CN115002719A - Green driver communication system based on machine vision and vehicle-mounted network - Google Patents
Green driver communication system based on machine vision and vehicle-mounted network Download PDFInfo
- Publication number
- CN115002719A CN115002719A CN202210581266.4A CN202210581266A CN115002719A CN 115002719 A CN115002719 A CN 115002719A CN 202210581266 A CN202210581266 A CN 202210581266A CN 115002719 A CN115002719 A CN 115002719A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- module
- verification
- relative
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
- B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/09623—Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
- G08G1/133—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams within the vehicle ; Indicators inside the vehicles or at stops
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Mechanical Engineering (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar, Positioning & Navigation (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a green driver communication system based on machine vision and a vehicle-mounted network, which comprises a communication device, wherein the communication device comprises a depth camera for acquiring a depth image, a DSP module for processing the depth image, a vehicle-mounted network module for signal broadcasting and signal receiving, a sound alarm module for being installed in a vehicle and warning that a vehicle enters behind a driver, and an LCD display module for displaying the position of the vehicle from which a signal comes, wherein the depth camera is connected with the DSP module, and the DSP module is connected with the vehicle-mounted network module, the sound alarm module and the LCD display module. The green driver communication system can effectively realize the mutual communication among drivers, enables the facing objects to be more accurate, can display the position of a signal source vehicle, and can warn the driver that the vehicle enters the rear part through the sound in the vehicle; the efficiency is higher; and is a more environmentally friendly green driver communication system.
Description
Technical Field
The invention relates to the field of computer vision and the field of vehicle mobile communication, in particular to a green driver communication system based on machine vision and a vehicle-mounted network.
Background
As the number of cars is rapidly increasing and the phenomenon of random whistle is not suppressed due to difficulty in defining, the noise pollution of car whistle is becoming more and more serious.
In order to solve the above problems, the invention with application number CN201720029031.9 discloses an interactive silent whistle system for vehicles, which mainly comprises a single chip microcomputer, a transmitting component, a receiving component, a bluetooth module component, a sound component, a memory and the like, wherein the single chip microcomputer is respectively connected with other modules. The interactive silent whistle system can reduce the noise pollution of automobile whistle to a certain extent, but the practicability needs to be improved, and the main defects are as follows: firstly, the interactive silent whistle system for the vehicle utilizes a Bluetooth broadcasting mode to transmit whistle signals, vehicles within a certain range receive the signals and trigger sound in the vehicle, and the signal orientation is still inaccurate; secondly, the triggering of the device still depends on the manual operation of a driver, and the automatic triggering of the whistle device cannot be realized; third, when there are multiple signal sources, it fails to achieve signal response prioritization; fourth, the signal display form is only one acoustic device, which is relatively single.
In summary, the interactive silent whistling system for the vehicle is not suitable for the current driving situation, and a new system for green communication between drivers needs to be invented.
Disclosure of Invention
The invention aims to solve the technical problem of providing a green driver communication system based on machine vision and a vehicle-mounted network aiming at the defects of the prior art, the green driver communication system based on the machine vision and the vehicle-mounted network can effectively realize the mutual communication among drivers, enables the facing objects to be more accurate, can display the position of a signal source vehicle and can warn the driver that a vehicle enters the rear part through the sound in the vehicle; the efficiency is higher; and is a more environmentally friendly green driver communication system.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
the utility model provides a green driver communication system based on machine vision and vehicle-mounted network, includes the communication device, the communication device is including the depth camera that is used for gathering the depth image, be used for to depth image processing's DSP module, be used for signal broadcast and signal reception's vehicle-mounted network module, be used for installing in the car and warn the driver rear have the sound alarm module that the vehicle drove into and be used for showing the LCD display module of the position of signal source vehicle, the depth camera is connected with the DSP module, the DSP module is connected with vehicle-mounted network module, sound alarm module and LCD display module.
The vehicle speed detection system is characterized by further comprising a power module, an electronic switch and a master controller, wherein the power module is connected with the alternating current device through the electronic switch, the master controller is connected with a vehicle speed sensor on the vehicle, the master controller is connected with the electronic switch, and the master controller is used for controlling the on-off of the electronic switch according to the vehicle speed detected by the vehicle speed sensor so as to control the on-off of the alternating current device.
As a further improved technical scheme of the invention, the depth camera is arranged at the front windshield of the vehicle, the left rearview mirror and the right rearview mirror or the front side of the interior rearview mirror.
As a further improved technical scheme of the invention, the depth camera is used for periodically acquiring the depth image information of the target vehicle.
As a further improved technical scheme, in each working period, when the depth camera acquires the depth image information of the target vehicle, the DSP module is used for acquiring a license plate number character string of the target vehicle from the depth image information based on a license plate number recognition system; the DSP module is used for acquiring position information of the target vehicle relative to the vehicle from the depth image information based on the depth camera principle, and the position information comprises the lateral distance of the target vehicle relative to the vehicle, the longitudinal distance of the target vehicle relative to the vehicle and the direction of the target vehicle relative to the vehicle; the DSP module is used for calculating the longitudinal speed of the target vehicle relative to the vehicle according to the position information obtained by the two frames of depth images; and the DSP module is used for calculating the road width according to the acquired depth image information.
As a further improved technical solution of the present invention, the DSP module is configured to screen out a real target vehicle according to the road width and the position information of each target vehicle in the target vehicle group relative to the host vehicle, calculate the relative collision time between the real target vehicle and the host vehicle according to the position information and the longitudinal speed of the real target vehicle relative to the host vehicle, and then classify the collision risk level according to the relative collision time.
As a further improved technical scheme of the invention, the DSP module is used for judging whether collision danger exists according to the collision danger level, and if so, the DSP module integrates and codes the license plate number character string information of the real target vehicle, the license plate number character string information of the vehicle, the position information of the vehicle relative to the real target vehicle and the collision danger level information in sequence based on a Unicode coding mode.
As a further improved technical solution of the present invention, the vehicle-mounted network module is configured to broadcast the encoded information in a DSRC protocol, vehicles within a broadcast range can all receive the information through the vehicle-mounted network module installed on their own vehicle, the DSP module installed on the vehicle that receives the information is configured to decode the received information based on a Unicode encoding manner, the DSP module is configured to compare and verify a license plate number character string of their own vehicle with a first item in the decoded information, and when the comparison and verification results are the same, the decoded information passes verification; if only one piece of information passes the verification, a buzzer in the sound alarm module mounted on the vehicle passing the verification is used for giving out sound warning according to the frequency corresponding to the collision risk level in the information passing the verification, and an LCD display module mounted on the vehicle passing the verification is used for displaying the position of the vehicle from which the signal comes according to an interface with the color corresponding to the collision risk level in the information passing the verification; if the number of the information passing the verification is multiple, the DSP module installed on the vehicle passing the verification is used for selecting the highest collision danger level from all the information passing the verification, the buzzer in the sound alarm module installed on the vehicle passing the verification is used for emitting sound warning according to the frequency corresponding to the highest collision danger level, and the LCD display module installed on the vehicle passing the verification is used for displaying the positions of all the signal source vehicles according to the interface of the color corresponding to the collision danger level in the decoded information.
The invention has the beneficial effects that:
(1) the invention utilizes the depth camera to collect images, can effectively extract the position information of the target vehicle relative to the signal source vehicle from the collected image information, and can identify the license plate number through the collected depth image by the DSP module, thereby coding the signal according to the identified license plate number, achieving multiple purposes.
(2) Compared with sensors such as radar and ultrasonic wave, the depth camera adopted by the invention has the advantages of wider visual angle, larger monitoring range and longer detection distance, thereby providing longer reaction time for a driver and further reducing the accident rate;
(3) compared with the traditional whistle device, the whistle device has the advantage that the propagation speed of the signal is higher. Conventional whistling devices transmit signals by sound, with a signal propagation velocity of about v sound 340m/s, the speed of signal propagation through a wireless network (essentially electromagnetic waves) is close to the speed of light c, and on a highway, if the vehicle distance is the minimum limit vehicle distance s is 100m, the signal transmission mode provided by the invention can save about time compared with the traditional whistle:this provides the driver with a longer reaction time and thus a higher safety for driving at high speeds.
(4) Compared with the traditional whistle device which conducts signal propagation through sound, the vehicle-mounted self-organizing network signal propagation device reduces noise pollution and is more environment-friendly.
(5) Compared with the traditional whistle device, the whistle device can still effectively work in the no-whistle area such as a suburb road section without violating the policy requirements, and the communication efficiency among drivers is improved.
(6) The invention adopts the computer vision technology to acquire the images of the vehicles (target vehicles) which hinder the normal running of the vehicle (namely the signal source vehicle), and acquires the license plate number of the target vehicle as the address identification based on the images, thereby realizing the accurate delivery of the signals, and the signal face is accurate enough; the harmful influence range of the signal is smaller, and the signal is more environment-friendly.
(7) The early warning reminding strategy of the invention adopts a mode of audio-visual combination, can rapidly arouse the alertness of the driver when the collision risk is higher, and improves the safety.
(8) The invention reasonably divides the level of the danger degree of possible collision based on the estimation of the collision time TTC, so that a buzzer in a sound alarm module arranged on a vehicle passing the verification sends out sound warning according to the frequency corresponding to the highest collision danger level in all decoded information, simultaneously the positions of all signal source vehicles are displayed through an LCD display screen in an LCD display module arranged on the vehicle passing the verification according to an interface of the color corresponding to the collision danger level in the decoded information, different collision danger levels are represented through different colors, and the positions of all signal source vehicles are displayed by colors, so that a driver can visually and rapidly sort the priority of emergency conditions, thereby improving the driving safety; the man-machine interaction is good.
(9) The master controller is connected with a vehicle speed sensor on the vehicle and is used for controlling the on-off of the electronic switch according to the vehicle speed detected by the vehicle speed sensor. When the vehicle speed sensor detects that the vehicle speed is 0, the master controller controls the electronic switch to be switched off, and the alternating current device does not work; when the vehicle speed sensor detects that the vehicle speed is not 0, the master controller controls the electronic switch to be closed, and the alternating current device is electrified to work. Therefore, when the vehicle runs, the alternating current device is automatically triggered to start working, and manual operation of a driver is not needed.
(10) The invention is a 'non-complete broadcast type' green whistle system which can effectively realize the mutual communication among drivers, realize the automatic identification of whistle signal targets, is more accurate in the facing objects, can display the signal source vehicle positions and collision danger levels by colors, has higher efficiency and good human-computer interaction performance, and is more environment-friendly. The applicable scenarios of the system are high speed and suburban road segments.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
Fig. 2 is a schematic diagram of several situations for which whistling is required in view of the present invention:
wherein (a) in FIG. 2 is a schematic view showing a case where a vehicle is present in the front left direction during passing;
wherein (b) in FIG. 2 is a schematic view showing a situation where a vehicle is present at the front right side during passing;
wherein (c) in fig. 2 is a schematic view showing a case where there is a vehicle in both the front left and front right during overtaking;
wherein (d) in FIG. 2 is a schematic view showing a case where there is a vehicle in front left, front right, and front right during passing.
Fig. 3 is a flow chart of the operation of the architecture of the present invention during a cycle.
Fig. 4 is a schematic diagram of screening real target vehicles according to the invention.
FIG. 5 is a schematic diagram of the location of a signal source vehicle relative to a real target vehicle according to the present invention.
Detailed Description
The following further description of embodiments of the invention is made with reference to the accompanying drawings:
as shown in fig. 1, a green driver communication system based on machine vision and a vehicle-mounted network comprises a communication device, wherein the communication device comprises a depth camera for collecting depth images, a DSP module for processing the depth images, a vehicle-mounted network module for signal broadcasting and signal receiving, an audio alarm module for being installed in a vehicle and warning a driver that a vehicle enters behind the vehicle, and an LCD display module for displaying the license plate number and the position of the vehicle from which the signal comes, the depth camera is connected with the DSP module, and the DSP module is connected with the vehicle-mounted network module, the audio alarm module, and the LCD display module. The LCD display module adopts an LCD display screen, and the sound alarm module adopts a buzzer. A green driver communication system is installed on each vehicle.
The green driver alternating current system further comprises a power module, an electronic switch and a master controller, wherein the power module is connected with the alternating current device through the electronic switch, the master controller is connected with a vehicle speed sensor on the vehicle, the master controller is connected with the electronic switch, and the master controller is used for controlling the on-off of the electronic switch according to the vehicle speed detected by the vehicle speed sensor so as to control the on-off of the alternating current device.
The depth camera of the present embodiment is provided at a front windshield of a vehicle, at left and right rear-view mirrors, or at the front side of an interior rear-view mirror.
As shown in fig. 1, the depth camera of the present embodiment periodically collects depth image information of a target vehicle. In each working period, when the depth camera acquires the depth image information of the target vehicle, the DSP module acquires the license plate number character string of the target vehicle from the depth image information based on the license plate number recognition system; the DSP module acquires position information of the target vehicle relative to the vehicle from the depth image information based on the depth camera principle, wherein the position information of the target vehicle relative to the vehicle comprises the lateral distance of the target vehicle relative to the vehicle, the longitudinal distance of the target vehicle relative to the vehicle and the direction of the target vehicle relative to the vehicle; the DSP module calculates the longitudinal speed of the target vehicle relative to the vehicle according to the position information obtained by the two frames of depth images; and the DSP module calculates the road width according to the acquired depth image information.
The DSP module of this embodiment further screens out real target vehicles according to the road width and the lateral distance of each target vehicle in the target vehicle group relative to the own vehicle, calculates the relative collision time between the real target vehicle and the own vehicle according to the longitudinal distance and the longitudinal velocity of the real target vehicle relative to the own vehicle, and then classifies the collision risk level according to the relative collision time.
The DSP module also judges whether collision danger exists according to the collision danger level, namely when the collision danger level is the first level, the second level or the third level, the collision danger exists, and if the collision danger exists, the DSP module integrates and codes the license plate number character string information of the real target vehicle, the license plate number character string information of the vehicle, the position information of the vehicle relative to the real target vehicle and the collision danger level information in sequence based on a Unicode coding mode.
The vehicle-mounted network module of this embodiment broadcasts the encoded information in a DSRC protocol, all vehicles within the broadcast range can receive the information through the vehicle-mounted network module installed on the vehicle, the DSP module installed on the vehicle receiving the information decodes the received information based on a Unicode encoding mode, the DSP module compares and verifies the license plate number character string of the vehicle with the first item in the decoded information, when the comparison and verification results are the same, the decoded information passes verification, i.e., passes identity authentication, if there is one information passing verification, the sound alarm module installed on the vehicle passing verification sends out a sound alarm under the control of the DSP module, the buzzer in the sound alarm module sends out a sound alarm according to the frequency corresponding to the collision risk level in the information passing verification, the LCD display module installed on the vehicle passing verification shows the license plate number and the license plate number of the vehicle from which the signal comes from according to the interface of the color corresponding to the collision risk level in the decoded information Location. If the verified information is multiple, namely when signals broadcasted by a plurality of vehicles are received simultaneously, the DSP module selects the highest collision danger level from all the verified information, the sound alarm module is controlled through the highest collision danger level, a buzzer in the sound alarm module installed on the verified vehicle sends out sound warning according to the frequency corresponding to the highest collision danger level, and meanwhile, an LCD display module installed on the verified vehicle displays the license plate number and the position of all the vehicles from which the signals come according to the interface of the color corresponding to the collision danger level in the verified information under the control of the DSP module. Different sound frequencies correspond to different collision risk levels, and different color interfaces correspond to different collision risk levels, so that a driver can be clear at a glance, the driver can conveniently and visually and rapidly sort the priorities of emergency situations, and the driving safety is improved.
The operation process of the embodiment is as follows:
(1) several situations requiring a blast are classified and enumerated:
as shown in fig. 2, in combination with the general knowledge, four typical scenes that require whistling at the highway or urban and rural junctions are summarized, which are: as shown in fig. 2 (a), when overtaking, a vehicle is present in the front left, and a whistle is given to remind to prevent the vehicle from changing lanes suddenly; as shown in fig. 2 (b), when passing, there is a car in front right, and a whistle is given to prevent it from changing lane suddenly; as shown in fig. 2 (c), when overtaking, both the front left and the front right have cars, and a whistle is given to remind the cars to prevent the cars from changing lanes suddenly; as shown in fig. 2 (d), a vehicle is present right in front, left in front, and right in front, and a whistle indicates a prompt driving.
(2) Triggering of the alternating current device:
and the master controller on the vehicle is connected with the vehicle speed sensor on the vehicle and is used for controlling the power-on and power-off of the alternating current device according to the vehicle speed detected by the vehicle speed sensor. The main controller and the electronic switch can supply power to the vehicle through the self-contained power supply of the vehicle. When the key for the vehicle is turned on, the vehicle is provided with a power supply to supply power to the master controller and the electronic switch, and when the vehicle speed sensor detects that the vehicle speed is 0 and the vehicle does not run, the master controller controls the electronic switch to be switched off and the alternating current device does not work, and when the vehicle speed sensor detects that the vehicle speed is not 0 and the vehicle runs, the master controller controls the electronic switch to be switched on and the alternating current device is switched on to work. Therefore, when the vehicle starts to run, the alternating current device automatically triggers to start working without manual operation of a driver. The electronic switch of the present embodiment may employ a relay.
The alternating-current device of the embodiment takes T as a working period (T changes with the change of the vehicle speed, and the faster the vehicle speed, the smaller T), each working period can be roughly divided into four processes of sampling, calculating, signal transmitting and signal receiving, when the signal transmitting process of one working period is finished, the sampling process of the next working period is started, and so on until the vehicle is flamed out.
(3) Image acquisition is carried out by setting a front depth camera:
as shown in fig. 3, the depth camera performs depth image acquisition on the road condition in front within the visible range, that is, acquires a depth image in front of the vehicle and sends the depth image to the DSP module.
As described above, the target vehicle is often located in front of the vehicle (including right front, left front, and right front), and a depth camera is not set in front of the vehicle to capture an image of a target vehicle group facing a front signal, that is, a potential target vehicle, where the captured depth image includes not only an RGB value of each pixel point but also depth information of each pixel point. The arrangement position of the depth camera can be selected by three schemes, the first scheme is to arrange the depth camera at the outer side of the front windshield, and the scheme has the advantages of simple arrangement and easy realization; secondly, a depth camera is respectively arranged at the front side of the left rearview mirror and the front side of the right rearview mirror, and the device has the advantages of wide visual angle range and high safety factor; the third is to arrange a depth camera at the front side of the interior rearview mirror, and the scheme is simple to realize.
(4) And (3) processing the depth image by the DSP module:
as shown in fig. 3, the DSP module obtains license plate number character string information and road width information of a potential target vehicle group from the depth image based on the license plate number recognition system; the DSP module acquires the position information of each target vehicle relative to the signal source vehicle from the depth image based on the depth camera principle.
After the state parameters (i.e. the position of the target vehicle relative to the signal source vehicle, etc.) and the road width of the potential target vehicle group are calculated and obtained based on the depth image, the target vehicles can be screened accordingly. The method comprises the following steps: the DSP module sets a reasonable lateral distance threshold value based on the width of the road, and marks the target vehicle with the lateral distance smaller than the lateral distance threshold value as a real target vehicle; and marking the target vehicle with the lateral distance greater than or equal to the lateral distance threshold value with the vehicle as an unreal target vehicle, namely an irrelevant vehicle. As shown in fig. 4, the rejection principle of the non-real target vehicles is as follows:
X≥2D;
where X is the lateral distance between the potential target vehicle and the vehicle (i.e., the signal source vehicle), and D is the road width. And 2D is the lateral distance threshold.
Therefore, non-real target vehicles can be preliminarily removed from the potential target vehicle group, and the real target vehicles in the potential target vehicle group are screened out, so that the facing range of the signals is reduced to a certain extent, and more accurate signal sending is realized.
Classifying collision danger:
the DSP module calculates the collision time of the real target vehicle relative to the vehicle, namely the relative collision time TTC according to the depth image, and classifies the collision danger grade according to the relative collision time TTC.
Since the driver needs sufficient attention during driving, the avoidance priority of a plurality of vehicles suddenly coming from different lanes behind is judged, the attention of the driver is necessarily dispersed, and the driving safety is not facilitated. Therefore, the early warning level (collision danger level) is not divided, so that the driver can intuitively and quickly sort the priorities of the emergency situations, and the driving safety is improved.
A thought for classifying collision danger grades of a rear vehicle is to calculate relative collision time TTC by a uniform motion model based on the longitudinal speed and the longitudinal distance of a real target vehicle, and according to the relative collision time TTC, a reasonable collision time threshold is set by combining the reaction time of a driver and signal delay, so that the target vehicle with collision danger is classified into the collision danger grades.
The relative time to collision TTC is the time required for the own vehicle to collide with the preceding vehicle at the present vehicle speed. The TTC is calculated based on the state parameters such as the longitudinal speed, the longitudinal distance and the like of the real target vehicle relative to the vehicle (i.e. the signal source vehicle). The smaller the relative collision time TTC, the higher the risk degree; the greater the relative time to collision TTC, the lower the risk level. The idea and danger classification strategy for calculating TTC by using depth image information captured by a depth camera is as follows:
sequentially recording the frame numbers of the front and rear two-frame depth images acquired by the depth camera as N 2 ,N 1 And if the sampling frequency is f, the time interval delta t for shooting two frames of depth images is as follows:
the longitudinal distance between the real target vehicle (i.e. the front vehicle) corresponding to the depth images of the front and the rear frames and the vehicle (i.e. the signal source vehicle) is d 1 ,d 2 Then the longitudinal relative speed of the real target vehicle with respect to the own vehicle is:
if the longitudinal distance of the vehicle relative to the real target vehicle at the current moment is Y, the relative time to collision TTC is:
namely:
setting a relative collision time threshold range according to the calculated relative collision time TTC and the investigated driver reaction time (about 0.6 s-0.8 s), and comparing and analyzing the calculated relative collision time TTC and the relative collision time threshold range, so that the early warning level of the collision (namely the collision risk level) can be reasonably classified according to the risk level grading strategy shown in Table 1:
table 1: a risk rating strategy;
remarking: wherein the first level of collision risk is higher than the second level of collision risk, the second level of collision risk is higher than the third level of collision risk, and the third level of collision risk is higher than the fourth level of collision risk.
Locating signal targets and sources with license plate number strings: the obtained license plate number character string of the real target vehicle is used as an address identification of a signal target, and accurate signal delivery is realized; the DSP module obtains the position information of the vehicle relative to the real target vehicle as shown in fig. 5 through coordinate transformation according to the position information of the real target vehicle relative to the vehicle, including the longitudinal distance y of the vehicle relative to the real target vehicle, the lateral distance x of the vehicle relative to the real target vehicle, and the azimuth information (i.e., the included angle θ) of the vehicle relative to the real target vehicle.
And the DSP module judges whether a collision risk exists according to the collision risk level, namely whether the collision risk level belongs to a first level, a second level or a third level, if so, the DSP module indicates that a certain collision risk exists and needs to encode and broadcast signals to send out early warning signals.
The DSP module integrates and encodes license plate number character string information of a real target vehicle, license plate number character string information of the vehicle, position information of the vehicle relative to the real target vehicle and collision risk grade information in sequence based on a Unicode encoding method; the data structure of the code is as follows: the "license plate number character string of the real target vehicle" + "the license plate number character string of the own vehicle" + "the position information of the own vehicle relative to the real target vehicle" + "the collision risk level" + "the time stamp".
(5) Broadcasting of the signal:
and the vehicle-mounted network module broadcasts the information coded and integrated by the DSP module to a signal within a certain range through a vehicle-mounted self-organizing network in the form of 'header' + 'content' by using a DSRC protocol. Wherein the "header" describes the license plate number of the signal facing the vehicle (i.e. the real target vehicle) and the license plate number of the own vehicle (corresponding to the first two items of the encoded data structure, respectively); the "contents" describe the position information of the own vehicle with respect to the real target vehicle, and the collision risk levels (respectively corresponding to the latter three items of the data structure).
(6) Reception and decoding of signals:
the vehicle-mounted network modules in the vehicles in the broadcasting range receive the signals and send the signals to the DSP module in the vehicle; the DSP module decodes the signal based on the Unicode coding table, compares and verifies the license plate number character string of the vehicle with a first item in the decoded information, and if the comparison and verification results are the same, the decoded information passes verification, namely passes identity authentication;
(7) sound warning and information display:
the buzzer in the sound alarm module mounted on the vehicle passing the verification sends out sound warning according to the frequency corresponding to the highest collision danger level in all the information passing the verification, meanwhile, the LCD display screen in the LCD display module mounted on the vehicle passing the verification displays the license plate number and the position of all the signal source vehicles according to the interface of the color corresponding to the collision danger level in the information passing the verification, and the positions and the collision danger levels of all the signal source vehicles are informed to the driver through different color representations, so that the driver can visually and rapidly sort the priority of the emergency, and the driving safety is improved. When a certain real target vehicle receives a plurality of pieces of verified information, namely a plurality of vehicles broadcast signals to the real target vehicle, the LCD display screen in the LCD display module of the real target vehicle respectively represents the license plate number and the position of the vehicle from which different signals originate by different colors (the specific color is set correspondingly according to the collision risk level in each piece of verified information), and the buzzer warns the frequency corresponding to the collision risk level with the highest collision risk in all pieces of verified information. According to the buzzer frequency and LCD display screen color setting scheme shown in Table 2, the higher the danger degree is, the higher the sound frequency for triggering the buzzer to emit is; the color displayed by the LCD display screen is different according to the signals with different danger degree grades. One buzzer frequency and LCD display color setting strategy is shown in table 2. Thereby intuitively and efficiently informing the driver of the degree of danger of the warning signal.
Table 2: a buzzer frequency and LCD interface color setting scheme;
collision risk or warning classes | Four stages | Three-stage | Second stage | First |
Buzzer frequency | ||||
0 | 2kHz | 3kHz | 5kHz | |
LCD display interface color | Blue color | Green colour | Orange colour | Red colour |
The higher the collision risk, the higher the frequency of the buzzer, the more rapid the warning sound, and the more red the warning interface color, such a setting strategy can fully show the collision risk level to the driver.
The scope of the present invention includes, but is not limited to, the above embodiments, and the present invention is defined by the appended claims, and any alterations, modifications, and improvements that may occur to those skilled in the art are all within the scope of the present invention.
Claims (8)
1. A green driver communication system based on machine vision and a vehicle-mounted network is characterized in that: the vehicle-mounted depth image monitoring system comprises an alternating current device, wherein the alternating current device comprises a depth camera for collecting a depth image, a DSP module for processing the depth image, a vehicle-mounted network module for signal broadcasting and signal receiving, a sound alarm module for being installed in a vehicle and warning a driver that a vehicle enters behind the driver, and an LCD display module for displaying the position of the vehicle with a signal source, the depth camera is connected with the DSP module, and the DSP module is connected with the vehicle-mounted network module, the sound alarm module and the LCD display module.
2. The machine-vision and in-vehicle network based green driver communication system of claim 1, wherein: the intelligent vehicle speed control system is characterized by further comprising a power module, an electronic switch and a master controller, wherein the power module is connected with the alternating current device through the electronic switch, the master controller is connected with a vehicle speed sensor on the vehicle, the master controller is connected with the electronic switch, and the master controller is used for controlling the on-off of the electronic switch according to the vehicle speed detected by the vehicle speed sensor so as to control the on-off of the alternating current device.
3. The machine-vision and in-vehicle network based green driver communication system of claim 2, wherein: the depth camera is arranged at the front windshield of the vehicle, the left rearview mirror and the right rearview mirror or at the front side of the interior rearview mirror.
4. The machine-vision and in-vehicle network based green driver communication system of claim 2, wherein: the depth camera is used for periodically collecting depth image information of a target vehicle.
5. The machine-vision and in-vehicle network based green driver communication system of claim 4, wherein: in each working period, when the depth camera acquires the depth image information of the target vehicle, the DSP module is used for acquiring a license plate number character string of the target vehicle from the depth image information based on a license plate number recognition system; the DSP module is used for acquiring position information of the target vehicle relative to the vehicle from the depth image information based on the depth camera principle, and the position information comprises the lateral distance of the target vehicle relative to the vehicle, the longitudinal distance of the target vehicle relative to the vehicle and the direction of the target vehicle relative to the vehicle; the DSP module is used for calculating the longitudinal speed of the target vehicle relative to the vehicle according to the position information obtained by the two frames of depth images; and the DSP module is used for calculating the road width according to the acquired depth image information.
6. The machine-vision and in-vehicle network based green driver communication system of claim 5, wherein: the DSP module is used for screening out real target vehicles according to the road width and the position information of each target vehicle in the target vehicle group relative to the vehicle, calculating the relative collision time between the real target vehicles and the vehicle according to the position information and the longitudinal speed of the real target vehicles relative to the vehicle, and then dividing the collision danger grades according to the relative collision time.
7. The machine-vision and in-vehicle network based green driver communication system of claim 6, wherein: the DSP module is used for judging whether collision danger exists according to the collision danger level, and if so, the DSP module sequentially integrates and codes license plate number character string information of the real target vehicle, license plate number character string information of the vehicle, position information of the vehicle relative to the real target vehicle and the collision danger level information based on a Unicode coding mode.
8. The machine-vision and on-board-network-based green driver communication system of claim 7, wherein: the vehicle-mounted network module is used for broadcasting the coded information by a DSRC protocol, all vehicles in a broadcasting range can receive the information through the vehicle-mounted network module arranged on the vehicle, the DSP module arranged on the vehicle receiving the information is used for decoding the received information based on a Unicode coding mode, the DSP module is used for comparing and checking the license plate number character string of the vehicle with a first item in the decoded information, and when the comparison and check results are the same, the decoded information passes the check; if only one piece of information passes the verification, a buzzer in the sound alarm module mounted on the vehicle passing the verification is used for giving out sound warning according to the frequency corresponding to the collision risk level in the information passing the verification, and an LCD display module mounted on the vehicle passing the verification is used for displaying the position of the vehicle from which the signal comes according to an interface with the color corresponding to the collision risk level in the information passing the verification; if the number of the information passing the verification is multiple, the DSP module installed on the vehicle passing the verification is used for selecting the highest collision danger level from all the information passing the verification, the buzzer in the sound alarm module installed on the vehicle passing the verification is used for emitting sound warning according to the frequency corresponding to the highest collision danger level, and the LCD display module installed on the vehicle passing the verification is used for displaying the positions of all the signal source vehicles according to the interface of the color corresponding to the collision danger level in the decoded information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210581266.4A CN115002719A (en) | 2022-05-26 | 2022-05-26 | Green driver communication system based on machine vision and vehicle-mounted network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210581266.4A CN115002719A (en) | 2022-05-26 | 2022-05-26 | Green driver communication system based on machine vision and vehicle-mounted network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115002719A true CN115002719A (en) | 2022-09-02 |
Family
ID=83029717
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210581266.4A Pending CN115002719A (en) | 2022-05-26 | 2022-05-26 | Green driver communication system based on machine vision and vehicle-mounted network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115002719A (en) |
-
2022
- 2022-05-26 CN CN202210581266.4A patent/CN115002719A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2383713B1 (en) | Detecting and recognizing traffic signs | |
CN102848920B (en) | A kind of method for limiting speed of automobile and speed-limiting device | |
CN112967501B (en) | Early warning system and method for dangerous driving-off behavior of vehicles on ramp | |
CN110264742B (en) | Vehicle-mounted information monitoring device suitable for expressway and warning method thereof | |
CN106314424B (en) | Householder method of overtaking other vehicles, device and automobile based on automobile | |
CN111899562A (en) | Vehicle meeting prompting method for curve blind area | |
CN109996212A (en) | Vehicle blind zone information acquisition method, car-mounted terminal and storage equipment | |
CN113808418B (en) | Road condition information display system, method, vehicle, computer device and storage medium | |
CN103832380A (en) | Dead zone automobile detection and warning system and method based on machine vision | |
CN113436436A (en) | Intelligent AI system for traffic violation data processing | |
CN112489383A (en) | Early warning system and method for preventing red light running accident based on machine vision | |
CN111260915B (en) | Early warning reminding method for pedestrian stay in expressway traffic abnormal area | |
CN116052472A (en) | Vehicle-mounted V2X collision early warning method based on road perception information fusion | |
CN110211073B (en) | Tunnel entry guiding device and method | |
CN112907979B (en) | System and method for tracking illegal running track of motor vehicle based on multiple cameras | |
CN111489560B (en) | Detection method and control method for detecting front vehicle starting based on shallow convolutional neural network | |
CN111746526B (en) | Early warning method, device and equipment for rear unmanned vehicle and vehicle | |
CN115002719A (en) | Green driver communication system based on machine vision and vehicle-mounted network | |
CN114801985A (en) | Information exchange method of vehicle environment-friendly whistling system | |
CN216772592U (en) | Traffic inspection equipment | |
CN116238332A (en) | HMI system-based multi-V2X scene display strategy, system and automobile | |
CN111845560B (en) | Warning system for objects rushed out of locomotive | |
CN203318280U (en) | Machine vision based blind-zone vehicle detection and warning system | |
CN114973655B (en) | Intelligent traffic real-time alarm system based on mobile internet | |
CN210515657U (en) | Mobile supervision system and bus |
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 |