Method and device for determining period duration of traffic light, electronic equipment and system

Abstract

The invention is suitable for the technical field of traffic light period mining, and provides a traffic light period duration determination method and device, electronic equipment and a system. The period duration determination method comprises the following steps: when a vehicle stops, receiving a traffic light image and vehicle position information collected by the vehicle; according to the vehicle position information, classifying the traffic light images to obtain a traffic light image group corresponding to each intersection, the traffic light image group comprising a plurality of traffic light images corresponding to the intersection; identifying traffic light information of each traffic light image in the target traffic light image group; and according to the information of each traffic light and the time information corresponding to each traffic light image, determining the period duration of the traffic light of the target intersection. According to the scheme, judgment is performed in combination with the traffic light information in the image and the corresponding time information, interference factors can be reduced, and the accuracy of determining the period duration of the traffic light is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of traffic light cycle mining, and in particular, relates to a method, device, electronic equipment and system for determining the cycle duration of a traffic light. Background Art

[0002] The design and optimization of traffic light cycle duration is a crucial part of urban traffic management. Mining the cycle duration of traffic lights is helpful for the construction of intelligent transportation, and can also alleviate the anxiety of users when waiting for red lights due to the unknown duration of red lights. The existing technology usually adopts the method of judging the cycle duration based on vehicle behavior. This method is based on vehicle behavior and contains many interference factors (such as vehicle failure, vehicle congestion, etc.), resulting in low accuracy. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and system for determining the cycle duration of a traffic light, which can solve the problem of low accuracy caused by cycle judgment based on vehicle behavior.

[0004] In a first aspect, an embodiment of the present application provides a method for determining a cycle duration of a traffic light, the method for determining a cycle duration comprising:

[0005] When the vehicle stops, receiving the traffic light image and vehicle position information collected by the vehicle;

[0006] Classifying the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, wherein the traffic light image group includes a plurality of traffic light images corresponding to the intersection;

[0007] identifying traffic light information of each traffic light image in the target traffic light image group;

[0008] The cycle duration of the traffic light at the target intersection is determined according to the time information corresponding to each traffic light information and each traffic light image.

[0009] In a possible implementation manner of the first aspect, the vehicle collects traffic light images and vehicle position information through a driving recorder installed on the vehicle, and the driving recorder adopts a unified time synchronization time.

[0010] In a possible implementation manner of the first aspect, the method for determining a cycle duration further includes:

[0011] Determine the switching time of the current traffic light at the target intersection according to the cycle length of the traffic light at the target intersection, the vehicle stopping time and the driving lane;

[0012] The switching time of the current traffic light at the target intersection is transmitted and displayed in the vehicle.

[0013] In a possible implementation manner of the first aspect, the traffic light images are classified according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, including:

[0014] Determine the vehicle position information as the shooting position information of the traffic light image;

[0015] The traffic light images whose shooting position information is less than a distance threshold are divided into a group to obtain a plurality of traffic image groups;

[0016] The traffic image group corresponding to each intersection is determined according to the shooting position information corresponding to the traffic image group.

[0017] In a possible implementation manner of the first aspect, the traffic light information includes traffic light position information and corresponding state information of the traffic light in the traffic light image; and determining the cycle duration of the traffic light at the target intersection according to each traffic light information and time information corresponding to each traffic light image includes:

[0018] According to the traffic light position information, the corresponding state information and the time information corresponding to each traffic light image of the traffic light in the traffic light image, the switching time of the corresponding state information of each type of traffic light is recorded;

[0019] According to the switching time, the cycle duration of each type of traffic light in the target intersection is determined, and the target intersection is the intersection corresponding to the target traffic light image group.

[0020] In a possible implementation of the first aspect, determining the cycle duration of each type of traffic light at the target intersection according to the switching time includes:

[0021] According to the switching time corresponding to each type of traffic light, the target cycle of each type of traffic light is calculated;

[0022] The cycle duration of each type of traffic light at the target intersection is determined based on the calculated target cycle of each type of traffic light display.

[0023] In a possible implementation manner of the first aspect, the calculating, according to the switching time corresponding to each type of traffic light, a target period for cyclic display of each type of traffic light includes:

[0024] Extract the switching time corresponding to each type of traffic light;

[0025] For any type of traffic lights, the time when the yellow light switches to the red light is determined in sequence as the first switching time, the time when the red light switches to the green light is determined as the second switching time, the time when the green light switches to the yellow light is determined as the third switching time, and the time when the next yellow light switches to the red light is determined as the fourth switching time;

[0026] The average duration of the total durations of all first switching times to fourth switching times within the target time period is determined as the target cycle duration of the traffic light of this type.

[0027] In a possible implementation manner of the first aspect, the method for determining the cycle duration further includes:

[0028] Determine the average value of the difference between all the second switching times and the first switching times within the target time period as the red light cycle length;

[0029] Determine the average value of the difference between all the third switching times and the second switching times within the target time period as the green light cycle length;

[0030] An average value of the differences between all fourth switching times and the third switching times within the target time period is determined as the yellow light cycle duration.

[0031] In a possible implementation of the first aspect, the target time period is divided according to the congestion situation of the driving environment; or the target time period is evenly divided according to the target duration; the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in different time periods are the same or different.

[0032] In a possible implementation manner of the first aspect, the method for determining the cycle duration further includes:

[0033] According to the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in each target time period of a day, the operating cycle regularity of each type of traffic light at the target intersection in each target time period is determined.

[0034] In a possible implementation manner of the first aspect, the traffic light information includes traffic light position information and corresponding state information of the traffic light in the traffic light image; and the traffic light information of each traffic light image in the identification target traffic light image group includes:

[0035] Each traffic light image is input into a target detection network, which outputs the position information and corresponding status information of each traffic light in the traffic light image; the target detection network is trained based on multiple sampled traffic light images.

[0036] In a second aspect, an embodiment of the present application provides a device for determining a cycle duration of a traffic light, the device for determining a cycle duration comprising:

[0037] A receiving module, used for receiving a traffic light image and vehicle position information collected by the vehicle when the vehicle stops;

[0038] A classification module, used for classifying the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, wherein the traffic light image group includes a plurality of traffic light images corresponding to the intersection;

[0039] A recognition module, used for recognizing traffic light information of each traffic light image in the target traffic light image group;

[0040] The first duration determination module is used to determine the cycle duration of the traffic light at the target intersection according to each traffic light information and the time information corresponding to each traffic light image.

[0041] In a possible implementation of the second aspect, when the above-mentioned cycle duration determination device receives the traffic light image and vehicle position information collected by the vehicle, it may be receiving the traffic light image and vehicle position information collected by a driving recorder installed on the vehicle, and the driving recorder adopts unified timing.

[0042] In a possible implementation manner of the second aspect, the apparatus for determining a cycle duration further includes:

[0043] A time determination module, used to determine the switching time of the current traffic light at the target intersection according to the cycle length of the traffic light at the target intersection, the vehicle stop time and the driving lane;

[0044] The transmission module is used to transmit the switching time of the current traffic light at the target intersection and display it in the vehicle.

[0045] In a possible implementation manner of the second aspect, the classification module includes:

[0046] A first determining unit, configured to determine the vehicle position information as the shooting position information of the traffic light image;

[0047] A first dividing unit is used to divide the traffic light images whose shooting position information is less than a distance threshold into one group to obtain a plurality of traffic image groups;

[0048] The second determining unit is used to determine the traffic image group corresponding to each intersection according to the shooting position information corresponding to the traffic image group.

[0049] In a possible implementation manner of the second aspect, the traffic light information includes traffic light position information and corresponding state information of the traffic light in the traffic light image; and the first duration determination module includes:

[0050] A first recording unit, configured to record a switching time of corresponding state information of each type of traffic light according to traffic light position information of the traffic light in the traffic light image, corresponding state information and time information corresponding to each traffic light image;

[0051] The third determining unit is used to determine the cycle duration of each type of traffic light in the target intersection according to the switching time, and the target intersection is the intersection corresponding to the target traffic light image group.

[0052] In a possible implementation manner of the second aspect, the third determining unit is configured to:

[0053] According to the switching time corresponding to each type of traffic light, the target cycle of each type of traffic light is calculated;

[0054] The cycle duration of each type of traffic light at the target intersection is determined based on the calculated target cycle of each type of traffic light display.

[0055] In a possible implementation manner of the second aspect, the third determining unit is further configured to:

[0056] Extract the switching time corresponding to each type of traffic light;

[0057] For any type of traffic lights, the time when the yellow light switches to the red light is determined in sequence as the first switching time, the time when the red light switches to the green light is determined as the second switching time, the time when the green light switches to the yellow light is determined as the third switching time, and the time when the next yellow light switches to the red light is determined as the fourth switching time;

[0058] The average duration of the total durations of all first switching times to fourth switching times within the target time period is determined as the target cycle duration of the traffic light of this type.

[0059] In a possible implementation manner of the second aspect, the apparatus for determining a cycle duration further includes:

[0060] A second duration determination module, used to determine the average value of the difference between all second switching times and the first switching time within the target time period as the red light cycle duration;

[0061] A third duration determination module, used to determine the average value of the difference between all third switching times and the second switching time within the target time period as the green light cycle duration;

[0062] The fourth duration determination module is used to determine the average value of the difference between all fourth switching times and the third switching times within the target time period as the yellow light cycle duration.

[0063] In a possible implementation of the second aspect, the target time period is divided according to the congestion situation of the driving environment; or the target time period is evenly divided according to the target duration; the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in different time periods are the same or different.

[0064] In a possible implementation manner of the second aspect, the apparatus for determining a cycle duration further includes:

[0065] The rule determination module is used to determine the operating cycle rule of each type of traffic light at the target intersection in each target time period according to the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in each target time period within a day.

[0066] In a possible implementation manner of the second aspect, the traffic light information includes traffic light position information and corresponding state information of the traffic light in the traffic light image, and the recognition module includes:

[0067] The detection unit is used to input each traffic light image into a target detection network, and the target detection network outputs the position information and corresponding state information of each traffic light in the traffic light image; the target detection network is trained based on multiple sampled traffic light images.

[0068] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned cycle duration determination method when executing the computer program.

[0069] In a fourth aspect, an embodiment of the present application provides a system for determining a cycle duration of a traffic light, the system comprising an electronic device and a vehicle, wherein the vehicle is equipped with a driving recorder;

[0070] An electronic device, configured to execute the method according to the first aspect;

[0071] The vehicle is used to collect traffic light images and vehicle position information at a target intersection through a driving recorder, and the target intersection is an intersection where the vehicle stops traveling.

[0072] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the method for determining the cycle duration as described above is implemented.

[0073] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the above-mentioned method for determining the period duration.

[0074] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0075] In an embodiment of the present application, when a vehicle stops, a traffic light image and vehicle position information collected by the vehicle are received. Secondly, the traffic light image is classified according to the vehicle position information to obtain a traffic light image group corresponding to each intersection. The cycle duration of the traffic light at the target intersection is determined by identifying the traffic light information of each traffic light image in the target traffic light image group and combining the time information corresponding to each traffic light image. By combining the traffic light information in the image and the corresponding time information for judgment, interference factors can be reduced and the accuracy of determining the traffic light cycle duration can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0077] Figure 1 It is a flowchart of a method for determining the cycle duration of a traffic light provided in an embodiment of the present application;

[0078] Figure 2 is a flow chart of a method for determining a cycle duration of a traffic light provided by another embodiment of the present application;

[0079] Figure 3 It is a structural schematic diagram of a device for determining the cycle duration of a traffic light provided in one embodiment of the present application;

[0080] Figure 4 It is a structural schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0081] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0082] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0083] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0084] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0085] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0086] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0087] It should be understood that the size of the serial numbers of the steps in this embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0088] Traffic lights are important infrastructure for controlling vehicle traffic, and they are also important for planning vehicle traffic. Existing methods for periodic mining based on user behavior in navigation maps contain many interference factors, such as vehicle failures, vehicle congestion, etc., and have low accuracy and large errors.

[0089] Therefore, in order to solve the above-mentioned problem of low accuracy caused by cycle judgment based on vehicle behavior, the present application proposes a method for determining the cycle duration of a traffic light. When a vehicle stops, a traffic light image and vehicle position information collected by the vehicle are received. Secondly, the traffic light image is classified according to the vehicle position information to obtain a traffic light image group corresponding to each intersection. The cycle duration of the traffic light at the target intersection is determined by identifying the traffic light information of each traffic light image in the target traffic light image group and combining the time information corresponding to each traffic light image. The judgment is made by combining the traffic light information in the image and the corresponding time information, which can reduce interference factors and improve the accuracy of determining the cycle duration of the traffic light.

[0090] The following describes in detail the method, device, electronic device, system, storage medium and computer program for determining the cycle duration of a traffic light provided in the present application with reference to the accompanying drawings.

[0091] Figure 1 A schematic flow chart of a method for determining a traffic light cycle duration provided in an embodiment of the present application is shown.

[0092] Step 101, when a vehicle stops, receiving a traffic light image and vehicle position information collected by the vehicle.

[0093] It should be noted that the method for determining the cycle duration of a traffic light in the embodiment of the present application can be executed by the device for determining the cycle duration of a traffic light in the embodiment of the present application. The device for determining the cycle duration of a traffic light in the embodiment of the present application can be configured in any electronic device to execute the method for determining the cycle duration of a traffic light in the embodiment of the present application. For example, the device for determining the cycle duration of a traffic light in the embodiment of the present application can be configured in a server to send the cycle duration of the traffic light at the target intersection to each vehicle passing through the target intersection after determining the cycle duration of the traffic light at the target intersection.

[0094] The traffic light image may refer to a traffic light image collected by a vehicle-mounted camera or other equipment.

[0095] The vehicle location information may refer to data on the current location of the vehicle, expressed in the form of coordinates or other geographic location information, such as the vehicle's GPS positioning information.

[0096] In the embodiment of the present application, when a vehicle approaches a target intersection and stops, the sensor or vehicle-mounted device in the system will detect a signal that the vehicle has stopped. Once the vehicle stops, the camera or other devices or other visual sensors mounted on the vehicle begin to collect images of traffic lights and use GPS or other positioning systems to obtain the current location information of the vehicle. After collecting the traffic light image and vehicle location information, the vehicle can send them to the electronic device, and the electronic device can receive the traffic light image and vehicle location information collected by the vehicle.

[0097] In one possible implementation, a vehicle can collect traffic light images and vehicle location information through a driving recorder installed on the vehicle. That is, when the vehicle stops, the driving recorder takes a traffic light image and obtains the GPS location information of the current traffic light image, and then transmits the traffic light image and GPS location information to an electronic device, such as uploading it to a cloud server.

[0098] Among them, the driving recorder adopts a unified time synchronization.

[0099] Step 102: classify the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection.

[0100] The traffic light image group includes a plurality of traffic light images corresponding to intersections.

[0101] Classifying the traffic light images according to the vehicle position information may refer to classifying the traffic light images at an intersection into one category, so as to facilitate the subsequent determination of the cycle duration of the traffic light at the intersection according to the traffic light images at the intersection.

[0102] The vehicle location information may refer to the GPS location of the driving recorder, that is, the longitude and latitude coordinates.

[0103] In an embodiment of the present application, the acquired GPS can be classified. Taking the GPS when the vehicle stops as the benchmark, all positions with a small difference from the GPS position can be classified into one category. Then, the collected traffic light images corresponding to the GPS position can be classified into one category to obtain a traffic light image group corresponding to each traffic light intersection.

[0104] In a possible implementation, traffic light images are classified according to vehicle position information to obtain a traffic light image group corresponding to each intersection, including:

[0105] Determine the vehicle position information as the shooting position information of the traffic light image;

[0106] The traffic light images whose shooting position information is less than a distance threshold are divided into a group to obtain a plurality of traffic image groups;

[0107] The traffic image group corresponding to each intersection is determined according to the shooting position information corresponding to the traffic image group.

[0108] In an embodiment of the present application, the vehicle position information can be directly associated with the traffic light image, and the vehicle position information can be determined as the shooting position information of the associated traffic light image, and then the traffic light image can be directly classified according to the shooting position information of the traffic light image.

[0109] Specifically, assuming that the position information when the vehicle stops is used as a reference, if the difference between the shooting position information of the traffic light image and the position information when the vehicle stops is less than a distance threshold, the traffic light image is divided into traffic light images of the intersection to obtain multiple traffic image groups, each traffic image group corresponding to an intersection.

[0110] Exemplarily, the distance threshold may be set to 20 meters, that is, all traffic light images with a GPS position deviation of no more than 20 meters may be classified into the same traffic image group.

[0111] It should be understood that different vehicles have different location information when they stop, so when receiving traffic light images uploaded by different vehicles, if the GPS position deviation between the vehicles does not exceed the preset deviation, it is considered that the multiple vehicles are located at the same intersection, and the traffic light images uploaded by them can be divided into the same traffic image group. The preset deviation can be set to 10 meters.

[0112] Step 103 : identifying traffic light information of each traffic light image in the target traffic light image group.

[0113] In the embodiment of the present application, the target traffic light image group corresponds to the target intersection, and the traffic lights in the traffic light images can be identified and relevant traffic light information can be extracted through computer vision technology.

[0114] Specifically, in the above step 102, a target traffic light image group is obtained, which includes multiple traffic light images of the target intersection. To identify the traffic light images in the target traffic group, the traffic lights in the traffic light images must first be identified. Once the traffic lights are successfully identified, the traffic light information can be extracted therefrom.

[0115] The traffic light information includes the traffic light position information and corresponding status information of the traffic light in the traffic light image. The traffic light position information is used to determine the category of the traffic light, and the corresponding status information is used to determine the color of the traffic light.

[0116] In a possible implementation manner, identifying traffic light information of each traffic light image in the target traffic light image group includes:

[0117] Input each traffic light image into the target detection network, and the target detection network outputs the position information and corresponding status information of each traffic light in the traffic light image;

[0118] Among them, the target detection network is trained based on multiple sampled traffic light images.

[0119] In the embodiment of the present application, before each traffic light image is input into the target detection network, each traffic light image may be preprocessed, that is, image size adjustment, denoising and other operations may be performed to improve the accuracy of subsequent recognition. After processing each input image, the target detection network outputs the location information and corresponding status information of each traffic light, where the location information is given in the form of a bounding box or coordinates, and the status information indicates the current status of the traffic light.

[0120] Step 104 , determining the cycle duration of the traffic light at the target intersection according to the information of each traffic light and the time information corresponding to each traffic light image.

[0121] Among them, the time information corresponding to the traffic light image may refer to the timestamp or time information when each traffic light image is captured, that is, the time when the traffic light image is collected. For example, a driving recorder is used to collect images. After the driving recorder collects the images, the images are transmitted to the cloud server in real time. The time information corresponding to each traffic light image is the time when the driving recorder collects the traffic light image.

[0122] The cycle duration of a traffic light may refer to the time required for the traffic light to pass through all states (red light, green light, yellow light) in a complete cycle.

[0123] In the embodiment of the present application, the switching moment of the traffic light state, i.e., the time point when the state changes from one state to another state, is first analyzed based on the time information corresponding to each traffic light information and each traffic light image. Then, the cycle duration is calculated, i.e., based on the state switching of the traffic light, the duration of each state is calculated, and the duration of a complete cycle of the entire traffic light is comprehensively calculated.

[0124] In a possible implementation, the traffic light information includes traffic light position information and corresponding state information of the traffic light in the traffic light image; and determining the cycle duration of the traffic light at the target intersection according to each traffic light information and the time information corresponding to each traffic light image includes:

[0125] According to the traffic light position information, the corresponding state information and the time information corresponding to each traffic light image of the traffic light in the traffic light image, the switching time of the corresponding state information of each type of traffic light is recorded;

[0126] According to the switching time, the cycle duration of each type of traffic light in the target intersection is determined, and the target intersection is the intersection corresponding to the target traffic light image group.

[0127] In an embodiment of the present application, the traffic lights at each intersection may include multiple types, such as a straight-ahead light, a left-turn light, or a right-turn light. Therefore, determining the cycle duration of the traffic lights at the target intersection includes determining the cycle duration of each type of traffic lights, i.e., the cycle duration of the straight-ahead light, the cycle duration of the left-turn light, and the cycle duration of the right-turn light.

[0128] Specifically, first, the category of the traffic light is determined based on the traffic light position information in the traffic light image, for example, the category of the traffic light is determined based on the image coordinates of the traffic light in the traffic light image. Then, based on the corresponding state information and the time information corresponding to each traffic light image, the switching time of the corresponding state information of the straight-ahead light, the left-turn light, and the right-turn light is recorded respectively, for example, the switching time from the green light to the yellow light, the switching time from the yellow light to the red light, and the switching time from the red light to the green light. By calculating based on the switching time, the cycle duration of each type of traffic light at the target intersection can be determined.

[0129] In a possible implementation, the cycle duration of each type of traffic light at the target intersection is determined according to the switching time, including:

[0130] According to the switching time corresponding to each type of traffic light, the target cycle of each type of traffic light is calculated;

[0131] The cycle duration of each type of traffic light at the target intersection is determined based on the calculated target cycle of each type of traffic light display.

[0132] For example, a cycle is straight-turn-left-straight. Assuming that the switching time corresponding to the straight-through light switching to the right turn light is the first time, the switching time corresponding to the right turn light switching to the left turn light is the second time, and the switching time corresponding to the left turn light switching to the straight-through light is the third time, then the target cycle of the straight-through light cyclic display can be obtained as: the time difference between the first time and the time when the left turn light switches to the straight-through light in the previous cycle, the target cycle of the right turn light cyclic display is the time difference between the second time and the first time, and the target cycle of the left turn light cyclic display is the time difference between the third time and the second time. Then, according to the corresponding time difference, the cycle length of each type of traffic light in the marked intersection can be determined.

[0133] In a possible implementation, according to the switching time corresponding to each type of traffic light, the target period of cyclic display of each type of traffic light is calculated, including:

[0134] Extract the switching time corresponding to each type of traffic light;

[0135] For any type of traffic lights, the time when the yellow light switches to the red light is determined in sequence as the first switching time, the time when the red light switches to the green light is determined as the second switching time, the time when the green light switches to the yellow light is determined as the third switching time, and the time when the next yellow light switches to the red light is determined as the fourth switching time;

[0136] The average duration of the total durations of all first switching times to fourth switching times within the target time period is determined as the target cycle duration of the traffic light of this type.

[0137] In the embodiment of the present application, the cycle duration of each type of traffic light can be determined by extracting the state switching time of each type of traffic light.

[0138] Specifically, taking the straight light as an example, when the straight light is identified to switch from yellow to red, the current time is recorded as the first switching time t1, when the red light is identified to switch from green, the current time is recorded as the second switching time t2, when the green light is identified to switch from yellow, the current time is recorded as the third switching time, and when the yellow light is identified to switch from red again, the current time is recorded as the fourth switching time t4. This is a cycle, and the cycle length is t4-t1.

[0139] And since the set duration of the cycle in different time periods may be different, for example, the morning rush hour and evening rush hour cycles are shorter, and other time cycles are longer, the average duration of the total duration of all first switching times to the fourth switching times in the target time period can be determined as the target cycle duration of this type of traffic light in the target time period.

[0140] In a possible implementation, the method for determining the cycle duration of a traffic light further includes:

[0141] Determine the average value of the difference between all the second switching times and the first switching times within the target time period as the red light cycle length;

[0142] Determine the average value of the difference between all the third switching times and the second switching times within the target time period as the green light cycle length;

[0143] An average value of the differences between all fourth switching times and the third switching times within the target time period is determined as the yellow light cycle duration.

[0144] Specifically, according to the above example, the red light cycle duration is the average value of all t2-t1 in the target time period, the green light cycle duration is the average value of all t3-t2 in the target time period, and the yellow light cycle duration is the average value of all t4-t3 in the target time period.

[0145] Exemplarily, assuming that the target time period includes n cycle durations, the target cycle duration within the target time period can be L=(L1+L2+L3+L4+…+Ln) / n, where L1, L2, L3…Ln are all corresponding values ​​of t4-t1 identified. Correspondingly, the red light cycle duration within the target time period can be Lr=(Lr1+Lr2+Lr3+Lr4+…+Lrn) / n, where Lr1, Lr2, Lr3…Lrn are all corresponding values ​​of t2-t1 identified. The green light cycle duration within the target time period can be Lg=(Lg1+Lg2+Lg3+Lg4+…+Lgn) / n, where Lg1, Lg2, Lg3…Lgn are all corresponding values ​​of t3-t2 identified. The duration of the yellow light cycle within the target time period may be Ly=(Ly1+Ly2+Ly3+Ly4+…+Lyn) / n, wherein Ly1, Ly2, Ly3…Lyn are all values ​​corresponding to the identified t4-t3.

[0146] In a possible implementation, the target time period is divided according to the congestion situation of the driving environment; or the target time period is evenly divided according to the target duration; the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in different time periods are the same or different.

[0147] In a possible implementation, the operating cycle regularity of each type of traffic light at the target intersection in each target time period is determined based on the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in each target time period of a day.

[0148] Exemplarily, a day may be divided into 24 time periods, and then the operating cycle rules of the red, green, and yellow lights of each type of traffic light in each time period may be determined.

[0149] In an embodiment of the present application, when a vehicle stops, a traffic light image and vehicle position information collected by the vehicle are received. Secondly, the traffic light image is classified according to the vehicle position information to obtain a traffic light image group corresponding to each intersection. The cycle duration of the traffic light at the target intersection is determined by identifying the traffic light information of each traffic light image in the target traffic light image group and combining the time information corresponding to each traffic light image. By combining the traffic light information in the image and the corresponding time information for judgment, interference factors can be reduced and the accuracy of determining the traffic light cycle duration can be improved.

[0150] Combine the following Figure 2 , the method for determining the cycle duration of a traffic light provided in an embodiment of the present application is further explained.

[0151] Figure 2 A schematic flow chart of a method for determining a traffic light cycle duration provided in another embodiment of the present application is shown.

[0152] like Figure 2 As shown, the method for determining the cycle duration of the traffic light comprises the following steps:

[0153] Step 201, when a vehicle stops, receiving a traffic light image and vehicle position information collected by the vehicle.

[0154] Step 202: classify the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection.

[0155] Step 203 : identifying traffic light information of each traffic light image in the target traffic light image group.

[0156] Step 204 , determining the cycle duration of the traffic light at the target intersection according to the information of each traffic light and the time information corresponding to each traffic light image.

[0157] The specific implementation process and principle of the above steps 201-204 can refer to the detailed description of the above embodiment, which will not be repeated here.

[0158] Step 205, determining the switching time of the current traffic light at the target intersection according to the cycle duration of the traffic light at the target intersection, the vehicle stopping time and the driving lane.

[0159] In the embodiment of the present application, when the cycle duration of each type of traffic light at the target intersection is obtained, the cycle duration applicable to the vehicle can be determined according to the cycle duration of the traffic light at the target intersection and the lane in which the vehicle is traveling, and then the switching time of the current traffic light at the target intersection can be determined according to the time when the vehicle stops. For example, if the current traffic light is red, the switching time when the current red light turns green can be determined.

[0160] Step 206, the switching time of the current traffic light at the target intersection is transmitted and displayed in the vehicle.

[0161] In an embodiment of the present application, the cloud server can transmit the current traffic light switching time to the navigation software or other software installed in the vehicle, and display the current traffic light switching time in the interface.

[0162] In an embodiment of the present application, the switching time of the current traffic light at the target intersection can be determined based on the cycle duration of the traffic light at the target intersection, the vehicle's stop time, and the driving lane. When the vehicle passes the target intersection, the current traffic light switching time of the target intersection can be displayed in the vehicle to alleviate the user's anxiety caused by the unknown duration of the red light when waiting for the red light.

[0163] Corresponding to the method for determining the cycle duration of a traffic light in the above embodiment, Figure 3The following is a schematic diagram showing the structure of a traffic light cycle duration determination device provided by an embodiment of the present application. For ease of description, only the parts related to the embodiment of the present application are shown.

[0164] See also Figure 3 , the cycle duration determining device 300 comprises:

[0165] The receiving module 301 is used to receive the traffic light image and vehicle position information collected by the vehicle when the vehicle stops;

[0166] A classification module 302, for classifying the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, wherein the traffic light image group includes a plurality of traffic light images corresponding to the intersection;

[0167] An identification module 303, used to identify traffic light information of each traffic light image in the target traffic light image group;

[0168] The first duration determination module 304 is used to determine the cycle duration of the traffic light at the target intersection according to each traffic light information and the time information corresponding to each traffic light image.

[0169] In an embodiment of the present application, when the above-mentioned cycle duration determination device 300 receives the traffic light image and vehicle position information collected by the vehicle, it can be received by a driving recorder installed on the vehicle, and the driving recorder adopts unified timing.

[0170] In the embodiment of the present application, the cycle duration determination device 300 further includes:

[0171] A time determination module, used to determine the switching time of the current traffic light at the target intersection according to the cycle length of the traffic light at the target intersection, the vehicle stop time and the driving lane;

[0172] The transmission module is used to transmit the switching time of the current traffic light at the target intersection and display it in the vehicle.

[0173] In the embodiment of the present application, the classification module 302 includes:

[0174] A first determining unit, configured to determine the vehicle position information as the shooting position information of the traffic light image;

[0175] A first dividing unit is used to divide the traffic light images whose shooting position information is less than a distance threshold into one group to obtain a plurality of traffic image groups;

[0176] The second determining unit is used to determine the traffic image group corresponding to each intersection according to the shooting position information corresponding to the traffic image group.

[0177] In the embodiment of the present application, the traffic light information includes the traffic light position information and corresponding state information of the traffic light in the traffic light image; the first duration determination module 304 includes:

[0178] A first recording unit, configured to record a switching time of corresponding state information of each type of traffic light according to traffic light position information of the traffic light in the traffic light image, corresponding state information and time information corresponding to each traffic light image;

[0179] The third determining unit is used to determine the cycle duration of each type of traffic light in the target intersection according to the switching time, and the target intersection is the intersection corresponding to the target traffic light image group.

[0180] In the embodiment of the present application, the third determining unit is used to:

[0181] According to the switching time corresponding to each type of traffic light, the target cycle of each type of traffic light is calculated;

[0182] The cycle duration of each type of traffic light at the target intersection is determined based on the calculated target cycle of each type of traffic light display.

[0183] In the embodiment of the present application, the third determining unit is further configured to:

[0184] Extract the switching time corresponding to each type of traffic light;

[0185] For any type of traffic lights, the time when the yellow light switches to the red light is determined in sequence as the first switching time, the time when the red light switches to the green light is determined as the second switching time, the time when the green light switches to the yellow light is determined as the third switching time, and the time when the next yellow light switches to the red light is determined as the fourth switching time;

[0186] The average duration of the total durations of all first switching times to fourth switching times within the target time period is determined as the target cycle duration of the traffic light of this type.

[0187] In the embodiment of the present application, the cycle duration determination device 300 further includes:

[0188] A second duration determination module, used to determine the average value of the difference between all second switching times and the first switching time within the target time period as the red light cycle duration;

[0189] A third duration determination module, used to determine the average value of the difference between all third switching times and the second switching time within the target time period as the green light cycle duration;

[0190] The fourth duration determination module is used to determine the average value of the difference between all fourth switching times and the third switching times within the target time period as the yellow light cycle duration.

[0191] In an embodiment of the present application, the above-mentioned target time period is divided according to the congestion situation of the driving environment; or the above-mentioned target time period is evenly divided according to the target duration; the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in different time periods are the same or different.

[0192] In the embodiment of the present application, the cycle duration determination device 300 further includes:

[0193] The rule determination module is used to determine the operating cycle rule of each type of traffic light at the target intersection in each target time period according to the target cycle duration, red light cycle duration, green light cycle duration and yellow light cycle duration in each target time period within a day.

[0194] In the embodiment of the present application, the traffic light information includes the traffic light position information and corresponding state information of the traffic light in the traffic light image, and the recognition module 303 includes:

[0195] The detection unit is used to input each traffic light image into a target detection network, and the target detection network outputs the position information and corresponding state information of each traffic light in the traffic light image; the target detection network is trained based on multiple sampled traffic light images.

[0196] In actual use, the device for determining the cycle duration of a traffic light provided in the embodiment of the present application can be configured in any electronic device to execute the aforementioned method for determining the cycle duration of a traffic light.

[0197] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0198] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0199] In a possible implementation, the embodiment of the present application further provides a traffic light cycle duration determination system, the cycle duration determination system comprising an electronic device and a vehicle, the vehicle being equipped with a driving recorder;

[0200] An electronic device, used to execute the method in the above method embodiment;

[0201] The vehicle is used to collect traffic light images and vehicle position information at a target intersection through a driving recorder, and the target intersection is an intersection where the vehicle stops traveling.

[0202] It should be understood that the above system may include multiple vehicles, that is, the traffic light images and vehicle position information of the target intersection are collected through the driving recorders of multiple vehicles.

[0203] See also Figure 4 , shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present application, such as Figure 4 As shown, the electronic device 400 of this embodiment includes: at least one processor 410 ( Figure 4 Only one is shown in the figure), a memory 420 and a computer program 421 stored in the memory 420 and executable on the at least one processor 410, wherein the processor 410 implements the steps in the above-mentioned traffic light cycle duration determination method embodiment when executing the computer program 421.

[0204] It should be noted that the electronic device 400 may refer to a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The electronic device may include, but is not limited to, a processor 410 and a memory 420. Those skilled in the art will understand that Figure 4 This is merely an example of the electronic device 400 and does not constitute a limitation on the electronic device 400 . The electronic device 400 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0205] The processor 410 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0206] In some embodiments, the memory 420 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 420 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 400. Further, the memory 420 may also include both an internal storage unit of the electronic device 400 and an external storage device. The memory 420 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as the program code of the computer program, etc. The memory 420 may also be used to temporarily store data that has been output or is to be output.

[0207] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0208] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0209] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0210] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0212] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0213] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be completed through a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing.

[0214] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above-mentioned embodiments, a person skilled in the art should understand that the technical solutions described in the above-mentioned embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for determining the cycle duration of a traffic light, It is characterized in that The cycle duration determination method comprises: When the vehicle stops, receiving the traffic light image and vehicle position information collected by the vehicle; Classifying the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, wherein the traffic light image group includes a plurality of traffic light images corresponding to the intersection; identifying traffic light information of each traffic light image in the target traffic light image group; The cycle duration of the traffic light at the target intersection is determined according to the time information corresponding to each of the traffic light information and each of the traffic light images.

2. The method for determining the cycle duration according to claim 1, It is characterized in that The vehicle collects the traffic light image and the vehicle position information through a driving recorder installed on the vehicle, and the driving recorder adopts a unified time synchronization time.

3. The method for determining the cycle duration as claimed in claim 2, It is characterized in that Also includes: Determine the switching time of the current traffic light at the target intersection according to the cycle length of the traffic light at the target intersection, the stopping time of the vehicle, and the driving lane; The switching time of the current traffic light at the target intersection is transmitted and displayed in the vehicle.

4. The method for determining the cycle duration according to claim 1, It is characterized in that The method of classifying the traffic light images according to the vehicle position information to obtain a traffic light image group corresponding to each intersection includes: Determining the vehicle position information as the shooting position information of the traffic light image; Dividing the traffic light images whose shooting position information is less than a distance threshold into one group to obtain a plurality of traffic image groups; The traffic image group corresponding to each intersection is determined according to the shooting position information corresponding to the traffic image group.

5. The method for determining the cycle duration according to claim 1, It is characterized in that The traffic light information includes traffic light position information and corresponding status information of the traffic light in the traffic light image; The determining, according to each of the traffic light information and the time information corresponding to each of the traffic light images, the cycle duration of the traffic light at the target intersection comprises: According to the traffic light position information of the traffic light in the traffic light image, the corresponding state information and the time information corresponding to each of the traffic light images, recording the switching time of the corresponding state information of each type of traffic light; According to the switching time, the cycle duration of each type of traffic light in the target intersection is determined, and the target intersection is the intersection corresponding to the target traffic light image group.

6. The method for determining the cycle duration as claimed in claim 5, It is characterized in that Determining the cycle duration of each type of traffic light at the target intersection according to the switching time includes: Calculate the target period of cyclic display of each type of traffic light according to the switching time corresponding to each type of traffic light; The cycle duration of each type of traffic light at the target intersection is determined according to the calculated target cycle for the cyclic display of each type of traffic light.

7. The method for determining the cycle duration according to claim 6, It is characterized in that The calculating, according to the switching time corresponding to each type of traffic light, a target period for cyclic display of each type of traffic light, comprises: Extracting the switching time corresponding to each type of traffic light; For any type of traffic lights, the time when the yellow light switches to the red light is determined in sequence as the first switching time, the time when the red light switches to the green light is determined as the second switching time, the time when the green light switches to the yellow light is determined as the third switching time, and the time when the next yellow light switches to the red light is determined as the fourth switching time; The average duration of the total durations of all first switching times to fourth switching times within the target time period is determined as the target cycle duration of the traffic light of this type.

8. The method for determining the cycle duration according to claim 7, It is characterized in that Also includes: Determine the average value of the difference between all the second switching times and the first switching times within the target time period as the red light cycle length; Determine the average value of the difference between all the third switching times and the second switching times within the target time period as the green light cycle length; An average value of the differences between all fourth switching times and the third switching times within the target time period is determined as the yellow light cycle duration.

9. The method for determining the cycle duration as claimed in claim 8, It is characterized in that The target time period is divided according to the congestion situation of the driving environment; or the target time period is evenly divided according to the target duration; the target cycle duration, the red light cycle duration, the green light cycle duration and the yellow light cycle duration in different time periods are the same or different.

10. The method for determining the cycle duration according to claim 9, It is characterized in that Also includes: According to the target cycle duration, the red light cycle duration, the green light cycle duration and the yellow light cycle duration in each target time period within a day, the operating cycle regularity of each type of traffic light at the target intersection in each target time period is determined.

11. The method for determining the cycle duration according to claim 1, It is characterized in that The traffic light information includes traffic light position information and corresponding status information of the traffic light in the traffic light image; The identifying traffic light information of each traffic light image in the target traffic light image group includes: Input each of the traffic light images into a target detection network, and the target detection network outputs the position information and corresponding status information of each traffic light in the traffic light image; The target detection network is trained based on a plurality of sampled traffic light images.

12. A device for determining the cycle duration of a traffic light, It is characterized in that The cycle duration determining device comprises: A receiving module, used for receiving a traffic light image and vehicle position information collected by the vehicle when the vehicle stops; A classification module, configured to classify the traffic light image according to the vehicle position information to obtain a traffic light image group corresponding to each intersection, wherein the traffic light image group includes a plurality of traffic light images corresponding to the intersection; A recognition module, used for recognizing traffic light information of each traffic light image in the target traffic light image group; The first duration determination module is used to determine the cycle duration of the traffic light at the target intersection according to each of the traffic light information and the time information corresponding to each of the traffic light images.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 11 is implemented.

14. A system for determining the cycle duration of a traffic light, It is characterized in that The cycle duration determination system includes an electronic device and a vehicle, wherein the vehicle is equipped with a driving recorder; The electronic device is used to perform the method according to any one of claims 1 to 11; The vehicle is used to collect traffic light images and vehicle position information at a target intersection through a driving recorder, and the target intersection is an intersection where the vehicle stops traveling.

15. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images