CN112034449B - System and method for correcting vehicle running track based on physical space attribute - Google Patents

System and method for correcting vehicle running track based on physical space attribute Download PDF

Info

Publication number
CN112034449B
CN112034449B CN202010769036.1A CN202010769036A CN112034449B CN 112034449 B CN112034449 B CN 112034449B CN 202010769036 A CN202010769036 A CN 202010769036A CN 112034449 B CN112034449 B CN 112034449B
Authority
CN
China
Prior art keywords
vehicle
information
dimensional
data information
road
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.)
Active
Application number
CN202010769036.1A
Other languages
Chinese (zh)
Other versions
CN112034449A (en
Inventor
冯保国
顾莉
孙晓宁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hebei Deguroon Electronic Technology Co ltd
Original Assignee
Hebei Deguroon Electronic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hebei Deguroon Electronic Technology Co ltd filed Critical Hebei Deguroon Electronic Technology Co ltd
Priority to CN202010769036.1A priority Critical patent/CN112034449B/en
Publication of CN112034449A publication Critical patent/CN112034449A/en
Application granted granted Critical
Publication of CN112034449B publication Critical patent/CN112034449B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/66—Radar-tracking systems; Analogous systems
    • G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
    • G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
    • G01S13/726—Multiple target tracking
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/865—Combination of radar systems with lidar systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/66—Tracking systems using electromagnetic waves other than radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention discloses a system and a method for correcting a vehicle running track based on physical space attributes, wherein the system comprises the following steps: the vehicle tracking detection sensor, the vehicle feature recognition device and the road side service platform are used for acquiring vehicle dynamic data information through the vehicle tracking detection sensor and carrying out data fusion on the vehicle dynamic data information and the vehicle feature data information acquired by the vehicle feature recognition device, the road side service platform carries out fuzzy matching on the vehicle three-dimensional outline dimension according to the vehicle feature data information and establishes three-dimensional digital projection of the vehicle, then the three-dimensional digital projection information of the road protection facilities along the road and the three-dimensional outline information of the vehicle are fused and calculated as space variables, the motion trail of the vehicle is corrected by utilizing the space three-dimensional attribute principle, and clutter interference filtering technology is started, so that stacking interference and crack interference are eliminated, and the positioning requirement of the vehicle is met. The invention solves the problems of easy occurrence of target confusion, tracking loss, stacking interference and crack interference in the continuous tracking and positioning process of the existing vehicle.

Description

System and method for correcting vehicle running track based on physical space attribute
Technical Field
The invention relates to the technical fields of target tracking, behavior track analysis, inertial navigation, automatic driving and automatic control, in particular to a system and a method for correcting a vehicle running track based on physical space attributes.
Background
At present, the accurate management of the expressway on the special vehicles is mainly realized by installing a vehicle-mounted GPRS or Beidou satellite positioning module for the special vehicles so as to realize the positioning and abnormal behavior management of the special vehicles. However, the technology cannot realize accurate management of common vehicles at present, and in addition, the traditional positioning management system can lose positioning effect in a special area or tunnel, cannot realize the whole-course dead-angle-free monitoring management application requirement, and brings inconvenience to road operation managers and vehicle owners.
The vehicle speed and the running state of the running vehicle are monitored on the expressway, basic information of the vehicle is collected, the existing license plate snapshot system is mainly triggered by the outside or self-triggered in two working modes, the image snapshot function of the vehicle is realized, and the external triggering working mode is mainly composed of: the vehicle detection system is realized by a coil vehicle detector, a speed measuring radar sensor, a multi-target radar sensor, a laser radar sensor and the like, when a vehicle passes through a detection area pre-drawn and defined by the detector, the sensor can give a license plate vehicle feature recognition device and a trigger signal (generally IO control quantity), and the license plate vehicle feature recognition device starts a camera shutter of the device to realize the snapshot of the image of the vehicle when receiving the trigger information number.
The radar sensing is utilized to track the characteristic information of the vehicle, including the information of the size, the type, the speed, the moving direction and the like of the vehicle, and the vehicle is shielded by other large vehicles or overlong in the vehicle body easily due to the large traffic flow of the high-speed road section and the complex vehicle condition information. During the movement of the vehicle, the radar tracks the same vehicle at different positions at different times, and the area scanned by the outer contour of the vehicle is continuously changed. The obtained original data of the vehicle is also changed continuously, so that the original data of the vehicle obtained by the radar at different time points and different positions are lost, and accurate continuous tracking cannot be realized.
The tracking of the characteristic information of the vehicle is realized by using radar sensing, but due to the motion state of the vehicle relative to the radar sensor and the different working principles of the radar sensor, the digital projection generated by the vehicle can have the phenomena of irregular action, twisting body, running outside a road, running in a lane at the other side, even running with two vehicles superimposed together and three vehicles running in two lanes side by side. This phenomenon is not possible in real traffic and has been severely beyond the limits of physical state. Therefore, the real physical properties are added to all tracked target objects, roads and facilities along the lines, so that the behavior and change rules and the motion state of the vehicle in the system can be consistent with the actual objects and environments in the real scene.
Disclosure of Invention
Therefore, the invention provides a system and a method for correcting the running track of a vehicle based on physical space attributes, so as to solve the problems of easy occurrence of target confusion, tracking loss, stacking interference and crack interference in the continuous tracking and positioning process of the existing vehicle.
In order to achieve the above object, the present invention provides the following technical solutions:
according to a first aspect of the present invention, a system for enabling correction of a vehicle travel track based on physical spatial properties is disclosed, the system comprising: the vehicle tracking detection sensor is arranged at the side of a road to track and detect passing vehicles, acquires the original data information of all vehicles in the detection area range in a real-time scanning mode, transmits the original data information to the road side service platform to be analyzed and processed in real time to obtain the preliminary data information of the vehicles, the road side service platform processes, converts and fuses the preliminary data information of the vehicles with map data in the area for the first time to obtain complete vehicle dynamic data information with longitude and latitude information, starts a preset synchronous triggering data fusion rule to continuously track and monitor the vehicles entering the detection area, converts unique ID identity number information in the vehicle dynamic data information into a triggering signal of the vehicle feature recognition device, after a vehicle enters a preset vehicle feature acquisition triggering area, vehicle feature recognition equipment extracts vehicle feature data information according to a triggering instruction sent by a road side service platform, the road side service platform further fuses the vehicle feature data information with vehicle dynamic data information, the road side service platform sends the vehicle feature data into a vehicle three-dimensional outline size recognition matching module to perform fuzzy matching on the vehicle feature data information, determines three-dimensional outline size information of the vehicle, forms complete vehicle data information with the three-dimensional outline size of the vehicle, establishes vehicle three-dimensional digital projection information according to the three-dimensional outline size information of the vehicle, establishes three-dimensional digital projection information along a road, fuses a vehicle three-dimensional space variable model with road three-dimensional digital projection information and calculates space variables, and the motion trail of the vehicle is corrected by utilizing the spatial three-dimensional attribute principle, a clutter interference filtering technology is started, stacking interference and crack interference are eliminated, and the positioning requirement of the vehicle is met.
Further, the vehicle tracking detection sensor is formed by combining one or more sensors of a laser radar sensor and a millimeter radar vehicle detector, the vehicle tracking detection sensor acquires original data information of all target vehicles in a detection range in a high-speed scanning mode, the data are sent into a road side service platform to be subjected to real-time analysis processing to acquire primary data information of the vehicles, unique ID digital identification information in the detection region is generated, the road side service platform carries out simultaneous analysis processing, interference filtering, mutual fusion and superposition conversion on the primary data information and map data information in the region, then acquires complete vehicle dynamic data information with longitude and latitude information and becomes D1 data information, and the dynamic data information comprises, but is not limited to longitude and latitude information, lane information, real-time speed information, movement direction information, direction angle information, acceleration information, XYZ relative distance information of each tracked target vehicle and unique ID digital identification information of the vehicles in the detection range of the road side vehicle tracking detection sensor.
Further, the vehicle feature recognition device is arranged above each lane according to the number of lanes, and corresponds to the number of lanes and the positions of lanes one by one, the system performs one-to-one numbering for each lane and sets a synchronous triggering data fusion area, after the vehicle tracking detection sensor detects that the vehicle enters the triggering fusion area, the system changes the unique ID identity number information corresponding to the vehicle into the triggering signal of the vehicle feature recognition device, the triggering signal is transmitted to the vehicle feature recognition device through the road side service platform, the vehicle feature recognition device acquires the vehicle feature data information, and the vehicle feature data information comprises: the method comprises the steps that the color, the train, the vehicle type, the brand, the trademark, the license plate and the category of vehicles are transmitted to a road side service platform through a communication network, the road side service platform fuses real-time vehicle dynamic data information transmitted by a vehicle tracking detection sensor and vehicle characteristic data information transmitted by the vehicle characteristic recognition device, each vehicle can have unique complete data information after fusion, and the system generates unique vehicle identity information in the system for each vehicle with complete information by adopting a vehicle identity information compiling principle and records the unique vehicle identity information as data D2.
Further, the road side service platform sends the vehicle characteristic data information to the vehicle three-dimensional outline size recognition and matching module, fuzzy matching is carried out according to the vehicle type information, brand information, model information and age information of the vehicle and the vehicle characteristic information in the database of the vehicle three-dimensional outline size recognition and matching module, the vehicle three-dimensional outline size recognition and matching module receives the vehicle characteristic information sent by the system, the vehicle characteristic matching key elements are utilized to match piece by piece with the vehicle model characteristic data information stored in the pre-system, the vehicle data information with the highest matching degree is found out, other data information of the vehicle comprises accurate vehicle type information and three-dimensional outline size information of the vehicle, the road side service platform fuses the matched vehicle three-dimensional outline size data with the vehicle dynamic data information and the vehicle characteristic data information to obtain complete vehicle data information with the vehicle three-dimensional outline size, and the complete vehicle data information is recorded as D3 data information.
Further, the road side service platform respectively analyzes the length, width and height data in the three-dimensional size of the vehicle as a combined three-dimensional limiting range fused by the same target vehicle point, comprehensively fuses the vehicle point trace data at different positions contained in the combined limiting range to generate complete, unique and three-dimensional vehicle point trace data information which is used for continuously tracking and positioning the target vehicle, strips redundant vehicle point trace information outside the three-dimensional limiting range, judges whether the stripped point trace information is in the three-dimensional limiting range of other vehicles, if so, the stripped point trace information is utilized, and if not, the stripped point trace information is considered as interference and filtered.
Further, the road side service platform finds out the vehicle data information with highest matching degree, invokes other data information of the vehicle including accurate vehicle type information and three-dimensional outline size information of the vehicle, and endows the target vehicle with three-dimensional digital projection information.
Further, the setting up process of the road three-dimensional digital projection information is as follows: setting virtual road digital information projection in a system; giving category attributes to the curb or the infrastructure; and endowing different types of infrastructure with corresponding digital three-dimensional space projection variable information to form three-dimensional digital projection information of the road.
Further, the three-dimensional digital projection information of the vehicle is imported into the three-dimensional digital projection information of the road, and the vehicle motion trail is corrected;
the method for acquiring the original data information of the target vehicle through the road side sensor comprises the following steps: digital pulse signals, radio wave signals, optical wave signals;
forming a preliminary digital projection signal of the vehicle through preliminary processing of the original data, and then fusing the signal with the three-dimensional digital information of the vehicle in the vehicle characteristic information acquired by the vehicle characteristic identification equipment to form three-dimensional digital projection information of the vehicle in the system;
Acquiring the central coordinate point information of the vehicle through three-dimensional digital projection information;
the method comprises the steps of calling three-dimensional digital projection information of a road and importing three-dimensional digital projection information of a vehicle and center point information of the vehicle;
the road three-dimensional digital projection information is used as the limit and the allowed movement range of the tracked vehicle three-dimensional digital projection information, the system can correlate the road with the three-dimensional spatial information of the vehicle, a complete spatial digital model is established, and the vehicle is ensured not to run outside the limit;
the road side service platform judges whether the same vehicle belongs to similar projection information of the vehicle or not, if so, the projections are fused into one, and if not, the projections are excluded.
Further, the three-dimensional digital projection information of the vehicle is led into the three-dimensional digital projection information of the road and then is fused and calculated as a space variable, the motion trail of the vehicle is corrected by utilizing the principle of the three-dimensional attribute of the space, the clutter interference filtering technology is carried out, the stacking interference and the crack interference are eliminated, the positioning accuracy of the vehicle reaches the lane level after the clutter is eliminated, and more than two vehicles running in the same direction, the same speed and transversely side by side or more than two vehicles running in the same direction and the same speed and longitudinally side by side are calculated through the physical space attribute, so that the vehicles can be accurately distinguished.
According to a second aspect of the present invention, a method for implementing correction of a vehicle driving track based on physical space properties is disclosed, the method being:
the vehicle tracking detection sensor is arranged at the road side, tracks and detects the passing vehicles in the detection range, acquires the original data information of all vehicles in the detection area range in a real-time scanning mode, and processes the original data information through the road side service platform to obtain the preliminary data information of the vehicles;
the road side service platform analyzes, processes, filters out interference, fuses and superimposes the map data in the area and the preliminary data information of the vehicle, acquires real-time dynamic data of the vehicle in the area, generates complete vehicle dynamic data information with longitude and latitude information and records the complete vehicle dynamic data information as D1 data information;
after the vehicle tracking detection sensor detects that the vehicle enters the vehicle feature acquisition triggering area, changing the unique ID digital identification information corresponding to the vehicle into a digital triggering control command, and transmitting the digital triggering control command to the vehicle feature recognition equipment through the road side service platform, wherein the vehicle feature recognition equipment acquires the feature data information of the vehicle, and the vehicle feature data information comprises: color, model, brand, trademark, license plate, and category of the vehicle;
The road side service platform fuses the dynamic vehicle data information transmitted by the vehicle tracking detection sensor and the characteristic vehicle data information transmitted by the vehicle characteristic recognition equipment, each vehicle after fusion has unique complete data information, the system adopts a vehicle identity information programming principle to generate unique vehicle identity information for each vehicle with complete information in the system, and the unique vehicle identity information is recorded as data D2;
the road side service platform sends the vehicle characteristic data into the vehicle three-dimensional outline size recognition matching module for carrying out fuzzy matching on the vehicle characteristic data information, and determines the three-dimensional outline size information of the vehicle to form complete vehicle data information with the three-dimensional outline size of the vehicle;
the road side service platform fuses the vehicle data information with the vehicle three-dimensional outline size with the vehicle dynamic data information and the vehicle characteristic data information to form complete vehicle digital information, records the complete vehicle digital information as data D3 and endows the target vehicle three-dimensional digital projection information;
establishing three-dimensional digital projection information for the protection arrangement along the road, fusing the three-dimensional digital projection information of the protection facilities along the road with the three-dimensional contour information of the vehicle, calculating space variables, and correcting the motion trail of the vehicle by utilizing the principle of the space three-dimensional attribute;
And starting clutter interference filtering technology, eliminating stacking interference and crack interference, removing clutter, enabling the positioning accuracy of the vehicle to reach a lane level, and calculating physical space attributes to enable more than two vehicles running in the same direction, at the same speed and transversely side by side or more than two vehicles running in the same direction and longitudinally side by side at the same speed to be accurately separated, so that the positioning requirement of the vehicle is met.
The invention has the following advantages:
the invention discloses a system and a method for correcting a vehicle running track based on physical space attributes, which can effectively filter a plurality of real false target track data caused by the fact that a millimeter wave radar sensor adopts a two-dimensional plane scanning mode and wave diffraction and diffusion phenomena in the running process of the same vehicle, and the phenomenon that a plurality of vehicles running in the same direction in parallel are fused into one vehicle in an error way, or the error that targets are lost and can not be identified again due to various shielding of a laser scanning radar sensor and an AI structured video sensor. Even if one or two vehicle trace point data are lost or appear in the original radar detection data of the vehicle, the vehicle trace positioning and the accuracy of data fusion cannot be interfered. Even if the vehicles run in different positions, different directions and side by side, the system can accurately track, position and distinguish any one of the vehicles. The method is characterized in that three-dimensional digital projection information is endowed to a vehicle, three-dimensional digital projection information is built on road protection facilities along the road, a three-dimensional spatial variable model of the vehicle is imported into the three-dimensional digital projection information of the road to correct the motion trail of the vehicle, clutter interference filtering technology is started, stacking interference and crack interference are eliminated, the motion range of the vehicle is limited on a virtual road, the vehicle cannot run out of the boundary, the positioning accuracy of the vehicle reaches the lane level, and the requirements of unmanned driving, automatic driving, large data platforms, map software and other platforms are met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those skilled in the art from this disclosure that the drawings described below are merely exemplary and that other embodiments may be derived from the drawings provided without undue effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a block diagram of a vehicle continuous tracking and positioning system based on vehicle size fuzzy matching according to an embodiment of the present invention;
FIG. 2 is a flowchart of a vehicle continuous tracking and positioning system based on vehicle size fuzzy matching according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing different scanning results of different positions of a vehicle in a vehicle continuous tracking and positioning system based on vehicle size fuzzy matching according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a vehicle continuous tracking and positioning system for tracking a vehicle target point based on vehicle size fuzzy matching according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of mutual occlusion of vehicles in a vehicle continuous tracking and positioning system based on vehicle size fuzzy matching according to an embodiment of the present invention;
fig. 6 is a diagram of a step of determining a three-dimensional contour of a vehicle in a vehicle continuous tracking and positioning system based on vehicle size fuzzy matching according to an embodiment of the present invention.
FIG. 7 is a road junction or infrastructure projection of a system for vehicle trajectory modification based on physical spatial attributes provided by an embodiment of the present invention;
FIG. 8 is a projection view of a guard rail of a system for performing vehicle trajectory modification based on physical space attributes according to an embodiment of the present invention;
FIG. 9 is a three-dimensional projection view of a system road boundary or base set for vehicle track modification based on physical space attributes according to an embodiment of the present invention;
fig. 10-13 are schematic diagrams of a process of fusion and superposition of three-dimensional projection information of a system vehicle and three-dimensional digital projection information of a road for vehicle track correction based on physical space attributes according to an embodiment of the present invention
In the figure: the system comprises a 1-vehicle tracking detection sensor, 2-vehicle feature recognition equipment, a 3-road side service platform, a 4-third party cloud service platform, a 5-data center, a 6-detection area, a 7-triggering snapshot area and an 8-overlapping detection area.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1 and 2, the present embodiment discloses a system for implementing correction of a vehicle running track based on physical space attributes, the system comprising: the vehicle tracking detection sensor 1 is arranged at the side of a road to track and detect passing vehicles, the original data information of all vehicles in the range of a detection area 6 is collected in a real-time scanning mode and transmitted to the road side service platform 3 to be analyzed and processed in real time to obtain the primary data information of the vehicles, the road side service platform 3 processes, converts and fuses the primary data information of the vehicles with map data in the area for the first time to obtain complete dynamic data information of the vehicles with longitude and latitude information, a preset synchronous trigger data fusion rule is started to continuously track and monitor the vehicles entering the detection range, unique ID identity number information in the dynamic data information of the vehicles is converted into a trigger signal of the vehicle feature recognition device 2, after the vehicle enters a preset vehicle feature acquisition trigger area, the vehicle feature recognition equipment 2 extracts vehicle feature data information according to a trigger instruction sent by the road side service platform 3, the road side service platform 3 further fuses the vehicle feature data information with vehicle dynamic data information, the road side service platform 3 sends the vehicle feature data into a vehicle three-dimensional outline size recognition matching module to carry out fuzzy matching of the vehicle feature data information, determines three-dimensional outline size information of the vehicle, forms complete vehicle data information with the three-dimensional outline size of the vehicle, establishes vehicle three-dimensional digital projection information according to the three-dimensional outline size information of the vehicle, establishes three-dimensional digital projection information along a road, fuses a vehicle three-dimensional space variable model with road three-dimensional digital projection information and calculates space variables, and the motion trail of the vehicle is corrected by utilizing the spatial three-dimensional attribute principle, a clutter interference filtering technology is started, stacking interference and crack interference are eliminated, and the positioning requirement of the vehicle is met.
The vehicle tracking detection sensor 1 includes, but is not limited to, one or more of a lidar sensor and a millimeter radar vehicle detector. The vehicle tracking detection sensor 1 obtains the original data information of all target vehicles in the detection range through a high-speed scanning mode, the data are sent into the road side service platform 3 to be analyzed and processed in real time to obtain the preliminary data information of the vehicles, unique ID digital identification information in the detection area 6 is generated, and the system can continuously track, position and monitor the target vehicles in real time. An overlapping detection area 8 is arranged between the adjacent detection areas 6, so that continuous tracking detection of the vehicle is realized. The vehicle tracking detection sensor 1 transmits the collected vehicle original data information to the road side service platform 3 through a network, and the road side service platform 3 temporarily stores the vehicle original data information.
The road side service platform 3 is a high-performance edge calculation server and is used for completing the functions of communication with each device, data transmission, data processing, synchronous triggering of the vehicle feature recognition device 2, data fusion, data transmission, graph analysis, acquisition of vehicle feature information, accurate time service of a positioning system and continuous tracking of a target.
The road side service platform 3 analyzes the original data of the vehicle collected and scanned in real time by the vehicle tracking detection sensor 1 to obtain preliminary data information, and simultaneously analyzes, filters interference, mutually fuses and superimposes and converts the preliminary data information and map data information in the region to obtain complete vehicle dynamic data information with longitude and latitude information and become D1 data information, wherein the dynamic data information comprises, but is not limited to, longitude and latitude information, lane information, real-time speed information, moving direction information, direction angle information, acceleration information, XYZ relative distance information of each tracked target vehicle and unique ID digital identification information of the vehicle in the detection range of the road side vehicle tracking detection sensor 1
In order to prevent the vehicle from being triggered by mistake, which is caused by the parallel and shielding of the vehicles, of the license plate vehicle feature recognition device 2, and further, the vehicle feature recognition device 2 acquires the mismatching and misfusion of the vehicle feature information and the dynamic information for the same vehicle, the vehicle feature recognition device 2 is arranged on each lane according to the number of lanes, the vehicle feature recognition device 2 corresponds to the lanes, a triggering snapshot area 7 is defined on each lane, and after the vehicle tracking detection sensor 1 detects that the vehicle enters the triggering snapshot area 7, the unique ID digital identification information corresponding to the vehicle is changed into a digital triggering control command and is transmitted to the vehicle feature recognition device 2 through the road side service platform 3. The vehicle feature recognition apparatus 2 photographs feature information of a vehicle including: color, model, brand, trademark, license plate, and category of the vehicle. Meanwhile, the characteristic information of the vehicle can also be identified and read through the ETC road side antenna to the vehicle-mounted unit (OBU) mounted on the vehicle to obtain the complete characteristic information and data information of the vehicle, and the description is omitted here.
The vehicle characteristic information collected by the vehicle characteristic recognition equipment 2 is transmitted to the road side service platform 3 through a network, the road side service platform 3 fuses the vehicle dynamic data transmitted by the vehicle tracking detection sensor 1 and the vehicle characteristic information transmitted by the vehicle characteristic recognition equipment 2, each vehicle can have unique complete data information after fusion, and the system adopts a vehicle identity information compiling principle to generate unique vehicle identity information in the system for each vehicle with complete information and records the unique vehicle identity information as data D2.
Referring to fig. 3, due to the working principle of the roadside vehicle tracking detection sensor 1, the vehicles pass through the vehicle tracking detection sensor 1 from far to near and from near to far, and in the process, when the same vehicle is at different positions at different times, the area of the vehicle, which is scanned by the vehicle tracking detection sensor 1, is continuously changed, and the obtained original data of the vehicle is also continuously changed, so that the original data of the vehicle, which is obtained by the roadside vehicle tracking detection sensor 1 at different time points and different positions, is lost. Since this lack can lead to errors in the continuous tracking and positioning of the same vehicle and in the fusion of multiple data, referring to fig. 5, if the parallel front and rear of the vehicle is serious, the target is lost briefly and cannot be compensated, thus resulting in a decrease in the overall stability of the system.
Due to the shape of the object, the surface reasons and the reasons for millimeter wave radar operation, two or more target points may appear after processing the radar data, but these points represent only one object. Referring to fig. 4, there are three traces. The three stitches are continuously tracked as three target objects. Any one of the three points can disappear temporarily or for a long time at different positions and different time points of the distance radar, if we fuse and bind the characteristic information of the vehicle with one of the points, the phenomenon of false loss of the target vehicle can be caused once the situation of complaints occurs, and continuous tracking and positioning of the target vehicle can not be realized, although we can fuse the three points to form a target point by using the point track fusion technology of the millimeter wave radar, the technology has great disadvantages, if the fusion distance is set too large: the fusion range of 8 meters or even 15 meters (the distance is the length value of the truck), the system can easily fuse two or more vehicles running in the same direction and in parallel in a certain time period into one vehicle, and the vehicles running in the same direction and in parallel are caused to artificially disappear. If too small, the effect is not achieved, and the problem still exists.
The road side service platform 3 sends the vehicle characteristic data information to the vehicle three-dimensional outline size identification matching module, and performs fuzzy matching according to the vehicle type information, brand information, model information and age information of the vehicle and the vehicle characteristic information in the database of the vehicle three-dimensional outline size identification matching module. The vehicle type model size pre-stored in the database is invoked. The data is that common vehicles running on roads are classified in a database, each type of common vehicles has unique characteristic information for one-to-one correspondence, and each type of common vehicles is endowed with three-dimensional dimensions according to actual dimensions, wherein the dimensions comprise: length, width and height data information. The target model size database includes, but is not limited to, the following types of information: pedestrians, bicycles, tricycles, motorcycles, tractors, agricultural trucks, sedans, off-road vehicles, minibuses, vans, wagons, commercial vehicles, non-motorized vehicles, sports cars, minicars, two-compartment sedans, three-compartment sedans, light buses, medium-sized trucks, trailers, tank trucks, watering vehicles and the like.
Referring to fig. 6, the vehicle three-dimensional outline size recognition and matching module receives the vehicle feature information sent by the system, performs piece-by-piece information matching with the vehicle model feature data information stored in the pre-system by utilizing the vehicle feature matching key element, finds out the vehicle data information with the highest matching degree, and retrieves other data information of the vehicle including the accurate vehicle type information and the three-dimensional outline size information of the vehicle. The road side service platform 3 fuses the matched vehicle three-dimensional outline size data with the vehicle dynamic data information and the vehicle characteristic data information to obtain complete vehicle data information with the vehicle three-dimensional outline size, and records the complete vehicle data information as D3 data information.
And (3) calling the three-dimensional physical size data information of the target vehicle in the D3 by the system, respectively analyzing the length, width and height data in the three-dimensional size as a merging three-dimensional limiting range for point merging of the same target vehicle, comprehensively merging the vehicle point trace data of different positions contained in the merging limiting range, and generating complete, unique and three-dimensional vehicle point trace data information for continuous tracking and positioning of the target vehicle. And stripping redundant vehicle trace information outside the three-dimensional limiting range, judging whether the stripped trace information is in the three-dimensional limiting range of other vehicles or not, and if so, utilizing the stripped trace information. If not, it will be considered as interference and filtered out. The method can effectively filter out a plurality of real false target point trace data caused by the fact that the millimeter wave radar sensor adopts a two-dimensional plane scanning mode and wave diffraction and diffusion phenomenon in the moving process of the same vehicle, and the phenomenon that a plurality of vehicles running in parallel and in the same direction are fused into one vehicle in an error way. Or the error that the targets are lost and can not be identified again due to various shielding caused by the laser scanning radar sensor and the AI structured video sensor, the system for realizing the vehicle point track data fusion technology, track correction and target vehicle separation through the three-dimensional model space variable calculation can easily distinguish vehicles which run in the same direction, same speed and parallel or longitudinal directions on different lanes within a certain time period. Even if one or two vehicle trace point data are lost or appear in the original radar detection data of the vehicle, the vehicle trace positioning and the accuracy of data fusion cannot be interfered. Even if the vehicles run in different positions, different directions and side by side, the system can accurately track, position and distinguish any one of the vehicles. In addition, the data fused by the three-dimensional vehicle track limiting range is integrated into the D3 data, so that the accuracy and reliability of the D3 data are improved. And then the system can correlate the target with the data obtained by the D3 by utilizing a target tracking and positioning principle and an inertial navigation principle to realize the functions of continuous tracking and positioning of the target vehicle and the like.
The road side service platform 3 sends the vehicle characteristic data information into the vehicle three-dimensional outline size recognition and matching module, performs fuzzy matching according to the vehicle type information, brand information, model information and age information of the vehicle and the vehicle characteristic information in the database of the vehicle three-dimensional outline size recognition and matching module, finds out the vehicle data information with the highest matching degree, and invokes other data information of the vehicle including the accurate vehicle type information and three-dimensional outline size information of the vehicle, so as to endow the target vehicle with three-dimensional stereoscopic digital projection information.
Due to the movement state of the vehicle relative to the vehicle tracking detection sensor 1 and the different operating principles of the vehicle tracking detection sensor 1, the digital projection generated by the vehicle may appear as a phenomenon of irregular movement, twisting the body, driving off the road, driving in the other lane, even driving with two vehicles superimposed together, and three vehicles driving side by side in the two lanes. This phenomenon is not possible in real traffic and has been severely beyond the limits of physical state. It is therefore necessary to add real physical properties to all tracked target objects, roads and along-line facilities. These physical attributes include: after the physical attributes are given to vehicles, roads and infrastructures in the system, virtual vehicle digital projection or road projection and other object projection in the system can be realized, and the expression and change rules and the motion state in the system can be kept consistent with the actual objects and environments in the real scene.
The method comprises the steps of giving a tracked target vehicle digital projection information with a three-dimensional space by using a target radar video fusion technology and a vehicle size fuzzy matching technology, and forming a non-intrusive simulated automobile outline body by taking a virtual digital space formed by digital variables X, Y, Z in the three-dimensional space as a boundary or a barrier, namely, not allowing other vehicle digital projections and space variables contained in digital projections of a line protection facility to intrude into the three-dimensional space variables formed by the target vehicle, so that the system simulates the physical attribute of the three-dimensional vehicle outline with the boundary.
The infrastructure of the road and the boundaries along the road are insurmountable unless a major traffic accident occurs to the vehicles on the road, crashing the guardrail or other infrastructure out of the road. Because of the conventional roadside sensor data processing technology, only the tracked vehicle or other object is focused on and the processing of the auxiliary equipment infrastructure information closely related to it is ignored. Thus, the tracked vehicle or other target object can virtually and digitally project information in the system, and the phenomenon of running out of the road and running to the opposite lane reversely occurs. The association and limitation are needed on the basic space structure, the road three-dimensional digital projection information is established, and the three-dimensional digital projection information is established by the following steps:
Referring to fig. 7, virtual road digital information projection is set in the system;
referring to fig. 8, category attributes are given to a curb or infrastructure: such as: rigid guard rails adopted in expressways, cement guard piers on bridges, closed walls in tunnels or shelters, green plant isolation belts in national provincial roads, metal guard rails of urban traffic or common roads, guard nets and the like;
corresponding digital three-dimensional space projection variable information is given to different kinds of infrastructure protection facilities: only endowing the infrastructure with a three-dimensional space variable can not only realize the definite limitation of the running area of the vehicle on the road, but also greatly differ from the attribute variable of the actual object, mainly because the object space variable is only used for the operation of the space environment to limit the movement area of the object, and the simulation of the actual object is not carried out;
referring to fig. 9, a rigid guard rail: digital three-dimensional space projection information: length (X): here length or defined length, width (Y) in the system: 0.3 meter height (Z): 1.2 meters;
cement protection pier: digital three-dimensional space projection information: length (X): here length or defined length, width (Y) in the system: 0.3 meter height (Z): 1.2 meters;
Closed wall: digital three-dimensional space projection information: length (X): here length or defined length, width (Y) in the system: 0.3 meter height (Z): 3 meters;
green isolation belt: digital three-dimensional space projection information: length (X): here length or defined length, width (Y) in the system: 1 meter high (Z): 1.5 meters;
metal guard rail: digital three-dimensional space projection information: length (X): here length or defined length, width (Y) in the system: 0.1 high (Z): 1 meter.
And importing the three-dimensional digital projection information of the vehicle into the three-dimensional digital projection information of the road, and correcting the motion trail of the vehicle.
Step one, the original data information of the target vehicle is acquired by the vehicle tracking detection sensor 1 as shown in fig. 10, where the original data information is generally: the digital pulse signals, the radio wave signals and the light wave signals, such as the millimeter wave radar, can form a reflected wave novel number of the vehicle after scanning the vehicle, and the reflected wave signals are processed to form digital projection signals of the vehicle in a system;
step two, forming a preliminary digital projection signal of the vehicle through preliminary processing of the original data, and then fusing the signal with the three-dimensional digital information of the vehicle in the vehicle characteristic information acquired by the license plate snapshot camera to form three-dimensional digital projection information of the vehicle in the system, as shown in fig. 11;
Step three, acquiring central coordinate point information of the vehicle through three-dimensional digital projection information, wherein the central coordinate point information is shown in fig. 12;
and step four, the digital projection information of the three-dimensional space of the road is called and is imported into the three-dimensional digital projection information of the vehicle and the central point information of the vehicle as shown in fig. 13.
The three-dimensional data information of the vehicle and the road are overlapped and fused through the steps, the three-dimensional space digital projection information of the road is used as the limit of the tracked three-dimensional space digital projection information of the vehicle and the allowed movement range, the road and the vehicle can be associated by the system through the mode, a complete space digital model is built, and then the system can continuously repeat the steps of 1-4 to finish the processing and data output of various data.
The system utilizes the three-dimensional space data of the vehicle and the central point data to form effective tracking data information and track information through a point track association and tracking algorithm, and the movement range of the vehicle is limited on a virtual road without going out of the boundary. The system continuously scans the vehicle to acquire new original digital information of the vehicle and processes the information in the above manner, and outputs new track (position) information of the vehicle, wherein the track information is based on the position information of the central point of the vehicle. In addition, the system can continuously judge whether more original digital projection information of the vehicle appears in the three-dimensional space of the vehicle (such as a middle-sized or large-sized truck and other special vehicles running on a road, when the vehicle runs on different positions, the digital projection information of two or more vehicles can be generated in the digital space projection of the system after the data acquired by the road side sensor are processed by the system, but the projection information belongs to one vehicle), if so, the system fuses the redundant digital projection information of the vehicle into one vehicle in the three-dimensional space of the vehicle, and the fusion range is within the digital projection limit of the three-dimensional space of the vehicle. If not, the system excludes it.
The system continuously calls and generates new data as reference and data processing objects by continuously scanning and acquiring the original data of the vehicle. The system excludes clutter outside of the digital projection variables of the vehicle's three-dimensional volume, but the system cannot determine whether the clutter is a projection produced by a real vehicle or an interfering wave produced by the reflection and diffraction principles of the wave. The information such as the driving rule, the motion state, the spatial attribute and the like of the vehicle driving on the actual road is used as a system to judge whether the three-dimensional digital projection of the vehicle is generated by a real vehicle to continue the operation processing or filter the three-dimensional digital projection.
The safe driving distance can be kept in the front, back, left and right of the vehicle in a smooth traffic state, a congested traffic state and a jammed traffic state unless a major traffic accident occurs, so that the vehicles are stacked together. According to traffic rules, when the motor vehicle runs on a highway and the speed exceeds 100 km per hour, the motor vehicle should keep a distance of more than 100 meters from the front vehicle of the same lane, and when the speed is lower than 100 km per hour, the distance from the front vehicle of the same lane can be properly shortened, but the minimum distance is not less than 50 meters. There are vehicles that cut down the distance of the vehicle to a range of 10 meters to 15 meters when the vehicle gets over a highway. Urban roads are often kept in the range of 3-5 meters from front to rear of the vehicle due to the high density low speed driving condition. The lateral distance between the vehicles when two vehicles are in parallel is between 1 meter and 2 meters on both highways and urban roads and national provinces. The distance between vehicles running on the expressway and the safety protection infrastructure is 1.5-4.75 m, and the distance between national provincial roads and urban road vehicles and the road boundary infrastructure is 1-2 m. The running speed of the expressway vehicle is 80-120Km/h, and national province roads and urban roads can be 30-80Km/h. Therefore, through the above description, a safety model and a space model and judgment basic conditions can be established for the actual rules, states, space positions and the roads where the vehicles run on different roads.
And judging whether the system is used on expressways, national provincial roads or urban roads, and calling different vehicle safety running models. The present embodiment describes a vehicle traveling on an expressway as an example:
when new vehicle three-dimensional digital projection appears around the tracked vehicle three-dimensional digital projection, if the distance between the two three-dimensional digital projections does not meet the minimum distance in the safe driving standard model, the vehicle digital projection is considered as a false target system to filter the false target system. If the safe driving distance of the vehicle is met, the real target is considered and tracking is kept and data information of the target is output. By the method, clutter interference caused by various reasons can be effectively filtered out. Various data output by the system becomes more stable and reliable. The method can lead the vehicle to run in a specified area and effectively filter various clutter interferences, so that the track and tracking and positioning formed by the system by acquiring the central point of the vehicle can be flatter and more accurate, the problems of large-amplitude sawness, excessive movement track and positioning deviation of the vehicle can be avoided, the positioning accuracy of the vehicle can reach the lane level by the method, and the platform with higher requirements such as unmanned driving, automatic driving, large data platform, map software and the like can be satisfied. The road side service platform 3 sends the vehicle information after fusion to the data center 5 and the third party cloud service platform 4, so that the vehicle can be more intelligently managed and controlled, the overall dispatching command capacity is improved, and the intelligent expressway big data platform is promoted to be built.
Example 2
The embodiment discloses a method for correcting a vehicle running track based on physical space attributes, which comprises the following steps:
the vehicle tracking detection sensor 1 is arranged on a road side, tracks and detects passing vehicles in a detection range, acquires original data information of all vehicles in the detection area 6 in a real-time scanning mode, and processes the original data information through the road side service platform 3 to obtain vehicle primary data information;
the road side service platform 3 analyzes, filters interference, fuses and superimposes the map data in the area and the preliminary data information of the vehicle, and converts the map data and the preliminary data information of the vehicle to obtain real-time dynamic data of the vehicle in the area, generates complete vehicle dynamic data information with longitude and latitude information and records the complete vehicle dynamic data information as D1 data information;
after the vehicle tracking detection sensor 1 detects that the vehicle enters the vehicle feature acquisition triggering area, changing the unique ID digital identification information corresponding to the vehicle into a digital triggering control command, and transmitting the digital triggering control command to the vehicle feature recognition device 2 through the road side service platform 3, wherein the vehicle feature recognition device 2 acquires the feature data information of the vehicle, and the vehicle feature data information comprises: color, model, brand, trademark, license plate, and category of the vehicle;
The road side service platform 3 fuses the dynamic vehicle data information transmitted by the vehicle tracking detection sensor 1 and the characteristic vehicle data information transmitted by the characteristic vehicle recognition equipment 2, each vehicle after fusion has unique and complete data information, and the system adopts a vehicle identity information programming principle to generate unique vehicle identity information in the system for each vehicle with complete information, and the unique vehicle identity information is recorded as data D2;
the road side service platform 3 sends the vehicle characteristic data into the vehicle three-dimensional outline size recognition matching module to carry out fuzzy matching on the vehicle characteristic data information, and determines the three-dimensional outline size information of the vehicle to form complete vehicle data information with the three-dimensional outline size of the vehicle;
the road side service platform 3 fuses the vehicle data information with the vehicle three-dimensional outline size with the vehicle dynamic data information and the vehicle characteristic data information to form complete vehicle digital information, and records the complete vehicle digital information as data D3, so that the remote tracking, positioning and monitoring of the vehicle are realized. And associating the targets by utilizing a target tracking and positioning principle and an inertial navigation principle to realize continuous tracking and positioning of the target vehicle.
The road side service platform 3 sends the vehicle characteristic data into the vehicle three-dimensional outline size recognition matching module to carry out fuzzy matching on the vehicle characteristic data information, and determines the three-dimensional outline size information of the vehicle to form complete vehicle data information with the three-dimensional outline size of the vehicle;
The road side service platform 3 fuses the vehicle data information with the vehicle three-dimensional outline size with the vehicle dynamic data information and the vehicle characteristic data information to form complete vehicle digital information, and endows the target vehicle with three-dimensional digital projection information;
establishing three-dimensional digital projection information for the protection arrangement along the road, fusing the three-dimensional digital projection information of the protection facilities along the road with the three-dimensional contour information of the vehicle, calculating space variables, and correcting the motion trail of the vehicle by utilizing the principle of the space three-dimensional attribute;
and starting a clutter interference filtering technology, eliminating stacking interference and crack interference, and eliminating clutter to ensure that the positioning accuracy of the vehicle reaches a lane level and meet the positioning requirement of the vehicle.
The road side service platform 3 sends the vehicle information after fusion to the data center 5 and the third party cloud service platform 4, so that the vehicle can be more intelligently managed and controlled, the overall dispatching command capacity is improved, and the intelligent expressway big data platform is promoted to be built.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.

Claims (9)

1. A system for implementing correction of a vehicle travel track based on physical spatial attributes, the system comprising: the vehicle tracking detection sensor is arranged at the side of a road to track and detect passing vehicles, acquires the original data information of all vehicles in the detection area range in a real-time scanning mode, transmits the original data information to the road side service platform to be analyzed and processed in real time to obtain the preliminary data information of the vehicles, the road side service platform processes, converts and fuses the preliminary data information of the vehicles with map data in the area for the first time to obtain complete vehicle dynamic data information with longitude and latitude information, starts a preset synchronous triggering data fusion rule to continuously track and monitor the vehicles entering the detection area, converts unique ID identity number information in the vehicle dynamic data information into a triggering signal of the vehicle feature recognition device, after a vehicle enters a preset vehicle feature acquisition triggering area, vehicle feature recognition equipment extracts vehicle feature data information according to a triggering instruction sent by a road side service platform, the road side service platform further fuses the vehicle feature data information with vehicle dynamic data information, the road side service platform sends the vehicle feature data into a vehicle three-dimensional outline size recognition matching module to perform fuzzy matching on the vehicle feature data information, determines three-dimensional outline size information of the vehicle, forms complete vehicle data information with the three-dimensional outline size of the vehicle, establishes vehicle three-dimensional digital projection information according to the three-dimensional outline size information of the vehicle, establishes three-dimensional digital projection information along a road along a protection facility, fuses the vehicle three-dimensional digital projection information with road three-dimensional digital projection information and calculates space variables, the motion trail of the vehicle is corrected by utilizing the spatial three-dimensional attribute principle, a clutter interference filtering technology is started, stacking interference and crack interference are eliminated, and the positioning requirement of the vehicle is met;
The method for fusing the three-dimensional digital projection information of the vehicle and the three-dimensional digital projection information of the road and calculating the space variable and correcting the motion trail of the vehicle by utilizing the principle of the three-dimensional attribute of the space specifically comprises the following steps:
acquiring central coordinate point information of a vehicle through three-dimensional digital projection information of the vehicle;
the method comprises the steps of calling three-dimensional digital projection information of a road and importing three-dimensional digital projection information of a vehicle and center point information of the vehicle;
the road three-dimensional digital projection information is used as the limit and the allowed movement range of the tracked vehicle three-dimensional digital projection information, the system can correlate the road with the three-dimensional spatial information of the vehicle, a complete spatial digital model is established, and the vehicle is ensured not to run outside the limit;
the road side service platform judges whether the same vehicle belongs to similar projection information of the vehicle or not, if so, the projections are fused into one, and if not, the projections are excluded.
2. The system for correcting the vehicle running track based on the physical space attribute according to claim 1, wherein the vehicle tracking detection sensor comprises one or more sensors of a laser radar sensor and a millimeter radar vehicle detector, the vehicle tracking detection sensor acquires the original data information of all target vehicles in a detection range in a high-speed scanning mode, the data are sent into a road side service platform to be analyzed and processed in real time to acquire the preliminary data information of the vehicles, unique ID digital identification information in the detection area is generated, the road side service platform simultaneously analyzes and processes the preliminary data information and map data information in the area, filters interference, fuses and superimposes the map data, converts the map data information into complete vehicle dynamic data information with longitude and latitude information, and becomes D1 data information, and the dynamic data information comprises longitude and latitude information, the information of each tracked target vehicle, real-time speed information, movement direction information, direction angle information, acceleration information, XYZ relative distance information and unique ID digital identification information of the vehicles in the detection range of the vehicle tracking detection sensor.
3. The system for correcting a vehicle driving track based on physical space attributes according to claim 1, wherein the vehicle feature recognition device is provided with vehicle feature recognition devices above each lane according to the number of lanes and corresponds to the number of lanes and the positions of lanes one by one, the system performs one numbering for each lane and sets a synchronous triggering data fusion area, after the vehicle tracking detection sensor detects that a vehicle enters the triggering fusion area, the system changes unique ID identity number information corresponding to the vehicle into triggering signals of the vehicle feature recognition device, the triggering signals are transmitted to the vehicle feature recognition device through a road side service platform, and the vehicle feature recognition device acquires vehicle feature data information, wherein the vehicle feature data information comprises: the method comprises the steps that the color, the train, the vehicle type, the brand, the trademark, the license plate and the category of vehicles are transmitted to a road side service platform through a communication network, the road side service platform fuses real-time vehicle dynamic data information transmitted by a vehicle tracking detection sensor and vehicle characteristic data information transmitted by the vehicle characteristic recognition device, each vehicle can have unique complete data information after fusion, and the system generates unique vehicle identity information in the system for each vehicle with complete information by adopting a vehicle identity information compiling principle and records the unique vehicle identity information as data D2.
4. The system for correcting the vehicle running track based on the physical space attribute according to claim 1, wherein the road side service platform sends the vehicle characteristic data information to the vehicle three-dimensional outline size recognition and matching module, fuzzy matching is carried out on the vehicle characteristic information in the database of the vehicle three-dimensional outline size recognition and matching module according to the vehicle type information, brand information, model information and age information of the vehicle, the vehicle three-dimensional outline size recognition and matching module receives the vehicle characteristic information sent by the system, the vehicle characteristic matching key element is utilized to carry out piece-by-piece information matching with the vehicle model characteristic data information stored in the previous system, the vehicle data information with the highest matching degree is found, other data information of the vehicle is extracted, the accurate vehicle type information and the three-dimensional outline size information of the vehicle are included, the road side service platform fuses the matched vehicle three-dimensional outline size data with the vehicle dynamic data information and the vehicle characteristic data information to obtain complete vehicle data information with the vehicle three-dimensional outline size, and the complete vehicle data information is recorded as D3 data information.
5. The system for correcting the vehicle running track based on the physical space attribute according to claim 4, wherein the road side service platform respectively analyzes the length, width and height data in the three-dimensional size of the vehicle as a combined three-dimensional limiting range fused by the same target vehicle point, comprehensively fuses the vehicle track data at different positions contained in the combined limiting range to generate complete, unique and three-dimensional vehicle track data information for continuous tracking and positioning of the target vehicle, strips redundant vehicle track information outside the three-dimensional limiting range, and if the stripped track information is within the three-dimensional limiting range of other vehicles, the stripped track information is utilized, and if the stripped track information is not, the stripped track information is considered to be interference and filtered.
6. The system for correcting the running track of the vehicle based on the physical space attribute according to claim 5, wherein the road side service platform finds the vehicle data information with highest matching degree, and invokes other data information of the vehicle including accurate vehicle type information and three-dimensional outline size information of the vehicle to give three-dimensional stereoscopic digital projection information to the target vehicle.
7. The system for correcting a vehicle running track based on physical space attributes according to claim 1, wherein the setting up process of the road three-dimensional digital projection information is: setting virtual road digital information projection in a system; giving category attributes to the curb or the infrastructure; and endowing different types of infrastructure with corresponding digital three-dimensional space projection variable information to form three-dimensional digital projection information of the road.
8. The system for correcting the vehicle running track based on the physical space attribute according to claim 7, wherein the vehicle three-dimensional digital projection information is introduced into the road three-dimensional digital projection information and then subjected to fusion and space variable calculation, the motion track of the vehicle is corrected by utilizing the space three-dimensional attribute principle, the clutter interference filtering technology is carried out, the stacking interference and the crack interference are eliminated, the positioning accuracy of the vehicle reaches the lane level after the clutter is eliminated, and more than two vehicles running in the same direction, the same speed and transversely side by side or more than two vehicles running in the same direction and the same speed and longitudinally side by side can be accurately distinguished through the calculation of the physical space attribute.
9. The method for correcting the running track of the vehicle based on the physical space attribute is characterized by comprising the following steps:
the vehicle tracking detection sensor is arranged at the road side, tracks and detects the passing vehicles in the detection range, acquires the original data information of all vehicles in the detection area range in a real-time scanning mode, and processes the original data information through the road side service platform to obtain the preliminary data information of the vehicles;
the road side service platform analyzes, processes, filters out interference, fuses and superimposes the map data in the area and the preliminary data information of the vehicle, acquires real-time dynamic data of the vehicle in the area, generates complete vehicle dynamic data information with longitude and latitude information and records the complete vehicle dynamic data information as D1 data information;
after the vehicle tracking detection sensor detects that the vehicle enters the vehicle feature acquisition triggering area, changing the unique ID digital identification information corresponding to the vehicle into a digital triggering control command, and transmitting the digital triggering control command to the vehicle feature recognition equipment through the road side service platform, wherein the vehicle feature recognition equipment acquires the feature data information of the vehicle, and the vehicle feature data information comprises: color, model, brand, trademark, license plate, and category of the vehicle;
The road side service platform fuses the dynamic vehicle data information transmitted by the vehicle tracking detection sensor and the characteristic vehicle data information transmitted by the vehicle characteristic recognition equipment, each vehicle after fusion has unique complete data information, the system adopts a vehicle identity information programming principle to generate unique vehicle identity information for each vehicle with complete information in the system, and the unique vehicle identity information is recorded as data D2;
the road side service platform sends the vehicle characteristic data into the vehicle three-dimensional outline size recognition matching module for carrying out fuzzy matching on the vehicle characteristic data information, and determines the three-dimensional outline size information of the vehicle to form complete vehicle data information with the three-dimensional outline size of the vehicle;
the road side service platform fuses the vehicle data information with the vehicle three-dimensional outline size with the vehicle dynamic data information and the vehicle characteristic data information to form complete vehicle digital information, records the complete vehicle digital information as data D3 and endows the target vehicle three-dimensional digital projection information;
establishing three-dimensional digital projection information of the road for the protection setting along the road, fusing the three-dimensional digital projection information of the road and the three-dimensional digital projection information of the vehicle, calculating space variables, and correcting the motion trail of the vehicle by utilizing the principle of the three-dimensional attribute of the space; the method specifically comprises the following steps:
Acquiring central coordinate point information of a vehicle through three-dimensional digital projection information of the vehicle;
the method comprises the steps of calling three-dimensional digital projection information of a road and importing three-dimensional digital projection information of a vehicle and center point information of the vehicle;
the road three-dimensional digital projection information is used as the limit and the allowed movement range of the tracked vehicle three-dimensional digital projection information, the system can correlate the road with the three-dimensional spatial information of the vehicle, a complete spatial digital model is established, and the vehicle is ensured not to run outside the limit;
the road side service platform judges whether the same vehicle belongs to similar projection information of the vehicle or not, if so, the projections are fused into one, and if not, the projections are removed;
and starting clutter interference filtering technology, eliminating stacking interference and crack interference, removing clutter, enabling the positioning accuracy of the vehicle to reach a lane level, and calculating physical space attributes to enable more than two vehicles running in the same direction, at the same speed and transversely side by side or more than two vehicles running in the same direction and longitudinally side by side at the same speed to be accurately separated, so that the positioning requirement of the vehicle is met.
CN202010769036.1A 2020-08-03 2020-08-03 System and method for correcting vehicle running track based on physical space attribute Active CN112034449B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010769036.1A CN112034449B (en) 2020-08-03 2020-08-03 System and method for correcting vehicle running track based on physical space attribute

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010769036.1A CN112034449B (en) 2020-08-03 2020-08-03 System and method for correcting vehicle running track based on physical space attribute

Publications (2)

Publication Number Publication Date
CN112034449A CN112034449A (en) 2020-12-04
CN112034449B true CN112034449B (en) 2024-01-12

Family

ID=73582196

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010769036.1A Active CN112034449B (en) 2020-08-03 2020-08-03 System and method for correcting vehicle running track based on physical space attribute

Country Status (1)

Country Link
CN (1) CN112034449B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113554866A (en) * 2021-06-03 2021-10-26 广东未来智慧城市科技有限公司 3D vehicle track calculation analysis display system
CN115631356B (en) * 2022-11-28 2023-08-08 北京闪马智建科技有限公司 Method and device for identifying missing of road facility, storage medium and electronic device
CN117593708B (en) * 2024-01-16 2024-04-16 苏州映赛智能科技有限公司 Traffic digital twin method, equipment and storage medium containing vehicle identity information

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107000745A (en) * 2014-11-28 2017-08-01 株式会社电装 The travel controlling system and travel control method of vehicle
CN108345822A (en) * 2017-01-22 2018-07-31 腾讯科技（深圳）有限公司 A kind of Processing Method of Point-clouds and device
CN108922188A (en) * 2018-07-24 2018-11-30 河北德冠隆电子科技有限公司 The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system
CN108961767A (en) * 2018-07-24 2018-12-07 河北德冠隆电子科技有限公司 Highway inspection based on four-dimensional outdoor scene traffic simulation, which is pursued and captured an escaped prisoner, takes alarm system
CN109064755A (en) * 2018-07-24 2018-12-21 河北德冠隆电子科技有限公司 Path identification method based on four-dimensional outdoor scene traffic simulation road conditions perception management system
CN110930692A (en) * 2019-10-24 2020-03-27 河北德冠隆电子科技有限公司 Active vehicle continuous tracking device, system and method
JP2020090119A (en) * 2018-12-03 2020-06-11 日立オートモティブシステムズ株式会社 Vehicle control device
CN111402588A (en) * 2020-04-10 2020-07-10 河北德冠隆电子科技有限公司 High-precision map rapid generation system and method for reconstructing abnormal roads based on space-time trajectory

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107000745A (en) * 2014-11-28 2017-08-01 株式会社电装 The travel controlling system and travel control method of vehicle
CN108345822A (en) * 2017-01-22 2018-07-31 腾讯科技（深圳）有限公司 A kind of Processing Method of Point-clouds and device
CN108922188A (en) * 2018-07-24 2018-11-30 河北德冠隆电子科技有限公司 The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system
CN108961767A (en) * 2018-07-24 2018-12-07 河北德冠隆电子科技有限公司 Highway inspection based on four-dimensional outdoor scene traffic simulation, which is pursued and captured an escaped prisoner, takes alarm system
CN109064755A (en) * 2018-07-24 2018-12-21 河北德冠隆电子科技有限公司 Path identification method based on four-dimensional outdoor scene traffic simulation road conditions perception management system
JP2020090119A (en) * 2018-12-03 2020-06-11 日立オートモティブシステムズ株式会社 Vehicle control device
CN110930692A (en) * 2019-10-24 2020-03-27 河北德冠隆电子科技有限公司 Active vehicle continuous tracking device, system and method
CN111402588A (en) * 2020-04-10 2020-07-10 河北德冠隆电子科技有限公司 High-precision map rapid generation system and method for reconstructing abnormal roads based on space-time trajectory

Also Published As

Publication number Publication date
CN112034449A (en) 2020-12-04

Similar Documents

Publication Publication Date Title
CN111524357B (en) Method for fusing multiple data required for safe driving of vehicle
CN112034449B (en) System and method for correcting vehicle running track based on physical space attribute
US11685360B2 (en) Planning for unknown objects by an autonomous vehicle
CN111402588B (en) High-precision map rapid generation system and method for reconstructing abnormal roads based on space-time trajectory
US10281920B2 (en) Planning for unknown objects by an autonomous vehicle
CN111540237A (en) Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion
WO2022141910A1 (en) Vehicle-road laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field
US20180259967A1 (en) Planning for unknown objects by an autonomous vehicle
CN112017431A (en) Active vehicle continuous tracking and positioning system and method based on multi-data fusion
JP7466396B2 (en) Vehicle control device
CN202071799U (en) Intelligent automobile safety warning device
DE112020002764T5 (en) SYSTEMS AND METHODS FOR VEHICLE NAVIGATION
DE102016217645A1 (en) A method for providing information about a probable driving intention of a vehicle
DE112021002001T5 (en) NAVIGATING A VEHICLE USING AN ELECTRONIC HORIZON
CN114419874B (en) Target driving safety risk early warning method based on road side sensing equipment data fusion
CN111768642A (en) Road environment perception and vehicle control method, system and device of vehicle and vehicle
CN109871787A (en) A kind of obstacle detection method and device
DE112020002592T5 (en) SYSTEMS AND METHODS FOR VEHICLE NAVIGATION BASED ON IMAGE ANALYSIS
CN110942623A (en) Auxiliary traffic accident handling method and system
CN113085852A (en) Behavior early warning method and device for automatic driving vehicle and cloud equipment
DE112020005275T5 (en) SYSTEMS AND METHODS FOR SELECTIVE DECELERATION OF A VEHICLE
US20230120095A1 (en) Obstacle information management device, obstacle information management method, and device for vehicle
CN112208532A (en) Vehicle control device, vehicle control method, and storage medium
DE112022000380T5 (en) SYSTEMS AND METHODS FOR UNIFORM SPEED MAPPING AND NAVIGATION
CN114694060A (en) Road shed object detection method, electronic equipment and storage medium

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 050030 2002, block B, white commercial plaza, 105 Huaian East Road, Yuhua District, Shijiazhuang City, Hebei Province

Applicant after: HEBEI DEGUROON ELECTRONIC TECHNOLOGY Co.,Ltd.

Address before: 050030 Xinhai Tiantian Residential Building, 295 Donggang Road, Yuhua District, Shijiazhuang City, Hebei Province, 15-3-1303

Applicant before: HEBEI DEGUROON ELECTRONIC TECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant