CN117876997A - Traffic signal lamp identification method, device, equipment and storage medium - Google Patents
Traffic signal lamp identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117876997A CN117876997A CN202311871090.7A CN202311871090A CN117876997A CN 117876997 A CN117876997 A CN 117876997A CN 202311871090 A CN202311871090 A CN 202311871090A CN 117876997 A CN117876997 A CN 117876997A
- Authority
- CN
- China
- Prior art keywords
- indication information
- vehicle
- determining
- traffic signal
- current intersection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000008569 process Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Abstract
The application discloses a traffic signal lamp identification method, a device, equipment and a storage medium, and belongs to the technical field of vehicles. The method comprises the steps of obtaining a first image sent by a front-view camera, identifying traffic signals in the first image to obtain first indication information, obtaining second indication information through a cloud platform, determining third indication information from the second indication information, and determining the identification result of the traffic signals based on the first indication information and the third indication information. Therefore, the method jointly determines the identification result of the traffic signal lamp based on the identification result of the image shot by the front-view camera and the indication information acquired from the cloud platform, so that the traffic signal lamp is accurately identified, and road congestion is avoided.
Description
Technical Field
The present disclosure relates to the field of vehicle technologies, and in particular, to a traffic signal lamp identification method, device, equipment, and storage medium.
Background
The traffic signal lamp is an indicator lamp for commanding traffic to run. For a vehicle driven by a driver, when the vehicle passes through an intersection, the driver can judge the color of a traffic signal lamp through human eyes, so that the vehicle is controlled to pass through the intersection based on the indication of the traffic signal lamp. For an automatic driving vehicle, when the vehicle passes through an intersection, the vehicle is required to identify a traffic signal lamp by itself, and corresponding driving operation is carried out according to an identification result, otherwise, road congestion is easy to cause.
Disclosure of Invention
The embodiment of the application provides a traffic signal lamp identification method, a device, equipment and a storage medium, which can accurately identify the traffic signal lamp so as to avoid road congestion. The technical scheme is as follows:
in one aspect, a traffic light identification method is provided, the method comprising:
determining a lane in which a vehicle is currently located;
acquiring a first image sent by a front-view camera of the vehicle, wherein the first image comprises traffic signal lamps of a current intersection;
based on the lane, identifying traffic signal lamps in the first image to obtain first indication information;
sending an acquisition request to a cloud platform, and receiving second indication information sent by the cloud platform based on the acquisition request, wherein the second indication information is the indication information of traffic lights of the current intersection, and the second indication information is uploaded to the cloud platform by a traffic management platform;
determining third indication information corresponding to the lane from the second indication information based on the lane;
and determining the identification result of the traffic signal lamp based on the first indication information and the third indication information.
In one possible implementation manner, the determining, based on the first indication information and the third indication information, the identification result of the traffic signal lamp includes:
if the first indication information is the same as the third indication information, determining the first indication information or the third indication information as a recognition result of the traffic signal lamp;
and if the first indication information is different from the third indication information, determining the first indication information as a recognition result of the traffic signal lamp.
In another possible implementation, the method further includes:
and if the first image does not comprise the traffic signal lamp of the current intersection, determining the third indication information as a recognition result of the traffic signal lamp.
In another possible implementation, the method further includes:
if the vehicle is in the driving process, determining the current speed of the vehicle and the distance between the vehicle and the current intersection;
determining whether the vehicle can pass through the current intersection based on the speed, the distance and the recognition result;
if the fact that the vehicle can pass through the current intersection according to the speed is determined, controlling the vehicle to pass through the current intersection according to the speed;
if the fact that the vehicle cannot pass through the current intersection according to the speed is determined, acquiring the highest speed of the current intersection allowed to pass through;
if the fact that the vehicle can pass through the current intersection according to the highest speed is determined, controlling the vehicle to accelerate, and enabling the vehicle to pass through the current intersection at the highest speed;
and if the vehicle is determined to be unable to pass through the current intersection according to the highest speed, controlling the vehicle to decelerate and stopping at the current intersection.
In another possible implementation, the method further includes:
acquiring a second image sent by a rearview camera of the vehicle;
identifying the second image, and determining whether a special vehicle exists behind the vehicle, wherein the special vehicle is a vehicle for executing a special task;
if the special vehicle exists behind the vehicle, determining an avoidance route;
and controlling the vehicle to run according to the avoidance route so as to enable the special vehicle to preferentially pass through the current intersection.
In another possible implementation manner, the determining the avoidance line if the special vehicle exists behind the vehicle includes:
if other vehicles exist in front of the vehicle, outputting a voice message, and prompting the other vehicles to move so as to avoid the special vehicle through the voice message;
and after the other vehicles move, determining the avoidance route based on the positions of the other vehicles after the movement and the positions of the special vehicles.
In another aspect, there is provided a traffic light identification device, the device comprising:
the first determining module is used for determining a lane where the vehicle is currently located;
the first acquisition module is used for acquiring a first image sent by a front-view camera of the vehicle, wherein the first image comprises traffic signal lamps of a current intersection;
the identifying module is used for identifying the traffic signal lamp in the first image based on the lane to obtain first indication information;
the receiving module is used for sending an acquisition request to a cloud platform, receiving second indication information sent by the cloud platform based on the acquisition request, wherein the second indication information is the indication information of the traffic signal lamp of the current intersection, and the second indication information is uploaded to the cloud platform by a traffic management platform;
the second determining module is used for determining third indication information corresponding to the lane from the second indication information based on the lane;
and the third determining module is used for determining the recognition result of the traffic signal lamp based on the first indication information and the third indication information.
In one possible implementation manner, the third determining module is configured to determine the first indication information or the third indication information as a recognition result of the traffic signal lamp if the first indication information is the same as the third indication information; and if the first indication information is different from the third indication information, determining the first indication information as a recognition result of the traffic signal lamp.
In another possible implementation, the apparatus further includes:
and the fourth determining module is used for determining the third indication information as the recognition result of the traffic signal lamp if the traffic signal lamp of the current intersection is not included in the first image.
In another possible implementation, the apparatus further includes:
a fifth determining module, configured to determine, if the vehicle is running, a current speed of the vehicle and a distance between the vehicle and the current intersection; determining whether the vehicle can pass through the current intersection based on the speed, the distance and the recognition result; if the fact that the vehicle can pass through the current intersection according to the speed is determined, controlling the vehicle to pass through the current intersection according to the speed; if the fact that the vehicle cannot pass through the current intersection according to the speed is determined, acquiring the highest speed of the current intersection allowed to pass through; if the fact that the vehicle can pass through the current intersection according to the highest speed is determined, controlling the vehicle to accelerate, and enabling the vehicle to pass through the current intersection at the highest speed; and if the vehicle is determined to be unable to pass through the current intersection according to the highest speed, controlling the vehicle to decelerate and stopping at the current intersection.
In another possible implementation, the apparatus further includes:
the second acquisition module is used for acquiring a second image sent by a rearview camera of the vehicle;
a sixth determining module, configured to identify the second image, and determine whether a special vehicle exists behind the vehicle, where the special vehicle is a vehicle that performs a special task;
a seventh determining module, configured to determine an avoidance route if the special vehicle exists behind the vehicle;
and the control module is used for controlling the vehicle to run according to the avoidance route so as to enable the special vehicle to pass through the current intersection preferentially.
In another possible implementation manner, the seventh determining module is configured to output a voice message if another vehicle exists in front of the vehicle, and prompt the other vehicle to move so as to avoid the special vehicle through the voice message; and after the other vehicles move, determining the avoidance route based on the positions of the other vehicles after the movement and the positions of the special vehicles.
In another aspect, a control device is provided, the control device including a processor and a memory, the memory storing at least one program code, the at least one program code loaded and executed by the processor to implement the traffic light identification method of any one of the above.
In another aspect, a computer readable storage medium having at least one program code stored therein, the at least one program code loaded and executed by a processor to implement the traffic light identification method of any of the above.
In another aspect, a computer program product is provided, in which at least one program code is stored, which is loaded and executed by a processor to implement the traffic light identification method according to any of the above.
The embodiment of the application provides a traffic signal lamp identification method, which comprises the steps of acquiring a first image sent by a front-view camera, identifying a traffic signal lamp in the first image to obtain first indication information, acquiring second indication information through a cloud platform, determining third indication information from the second indication information, and determining an identification result of the traffic signal lamp based on the first indication information and the third indication information. Therefore, the method jointly determines the identification result of the traffic signal lamp based on the identification result of the image shot by the front-view camera and the indication information acquired from the cloud platform, so that the traffic signal lamp is accurately identified, and road congestion is avoided.
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
Fig. 1 is a schematic diagram of an implementation environment of a traffic light identification method according to an embodiment of the present application;
fig. 2 is a flowchart of a traffic light identification method provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a traffic signal lamp identification device according to an embodiment of the present application;
fig. 4 is a block diagram of a control device according to an embodiment of the present application.
Detailed Description
In order to make the technical solution and advantages of the present application more clear, the following embodiments of the present application are described in further detail.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprising," "including," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
It should be noted that, information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals referred to in this application are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of relevant data is required to comply with relevant laws and regulations and standards of relevant countries and regions. For example, the images, instruction information, lane information, and the like referred to in this application are acquired with sufficient authorization.
Fig. 1 is a schematic diagram of an implementation environment of a traffic light identification method provided in an embodiment of the present application, referring to fig. 1, the implementation environment includes: the traffic management platform 101, the cloud platform 102, the front-view camera 103 and the control device 104 are connected through a wireless or wired network, the cloud platform 102 and the control device 104 are connected through a wireless or wired network, and the front-view camera 103 and the control device 104 are connected through a wireless or wired network.
For example, the traffic management platform 101 and the cloud platform 102 are connected through a 5G (5 th Generation Mobile Communication Technology, fifth generation mobile communication technology) network, the cloud platform 102 and the control device 104 are connected through a 5G network, and the front-view camera 103 and the control device 104 are connected through LVDS (Low Voltage Differential Signaling ) data lines.
In this embodiment of the present application, the cloud platform 102 includes a high-precision map database, the high-precision map database stores a high-precision map, the control device 104 may obtain the high-precision map from the high-precision map database, and the control device 104 may also perform high-precision positioning through a positioning module of the vehicle itself, and determine, based on the high-precision map and the high-precision positioning, a lane where the vehicle is currently located.
The front-view camera 103 and the control device 104 are located in the same vehicle, and when the vehicle runs or stops, the front-view camera 103 shoots a first image in real time or periodically, and sends the first image to the control device 104, wherein the first image comprises traffic lights of the current intersection. The control device 104 identifies the first image based on the lane in which the vehicle is currently located, so as to determine indication information corresponding to the traffic signal lamp of the lane in which the vehicle is currently located, that is, first indication information.
The cloud platform 102 further comprises a traffic information database, and for any city, the traffic management platform 101 can upload the indication information of the traffic lights of different intersections in the city at different moments to the traffic information database, so that the control device 104 can obtain the second indication information of the traffic lights of the current intersection at the current moment from the cloud platform 102, and then determine the third indication information corresponding to the lane from the second indication information based on the lane where the vehicle is currently located.
The control device 104 fuses the first indication information and the third indication information, determines the recognition result of the traffic signal lamp based on the first indication information and the third indication information together, and further performs corresponding driving operation according to the recognition result of the traffic signal lamp. For example, the vehicle is controlled to pass through or stop at the current intersection.
In this embodiment of the present application, the cloud platform 102 may further include a traffic information database, where the control device 104 may obtain the latest traffic information from the traffic information database, and update the navigation information of the vehicle in time based on the latest traffic information, where the navigation information includes information such as road congestion between the departure point and the destination, the number of traffic lights, and the service area, and controls the vehicle to travel according to the latest navigation information.
In this embodiment of the present application, after determining the identification result of the traffic light, the control device 104 may send a control instruction to each actuator 106 in the vehicle through the gateway 105, so that each actuator 106 performs a corresponding operation based on the respective control instruction. Correspondingly, the implementation environment further comprises: the gateway 105 and the control device 104 may be connected through a wireless or wired network, the plurality of actuators 106 and the control device 104 may be connected through a wireless or wired network, for example, the gateway 105 and the control device 104 may be connected through an ethernet, and the plurality of actuators 106 and the control device 104 may be connected through an ethernet.
The plurality of actuators 106 may include, but are not limited to, IPB (Intelligent Park Brake System, electronically controlled intelligent brake system), EPS (Electric Power Steering, electric power steering system), and other actuators.
In addition, the control device 104 can also determine whether a special vehicle exists behind the vehicle, such as an ambulance, a police car, a fire truck and the like, through the rearview camera 107 and the microphone 108, and if the special vehicle exists, the control device 104 can take avoidance measures to avoid the special vehicle through other vehicles nearby the speaker 109 in a voice prompt mode. Correspondingly, the implementation environment further comprises: the rear-view camera 107, the microphone 108, and the speaker 109, the rear-view camera 107 and the microphone 108 may be connected to the control device 104 through wireless or wired networks, for example, the rear-view camera 107 and the microphone 108 may be connected to the control device 104 through ethernet. The speaker 109 is connected to the gateway 105 via an ethernet network, and the control device 104 can control other vehicles in the vicinity of the speaker 109 by means of the gateway 105.
Wherein the control device 104 may be an autopilot controller. Cloud platform 102 may be at least one of a server, a server cluster composed of a plurality of servers, and a virtualization center. The traffic management platform 101 may be at least one of a server, a server cluster composed of a plurality of servers, and a virtualization center.
Fig. 2 is a flowchart of a traffic light identification method provided in an embodiment of the present application, and the method is executed by a control device, referring to fig. 2, and includes:
step 201: the control device determines the lane in which the vehicle is currently located.
The vehicle comprises a positioning module, the control equipment can send a first acquisition request to the positioning module, the positioning module determines the current position of the vehicle based on the first acquisition request, and the position is sent to the control equipment. Or the positioning module can determine the current position of the vehicle in real time or periodically and actively send the position to the control device.
The control device may also send a second acquisition request to the cloud platform, and the cloud platform acquires the high-precision map from the high-precision map database based on the second acquisition request and sends the high-precision map to the control device. Or the cloud platform can also acquire the high-precision map from the high-precision map database in real time or periodically and send the high-precision map to the control equipment.
The control device determines a lane in which the vehicle is currently located based on a position in which the vehicle is currently located and a high-precision map. For example, the road on which the vehicle is currently located has 3 lanes, and the vehicle is in a straight lane, a left-turn lane, or a right-turn lane.
Step 202: the control device acquires a first image sent by a front-view camera of the vehicle.
The front-view camera shoots images in front of the vehicle in real time or periodically, and sends the shot images to the control equipment, wherein the images comprise traffic lights of the current intersection.
Step 203: the control equipment identifies traffic signal lamps in the first image based on the lanes to obtain first indication information.
In one possible implementation manner, the current intersection includes traffic signals corresponding to a plurality of lanes, and correspondingly, the first image includes traffic signals corresponding to a plurality of lanes, and the control device identifies the traffic signals corresponding to the lanes in the first image based on the lane where the vehicle is currently located, so as to obtain first indication information corresponding to the lane.
For example, the first image includes traffic signals corresponding to a left-turning lane, traffic signals corresponding to a straight lane and traffic signals corresponding to a right-turning lane, and the vehicle is currently in the left-turning lane, and the control device identifies the traffic signals corresponding to the left-turning lane in the first image to obtain first indication information corresponding to the left-turning lane.
In another possible implementation manner, the current intersection includes traffic signals corresponding to a plurality of lanes, and correspondingly, the first image includes traffic signals corresponding to a plurality of lanes, the control device identifies the traffic signals corresponding to each lane to obtain a plurality of indication information, and then determines, based on the lane where the vehicle is currently located, first indication information corresponding to the lane from the plurality of indication information.
For example, the first image includes traffic signals corresponding to a left-turn lane, traffic signals corresponding to a straight lane and traffic signals corresponding to a right-turn lane, the vehicle is currently in the left-turn lane, the control device identifies the traffic signals corresponding to each lane to obtain a plurality of indication information, and then determines first indication information corresponding to the left-turn lane from the plurality of indication information.
In another possible implementation manner, the current intersection only includes traffic signals corresponding to one lane, and correspondingly, the first image only includes traffic signals corresponding to one lane, and then the control device directly identifies the traffic signals corresponding to the lane to obtain the first indication information.
The first indication information not only can include the color of the traffic signal lamp, but also can include the countdown number of the traffic signal lamp.
Step 204: the control device sends an acquisition request to the cloud platform, and receives second indication information sent by the cloud platform based on the acquisition request.
The control equipment sends an acquisition request to the cloud platform, the acquisition request carries an intersection identifier of a current intersection and a current moment, the cloud platform receives the acquisition request, second indication information of a traffic signal lamp corresponding to the intersection identifier is acquired from a traffic information database based on the current moment, the second indication information is sent to the control equipment, and the control equipment receives the second indication information correspondingly.
The second indication information is the indication information of the traffic signal lamp of the current intersection, which is uploaded to the cloud platform by the traffic management platform. If the current intersection comprises traffic lights corresponding to a plurality of lanes, the second indication information comprises indication information corresponding to the plurality of lanes. If the current intersection only comprises a traffic signal lamp corresponding to one lane, the second indicating information only comprises the indicating information corresponding to the lane. And, the second indication information may include not only the color of the traffic light but also a countdown number of the traffic light.
Step 205: the control device determines third indication information corresponding to the lane from the second indication information based on the lane.
If the second indication information comprises indication information corresponding to a plurality of lanes, the control equipment determines third indication information corresponding to the lane where the vehicle is currently located from the indication information corresponding to the plurality of lanes based on the lane where the vehicle is currently located.
For example, the second indication information includes indication information corresponding to a left-turn lane, indication information corresponding to a straight lane, and indication information corresponding to a right-turn lane, and if the lane where the vehicle is currently located is a right-turn lane, the control device determines third indication information corresponding to the right-turn lane from the plurality of indication information.
If the second indication information only comprises indication information corresponding to one lane, the control equipment directly takes the indication information as third indication information.
Step 206: the control device determines the recognition result of the traffic signal lamp based on the first indication information and the third indication information.
After the control equipment acquires the first indication information and the third indication information, determining whether the first indication information and the third indication information are identical, and if the first indication information and the third indication information are identical, determining the first indication information or the third indication information as the identification result of the traffic signal lamp. And if the first indication information and the third indication information are different, determining the first indication information as the identification result of the traffic signal lamp.
It should be noted that when an obstacle exists in front of the vehicle, the forward-looking camera may not be able to capture the traffic signal lamp, that is, the first image does not include the traffic signal lamp at the current intersection, and the control device does not obtain the first indication information when identifying the first image, where the control device determines the third indication information as the identification result of the traffic signal lamp.
The obstacle may be a large truck, a bus or other objects for shielding traffic lights, which is not particularly limited.
In the embodiment of the application, after the control device determines the identification result of the traffic signal lamp, the running state of the vehicle can be controlled according to the identification result.
If the vehicle is in the driving process, the control equipment can determine the current speed of the vehicle and the distance between the vehicle and the current intersection; determining whether the vehicle can pass through the current intersection based on the speed, the distance and the recognition result; if the vehicle is determined to pass through the current intersection according to the speed, controlling the vehicle to pass through the current intersection according to the speed; if the fact that the vehicle cannot pass through the current intersection according to the speed is determined, acquiring the highest speed of the allowed traffic of the current intersection; if the fact that the vehicle can pass through the current intersection according to the highest speed is determined, controlling the vehicle to accelerate, and enabling the vehicle to pass through the current intersection at the highest speed; if the fact that the vehicle cannot pass through the current intersection according to the highest speed is determined, controlling the vehicle to decelerate, and stopping at the current intersection.
If the vehicle is in a parking state at the current intersection, the control device determines a time interval between the current moment and the allowed passing moment, controls the vehicle to be in a ready-to-start state based on the time interval, and controls the vehicle to start when the allowed passing moment is reached, and passes through the current intersection.
Wherein the control device can determine the time interval from a first image taken by the front-view camera. In this implementation manner, the first image includes not only the traffic signal lamp of the current intersection, but also the time interval between the current time and the allowed traffic time. For example, the traffic signal lamp of the current intersection is a red lamp, the forbidden traffic time is 5s, and the time interval is 5s.
The control device may also determine the time interval through the cloud platform. In this implementation manner, the time interval is included in the second indication information sent by the cloud platform to the control device, and then the control device may determine the time interval from the second indication information.
When the time interval is not greater than the preset time interval, the control device controls the vehicle to be in a ready-to-start state, such as brake loosening, slight accelerator increasing and the like, and when the allowed passing time is reached, the control device can directly control the vehicle to start and pass through the current intersection.
In the embodiment of the application, when the vehicle is in a driving process or is parked and waiting for a traffic signal lamp, whether a special vehicle exists behind the vehicle or not can be determined through the rearview camera, and if the special vehicle exists, an avoidance route is determined, so that the special vehicle preferentially passes through a current intersection.
The process may be: the control equipment acquires a second image sent by a rearview camera of the vehicle; identifying the second image, and determining whether a special vehicle exists behind the vehicle, wherein the special vehicle is a vehicle for executing a special task; if a special vehicle exists behind the vehicle, determining an avoidance route; and controlling the vehicle to run according to the avoidance route so as to enable the special vehicle to preferentially pass through the current intersection.
In this implementation, the control device determines, through the second image sent by the rear-view camera, whether a special vehicle is present behind the vehicle, for example, a police car, a fire truck, an ambulance, a large truck, or the like. Of course, the control apparatus may also determine whether a special vehicle is present through the vehicle rear microphone, for example, the rear microphone collects sound, extracts sound characteristics, and determines whether a special vehicle is present based on the sound characteristics. Or, the control device determines whether or not there is a special vehicle based on the second image transmitted from the rear-view camera and the rear microphone together, which is not particularly limited.
If the special vehicle exists, the control equipment can determine whether other vehicles exist in front of the vehicle through the image shot by the front-view camera, if the other vehicles exist, voice information is output through the loudspeaker, and the other vehicles are prompted to move through the voice information so as to avoid the special vehicle; after other vehicles move, an avoidance route is determined based on the positions of the other vehicles and the positions of the special vehicles, and the vehicles are controlled to run according to the avoidance route so that the special vehicles pass through the current intersection preferentially.
If no other vehicles exist, the control equipment directly determines an avoidance route and controls the vehicles to run according to the avoidance route so as to enable the special vehicles to pass through the current intersection preferentially.
In a possible implementation manner, the cloud platform further comprises a road condition information database, if a special vehicle exists, the control device can upload the road condition information of the current intersection to the road condition information database, so that other nearby vehicles can acquire the road condition information of the current intersection from the road condition information database, and further take avoidance measures to avoid the special vehicle.
Of course, the control device may also obtain road condition information of other intersections from the road condition information database, and update navigation information of the vehicle based on the road condition information of other intersections, so that the vehicle reaches the destination as soon as possible based on the latest navigation information.
In the related art, when a special vehicle is encountered, a driver generally judges whether to take an avoidance measure or not, what kind of avoidance measure is taken and whether the avoidance measure is reasonable or not by people, but the method is a challenge for a novice driver, and the avoidance measure is unreasonable and is easy to cause traffic jam and traffic violation. In the embodiment of the application, the control device can automatically determine the avoiding route and then control the vehicle to run according to the avoiding route, so that traffic jam and traffic violation can be avoided, and task execution of special vehicles can be ensured.
The embodiment of the application provides a traffic signal lamp identification method, which comprises the steps of acquiring a first image sent by a front-view camera, identifying a traffic signal lamp in the first image to obtain first indication information, acquiring second indication information through a cloud platform, determining third indication information from the second indication information, and determining an identification result of the traffic signal lamp based on the first indication information and the third indication information. Therefore, the method jointly determines the identification result of the traffic signal lamp based on the identification result of the image shot by the front-view camera and the indication information acquired from the cloud platform, so that the traffic signal lamp is accurately identified, and road congestion is avoided. The scheme is safe, reliable, high in practicability and suitable for any intelligent vehicle.
Fig. 3 is a schematic structural diagram of a traffic signal lamp identification device according to an embodiment of the present application, where the device includes:
a first determining module 301, configured to determine a lane in which a vehicle is currently located;
the first obtaining module 302 is configured to obtain a first image sent by a front-view camera of a vehicle, where the first image includes a traffic signal lamp of a current intersection;
the identifying module 303 is configured to identify, based on the lane, the traffic signal lamp in the first image, so as to obtain first indication information;
the receiving module 304 is configured to send an acquisition request to the cloud platform, receive second indication information sent by the cloud platform based on the acquisition request, where the second indication information is indication information of a traffic light at a current intersection, and the second indication information is uploaded to the cloud platform by the traffic management platform;
a second determining module 305, configured to determine, based on the lane, third indication information corresponding to the lane from the second indication information;
and a third determining module 306, configured to determine a recognition result of the traffic signal lamp based on the first indication information and the third indication information.
In one possible implementation manner, the third determining module 306 is configured to determine the first indication information or the third indication information as the identification result of the traffic signal lamp if the first indication information is the same as the third indication information; and if the first indication information is different from the third indication information, determining the first indication information as the identification result of the traffic signal lamp.
In another possible implementation, the apparatus further includes:
and the fourth determining module is used for determining the third indication information as the recognition result of the traffic signal lamp if the traffic signal lamp of the current intersection is not included in the first image.
In another possible implementation, the apparatus further includes:
a fifth determining module, configured to determine a current speed of the vehicle and a distance between the vehicle and a current intersection if the vehicle is in a driving process; determining whether the vehicle can pass through the current intersection based on the speed, the distance and the recognition result; if the fact that the vehicle passes through the current intersection according to the speed is determined, controlling the vehicle to pass through the current intersection according to the speed; if the fact that the vehicle cannot pass through the current intersection according to the speed is determined, acquiring the highest speed of the current intersection allowed to pass through; if the fact that the vehicle can pass through the current intersection according to the highest speed is determined, controlling the vehicle to accelerate, and enabling the vehicle to pass through the current intersection at the highest speed; if the fact that the vehicle cannot pass through the current intersection according to the highest speed is determined, controlling the vehicle to decelerate, and stopping at the current intersection.
In another possible implementation, the apparatus further includes:
the second acquisition module is used for acquiring a second image sent by a rearview camera of the vehicle;
the sixth determining module is used for identifying the second image and determining whether a special vehicle exists behind the vehicle, wherein the special vehicle is a vehicle for executing a special task;
the seventh determining module is used for determining an avoidance route if a special vehicle exists behind the vehicle;
and the control module is used for controlling the vehicle to run according to the avoidance route so as to enable the special vehicle to pass through the current intersection preferentially.
In another possible implementation manner, the seventh determining module is configured to output a voice message if another vehicle exists in front of the vehicle, and prompt the other vehicle to move so as to avoid the special vehicle through the voice message; and after the other vehicles move, determining an avoidance route based on the positions of the other vehicles and the positions of the special vehicles after the other vehicles move.
The embodiment of the application provides a traffic signal lamp identification device, the device obtains a first image sent by a front-view camera, identifies the traffic signal lamp in the first image to obtain first indication information, and also obtains second indication information through a cloud platform, determines third indication information from the second indication information, and determines the identification result of the traffic signal lamp based on the first indication information and the third indication information. Therefore, the device jointly determines the identification result of the traffic signal lamp based on the identification result of the image shot by the front-view camera and the indication information acquired from the cloud platform, so that the traffic signal lamp is accurately identified, and road congestion is avoided.
As shown in fig. 4, the control device 400 may include a processor (Central Processing Units, CPU) 401 and a memory 402, where the memory 402 stores at least one program code, and the at least one program code is loaded and executed by the processor 401 to implement the traffic light recognition method. Of course, the control device 400 may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.
In an exemplary embodiment, there is also provided a computer readable storage medium storing at least one program code loaded and executed by a processor to implement the traffic light identification method of the above-described embodiments.
In an exemplary embodiment, there is also provided a computer program product storing at least one program code loaded and executed by a processor to implement the traffic light identification method of the above embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing is merely for facilitating understanding of the technical solutions of the present application by those skilled in the art, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method of traffic signal identification, the method comprising:
determining a lane in which a vehicle is currently located;
acquiring a first image sent by a front-view camera of the vehicle, wherein the first image comprises traffic signal lamps of a current intersection;
based on the lane, identifying traffic signal lamps in the first image to obtain first indication information;
sending an acquisition request to a cloud platform, and receiving second indication information sent by the cloud platform based on the acquisition request, wherein the second indication information is the indication information of traffic lights of the current intersection, and the second indication information is uploaded to the cloud platform by a traffic management platform;
determining third indication information corresponding to the lane from the second indication information based on the lane;
and determining the identification result of the traffic signal lamp based on the first indication information and the third indication information.
2. The method of claim 1, wherein the determining the identification result of the traffic light based on the first indication information and the third indication information comprises:
if the first indication information is the same as the third indication information, determining the first indication information or the third indication information as a recognition result of the traffic signal lamp;
and if the first indication information is different from the third indication information, determining the first indication information as a recognition result of the traffic signal lamp.
3. The method according to claim 2, wherein the method further comprises:
and if the first image does not comprise the traffic signal lamp of the current intersection, determining the third indication information as a recognition result of the traffic signal lamp.
4. The method according to claim 1, wherein the method further comprises:
if the vehicle is in the driving process, determining the current speed of the vehicle and the distance between the vehicle and the current intersection;
determining whether the vehicle can pass through the current intersection based on the speed, the distance and the recognition result;
if the fact that the vehicle can pass through the current intersection according to the speed is determined, controlling the vehicle to pass through the current intersection according to the speed;
if the fact that the vehicle cannot pass through the current intersection according to the speed is determined, acquiring the highest speed of the current intersection allowed to pass through;
if the fact that the vehicle can pass through the current intersection according to the highest speed is determined, controlling the vehicle to accelerate, and enabling the vehicle to pass through the current intersection at the highest speed;
and if the vehicle is determined to be unable to pass through the current intersection according to the highest speed, controlling the vehicle to decelerate and stopping at the current intersection.
5. The method according to claim 1, wherein the method further comprises:
acquiring a second image sent by a rearview camera of the vehicle;
identifying the second image, and determining whether a special vehicle exists behind the vehicle, wherein the special vehicle is a vehicle for executing a special task;
if the special vehicle exists behind the vehicle, determining an avoidance route;
and controlling the vehicle to run according to the avoidance route so as to enable the special vehicle to preferentially pass through the current intersection.
6. The method of claim 5, wherein determining the avoidance route if the particular vehicle is present behind the vehicle comprises:
if other vehicles exist in front of the vehicle, outputting a voice message, and prompting the other vehicles to move so as to avoid the special vehicle through the voice message;
and after the other vehicles move, determining the avoidance route based on the positions of the other vehicles after the movement and the positions of the special vehicles.
7. A traffic light identification device, the device comprising:
the first determining module is used for determining a lane where the vehicle is currently located;
the first acquisition module is used for acquiring a first image sent by a front-view camera of the vehicle, wherein the first image comprises traffic signal lamps of a current intersection;
the identifying module is used for identifying the traffic signal lamp in the first image based on the lane to obtain first indication information;
the receiving module is used for sending an acquisition request to a cloud platform, receiving second indication information sent by the cloud platform based on the acquisition request, wherein the second indication information is the indication information of the traffic signal lamp of the current intersection, and the second indication information is uploaded to the cloud platform by a traffic management platform;
the second determining module is used for determining third indication information corresponding to the lane from the second indication information based on the lane;
and the third determining module is used for determining the recognition result of the traffic signal lamp based on the first indication information and the third indication information.
8. A control device, characterized in that it comprises a processor and a memory in which at least one program code is stored, which is loaded and executed by the processor to implement the traffic light identification method according to any one of claims 1 to 6.
9. A computer readable storage medium having stored therein at least one program code, the at least one program code being loaded and executed by a processor to implement the traffic light identification method of any one of claims 1 to 6.
10. A computer program product, characterized in that it has stored therein at least one program code, which is loaded and executed by a processor to implement the traffic light identification method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311871090.7A CN117876997A (en) | 2023-12-29 | 2023-12-29 | Traffic signal lamp identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311871090.7A CN117876997A (en) | 2023-12-29 | 2023-12-29 | Traffic signal lamp identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117876997A true CN117876997A (en) | 2024-04-12 |
Family
ID=90578569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311871090.7A Pending CN117876997A (en) | 2023-12-29 | 2023-12-29 | Traffic signal lamp identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117876997A (en) |
-
2023
- 2023-12-29 CN CN202311871090.7A patent/CN117876997A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11853056B2 (en) | Remote control method and remote control apparatus for autonomous vehicle | |
| CN107608388B (en) | Autonomous police vehicle | |
| US10685561B2 (en) | Method for operating a central server and a method for handling a control card | |
| US11485382B2 (en) | Control unit and method for operating a driving function at a signalling installation | |
| WO2015156146A1 (en) | Travel control device, onboard display device, and travel control system | |
| JP7271259B2 (en) | Vehicle management system, vehicle management device, and vehicle management method | |
| CN112585660B (en) | Driving assistance method and vehicle control device | |
| JP2022514518A (en) | Self-driving vehicle platoon transfer method, equipment and system | |
| CN112230656A (en) | Automatic driving method for park vehicle, system, client and storage medium thereof | |
| CN110956818A (en) | Method and device for controlling unmanned vehicle to drive and unmanned vehicle | |
| JP2020165832A (en) | Route setting device, route setting method, and program | |
| CN113479195A (en) | Method for automatic valet parking and system for carrying out said method | |
| CN110217230A (en) | Vehicle drive assisting method, device and vehicle | |
| CN110853406A (en) | Lane change early warning method, system, server and vehicle based on 5G technology | |
| CN113401056A (en) | Display control device, display control method, and computer-readable storage medium | |
| KR102103450B1 (en) | Advanced driving assistance system based on car distributed simulation | |
| CN117876997A (en) | Traffic signal lamp identification method, device, equipment and storage medium | |
| WO2021199345A1 (en) | Vehicle control system, device, method, and computer-readable medium | |
| JP6942913B1 (en) | car | |
| WO2020202373A1 (en) | Control device, control method, and program | |
| CN114973697A (en) | Vehicle priority passing control method and related equipment | |
| CN114973695A (en) | Vehicle priority passing control method and related equipment | |
| CN111835818A (en) | Communication device, communication method, and storage medium | |
| EP4161109B1 (en) | System for transmitting and receiving data related to autonomous driving and method thereof | |
| TWI793894B (en) | Driving assistance method based on hd map and vehicle intercommunication system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |