  • the arc refers to the arc part at the junction of the road and the intersection (as shown in Figure 9 ).
  • the traffic trajectory composed of multiple vehicle trajectories may depict the shape or contour of the road, and the geometric condition of the intersection may be determined according to the shape or contour.
  • Step 730 based on the geometric conditions of the intersection, calculate the left turn radius of the variable left turn lane.
  • the theoretical turning path of the variable left-turning lane may be determined according to the geometric conditions of the intersection, the theoretical turning radius is a circular arc, and the radius of the arc-like theoretical turning path is determined as the variable left-turning The left turn radius of the lane.
  • intersection boundary lines 930 and 940 The intersection boundary line can be determined according to the end position of the arc. For example, arc The end position at exit 3 is point C, and the end position at entrance 4 is point D. It is determined that the straight line passing point C perpendicular to exit 3 (or entrance 1) is the intersection boundary line 930, passing D The straight line whose point is perpendicular to the entrance 4 (or exit 2) is the intersection boundary 940.
  • the center line 910, 920 and the intersection boundary line 930, 940 form a rectangle, and determine the largest inscribed circle O within the rectangle, the center of the inscribed circle is O point, and the radius is r.
  • FIG. 8 is a schematic diagram of a target intersection provided with a variable left-turn lane according to some embodiments of the present application.
  • FIG. 8 shows a target intersection, which is composed of lanes that are perpendicular to each other.
  • the leftmost lane L1 of the entrance lane 1 is a fixed left-turn lane.
  • the section of the lane L2 closest to the entrance 1 of the exit 3 near the intersection can be set as a variable left turn lane L6, and at the same time the separation zone between the entrance 1 and the exit 3
  • An entrance 820 is opened for the vehicle to enter the variable left turn lane L6.
  • the left-turn signal turns green and the left-turn vehicle is released, the left-turn vehicle can not only turn left through the fixed left-turn lane L1, but also enter the variable left-turn lane L6 through the entrance 820 to turn left.
  • the turn radius of the left turn path 830 of the fixed left turn lane is greater than the first threshold.
  • the turning radius of the left turning path 840 of the variable left turning lane L6 is also greater than the first threshold.
  • FIG. 9 is a schematic diagram of an intersection for determining a turning radius of a variable left-turning lane of an intersection according to some embodiments of the present application. For specific determination steps, refer to FIG. 7 and its description, and details are not described here.
  • the possible beneficial effects brought by the embodiments of the present application include, but are not limited to: (1) Use traffic trajectory data and other methods to identify intersections suitable for reverse variable left-turn lanes, reducing the workload of manually selecting and selecting intersections; ( 2) A reverse variable left-turn lane can be set at the identified intersection to improve the traffic efficiency of left-turn vehicles and ease the traffic pressure at the intersection. It should be noted that different embodiments may have different beneficial effects. In different embodiments, the possible beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.
  • the present application uses specific words to describe the embodiments of the present application.
  • “one embodiment”, “one embodiment”, and/or “some embodiments” mean a certain feature, structure, or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that the reference to “one embodiment” or “one embodiment” or “an alternative embodiment” at two or more different places in this specification does not necessarily refer to the same embodiment .
  • certain features, structures, or characteristics in one or more embodiments of the present application may be combined as appropriate.
  • the computer storage medium may contain a propagated data signal containing a computer program code, for example, on baseband or as part of a carrier wave.
  • the propagated signal may have multiple manifestations, including electromagnetic, optical, etc., or a suitable combination.
  • the computer storage medium may be any computer-readable medium other than the computer-readable storage medium, and the medium may be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transmit a program for use.
  • Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the foregoing.
  • the computer program codes required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python Etc., conventional programming languages such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages.
  • the program code may run entirely on the user's computer, or as an independent software package on the user's computer, or partly on the user's computer, partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any form of network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (eg, via the Internet), or in a cloud computing environment, or as a service Use as software as a service (SaaS).
  • LAN local area network
  • WAN wide area network
  • SaaS software as a service
  • Some embodiments use numbers describing the number of components and attributes. It should be understood that such numbers used in embodiment descriptions use the modifiers "about”, “approximately”, or “generally” in some examples. Grooming. Unless otherwise stated, “approximately”, “approximately” or “substantially” indicates that the figures allow a variation of ⁇ 20%.
  • the numerical parameters used in the specification and claims are all approximate values, and the approximate values may be changed according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of general digit retention. Although the numerical fields and parameters used to confirm the breadth of their ranges in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种识别交叉路口的方法和系统，该识别交叉路口方法包括：获取交叉路口的交通信号灯的相序，当该交叉路口的交通信号灯的相序为左转灯先于直行灯时，将该交叉路口作为第一候选路口(210)；将该交叉路口的一段对向来车车道设置为左转弯车道，并计算该左转弯车道的左转弯半径，当该左转弯半径大于第一阈值时，将该交叉路口作为第二候选路口(220)；将同时属于该第一候选路口和该第二候选路口的交叉路口标记为目标交叉路口(230)。通过交通轨迹数据识别适合采用逆向可变左转车道的交叉路口，可以提高左转车辆的通行效率，缓解交叉口的交通压力。

Description

一种识别交叉路口的方法和系统
本申请要求2018年12月25日提交的中国专利申请201811591024.3的优先权，所述申请以全文引用的方式并入本文中。
技术领域
本申请涉及道路交通控制领域，特别涉及一种识别交叉路口的方法和系统。
背景技术
随着私家车等交通工具日益增多，道路拥堵问题日益严重，一些交叉路口，更是拥堵频发。例如，在早晚高峰期间，道路交叉口的左转车流量较大，而左转车道通行能有有限，导致左转车辆排队积压，容易造成交通拥堵现象。为了缓解这种现象，有必要提升道路交叉口的通行能力，特别是提升高峰期左转车道的通行能力。
发明内容
本申请实施例之一提供一种识别交叉路口的方法。所述识别交叉路口方法包括可以依次识别第一候选路口和第二候选路口，并将同时属于第一候选路口和第二候选路口标记为目标交叉路口。所述识别交叉路口方法包括：可以获取交叉路口的交通信号灯的相序，当所述交叉路口的交通信号灯的相序为左转灯先于直行灯时，将所述交叉路口作为第一候选路口；可以将所述交叉路口的一段对向来车车道设置为左转弯车道，并计算所述左转弯车道的左转弯半径，当所述左转弯半径大于第一阈值时，将所述交叉路口作为第二候选路口；可以将同时属于所述第一候选路口和所述第二候选路口的交叉路口标记为目标交叉路口。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以判断所述交叉路口左转车道的饱和度是否大于第二阈值；可以当所述交叉路口左转车道的饱和度大于第二阈值时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口左转车道的车流量；可以基于所述车流量，判断所述交叉路口左转车道的饱和度是否大于所述第二阈值。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以判断所述交叉路口是否为十字交叉路口或丁字交叉路口；可以当所述交叉路口为十字交叉路口或丁字交 叉路口时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，判断所述交叉路口是否为十字交叉路口或丁字交叉路口。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以判断所述交叉路口的人流量是否小于第三阈值；可以当所述交叉路口的人流量小于第三阈值时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口的人流量。
在一些实施例中，所述识别交叉路口的方法进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口的几何条件；可以基于所述几何条件，计算所述左转弯车道的左转弯半径。
本申请实施例之一提供一种交叉路口识别系统。所述交叉路口识别系统包括：第一候选路口确定模块、第二候选路口确定模块、目标交叉路口确定模块。其中，所述第一候选路口确定模块用于获取交叉路口的交通信号灯的相序，当所述交叉路口的交通信号灯的相序为左转灯先于直行灯时，将所述交叉路口作为第一候选路口；所述第二候选路口确定模块用于将所述交叉路口的一段对向来车车道设置为左转弯车道，并计算所述左转弯车道的左转弯半径，当所述左转弯半径大于第一阈值时，将所述交叉路口作为第二候选路口；所述目标交叉路口确定模块用于将同时属于所述第一候选路口和所述第二候选路口的交叉路口标记为目标交叉路口。
在一些实施例中，所述交叉路口识别系统进一步包括：可以判断所述交叉路口左转车道的饱和度是否大于第二阈值；可以当所述交叉路口左转车道的饱和度大于第二阈值时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述交叉路口识别系统进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口左转车道的车流量流量；可以基于所述车流量，判断所述交叉路口左转车道的饱和度是否大于所述第二阈值。
在一些实施例中，所述交叉路口识别系统进一步包括：可以判断所述交叉路口是否为十字交叉路口或丁字交叉路口；可以当所述交叉路口为十字交叉路口或丁字交叉路口时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述交叉路口识别系统进一步包括：可以获取所述交叉路口 的交通轨迹信息；可以基于所述交通轨迹信息，判断所述交叉路口是否为十字交叉路口或丁字交叉路口。
在一些实施例中，所述交叉路口识别系统进一步包括：可以判断所述交叉路口的人流量是否小于第三阈值；可以当所述交叉路口的人流量小于第三阈值时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，所述交叉路口识别系统进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口的人流量。
在一些实施例中，所述交叉路口识别系统进一步包括：可以获取所述交叉路口的交通轨迹信息；可以基于所述交通轨迹信息，确定所述交叉路口的几何条件；可以基于所述几何条件，计算所述左转弯车道的左转弯半径。
本申请实施例之一提供一种识别交叉路口装置。所述识别交叉路口装置包括至少一个处理器以及至少一个存储器，所述存储器用于存储计算机指令；所述处理器用于执行所述计算机指令以实现识别交叉路口方法。
本申请实施例之一提供一种计算机可读存储介质。所述计算机可读存储介质存储计算机指令，当所述计算机指令被处理器执行时实现识别交叉路口方法。
附图说明
本申请将以示例性实施例的方式进一步说明，这些示例性实施例将通过附图进行详细描述。这些实施例并非限制性的，在这些实施例中，相同的编号表示相同的结构，其中：
图1是根据本申请一些实施例所示的交叉路口识别系统的应用场景示意图；
图2是根据本申请一些实施例所示的交叉路口识别系统的模块图；
图3是根据本申请一些实施例所示的识别目标交叉路口方法的示例性流程图；
图4是根据本申请一些实施例所示的识别目标交叉路口方法的示意图；
图5是根据本申请一些实施例所示的识别目标交叉路口方法的流程图；
图6是根据本申请一些实施例所示的识别目标交叉路口方法的流程图；
图7是根据本申请一些实施例所示的计算左转弯车道的左转弯半径的流程图；
图8是根据本申请一些实施例所示的设置有可变左转弯车道的目标交叉路口的示意图；以及
图9为根据本申请一些实施例所示的用于确定交叉路口可变左转弯车道的转弯 半径的交叉路口示意图。
具体实施方式
为了更清楚地说明本申请实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其它类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。
应当理解，本文使用的“系统”、“装置”、“单元”和/或“模组”是用于区分不同级别的不同组件、元件、部件、部分或装配的一种方法。然而，如果其他词语可实现相同的目的，则可通过其他表达来替换所述词语。
如本申请和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其它的步骤或元素。
本申请中使用了流程图用来说明根据本申请的实施例的系统所执行的操作。应当理解的是，前面或后面操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各个步骤。同时，也可以将其他操作添加到这些过程中，或从这些过程移除某一步或数步操作。
本申请的实施例可以应用于不同的交通服务系统，不同的交通系统包括但不限于陆地、海洋、航空、航天等中的一种或几种的组合。例如，出租车、专车、顺风车、巴士、代驾、火车、动车、高铁、无人驾驶的交通工具、收/送快递等需要识别交叉路口的运输系统。本申请的不同实施例应用场景包括但不限于网页、浏览器插件、客户端、定制系统、企业内部分析系统、人工智能机器人等中的一种或几种的组合。应当理解的是，本申请的系统及方法的应用场景仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其它类似情景。例如，其他类似的需要识别交叉路口的系统。
图1所示为根据本申请一些实施例所示的交叉路口识别系统的应用场景示意图。交叉路口识别系统100可以识别交叉路口，便于有效控制道路左转车道的通行能力。交叉路口识别系统100可以是用于互联网服务的线上服务平台。例如，交叉路口识别系统 100可以用于运输服务的线上运输服务平台。在一些实施例中，交叉路口识别系统100可以应用于网约车服务，例如出租车呼叫、快车呼叫、专车呼叫、小巴呼叫、拼车、公交服务、司机雇佣和接送服务等。交叉路口识别系统100可以包含服务器110、网络120、交通信号装置130、车辆终端140、以及存储器150。服务器110可包含处理设备112。
在一些实施例中，服务器110可以用于处理与识别交叉路口相关的信息和/或数据。服务器110可以是独立的服务器或者服务器组。该服务器组可以是集中式的或者分布式的(如：服务器110可以是分布系统)。在一些实施例中该服务器110可以是区域的或者远程的。例如，服务器110可通过网络120访问存储于车辆终端140、存储器150中的信息和/或资料。在一些实施例中，服务器110可直接与车辆终端140、存储器150连接以访问存储于其中的信息和/或资料。在一些实施例中，服务器110可在云平台上执行。例如，该云平台可包括私有云、公共云、混合云、社区云、分散式云、内部云等中的一种或其任意组合。
在一些实施例中，服务器110可包含处理设备112。该处理设备112可处理与交通运输有关的数据和/或信息以执行一个或多个本申请中描述的功能。例如，处理设备112可以根据交通运输有关的数据和/或信息识别出目标交叉路口。在一些实施例中，处理设备112可包含一个或多个子处理设备(例如，单芯处理设备或多核多芯处理设备)。仅仅作为范例，处理设备112可包含中央处理器(CPU)、专用集成电路(ASIC)、专用指令处理器(ASIP)、图形处理器(GPU)、物理处理器(PPU)、数字信号处理器(DSP)、现场可编程门阵列(FPGA)、可编辑逻辑电路(PLD)、控制器、微控制器单元、精简指令集电脑(RISC)、微处理器等或以上任意组合。
网络120可促进数据和/或信息的交换。在一些实施例中，交叉路口识别系统100中的一个或多个组件(例如，服务器110、交通信号装置130、车辆终端140、存储器150)可通过网络120发送数据和/或信息给交叉路口识别系统100中的其他组件。在一些实施例中，网络120可以是任意类型的有线或无线网络。例如，网络120可包括缆线网络、有线网络、光纤网络、电信网络、内部网络、网际网络、区域网络(LAN)、广域网络(WAN)、无线区域网络(WLAN)、都会区域网络(MAN)、公共电话交换网络(PSTN)、蓝牙网络、ZigBee网络、近场通讯(NFC)网络等或以上任意组合。在一些实施例中，网络120可包括一个或多个网络进出点。例如，网络120可包含有线或无线网络进出点，如基站和/或网际网络交换点120-1、120-2、…，通过这些进出点，交叉路口识别系统100的一个或多个组件可连接到网络120上以交换数据和/或信息。
车辆终端140可以获取交通运输数据和/或信息。在一些实施例中，车辆终端140可以包括出租车终端140-1、私家车终端140-2、巴士终端140-3等中的一种或其任意组合。在一些实施例中，车辆终端140可以是移动装置、平板电脑、笔记本电脑等独立于车辆的终端设备，也可以是车辆内置装置。在一些实施例中，移动装置可包括智能家居装置、可穿戴装置、智能行动装置、虚拟实境装置、增强实境装置等或其任意组合。在一些实施例中，智能家具装置可包括智能照明装置、智能电器的控制装置、智能监测装置、智能电视、智能摄像机、对讲机等或其任意组合。在一些实施例中，可穿戴装置可包括智能手环、智能鞋袜、智能眼镜、智能头盔、智能手表、智能衣物、智能背包、智能配饰等或其任意组合。在一些实施例中，智能行动装置可包括智能电话、个人数字助理(PDA)、游戏装置、导航装置、POS装置等或其任意组合。在一些实施例中，虚拟实境装置和/或增强实境装置可包括虚拟实境头盔、虚拟实境眼镜、虚拟实境眼罩、增强实境头盔、增强实境眼镜、增强实境眼罩等或以上任意组合。在一些实施例中，车辆终端140可具有定位功能，以确定用户和/或车辆终端140的位置。在一些实施例中，车辆终端140可具有传感器，可以检测车辆的行驶状态，包括但不限于行驶方向、速度、加速度、角速度、角加速度等。
存储器150可存储资料和/或指令。在一些实施例中，存储器150可存储从车辆终端140获取的资料。在一些实施例中，存储器150可存储供服务器110执行或使用的信息和/或指令，以执行本申请中描述的示例性方法。在一些实施例中，存储器150可包括大容量存储器、可移动存储器、挥发性读写存储器(例如，随机存取存储器RAM)、只读存储器(ROM)等或以上任意组合。在一些实施例中，存储器150可在云平台上实现。例如，该云平台可包括私有云、公共云、混合云、社区云、分散式云、内部云等或以上任意组合。
在一些实施例中，存储器150可与网络120连接以与交叉路口识别系统100的一个或多个组件(例如，服务器110、车辆终端140等)通讯。交叉路口识别系统100的一个或多个组件可通过网络120访问存储于存储器150中的资料或指令。在一些实施例中，存储器150可直接与交叉路口识别系统100中的一个或多个组件(如，服务器110、车辆终端140)连接或通讯。在一些实施例中，存储器150可以是服务器110的一部分。
信息源160是为交叉路口识别系统100提供其他信息的一个源。在一些实施例中，信息源160可以用于为系统提供交通轨迹数据、交通图像数据。信息源160可以是 一个单独的中央服务器的形式存在，也可以是以多个通过网络连接的服务器的形式存在，还可以是以大量的个人设备形式存在。当信息源160以大量个人设备形式存在时，这些设备可以通过一种用户生成内容(user-generated contents)的方式，例如向云端服务器上传文字、语音、图像、视频等，从而是云端服务器连通与其连接的众多个人设备一起组成信息源160。
图2所示为根据本申请一些实施例所示的识别目标交叉路口方法的示例性流程图。具体地，该识别目标交叉路口的方法200可以由服务器110执行。
一般来说，同一道路由不同车道组成，具有双向通行能力，可以允许车辆按相反方向行驶。例如，对于组成交叉路口的某一道路，可以同时具备允许车辆驶向交叉路口的车道和允许车辆驶离交叉路口的车道。在本申请中，将车辆行驶方向为驶向交叉路口并在交叉路口处左转弯的车道称为固定左转弯车道；将固定左转弯车道旁车辆行驶方向为驶离交叉路口的车道称为对向来车车道。例如，可参见图8，进道口1最左侧车道L1为固定左转弯车道，出道口3上的三股车道L2、L3、L4为对向来车车道。当固定左转弯车道左转车流量较大(例如超过一定流量阈值)时，可以将一段对向来车车道设置为可变左转弯车道。具体地，可以将至少一股对向来车车道靠近交叉路口的一段设置为可变左转弯车道。例如，可以将出口道3上的车道L2靠近交叉路口的一段设置为可变左转弯车道，或者，还可以将出口道3上中间一股车道L3靠近交叉路口的一段也设置为可变左转车道。通过增加左转弯车道的数量，可以增加交叉路口处左转弯的通行能力，缓解左转弯车辆积压拥堵的情况。在一些实施例中，可变左转弯车道的长度可以由人工设定，也可以由服务器110自动设定。所述长度可以为，例如200米、150米、100米、80米、50米等。车辆可以通过可变左转弯车道入口(例如图8中的820)进入可变左转弯车道。在一些实施例中，可以在可变左转弯车道入口处设置提示装置(如标识牌等)，提示驾驶者可以进入可变左转弯车道进行左转。
可以理解，尽管提出了将一段对向来车车道设置为可变左转弯车道这种缓解左转弯压力的方法，但并非所有交叉路口都满足可以设置可变左转弯车道的条件。例如，如果交叉路口的放行顺序为先直行再左转，或者同时直行和左转，放行结束时左转弯尾车可能尚未行驶到道路对面，这时垂直方向的直行车辆开始放行，或者垂直方向的直行和左转车辆同时开始放行，很容易与左转弯尾车交织，导致路口拥堵。可见，对于放行顺序为先直行再左转，或同时直行和左转的交叉路口来说，如果将一段对向来车车道设置为可变左转弯车道，会加剧这种垂直方向车辆交织导致路口拥堵的情况。而如果交叉 路口的放行顺序为先左转再直行，放行结束时直行尾车可能尚未行驶到道路对面，这时垂直方向的左转车辆开始放行，与直行尾车的行驶方向相同，不会交织，导致路口拥堵的可能性较小。可见，对于放行顺序为先左转再直行的交叉路口来说，可以将一段对向来车车道临时设置为左转弯车道，以缓解左转弯车流量太大的压力。因此，需要识别出放行顺序为先左转再直行的交叉路口。又例如，可变左转弯车道转弯半径比固定左转弯车道的转弯半径小，如果转弯半径太小，容易造成车内人员不适甚至引发交通事故。根据国家相关道路工程设计规范，转弯半径必须符合一定标准，因此需要识别出左转弯半径满足一定条件的交叉路口。
如图2所示，该识别目标交叉路口方法200可以包括：
步骤210，获取交叉路口的交通信号灯的相序，当所述交叉路口的交通信号灯的相序为左转灯先于直行灯时，将所述交叉路口作为第一候选路口。
交叉路口可以包括但不限于平面交叉路口、环形交叉路口、立体交叉路口等。平面交叉路口可以表示在同一个平面上相交形成的交叉路口。在一些实施例中，平面交叉路口可以包括十字交叉路口、丁字交叉路口、Y字交叉路口、X字交叉路口、五岔路口、六岔路口等。环形交叉路口可以表示在路口中间设置一个面积较大的环岛，车辆绕岛单向行驶。立体交叉路口可以表示不在同一个平面上相交形成的立体交叉路口。在一些实施例中，立体交叉路口可以由立交桥、引道和坡道等部分组成。交通信号灯可以由红灯、绿灯、和黄灯组成。交通信号灯可以包括但不限于机动车信号灯、非机动车信号灯、人行横道信号灯、车道信号灯、方向指示信号灯、道路与铁路平面交叉道口信号灯等中的一种或其任意组合。交通信号灯的相序可以表示在一个信号周期内路口车辆放行方向的顺序。例如，交通信号灯的相序可以为先直行再左转。又例如，交通信号灯的相序可以为先左转再直行。再例如，交通信号灯的相序可以为同步直行和左转。在一些实施例中，交通信号灯的相序为左转灯先于直行灯，可以理解为，当交通信号灯为方向指示信号灯时，在一个信号周期内，左转的绿灯点亮时间早于直行的绿灯点亮时间。
在一些实施例中，服务器110可以从交通信号装置130处获取交叉路况交通信号灯的相序。具体地，交通信号装置130设定了各信号灯的相序，服务器110可以获取该相序设定信息。在一些实施例中，服务器110可以根据交叉路口的图像数据(例如视频)确定交通信号灯的相序。具体地，可以通过图像获取装置(例如摄像头)获取交叉路口的图像数据，图像数据可以反映交叉路口的真实交通状况，包括各车道的放行顺序，服务器110可以根据图像中的放行顺序确定信号灯的相序。在一些实施例中，服务器 110可以基于车辆运行轨迹确定交叉路口的交通信号灯的相序。具体地，车辆运行轨迹可以通过定位装置获取，交叉路口的车辆运行轨迹可以包括左转车流轨迹或直行车流轨迹。在一些实施例中，服务器110可以基于交叉路口在一定时间(如一个信号灯周期、3分钟、10分钟、1小时等)的左转车流轨迹或直行车流轨迹，确定交叉路口的交通信号灯的相序，筛选出交叉路口的交通信号灯的相序为先左转后直行的路口。在一些实施例中，服务器110可以将交通信号灯的相序为先左转后直行的路口确定为第一候选路口。在一些实施例中，可以将确定的第一候选路口信息通过网络120存储于存储器150。
步骤220，将交叉路口的一段对向来车车道设置为左转弯车道，并计算左转弯车道的左转弯半径，当左转弯半径大于第一阈值时，将交叉路口作为第二候选路口。
在一些实施例中，服务器110可以基于交叉路口的几何条件计算可变左转弯车道的左转弯半径。在一些实施例中，交叉路口的几何条件包括但不限于道路宽度、弧道的形状和大小等。道路宽度可以包括出口道宽度和/或进口道宽度。道路宽度还可以包括各车道的宽度。弧道是指道路与路口交界处的弧形部分(如图9中的弧道
Figure PCTCN2018124048-appb-000001
)。在一些实施例中，可以通过人工测量的方式确定交叉路口的几何条件。在一些实施例中，服务器110可以基于交叉路口的图像数据确定交叉路口的几何条件。在一些实施例中，服务器110可以基于交通轨迹信息确定交叉路口的几何条件。关于通过交通轨迹信息计算左转弯车道的左转弯半径的其他描述可以参见图7及其描述，在此不再赘述。
在一些实施例中，服务器110可以将可变左转弯车道的左转弯半径与第一阈值进行比较，判断可变左转弯车道的左转弯半径是否大于第一阈值。在一些实施例中，第一阈值可以是预先设置的第一阈值，也可以是根据实际需要动态设置的第一阈值。例如，预设的第一阈值为30m，当计算的左转弯半径为35m时，服务器110可以判断出左转弯半径大于第一阈值。
在一些实施例中，第一阈值可以根据相关行业规范或标准计算得到。例如，可以计算圆曲线最小半径作为第一阈值。圆曲线最小半径是根据车辆在曲线部分能安全或顺适地行驶所需要的条件而确定的，即车辆行驶在道路曲线部分所产生的离心力等横向力不超过轮胎与路面的摩阻力所允许的界限。具体地，圆曲线最小半径可以通过式(1)计算得到：
Figure PCTCN2018124048-appb-000002
其中，R为圆曲线最小半径；V为设计车速；μ为横向力系数，取轮胎与路面之间的横 向摩阻系数；i为路面横坡或超高横坡度，以小数表示，反超高时用负值。在一些实施例中，圆曲线半径可以包括极限最小半径、一般最小半径和/或不设超高的最小半径。极限最小半径是指保证车辆安全行驶的最小半径，计算极限最小半径时，可以取路面横坡或超高横坡度i的最大值、允许的横向力系数μ的最大值。一般最小半径是指保证车辆以设计车速安全、舒适行车的最小半径，计算一般最小半径时，可以取路面横坡或超高横坡度i、横向力系数μ的舒适值来计算。不设超高的最小半径是指保证车辆行驶稳定性的最小半径，计算不设超高的最小半径时，i和μ的取值可以是：当i≤2％时，μ＝0.035～0.04；当i>2％时，μ＝0.04～0.05。有关圆曲线最小半径的更多内容可以参见《公路工程技术标准》(JTG B01-2014)。
应理解的是，在一些实施例中，上述步骤220中所描述的将交叉口的一段对向来车车道设置为可变左转弯车道，并非在交叉路口处设置真实的可变左转弯车道，而是模拟设置，例如，可以通过计算机进行模拟。只有在确定交叉路口为适合设置可变左转弯车道的目标交叉路口后，再考虑在该交叉路口处设置真实的可变左转弯车道。
步骤230，将同时属于第一候选路口和第二候选路口的交叉路口标记为目标交叉路口。
目标交叉路口是指满足在对向来车车道设置可变左转弯车道条件的交叉路口。在一些实施例中，可以采用机器标记、人工标记、或机器标记与人工标记组合等多种方式标记目标交叉路口。
应当注意的是，上述有关识别目标交叉路口方法200的描述仅仅是为了示例和说明，而不限定本申请的适用范围。对于本领域技术人员来说，在本申请的指导下可以对该方法200进行各种修正和改变。然而，这些修正和改变仍在本申请的范围之内。例如，步骤210可以在步骤220之后，或者两个步骤同时进行。又例如，在步骤230后，可以增加在目标交叉路口设置真实可变左转弯车道的步骤。
图3是根据本申请一些实施例所示的交叉路口识别系统的模块图。如图3所示，该交叉路口识别系统300可以包括第一候选路口确定模块310、第二候选路口确定模块320和目标交叉路口确定模块330。
第一候选路口确定模块310可以用于确定第一候选路口。在一些实施例中，第一候选路口确定模块310可以获取交叉路口的交通信号灯的相序，当交叉路口的交通信号灯的相序为左转灯先于直行灯时，将交叉路口确定为第一候选路口。关于确定第一候选路口的详细描述可以参见图3所示的步骤210及其描述，在此不再赘述。
第二候选路口确定模块320可以用于确定第二候选路口。在一些实施中，第二候选路口确定模块320可以将交叉路口的一段对向来车车道设置为左转弯车道，并计算左转弯车道的左转弯半径，当左转弯半径大于第一阈值时，将交叉路口作为第二候选路口。在一些实施例中，第二候选路口确定模块320可以基于道路宽度，计算左转弯车道的左转弯半径。在一些实施例中，第二候选路口确定模块320可以基于交通轨迹信息，确定交叉路口的道路宽度。在一些实施例中，第二候选路口确定模块320可以获取交通轨迹信息。关于确定第二候选路口的详细描述可以参见步骤220，在此不再赘述。
目标交叉路口确定模块330可以用于确定目标交叉路口。在一些实施例中，目标交叉路口确定模块330将同时属于第一候选路口和第二候选路口的交叉路口标记为目标交叉路口。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、以及左转车道的饱和度大于第二阈值的交叉路口标记为目标交叉路口。车道饱和度可以表示为车道的车流量与车道通行能力的比值。关于将交叉路口左转车道的饱和度大于第二阈值的交叉路口标记为目标交叉路口的详细描述可以参见图4及其描述，在此不再赘述。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、以及十字交叉路口或丁字路口的交叉路口标记为目标交叉路口。关于将十字交叉路口或丁字路口的交叉路口标记为目标交叉路口的详细描述可以参见图5及其描述，在此不再赘述。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、以及人流量小于第三阈值的交叉路口标记为目标交叉路口。关于将人流量小于第三阈值的交叉路口标记为目标交叉路口的详细描述可以参见图6及其描述，在此不再赘述。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、十字交叉路口或丁字路口交叉、以及左转车道的饱和度大于第二阈值的交叉路口标记为目标交叉路口。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、十字交叉路口或丁字路口的交叉路口、以及人流量小于第三阈值的交叉路口标记为目标交叉路口。在一些实施例中，目标交叉路口确定模块330可以将同时属于第一候选路口、第二候选路口、十字交叉路口或丁字路口交叉、左转车道的饱和度大于第二阈值的交叉路口、以及人流量小于第三阈值的交叉路口标记为目标交叉路口。
应当理解，图3所示的系统及其模块可以利用各种方式来实现。例如，在一些实施例中，系统及其模块可以通过硬件、软件或者软件和硬件的结合来实现。其中，硬件部分可以利用专用逻辑来实现；软件部分则可以存储在存储器中，由适当的指令执行 系统，例如微处理器或者专用设计硬件来执行。本领域技术人员可以理解上述的方法和系统可以使用计算机可执行指令和/或包含在处理器控制代码中来实现，例如在诸如磁盘、CD或DVD-ROM的载体介质、诸如只读存储器(固件)的可编程的存储器或者诸如光学或电子信号载体的数据载体上提供了这样的代码。本申请的系统及其模块不仅可以有诸如超大规模集成电路或门阵列、诸如逻辑芯片、晶体管等的半导体、或者诸如现场可编程门阵列、可编程逻辑设备等的可编程硬件设备的硬件电路实现，也可以用例如由各种类型的处理器所执行的软件实现，还可以由上述硬件电路和软件的结合(例如，固件)来实现。
需要注意的是，以上对于交叉路口识别系统及其模块的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解该系统的原理后，可能在不背离这一原理的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接。例如，在一些实施例中，例如，图3中披露的第一候选路口确定模块310、第二候选路口确定模块320和目标交叉路口确定模块330可以是一个系统中的不同模块，也可以是一个模块实现上述的两个或两个以上模块的功能。例如，第一候选路口确定模块310、第二候选路口确定模块320可以是两个模块，也可以是一个模块同时具有确定第一候选路口和第二候选路口的功能。例如，各个模块可以共用一个存储模块，各个模块也可以分别具有各自的存储模块。诸如此类的变形，均在本申请的保护范围之内。
图4所示为根据本申请一些实施例所示的识别目标交叉路口方法的示例性流程图。如图4所示，该识别目标交叉路口方法400可以包括：
步骤410，判断交叉路口左转车道的饱和度是否大于第二阈值。
在一些实施例中，只有交叉路口的左转车道饱和度到达一定条件才有必要在该交叉路口设置可变左转弯车道。车道饱和度可以表示为车道的车流量与车道通行能力的比值。车道通行能力是指单位时间内该车道可以通过的最大车辆数，车道的车流量是指单位时间内通过该车道的实际车辆数。例如，某车道的通行能力为2000pcu/h(即标准车当量数/小时)，车流量为1600pcu/h，则该车道的饱和度为1600/2000＝0.8。在一些实施例中，车道通行能力可以根据左转车道宽度、左转放行的时长、信号灯周期时长等中的一种或任意组合来计算。当左转车道饱和度超过第二阈值时，表明左转车道上的车流量很大，左转车辆可能会出现积压拥堵的现象。在一些实施例中，第二阈值可以是服务器110或人工基于交叉路口左转车道的历史交通数据预设的值。在一些实施例中，第 二阈值可以由服务器110或人工每隔一段时间(例如，一天、一个月、两个月、半年)根据最新的交通数据进行更新。
在一些实施例中，服务器110可以获取交叉路口的图像数据(例如视频)，根据图像数据确定交叉路口左转车道的车流量。在一些实施例中，可以通过人工统计的方法获取交叉路口左转车道的车流量数据。在一些实施例中，可以通过设在交叉路口左转车道的传感器(例如线圈检测器)，获取交叉路口左转车道的车流量数据。
在一些实施例中，可以根据车辆运行轨迹确定左转车道的饱和度。例如，可以根据车辆运行轨迹确定左转车辆通过交叉路口的时长，时长越长，说明左转车道的饱和度越高。特别地，如果左转车辆通过交叉路口的时长超过信号灯周期时长(也称为延误时长)，则表明左转车辆在一个信号灯周期内未能通过交叉路口，因此超过信号灯周期时长越长，左转车道饱和度越高。具体地，可以计算左转车辆通过交叉路口的平均时长，平均时长越长，左转车道饱和度越高；或者，可以计算左转车辆通过交叉路口的时长超过信号灯周期的平均延误时长，平均延误时长越长，左转车道饱和度越高。又例如，可以根据车辆运行轨迹确定左转车辆在交叉路口停车的次数，如果大于一次，说明车辆在一个信号灯周期内未能通过交叉路口。具体地，可以计算左转车辆在交叉路口停车次数的平均值，该数值越大，左转车道饱和度越高。
在一些实施例中，服务器110可以基于车道饱和度预测模型判断交叉路口左转车道的饱和度是否大于第二阈值。仅作为示例，车道饱和度预测模型的输入特征可以包含左转车道宽度、信号灯周期、左转放行时长、车流量、车辆运行轨迹等中的一种或任意组合。
在一些实施例中，服务器110基于交叉路口左转车道的饱和度，与预设的第二阈值进行比较，判断交叉路口左转车道的饱和度是否大于预设的第二阈值。例如，当交叉路口左转车道的饱和度为0.9，预设的第二阈值设为0.8时，服务器110可以判定交叉路口左转车道的饱和度大于预设的第二阈值。又例如，当交叉路口左转车道的饱和度为0.75，预设的第二阈值设为0.8时，服务器110可以判定交叉路口左转车道的饱和度小于预设的第二阈值。
步骤420，当交叉路口左转车道的饱和度大于第二阈值时，将交叉路口标记为目标交叉路口。
在一些实施例中，服务器110可以将目标交叉路口信息存储于存储器150中或向目标交叉路口相应的信号灯设备130发送目标交叉路口信息。在一些实施例中，服务 器110可以每隔一段时间基于更新的交叉路口左转车道的饱和度、或更新的第二阈值来更新目标交叉路口信息。例如，服务器110可以在每个信号周期更新交叉路口左转车道的饱和度，与预设的第二阈值比较，动态更新目标交叉路口。
需要注意的是，图4所示识别目标交叉路口的方法是对通过图3所示方法识别出的目标交叉路口进行进一步筛选，即通过图4所示方法识别出的目标交叉路口，既满足交通信号灯的相序为左转灯先于直行灯、对向来车车道的一段作为左转弯车道时左转弯半径大于第一阈值，又满足左转车道的饱和度大于第二阈值。针对目标交叉路口，可以通过将一段对向来车车道设置为左转弯车道来缓解左转弯的通行压力。
图5所示为根据本申请一些实施例所示的识别目标交叉路口方法的示例性流程图。如图5所示，该识别目标交叉路口方法500可以包括：
步骤510，判断交叉路口的类型。
交叉路口的类型可以包括但不限于平面交叉路口、环形交叉路口、立体交叉路口等。例如，平面交叉路口可以包括十字交叉路口、丁字交叉路口、Y字交叉路口、X字交叉路口、五岔路口、六岔路口、或异形路口等中的一种或其任意组合。对于某些类型的交叉路口，例如十字交叉路口或丁字交叉路口，通过将一段对向来车车道设置为左转车道可以有效缓解左转通行压力；对于其他一些类型的交叉路口，有的本身就不包含对向来车车道(例如环形交叉路口)，有的通过将一段对向来车车道设置为左转车道并不能有效缓解左转通行压力(例如五岔路口、六岔路口这类复杂交叉路口)，对于这些类型的交叉路口来说，并不适合将一段对向来车车道设置为左转车道。因此，需要识别出十字交叉路口或丁字交叉路口等适合的目标交叉路口。
在一些实施例中，可以基于车辆运行轨迹确定交叉路口的类型。例如，如果车辆运行轨迹显示有四条呈十字型的道路上行驶有车辆，并且这四条道路组成了交叉路口，则该交叉路口的类型十字交叉路口。又例如，如果车辆运行轨迹呈单向环形状，则可以确定交叉路口为环形交叉路口。又例如，如果车辆运行轨迹显示，在相交道路方向的冲突轨迹可以同时通过交叉路口，且交叉路口平均车速较高，则该交叉路口可能为立交交叉路口。再例如，如果车辆运行轨迹显示，车辆在交叉路口的轨迹速度较慢且无周期性，则该交叉路口可能是无信号灯控制的交叉路口。具体地，车辆运行轨迹可以通过定位装置获取。在一些实施例中，处理器110可以通过网络120从信息源160处获取车辆运行轨迹。信息源160可以为，例如，交通管理部门的数据库、地图公司的数据库等第三方数据库。在一些实施例中，可以获取地图数据(例如从第三方地图公司获取)，地图数 据中含有交叉路口的类型信息，因此可以直接基于地图数据确定交叉路口的类型。在一些实施例中，还可以通过交叉路口的图像数据(例如视频)确定交叉路口的类型。例如，交叉路口的图像数据中可能包括交通标志图像，其中可能有表明交叉路口类型的交通标志，服务器110可以通过图像识别技术确定交叉路口的类型。又例如，交叉路口中的图像数据反映了车辆的行驶方向，可以用于确定交叉路口的类型。在一些实施例中，服务器110可以通过图像识别技术识别出图像数据中有关交叉路口的交通标志，确定其含义，从而确定交叉路口的类型。在一些实施例中，可以通过人工或服务器110自动的方式确定交叉路口的类型。例如，服务器110可以采用机器学习模型确定交叉路口的类型。仅仅作为示例，机器学习模型的输入可以包括车辆运行轨迹、交叉路口的图像数据等，输出为交叉路口的类型。
步骤520，当交叉路口为十字交叉路口或丁字交叉路口时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，服务器110可以将目标交叉路口信息存储于存储器150中或向目标交叉路口相应的信号灯设备130发送目标交叉路口信息。在一些实施例中，服务器110可以定期或不定期更新目标交叉路口信息。
需要注意的是，图5所示识别目标交叉路口的方法是对通过图3所示方法识别出的目标交叉路口进行进一步筛选，即通过图5所示方法识别出的目标交叉路口，既满足交通信号灯的相序为左转灯先于直行灯、对向来车车道的一段作为左转弯车道时左转弯半径大于第一阈值，又满足交叉路口类型为十字交叉路口或丁字交叉路口。针对目标交叉路口，可以通过将一段对向来车车道设置为左转弯车道来缓解左转弯的通行压力。
图6所示为根据本申请一些实施例所示的识别目标交叉路口方法的示例性流程图。如图6所示，该识别目标交叉路口方法600可以包括：
步骤610，判断交叉路口的人流量是否小于第三阈值。
对于人流量较大的路口来说，将一段对向来车车道设置为左转车道可能会带来安全隐患。如图8所示，正常情况下，进道口1和出道口3之间设有隔离带，如果要将出道口3的一段设置为左转弯车道，则需要在进道口1和出道口3之间的隔离带打开一个开口820，此时，行人看到该开口820，可能会以为该开口处可供行人过马路，于是在与进到口1和出道口3垂直的方向上出现横穿马路的行人，从而产生安全隐患。因此，需要分析交叉路口的人流量，来判断交叉路口是否适合作为目标交叉路口。
在一些实施例中，人流量可以是单位时间内通过交叉路口的人次。在一些实施 例中，服务器110可以基于交通轨迹信息确定交叉路口的人流量。在一些实施例中，服务器110可以基于交叉路口的图像数据(例如视频)确定人流量。在一些实施例中，可以在交叉路口设置传感器，例如红外传感器、摄像头、雷达、激光雷达等，获取交叉路口的人流量数据。在一些实施例中，可以通过人工统计的方法获取交叉路口的人流量数据。
在一些实施例中，服务器110可以将确定的交叉路口的人流量与第三阈值进行比较，判断该人流量是否小于第三阈值。其中，第三阈值可以是预设的固定值，也可以根据实际需要每隔一段时间(早上高峰期、下班高峰期等)进行更新。
步骤620，当所述交叉路口的人流量小于第三阈值时，将所述交叉路口标记为目标交叉路口。
在一些实施例中，服务器110可以将目标交叉路口信息存储于存储器150中或向目标交叉路口相应的信号灯设备130发送目标交叉路口信息。在一些实施例中，服务器110可以定期或不定期更新目标交叉路口信息。
除了图6所示的根据人流量确定目标交叉路口的方法外，在一些实施例中，可以根据历史用车订单确定目标交叉路口。例如，可以分析历史用车订单的上车地点和/或下次地点，如果交叉路口及周边被频繁作为上车地点和/或下次地点(如次数超过设定次数阈值)，则确定该交叉路口处人流量较大，不适合作为目标交叉路口。在一些实施例中，还可以根据交叉路口周边的场所信息确定目标交叉路口。例如，如果交叉路口附近有医院、学校、大型商场等场所时，也不适合作为目标交叉路口。这些场所通常人流量较大，如果将一段对向来车车道设置为左转弯车道，也会导致安全隐患。在一些实施例中，服务器110可以从信息源160处获取交叉路口周边的场所信息。例如，信息源160可以是交通管理部门的数据库或地图公司的数据库等第三方数据库。
需要注意的是，图6所示识别目标交叉路口的方法是对通过图3所示方法识别出的目标交叉路口进行进一步筛选，即通过图6所示方法识别出的目标交叉路口，既满足交通信号灯的相序为左转灯先于直行灯、对向来车车道的一段作为左转弯车道时左转弯半径大于第一阈值，又满足人流量小于第三阈值。针对目标交叉路口，可以通过将一段对向来车车道设置为左转弯车道来缓解左转弯的通行压力。
图7所示为根据本申请一些实施例所示的计算左转车道的左转弯半径的流程图。如图7所示，计算左转车道的左转弯半径的方法700可以包括：
步骤710，获取交叉路口的交通轨迹信息。
在一些实施例中，交通轨迹信息可以由定位设备采用定位技术获取。定位技术包括但不限于GPS卫星定位、蓝牙定位、WIFI网络定位、北斗定位、移动通讯技术定位等。交通轨迹可以由多个车辆的行驶轨迹组成。每个车辆的行驶轨迹都由大量轨迹点连成。每个轨迹点数据包括该轨迹点的位置(例如经纬度)、时间等信息。在一些实施例中，可以每隔一段时间(例如10秒、5秒、2秒等)获取一次车辆的位置，将该次获取的时间及位置信息形成一个轨迹点。
步骤720，基于交通轨迹信息，确定交叉路口的几何条件。
在一些实施例中，交叉路口的几何条件包括但不限于道路宽度、弧道的形状和大小等。道路宽度可以包括出口道宽度和/或进口道宽度。道路宽度还可以包括各车道的宽度。弧道是指道路与路口交界处的弧形部分(如图9中的弧道
Figure PCTCN2018124048-appb-000003
)。在一些实施例中，多个车辆的行驶轨迹组成的交通轨迹可以描绘出道路的形状或轮廓，根据该形状或轮廓可以确定交叉路口的几何条件。
步骤730，基于交叉路口的几何条件，计算可变左转弯车道的左转弯半径。
在一些实施例中，可以根据交叉路口的几何条件，确定可变左转弯车道的理论转弯路径，该理论转弯半径为一段圆弧，确定该圆弧状的理论转弯路径的半径作为可变左转弯车道的左转弯半径。
为了方便描述，以下结合图9说明可变左转弯车道左转弯半径的计算。计算步骤如下：
a.确定可变左转弯车道L6(或车道L2)的中心线910、出口道2内侧车道L5的中心线920。
b.确定路口边界线930和940。路口边界线可以根据弧道结束位置确定。例如，弧道
Figure PCTCN2018124048-appb-000004
在出道口3处的结束位置为C点，在进道口4处的结束位置为D点，确定通过C点与出口道3(或进口道1)垂直的直线即为路口边界线930，通过D点与进口道4(或出口道2)垂直的直线即为路口边界线940。
c.中心线910、920与路口边界线930、940组成一个矩形，确定该矩形内的最大内切圆O，该内切圆的圆心为O点，半径为r。圆O右上角的圆弧
Figure PCTCN2018124048-appb-000005
即为通过可变左转弯车道L6进行左转的车辆的理论转弯路径，可变左转弯车道L6的左转弯半径即为r。
图8所示为根据本申请一些实施例所示的设置有可变左转弯车道的目标交叉路口的示意图。
图8示出了一个目标交叉路口，该交叉路口由方向互相垂直的车道构成。其中，进口道1的最左侧车道L1为固定左转弯车道。当左转弯车流量较大时，可将出道口3最靠近进道口1的车道L2靠近交叉路口的一段设置为可变左转弯车道L6，同时将进口道1与出口道3之间的隔离带打开一个入口820供车辆驶入可变左转弯车道L6。当左转信号变绿左转车辆放行时，左转车辆除了可以通过固定左转弯车道L1左转外，还可以通过入口820进入可变左转弯车道L6进行左转。在一些实施例中，固定左转弯车道的左转弯路径830的转弯半径大于第一阈值。在一些实施例中，可变左转弯车道L6的左转弯路径840的转弯半径也大于第一阈值。
图9为根据本申请一些实施例所示的用于确定交叉路口可变左转弯车道的转弯半径的交叉路口示意图。具体的确定步骤可以参见图7及其描述，此处不再赘述。
本申请实施例可能带来的有益效果包括但不限于：(1)利用交通轨迹数据等方法识别适合采用逆向可变左转车道的交叉路口，减少了人工逐一排查选取交叉路口的工作量；(2)在识别的交叉路口可以设置逆向可变左转车道，提高左转车辆的通行效率，缓解交叉口的交通压力。需要说明的是，不同实施例可能产生的有益效果不同，在不同的实施例里，可能产生的有益效果可以是以上任意一种或几种的组合，也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述，显然，对于本领域技术人员来说，上述详细披露仅仅作为示例，而并不构成对本申请的限定。虽然此处并没有明确说明，本领域技术人员可能会对本申请进行各种修改、改进和修正。该类修改、改进和修正在本申请中被建议，所以该类修改、改进、修正仍属于本申请示范实施例的精神和范围。
同时，本申请使用了特定词语来描述本申请的实施例。如“一个实施例”、“一实施例”、和/或“一些实施例”意指与本申请至少一个实施例相关的某一特征、结构或特点。因此，应强调并注意的是，本说明书中在不同位置两次或多次提及的“一实施例”或“一个实施例”或“一个替代性实施例”并不一定是指同一实施例。此外，本申请的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外，本领域技术人员可以理解，本申请的各方面可以通过若干具有可专利性的种类或情况进行说明和描述，包括任何新的和有用的工序、机器、产品或物质的组合，或对他们的任何新的和有用的改进。相应地，本申请的各个方面可以完全由硬件执行、可以完全由软件(包括固件、常驻软件、微码等)执行、也可以由硬件和软件组合执行。以上硬件或软件均可被称为“数据块”、“模块”、“引擎”、“单元”、“组件”或 “系统”。此外，本申请的各方面可能表现为位于一个或多个计算机可读介质中的计算机产品，该产品包括计算机可读程序编码。
计算机存储介质可能包含一个内含有计算机程序编码的传播数据信号，例如在基带上或作为载波的一部分。该传播信号可能有多种表现形式，包括电磁形式、光形式等，或合适的组合形式。计算机存储介质可以是除计算机可读存储介质之外的任何计算机可读介质，该介质可以通过连接至一个指令执行系统、装置或设备以实现通讯、传播或传输供使用的程序。位于计算机存储介质上的程序编码可以通过任何合适的介质进行传播，包括无线电、电缆、光纤电缆、RF、或类似介质，或任何上述介质的组合。
本申请各部分操作所需的计算机程序编码可以用任意一种或多种程序语言编写，包括面向对象编程语言如Java、Scala、Smalltalk、Eiffel、JADE、Emerald、C++、C#、VB.NET、Python等，常规程序化编程语言如C语言、Visual Basic、Fortran 2003、Perl、COBOL 2002、PHP、ABAP，动态编程语言如Python、Ruby和Groovy，或其他编程语言等。该程序编码可以完全在用户计算机上运行、或作为独立的软件包在用户计算机上运行、或部分在用户计算机上运行部分在远程计算机运行、或完全在远程计算机或服务器上运行。在后种情况下，远程计算机可以通过任何网络形式与用户计算机连接，比如局域网(LAN)或广域网(WAN)，或连接至外部计算机(例如通过因特网)，或在云计算环境中，或作为服务使用如软件即服务(SaaS)。
此外，除非权利要求中明确说明，本申请所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用，并非用于限定本申请流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的发明实施例，但应当理解的是，该类细节仅起到说明的目的，附加的权利要求并不仅限于披露的实施例，相反，权利要求旨在覆盖所有符合本申请实施例实质和范围的修正和等价组合。例如，虽然以上所描述的系统组件可以通过硬件设备实现，但是也可以只通过软件的解决方案得以实现，如在现有的服务器或移动设备上安装所描述的系统。
同理，应当注意的是，为了简化本申请披露的表述，从而帮助对一个或多个发明实施例的理解，前文对本申请实施例的描述中，有时会将多种特征归并至一个实施例、附图或对其的描述中。但是，这种披露方法并不意味着本申请对象所需要的特征比权利要求中提及的特征多。实际上，实施例的特征要少于上述披露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字，应当理解的是，此类用于实施例描述的数字，在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。 除非另外说明，“大约”、“近似”或“大体上”表明所述数字允许有±20％的变化。相应地，在一些实施例中，说明书和权利要求中使用的数值参数均为近似值，该近似值根据个别实施例所需特点可以发生改变。在一些实施例中，数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本申请一些实施例中用于确认其范围广度的数值域和参数为近似值，在具体实施例中，此类数值的设定在可行范围内尽可能精确。
针对本申请引用的每个专利、专利申请、专利申请公开物和其他材料，如文章、书籍、说明书、出版物、文档等，特此将其全部内容并入本申请作为参考。与本申请内容不一致或产生冲突的申请历史文件除外，对本申请权利要求最广范围有限制的文件(当前或之后附加于本申请中的)也除外。需要说明的是，如果本申请附属材料中的描述、定义、和/或术语的使用与本申请所述内容有不一致或冲突的地方，以本申请的描述、定义和/或术语的使用为准。
最后，应当理解的是，本申请中所述实施例仅用以说明本申请实施例的原则。其他的变形也可能属于本申请的范围。因此，作为示例而非限制，本申请实施例的替代配置可视为与本申请的教导一致。相应地，本申请的实施例不仅限于本申请明确介绍和描述的实施例。

Claims (18)

  1. 一种识别交叉路口的方法，其特征在于，所述方法包括：
    获取交叉路口的交通信号灯的相序，当所述交叉路口的交通信号灯的相序为左转灯先于直行灯时，将所述交叉路口作为第一候选路口；
    将所述交叉路口的一段对向来车车道设置为左转弯车道，并计算所述左转弯车道的左转弯半径，当所述左转弯半径大于第一阈值时，将所述交叉路口作为第二候选路口；
    将同时属于所述第一候选路口和所述第二候选路口的交叉路口标记为目标交叉路口。
  2. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    判断所述交叉路口左转车道的饱和度是否大于第二阈值；
    当所述交叉路口左转车道的饱和度大于第二阈值时，将所述交叉路口标记为目标交叉路口。
  3. 根据权利要求2所述的方法，其特征在于，所述方法进一步包括：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口左转车道的车流量；
    基于所述车流量，判断所述交叉路口左转车道的饱和度是否大于所述第二阈值。
  4. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    判断所述交叉路口是否为十字交叉路口或丁字交叉路口；
    当所述交叉路口为十字交叉路口或丁字交叉路口时，将所述交叉路口标记为目标交叉路口。
  5. 根据权利要求4所述的方法，其特征在于，所述方法进一步包括：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，判断所述交叉路口是否为十字交叉路口或丁字交叉路口。
  6. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    判断所述交叉路口的人流量是否小于第三阈值；
    当所述交叉路口的人流量小于第三阈值时，将所述交叉路口标记为目标交叉路口。
  7. 根据权利要求6所述的方法，其特征在于，所述方法进一步包括：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口的人流量。
  8. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口的几何条件；
    基于所述几何条件，计算所述左转弯车道的左转弯半径。
  9. 一种交叉路口识别系统，其特征在于，包括第一候选路口确定模块、第二候选路口确定模块、目标交叉路口确定模块，其中，
    所述第一候选路口确定模块用于获取交叉路口的交通信号灯的相序，当所述交叉路口的交通信号灯的相序为左转灯先于直行灯时，将所述交叉路口作为第一候选路口；
    所述第二候选路口确定模块用于将所述交叉路口的一段对向来车车道设置为左转弯车道，并计算所述左转弯车道的左转弯半径，当所述左转弯半径大于第一阈值时，将所述交叉路口作为第二候选路口；
    所述目标交叉路口确定模块用于将同时属于所述第一候选路口和所述第二候选路口的交叉路口标记为目标交叉路口。
  10. 根据权利要求9所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    判断所述交叉路口左转车道的饱和度是否大于第二阈值；
    当所述交叉路口左转车道的饱和度大于第二阈值时，将所述交叉路口标记为目标交叉路口。
  11. 根据权利要求10所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口左转车道的车流量；
    基于所述车流量，判断所述交叉路口左转车道的饱和度是否大于所述第二阈值。
  12. 根据权利要求9所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    判断所述交叉路口是否为十字交叉路口或丁字交叉路口；
    当所述交叉路口为十字交叉路口或丁字交叉路口时，将所述交叉路口标记为目标交叉路口。
  13. 根据权利要求12所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，判断所述交叉路口是否为十字交叉路口或丁字交叉路口。
  14. 根据权利要求9所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    判断所述交叉路口的人流量是否小于第三阈值；
    当所述交叉路口的人流量小于第三阈值时，将所述交叉路口标记为目标交叉路口。
  15. 根据权利要求14所述的交叉路口识别系统，其特征在于，所述目标交叉路口确定模块进一步用于：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口的人流量。
  16. 根据权利要求9所述的交叉路口识别系统，其特征在于，所述第二候选路口确定模块进一步用于：
    获取所述交叉路口的交通轨迹信息；
    基于所述交通轨迹信息，确定所述交叉路口的几何条件；
    基于所述几何条件，计算所述左转弯车道的左转弯半径。
  17. 一种识别交叉路口装置，包括至少一个处理器和至少一个存储器，其特征在于，
    所述存储器用于存储计算机指令；
    所述处理器用于执行所述计算机指令以实现如权利要求1-8中任一项所述的识别交叉路口方法。
  18. 一种计算机可读存储介质，所述计算机可读存储介质存储计算机指令，当所述计算机指令被执行时，实现如权利要求1-8中任一项所述的识别交叉路口方法。
PCT/CN2018/124048 2018-12-25 2018-12-26 一种识别交叉路口的方法和系统 Ceased WO2020132990A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811591024.3 2018-12-25
CN201811591024.3A CN111369783B (zh) 2018-12-25 2018-12-25 一种识别交叉路口的方法和系统

Publications (1)

Publication Number Publication Date
WO2020132990A1 true WO2020132990A1 (zh) 2020-07-02

Family

ID=71127279

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/124048 Ceased WO2020132990A1 (zh) 2018-12-25 2018-12-26 一种识别交叉路口的方法和系统

Country Status (2)

Country Link
CN (1) CN111369783B (zh)
WO (1) WO2020132990A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113240914A (zh) * 2021-03-26 2021-08-10 合肥学院 一种动态调整左转专用车道和左转专用相位的控制方法
CN113936453A (zh) * 2021-09-09 2022-01-14 上海宝康电子控制工程有限公司 一种基于车头时距的信息识别方法及系统
CN114283578A (zh) * 2021-12-14 2022-04-05 淮阴工学院 一种交叉口左转弯待行区长度设计方法
CN114613156A (zh) * 2022-01-26 2022-06-10 大连理工大学 十字形逆向左转交叉口的全感应式独立信号控制技术
CN114973741A (zh) * 2022-06-17 2022-08-30 浙江大华技术股份有限公司 异常数据的处理方法、装置、存储介质及电子装置
CN115452701A (zh) * 2022-08-23 2022-12-09 中冶南方城市建设工程技术有限公司 一种水泥混凝土路面基层摩阻系数的现场测试装置及测量方法
CN115762196A (zh) * 2022-11-21 2023-03-07 北京东土正创科技有限公司 基于进出口方向锁定交通流的方法及交通信号控制装置
CN116798306A (zh) * 2023-05-31 2023-09-22 武汉中海庭数据技术有限公司 一种基于众包轨迹与路面要素生成准确路口的方法及装置
CN117218870A (zh) * 2023-11-09 2023-12-12 天津易华录信息技术有限公司 一种智慧城市交通信号管理系统
CN117315972A (zh) * 2023-09-18 2023-12-29 河南城建学院 一种基于非监督学习的车道级转向信息探测方法和系统
CN119445868A (zh) * 2024-09-24 2025-02-14 江苏艾提斯交通科技有限公司 基于云计算的实时监控系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112836586B (zh) * 2021-01-06 2024-09-06 北京嘀嘀无限科技发展有限公司 一种交叉口信息确定方法、系统和装置
CN113064439B (zh) * 2021-06-02 2021-09-24 北京三快在线科技有限公司 一种控制无人驾驶设备及设置枢纽的方法及装置
CN114926980B (zh) * 2022-04-22 2023-04-14 阿里巴巴（中国）有限公司 交通数据挖掘方法、装置、电子设备及计算机程序产品
CN116645652A (zh) * 2023-05-30 2023-08-25 上海交通大学 井下巷道交叉路口识别方法及系统
CN117845673A (zh) * 2023-12-04 2024-04-09 济南市市政工程设计研究院（集团）有限责任公司 基于衔接道路的物流地块开口宽度确定方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1776093A (zh) * 2005-12-08 2006-05-24 钱红波 左转车辆二次停车控制平面十字交叉口交通设计与交通控制方法
CN102493298A (zh) * 2011-11-17 2012-06-13 何晓艳 能同时实现左转的交叉路口
CN104064036A (zh) * 2014-06-19 2014-09-24 浙江大学 借道对向出口道左转的交叉口交通组织与信号配时方法
CN104631247A (zh) * 2015-01-04 2015-05-20 邯郸市公安交通警察支队 一种十字路口借道左转的交通指示系统及控制方法
CN107622675A (zh) * 2017-10-24 2018-01-23 河南城建学院 信号交叉口可变进出口车道交通流控制方法
CN107798874A (zh) * 2017-10-31 2018-03-13 哈尔滨工业大学 一种借用对向出口车道消除交叉口左转相位的方法
US10282981B1 (en) * 2016-04-11 2019-05-07 State Farm Mutual Automobile Insurance Company Networked vehicle control systems to facilitate situational awareness of vehicles

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1328314A (zh) * 2000-06-13 2001-12-26 同济大学 一种提高城市环行交叉口车辆通行能力的方法
JP4710981B2 (ja) * 2009-01-23 2011-06-29 トヨタ自動車株式会社 区画線認識装置、及び当該装置で用いられる区画線認識方法
CN102610093A (zh) * 2012-04-11 2012-07-25 天津市市政工程设计研究院 分离式货车专用左转车道设置方法
US8855904B1 (en) * 2012-10-10 2014-10-07 Google Inc. Use of position logs of vehicles to determine presence and behaviors of traffic controls
US9129526B2 (en) * 2013-07-19 2015-09-08 Superior Traffic Sysems, LLC Traffic management system
US9595192B1 (en) * 2016-04-14 2017-03-14 Ahmad Abdulaziz Alrashid Traffic violation detection system
CN108831166B (zh) * 2018-07-31 2019-09-24 北京航空航天大学 车路协同环境下交叉口可变导向车道功能变换方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1776093A (zh) * 2005-12-08 2006-05-24 钱红波 左转车辆二次停车控制平面十字交叉口交通设计与交通控制方法
CN102493298A (zh) * 2011-11-17 2012-06-13 何晓艳 能同时实现左转的交叉路口
CN104064036A (zh) * 2014-06-19 2014-09-24 浙江大学 借道对向出口道左转的交叉口交通组织与信号配时方法
CN104631247A (zh) * 2015-01-04 2015-05-20 邯郸市公安交通警察支队 一种十字路口借道左转的交通指示系统及控制方法
US10282981B1 (en) * 2016-04-11 2019-05-07 State Farm Mutual Automobile Insurance Company Networked vehicle control systems to facilitate situational awareness of vehicles
CN107622675A (zh) * 2017-10-24 2018-01-23 河南城建学院 信号交叉口可变进出口车道交通流控制方法
CN107798874A (zh) * 2017-10-31 2018-03-13 哈尔滨工业大学 一种借用对向出口车道消除交叉口左转相位的方法

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113240914B (zh) * 2021-03-26 2023-05-16 合肥学院 一种动态调整左转专用车道和左转专用相位的控制方法
CN113240914A (zh) * 2021-03-26 2021-08-10 合肥学院 一种动态调整左转专用车道和左转专用相位的控制方法
CN113936453A (zh) * 2021-09-09 2022-01-14 上海宝康电子控制工程有限公司 一种基于车头时距的信息识别方法及系统
CN114283578A (zh) * 2021-12-14 2022-04-05 淮阴工学院 一种交叉口左转弯待行区长度设计方法
CN114613156A (zh) * 2022-01-26 2022-06-10 大连理工大学 十字形逆向左转交叉口的全感应式独立信号控制技术
CN114973741A (zh) * 2022-06-17 2022-08-30 浙江大华技术股份有限公司 异常数据的处理方法、装置、存储介质及电子装置
CN115452701A (zh) * 2022-08-23 2022-12-09 中冶南方城市建设工程技术有限公司 一种水泥混凝土路面基层摩阻系数的现场测试装置及测量方法
CN115762196A (zh) * 2022-11-21 2023-03-07 北京东土正创科技有限公司 基于进出口方向锁定交通流的方法及交通信号控制装置
CN116798306A (zh) * 2023-05-31 2023-09-22 武汉中海庭数据技术有限公司 一种基于众包轨迹与路面要素生成准确路口的方法及装置
CN117315972A (zh) * 2023-09-18 2023-12-29 河南城建学院 一种基于非监督学习的车道级转向信息探测方法和系统
CN117218870A (zh) * 2023-11-09 2023-12-12 天津易华录信息技术有限公司 一种智慧城市交通信号管理系统
CN117218870B (zh) * 2023-11-09 2024-01-16 天津易华录信息技术有限公司 一种智慧城市交通信号管理系统
CN119445868A (zh) * 2024-09-24 2025-02-14 江苏艾提斯交通科技有限公司 基于云计算的实时监控系统

Also Published As

Publication number Publication date
CN111369783A (zh) 2020-07-03
CN111369783B (zh) 2021-06-01

Similar Documents

Publication Publication Date Title
WO2020132990A1 (zh) 一种识别交叉路口的方法和系统
US11669097B2 (en) Systems and methods for autonomous driving
TWI715904B (zh) 用於確定交通物件的處理優先順序的系統、方法和儲存媒體
TWI715898B (zh) 路口是否存在目標道路設施的判斷方法、系統、裝置及儲存媒體
AU2019203926B9 (en) Systems and methods for performing location-based actions
AU2018286610B2 (en) Systems and methods for determining driving action in autonomous driving
JP6602352B2 (ja) 自律走行車用の計画フィードバックに基づく決定改善システム
CN112325896B (zh) 导航方法、装置、智能行驶设备及存储介质
CN110546695A (zh) 用于交通灯的信号相位和定时的综合管理的方法、装置和计算机程序产品
AU2018229223A1 (en) Systems and methods for recommending a pick-up location
US11676485B2 (en) Systems and methods for determining traffic information of a region
CN111881713A (zh) 一种识别违停地点的方法、系统、装置及存储介质
US20230159052A1 (en) Method for processing behavior data, method for controlling autonomous vehicle, and autonomous vehicle
JP2023531004A (ja) ダイヤグラムの生成方法、ダイヤグラムの生成装置、電子設備及びコンピュータ読取可能な記憶媒体
CN103208180B (zh) 基于多智能体交互技术的智能交通调度系统及方法
CN110998686A (zh) 一种交通灯配时的系统和方法
WO2020019237A1 (en) Systems and methods for dispatching service providers
WO2020098079A1 (zh) 预测通行时长的方法和系统
CN111325986A (zh) 异常停车监测方法、装置、电子设备以及存储介质
US10907986B2 (en) User familiarization with a novel route for reducing cognitive load associated with navigation
CN110781412B (zh) 用于识别路网中孤岛区域的系统和方法
CN103745613A (zh) 缩微道路环境下缩微智能车的定位导航实施方法
US11047697B2 (en) User familiarization with a novel route for reducing cognitive load associated with navigation
US20240192018A1 (en) System and method for virtual lane generation
US20210088339A1 (en) Methods and systems for identifying ramp links of a road

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: 18944528

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: 18944528

Country of ref document: EP

Kind code of ref document: A1