WO2023151034A1

WO2023151034A1 - Traffic condition detection method, readable medium and electronic device

Info

Publication number: WO2023151034A1
Application number: PCT/CN2022/076064
Authority: WO
Inventors: 王矿磊
Original assignee: 华为技术有限公司
Priority date: 2022-02-11
Filing date: 2022-02-11
Publication date: 2023-08-17
Also published as: CN116897380A

Abstract

A traffic condition detection method, a readable medium, and an electronic device. The traffic condition detection method is used for an electronic device and comprises: acquiring a video stream acquired by a camera on a target road section; according to the video stream, determining current feature information of a target object on the target road section, the feature information comprising motion state information and/or position state information; and on the basis of the current feature information of the target object and/or historical feature information of the target object, determining current traffic condition information of the target road section; and sending the current traffic condition information of the target road section to vehicles within a preset range of the target road section. Therefore, the vehicles in the preset range of the target road section are enabled to obtain the traffic condition information of the target road section in real time, and the accuracy of said traffic condition information, of the target road section, received by autonomous vehicles is improved, thereby increasing the accuracy of control of autonomous vehicles, and further improving safety and the user experience of autonomous vehicles.

Description

Road condition detection method, readable medium and electronic device

technical field

The present application relates to the field of automatic driving, and in particular to a road condition detection method, a readable medium and an electronic device.

Background technique

Traffic safety has always been a hot issue in the field of transportation. There are many studies on road traffic safety at home and abroad. At present, for accident-prone areas where road accidents are prone to occur, traffic warning signs are set up on accident-prone road sections, or marked on the navigation map of the car to remind drivers of this road section. Belongs to accident-prone section, need to drive carefully. However, the implementation of these two modes all requires a period of time after a traffic accident occurs on the road before it can be known by the driver. This will cause the self-driving vehicle to be unable to obtain the information of the most recent traffic accident-prone areas in the first place, thereby affecting the driving safety and user experience of the self-driving vehicle.

For example, the information on traffic accident-prone areas released by the navigation map is mainly based on the relevant information of traffic accidents on the road section collected by third-party data in the past period of time. The information of traffic accident-prone areas is published on the navigation map. However, there is a long time interval between the collection and analysis of the above-mentioned traffic accident-related information and the release to the navigation map. The traffic accidents that occurred during this time interval have not been collected and analyzed, so the release cannot be guaranteed. Timeliness of information on traffic accident-prone areas.

Contents of the invention

Embodiments of the present application provide a road condition detection method, a readable medium, and an electronic device.

In a first aspect, an embodiment of the present application provides a road condition detection method for an electronic device, including: acquiring a video stream collected by a camera on a target road section. According to the video stream, current feature information of the target object on the target road section is determined, wherein the feature information includes motion state information and/or position state information. Based on the current characteristic information of the target object and/or the historical characteristic information of the target object, the current road condition information of the target road segment is determined.

For example, the drive test equipment obtains the video stream collected in real time by the camera set on the target road section, performs target detection on each frame of image in the video stream, and determines each target object and the position of each target object in each frame of image. The position of each target object in the frame image determines the feature information corresponding to each target object, and the feature information includes motion state information and/or position state information. Wherein, the motion state information may be information such as speed and acceleration, and the position state information may be position coordinates in the world coordinate system. According to the characteristic information of the current target objects of the road section and the characteristic information of the historical target objects of the road section, the current road condition information of the target road section is determined, and then the current road condition information of the target road section is sent to vehicles within the preset range of the target road section . Wherein, the current road condition information of the target road segment may be the road risk level of the target road segment.

It can be understood that, according to the road condition detection method of the present application, the electronic device can update the road condition information of the target road section in real time, and can send the road condition information of the target road section to vehicles within the preset range of the target road section in real time. In this way, vehicles within the preset range of the target road section can obtain the road condition information of the target road section in real time, ensuring the accuracy of the obtained road condition information of the target road section, thereby improving the accuracy of the control of the automatic driving vehicle and further improving the safety of the automatic driving vehicle and user experience.

In a possible implementation of the above first aspect, the above method further includes: sending the current road condition information of the target road segment to vehicles within a preset range of the target road segment.

In a possible implementation of the foregoing first aspect, the foregoing method further includes: the target object includes at least one of the following: a vehicle, a person, and an obstacle.

In a possible implementation of the above first aspect, the above method further includes: the current road condition information of the target road section includes a reasonable risk level. And, based on the current characteristic information of the target object and/or the historical characteristic information of the target object, determining the current traffic condition information of the target road segment includes: determining the current traffic flow of the target road segment based on the current characteristic information of the target object and the historical characteristic information of the target object and collision accident information, as well as historical traffic flow and collision accident information. Based on the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information, the current road risk level of the target road section is determined.

In a possible implementation of the above first aspect, the above method further includes: the collision accident information includes at least one of the following: the number of collision accidents, the average relative acceleration of the collision vehicles, and the average relative speed of the collision vehicles.

In a possible implementation of the above first aspect, the above method further includes: based on the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information, determining the current road risk level of the target road section includes:

Based on the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information, the collision risk index parameters of the target road section are determined, wherein the collision risk index parameters include at least one of the following: the severity of the collision accident, the Exposure, the controllability of collision accidents.

Based on the collision risk index parameters of the target road segment, the current road risk level of the target road segment is determined.

In a possible implementation of the above first aspect, the above method further includes: the current road risk level R _dynamic is calculated by the following formula:

R _dynamic = S*E*C

Among them, S represents the severity of the collision accident. C represents the controllability of the collision accident, and E represents the exposure degree of the collision accident.

In a possible implementation of the above first aspect, the above method further includes: based on the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information, determining the collision risk index parameters of the target road section includes:

Based on the number of current and historical collision accidents on the target road section, the average relative acceleration of the collision vehicle, and the average relative speed of the collision vehicle, the severity of the collision accident on the target road section is determined.

In a possible implementation of the above first aspect, the above method further includes: the number of collision accidents includes: the number of vehicle-to-vehicle collisions, the number of vehicle-to-person collisions, and the number of vehicle-to-obstacle collisions.

The severity S of the collision accident is calculated by the following formula:

S＝α ₀ v _r exp(β ₀ a _r )*(α ₁ *N _CC +α ₂ *N _CO +α ₃ *N _CP )*exp(β ₁ N _death )

Among them, v _r represents the average relative velocity of the colliding vehicle, a _r represents the average relative acceleration of the colliding vehicle, N _CC represents the number of vehicle-to-vehicle collisions, N _CO represents the number of vehicle-to-obstacle collisions, and N _CP represents the number of vehicle-to-person collisions α ₀ , α ₁ , α ₂ , α ₃ , β ₀ , and β ₁ represent the weight parameters respectively, N _death represents the number of fatalities in collision accidents on the current and historical target road sections, and exp represents the exponential function.

The controllability of the collision accident of the target road section is determined based on the average relative acceleration of the collision vehicle and the average relative speed of the collision vehicle in the current and historical target road sections.

In a possible implementation of the above first aspect, the above method further includes: the controllability C of the collision accident of the target road section is calculated by the following formula:

Among them, a _r represents the average relative acceleration of the colliding vehicle, v _r represents the average relative velocity of the colliding vehicle, β ₂ represents the weight parameter, N _death represents the number of fatalities in the current and historical target road section collision accidents, and exp represents the exponential function.

Based on the current and historical traffic flow of the target road section and the number of collision accidents, the exposure degree of the collision accident of the current target road section is determined.

In a possible implementation of the above first aspect, the above method further includes: the exposure E of the collision accident is calculated by the following formula:

Among them, N _accident represents the number of collision accidents, and N _total represents the traffic flow.

In a possible implementation of the above first aspect, the above method further includes: the current road condition information of the target road section includes characteristic information of sensitive traffic participants.

Based on the current characteristic information of the target object and/or the historical characteristic information of the target object, determining the current road condition information of the target road section includes:

Based on the current characteristic information of the target object, the sensitive traffic participants are screened out from the target object, and the current characteristic information of the sensitive traffic participants is determined, wherein the sensitive traffic participants include at least one of the following: pedestrians, heavy trucks, bicycles, vans, etc. van.

In the second aspect, the embodiment of the present application provides a readable medium, and instructions are stored on the readable medium, and when the instructions are executed on the electronic device, the electronic device executes the above-mentioned first aspect and various possible implementations of the first aspect. Any road condition detection method.

In a third aspect, the embodiment of the present application provides an electronic device, including:

The memory is used to store instructions executed by one or more processors of the electronic device, and the processor is one of the processors of the electronic device, used to implement the above first aspect and various possible implementations of the first aspect Any road condition detection method.

In a fourth aspect, an embodiment of the present application provides a computer program product, including computer programs/instructions, and when the computer programs/instructions are executed by a processor, any one of the above-mentioned first aspect and various possible implementations of the first aspect can be realized. Road condition detection method.

Description of drawings

Fig. 1 is according to the embodiment of the present application, has shown a kind of scene diagram of road condition detection;

Fig. 2 is an embodiment according to the present application, showing another scene diagram of road condition detection;

FIG. 3 is a flow chart showing a road condition detection according to an embodiment of the present application;

FIG. 4 is a flow chart showing another road condition detection according to an embodiment of the present application;

FIG. 5 is a flow chart showing another road condition detection according to an embodiment of the present application;

Fig. 6 is a block diagram showing a consistent electronic device according to an embodiment of the present application.

Detailed ways

Illustrative embodiments of the present application include, but are not limited to, road condition detection methods, readable media, and electronic devices.

In order to solve the above problems, the present application proposes a road condition detection method applied to electronic equipment. The method includes: by obtaining the video stream collected in real time by the camera set on the target road section, performing target detection on each frame of image in the video stream, determining each target object and the position of each target object in each frame of image, and according to the continuous multi-frame image The location of each target object in the target object is determined, and the feature information corresponding to each target object is determined, and the feature information includes motion state information and/or position state information. Wherein, the motion state information may be information such as speed and acceleration, and the position state information may be position coordinates in the world coordinate system. According to the characteristic information of the current target objects of the road section and the characteristic information of the historical target objects of the road section, the current road condition information of the target road section is determined, and then the current road condition information of the target road section is sent to vehicles within the preset range of the target road section . Wherein, the current road condition information of the target road segment may be the road risk level of the target road segment.

It can be understood that the above target objects may be various vehicles, such as bicycles, cars, heavy trucks and so on. The vehicles within the preset range of the target road section may be vehicles on the target road section, or vehicles within a preset distance from the target road section.

Wherein, according to the feature information of each current target object (each vehicle) of the road section, and the feature information of each target object of the history of the road section, the specific way of determining the current road condition information of the target road section (taking the road risk level as an example) can be as follows:

According to the current characteristic information of each vehicle in the road section and the historical position of each vehicle in the road section, the current and historical traffic flow and collision accident information of the target road section can be determined, wherein the collision accident information can include the number of collision accidents. It can be understood that, for example, when the distance between the positions of the two vehicles is within a certain range, it can be determined that the two vehicles have collided. The road risk level of the target road section can be determined according to the current moment and the traffic flow and the number of vehicle collision accidents in the past period of time. For example, when the traffic flow and the number of vehicle collision accidents at the current moment and in the past period of time are relatively large, the road risk level is relatively high; relatively low.

It can be understood that the electronic device in the embodiment of the present application may specifically be a roadside device, a server, or a vehicle or other device, and this application does not specifically limit the type of the electronic device according to the actual application.

It can be understood that the road condition detection method of the present application can be applied to automatic driving scenarios, manual driving scenarios, or unmanned driving scenarios. Not specifically limited.

For the convenience of understanding, terms related to road risk levels in this article, for example, the term "severity" can refer to the extent to which relevant people and property will suffer damage once the risk becomes a reality. "Exposure rate" can refer to the probability that people or property may be affected when a risk occurs. "Controllability" can refer to the extent to which the driver can take active measures to avoid damage when a risk occurs.

In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be described in detail below in conjunction with FIG. 1 to FIG. 6 .

Fig. 1 shows a road condition detection scene diagram according to an embodiment of the present application. The scene in Fig. 1 includes: road section A, road section B, road section C, and road section D. As shown in FIG. 1 , the electronic device 100 may be a roadside device. Wherein, the roadside equipment 100 is arranged on the roadside of the A section.

As shown in FIG. 1 , taking road section A as an example, a camera 200 - 1 , a camera 200 - 2 , and a camera 200 - 3 are installed on road section A. Section A also includes multiple target objects, the multiple target objects are vehicle 300-1, collision vehicle 300-2, collision vehicle 300-3, pedestrian 300-4, pedestrian 300-5, and pedestrian 300-6.

As shown in FIG. 1 , the camera 200 - 1 , the camera 200 - 2 , and the camera 200 - 3 are used to collect video streams on road section A in real time, and send the video streams to the roadside device 100 .

As shown in FIG. 1 , the roadside device 100 is used to receive the video streams on the road section A collected by the cameras 200-1 to 200-3 in real time, and determine the target of the road section A according to the video streams on the road section A collected by the cameras 100 Object information, wherein, the target object information of the section A is used to describe the position of the vehicle 300-1, the collision vehicle 300-2, the collision vehicle 300-3, the pedestrian 300-4, the pedestrian 300-5, and the pedestrian 300-6 in the section A and/or exercise status. The roadside device 100 is further configured to determine the road condition information of the A section based on the characteristic information of the target object of the A section, and send the A section's road condition information to vehicles within a preset range of the A section. Wherein, the vehicle that has received the road condition information can adjust the driving speed of the vehicle on the road section A according to the road condition information.

For example, as shown in Figure 1, when the vehicle 300-1 enters the road section A, it receives the road risk level of the section A sent by the electronic device 100 in real time. According to the road risk level, the driving speed of the vehicle 300-1 on the section A can be adjusted from 100Km/h to 30Km/h.

It can be understood that the road condition information on the road section A can be used to assist the driver or the self-driving vehicle to adjust the driving speed of the vehicle on the road section A. After the vehicles within the preset range of A section receive the road condition information of A section, they can predetermine whether to adjust the driving of the vehicle on A section before the self-driving vehicle is in A section or before entering A section according to the A section's road condition information speed. The accuracy of autonomous vehicle control is improved, further improving the safety and driving experience of autonomous vehicles.

It can be understood that, as shown in FIG. 1 , the roadside device 10 may also obtain video streams collected by cameras of road sections B, C, and D, and generate road sections B, Road condition information of C road section and D road section.

As shown in FIG. 1 , the roadside equipment 100 is installed on the roadside of section A. In some other embodiments, other roadside equipment can also be installed on the roadsides of section B, section C, and section D respectively. Other roadside devices can also obtain the video streams collected by the cameras of road sections B, C, and D respectively, and generate road condition information for road sections B, C, and D based on the video streams collected for road sections B, C, and D. . It can be understood that the scene ratio of this application is not limited to the scene shown in FIG. 1 , and the specific location and quantity of roadside equipment installed on the roadside are not specifically limited in this application according to actual applications.

The roadside equipment 100 can be infrastructure equipment or fixed equipment or roadside unit (Road Side Unit, RSU) set on the roadside, or can be a vehicle-to-everything (V2X) set on the roadside ) Applied equipment. It can be understood that, according to practical applications, the present application does not limit the roadside equipment 100 .

Fig. 2 shows another road condition detection scene diagram according to an embodiment of the present application. Compared with the scenario in FIG. 1 , in the scenario in FIG. 2 , the electronic device 100 may be a remote server.

As shown in Figure 2, taking section A as an example, the server 100 is used to receive in real time the video streams on section A collected by cameras 200-1 to 200-3, and The video stream on the road segment determines the target object information on the A road segment, wherein the target object information on the A road segment is used to describe the position and/or motion state of the target object on the target road segment. The server 100 is further configured to determine road condition information of the road section A based on the target object information of the road section A, wherein the road condition information of the road section A is used to adjust the driving speed of the vehicle on the road section A. The server 100 is also used to send the road condition information of the road section A to the vehicles within the preset range of the road section A.

It can be understood that the server 100 is also used to receive the video streams captured by the cameras of the road sections B, C, and D, and generate the video streams of the road sections B, C, and D according to the video streams collected for the road sections B, C, and D. traffic information. For specific content, refer to the content described in section A, and details will not be repeated here.

It can be understood that the server 100 can be a hardware server, and the server 100 can be an independent physical server, or a server cluster composed of multiple physical servers, or a server that provides basic cloud computing services such as cloud database, cloud storage, and CDN. According to practical applications, this embodiment of the present application does not limit this.

It can be understood that, in the scenario of FIG. 1 or FIG. 2 , the camera 200-1, the camera 200-2, the camera 200-3, and the electronic device 100 may be communicatively connected through one or more networks. Wherein, the network may be a wired network or a wireless network, for example, the wireless network may be a mobile cellular network (such as 5G, 4G, 3G or GPRS), or may be a Wireless-Fidelity (WIFI) network, of course It may also be other possible networks, which are not limited in this embodiment of the present application. For example, the cameras 200-1 to 200-3 send the video streams collected in real time on the section A to the electronic device 100 through the wired network.

It can be understood that, in the scenario shown in FIG. 1 or FIG. 2 , the electronic device 100 and the vehicles within the preset range of the road segment A may be in communication connection through one or more wireless networks. For example, the wireless network can be a mobile cellular network (such as 5G, 4G, 3G or GPRS), or it can be a Wireless-Fidelity (Wireless-Fidelity, WIFI) network, and of course it can also be other possible networks. Do limit. For example, the electronic device 100 sends the road condition information of the road section A to the vehicles within the preset range of the road section A through the wireless network.

It can be understood that the camera for collecting the video stream of the road section in the present application can be a 360-degree rotating camera (i.e., the camera 200-1), and can also be a long-range camera, a zoom camera, a close-up camera, a flash camera, a buckle camera, and a speed camera.

It can be understood that the electronic device 100 to which the road condition detection method of the present application is applied may be the roadside device in the scenario in FIG. 1, or the server in the scenario in FIG. 2, or a car machine, a laptop computer, a desktop computer, or a tablet computer , mobile phone, wearable device, head-mounted display, mobile email device, portable game console, portable music player, reader device, or other electronic device capable of accessing the Internet. In some implementations, embodiments of the present application may also be applied to wearable devices worn by users. For example, smart watches, bracelets, jewelry (eg, devices made into decorative items such as earrings, bracelets), or glasses, or as part of watches, bracelets, jewelry, or glasses, etc. According to practical applications, the embodiment of the present application does not limit the electronic device 100 .

Based on the above scenario, FIG. 3 shows a flow chart of road condition detection. The execution subject in FIG. 3 is the electronic device 100, as shown in FIG. 3 , specifically including:

S301: Obtain the target object of the target road segment in real time.

In some embodiments, the electronic device 100 acquires a video stream shot on the target road section, performs target detection on each frame of image in the video stream, and determines the target object in each frame of image.

In some embodiments, the target object may include at least one of the following: a colliding vehicle, a bicycle, a car, a heavy truck, and the like. In some other embodiments, the target object may also include stagnant objects such as stagnant water and roadblocks. It can be understood that, according to practical applications, the present application does not limit the type of the target object of the target road segment.

For example, as shown in FIG. 1 , taking road section A as an example, the electronic device 100 can analyze the video stream according to the target detection algorithm based on the video of the road section A captured by the cameras 200-1 to 200-3 set on the road section A acquired in real time. The target object detection is performed on each frame of the image, and the target object appearing in each frame of the video stream is obtained.

S302: Determine feature information corresponding to the target object according to the target object of the target road section acquired in real time.

In some embodiments, the electronic device 100 determines the feature information corresponding to the target object according to the target object of the target road section acquired in real time. The feature information corresponding to the target object may include: motion state information and position state information of the target object. The position status information of the target object on the target road section may be the position coordinates of the target object on the target road section. The motion state information of the target object on the target road section may be information such as speed and acceleration.

In some embodiments, after the electronic device 100 detects the target object in each frame of image, it may also determine the motion state information of the target object through a speed detection algorithm. For example, the speed detection algorithm is used to determine the running time Δt of the target object based on the frame rate of the camera that collects the video stream, and obtain the actual running distance ΔS of the target object by calculating the coordinates of the three-dimensional space for the position of the target object, and then calculate Get the instantaneous speed or average speed V or acceleration a of the target object. The information for determining the target object will be described in detail below, and details will not be repeated here.

In some embodiments, the above-mentioned target object in each frame of image may also include static objects such as stagnant water and roadblocks, then determine the position of the target object in each frame of image, determined according to the position of the target object in consecutive multiple frame images The characteristic information of the target object and the location status information of the target object may be the location of water accumulation in the target road section, the location of roadblocks in the target road section, and the like. The state information of the target object may be that the speed is 0 or the acceleration is 0, etc.

S303: Based on the characteristic information of the target object of the target road segment, determine the traffic condition information of the target road segment, and the traffic condition information of the target road segment is used to describe the road condition of the target road segment.

In some embodiments, in addition to the road risk level of section A, the road condition information of section A may also include sensitive traffic participants of section A, traffic flow of section A, water depth of section A, and roadblock location of section A wait.

In some embodiments, the electronic device 100 determines the road condition information of the target road segment based on the target object information of the target road segment, and the road condition information of the target road segment is used to describe the road condition of the target road segment. According to the road condition information of the target road segment, the vehicle can adjust the running state (for example, deceleration, parking, etc.) or running trajectory (for example, the running route of the automatic driving vehicle) of the autonomous vehicle in time before entering the target road segment or when the target road segment is in progress, Thereby ensuring the driving safety of self-driving vehicles.

In some embodiments, the road condition information of the target road segment may be the road risk level of the target road segment. For example, the electronic device 100 can determine the colliding vehicle on the target road section at the current moment and the past period of time according to the relative position of the vehicle at the current moment and the past period of time, and according to the current moment and the relative position of the vehicle during the past period of time, the speed, Acceleration, etc. determine the road risk level of the target road section.

Specifically, taking the target object as a vehicle, the electronic device 100 determines the collision accident information and the cumulative number of vehicles on the target road segment at the current moment and in the past preset time period based on the vehicle information of the target road segment acquired in real time. Wherein, the collision accident information includes at least one of the following: the cumulative number of vehicle collision accidents, the average relative speed of vehicle collision, the average relative acceleration of vehicle collision, etc., wherein the cumulative number of vehicle collision accidents includes: the number of vehicle-to-vehicle collision accidents , the number of car-obstacle collision accidents, the number of car-pedestrian collision accidents, etc.

In some embodiments, the electronic device 100 determines the characteristic information of the colliding vehicle on the target road section at the current moment and within the past preset time period according to the target object information of the target road section acquired in real time and the target object information of the target road section in the past preset time period , based on the characteristic information of the colliding vehicle on the target road section at the current moment and the past preset time period, determine the collision accident information of the target road section at the current moment and the past preset time period. Taking the target object as the vehicle in FIG. 1 as an example, as shown in FIG. 1 , according to the position states of the vehicles 300-2 and 300-3, it is determined that the vehicle 300-2 collides with the vehicle 300-3. Therefore, the relative speed and relative acceleration of the vehicle 300-2 and the vehicle 300-3 at the time of the collision are obtained respectively.

Further, the electronic device 100 determines the collision risk index parameters of the target road segment according to the collision accident information of the target road segment in the past preset time period, and determines the road risk level of the target road segment according to the collision risk index parameters of the target road segment. Wherein, the collision risk index parameter of the target road section includes at least one of the following: severity of collision accident, exposure degree of collision accident, and controllability of collision accident. The following describes in detail how the electronic device 100 determines the road risk level of the target road segment based on the target object information of the target road segment, and details are not repeated here.

In some embodiments, the road condition information of the target road segment may be sensitive traffic participants of the target road segment. Specifically, the electronic device 100 screens out sensitive traffic participants of the target road segment based on the target object information of the target road segment, wherein the characteristic information of the sensitive traffic participant may include at least one of the following: the position of the sensitive traffic participant on the target road segment, driving speed and driving acceleration.

In some embodiments, in urban road traffic, sensitive traffic participants may include, but are not limited to: pedestrians, bicycles, strollers, people in wheelchairs, and the like. In expressway traffic, sensitive traffic participants include but are not limited to large trucks, vans, etc.

In some other embodiments, the road condition information of the target road segment may also be the traffic volume of the target road segment, the depth of water accumulation of the target road segment, the location of roadblocks of the target road segment, and the like. It can be understood that the road condition information of the target road section can be used by the self-driving vehicle to adjust the vehicle's running state (for example, deceleration, parking, etc.) or running track (for example, the running route of the self-driving vehicle) on the target road section, so as to ensure driving safety.

S304: Sending road condition information to vehicles within the preset range of the target road section.

In some embodiments, the electronic device 100 sends assisted driving information to vehicles within the preset range of the target road section, and the vehicle can predetermine Whether to adjust the driving speed of the vehicle on the target road section. The accuracy of autonomous vehicle control is improved, further improving the safety and driving experience of autonomous vehicles.

According to the road condition detection method described in FIG. 3 above, the electronic device 100 determines the road condition information of the target road section according to the target object information of the target road section acquired in real time, and sends the road condition information of the target road section to the preset range of the target road section in real time. vehicle. Wherein, the road condition information of the target road section may include information such as road risk level, sensitive traffic participants, traffic flow, water depth, and roadblock location.

It is not difficult to see that according to the road condition detection method of the present application, the electronic device 100 can update the road condition information of the target road section in real time, and the road condition information of the target road section can be used to assist the driver or the self-driving vehicle to adjust the driving speed of the vehicle on the target road section. Vehicles within the preset range of the target road segment can obtain the road condition information of the target road segment in real time, and the driver or the self-driving vehicle can know the road segment information of the target road segment in real time according to the road condition information of the target road segment, so that the vehicle is within the target road segment or enters the target road segment. Before the road section, it is determined in advance whether to adjust the driving speed of the self-driving vehicle on the target road section. Improving the accuracy of autonomous vehicle control further improves the safety and driving experience of autonomous vehicles.

In some embodiments, the road condition information of the target road section may be the road risk level. The following describes in detail in conjunction with FIG. The grade is sent to vehicles within the preset range of the target road segment.

Based on the road condition detection scene in FIG. 1 or FIG. 2, FIG. 4 shows a flowchart of another road condition detection method. The execution subject of the process in FIG. 4 is the electronic device 100, as shown in FIG. 4, specifically including:

S401: Obtain in real time a video stream collected by at least one camera on section A.

For example, as shown in FIG. 1, the electronic device 100 obtains video streams related to road section A collected by cameras 200-1 to 200-3 on road section A, and may also obtain video streams related to road section B collected by three cameras on road section B. The video stream may also obtain video streams related to road segment C captured by two cameras on road segment C, and may also acquire video streams related to road segment C collected by two cameras on road segment D. Hereinafter, taking the target road section as the road section A as an example, the process of road condition detection in FIG. 4 will be described in detail.

S402: Determine a real-time target object and feature information corresponding to the target object on the road section A based on the video stream of the section A acquired in real time.

In some embodiments, the electronic device 100 determines the feature information corresponding to the target object according to the target object of the section A acquired in real time. The feature information corresponding to the target object may include: motion state information and position state information of the target object. The position state information of the target object on the A road segment may be the position coordinates of the target object on the A road segment. The motion state information of the target object on section A may be information such as speed and acceleration.

In some embodiments, the electronic device 100 performs target object detection on each frame image of the video stream based on the obtained video stream of the road section A collected by the camera set on the road section A, and obtains all objects appearing in the video stream object. Specifically, target object detection may be performed on each frame image of the video stream through a target detection algorithm to obtain all target objects appearing in the video stream. For example, in the scene in FIG. 1, if the target object is set to be a car, it is detected by the target detection algorithm that there are three target objects on road section A, namely, vehicle 300-1, vehicle 300-2 and vehicle 300-3. . If the target object is set as a car and a person, it is detected by the target detection algorithm that there are six target objects on road section A, namely, vehicle 300-1, vehicle 300-2, vehicle 300-3, pedestrian 300-4, pedestrian 300-5, pedestrian 300-6. In some other embodiments, the target object can also be set as a colliding vehicle, a heavy truck, a van, or waterlogging and roadblocks on a road section. It can be understood that, according to practical applications, the present application does not limit the types of target objects on the road.

In some embodiments, the target detection algorithm is mainly used for traversing each frame image of the input video stream, classifying target objects and non-target objects in each frame image, and determining the position coordinates of the target object in each frame image. In some embodiments, a faster-region convolutional neural network architecture (faster-region convolutional neural networks, Faster RCNN) can be implemented through a cascade-region convolutional neural network architecture (cascade-region convolutional neural networks, cascade RCNN) algorithm Algorithm, a target detection (Single-Shot MultiBox Detector, SSD) algorithm, any target detection algorithm in the real-time fast target detection (You Only Look Once, YOLO) algorithm, etc. Detect, get all target objects appearing in the video stream.

In some embodiments, after the electronic device 100 detects the target object in each frame of image, it may also determine the speed, acceleration, etc. of the target object through a speed detection algorithm. For example, the speed detection algorithm is used to determine the running time Δt of the target object according to the frame rate of the camera that collects the video stream, and obtain the coordinates of the three-dimensional space through the positioning of the target object, so as to obtain the actual running distance ΔS of the target object, and then calculate Get the instantaneous speed or average speed V or acceleration a of the target object.

S403: According to the characteristic information corresponding to the real-time target object of the road section A and the characteristic information corresponding to the target object of the road section A in the past preset time period, determine the collision accident information of the road section A in the past preset time period.

In some embodiments, the electronic device 100 determines, according to the feature information corresponding to the real-time target object of the road segment A and the feature information corresponding to the target object of the road segment A in the past preset time period, within the preset time period in the past. Accumulated quantity of traffic flow (i.e. traffic flow) and collision accident information, the collision accident information of the section A can include at least one of the following: the cumulative quantity of vehicle collision accidents, the average relative speed when the vehicle collides, the average relative speed when the vehicle collides acceleration. Among them, the cumulative number of vehicle collision accidents includes: the number of vehicle-to-vehicle collision accidents, the number of vehicle-to-obstacle collision accidents, and the number of vehicle-to-pedestrian collision accidents.

Taking road section A as an example, the preset time period can be within the past year. For example, if the current time is 13:00 on December 24, 2021, the past year will be from 13:00 on December 24, 2020 to December 2021. At 13 o'clock on the 24th.

Specifically, the electronic device 100 determines the collision accident information of the road section A in the past preset time period according to the characteristic information corresponding to the real-time target object of the road section A and the characteristic information corresponding to the target object of the road section A in the past preset time period. . For example, it is determined that in the past year, the number of collision accidents on section A totaled 10, of which the number of car-vehicle collision accidents was 5 cases, the number of car-obstacle collision accidents was 3 cases, and the number of car-pedestrian collision accidents was 3. from 2. Then the average relative speed when the vehicle collides is: the average relative speed when the vehicles collide in 10 collision accidents. The average relative acceleration at the time of vehicle collision is: the average relative acceleration at the time of vehicle collision of 10 collision accidents. In a collision accident between vehicle E and vehicle F, the relative velocity at the time of vehicle collision is the velocity of vehicle E relative to vehicle F. Similarly, the relative acceleration at the time of vehicle collision is the acceleration of vehicle E relative to vehicle F. In a collision accident between vehicle X and obstacle Y, the relative speed of the vehicle at the time of collision is the speed of vehicle X, and similarly, the relative acceleration of the vehicle at the time of collision is the acceleration of vehicle X. In a collision accident between a vehicle M and a pedestrian N, the relative speed of the vehicle at the time of collision is the speed of the vehicle M relative to the pedestrian N. Similarly, the relative acceleration of the vehicle M during the collision is the acceleration of the vehicle M relative to the pedestrian N.

S404: Based on the collision accident information of the road section A in the past preset time period, determine the collision risk index parameters of the road section A, the collision risk index parameters of the road section A include at least one of the following: the severity of the collision accident, the exposure of the collision accident, Controllability of collision accidents.

For example, during the preset time period in the past, the collision accident information of section A includes the average relative speed when the vehicle collides, the average relative acceleration when the vehicle collides, the number of vehicle-to-vehicle collision accidents, the number of vehicle-to-obstacle collision accidents, Number of car-pedestrian collisions. The electronic device 100 may determine the number of collision accidents on road section A according to the average relative speed at the time of vehicle collision, the average relative acceleration at the time of vehicle collision, the number of vehicle-to-vehicle collision accidents, the number of vehicle-to-obstacle collision accidents, and the number of vehicle-to-pedestrian collision accidents. Severity.

In some embodiments, the electronic device 100 determines the severity S of the collision accident on the road section A in the past preset time period based on the collision accident information on the road section A in the past preset time period can be calculated by formula (1) :

S＝α ₀ v _r exp(β ₀ a _r )*(α ₁ *N _CC +α ₂ *N _CO +α ₃ *N _CP )*exp(β ₁ N _death ) (1)

In the formula (1), v _r represents the average relative velocity of vehicles on road section A when they collide within the preset time period, a _r represents the average relative acceleration of vehicles on road section A during the preset time period when they collide, and N _CC represents the expected The number of vehicle-to-vehicle collision accidents on road section A within the preset time period, N _CO represents the number of vehicle-to-obstacle collision accidents on road section A within the preset time period, α ₀ , α ₁ , α ₂ , α ₃ , β ₀ , _β1 represents the weight parameter. N _death represents the number of fatalities in collision accidents on section A within a preset time period. exp represents an exponential function. The * in this article means to multiply.

It is not difficult to understand that in the preset time period in the past, the higher the average relative speed of the collision of the vehicles on the A road section, the higher the severity of the collision accident on the A road section. In the preset time period in the past, the higher the average relative acceleration of the vehicle collision on the A road section, the higher the severity of the collision accident on the A road section. In the past preset time period, the higher the cumulative number of vehicle collision accidents on the A road section, the higher the severity of the collision accidents on the A road section. In the preset time in the past, the higher the death toll of the vehicle collision accident on the A road section, the higher the severity of the collision accident on the A road section.

For example, in the past preset period of time, the collision accident information on road section A includes the average relative speed when the vehicle collides, and the average relative acceleration when the vehicle collides. The electronic device 100 may determine, according to the average relative speed and the average relative acceleration of the collision of the vehicle on the road section A in the past preset time period, whether the collision accident on the road section A is controllable in the past preset time period. Spend. Specifically, in the past preset time period, the controllability C of the collision accident on road section A can be calculated by the following formula (2):

In the formula (2), a _r represents the relative acceleration of the collision accident on road section A in the past preset time period, v _r represents the relative velocity of the collision accident on road section A in the past preset time period, β ₂ Indicates the weight parameter. N _death represents the number of fatalities in collision accidents. exp represents an exponential function.

It is not difficult to understand that the higher the average relative speed of vehicles on road section A when they collide in the past preset time period, the lower the controllability of the collision accident on road section A in the past preset time period. In the past preset time period, the higher the average relative acceleration of the collision of the vehicles on the road section A, the lower the controllability of the collision accident on the road section A in the past preset time period. In the past preset time period, the higher the death toll of the vehicle collision accident on the road section A, the lower the controllability of the collision accident on the road section A in the past preset time period.

For example, in the past preset time period, the collision accident information of section A includes the cumulative number of vehicles passing and the cumulative number of vehicle collision accidents. The electronic device 100 may determine the exposure of collision accidents on road section A in the past preset time period according to the cumulative number of vehicles passing on road section A and the cumulative number of vehicle collision accidents in the past preset time period. Specifically, during the preset time period in the past, the exposure E of the collision accident on road section A can be calculated by the following formula (3):

In formula (3), N _accident represents the cumulative number of vehicle collision accidents on road section A in the past preset time period, and N _total represents the cumulative number of vehicle traffic on road section A in the past preset time period.

It is not difficult to understand that in the past preset time period, the higher the cumulative number of vehicle collision accidents on road section A accounted for in the cumulative number of vehicle traffic, the higher the exposure of collision accidents on road section A in the past preset time period. higher.

S405: Determine the road risk level of the road section A based on the collision risk index parameters of the road section A in the past preset time.

In some embodiments, the electronic device 100 determines the road risk index of the target road segment based on the collision risk index parameters of the target road segment within a preset time in the past. The electronic device 100 may determine the road risk level of the section A according to the value range of the road risk index corresponding to the pre-divided road risk level.

For example, the road risk level of section A includes four levels, namely 1, 2, 3, and 4, wherein 1 is the lowest level and 4 is the highest level. For example, the value range of the road risk index corresponding to the pre-divided road risk level 1 is [a, b], the value range of the road risk index corresponding to the pre-divided road risk level 2 is [c, d], and the pre-divided road The value range of the road risk index corresponding to risk level 3 is [e, f], and the value range of the road risk index corresponding to the pre-divided road risk level 4 is [g, h].

In some embodiments, the electronic device 100 determines the road risk index of the target road segment based on the collision risk index parameters of the target road segment within a preset time in the past. Specifically, the road risk index R _dynamic of the target road section can be calculated by formula (4):

R _dynamic = S*E*C (4)

Wherein, S represents the severity of collision accidents on road section A in the past preset time period. C represents the controllability of collision accidents on road section A in the past preset time period. E represents the exposure of collision accidents on section A in the past preset time period.

It is not difficult to see that the higher the severity of the collision accident on section A, the higher the road risk level on section A. The higher the controllability of the collision accident on section A, the higher the road risk level of section A. The higher the exposure degree of collision accidents on section A, the higher the road risk level of section A.

S406: Sending the road risk level of the section A to the vehicles within the preset range of the section A.

In some embodiments, the vehicles within the preset range of the road section A may be vehicles on the road section A, or vehicles within a preset distance from the road section A. For example, the preset distance may be 1 kilometer, and vehicles within the preset range of section A may adjust their vehicle speeds according to the received road risk level of section A. For example, in an automatic driving scenario, when the road risk level of the received section A is 3, the vehicle can automatically reduce the speed of the vehicle when it is a preset distance away from the section A or enters the section A. When the road risk level of section A received by the vehicle is 1, the vehicle does not need to adjust the speed, that is, maintains the original speed to pass the section A.

It can be seen from the above description that the electronic device 100 can obtain the video stream collected in real time by at least one camera on the road section A, and analyze the video stream collected in real time, and obtain the target object information of the road section A in real time. Object information to determine the road risk level of the A section. And the electronic device 100 can also update the road risk level of the A road section in real time, so that vehicles within the preset range of the A road section can know the road risk level of the A road section in real time, so that when the self-driving vehicle is in the A road section or enters the target Before the road section, according to the real-time understanding of the road risk level of section A, it is pre-determined whether to adjust the driving speed of the self-driving vehicle on the target road section. Improving the accuracy of autonomous vehicle control further improves the safety and driving experience of autonomous vehicles.

In some embodiments, the road condition information of the target road section may be sensitive traffic participants. The electronic device 100 determines the sensitive traffic of the target road section according to the target object of the target road section and the characteristic information of the target object obtained in real time in conjunction with FIG. Participants, and send sensitive traffic participants to vehicles within the preset range of the target road segment.

Based on the road condition detection scene in FIG. 1 or FIG. 2, FIG. 5 shows a flow chart of another road condition detection method. The execution subject of the process in FIG. 5 is the electronic device 100, as shown in FIG. 5, specifically including:

S501: Obtain in real time the video stream captured by at least one camera on the target road section. For details, refer to step S401, which will not be repeated here.

S502: Based on the video stream of the target road section acquired in real time, determine the target object of the target road section and the feature information corresponding to the target object. For details, refer to step S402, which will not be repeated here.

S503: According to the type of the target object, select the sensitive traffic participants of the target road segment from the target objects of the target road segment.

As described in step S402 in FIG. 4 , the target object of the target road section may be a vehicle traveling on the target road section, or a pedestrian or the like. Specifically, it can be cars, trucks, vans, bicycles, pedestrians, baby carriages, etc.

In some embodiments, sensitive traffic participants are target objects that may affect the speed of vehicles on the road section. In urban road traffic, sensitive traffic participants include but are not limited to: pedestrians, bicycles, baby carriages, people in wheelchairs, etc. In expressway traffic, sensitive traffic participants include but are not limited to large trucks, vans, etc.

In some embodiments, the electronic device 100 obtains characteristic information corresponding to sensitive traffic participants based on filtering sensitive traffic participants of the target road segment from the target objects of the target road segment according to the type of the target object. Wherein, the characteristic information of the sensitive traffic participants of the target road section includes the position, driving speed and driving acceleration of the sensitive traffic participants in the target road section.

For example, at the current moment, the sensitive traffic participant p _n on section A can be expressed as (x _n , y _n , v _n , a _n ), where (x _n , y _n ) means that the sensitive traffic participant p _n is on A The position coordinates on the road section, v _n represents the speed of the sensitive traffic participant p _n at the current moment, and a _n represents the acceleration of the sensitive traffic participant p _n at the current moment. Specifically, as shown in FIG. 1 , road section A is an urban road, and sensitive traffic participants in road section A may include pedestrian 300-4, pedestrian 300-5, and pedestrian 300-6. Then the position information of the pedestrian 300-4 can be expressed as (x ₁ , y ₁ , v ₁ , a ₁ ), the position information of the pedestrian 300-4 can be expressed as (x ₂ , y ₂ , v ₂ , a ₂ ), and the pedestrian The position information of 300-4 can be expressed as (x ₃ , y ₃ , v ₃ , a ₃ ).

Because in step S502, the electronic device 100 determines the position state corresponding to the target object of the target road segment based on the video stream of the target road segment acquired in real time, if the position state corresponding to the target object is the position coordinate generated based on its own coordinate system, then in step S502 In S503, among the sensitive traffic participants in the target road section screened out from the location status of the target object in the target road section, the sensitive traffic participants' position coordinates included in the sensitive traffic participants are also generated based on the own coordinate system. Therefore, the electronic device 100 needs to convert the position coordinates of the sensitive traffic participants generated based on its own coordinate system into the position coordinates of the sensitive traffic participants generated based on the world coordinate system, and then convert the position coordinates of the sensitive traffic participants generated based on the world coordinate system to The location coordinates of sensitive traffic participants are sent to the vehicle on the target road segment.

In some embodiments, the electronic device 100 can generate the traffic based on the self-coordinate system based on the self-coordinate system-world coordinate system conversion matrix, the reference coordinates of the self-coordinate system, and the position coordinates of sensitive traffic participants generated based on the self-coordinate system. The position coordinates of the sensitive traffic participants are transformed into the position coordinates of the sensitive traffic participants generated based on the world coordinate system. Specifically, the location coordinates L of sensitive traffic participants generated based on the world coordinate system can be expressed by the following formula (5):

L＝M*P*N (5)

In formula (5), M represents the conversion relationship matrix between the self-coordinate system and the world coordinate system, N represents the reference coordinates of the self-coordinate system, and P represents the position coordinates of sensitive traffic participants generated based on the self-coordinate system.

S504: Send the sensitive traffic participants of the target road section and the characteristic information corresponding to the sensitive traffic participants to the vehicles within the preset range of the target road section.

In some embodiments, when the vehicle does not enter the target road segment, the vehicle speed can be adjusted according to the received positions and speeds of sensitive traffic participants in the target road segment. For example, as shown in Figure 1, in the automatic driving scenario, when the vehicle receives three sensitive traffic participants (i.e., pedestrian 300-4, pedestrian 300-5, and pedestrian 300-6) in section A, the vehicle automatically drives It can automatically reduce the speed of the self-driving vehicle when it does not enter the A road section or enters the A road section.

It can be understood that according to the road condition detection process described in FIG. 5 , the electronic device 100 can update the sensitive traffic participants of the target road segment in real time, and can send the sensitive traffic participants of the target road segment to vehicles within the preset range of the target road segment in real time. In this way, the vehicles within the preset range of the target road segment can know the sensitive traffic participants of the target road segment in real time, and can know the road segment information of the target road segment in real time according to the sensitive traffic participants of the target road segment, so that the automatic driving vehicle can enter or enter the target road segment. Before the target road section, it is determined in advance whether to adjust the driving speed of the self-driving vehicle on the target road section. Improving the accuracy of autonomous vehicle control further improves the safety and driving experience of autonomous vehicles.

Fig. 6 is a structural block diagram of an electronic device 100 according to an embodiment of the present application, and Fig. 6 schematically shows an example electronic device 100 according to multiple embodiments. In one embodiment, the electronic device 100 may include one or more processors 1404, a system control logic 1408 connected to at least one of the processors 1404, a system memory 1412 connected to the system control logic 1408, a system memory 1412 connected to the system control logic 1408 A non-volatile memory (NVM) 1416 is connected, and a network interface 1420 is connected to the system control logic 1408 .

In some embodiments, processor 1404 may include one or more single-core or multi-core processors. In some embodiments, processor 1404 may include any combination of general purpose processors and special purpose processors (eg, graphics processors, application processors, baseband processors, etc.). In an embodiment where the electronic device 100 adopts an eNB (Evolved Node B, enhanced base station) or a RAN (Radio Access Network, radio access network) controller, the processor 1404 may be configured to execute various consistent embodiments, for example , one or more of the multiple embodiments shown in FIG. 3 or FIG. 4 or FIG. 5 . For example, processing 1404 may be used to execute the above road condition-based detection method. For example, processing 1404 may be used to acquire video streams captured by at least one camera on road section A, determine target object information, and may also be used to target object information based on the target road section, Determine the road condition information of the target road section, etc.

In some embodiments, system control logic 1408 may include any suitable interface controller to provide any suitable interface to at least one of processors 1404 and/or any suitable device or component in communication with system control logic 1408 .

In some embodiments, system control logic 1408 may include one or more memory controllers to provide an interface to system memory 1412 . System memory 1412 can be used for loading and storing data and/or instructions. Memory 1412 of system 1400 may in some embodiments include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

NVM/memory 1416 may include one or more tangible, non-transitory computer-readable media for storing data and/or instructions. In some embodiments, NVM/memory 1416 may include any suitable non-volatile memory such as flash memory and/or any suitable non-volatile storage device, such as HDD (Hard Disk Drive, hard disk drive), CD (Compact Disc , CD) drive, DVD (Digital Versatile Disc, Digital Versatile Disc) drive at least one.

NVM/memory 1416 may comprise a portion of storage resources on the device on which electronic device 100 is installed, or it may be accessed by, but not necessarily part of, the device. For example, NVM/storage 1416 may be accessed over a network via network interface 1420 .

In particular, system memory 1412 and NVM/storage 1416 may include, respectively, temporary and permanent copies of instructions 1424 . The instructions 1424 may include: instructions that cause the electronic device 100 to implement the method shown in FIG. 1 when executed by at least one of the processors 1404 . In some embodiments, instructions 1424 , hardware, firmware and/or software components thereof may additionally/alternatively reside in system control logic 1408 , network interface 1420 and/or processor 1404 .

The network interface 1420 may include a transceiver for providing a radio interface for the electronic device 100 to communicate with any other suitable devices (such as front-end modules, antennas, etc.) through one or more networks. In some embodiments, the network interface 1420 may be integrated with other components of the electronic device 100 . For example, network interface 1420 may be integrated into at least one of processor 1404, system memory 1412, NVM/storage 1416, and a firmware device (not shown) with instructions, when at least one of processor 1404 executes the When instructing, the electronic device 100 implements the methods shown in FIG. 3 to FIG. 5 .

Network interface 1420 may further include any suitable hardware and/or firmware to provide a multiple-input multiple-output radio interface or a wired electrical interface. For example, network interface 1420 may be a network adapter, a wireless network adapter, a telephone modem and/or a wireless modem.

In one embodiment, at least one of the processors 1404 may be packaged with logic for one or more controllers of the system control logic 1408 to form a system in package (SiP). In one embodiment, at least one of the processors 1404 may be integrated on the same die with logic for one or more controllers of the system control logic 1408 to form a system on chip (SoC).

The electronic device 100 may further include: an input/output (I/O) device 1432 . The I/O device 1432 may include a user interface, enabling the user to interact with the electronic device 100 ; the design of the peripheral component interface enables the peripheral components to also interact with the electronic device 100 . In some embodiments, the electronic device 100 further includes a sensor for determining at least one of environmental conditions and location information related to the electronic device 100 .

In some embodiments, the user interface may include, but is not limited to, a display (e.g., a liquid crystal display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and/or a video camera), a flashlight (e.g., LED flash light) and keyboard.

In some embodiments, peripheral component interfaces may include, but are not limited to, non-volatile memory ports, audio jacks, and power interfaces.

In some embodiments, sensors may include, but are not limited to, gyroscope sensors, accelerometers, proximity sensors, ambient light sensors, and positioning units. The positioning unit may also be part of or interact with the network interface 1420 to communicate with components of the positioning network, such as global positioning system (GPS) satellites.

It can be understood that the structure shown in FIG. 6 does not constitute a specific limitation on the electronic device 100 . In some other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.

Various embodiments of the mechanisms disclosed in this application may be implemented in hardware, software, firmware, or a combination of these implementation methods. Embodiments of the present application may be implemented as a computer program or program code executed on a programmable system comprising at least one processor, a storage system (including volatile and non-volatile memory and/or storage elements) , at least one input device, and at least one output device.

Program code can be applied to input instructions to perform the functions described herein and to generate output information. The output information may be applied to one or more output devices in known manner. For the purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), microcontroller, application specific integrated circuit (ASIC), or microprocessor.

The program code can be implemented in a high-level procedural language or an object-oriented programming language to communicate with the processing system. Program code can also be implemented in assembly or machine language, if desired. In fact, the mechanisms described in this application are not limited in scope to any particular programming language. In either case, the language may be a compiled or interpreted language.

In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments can also be implemented as instructions carried by or stored on one or more transitory or non-transitory machine-readable (e.g., computer-readable) storage media, which can be executed by one or more processors read and execute. For example, instructions may be distributed over a network or via other computer-readable media. Thus, a machine-readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magnetic Optical discs, read-only memory (ROM), random-access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic or optical cards, flash memory, or A tangible, machine-readable memory used to transmit information (eg, carrier waves, infrared signals, digital signals, etc.) by electrical, optical, acoustic, or other forms of propagating signals using the Internet. Thus, a machine-readable medium includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, a computer).

In the drawings, some structural or methodological features may be shown in a particular arrangement and/or order. However, it should be understood that such specific arrangements and/or orderings may not be required. Rather, in some embodiments, these features may be arranged in a different manner and/or order than shown in the illustrative figures. Additionally, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments these features may not be included or may be combined with other features.

It should be noted that each unit/module mentioned in each device embodiment of this application is a logical unit/module. Physically, a logical unit/module can be a physical unit/module, or a physical unit/module. A part of the module can also be realized with a combination of multiple physical units/modules, the physical implementation of these logical units/modules is not the most important, the combination of functions realized by these logical units/modules is the solution The key to the technical issues raised. In addition, in order to highlight the innovative part of this application, the above-mentioned device embodiments of this application do not introduce units/modules that are not closely related to solving the technical problems proposed by this application, which does not mean that the above-mentioned device embodiments do not exist other units/modules.

It should be noted that in the examples and descriptions of this patent, relative terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply There is no such actual relationship or order between these entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Although this application has been shown and described with reference to certain preferred embodiments thereof, those skilled in the art will understand that various changes in form and details may be made therein without departing from this disclosure. The spirit and scope of the application.

Claims

A road condition detection method, used for electronic equipment, is characterized in that,

Obtain the video stream collected by the camera on the target road section;

According to the video stream, determine the current feature information of the target object on the target road section, wherein the feature information includes motion state information and/or position state information;

Based on the current characteristic information of the target object and/or the historical characteristic information of the target object, the current road condition information of the target road section is determined.
The method according to claim 1, further comprising:

Sending the current road condition information of the target road section to vehicles within a preset range of the target road section.
The method according to claim 1, wherein the target object includes at least one of the following: a vehicle, a person, and an obstacle.
The method according to claim 3, wherein the current road condition information of the target road section includes a reasonable risk level; and

The determining the current road condition information of the target road segment based on the current feature information of the target object and/or the historical feature information of the target object includes:

Based on the current characteristic information of the target object and the historical characteristic information of the target object, determine the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information;

The current road risk level of the target road section is determined based on the current traffic flow and collision accident information of the target road section, as well as historical traffic flow and collision accident information.
The method according to claim 4, wherein the collision accident information includes at least one of the following: the number of collision accidents, the average relative acceleration of the collision vehicles, and the average relative speed of the collision vehicles.
The method according to claim 5, characterized in that the current road risk level of the target road section is determined based on the current traffic flow and collision accident information of the target road section, as well as historical traffic flow and collision accident information include:

Based on the current traffic flow and collision accident information of the target road section, as well as the historical traffic flow and collision accident information, determine the collision risk index parameters of the target road section, wherein the collision risk index parameters include at least one of the following: the severity of the collision accident , the degree of exposure to collision accidents, and the degree of controllability of collision accidents;

Based on the collision risk index parameters of the target road section, the current road risk level of the target road section is determined.
The method according to claim 6, wherein the current road risk level R dynamic is calculated by the following formula:

R dynamic = S*E*C

Among them, S represents the severity of the collision accident. C represents the controllability of the collision accident, and E represents the exposure degree of the collision accident.
The method according to claim 6 or claim 7, wherein the collision risk index parameters of the target road section are determined based on the current traffic flow and collision accident information of the target road section, as well as historical traffic flow and collision accident information include:

Based on the number of current and historical collision accidents of the target road section, the average relative acceleration of the collision vehicle, and the average relative speed of the collision vehicle, the severity of the collision accident of the target road section is determined.
The method according to claim 8, characterized in that,

The number of collision accidents includes: the number of car-to-car collisions, the number of car-to-person collisions, and the number of car-to-obstacle collisions;

The severity S of the collision accident is calculated by the following formula:

S＝α 0 v r exp(β 0 a r )*(α 1 *N CC +α 2 *N CO +α 3 *N CP )*exp(β 1 N death )

Among them, v r represents the average relative velocity of the colliding vehicle, a r represents the average relative acceleration of the colliding vehicle, N CC represents the number of collisions between vehicles, N CO represents the number of collisions between vehicles and obstacles, and N CP represents The number of collisions between vehicles and people, α 0 , α 1 , α 2 , α 3 , β 0 , and β 1 represent the weight parameters respectively, N death represents the number of deaths in collision accidents in the current and historical target road sections, and exp represents the exponential function .
The method according to claim 6 or claim 7, wherein, based on the current traffic flow and collision accident information of the target road section, as well as historical traffic flow and collision accident information, determining the collision risk index parameters of the target road section includes:

Based on the average relative acceleration of the colliding vehicle and the average relative speed of the colliding vehicle in the current and historical target road section, the controllability of the collision accident of the target road section is determined.
The method according to claim 10, characterized in that,

The controllability C of the collision accident of the target road section is calculated by the following formula:

Among them, a r represents the average relative acceleration of the collision vehicle, v r represents the average relative velocity of the collision vehicle, β 2 represents a weight parameter, N death represents the number of deaths in current and historical collision accidents of the target road section, exp represents an exponential function.
The method according to claim 6 or claim 7, wherein, based on the current traffic flow and collision accident information of the target road section, as well as historical traffic flow and collision accident information, determining the collision risk index parameters of the target road section includes:

Based on the current and historical traffic flow of the target road section and the number of collision accidents, the exposure degree of the collision accident of the current target road section is determined.
The method according to claim 12, characterized in that,

The exposure E of the collision accident is calculated by the following formula:

Wherein, N accident represents the number of collision accidents, and N total represents the traffic flow.
The method according to claim 3, wherein the current road condition information of the target section includes characteristic information of sensitive traffic participants;

The determining the current road condition information of the target road segment based on the current feature information of the target object and/or the historical feature information of the target object includes:

Based on the current characteristic information of the target object, the sensitive traffic participants are screened out from the target object, and the current characteristic information of the sensitive traffic participants is determined, wherein the sensitive traffic participants include at least one of the following Types: Pedestrians, heavy trucks, bicycles, vans.
A readable medium, characterized in that instructions are stored on the readable medium, and when the instructions are executed on the electronic equipment, the electronic equipment executes the road condition detection method according to any one of claims 1 to 14.
An electronic device, characterized in that it comprises:

memory for storing instructions to be executed by one or more processors of the electronic device, and

The processor is one of the processors of the electronic device, configured to execute the road condition detection method according to any one of claims 1 to 14.