CN114842654A

CN114842654A - Traffic signal lamp control method and device, electronic equipment and storage medium

Info

Publication number: CN114842654A
Application number: CN202210443705.5A
Authority: CN
Inventors: 刘瀛; 卢凌飞
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2022-04-25
Filing date: 2022-04-25
Publication date: 2022-08-02
Anticipated expiration: 2042-04-25
Also published as: CN114842654B

Abstract

The disclosure provides a traffic signal lamp control method and device, electronic equipment and a storage medium, and relates to the technical field of intelligent traffic. The method comprises the following steps: receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network; determining the passing time length of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval; and controlling the display time length of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time length of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched. The traffic flow information and the pedestrian information can be rapidly combined and judged, and the problem of traffic signal lamp switching between the traffic road and the pedestrian road is rapidly solved.

Description

Traffic signal lamp control method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of intelligent traffic technologies, and in particular, to a traffic signal lamp control method and apparatus, an electronic device, and a storage medium.

Background

At present, the domestic traffic signal lamp control method mainly comprises a timing distribution mode, a monitoring room control mode and an induction control mode.

The timing distribution mode is to control traffic signals according to a preset timing scheme, which is also called periodic control, and is suitable for traffic conditions with a relatively regular traffic flow change, but when the traffic flow change has large fluctuation, traffic guidance blind spots occur, and the flexibility is poor.

The control mode of the monitoring room is that real-time traffic conditions of the intersection are transmitted to the monitoring room through camera video equipment of each phase, and the monitoring room is manually regulated and controlled according to the real-time traffic conditions, so that the flexibility is higher, but continuous regulation and control are required manually, and the labor consumption is higher.

The induction type control mode is an induction type control mode that a vehicle detector is arranged on an intersection entrance road, a control signal can be changed at any time along with traffic flow information detected by the vehicle detector, and a pedestrian button signal when a pedestrian crosses the street is also an induction type control mode.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure provides a traffic signal lamp control method, device, electronic device, and storage medium, which at least to some extent overcome the problem that traffic signal lamps between a traffic road and a pedestrian road cannot be switched quickly by determining traffic flow information and pedestrian information in a combination manner in the related art.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to an aspect of the present disclosure, there is provided a traffic signal control method including: receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network; determining the passing time length of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval; and controlling the display time length of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time length of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

In one embodiment of the present disclosure, determining the passing time of the traffic road at the time of the next round of traffic signal light switching according to the video image data of the traffic road in the traffic signal light switching time interval includes: inputting video image data of a traffic road in a traffic signal lamp switching time interval into a pre-trained vehicle recognition model, and outputting the number of vehicles of different vehicle types on the traffic road; and determining the passing time of the traffic road when the traffic signal lamps of the next round are switched according to the number of vehicles of different vehicle types on the traffic road.

In one embodiment of the present disclosure, after determining the passing time of the traffic road at the time of the next round of traffic signal lamp switching according to the number of vehicles of different vehicle types on the traffic road, the method further includes: and correcting the passing time length of the vehicle road when the next round of traffic signal lamp is switched by utilizing the display time length of the traffic signal lamps at the adjacent intersections.

In one embodiment of the present disclosure, determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval includes: inputting video image data of pedestrian roads in a traffic signal lamp switching time interval into a pre-trained age identification model, and outputting the number of pedestrians in different age ranges on the pedestrian roads; and determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the sidewalk road.

In one embodiment of the present disclosure, after determining the passage time of the pedestrian road at the time of the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the pedestrian road, the method further includes: inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained behavior recognition model, and outputting the number of pedestrians meeting preset behaviors on the pedestrian road; and correcting the passing time of the pedestrian road when the traffic signal lamp is switched in the next round according to the number of the pedestrians meeting the preset behavior on the sidewalk road.

In one embodiment of the present disclosure, after determining the passage time of the pedestrian road at the time of the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the pedestrian road, the method further includes: inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained face recognition model, and outputting identity information of one or more pedestrians on the pedestrian road; judging whether the pedestrian belonging to the target group exists on the sidewalk according to the identity information of one or more pedestrians on the sidewalk and a pre-constructed target group information base; and when the pedestrian belonging to the target group exists on the sidewalk, correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching.

In one embodiment of the present disclosure, the video image data includes: the system comprises a first camera and a second camera which are arranged on two sides of a road, wherein the first camera is used for collecting video image data in a first traffic direction of the road, and the second camera is used for collecting video image data in a second traffic direction of the road; the method further comprises the following steps: determining the maximum passing time length in the first passing time length and the second passing time length as the passing time length of the road, wherein the first passing time length is the passing time length of the road determined according to the video image data collected by the first camera, and the second passing time length is the passing time length of the road determined according to the video image data collected by the second camera.

In accordance with another aspect of the present disclosure, there is provided a traffic signal control system including: the system comprises a cloud platform server, a 5G network, cameras, traffic signal lamps and traffic signal lamp control modules, wherein the cameras, the traffic signal lamps and the traffic signal lamp control modules are installed on two sides of a vehicle road and a pedestrian road; the camera is used for acquiring video image data of a vehicle road and/or a pedestrian road and transmitting the video image data to the cloud platform server through a 5G network; the cloud platform server is used for determining the passing time of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval, and transmitting the passing time to the corresponding traffic signal lamp control module through a 5G network; the traffic signal lamp control module is used for controlling the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the traffic duration of the vehicle road and/or the pedestrian road issued by the cloud platform server.

In one embodiment of the present disclosure, there is provided a traffic signal control apparatus including: the data receiving module is used for receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network; the traffic road duration determining module is used for determining the traffic duration of the traffic road during the switching of the next round of traffic signal lamps according to the video image data of the traffic road in the traffic signal lamp switching time interval; the pedestrian road duration determining module is used for determining the passing duration of the pedestrian road during the switching of the next round of traffic signal lamps according to the video image data of the pedestrian road in the traffic signal lamp switching time interval; and the traffic signal lamp control module is used for controlling the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing duration of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

According to still another aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the traffic signal control method described above via execution of the executable instructions.

According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the traffic signal control method described above.

The embodiment of the disclosure provides a traffic signal lamp control method, a traffic signal lamp control device, electronic equipment and a storage medium, and the method comprises the steps of receiving video image data of a traffic road and/or a pedestrian road uploaded by a 5G network; determining the passing time length of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval; and controlling the display time length of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time length of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched. The traffic flow information and the pedestrian information can be rapidly combined and judged, and the problem of traffic signal lamp switching between the traffic road and the pedestrian road is rapidly solved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

FIG. 1 is a schematic diagram illustrating a traffic signal control system according to one embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating a method for controlling a traffic signal in an embodiment of the present disclosure;

FIG. 3 is a flow chart illustrating an embodiment of a traffic light control method according to the disclosed embodiment;

FIG. 4 is a flow chart illustrating a specific example of a traffic signal control method in accordance with an embodiment of the present disclosure;

FIG. 5 is a flow chart illustrating an exemplary embodiment of a traffic light control method according to an embodiment of the disclosure;

FIG. 6 is a schematic diagram of a traffic signal control apparatus according to an embodiment of the disclosure;

FIG. 7 is a schematic diagram illustrating a traffic signal control system in an embodiment of the present disclosure;

fig. 8 shows a flow chart of a cloud platform server controlling traffic lights in an embodiment of the present disclosure;

FIG. 9 illustrates an example of a word-road in an embodiment of the disclosure;

FIG. 10 illustrates an example of a T-way in an embodiment of the present disclosure;

fig. 11 shows a block diagram of an electronic device in an embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

For ease of understanding, the following first explains several terms to which the disclosure relates:

5G: 5th Generation Mobile Communication Technology, fifth Generation, Mobile Communication Technology.

5G network: 5G Network, fifth generation mobile communication Network.

CNN: convolutional Neural Networks.

Fig. 1 shows a schematic diagram of an exemplary system architecture of a traffic signal control method or a traffic signal control apparatus to which an embodiment of the present disclosure may be applied.

As shown in fig. 1, the system architecture 100 may include a cloud platform server 101, a 5G network 102, cameras 103 installed on both sides of a traffic road and a pedestrian road, traffic lights 104, a traffic light control module 105, and a demographic information database 106 connected to the cloud platform server 101.

The cloud platform server 101 is used for determining the passing time of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; and determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval, and transmitting the passing time to the corresponding traffic signal lamp control module through the 5G network.

The cloud platform server 101 may be a server providing various services, and may perform processing such as analysis on data such as received images, and feed back a processing result to the traffic signal lamp control module 105 in combination with information in the demographic information database 106 (including handicapped person information).

Optionally, the server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like.

The 5G network 102 is a medium used to provide communication links between the platform server 101 and the cameras 103 and traffic light control module 105, respectively.

The camera 103 is used for collecting video image data of a vehicle road and/or a pedestrian road and transmitting the video image data to the cloud platform server through the 5G network.

The traffic signal lamp control module 105 is configured to control the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the traffic duration of the vehicle road and/or the pedestrian road sent by the cloud platform server.

Those skilled in the art will appreciate that the number of traffic light control modules, cameras, traffic lights, 5G networks, and servers in fig. 1 is merely illustrative, and that any number of traffic light control modules, cameras, traffic lights, 5G networks, and servers may be provided, as desired. The embodiments of the present disclosure are not limited thereto.

The present exemplary embodiment will be described in detail below with reference to the drawings and examples.

The embodiment of the disclosure provides a traffic signal lamp control method, which can be executed by any electronic device with computing processing capability.

Fig. 2 shows a flowchart of a traffic light control method in an embodiment of the present disclosure, and as shown in fig. 2, the traffic light control method provided in the embodiment of the present disclosure includes the following steps:

and S202, receiving the video image data of the vehicle road and/or the pedestrian road uploaded by the 5G network.

The driving road may be a road width on which various vehicles travel in a mixed manner within the same road surface width, and is also referred to as a driving road. The pedestrian road can be a pedestrian crossing for people to pass through. The video image data may be a continuous sequence of images, consisting of a set of consecutive images.

In one embodiment, all video image data collected by the high-definition camera on the vehicle road and/or the sidewalk are uploaded to the cloud platform server through the 5G network.

In one embodiment, video image data collected by a high-definition camera on a vehicle road and/or a sidewalk route is uploaded to a cloud platform server through a 5G network in a traffic signal lamp switching time interval.

And S204, determining the passing time of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval.

It should be noted that the traffic signal switching time interval may be a time interval between two turns of traffic signal switching, for example, in a traffic signal composed of a red light, a yellow light, and a green light, the traffic signal switching time interval is a time period displayed by the yellow light; in the new national standard traffic lights, the switching time interval of the traffic lights is the time period of red light and/or green light stroboscopic display.

In one embodiment, the cloud platform server determines the passing time of the traffic road at the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval.

And S206, determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval.

In one embodiment, the cloud platform server determines the passing time of the pedestrian road at the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval.

And S208, controlling the display time of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time of the vehicle road and/or the pedestrian road during the switching of the traffic signal lamp.

For example, the cloud platform server sends the determined traffic time length of the traffic road of 30 seconds and the determined traffic time length of the pedestrian road of 20 seconds to the traffic signal lamp control module when the traffic signal lamps are switched, and the traffic signal lamp control module controls the traffic green lamp time length to be 30 seconds and the pedestrian road green lamp time length to be 20 seconds.

In specific implementation, the method utilizes the strong computing capacity of the cloud platform server to combine and judge the traffic flow information and the pedestrian information, can quickly determine the passing time of the traffic road and/or the pedestrian road, and transmits the calculated passing time by combining the low delay and the high speed of the 5G network, so as to control the display time of the corresponding traffic signal lamp, and can quickly solve the problem of traffic signal lamp switching between the traffic road and the pedestrian road.

In an embodiment of the present disclosure, as shown in fig. 3, the traffic signal lamp control method provided in the embodiment of the present disclosure may determine the passing time length of the traffic road when the traffic signal lamp is switched in the next round, and may determine the passing time length of the traffic road more accurately by the following steps:

s302, inputting video image data of a traffic road in a traffic signal lamp switching time interval into a pre-trained vehicle recognition model, and outputting the number of vehicles of different vehicle types on the traffic road;

s304, determining the passing time of the vehicle road when the traffic signal lamp of the next round is switched according to the number of vehicles of different vehicle types on the vehicle road.

In one embodiment, after determining the passing time of the traffic light on the road at the time of the next turn of traffic light switching according to the number of vehicles of different vehicle types on the road, the traffic light control method may further include:

and S306, correcting the passing time of the vehicle road when the next round of traffic signal lamp is switched by using the display time of the traffic signal lamps of the adjacent intersections.

In specific implementation, the time length displayed by the traffic signal lamps of the adjacent intersections can be used for more reasonably correcting the passing time length of the vehicle-driving road, so that the volume rate of road vehicles at the intersection accessories is reduced.

In an embodiment of the present disclosure, as shown in fig. 4, the traffic signal lamp control method provided in the embodiment of the present disclosure may determine the passing time of the pedestrian road when the next round of traffic signal lamp is switched by the following steps, so that the passing time of the pedestrian road can be determined more accurately:

s402, inputting video image data of pedestrian roads in a traffic signal lamp switching time interval into a pre-trained age identification model, and outputting the number of pedestrians in different age ranges on the pedestrian roads;

s404, determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the sidewalk road.

For example, the pedestrian age range is divided into three groups of 1-12 years old, 12-60 years old and over 60 years old, and different passage time lengths are set for the three groups of age groups respectively, so that the pedestrian road passage time length determination is more humanized.

In one embodiment, after determining the passing time of the pedestrian road at the next round of traffic light switching according to the number of pedestrians in different age ranges on the pedestrian road, the traffic light control method may further include:

s406, inputting video image data of the pedestrian road in the traffic signal lamp switching time interval into a pre-trained behavior recognition model, and outputting the number of pedestrians meeting preset behaviors on the pedestrian road;

and S408, correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians meeting the preset behaviors on the pedestrian road.

In one embodiment, after determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the sidewalk, the traffic signal lamp control method may further correct the passing time of the pedestrian road during the next round of traffic signal lamp switching by the following steps, so that the passing time of the pedestrian road can be determined more humanized:

s410, inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained face recognition model, and outputting identity information of one or more pedestrians on the pedestrian road;

s412, judging whether the pedestrian belonging to the target group exists on the sidewalk according to the identity information of one or more pedestrians on the sidewalk and a pre-constructed target group information base;

and S414, when pedestrians belonging to the target group exist on the sidewalk, correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching.

For example, the pre-constructed target group information base comprises identity information of disabled persons, and when the video image data comprises the disabled persons, the green light passing time of the pedestrian road can be prolonged.

In specific implementation, the method can perform special humanized care on the target group by increasing the passing time by using the pre-constructed target group information base.

In an embodiment of the present disclosure, as shown in fig. 5, in a traffic signal light control method provided in an embodiment of the present disclosure, video image data includes: the method comprises the following steps that video image data collected by a first camera and a second camera which are arranged on two sides of a road are collected, the first camera collects video image data in a first traffic direction of the road, and the second camera collects video image data in a second traffic direction of the road; the traffic signal lamp control method can also determine the passing time of the road through the following steps:

s502, determining the maximum passing time length in the first passing time length and the second passing time length as the passing time length of the road, wherein the first passing time length is the passing time length of the road determined according to the video image data collected by the first camera, and the second passing time length is the passing time length of the road determined according to the video image data collected by the second camera.

In one example, a first camera and a second camera are respectively arranged in the east-west direction of a traffic road of the east-west bidirectional lane, the first camera collects video data of the traffic road with the traffic direction from east to west to obtain a first passing time length of 30 seconds, the second camera collects video data of the traffic road with the traffic direction from west to east to obtain a second passing time length of 50 seconds, and then the 50 seconds are determined as the passing time length of the traffic road.

In specific implementation, the method calculates the passing time lengths of two directions of a two-way lane or a two-way sidewalk, determines the maximum passing time length as the passing time length of the road, and can ensure that vehicles or people in each passing direction can pass through.

Based on the same inventive concept, the embodiment of the present disclosure further provides a traffic signal lamp control device, as described in the following embodiments. Because the principle of the embodiment of the apparatus for solving the problem is similar to that of the embodiment of the method, the embodiment of the apparatus can be implemented by referring to the implementation of the embodiment of the method, and repeated details are not described again.

Fig. 6 shows a schematic diagram of a traffic signal lamp control device in an embodiment of the present disclosure, and as shown in fig. 6, the device includes: the system comprises a data receiving module 601, a driving road time length determining module 602, a pedestrian road time length determining module 603, a traffic light control module 604, a first time length correcting module 605, a second time length correcting module 606, a third time length correcting module 607 and a maximum time length determining module 608.

The data receiving module 601 is configured to receive video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network; a driving road duration determining module 602, configured to determine a passing duration of a driving road during switching of a next round of traffic signal lamps according to video image data of the driving road in a traffic signal lamp switching time interval; the pedestrian road duration determining module 603 is configured to determine a passing duration of a pedestrian road during switching of a next round of traffic signal lamps according to video image data of the pedestrian road within a traffic signal lamp switching time interval; the traffic signal lamp control module 604 is configured to control the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the traffic duration of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

In one embodiment, the driving road duration determining module is further configured to: inputting video image data of a traffic road in a traffic signal lamp switching time interval into a pre-trained vehicle identification model, and outputting the number of vehicles of different vehicle types on the traffic road; and determining the passing time of the traffic road when the traffic signal lamp of the next round is switched according to the number of vehicles of different vehicle types on the traffic road.

In one embodiment, the traffic signal control apparatus may further include a first duration correction module 605: the method is used for correcting the passing time of the vehicle road when the next round of traffic signal lamp is switched by utilizing the display time of the traffic signal lamps of the adjacent intersections.

In one embodiment, the pedestrian road duration determining module is further configured to: inputting video image data of pedestrian roads in a traffic signal lamp switching time interval into a pre-trained age identification model, and outputting the number of pedestrians in different age ranges on the pedestrian roads; and determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the sidewalk road.

In one embodiment, the traffic signal control apparatus may further include a second duration modification module 606: the system comprises a traffic signal lamp switching time interval input module, a behavior recognition module and a pedestrian number output module, wherein the traffic signal lamp switching time interval input module is used for inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained behavior recognition model and outputting the pedestrian number meeting preset behaviors on the pedestrian road; and correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians meeting the preset behaviors on the sidewalk road.

In one embodiment, the traffic signal control apparatus may further include a third duration modification module 607: the system comprises a face recognition model, a traffic signal lamp switching time interval and a pedestrian road switching time interval, wherein the face recognition model is used for inputting video image data of the pedestrian road in the traffic signal lamp switching time interval into the pre-trained face recognition model and outputting identity information of one or more pedestrians on the pedestrian road; judging whether pedestrians belonging to a target group exist on the sidewalk according to the identity information of one or more pedestrians on the sidewalk and a pre-constructed target group information base; and when pedestrians belonging to the target group exist on the sidewalk, correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching.

In one embodiment, the video image data includes: the method comprises the following steps that video image data collected by a first camera and a second camera which are arranged on two sides of a road are collected, the first camera collects video image data in a first traffic direction of the road, and the second camera collects video image data in a second traffic direction of the road; the traffic signal control apparatus may further include a maximum duration determination module 608: the device is used for determining the maximum passing time length in the first passing time length and the second passing time length as the passing time length of the road, wherein the first passing time length is the road passing time length determined according to the video image data collected by the first camera, and the second passing time length is the road passing time length determined according to the video image data collected by the second camera.

Fig. 7 is a schematic diagram of a traffic signal light control system in an embodiment of the present disclosure, and as shown in fig. 7, the traffic signal light control system provided in the embodiment of the present disclosure may include: high definition camera 701, 5G module 702, cloud server 705, demographic database 711, traffic light time control module 708, traffic light display screen 712, wherein, cloud server 705 may include: CNN703 based on vehicle recognition, a vehicle road neural network 704, CNN706 based on age recognition, a pedestrian road neural network 707, a behavior recognition algorithm module 709 and a face recognition algorithm module 710.

When the traffic signal lamp control system operates, roads are divided into two categories of traffic roads and pedestrian roads, the high-definition cameras installed beside each traffic signal lamp of the intersection are respectively controlled corresponding to the time of the traffic signal lamp, and road video stream information is captured in real time; when the yellow light of the corresponding intersection starts, the road image at the moment is transmitted to a cloud server (equivalent to the cloud platform server) through a 5G module; the cloud server is combined with an external demographic database and an adjacent intersection traffic signal lamp time control module, corresponding vehicle-driving and pedestrian road traffic signal lamp time is calculated and output in the cloud server, and the vehicle-driving and pedestrian road traffic signal lamp time is output to the traffic signal lamp time control module through the 5G module and then displayed through a traffic signal lamp display screen.

The flow of calculating the time of the traffic light by using the cloud platform server is shown in fig. 8.

Fig. 8 shows a flow chart of controlling a traffic signal lamp by a cloud platform server in the embodiment of the present disclosure, and as shown in fig. 8, the flow chart of controlling a traffic signal lamp by a cloud platform server in the embodiment of the present disclosure includes the following steps:

s802, calculating the time T of the vehicle running road _{Vehicle with wheels} The method comprises the steps that a high-definition camera is arranged on each vehicle road, video stream information of the corresponding vehicle road is captured and input into a cloud server (equivalent to the cloud platform server), the model of each vehicle on the road is output through a vehicle identification convolutional neural network, and then the model of each vehicle is input into a vehicle road neural networkCollaterals of formula (I) _θ In which x is ₁ Characterizing the number of small cars, x ₂ Characterizing the number of medium-sized vehicles, x ₃ Characterizing the number of heavy vehicles and outputting f _θ (x ₁ ，x ₂ ，x ₃ ) Meanwhile, the problem of road volume rate is considered, the green time of the vehicles at the adjacent intersection is taken into account, if the green time is less than a certain threshold value, the number of the vehicles coming at the next stage can be borne by the road, and t is made ₂ If not, let t be 0s ₂ 10s (length can be customized), and finally T _{Vehicle with wheels} ＝f _θ (x ₁ ，x ₂ ，x ₃ )+t ₂ 。

For example, the influence factor of the vehicle type is considered in calculating the traffic road time, the traffic road is the motor vehicles, the traffic time is mainly determined by the number of the medium-sized vehicles, the large-sized vehicles and the heavy-duty vehicles on the road, and the three types of vehicles are different in length, starting time, traveling speed and the like, and the traffic time is determined together. The road image information is transmitted to the cloud server through the 5G module by the first high-definition camera and the second high-definition camera beside the traffic signal lamp of the vehicle road, then is input into the trained convolutional neural network CNN, and the vehicle numbers corresponding to the three vehicle models in the identified road image are output and respectively correspond to the three vehicle models. CNN based on vehicle identification: preferably, the convolutional neural network is selected as the method for identifying the vehicle model, and the network parameters are trained in advance from the road video stream information, which is not described in detail herein as patent content. The method comprises the steps of inputting three vehicle models into a constructed neural network of a driving road to obtain the passing time of each wheel of the corresponding driving road, wherein the specific network is constructed as the neural network of the driving road, the neural network is simple in construction, the input layer comprises three neurons and the number of the three types of vehicles is respectively considered, the middle layer is provided with four neurons, and the output layer comprises one neuron and corresponds to the passing time. All the layers are connected, weight and bias parameters are set on each connection from the input layer to the middle layer and from the middle layer to the output layer, and proper activation functions are selected correspondingly for each neuron of the middle layer and the output layer. The method comprises the steps that road video information of a plurality of months before is stored by a traffic administration during network training, a video stream is analyzed by a pre-trained CNN based on vehicle identification to obtain each vehicle type on a road, an input layer only selects the number of various types of vehicles stopping at an intersection before a green light is lighted, an actual output layer, namely the passing time is the time when the corresponding vehicle passes, the vehicles which directly pass without stopping before the green light is lighted are not calculated, and the phenomenon that inaccurate results are caused by the limitation of the duration of traffic lights in actual life is prevented, and parameters in the training network are transmitted reversely.

Further, the road volume rate factor is considered in calculating the vehicle driving road time, the actual traffic signal lamp conversion is not only influenced by the factor, but also needs to consider other human factors, if the road volume rate is limited, the influence of the time length of the adjacent traffic signal lamp on the number of vehicles passing in the next round needs to be considered, and therefore the vehicle driving green time needs to be properly prolonged at the moment.

Furthermore, the final calculation of the time of the vehicle road is that the road information acquired by the road high-definition camera is input into the cloud server and passes through the vehicle road neural network 4f when the vehicle road starts to be yellow light every time _θ Time output of output f _θ (x ₁ ，x ₂ ，x ₃ ) Wherein x is ₁ Characterizing the number of small cars, x ₂ Characterizing the number of medium-sized vehicles, x ₃ And characterizing the number of heavy vehicles. Meanwhile, the problem of road volume rate is considered, the green time of the vehicles at the adjacent intersections is taken into consideration, if the green time is less than a certain threshold value, the number of the vehicles coming at the next stage can be borne by the road, and t is set ₂ If not, let t be 0s ₂ The green time of the driving road at the stage is finally determined to be T (the time length can be defined by user) 10s _{Vehicle with wheels} ＝f _θ (x ₁ ，x ₂ ，x ₃ )+t ₂ . If there are k traffic lights on the driving roads, each driving road goes through the same calculation method to obtain the final green time, which is denoted as T _{Vehicle with wheels} ¹ To T _{Vehicle with wheels} ^k And the time information is input into a traffic signal lamp time control module.

Compared with the prior art, the method for calculating the vehicle-running road time can reduce the material and labor cost by measuring the weight of the road pavement and the weight, and is more accurate in comparison with the method for determining the running time only by the road vehicle proportion.

S804, calculating pedestrian road time T _{Human being} The high-definition camera is arranged on each pedestrian road, captures video stream information of the corresponding pedestrian road, inputs the video stream information into the cloud server, firstly identifies the age of each pedestrian on the convolutional neural network output path through the age, and then inputs the video stream information into the pedestrian road neural network g _θ In which y is ₁ Characterizing the number of children, y ₂ Characterization of the number of middle and young adults, y ₃ Characterize the number of the elderly and output g _θ (y ₁ ，y ₂ ，y ₃ ). The pedestrian road video stream information is subjected to behavior recognition convolutional neural network at the same time, and whether special behaviors such as leaning on a crutch, sitting on a wheelchair and the like exist is judged; meanwhile, judging whether the road pedestrian is successfully matched with the disabled person information base established in the external demographic database by using the face recognition convolutional neural network, and if the two are not met, outputting t ₁ 0s, otherwise t ₁ 10s (length can be customized), and finally T _{Human being} ＝g _θ (y ₁ ，y ₂ ，y ₃ )+t ₁ 。

For example, when the pedestrian passage time is calculated, the influence factors of the ages of pedestrians are considered, pedestrians pass through the sidewalk, the passage time is mainly determined by the age classification of the pedestrians and can be divided into children, middle-aged and young people and old people, and the pedestrians at the three ages have different walking speeds, different response speeds to the road conditions and the like, and the passage time of the pedestrians is determined together. And the third high-definition camera and the fourth high-definition camera beside the pedestrian road traffic signal lamp transmit pedestrian road image information to the cloud server through the 5G module, then input the pedestrian road image information into the trained Convolutional Neural Network (CNN), and output the pedestrian age in the identified image to obtain the number of people corresponding to the three age groups respectively. Age-based identified CNN: preferably, the method for identifying the age of the pedestrian selects a Convolutional Neural Network (CNN), and the network parameters are trained in advance from the road video stream information, which is not described in detail herein again as patent content. Inputting the number of people in three age groups into a constructed pedestrian road neural network to obtain the passing time of each round of corresponding pedestrian road, wherein the concrete network structure is as follows: pedestrian road neural network: the input layer is three neurons which are the number of pedestrians at three ages, the middle layer is provided with four neurons, and the output layer is one neuron and corresponds to the transit time. All the layers are connected, weight and bias parameters are set on each connection from the input layer to the middle layer and from the middle layer to the output layer, and proper activation functions are selected correspondingly for each neuron of the middle layer and the output layer. When the network is trained, video information of pedestrian roads in previous months stored by a traffic bureau is analyzed by a pre-trained CNN-based age identification model to obtain age prediction of each pedestrian on the sidewalk, the number of pedestrians in three age groups on an input layer is respectively, the actual output layer, namely the passing time is the passing finish time of the pedestrian, the pedestrian which does not stop waiting on one side of the road before a green light is lighted is not calculated, and parameters in the training network are reversely propagated.

Furthermore, when calculating the passing time of the road of the examinee, the influence factors of special pedestrians such as disabled people are considered, besides the influence factors, for some pedestrians with disabilities and unable to walk at normal speed, the longitudinal green light time also needs to be properly prolonged, here, a database of the disabled people is established in a demographic database in consideration of communication with related departments, the disabled people needing to prolong the time on the longitudinal road can apply for inputting the face information of the disabled people in the database, the high-definition camera on the first-stage road recognizes the face information, and the system prolongs the green light time after the successful matching is uploaded to the database.

Furthermore, the final pedestrian road time is calculated, when the pedestrian road starts at a yellow light each time, road video stream information acquired by the road high-definition camera is input into the cloud server and passes through the pedestrian road neural network g _θ Output g _θ (y ₁ ，y ₂ ，y ₃ ) Wherein y is ₁ Characterisation of the number of children (1-12 years old), y ₂ Characterization of the number of young (12-60 years old), y ₃ The number of elderly (over 60 years old) is characterized. The pedestrian road video stream information passes through the behavior recognition convolutional neural network at the same time, and the judgment is thatWhether special behaviors such as leaning on a crutch, sitting on a wheelchair and the like exist; meanwhile, judging whether the road pedestrian is successfully matched with the disabled person information base established in the external demographic database by using the face recognition convolutional neural network, and if the two are not met, outputting t ₁ 0s, otherwise t ₁ The green time of the pedestrian road at the stage is finally determined to be T (the time length can be defined by user) 10s _{Human being} ＝g _θ (y ₁ ，y ₂ ，y ₃ )+t ₁ . If there are q number of traffic lights on the road, each one is processed by the same calculation method to obtain the final green time, which is marked as T _{Human being} ¹ To T _{Human being} ^q And the time information is input into a traffic signal lamp time control module.

S806, calculating the final time, wherein the number of the traffic roads and the number of the pedestrian roads at different intersection types are different, for example, at a straight intersection, the green time corresponding to two opposite traffic lights of the traffic roads is

The two opposite traffic signal lamps of the pedestrian road respectively correspond to green light time as

Obtaining:

first stage T ₁ ：

Wherein max represents the maximum value;

second stage T ₂ : 2 vehicle running yellow lamps are 2 personal running yellow lamps are 3 (self-defined, and only information transmission and calculation time are met);

third stage T ₃ ：

Fourth stage T ₄ ：

And S808, correspondingly outputting at different intersections, and then outputting the display duration of each traffic signal lamp at the corresponding stage by a user (such as a traffic administration) by selecting the type of the intersection in the traffic signal lamp control module 8, outputting the display duration to the traffic signal lamp time control module by the 5G module, and further displaying the display duration by a traffic signal lamp display screen. If the type of the intersection is special, a user (such as a traffic administration) only needs to give the switching sequence of each traffic signal lamp.

In an embodiment of the present disclosure, as shown in fig. 9, in a straight road, a vehicle is led to a road (equivalent to the above-mentioned traffic road) in the horizontal direction, and a pedestrian road is arranged in the vertical direction, and four traffic lights are arranged in total, wherein the time settings of the traffic light 903 and the traffic light 904 are the same, the time settings of the traffic light 901 and the traffic light 902 are the same, and the four traffic lights respectively have four high definition cameras corresponding to the corresponding roads.

The traffic signal lamp 901 and the traffic signal lamp 902 of the vehicle road correspond to the cameras to acquire video stream information of the opposite road, the video stream information is transmitted to the cloud server through the 5G module, and the corresponding video stream information is calculated by combining green time in the adjacent traffic signal lamp control module

The traffic signal lamp 903 and the traffic signal lamp 904 of the pedestrian road correspond to cameras to acquire video stream information of the opposite road, the video stream information is transmitted to a cloud server through a 5G module, and corresponding video stream information is obtained through calculation by combining with an external demographic database

For t ₁ ，t ₂ The following three rules are satisfied:

firstly, a face recognition algorithm module recognizes that the pedestrians on the sidewalk are successfully matched with the disability database.

Preferably, the face recognition algorithm selects a face recognition method based on a Convolutional Neural Network (CNN), which is already applied in practice at present and is not described herein again. However, the threshold of the matching degree can be increased according to the requirement, so that the frequent extension of the green time is prevented, and if a disabled person does not recognize the threshold, the rule (II) is also an adjusting method.

Secondly, the behavior recognition algorithm module recognizes that the pedestrian has special behaviors (such as sitting on a wheelchair, leaning on a crutch and the like).

Preferably, the behavior recognition algorithm selects a deep learning technique that can be used in the video behavior analysis.

And thirdly, green light time T 'of the vehicle road is transmitted to the traffic signal light time control module of the intersection in the traffic signal light time control module corresponding to the adjacent intersection, and the T' is larger than a preset threshold value.

In summary, the traffic signal light display and time of the traffic road and the pedestrian road are as shown in the following table 1:

TABLE 1

In one embodiment, if the local 5G signal is weak or the network is disconnected, and the digital signal sent by the 5G module is not received in the traffic signal control module, the traffic signal time stored in the offline mode is used to control the traffic signal display screen, so as to prevent the occurrence of the situation that the information cannot be transmitted due to poor network.

In specific implementation, the high computing power of the cloud platform and the high-speed low-delay characteristic of the 5G network are utilized by the system, the information interaction between traffic signal lamp control and a cloud platform server is realized, the intelligent control effect of the traffic signal lamp time is achieved, the traffic signal lamp time calculation of the whole traffic signal lamp control system is completed in the cloud platform, the influence factors of the traffic time of a vehicle road and a pedestrian road are fully considered, a deep learning method is combined on the basis, a behavior recognition module is introduced to recognize special behaviors (such as sitting on a wheelchair and leaning on a crutch), an external demographic database is introduced to match the face information of disabled persons, and the like, the traffic time of the vehicle road is corrected, the traffic time of adjacent intersections is taken into the database to correct the time of the vehicle road, the road volume rate is prevented from being too high, and the final traffic signal lamp time is more humanized, and the traffic signal lamp control system can safely and effectively improve the traffic efficiency in practical application.

In an embodiment of the present disclosure, as shown in fig. 10, in a t-shaped road, three lanes all have two directions and are split into two traffic signal lamp control modules, where a traffic signal lamp 1001, a traffic signal lamp 1002, a traffic signal lamp 1009, a traffic signal lamp 1010, a traffic signal lamp 1011, and a traffic signal lamp 1012 of the lanes are output via a cloud server

Pedestrian road traffic light 1003, traffic light 1004, traffic light 1005, traffic light 1006, traffic light 1007, traffic light 1008 are output via the cloud server

Determining the switching sequence of the traffic lights according to the type of the intersection, and obtaining the time of each stage shown in the following table 2 in the cloud server:

TABLE 2

And the 5G module outputs the data to the traffic signal lamp time control module, and the data is displayed by a traffic signal lamp display screen. In other intersections, such as crossroads and the like, the embodiments of the first intersection and the second intersection can be compared, and the traffic signal lamp conversion rule can be directly applied to the time control of the traffic signal lamp after being given.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 1100 according to this embodiment of the disclosure is described below with reference to fig. 11. The electronic device 1100 shown in fig. 11 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present disclosure.

As shown in fig. 11, electronic device 1100 is embodied in the form of a general purpose computing device. The components of the electronic device 1100 may include, but are not limited to: the at least one processing unit 1110, the at least one memory unit 1120, and a bus 1130 that couples various system components including the memory unit 1120 and the processing unit 1110.

Wherein the storage unit stores program code that is executable by the processing unit 1110 to cause the processing unit 1110 to perform steps according to various exemplary embodiments of the present disclosure as described in the above section "exemplary methods" of this specification.

For example, the processing unit 1110 may perform the following steps of the above-described method embodiment: receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network; determining the passing time length of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval; and controlling the display time length of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time length of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

The storage unit 1120 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM)11201 and/or a cache memory unit 11202, and may further include a read only memory unit (ROM) 11203.

Storage unit 1120 may also include a program/utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1130 may be representative of one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1100 may also communicate with one or more external devices 1140 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1100 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 1150. Also, the electronic device 1100 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 1160. As shown, the network adapter 1160 communicates with the other modules of the electronic device 1100 over the bus 1130. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, which may be a readable signal medium or a readable storage medium. On which a program product capable of implementing the above-described method of the present disclosure is stored. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.

More specific examples of the computer-readable storage medium in the present disclosure may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In the present disclosure, a computer readable storage medium may include a propagated data signal with readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Alternatively, program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

In particular implementations, program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A traffic signal light control method, comprising:

receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network;

determining the passing time length of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval;

determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval;

and controlling the display time length of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing time length of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

2. The traffic signal light control method according to claim 1, wherein determining the passing time of the traffic road at the time of the next turn of traffic signal light switching according to the video image data of the traffic road in the traffic signal light switching time interval comprises:

inputting video image data of a traffic road in a traffic signal lamp switching time interval into a pre-trained vehicle recognition model, and outputting the number of vehicles of different vehicle types on the traffic road;

and determining the passing time of the traffic road when the traffic signal lamps of the next round are switched according to the number of vehicles of different vehicle types on the traffic road.

3. The traffic signal lamp control method according to claim 2, wherein after determining a passage duration of a traffic road at the time of next round of traffic signal lamp switching according to the number of vehicles of different vehicle types on the traffic road, the method further comprises:

and correcting the passing time length of the vehicle road when the next round of traffic signal lamp is switched by utilizing the display time length of the traffic signal lamps at the adjacent intersections.

4. The traffic signal lamp control method according to claim 1, wherein determining the passing time of the pedestrian road in the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval comprises:

inputting video image data of pedestrian roads in a traffic signal lamp switching time interval into a pre-trained age identification model, and outputting the number of pedestrians in different age ranges on the pedestrian roads;

and determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of pedestrians in different age ranges on the sidewalk road.

5. The traffic signal light control method according to claim 4, wherein after determining the passage time of the pedestrian road at the next round of traffic signal light switching according to the number of pedestrians in different age ranges on the pedestrian road, the method further comprises:

inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained behavior recognition model, and outputting the number of pedestrians meeting preset behaviors on the pedestrian road;

and correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the number of the pedestrians meeting the preset behavior on the sidewalk road.

6. The traffic signal light control method according to claim 4, wherein after determining the passage time of the pedestrian road at the next round of traffic signal light switching according to the number of pedestrians in different age ranges on the pedestrian road, the method further comprises:

inputting video image data of a pedestrian road in a traffic signal lamp switching time interval into a pre-trained face recognition model, and outputting identity information of one or more pedestrians on the pedestrian road;

judging whether the pedestrian belonging to the target group exists on the sidewalk according to the identity information of one or more pedestrians on the sidewalk and a pre-constructed target group information base;

and when the pedestrian belonging to the target group exists on the sidewalk, correcting the passing time of the pedestrian road during the next round of traffic signal lamp switching.

7. The traffic signal light control method according to any one of claims 1 to 6, wherein the video image data includes: the system comprises a first camera and a second camera which are arranged on two sides of a road, wherein the first camera is used for collecting video image data in a first traffic direction of the road, and the second camera is used for collecting video image data in a second traffic direction of the road; the method further comprises the following steps:

determining the maximum passing time length in the first passing time length and the second passing time length as the passing time length of the road, wherein the first passing time length is the passing time length of the road determined according to the video image data collected by the first camera, and the second passing time length is the passing time length of the road determined according to the video image data collected by the second camera.

8. A traffic signal control system, comprising: the system comprises a cloud platform server, a 5G network, cameras, traffic signal lamps and traffic signal lamp control modules, wherein the cameras, the traffic signal lamps and the traffic signal lamp control modules are installed on two sides of a vehicle road and a pedestrian road;

the camera is used for acquiring video image data of a vehicle road and/or a pedestrian road and transmitting the video image data to the cloud platform server through a 5G network;

the cloud platform server is used for determining the passing time of the traffic road during the next round of traffic signal lamp switching according to the video image data of the traffic road in the traffic signal lamp switching time interval; determining the passing time of the pedestrian road during the next round of traffic signal lamp switching according to the video image data of the pedestrian road in the traffic signal lamp switching time interval, and transmitting the passing time to the corresponding traffic signal lamp control module through a 5G network;

the traffic signal lamp control module is used for controlling the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the traffic duration of the vehicle road and/or the pedestrian road issued by the cloud platform server.

9. A traffic signal control apparatus, comprising:

the data receiving module is used for receiving video image data of a vehicle road and/or a pedestrian road uploaded by a 5G network;

the traffic road duration determining module is used for determining the traffic duration of the traffic road during the switching of the next round of traffic signal lamps according to the video image data of the traffic road in the traffic signal lamp switching time interval;

the pedestrian road duration determining module is used for determining the passing duration of the pedestrian road during the switching of the next round of traffic signal lamps according to the video image data of the pedestrian road in the traffic signal lamp switching time interval;

and the traffic signal lamp control module is used for controlling the display duration of the corresponding traffic signal lamp on the vehicle road and/or the sidewalk according to the passing duration of the vehicle road and/or the pedestrian road when the traffic signal lamp is switched.

10. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to execute the traffic signal control method of any one of claims 1-7 via execution of the executable instructions.

11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a traffic signal control method according to any one of claims 1 to 7.