CN113628449A - Early warning method and system for driving safety risk - Google Patents
Early warning method and system for driving safety risk Download PDFInfo
- Publication number
- CN113628449A CN113628449A CN202110802901.2A CN202110802901A CN113628449A CN 113628449 A CN113628449 A CN 113628449A CN 202110802901 A CN202110802901 A CN 202110802901A CN 113628449 A CN113628449 A CN 113628449A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image sequence
- mounted terminal
- lane
- edge computing
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a driving safety risk early warning method and system, and relates to the technical field of driving safety. The method comprises the steps that a first vehicle-mounted terminal obtains a first image sequence in front of a current vehicle and a second image sequence behind the current vehicle, wherein the first image sequence is acquired by a depth camera; the first vehicle-mounted terminal identifies whether a pedestrian exists in a front lane according to the first image sequence; if the pedestrian is in the front lane, the first vehicle-mounted terminal sends the first image sequence and the second image sequence to an edge computing device in communication connection with the first vehicle-mounted terminal; the edge computing equipment identifies whether safety accident risks exist or not according to the first image sequence, and identifies the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence; and if the safety accident risk exists, the edge computing equipment sends early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number. The method and the system provided by the application can guarantee driving safety and avoid safety accidents.
Description
Technical Field
The application relates to the technical field of driving safety, in particular to a driving safety risk early warning method and system.
Background
With the development of social economy, the number of automobiles is increasing, and the driving safety becomes an important subject in daily life of people.
Among the traffic accidents that have occurred, there are many traffic accidents caused by pedestrians crossing lanes without complying with traffic regulations. At present, most drivers take corresponding measures according to the situation that the drivers observe the lane in front for the situation that the pedestrians cross the lane, however, due to the blockage of the vehicles in front, the drivers of the vehicles in the rear are likely not to observe the situation that the pedestrians cross the lane, and therefore safety accidents are often caused due to the fact that the corresponding measures cannot be taken timely.
Therefore, how to provide an effective solution to avoid the occurrence of safety accidents has become an urgent problem in the prior art.
Disclosure of Invention
The embodiment of the application provides a driving safety risk early warning method and system, which are used for solving the problem of safety accidents caused by the fact that pedestrians cross lanes in the prior art.
The embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for early warning of driving safety risk, including:
the method comprises the steps that a first vehicle-mounted terminal obtains a first image sequence in front of a current vehicle and a second image sequence behind the current vehicle, wherein the first image sequence is acquired by a depth camera;
the first vehicle-mounted terminal identifies whether a pedestrian exists in a front lane according to the first image sequence;
if the pedestrian exists in the front lane, the first vehicle-mounted terminal sends the first image sequence and the second image sequence to an edge computing device in communication connection with the first vehicle-mounted terminal;
the edge computing equipment identifies whether safety accident risks exist or not according to the first image sequence, and identifies the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence;
and if the safety accident risk exists, the edge computing equipment sends early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number so as to early warn the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
In one possible design, the edge computing device identifies whether a security incident risk exists based on the first sequence of images, including:
the edge computing device identifies the moving direction of the pedestrian in the lane according to the latest continuous multiframe images in the first image sequence, and identifies whether the safety accident risk exists according to the moving direction of the pedestrian in the lane.
In one possible design, identifying whether there is a risk of a safety accident based on a direction of movement of a pedestrian in the lane includes:
if the moving direction of the pedestrian in the lane is from one side of the lane to the other side of the lane, judging that the safety accident risk exists;
otherwise, judging that the safety accident risk does not exist.
In one possible design, the edge computing device identifies whether a security incident risk exists based on the first sequence of images, including:
the edge computing equipment extracts a face image of a pedestrian in the lane from the first image sequence;
searching the history crossing lane record of the pedestrian in the lane from a database of the server according to the face image;
identifying the age of the pedestrian in the lane according to the face image;
recognizing the moving direction and the moving speed of the pedestrian in the lane according to the latest continuous multi-frame image in the first image sequence; and
and calculating the historical lane crossing record, the age, the moving direction and the moving speed as the input of a pre-trained model to obtain an output result, wherein the output result represents that the lane crossing safety accident risk exists or the lane crossing safety risk does not exist.
In one possible design, the method further includes:
if the safety accident risk exists, the edge computing equipment sends a control signal to the traffic warning equipment connected with the roadside, so that the traffic warning equipment sends out a warning signal, and the traffic warning equipment is a variable information board or a loudspeaker.
In one possible design, the method further includes:
the edge computing equipment acquires vehicle identification information bound by a vehicle-mounted terminal which is connected with the edge computing equipment, wherein the vehicle identification information comprises a license plate number.
In one possible design, after the edge computing device sends the warning information to the first vehicle-mounted terminal, the method further includes:
and the first vehicle-mounted terminal marks the position of the target vehicle in the currently displayed navigation map according to the distance between the current vehicle and the target vehicle.
In one possible design, the method further includes:
the edge computing device establishes communication connection with the first vehicle-mounted terminal and the second vehicle-mounted terminal within the signal coverage range of the edge computing device.
In a second aspect, an embodiment of the present application provides an early warning system for driving safety risks, including a first vehicle-mounted terminal and an edge computing device that establishes a communication connection with the first vehicle-mounted terminal;
the first vehicle-mounted terminal is used for acquiring a first image sequence in front of the current vehicle and a second image sequence behind the current vehicle, which are acquired by the depth camera;
the first vehicle-mounted terminal is also used for identifying whether a pedestrian exists in the front lane according to the first image sequence;
the first vehicle-mounted terminal is further used for sending the first image sequence and the second image sequence to the edge computing device when a pedestrian exists in a front lane;
the edge computing equipment is used for identifying whether safety accident risks exist or not according to the first image sequence and identifying the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence;
and the edge computing equipment is also used for sending early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number when the identification result shows that the safety accident risk exists, so as to early warn the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
The above-mentioned at least one technical scheme that this application one or more embodiments adopted can reach following beneficial effect:
the first vehicle-mounted terminal obtains a second image sequence behind a first image sequence in front of a current vehicle, whether pedestrians exist in a lane in front is identified according to the first image sequence, when the pedestrians exist in the lane in front, the first image sequence and the second image sequence are sent to the edge computing device, whether safety accident risks exist or not is identified by the edge computing device according to the first image sequence, the license plate number of a target vehicle within a preset distance behind is identified according to the second image sequence, and then early warning information is sent to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number for early warning according to the identification result. Therefore, safety accident risks can be evaluated when pedestrians break into the lane, early warning is carried out on the vehicle owner of the front vehicle and the vehicle owner of the target vehicle with the rear distance being short when the safety accident risks crossing the lane exist, driving safety is guaranteed, and safety accidents are avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure in any way. In the drawings:
fig. 1 is a flowchart of an early warning method for driving safety risk provided in an embodiment of the present application.
Fig. 2 is a schematic structural diagram of an early warning system for driving safety risk provided in an embodiment of the present application.
Detailed Description
In order to ensure driving safety, the embodiment of the application provides a driving safety risk early warning method and a driving safety risk early warning system, and the driving safety risk early warning method and the driving safety risk early warning system can effectively avoid the problem of safety accidents caused by the fact that pedestrians cross lanes.
First, in order to more intuitively understand the scheme provided by the embodiment of the present application, a system architecture of the early warning scheme of driving safety risk provided by the embodiment of the present application is described.
The edge computing device is in communication connection with a first vehicle-mounted terminal on a vehicle within a signal coverage range of the edge computing device and a second vehicle-mounted terminal on a vehicle behind the vehicle through a network respectively so as to perform data interaction or communication. The edge computing device can be an embedded computer which accesses a network in a wireless mode and is arranged beside lanes of some important road sections.
The following describes in detail a driving safety risk early warning method provided in an embodiment of the present application.
As shown in fig. 1, the method is a flowchart of a driving safety risk early warning method provided in an embodiment of the present application, and the driving safety risk early warning method may include the following steps:
step S201, the first vehicle-mounted terminal obtains a first image sequence in front of the current vehicle and a second image sequence behind the current vehicle, which are acquired by the depth camera.
In the embodiment of the application, the first vehicle-mounted terminal is a vehicle-mounted terminal on a current vehicle, and the current vehicle is provided with a depth camera and is used for acquiring a first image sequence in front of the current vehicle and a second image sequence behind the current vehicle and sending the acquired first image sequence and second image sequence to the first vehicle-mounted terminal.
Step S202, the first vehicle-mounted terminal identifies whether a pedestrian exists in the front lane according to the first image sequence.
In the embodiment of the application, the lane in front of the vehicle can be identified through lane line identification, and then whether a pedestrian exists in the lane in front is identified through contour identification. Lane line recognition and contour recognition are prior art, and are not described in detail in the embodiments of the present application.
In step S203, if there is a pedestrian in the lane ahead, the first vehicle-mounted terminal transmits the first image sequence and the second image sequence to the edge calculation device communicatively connected thereto.
If the pedestrian exists in the front lane, the first vehicle-mounted terminal sends the obtained first image sequence and the second image sequence to the edge computing device in communication connection with the first vehicle-mounted terminal, so that the edge computing device can judge whether the safety risk exists or not.
In the embodiment of the application, before the first vehicle-mounted terminal establishes the communication connection with the edge computing device, the current vehicle needs to be driven into the signal coverage range of the edge computing device. Then, a communication connection is established with the edge computing device after driving into the signal coverage of the edge computing device.
And S204, the edge computing equipment identifies whether a safety accident risk exists according to the first image sequence, and identifies the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence.
The edge computing device may take a variety of ways in identifying whether a security risk exists. In one possible design, when identifying whether the safety risk exists, the edge computing device may identify the moving direction of the pedestrian in the lane according to the latest continuous multiframe image in the first image sequence, and then identify whether the safety accident risk exists according to the moving direction of the pedestrian in the lane.
More specifically, the moving direction of the pedestrian may be determined based on the position of the pedestrian in the latest continuous multi-frame image in the image. For example, in the latest continuous multi-frame image, the position of the pedestrian in the latter frame image is closer to the middle position of the lane than the position of the pedestrian in the former frame image, and it is determined that the moving direction of the pedestrian is from one side of the lane to the other side of the lane, at which time it can be determined that there is a risk of a safety accident.
In one possible design, the edge computing device may also identify whether a security risk exists through a pre-established neural network model, which includes, but is not limited to, the steps of:
in step S2041, the edge calculation device extracts a face image of a pedestrian in the lane from the first image sequence.
In step S2042, the edge computing device finds out the history of the pedestrian crossing lane record in the lane from the database of the server according to the face image.
Wherein the server can be a server of a traffic management department, the database of the server records the records of all the pedestrians crossing the lane shot before the server,
after the edge computing device extracts the face image of the pedestrian in the lane, the extracted face image can be matched with the face image of the pedestrian corresponding to the transverse vehicle record in the database to obtain the historical transverse lane record of the pedestrian in the lane. In the embodiment of the application, the history of crossing lanes of the pedestrians in the lanes refers to the history of the number of times that the pedestrians in the lanes cross the lanes.
In step S2043, the edge calculation device identifies the age of the pedestrian in the lane from the face image.
In step S2044, the edge calculation apparatus recognizes the moving direction and moving speed of the pedestrian in the lane from the latest continuous multi-frame image in the first image sequence.
In this step, the moving direction of the pedestrian in the lane is identified to be consistent with the process of identifying the moving direction of the pedestrian, and the detailed description is omitted here.
In the embodiment of the present application, the lens of the depth camera may be disposed toward the vehicle traveling direction. For the moving speed, the distance between the pedestrian and the vehicle in the direction perpendicular to the lane can be obtained according to the connecting line between the current vehicle and the pedestrian in the image, the included angle between the connecting line and the image in the vertical direction (lane direction) and the distance between the current vehicle and the pedestrian (which can be directly obtained by a depth camera), and the moving speed of the pedestrian can be obtained according to the distance between the pedestrian and the vehicle in the direction perpendicular to the lane in two adjacent frames of images, the moving direction of the pedestrian and the time stamps of the two adjacent images.
In step S2045, the history of crossing lanes, age, moving direction, and moving speed are calculated as inputs to a model trained in advance, and an output result is obtained.
Wherein the output is indicative of the presence or absence of a lane crossing safety risk.
In the embodiment of the application, a training model for evaluating whether the safety risk of crossing lanes exists is established in advance, and the training film is obtained by training by taking the history of crossing lane records, ages, moving directions and moving speeds of a large number of pedestrians crossing lanes and pedestrians not crossing lanes as the input of the model and taking the result of crossing lanes as the output of the model.
The history of the pedestrians in the lane crossing lane record, the age, the moving direction and the moving speed can be quantized to obtain 4 vectors, the 4 vectors are spliced to obtain spliced vectors, then the spliced vectors are used as the input of a model to be operated to obtain an output result, and the output result represents the safety accident risk or the safety risk of the pedestrians in the lane crossing lane.
In the embodiment of the present application, the model may be, but is not limited to, a classification model of a Support Vector Machine (SVM), a Back Propagation Neural Network (BP) model, and the like.
Meanwhile, the edge computing device can also identify the target vehicle within a preset distance behind the current vehicle, the preset distance can be set according to actual conditions, and it is ensured that when the current vehicle decelerates suddenly and stops, the rear vehicle exceeding the preset distance can have enough time to react. Then the edge computing equipment identifies the license plate number of the target vehicle within a preset distance behind the current vehicle through license plate identification
Step S205, if the safety accident risk exists, the edge computing device sends early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number so as to give early warning to the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
In the embodiment of the application, before the edge computing device sends the early warning information to the second vehicle-mounted terminal, a target vehicle needing to be provided with the second vehicle-mounted terminal enters a signal coverage range of the edge computing device and establishes connection with the edge computing device, meanwhile, the second vehicle-mounted terminal uploads vehicle identification information of the target vehicle corresponding to the second vehicle-mounted terminal to the edge computing device, and the vehicle identification information at least comprises a license plate number so that the license plate number of the target vehicle is bound with the second vehicle-mounted terminal at the edge computing device.
If the identified structure is that safety accident risk exists, the edge computing device sends early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number to give an early warning to a vehicle owner on the current vehicle and a vehicle owner on a target vehicle corresponding to the second vehicle-mounted terminal, so that corresponding avoidance measures can be taken according to the early warning when the current vehicle is close to the rear vehicle, and safety accidents caused by the fact that the vehicle close to the rear cannot observe that a pedestrian crosses a lane and does not take corresponding measures in time after the front vehicle takes the avoidance measures are avoided.
Furthermore, in this embodiment of the application, if the identification result indicates that there is a safety risk, the edge computing device may further send a control signal to a roadside traffic warning device connected to the edge computing device, so that the traffic warning device sends a warning signal, where the traffic warning device may be a variable message sign or a speaker. Therefore, the traffic warning equipment can send out warning signals to remind pedestrians crossing the lane, and the occurrence of traffic accidents is slowed down.
In addition, the first vehicle-mounted terminal can mark the position of the target vehicle in the currently displayed navigation map according to the distance between the current vehicle and the target vehicle so as to remind a driver on the current vehicle.
According to the early warning method for the driving safety risk, a second image sequence behind a first image sequence in front of a current vehicle is obtained through a first vehicle-mounted terminal, whether pedestrians exist in a lane in front is identified according to the first image sequence, when the pedestrians exist in the lane in front, the first image sequence and the second image sequence are sent to an edge computing device, whether safety accident risks exist or not is identified through the edge computing device according to the first image sequence, a license plate number of a target vehicle within a preset distance behind is identified according to the second image sequence, and then early warning information is sent to the first vehicle-mounted terminal and a second vehicle-mounted terminal bound with the license plate number for early warning according to the identification result. Therefore, safety accident risks can be evaluated when pedestrians break into the lane, early warning is carried out on the vehicle owner of the front vehicle and the vehicle owner of the target vehicle with the short rear distance when the safety accident risks crossing the lane exist, corresponding avoidance measures can be taken according to the early warning on the current vehicle and the vehicle with the short rear distance, and the situation that after the avoidance measures are taken on the front vehicle, the vehicle with the short rear distance does not take the corresponding measures in time and further causes safety accidents due to the fact that the pedestrians cross the lane cannot be observed is avoided, and driving safety is guaranteed. Meanwhile, the edge computing equipment can also send a control signal to the traffic warning equipment connected with the roadside so as to enable the traffic warning equipment to send out a warning signal. Therefore, the traffic warning equipment can send out warning signals to remind pedestrians crossing the lane, and the occurrence of traffic accidents is slowed down.
In a second aspect, please refer to fig. 2, an embodiment of the present application further provides an early warning system for driving safety risk, including a first vehicle-mounted terminal and an edge computing device that establishes a communication connection with the first vehicle-mounted terminal;
the first vehicle-mounted terminal is used for acquiring a first image sequence in front of the current vehicle and a second image sequence behind the current vehicle, which are acquired by the depth camera;
the first vehicle-mounted terminal is also used for identifying whether a pedestrian exists in the front lane according to the first image sequence;
the first vehicle-mounted terminal is further used for sending the first image sequence and the second image sequence to the edge computing device when a pedestrian exists in a front lane;
the edge computing equipment is used for identifying whether safety accident risks exist or not according to the first image sequence and identifying the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence;
and the edge computing equipment is also used for sending early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number when the identification result shows that the safety accident risk exists, so as to early warn the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
The early warning system for the driving safety risk obtains a second image sequence behind a first image sequence in front of a current vehicle through a first vehicle-mounted terminal, identifies whether pedestrians exist in a lane in front according to the first image sequence, sends the first image sequence and the second image sequence to an edge computing device when the pedestrians exist in the lane in front, identifies whether a safety accident risk exists according to the first image sequence and identifies a license plate number of a target vehicle within a preset distance behind according to the second image sequence through the edge computing device, and then sends early warning information to the first vehicle-mounted terminal and a second vehicle-mounted terminal bound with the license plate number for early warning when the safety accident risk exists according to an identification result. Therefore, safety accident risks can be evaluated when pedestrians break into the lane, early warning is carried out on the vehicle owner of the front vehicle and the vehicle owner of the target vehicle with the short rear distance when the safety accident risks crossing the lane exist, corresponding avoidance measures can be taken according to the early warning on the current vehicle and the vehicle with the short rear distance, and the situation that after the avoidance measures are taken on the front vehicle, the vehicle with the short rear distance does not take the corresponding measures in time and further causes safety accidents due to the fact that the pedestrians cross the lane cannot be observed is avoided, and driving safety is guaranteed.
In short, the above description is only a preferred embodiment of this document, and is not intended to limit the scope of protection of this document. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document shall be included in the protection scope of this document.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
All the embodiments in this document are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (9)
1. A driving safety risk early warning method is characterized by comprising the following steps:
the method comprises the steps that a first vehicle-mounted terminal obtains a first image sequence in front of a current vehicle and a second image sequence behind the current vehicle, wherein the first image sequence is acquired by a depth camera;
the first vehicle-mounted terminal identifies whether a pedestrian exists in a front lane according to the first image sequence;
if the pedestrian exists in the front lane, the first vehicle-mounted terminal sends the first image sequence and the second image sequence to an edge computing device in communication connection with the first vehicle-mounted terminal;
the edge computing equipment identifies whether safety accident risks exist or not according to the first image sequence, and identifies the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence;
and if the safety accident risk exists, the edge computing equipment sends early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number so as to early warn the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
2. The method of claim 1, wherein the edge computing device identifies from the first sequence of images whether a security incident risk exists, comprising:
the edge computing device identifies the moving direction of the pedestrian in the lane according to the latest continuous multiframe images in the first image sequence, and identifies whether the safety accident risk exists according to the moving direction of the pedestrian in the lane.
3. The method of claim 2, wherein identifying whether there is a risk of a safety accident according to a direction of movement of a pedestrian in a lane comprises:
if the moving direction of the pedestrian in the lane is from one side of the lane to the other side of the lane, judging that the safety accident risk exists;
otherwise, judging that the safety accident risk does not exist.
4. The method of claim 1, wherein the edge computing device identifies from the first sequence of images whether a security incident risk exists, comprising:
the edge computing equipment extracts a face image of a pedestrian in the lane from the first image sequence;
searching the history crossing lane record of the pedestrian in the lane from a database of the server according to the face image;
identifying the age of the pedestrian in the lane according to the face image;
recognizing the moving direction and the moving speed of the pedestrian in the lane according to the latest continuous multi-frame image in the first image sequence; and
and calculating the historical lane crossing record, the age, the moving direction and the moving speed as the input of a pre-trained model to obtain an output result, wherein the output result represents that the lane crossing safety accident risk exists or the lane crossing safety risk does not exist.
5. The method of claim 1, further comprising:
if the safety accident risk exists, the edge computing equipment sends a control signal to the traffic warning equipment connected with the roadside, so that the traffic warning equipment sends out a warning signal, and the traffic warning equipment is a variable information board or a loudspeaker.
6. The method of claim 1, further comprising:
the edge computing equipment acquires vehicle identification information bound by a vehicle-mounted terminal which is connected with the edge computing equipment, wherein the vehicle identification information comprises a license plate number.
7. The method of claim 1, wherein after the edge computing device sends the warning information to the first onboard terminal, the method further comprises:
and the first vehicle-mounted terminal marks the position of the target vehicle in the currently displayed navigation map according to the distance between the current vehicle and the target vehicle.
8. The method of claim 1, further comprising:
the edge computing device establishes communication connection with the first vehicle-mounted terminal and the second vehicle-mounted terminal within the signal coverage range of the edge computing device.
9. The early warning system for the driving safety risk is characterized by comprising a first vehicle-mounted terminal and edge computing equipment which establishes communication connection with the first vehicle-mounted terminal;
the first vehicle-mounted terminal is used for acquiring a first image sequence in front of the current vehicle and a second image sequence behind the current vehicle, which are acquired by the depth camera;
the first vehicle-mounted terminal is also used for identifying whether a pedestrian exists in the front lane according to the first image sequence;
the first vehicle-mounted terminal is further used for sending the first image sequence and the second image sequence to the edge computing device when a pedestrian exists in a front lane;
the edge computing equipment is used for identifying whether safety accident risks exist or not according to the first image sequence and identifying the license plate number of the target vehicle within a preset distance behind the current vehicle according to the second image sequence;
and the edge computing equipment is also used for sending early warning information to the first vehicle-mounted terminal and the second vehicle-mounted terminal bound with the license plate number when the identification result shows that the safety accident risk exists, so as to early warn the owner of the current vehicle and the owner of the target vehicle corresponding to the second vehicle-mounted terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110802901.2A CN113628449A (en) | 2021-07-15 | 2021-07-15 | Early warning method and system for driving safety risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110802901.2A CN113628449A (en) | 2021-07-15 | 2021-07-15 | Early warning method and system for driving safety risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113628449A true CN113628449A (en) | 2021-11-09 |
Family
ID=78379888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110802901.2A Pending CN113628449A (en) | 2021-07-15 | 2021-07-15 | Early warning method and system for driving safety risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113628449A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120182140A1 (en) * | 2011-01-14 | 2012-07-19 | Denso Corporation | Obstacle notification apparatus |
| CN105957401A (en) * | 2016-06-08 | 2016-09-21 | 上海汽车集团股份有限公司 | Intersection pedestrian anti-collision method based on vehicle-road coordination and device thereof |
| CN107161147A (en) * | 2017-05-04 | 2017-09-15 | 广州汽车集团股份有限公司 | A kind of vehicle collision avoidance cruise control system and its control method |
| CN111488792A (en) * | 2019-01-29 | 2020-08-04 | 福特全球技术公司 | System and method for predicting pedestrian behavior |
| US20210150895A1 (en) * | 2019-11-14 | 2021-05-20 | Shang Huang | Traffic condition system for internet of vehicles based on image recognition |
-
2021
- 2021-07-15 CN CN202110802901.2A patent/CN113628449A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120182140A1 (en) * | 2011-01-14 | 2012-07-19 | Denso Corporation | Obstacle notification apparatus |
| CN105957401A (en) * | 2016-06-08 | 2016-09-21 | 上海汽车集团股份有限公司 | Intersection pedestrian anti-collision method based on vehicle-road coordination and device thereof |
| CN107161147A (en) * | 2017-05-04 | 2017-09-15 | 广州汽车集团股份有限公司 | A kind of vehicle collision avoidance cruise control system and its control method |
| CN111488792A (en) * | 2019-01-29 | 2020-08-04 | 福特全球技术公司 | System and method for predicting pedestrian behavior |
| US20210150895A1 (en) * | 2019-11-14 | 2021-05-20 | Shang Huang | Traffic condition system for internet of vehicles based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107608388B (en) | Autonomous police vehicle | |
| US11380193B2 (en) | Method and system for vehicular-related communications | |
| CN108022450B (en) | Auxiliary driving method based on cellular network and traffic control unit | |
| US9694747B2 (en) | Method and system for providing a collision alert | |
| JP2018505422A (en) | Accident avoidance method and system | |
| KR20210038852A (en) | Method, apparatus, electronic device, computer readable storage medium and computer program for early-warning | |
| CN108860166A (en) | Processing system and processing method occur for pilotless automobile accident | |
| Saiprasert et al. | Driver behaviour profiling using smartphone sensory data in a V2I environment | |
| US20170263128A1 (en) | Methods for enabling safe tailgating by a vehicle and devices thereof | |
| CN104134360A (en) | Intersection pedestrian recognition safety control system and method based on short-range communication | |
| CN105844965A (en) | Vehicle distance prompting method and device | |
| US20170046952A1 (en) | Dangerous Vehicle Warning Method and Dangerous Vehicle Warning System | |
| JP2020024580A (en) | Driving evaluation device and on-vehicle device | |
| CN112017438B (en) | Driving decision generation method and system | |
| JP2017167795A (en) | Annoying drive detection device and annoying drive detection method | |
| JP2017027598A (en) | Method and system for giving warning to driver of vehicle | |
| CN112927509A (en) | Road driving safety risk assessment system based on traffic conflict technology | |
| CN112907979B (en) | System and method for tracking illegal running track of motor vehicle based on multiple cameras | |
| KR20230052444A (en) | Smart safety mirror device | |
| CN109583410B (en) | Driving safety early warning system based on image recognition technology | |
| CN113628449A (en) | Early warning method and system for driving safety risk | |
| CN112581792B (en) | Driving support system, driving support method, and computer-readable storage medium | |
| CN111932942A (en) | Vehicle collision early warning method and device, terminal device and computer readable storage medium | |
| TWI843641B (en) | Method and computer device for automatically sorting out accident factors and predicting road accidents based on traffic scene videos , computer-readable medium | |
| KR20180111292A (en) | A Large Vehicle with a Virtual Traffic Light for Guiding Ahead Traffic Situation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211109 |
|
| RJ01 | Rejection of invention patent application after publication |