CN109212514A - A kind of detections of radar equipment persistently tracks correlating method to movement and static target - Google Patents
A kind of detections of radar equipment persistently tracks correlating method to movement and static target Download PDFInfo
- Publication number
- CN109212514A CN109212514A CN201811151782.3A CN201811151782A CN109212514A CN 109212514 A CN109212514 A CN 109212514A CN 201811151782 A CN201811151782 A CN 201811151782A CN 109212514 A CN109212514 A CN 109212514A
- Authority
- CN
- China
- Prior art keywords
- mark
- information
- point
- point mark
- mark information
- 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.)
- Granted
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
- G01S13/006—Theoretical aspects
-
- 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
Abstract
The invention discloses a kind of detections of radar equipment persistently to track correlating method to movement and static target, and the detections of radar equipment persistently tracks correlating method to movement and static target the following steps are included: obtaining the point mark information parameter of multiple mobile targets；The point mark information that corresponding parameter difference is less than preset threshold is screened, similitude mark information is defined as；According to a mark information parameter, similitude mark is merged；It is associated or is excluded according to the click information that the speed, acceleration in mark information parameter, the judgement of turning rate information detect；Point mark information is associated at will acquire at least two；According to one estimation range of associated mark information creating, the estimation range be one formed before mark predict the mark occur next position where regional scope；The lasting scanning that a mark is carried out in the estimation range of mark obtains.Point mark information corresponding to mobile target is recognized accurately by the methods of Contact fusion, point mark association in the present invention, reduces the treating capacity of system data.
Description
Technical field
The present invention relates to traffic monitoring and a large amount of target following technical fields of higher-frequency radar, and in particular to a kind of radar inspection
Measurement equipment persistently tracks correlating method to movement and static target.
Background technique
With the fast development of China's highway, the hardware device and software level of preventing road monitoring system are also with science and technology
The raising of development level and keep updating.Expressway Road monitoring system is mainly by highway all fronts
Magnitude of traffic flow detection, the monitoring of traffic condition, environment weather detection, the monitoring of operation conditions, are advised according to a series of intelligent controls
Control program then is generated with strategy, controls the flow of traffic to realize, improves traffic environment, reduction accident, reaches highway
To higher service level.
Video traffic event automatic detection system is remotely controlled using roadside or the fixation video camera in tunnel and outfield
The high clear video image of video camera automatically updates technology using vehicle tracking technology and background image, from image sequence as input
Target information is chosen in the variation of column and carries out calculation processing, and vehicle motion track is analyzed, is produced according to image processing algorithm
Raw event alarm.By processing to video image analysis, in the coverage area of image, be able to carry out various traffic events,
The automatic detection such as fire of accident, pedestrian, vehicle lay-off, traffic congestion, vehicle drives in the wrong direction, vehicle sheds object fragment, low visibility
Detection etc., and system can fast automatic alarm and video recording in real time, for road traffic safety management and road operation mention
For greatly helping.
The fusion application of high-definition video monitoring system and Video Events detection system at this stage, even more promotes road monitoring
System has strided forward major step towards automation, humanized direction, is capable of active by the video detection analytical equipment of rear end
To the vehicle and hazard event that are travelled on road and in tunnel and pedestrian, sheds object and be used for quickly detecting and quickly pre-
It is alert, so that the safety management level of highway has been obtained very big promotion, and reduce the generation of various hidden dangers, uses
The environment of driving of passerby is also safer, and various accidents constantly reduce, and economic loss also significantly reduces.
Although being equipped with total factor detection device or more elements on demand at both sides of the road in highway monitoring system
Detection device, but since the weather detection devices price of profession is very expensive, valuableness can not be still widely used, even
It is that many functions are not utilized and cause very big waste.Since Professional Meteorological station is all to be pinpointed the position for being laid in a certain fixation
It sets and cannot at will move, acquired data also can only be the meteorological data of single-point, rather than continuum or a wide range of
Accurate data, although we can obtain the local weather condition on following several days or the same day by meteorological observatory, but it is past
Toward the situation for appearing in same city or uniform areas " here rain, fine over there ", the more element detection devices of highway it
Between laying spacing distance be even more at 20 kilometers or more, even farther distance can just lay a set of equipment, and it is even more impossible to true quasi-
The actual Road Weather situation of true reflection.And such case is even more to road operation management person and other important mechanisms or portion
Door causes very big influence, even causes the danger of unnecessary economic loss either life.For example winter high speed is public
Road or urban transportation major trunk roads will cause after snowing it is icy on road, and it is this it is icy on road be not fixed point, this is just
Needing the ice condition to entire road, weather condition to carry out the authentic and valid data of effective detection acquisition can take more
Add effective methods to avoid the generation of various disasters.There are also haze weather, rain, snow weather or foggy weather it is same
Sample also has a generation of such case, and it is this under the conditions of fixed point weather detector will seem that power is had no way of the heart.There are also in tunnel
Although also having laid smoke sensor device in road but being all that fixed point is laid, there are also the pernicious gas detections and environment measuring in tunnel
It is all using fixed point detection, and the data for reflecting some node and/or a section that quantity seldom can only be unilateral, no
The large-scale accurate data in successional region can be represented, especially when traffic accident event occurs in tunnel, this number
According to even more important, obtaining continuity earlier, accurately and reliably valid data alert reconciliation lifesaving life to danger and provide technology branch
Support, this is extremely important for a traffic administration person.
When carrying out target following in the prior art, according to radar tracking, point mark can be formed to tracking target, point mark refers to
Radar passes through the data-signal of a certain position of the mobile target obtained after data processing during the scanning process, he is to realize tracking
Most basic data cell.It, can but if a reason of target object is excessive or too long even its appearance physical structure
Energy can be by multiple " sampling ".Such as truck is sampled, due to the shape of object, surface and 360 ° of radar scanning
Reason, after being handled by radar data, we may have 2 or more point mark appearance, but these marks but only represent
One object！As in oneainstance, radar scanning truck can collect three marks, and three marks can be as three targets
Object carries out continuing tracking, if information and the pedestrian information phase such as track, direction, speed, signal strength or weakness of Targets Dots traveling
When mutually coincideing, these three point marks will be taken as pedestrian or other types object to track and identify, and the inspection for vehicle
Observing and predicting police just will not always obtain.
Summary of the invention
A kind of detections of radar equipment of being designed to provide of the embodiment of the present invention persistently tracks movement and static target
Correlating method, more to solve existing traffic information or radar chaff, radar identification process causes target identification tracking inaccuracy,
The same target or a large amount of targets can not be carried out simultaneously and continue the problem of tracking precise positioning.
To achieve the above object, the technical solution of the embodiment of the present invention is
A kind of detections of radar equipment persistently tracks correlating method, the detections of radar equipment pair to movement and static target
Movement and static target persistently track correlating method the following steps are included:
Obtain the point mark information parameter of multiple mobile targets；
The point mark information that corresponding parameter difference is less than preset threshold is screened, similitude mark information is defined as；
According to a mark information parameter, similitude mark is merged；
It is to be closed according to the click information that the speed, acceleration in mark information parameter, the judgement of turning rate information detect
Join or is excluded；
Point mark information is associated at will acquire at least two；
According to one estimation range of associated mark information creating, the estimation range is formed before mark one pre-
Survey the regional scope where next position of mark appearance；
The lasting scanning that a mark is carried out in the estimation range of mark obtains.
As a preferred solution of the present invention, the point mark information parameter for obtaining multiple mobile targets, comprising:
Obtain multiple Targets Dots mobile track, direction, speed and signal strength or weakness information；
Classify to the track of acquisition, direction, speed, signal strength information.
As a preferred solution of the present invention, the point mark information screened corresponding parameter difference and be less than preset threshold,
It is defined as similitude mark information, comprising:
Obtain the trace information of first mark and its neighbouring second point mark；
Judge whether first mark be consistent with the trace information of second point mark；
If the determination result is YES, continue the directional information of first mark of acquisition and second point mark；
Judge whether first mark be consistent with the directional information of second point mark；
If the determination result is YES, continue the velocity information of first mark of acquisition and second point mark；
Setting speed difference threshold, judges whether the difference of the velocity information of first mark and second point mark is less than setting
Threshold value；
If the determination result is YES, continue the signal strength information of first mark of acquisition and second point mark；
Setting signal strength difference threshold value judges whether the difference of first mark and the signal strength of second point mark is less than and sets
Fixed threshold value；
If the determination result is YES, then it defines first mark and second point mark is similitude mark.
As a preferred solution of the present invention, the speed, acceleration according in mark information parameter, turning rate letter
The point mark information that breath judgement detects is associated or is excluded, comprising:
The minimum speed and maximum speed of normally travel vehicle are set, the minimum speed and maximum of normal walking pedestrian are set
Speed；
The peak acceleration of the minimum acceleration sum of normally travel vehicle is set, the minimum of setting normal walking pedestrian accelerates
Degree and peak acceleration；
Set the minimum turning rate and maximum turning rate of normally travel vehicle；
Generate rate/turning rate value, the rate of the normal walking pedestrian/turning rate value of normally travel vehicle；
Speed, acceleration, the turning rate in multiple mark informations parameter are obtained, judges rate/turning rate of a mark parameter
Value, whether the value of acceleration match with the vehicles or pedestrians respective value of normally travel；
If judging result is to match with the vehicle of normally travel, multiple mark information are subjected to the association of vehicle point mark,
Exclude pedestrian's point mark information；
If judging result is to match with the pedestrian of normal walking, multiple mark information are subjected to the association of pedestrian's point mark,
Exclude vehicle point mark information.
As a preferred solution of the present invention, when setting the speed and turning rate parameter of normally travel vehicle and pedestrian,
The mobile target type setting matching numerical value tracked as needed.
As a preferred solution of the present invention, described according to one estimation range of associated mark information creating, it is described
Estimation range be one formed before mark predict the mark occur next position where regional scope, wherein area
Domain range is formed by speed, acceleration, rate of turn.
As a preferred solution of the present invention, the method also includes:
Judge whether mobile Targets Dots have non-continuous association；
If the determination result is YES, then inertia forecasting complement point is carried out to the point mark of disappearance；
The inertia forecasting complement point includes:
Obtain the moving direction information before Targets Dots disappear, velocity information, acceleration information；
The following several moulds of Targets Dots are generated according to the moving direction information, velocity information, acceleration information of Targets Dots
Quasi- point mark information；
The point mark information occurred again is obtained, is matched with simulation point mark information, judges the point mark information occurred again
It is whether consistent with simulation point mark information；
If the determination result is YES, then confirm the point mark information lost before this mark information is, continue for tracking target.
It as a preferred solution of the present invention, further include interference filtering, the interference filtering includes:
Newly-built clutter map；
Scanned by first time of radar sensor, by scanning information result be sent in clutter map as new background into
Row processing；
The scanning new each time of tracing detection radar sensor, scanning information result is sent in clutter map, and first
Data carry out continuing Overlapping display；
Obtain the picture of stationary object in clutter map；
Stationary object back wave is removed according to the picture of stationary object in clutter map；
Clutter map is saved in the database, and is reused as base map.
As a preferred solution of the present invention, when clutter map is reused as base map, comprising:
Clutter map is extracted from new data；
According to clutter map, static object is removed from Data processing.
The embodiment of the present invention has the advantages that
The embodiment of the present invention utilizes radar scanning, continue tracking without will cause to a large amount of movement path of movable objective
Clutter objects track mistake, cause to scan multiple marks for that may scan to different parts same target object
Point mark information corresponding to mobile target is recognized accurately by the methods of Contact fusion, point mark association in target, meanwhile, it is capable to
The interference of stationary object is filtered by clutter map, obtains more accurately putting mark information, be extracted from new data every time
Clutter map, static object can be eliminated from data handling procedure, not need to analyze the data of clutter map, from
And reduce the treating capacity of system data.
Detailed description of the invention
Fig. 1 is that target Continuous tracks process flow diagram flow chart in an embodiment of the present invention.
Fig. 2 is point mark acquisition schematic diagram of the detections of radar equipment for lorry.
Fig. 3 is point mark extraction schematic diagram of the detections of radar equipment for lorry.
Fig. 4 is the Contact fusion schematic diagram that detections of radar equipment is directed to lorry.
Fig. 5 is the method flow schematic diagram of an embodiment of the present invention.
Fig. 6 is the method flow schematic diagram of another embodiment of the invention.
Fig. 7 is the method flow schematic diagram of another embodiment of the invention.
Fig. 8 is that detections of radar equipment collection point mark blocks schematic diagram.
Fig. 9 is the method flow schematic diagram of an embodiment of the present invention.
Figure 10 is the point mark horizon prediction schematic diagram that turning rate and speed are formed.
Figure 11 is that a mark loses schematic diagram.
Figure 12 is that inertia forecasting point is automatically replenished schematic diagram in an embodiment of the present invention.
Figure 13 is the method flow schematic diagram of another embodiment of the invention.
Figure 14 is the method flow schematic diagram of another embodiment of the invention.
Figure 15 is detections of radar clutter schematic diagram.
Figure 16 is the method flow schematic diagram of another embodiment of the invention.
Figure 17 is the method flow schematic diagram of another embodiment of the invention.
Figure 18 is the method flow schematic diagram of another embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Usually herein
The component of the embodiment of the present invention described and illustrated in place's attached drawing can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention..
The embodiment of the present invention carries out a mark tracking using more element omnidirectional trackings monitoring radar sensor, which uses
Dominant frequency is 77GHZ high-frequency emission unit, signal receiving unit, 360 ° of scanning elements, data processing unit and communication unit, power supply
Administrative unit etc. composition, core data processing unit using multithreading high speed processor can simultaneously tracking and positioning detection zone
1000 target objects are no less than in domain.The radar detector uses 360 ° of high speed scanning modes can be centered on radar, partly
Diameter is that target object carries out continuing tracking and positioning in 500 meters of entire areas, and equipment can be with 50-250 milliseconds of time interval to outgoing
One group of data is sent, the initial data that furthermore radar will acquire is sent to data analysis processor, at system global analysis
It can provide each vehicles or pedestrians and the instantaneous velocity of animal, the direction of motion, longitude and latitude, target ruler in one kilometer after reason
The important informations such as very little, ID number, deflection, place lane.The vehicle model information of vehicle is extracted, system can be empty by setting
Intend the mode of coil to obtain the approximate shape and vehicle of vehicle.The radar sensor is using integrated design and is integrated with
8000000 pixel high-speed dome monitor cameras and more element meteorology detection sensors (can detecte and export data of the Temperature and Humidity module, light
According to light intensity data, wind direction and wind velocity data, rainfall data, sulfur dioxide, carbon dioxide, carbon monoxide, methane, formaldehyde, natural gas,
The pernicious gases such as gas of liquefied gas data), in order to guarantee the radar service life equipment body using IP67 security protection etc.
Grade.In order to which equipment power dissipation is effectively reduced, low power dissipation design and device are all selected and used to all components of radar.Using RJ45
10/100/1000M adaptive network interface cable connection type, and POE can be supported to power.
See Fig. 1, is that target Continuous tracks process flow diagram flow chart in an embodiment of the present invention.Movement and static target are held
When continuous tracking association, following steps is needed to be executed, including mark extractions, Contact fusion, point mark be associated with (speed, acceleration,
Turning rate), inertia rule target loss compensate automatically, be continuously tracked target point information export.
See Fig. 2-Fig. 4, truck is carried out in a kind of practical application to continue tracking, but has the shape of truck, table
The reason of 360 ° of scanning of face reason and radar, after handling by radar data, may there is 2 or multiple marks appearance, but this
A little point marks only represent this target of truck.Multiple marks are taken as multiple target objects in figure and carry out continuing tracking, such as
The information such as track, direction, speed, the signal strength or weakness of fruit Targets Dots traveling and pedestrian information are mutually coincide, multiple mark information
Pedestrian information will be mistaken as to be tracked and identified, can not finally obtain the detection alarm to vehicle.
See Fig. 5, a kind of detections of radar equipment disclosed in the present embodiment persistently tracks affiliated party to movement and static target
Method monitors radar sensor using more element omnidirectional trackings and server is realized.
Specifically, in the step s 100, obtaining the point mark information parameter of multiple mobile targets.
See Fig. 6, in step s101, obtains the mobile track of multiple Targets Dots, direction, speed and signal strength or weakness letter
Breath；
In step s 102, classify to the track of acquisition, direction, speed, signal strength information.
The Targets Dots mobile message got, after collated, as subsequent Contact fusion, the point associated foundation of mark.
In step s 200, the point mark information that corresponding parameter difference is less than preset threshold is screened, similitude mark letter is defined as
Breath.
Fig. 7 is seen, specifically, in step 201, obtaining the trace information of first mark and its neighbouring second point mark；
In step 202, judge whether first mark be consistent with the trace information of second point mark；
In step 203, if the determination result is YES, continue the directional information of first mark of acquisition and second point mark；
In step 204, judge whether first mark be consistent with the directional information of second point mark；
In step 205, if the determination result is YES, continue the velocity information of first mark of acquisition and second point mark；
In step 206, setting speed difference threshold, judges first mark and the difference of the velocity information of second point mark is
The no threshold value for being less than setting；
In step 207, if the determination result is YES, continue the signal strength information of first mark of acquisition and second point mark；
In a step 208, setting signal strength difference threshold value judges the difference of the signal strength of first mark and second point mark
Whether value is less than the threshold value of setting；
In step 209, if the determination result is YES, then it defines first mark and second point mark is similitude mark.
In step S300, according to a mark information parameter, similitude mark is merged.Contact fusion refers to a spacing
Point mark from, the very close tracking target of the direction of motion, movement velocity, turning rate, which carries out effectively merging, to be prevented because of same mesh
Mark object scanning scans the appearance of multiple Targets Dots mistake phenomenons to different parts and causing, specifically include that consolidation scope,
Point mark after merging azimuth, merging defines (delineation) into an entity, and the size of this entity, pixel number etc. is all new
, it automatically tracks so higher with the confidence level of event category information.
After point mark extracts, next a mark will be associated, and can not judge to be obtained if not being associated
Radar data and point it is corresponding on earth be those target objects, the same object can not be carried out continue tracking,
Therefore same moving object can continue tracking and can obtain lasting point mark to believe by point mark correlation technology
It ceases, effectively lasting point mark information is the basis to moving target object state judgement.
See Fig. 8, it is the continuous judgement to the movement of same target that system, which automatically tracks, and the accuracy automatically tracked directly determines
This system key point that can anomalous event accident detection and traffic data collection function be realized, automatically track inaccuracy
Even the not high detection accuracy that will lead to whole system of stability reduces, false alarm is high, fail to report more, accuracy of data acquisition is poor,
The appearance of the weak equal shortcomings of system stability, therefore possess for this system and a set of reliable and stable to automatically track algorithm
It is extremely important for this system with realization mechanism.But the feelings that persistently can be tracked and be detected by radar in actual traffic
Condition is seldom, and always have and occur such as not as good as the case where meaning: occlusion (cart screening trolley), barrier block, sometimes
Even tracked target object is continuously blocked.The appearance of such case will be such that tracked vehicle loses in systems
It loses, and can not be arrived by effective recognition and tracking, it is even more impossible to any abnormal conditions progress and alarm and nothing occurs to the target
Method collects correct traffic data.
In step S400, the point detected is judged according to speed, acceleration, the turning rate information in mark information parameter
Hitting information is associated or is excluded.
Wherein, for speed, if a mark association is allowed to detect only for pedestrian, we cannot be by speed
50,000 ms/hour are set as, if being directed to the vehicle of normally travel, its speed cannot be set as 3,000 ms/hour by we, because
This does not meet practical rule in practice.Therefore, suitable and accurate target is selected to be detected.
For acceleration, defining acceleration is the degree for determining target and accelerating or slowing down.
For turning rate, defining turning rate is the direction degree that target changes movement.
By to the setting with three data can effectively judge the point mark information being detected be it is associated or
It is excluded.
See Fig. 9, in step S401, sets the minimum speed and maximum speed of normally travel vehicle, set normal walking
The minimum speed and maximum speed of pedestrian；
In step S402, the peak acceleration of the minimum acceleration sum of normally travel vehicle is set, sets normal walking
The minimum acceleration and peak acceleration of pedestrian；
In step S403, the minimum turning rate and maximum turning rate of normally travel vehicle are set；
In step s 404, rate/turning rate value, the rate of normal walking pedestrian/turn of normally travel vehicle are generated
The value of curved rate；
Setting speed/turning rate value is higher, then is easier to be associated the target of appearance, but may be unrelated
Target be associated, cause trigger false alarm；
Setting speed/turning rate value is lower, then reduces the association of inaccuracy, may close to relevant target
Connection, cannot form tracking.
See Figure 10, when setting the speed and turning rate parameter of normally travel vehicle and pedestrian, the movement that tracks as needed
Target type setting matching numerical value.Because according to automobile, pedestrian, shedding the normal motion state of object it can be concluded that following knot
By:
In the case where not causing to automatically track loss, speed/turning rate value is arranged the smaller the better, according to practical feelings
Condition is specifically arranged；
The speed of pedestrian movement is very slow (< 10m/s), but the change direction of pedestrian is quickly；
It is relatively slow (but Vehicle Speed is quickly) that vehicle changes direction；
If both vehicle and pedestrian will track, need to set the compromise value of a speed/turning rate value.
In step S405, speed, acceleration, the turning rate in multiple mark informations parameter are obtained, judges a mark parameter
Rate/turning rate value, whether the value of acceleration match with the vehicles or pedestrians respective value of normally travel；
In step S406, if judging result is to match with the vehicle of normally travel, multiple mark information are carried out
The association of vehicle point mark, excludes pedestrian's point mark information；
In step S 407, if judging result is to match with the pedestrian of normal walking, multiple mark information are carried out
The association of pedestrian's point mark, excludes vehicle point mark information.
In step S500, will acquire at least two at point mark information be associated.Because only that a mark information is
It can not be judged, an estimation range can be created by three above parameter.Wherein, estimation range is before mark
One formed predicts the regional scope where next position that the mark occurs, wherein regional scope is by speed, acceleration
Degree, rate of turn are formed.
In step S600, according to one estimation range of associated mark information creating, the estimation range is in a mark
One of preceding formation predicts the regional scope where next position that the mark occurs.
In step S700, the lasting scanning that a mark is carried out in the estimation range of mark is obtained.
In practical applications, detected target due to traveling vehicle or barrier block or other reasons, very may be used
It Targets Dots can be will lead to disappears without method and form lasting point mark association, less will form and effectively automatically track.Such as Figure 11
It is shown, be wherein exactly at blank spot target object point mark disappear point information, inertia phenomena and principle based on object of which movement,
Although point mark can sometimes be lost, we are appointed using principle of inertia so can smoothly predict its position, in the mark
When occurring again, it is just able to maintain tracking, this process is just called coast prediction.Although there is partial dot mark information loss,
By that can obtain after the progress operation of computer inertial model, target future 1 is total, 2 even more " simulations " point marks are believed
Breath, when the mark again "true" detected and obtained mark information and simulation put mark information it is consistent when, our energy
It enough determines the point mark lost before the mark is exactly, can continue to track identical target, complement point is predicted by inertia point mark
The result that the automatic loss point mark that filling technique is realized is filled automatically is as shown in figure 12.
See Figure 13, in an embodiment of the present invention, inertia forecasting complement point technology is as follows:
In step S800, judge whether mobile Targets Dots have non-continuous association；
In step S900, if the determination result is YES, then inertia forecasting complement point is carried out to the point mark of disappearance；
See Figure 14, the inertia forecasting complement point includes:
In step S901, the moving direction information before Targets Dots disappear, velocity information, acceleration information are obtained；
In step S902, target point is generated according to the moving direction information, velocity information, acceleration information of Targets Dots
The following several simulation point mark information of mark；
In step S903, the point mark information occurred again is obtained, is matched with simulation point mark information, judgement goes out again
Whether existing point mark information and simulation point mark information are consistent；
In step S904, if the determination result is YES, then confirms the point mark information lost before this mark information is, continue
Persistently track target.
It should be noted that the automatic filling technique of inertia forecasting point is a kind of when target point information is lost, simulation
Point mark simulates the False Intersection Points mark information come, which is not true point according to the characteristics of motion and motion state before
Mark information is an illusory point mark information.Therefore, this mark information cannot be excessive, if excessively will lead to system accuracy
Decline, and will lead to the tracking of mistake and the warning message of mistake.It is indicated with a model, Z is true point mark information, and X is
The point mark information of inertia simulation, Z value become larger be equivalent to it is bigger to the detection information of real target, but need it is farther distance
Tracking can be obtained, and X value is bigger, the detection accuracy and reliability of system are lower, generally set Z value as 5, X based on experience value
Value is 2, i.e., the five point mark information being continuously tracked allow 2 marks to disappear.
When conditions above all meets, one effectively automatically tracks model and will be established, and can carry out to same target
Lasting tracking, subsequent data interface can be right after being handled by the continuous mark information, analyze, judge, calculate
Target object representated by this mark carries out the alarm of anomalous event accident detection, traffic data collection, trajectory analysis, video camera
Tracking is checked.
Clutter map is the adaptive processing method in a kind of time domain.It is mainly used to record radar site ambient enviroment in real time
Clutter distribution and its Strength Changes.It is handled based on the multiple sweeping value to the same space unit to estimate this element
The average amplitude of clutter, to provide two hierarchical informations of radar site ambient enviroment.See Figure 15, clutter map is to radar sensor
Stationary body in working range carries out record identification image.Clutter map has as radar sensor and its reference point of tracking
Help it more to concentrate on mobile object focus, it is the basis for further effectively filtering out interference.System is initially installed
After the completion, it needs to create a clutter map for each radar sensor and preferably constantly updates each thunder in the actual operation process
The object temporarily moved is updated to wherein with interference source changeless in wiping out background up to the clutter map of equipment.Furthermore sharp
Unnecessary treatment loss can be reduced with clutter map, improves the detection energy of target especially low speed (being lower than 5km/h) Small object
Power.There are also some objects such as lawn, trees, road sign etc. can also feed back strong signal out, just need in this case
The generation of such case is limited using real-time clutter map.Clutter map is to form noise background for static object.Clutter
Figure working method is as follows: the scanning new each time of more element omnidirectional tracking detection radar sensors just will be updated a clutter
Figure.System data information obtained will be fed in clutter map to be handled as completely new background, in addition clutter map
Renewal frequency be modified also by parameter setting.Once first clutter map is established, each subsequent new scanning is miscellaneous
Wave diagram data will carry out continuing to be superimposed with first clutter diagram data, and the new data that first clutter map absorbs is more, behind
The data for needing to be parsed into tracking will be fewer.When system processes data, the back wave for removing static object is critically important, and quiet
Only the back wave of object is exactly to be reflected in clutter map.Once clutter map establish, it is seen that be exactly static object figure
Piece, clutter map can be saved in the database, be recycled as background (base map) data.Data that treated can with it is miscellaneous
Wave figure base map is compared, and prevents the clutter diagram data in shade processed.
Clutter map is extracted from new data every time, static object can be eliminated from data handling procedure, also
It is not need to analyze the data of clutter map, to reduce the treating capacity of system data.
See Figure 16, filters out flow chart for system interference.Detections of radar is equipped with detection and alarm nucleus module, services obtaining
After setting regular data information/control instruction that device sends over, Target Signal Strength is adjusted according to corresponding information, judges target
Whether in detection zone, if the determination result is YES, then further judge whether target is just detecting in lane, it is established that beginning track
And algorithm model is called, including immediacy arithmetic model, logical algorithm model and correction algorithm model, judge that tracked target moves
Whether direction/movement angle is being allowed in range, and if the determination result is YES, foundation can satisfy target and identification is continuously tracked
Radix, generates clutter map, and the interference of the fixed target of wiping out background (map) further filters out other irregular signal interferences, filters
Except carry out the interference of electromagnetic signal.
See Figure 17, in an embodiment of the present invention, interference filtering is as follows:
In step S1000, clutter map is created；
In step S1100, is scanned by the first time of radar sensor, scanning information result is sent in clutter map
It is handled as new background；
In step S1200, scanning information result is sent to miscellaneous by the scanning new each time of tracing detection radar sensor
In wave figure, carry out continuing Overlapping display with first data；
In step S1300, the picture of stationary object in clutter map is obtained；
In step S1400, stationary object back wave is removed according to the picture of stationary object in clutter map；
In step S1500, clutter map is saved in the database, and is reused as base map.
Figure 18 is seen, specifically, extracting clutter map from new data in step S1501；
In step S1502, according to clutter map, static object is removed from Data processing.
In embodiment provided by the present invention, it should be understood that disclosed devices, systems, and methods can also lead to
Other modes are crossed to realize.Devices, systems, and methods embodiment described above is only schematical, for example, in attached drawing
Flow chart and block diagram show that the system of multiple embodiments according to the present invention, the possibility of method and computer program product are real
Existing architecture, function and operation.In this regard, each box in flowchart or block diagram can represent module, a journey
A part of sequence section or code, a part of the module, section or code include one or more for realizing defined
The executable instruction of logic function.It should also be noted that in some implementations as replacement, function marked in the box
It can also occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be substantially in parallel
It executes, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/
Or the combination of each box in flow chart and the box in block diagram and or flow chart, can with execute as defined in function or
The dedicated hardware based system of movement is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It can replace, can be realized wholly or partly by software, hardware, firmware or any combination thereof.When
When using software realization, can entirely or partly it realize in the form of a computer program product.The computer program product
Including one or more computer instructions.It is all or part of when loading on computers and executing the computer program instructions
Ground is generated according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, special purpose computer,
Computer network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or
Person is transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction
Wired (such as coaxial cable, optical fiber, digital subscriber can be passed through from a web-site, computer, server or data center
Line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or data
It is transmitted at center.The computer readable storage medium can be any usable medium that computer can access and either wrap
The data storage devices such as server, the data center integrated containing one or more usable mediums.The usable medium can be magnetic
Property medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc..
It should be noted that, in this document, term " including ", " including " or its any other variant are intended to non-row
Its property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and
And further include the other elements being not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including one ... ", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
The technical solution that the present invention is protected, it is not limited to above-described embodiment, it is noted that any one embodiment
The combination of technical solution in technical solution and other one or more embodiments, within the scope of the present invention.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (9)
1. a kind of detections of radar equipment persistently tracks correlating method to movement and static target, which is characterized in that the radar
Detection device to movement and static target persistently track correlating method the following steps are included:
Obtain the point mark information parameter of multiple mobile targets；
The point mark information that corresponding parameter difference is less than preset threshold is screened, similitude mark information is defined as；
According to a mark information parameter, similitude mark is merged；
According to speed, acceleration, the click information that detects of turning rate information judgement in mark information parameter be it is associated or
It is to be excluded；
Point mark information is associated at will acquire at least two；
According to one estimation range of associated mark information creating, the estimation range is that the prediction formed before mark should
Regional scope where next position that point mark occurs；
The lasting scanning that a mark is carried out in the estimation range of mark obtains.
2. a kind of detections of radar equipment according to claim 1 persistently tracks correlating method to movement and static target,
It is characterized in that, the point mark information parameter for obtaining multiple mobile targets, comprising:
Obtain multiple Targets Dots mobile track, direction, speed and signal strength or weakness information；
Classify to the track of acquisition, direction, speed, signal strength information.
3. a kind of target Continuous according to claim 2 tracks correlating method, which is characterized in that the corresponding parameter of the screening
Difference is less than the point mark information of preset threshold, is defined as similitude mark information, comprising:
Obtain the trace information of first mark and its neighbouring second point mark；
Judge whether first mark be consistent with the trace information of second point mark；
If the determination result is YES, continue the directional information of first mark of acquisition and second point mark；
Judge whether first mark be consistent with the directional information of second point mark；
If the determination result is YES, continue the velocity information of first mark of acquisition and second point mark；
Setting speed difference threshold, judges whether the difference of the velocity information of first mark and second point mark is less than the threshold of setting
Value；
If the determination result is YES, continue the signal strength information of first mark of acquisition and second point mark；
Setting signal strength difference threshold value, judges whether the difference of the signal strength of first mark and second point mark is less than setting
Threshold value；
If the determination result is YES, then it defines first mark and second point mark is similitude mark.
4. a kind of detections of radar equipment according to claim 1 persistently tracks correlating method to movement and static target,
It is characterized in that, the speed, acceleration according in mark information parameter, turning rate information judge the point mark information detected
It is to be associated or be excluded, comprising:
The minimum speed and maximum speed of normally travel vehicle are set, the minimum speed and maximum speed of normal walking pedestrian are set
Degree；
Set normally travel vehicle minimum acceleration sum peak acceleration, set normal walking pedestrian minimum acceleration and
Peak acceleration；
Set the minimum turning rate and maximum turning rate of normally travel vehicle；
Generate rate/turning rate value, the rate of the normal walking pedestrian/turning rate value of normally travel vehicle；
Obtain speed, acceleration, the turning rate in multiple mark informations parameter, judge a mark parameter rate/turning rate value,
Whether the value of acceleration matches with the vehicles or pedestrians respective value of normally travel；
If judging result is to match with the vehicle of normally travel, multiple mark information are subjected to the association of vehicle point mark, are excluded
Pedestrian's point mark information；
If judging result is to match with the pedestrian of normal walking, multiple mark information are subjected to the association of pedestrian's point mark, are excluded
Vehicle point mark information.
5. a kind of detections of radar equipment according to claim 4 persistently tracks correlating method to movement and static target,
It is characterized in that, when the speed and turning rate parameter of setting normally travel vehicle and pedestrian, the mobile target that tracks as needed
Type set matches numerical value.
6. a kind of detections of radar equipment according to claim 5 persistently tracks correlating method to movement and static target,
It is characterized in that, described according to one estimation range of associated mark information creating, the estimation range is to be formed before mark
One predict the mark occur next position where regional scope, wherein regional scope by speed, acceleration, turn
Curved rate is formed.
7. a kind of detections of radar equipment according to claim 1 persistently tracks correlating method to movement and static target,
It is characterized in that, the method also includes:
Judge whether mobile Targets Dots have non-continuous association；
If the determination result is YES, then inertia forecasting complement point is carried out to the point mark of disappearance；
The inertia forecasting complement point includes:
Obtain the moving direction information before Targets Dots disappear, velocity information, acceleration information；
The following several simulation points of Targets Dots are generated according to the moving direction information, velocity information, acceleration information of Targets Dots
Mark information；
The point mark information occurred again is obtained, is matched with simulation point mark information, judges the point mark information occurred again and mould
Whether quasi- point mark information is consistent；
If the determination result is YES, then confirm the point mark information lost before this mark information is, continue for tracking target.
8. a kind of detections of radar equipment according to claim 1 persistently tracks correlating method to movement and static target,
It is characterized in that, further including interference filtering, the interference filtering includes:
Newly-built clutter map；
It is scanned by the first time of radar sensor, scanning information result is sent in clutter map at as new background
Reason；
The scanning new each time of tracing detection radar sensor, scanning information result is sent in clutter map, with first data
It carries out continuing Overlapping display；
Obtain the picture of stationary object in clutter map；
Stationary object back wave is removed according to the picture of stationary object in clutter map；
Clutter map is saved in the database, and is reused as base map.
9. a kind of detections of radar equipment according to claim 8 persistently tracks correlating method to movement and static target,
It is characterized in that, when clutter map is reused as base map, comprising:
Clutter map is extracted from new data；
According to clutter map, static object is removed from Data processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811151782.3A CN109212514B (en) | 2018-09-29 | 2018-09-29 | Continuous tracking and associating method for moving and static targets by radar detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811151782.3A CN109212514B (en) | 2018-09-29 | 2018-09-29 | Continuous tracking and associating method for moving and static targets by radar detection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109212514A true CN109212514A (en) | 2019-01-15 |
| CN109212514B CN109212514B (en) | 2022-10-14 |
Family
ID=64982459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811151782.3A Active CN109212514B (en) | 2018-09-29 | 2018-09-29 | Continuous tracking and associating method for moving and static targets by radar detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109212514B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109782267A (en) * | 2019-01-25 | 2019-05-21 | 北京润科通用技术有限公司 | Data Association and trailer-mounted radar |
| CN110020642A (en) * | 2019-05-14 | 2019-07-16 | 江苏省气象服务中心 | A kind of visibility recognition methods based on vehicle detection |
| CN110412516A (en) * | 2019-08-20 | 2019-11-05 | 河北德冠隆电子科技有限公司 | Detection method and device of the millimetre-wave radar to stationary object and slow changing object |
| CN110426697A (en) * | 2019-07-05 | 2019-11-08 | 上海矽杰微电子有限公司 | A kind of radar target detection method and system |
| CN110930721A (en) * | 2019-12-03 | 2020-03-27 | 上海熹翼科技有限公司 | Road vehicle monitoring system and method based on soft handover radar |
| 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 |
| CN111091148A (en) * | 2019-12-10 | 2020-05-01 | 成都纳雷科技有限公司 | Vehicle-mounted radar target tracking method and device based on target prior information |
| CN111157008A (en) * | 2020-03-05 | 2020-05-15 | 齐鲁工业大学 | Local autonomous navigation system and method based on multidimensional environment information perception |
| CN111257864A (en) * | 2020-01-17 | 2020-06-09 | 河北德冠隆电子科技有限公司 | Active type detection vehicle continuous tracking breakpoint compensation device, system and method |
| CN111260808A (en) * | 2020-01-17 | 2020-06-09 | 河北德冠隆电子科技有限公司 | Free flow vehicle charging device, system and method based on multi-data fusion |
| CN111289967A (en) * | 2020-03-31 | 2020-06-16 | 四川长虹电器股份有限公司 | Personnel detection tracking and counting algorithm based on millimeter wave radar |
| CN111708021A (en) * | 2020-07-15 | 2020-09-25 | 四川长虹电器股份有限公司 | Personnel tracking and identifying algorithm based on millimeter wave radar |
| CN112305534A (en) * | 2019-07-26 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | Target detection method, device, equipment and storage medium |
| CN112356845A (en) * | 2020-11-19 | 2021-02-12 | 中国第一汽车股份有限公司 | Method, device and equipment for predicting motion state of target and vehicle |
| US20210241547A1 (en) * | 2016-11-15 | 2021-08-05 | At&T Mobility Ii Llc | Facilitation of smart communications hub to support driverless vehicles in 5g networks or other next generation networks |
| CN113495270A (en) * | 2020-04-07 | 2021-10-12 | 富士通株式会社 | Monitoring device and method based on microwave radar |
| CN113589254A (en) * | 2021-08-23 | 2021-11-02 | 东莞正扬电子机械有限公司 | Radar-based moving target detection method and device and radar detection equipment |
| CN114187328A (en) * | 2022-02-15 | 2022-03-15 | 智道网联科技(北京)有限公司 | Object detection method and device and electronic equipment |
| CN114417942A (en) * | 2022-03-28 | 2022-04-29 | 成都数之联科技股份有限公司 | Clutter recognition method, system, device and medium |
| CN114897944A (en) * | 2021-11-10 | 2022-08-12 | 北京中电兴发科技有限公司 | Multi-target continuous tracking method based on DeepSORT |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02238388A (en) * | 1989-03-13 | 1990-09-20 | Nec Corp | Tracking system of target |
| CN104793202A (en) * | 2014-01-16 | 2015-07-22 | 通用汽车环球科技运作有限责任公司 | Object fusion system of multiple radar imaging sensors |
| CN104991235A (en) * | 2015-06-15 | 2015-10-21 | 南京航空航天大学 | Method for rapid tracking target based on radar trace points |
| CN105116394A (en) * | 2015-06-29 | 2015-12-02 | 中国船舶重工集团公司第七二四研究所 | Object trace point extraction method based on multi-dimensional fine characteristic analysis |
| US9229102B1 (en) * | 2009-12-18 | 2016-01-05 | L-3 Communications Security And Detection Systems, Inc. | Detection of movable objects |
| CN105353368A (en) * | 2015-11-09 | 2016-02-24 | 中国船舶重工集团公司第七二四研究所 | Adaptive variable structure radar sea target tracking method based on policy decision |
| CN105487061A (en) * | 2015-12-01 | 2016-04-13 | 中国人民解放军海军航空工程学院 | Multi-characteristic information fusion method for target data correlation |
| CN106199583A (en) * | 2016-06-30 | 2016-12-07 | 大连楼兰科技股份有限公司 | Multi-target Data coupling and the method and system followed the tracks of |
-
2018
- 2018-09-29 CN CN201811151782.3A patent/CN109212514B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02238388A (en) * | 1989-03-13 | 1990-09-20 | Nec Corp | Tracking system of target |
| US9229102B1 (en) * | 2009-12-18 | 2016-01-05 | L-3 Communications Security And Detection Systems, Inc. | Detection of movable objects |
| CN104793202A (en) * | 2014-01-16 | 2015-07-22 | 通用汽车环球科技运作有限责任公司 | Object fusion system of multiple radar imaging sensors |
| CN104991235A (en) * | 2015-06-15 | 2015-10-21 | 南京航空航天大学 | Method for rapid tracking target based on radar trace points |
| CN105116394A (en) * | 2015-06-29 | 2015-12-02 | 中国船舶重工集团公司第七二四研究所 | Object trace point extraction method based on multi-dimensional fine characteristic analysis |
| CN105353368A (en) * | 2015-11-09 | 2016-02-24 | 中国船舶重工集团公司第七二四研究所 | Adaptive variable structure radar sea target tracking method based on policy decision |
| CN105487061A (en) * | 2015-12-01 | 2016-04-13 | 中国人民解放军海军航空工程学院 | Multi-characteristic information fusion method for target data correlation |
| CN106199583A (en) * | 2016-06-30 | 2016-12-07 | 大连楼兰科技股份有限公司 | Multi-target Data coupling and the method and system followed the tracks of |
Non-Patent Citations (1)
| Title |
|---|
| 戴麒麟: "雷达数据处理算法及实现技术研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑（月刊）》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11631286B2 (en) * | 2016-11-15 | 2023-04-18 | At&T Mobility Ii Llc | Facilitation of smart communications hub to support registering, monitoring, and managing a driverless vehicle |
| US20230215224A1 (en) * | 2016-11-15 | 2023-07-06 | At&T Mobility Ii Llc | Facilitation of smart communications hub to support driverless vehicles in 5g networks or other next generation networks |
| US20210241547A1 (en) * | 2016-11-15 | 2021-08-05 | At&T Mobility Ii Llc | Facilitation of smart communications hub to support driverless vehicles in 5g networks or other next generation networks |
| US11978288B2 (en) | 2016-11-15 | 2024-05-07 | At&T Mobility Ii Llc | Method, apparatus, and non-transitory machine-readable medium for activating public entity imaging device for observing vehicle status |
| CN109782267B (en) * | 2019-01-25 | 2021-01-22 | 北京润科通用技术有限公司 | Track correlation method and vehicle-mounted radar |
| CN109782267A (en) * | 2019-01-25 | 2019-05-21 | 北京润科通用技术有限公司 | Data Association and trailer-mounted radar |
| CN110020642A (en) * | 2019-05-14 | 2019-07-16 | 江苏省气象服务中心 | A kind of visibility recognition methods based on vehicle detection |
| CN110020642B (en) * | 2019-05-14 | 2023-03-24 | 江苏省气象服务中心 | Visibility identification method based on vehicle detection |
| CN110426697A (en) * | 2019-07-05 | 2019-11-08 | 上海矽杰微电子有限公司 | A kind of radar target detection method and system |
| CN112305534B (en) * | 2019-07-26 | 2024-03-19 | 杭州海康威视数字技术股份有限公司 | Target detection method, device, equipment and storage medium |
| CN112305534A (en) * | 2019-07-26 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | Target detection method, device, equipment and storage medium |
| CN110412516A (en) * | 2019-08-20 | 2019-11-05 | 河北德冠隆电子科技有限公司 | Detection method and device of the millimetre-wave radar to stationary object and slow changing object |
| CN110930692B (en) * | 2019-10-24 | 2021-06-18 | 河北德冠隆电子科技有限公司 | Active vehicle continuous tracking device, system and method |
| 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 |
| CN110930721A (en) * | 2019-12-03 | 2020-03-27 | 上海熹翼科技有限公司 | Road vehicle monitoring system and method based on soft handover radar |
| CN111091148A (en) * | 2019-12-10 | 2020-05-01 | 成都纳雷科技有限公司 | Vehicle-mounted radar target tracking method and device based on target prior information |
| CN111260808A (en) * | 2020-01-17 | 2020-06-09 | 河北德冠隆电子科技有限公司 | Free flow vehicle charging device, system and method based on multi-data fusion |
| CN111257864A (en) * | 2020-01-17 | 2020-06-09 | 河北德冠隆电子科技有限公司 | Active type detection vehicle continuous tracking breakpoint compensation device, system and method |
| CN111260808B (en) * | 2020-01-17 | 2021-12-10 | 河北德冠隆电子科技有限公司 | Free flow vehicle charging device, system and method based on multi-data fusion |
| CN111157008A (en) * | 2020-03-05 | 2020-05-15 | 齐鲁工业大学 | Local autonomous navigation system and method based on multidimensional environment information perception |
| CN111289967A (en) * | 2020-03-31 | 2020-06-16 | 四川长虹电器股份有限公司 | Personnel detection tracking and counting algorithm based on millimeter wave radar |
| CN113495270A (en) * | 2020-04-07 | 2021-10-12 | 富士通株式会社 | Monitoring device and method based on microwave radar |
| CN111708021B (en) * | 2020-07-15 | 2022-04-15 | 四川长虹电器股份有限公司 | Personnel tracking and identifying algorithm based on millimeter wave radar |
| CN111708021A (en) * | 2020-07-15 | 2020-09-25 | 四川长虹电器股份有限公司 | Personnel tracking and identifying algorithm based on millimeter wave radar |
| CN112356845A (en) * | 2020-11-19 | 2021-02-12 | 中国第一汽车股份有限公司 | Method, device and equipment for predicting motion state of target and vehicle |
| CN113589254A (en) * | 2021-08-23 | 2021-11-02 | 东莞正扬电子机械有限公司 | Radar-based moving target detection method and device and radar detection equipment |
| CN114897944A (en) * | 2021-11-10 | 2022-08-12 | 北京中电兴发科技有限公司 | Multi-target continuous tracking method based on DeepSORT |
| CN114897944B (en) * | 2021-11-10 | 2022-10-25 | 北京中电兴发科技有限公司 | Multi-target continuous tracking method based on DeepSORT |
| CN114187328A (en) * | 2022-02-15 | 2022-03-15 | 智道网联科技(北京)有限公司 | Object detection method and device and electronic equipment |
| CN114417942B (en) * | 2022-03-28 | 2022-06-07 | 成都数之联科技股份有限公司 | Clutter recognition method, system, device and medium |
| CN114417942A (en) * | 2022-03-28 | 2022-04-29 | 成都数之联科技股份有限公司 | Clutter recognition method, system, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109212514B (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109212514A (en) | A kind of detections of radar equipment persistently tracks correlating method to movement and static target | |
| CN109641589B (en) | Route planning for autonomous vehicles | |
| US10325490B2 (en) | Providing driving condition alerts using road attribute data | |
| CN108961790A (en) | Bad weather pre-warning management system and method based on four-dimensional outdoor scene traffic simulation | |
| US7209051B2 (en) | Intersection assistance system and method | |
| CN107424410B (en) | A kind of accident detection method calculated based on route travel time | |
| Ai et al. | Critical assessment of an enhanced traffic sign detection method using mobile LiDAR and INS technologies | |
| US11734880B2 (en) | Sensor calibration with environment map | |
| CN107924617A (en) | System and method for determining navigation information for autonomous vehicle | |
| Goyat et al. | Vehicle trajectories evaluation by static video sensors | |
| US11914041B2 (en) | Detection device and detection system | |
| CN108242168A (en) | A kind of method and device for monitoring vehicle traveling | |
| US20210208282A1 (en) | Detection device and detection system | |
| CN108458746A (en) | One kind being based on sensor method for self-adaption amalgamation | |
| CN110428604A (en) | It is a kind of based on the taxi illegal parking of GPS track data and map datum monitoring and method for early warning | |
| EP4016115A1 (en) | Vehicle localization based on radar detections | |
| Wu et al. | A novel skateboarder-related near-crash identification method with roadside LiDAR data | |
| US20220234588A1 (en) | Data Recording for Advanced Driving Assistance System Testing and Validation | |
| CN117192513A (en) | Road side laser radar background filtering method in snowy environment | |
| WO2022007143A1 (en) | Roadside internet of vehicles device, flyover road segment identification method, and vehicle-mounted internet of vehicles device | |
| CN116142178A (en) | Vehicle auxiliary driving method, system, medium and electronic equipment | |
| CN112415518B (en) | Passable space detection method based on vehicle-mounted millimeter wave radar | |
| US11468593B2 (en) | Method and system for creating ground control point within spatial area | |
| Wu | Data processing algorithms and applications of LiDAR-enhanced connected infrastructure sensing | |
| Dorrazehi et al. | A Warning System Design for Camel-Vehicle Collisions Mitigation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |