CN109212514B - Continuous tracking and associating method for moving and static targets by radar detection equipment - Google Patents
Continuous tracking and associating method for moving and static targets by radar detection equipment Download PDFInfo
- Publication number
- CN109212514B CN109212514B CN201811151782.3A CN201811151782A CN109212514B CN 109212514 B CN109212514 B CN 109212514B CN 201811151782 A CN201811151782 A CN 201811151782A CN 109212514 B CN109212514 B CN 109212514B
- Authority
- CN
- China
- Prior art keywords
- trace
- information
- trace point
- speed
- point
- 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
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a continuous tracking and associating method for a moving target and a static target by radar detection equipment, which comprises the following steps: acquiring trace point information parameters of a plurality of moving targets; screening trace point information corresponding to the parameter difference value smaller than a preset threshold value, and defining the trace point information as similar trace point information; fusing similar traces according to the trace information parameters; judging whether the detected click information is associated or excluded according to the speed, acceleration and turning rate information in the click information parameters; associating the acquired trace point information at least two positions; creating a prediction area according to the associated trace point information, wherein the prediction area is an area range where the next position where the trace point appears is predicted and is formed before the trace point; and continuously scanning and acquiring the trace points in the predicted region of the trace points. The invention accurately identifies the trace point information corresponding to the moving target by the methods of trace point fusion, trace point association and the like, thereby reducing the processing amount of system data.
Description
Technical Field
The invention relates to the technical field of traffic monitoring and high-frequency radar large-scale target tracking, in particular to a continuous tracking association method for moving and static targets by radar detection equipment.
Background
With the rapid development of the expressway in China, the hardware equipment and software level of the road monitoring system are continuously updated with the improvement of the technological development level. The highway monitoring system mainly generates a control scheme according to a series of intelligent control rules and strategies by detecting the traffic flow, monitoring the traffic condition, detecting environmental weather and monitoring the running condition of the whole highway, thereby realizing the control of the traffic flow, improving the traffic environment, reducing accidents and enabling the highway to reach higher service level.
The video traffic incident automatic detection system uses high-definition video images of a fixed camera and an external field remote control camera along a road or in a tunnel as input, adopts a vehicle tracking technology and a background image automatic updating technology, selects target information from the change of an image sequence for calculation processing, analyzes the moving track of a vehicle, and generates incident alarm according to an image processing algorithm. Through the processing and analysis of the video images, various traffic events and accidents such as fire disasters, pedestrians, vehicle stopping, traffic jam, vehicle retrograde motion, vehicle throwing debris, low visibility detection and the like can be automatically detected in the coverage range of the images, and the system can rapidly and automatically alarm and record in real time, so that great help is provided for traffic safety management and road operation of roads.
The fusion application of the high-definition video monitoring system and the video event detection system in the prior stage promotes the road monitoring system to take a big step towards the direction of automation and humanization, vehicles, dangerous events, pedestrians and objects thrown away, which run on the road and in the tunnel, can be actively and quickly detected and early warned through the video detection and analysis equipment at the rear end, the safety management level of the expressway is greatly improved, the occurrence of various unsafe hidden dangers is reduced, the driving environment of passerby is safer, various accidents are continuously reduced, and the economic loss is greatly reduced.
In the expressway monitoring system, although full-element detection equipment or multi-element detection equipment is installed on two sides of a road as required, professional meteorological detection equipment is very expensive, so that the meteorological detection equipment is still expensive and cannot be widely used, and even a plurality of functions are not utilized, so that great waste is caused. The professional weather stations are all arranged at fixed positions and cannot move randomly, the acquired data can only be single-point weather data and not continuous area or large-range accurate data, although local weather conditions of several days or the current day in the future can be acquired through weather stations, the conditions that the weather conditions are rainy and sunny in the side and are often in the same city or uniform area are often generated, the arrangement interval distance between the highway multi-element detection devices is more than 20 kilometers, and even a longer distance can be used for arranging one set of equipment, so that the actual road weather conditions cannot be truly and accurately reflected. This situation may even have a great impact on road operation managers and other important institutions or departments, and even cause unnecessary economic loss or life risks. For example, in winter, an expressway or an urban main traffic road may cause road icing after raining and snowing, and the road icing is not fixed, so that a more effective method can be adopted to avoid various disasters only by effectively detecting the icing condition and the weather condition of the whole road to obtain real and effective data. The fixed-point weather detection device can also be used in haze weather, rain weather, snow weather or fog weather, and the fixed-point weather detection device can be helpless under the condition. Although the smoke sensors are also arranged in the tunnel, the smoke sensors are arranged at fixed points, the harmful gas detection and the environment detection in the tunnel adopt fixed point detection, the quantity is small, the data of a certain node and/or a section can be reflected on one surface, the accurate data in a continuous area and a large range cannot be represented, particularly, once a traffic accident happens in the tunnel, the data is more important, the effective data which is obtained at an early point, accurate and reliable in continuity provides technical support for critical warning and life saving, and the method is very important for a traffic manager.
In the prior art, when target tracking is performed, if radar tracking is adopted, a trace point is formed on a tracked target, the trace point refers to a data signal of a certain position of a moving target obtained after data processing is performed on a radar in a scanning process, and the trace point is a data unit which is the most basic for realizing tracking. But may be "sampled" multiple times if a target object is too large or too long, or even due to its physical appearance. For example, in the case of sampling a large truck, after processing the radar data, we may have 2 or more traces of points that represent only one object, due to the shape of the object, the surface, and the 360 ° scanning of the radar! If the information such as the running track, the direction, the speed, the signal strength and the like of the target spot is matched with the pedestrian information, the three spots can be taken as pedestrians or other types of objects for tracking and identifying, and the detection alarm for the vehicle can never be obtained.
Disclosure of Invention
The embodiment of the invention aims to provide a continuous tracking and associating method of a radar detection device for moving and static targets, which is used for solving the problems that the existing traffic information or radar interference is large, the target identification and tracking are not accurate in the radar identification process, and the same target or a large number of targets cannot be simultaneously, continuously and accurately tracked and positioned.
In order to achieve the purpose, the technical scheme of the embodiment of the invention is that
A continuous tracking association method for a moving target and a static target by a radar detection device comprises the following steps:
acquiring trace point information parameters of a plurality of moving targets;
screening trace point information corresponding to the parameter difference value smaller than a preset threshold value, and defining the trace point information as similar trace point information;
fusing similar traces according to the trace information parameters;
judging whether the detected click information is associated or excluded according to the speed, acceleration and turning rate information in the click information parameters;
associating the acquired trace point information at least two positions;
creating a prediction area according to the associated trace point information, wherein the prediction area is an area range where the next position where the trace point appears is predicted and is formed before the trace point;
and continuously scanning and acquiring the trace points in the predicted region of the trace points.
As a preferred aspect of the present invention, the acquiring trace point information parameters of a plurality of moving targets includes:
acquiring the moving track, direction, speed and signal strength information of a plurality of target point tracks;
and classifying the acquired track, direction, speed and signal strength information.
As a preferred scheme of the present invention, the screening of trace point information corresponding to a parameter difference smaller than a preset threshold is defined as similar trace point information, and includes:
acquiring track information of a first trace point and a second trace point nearby the first trace point;
judging whether the track information of the first trace and the second trace is consistent;
if the judgment result is yes, continuously acquiring the direction information of the first trace point and the second trace point;
judging whether the direction information of the first trace and the second trace is consistent;
if the judgment result is yes, continuously acquiring the speed information of the first trace and the second trace;
setting a speed difference threshold value, and judging whether the difference value of the speed information of the first trace and the second trace is smaller than the set threshold value or not;
if the judgment result is yes, continuously acquiring the signal intensity information of the first trace and the second trace;
setting a signal intensity difference threshold, and judging whether the difference value of the signal intensities of the first trace and the second trace is smaller than the set threshold or not;
if the judgment result is yes, the first trace point and the second trace point are defined as similar trace points.
As a preferable aspect of the present invention, the determining whether the detected trace point information is associated or excluded according to the speed, acceleration, and turning rate information in the trace point information parameter includes:
setting the minimum speed and the maximum speed of a vehicle which normally runs, and setting the minimum speed and the maximum speed of a pedestrian which normally runs;
setting the minimum acceleration and the maximum acceleration of a vehicle which normally runs, and setting the minimum acceleration and the maximum acceleration of a pedestrian who normally walks;
setting a minimum turning rate and a maximum turning rate of a vehicle which normally runs;
generating a value of a speed/turning rate of a normal-running vehicle, a value of a speed/turning rate of a normal-running pedestrian;
acquiring speed, acceleration and turning rate in the multiple trace information parameters, and judging whether the speed/turning rate value and the acceleration value of the trace information parameters are matched with corresponding values of normally-running vehicles or pedestrians or not;
if the judgment result is that the vehicle is matched with a normally running vehicle, performing vehicle point correlation on the multiple point information, and excluding pedestrian point information;
and if the judgment result is that the pedestrian is matched with the pedestrian walking normally, carrying out pedestrian trace point association on the multiple trace information, and excluding the vehicle trace point information.
As a preferable aspect of the present invention, when the speed and the turning rate parameters of the normal running vehicle and the pedestrian are set, the matching numerical value is set according to the type of the moving object to be tracked.
As a preferable aspect of the present invention, a prediction region is created according to the associated trace point information, and the prediction region is a region range where a next position where the trace point appears is predicted, where the region range is formed before the trace point, and the region range is formed by a speed, an acceleration, and a turning rate.
As a preferred aspect of the present invention, the method further comprises:
judging whether the moving target point trace has non-continuous correlation;
if the judgment result is yes, performing inertial prediction point compensation on the disappeared trace points;
the inertial prediction supplementary point comprises:
acquiring moving direction information, speed information and acceleration information before a target point trace disappears;
generating a plurality of future simulation trace point information of the target trace point according to the moving direction information, the speed information and the acceleration information of the target trace point;
acquiring recurrent tracing information, matching the recurrent tracing information with the simulated tracing information, and judging whether the recurrent tracing information is consistent with the simulated tracing information or not;
if the judgment result is yes, the trace point information is confirmed to be the trace point information lost before, and the target is continuously tracked.
As a preferable aspect of the present invention, the present invention further includes interference filtering, where the interference filtering includes:
newly building a clutter map;
sending a scanning information result to a clutter map as a new background for processing through the first scanning of the radar sensor;
tracking and detecting each new scanning of the radar sensor, sending a scanning information result to a clutter map, and continuously overlapping and displaying the result with previous data;
acquiring a picture of a static object in the clutter map;
clearing reflected waves of the static object according to the picture of the static object in the clutter map;
and storing the clutter maps in a database, and reusing the clutter maps as base maps.
In a preferred embodiment of the present invention, when the clutter map is reused as a base map, the method includes:
extracting a clutter map from the new data;
stationary objects are removed from the data processing based on the clutter maps.
The embodiment of the invention has the following advantages:
the embodiment of the invention utilizes radar scanning to continuously track a large amount of moving target motion tracks without causing messy target tracking errors, accurately identifies the point trace information corresponding to the moving target by the methods of point trace fusion, point trace association and the like for targets which may scan a plurality of point traces on the same target object to different parts, and simultaneously filters the interference of a static object through a clutter map to obtain more accurate point trace information.
Drawings
FIG. 1 is a flow chart of a target continuous tracking process in an embodiment of the invention.
Fig. 2 is a schematic diagram of a trace point acquisition of a radar detection device for a truck.
Fig. 3 is a schematic diagram of trace point extraction for a truck by a radar detection device.
Fig. 4 is a schematic diagram of spot-trace fusion of a radar detection device for a truck.
FIG. 5 is a flow chart of a method according to an embodiment of the present invention.
FIG. 6 is a schematic flow chart of a method according to another embodiment of the present invention.
Fig. 7 is a schematic flow chart of a method according to another embodiment of the present invention.
FIG. 8 is a schematic diagram of a radar detection device acquiring trace occlusions.
FIG. 9 is a flow chart of a method according to an embodiment of the present invention.
FIG. 10 is a schematic diagram of a trace point range prediction formed by turning rate and speed.
Fig. 11 is a schematic diagram of trace loss.
FIG. 12 is a schematic diagram illustrating automatic replenishment of inertia prediction sites according to an embodiment of the present invention.
FIG. 13 is a schematic flow chart of a method according to another embodiment of the present invention.
FIG. 14 is a schematic flow chart of a method according to another embodiment of the present invention.
FIG. 15 is a schematic diagram of radar detection clutter.
FIG. 16 is a schematic method flow diagram of another embodiment of the present invention.
FIG. 17 is a schematic flow chart of a method according to another embodiment of the present invention.
FIG. 18 is a schematic flow chart of a method according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The embodiment of the invention adopts a multi-element omnibearing tracking monitoring radar sensor to track the point trace, the radar adopts a high-frequency transmitting unit with a main frequency of 77GHZ, a signal receiving unit, a 360-degree scanning unit, a data processing unit, a communication unit, a power supply management unit and the like, and a core data processing unit adopts a multi-thread high-speed processor and can simultaneously track, position and detect no less than 1000 target objects in a detection area. The radar detector can use a 360-degree high-speed scanning mode to continuously track and position a target object in a whole area with the radius of 500 m and take a radar as a center, equipment can send a group of data to the outside at a time interval of 50-250 milliseconds, in addition, the radar sends the acquired original data to a data analysis processor, and important information such as the instant speed, the moving direction, the longitude and latitude, the target size, the ID number, the direction angle, the lane where the vehicle or the pedestrian and the animal are located can be provided after the system is integrally analyzed and processed. For vehicle type information extraction of a vehicle, the system can acquire the approximate shape of the vehicle and the vehicle type by setting a virtual coil. The radar sensor adopts an integrated design and integrates an 800-kilo-pixel high-speed spherical monitoring camera and a multi-element meteorological detection sensor (capable of detecting and outputting temperature and humidity data, illumination light intensity data, wind direction and wind speed data, rainfall data, sulfur dioxide, carbon monoxide, methane, formaldehyde, natural gas, liquefied gas and other harmful gas data), and the equipment main body adopts an IP67 safety protection level for ensuring the service life of a radar. In order to effectively reduce the power consumption of equipment, all parts of the radar are selected and low-power-consumption designs and devices are adopted. The RJ 45/100/1000M adaptive network interface network cable connection mode is adopted, and POE power supply can be supported.
Fig. 1 is a flowchart of a target continuous tracking process according to an embodiment of the present invention. When continuously tracking and associating moving and static targets, the method needs to be executed by the following steps of trace point extraction, trace point fusion, trace point association (speed, acceleration and turning rate), automatic compensation of inertia rule target loss and point number information output of continuously tracked targets.
Referring to fig. 2-4, the cart is continuously tracked in a practical application, but there are the shape of the cart, the reason for the surface, and the reason for the 360 ° scan of the radar, and after the radar data is processed, there may be 2 or more traces that are only representative of the target of the cart. The multiple traces are regarded as multiple target objects in the graph to be continuously tracked, if information such as the driving track, direction, speed, signal strength and the like of the target trace is matched with pedestrian information, the multiple trace information can be mistaken for the pedestrian information to be tracked and identified, and finally detection and alarm of the vehicle cannot be obtained.
Referring to fig. 5, the radar detection device continuously tracks and associates a moving target and a stationary target disclosed in this embodiment, which is implemented by applying a multi-element omni-directional tracking and monitoring radar sensor and a server.
Specifically, in step S100, trace information parameters of a plurality of moving targets are acquired.
Referring to fig. 6, in step S101, the trajectory, direction, speed and signal strength information of the movement of a plurality of target point traces are obtained;
in step S102, the acquired trajectory, direction, speed, signal strength information is classified.
And the acquired target trace movement information is arranged and then used as the basis for subsequent trace point fusion and trace point association.
In step S200, trace point information corresponding to the parameter difference smaller than the preset threshold is filtered and defined as similar trace point information.
Specifically, in step 201, track information of a first trace and a second trace nearby the first trace is obtained, see fig. 7;
in step 202, judging whether the track information of the first trace and the second trace is consistent;
in step 203, if the determination result is yes, continuously acquiring the direction information of the first trace and the second trace;
in step 204, judging whether the direction information of the first trace and the second trace is consistent;
in step 205, if the determination result is yes, the speed information of the first trace point and the second trace point is continuously obtained;
in step 206, a speed difference threshold is set, and whether the difference between the speed information of the first trace and the speed information of the second trace is smaller than the set threshold is judged;
in step 207, if the determination result is yes, continuing to acquire the signal strength information of the first trace and the second trace;
in step 208, a signal strength difference threshold is set, and it is determined whether the difference between the signal strengths of the first trace and the second trace is smaller than the set threshold;
in step 209, if the determination result is yes, the first trace point and the second trace point are defined as similar trace points.
In step S300, similar traces are fused according to the trace information parameters. The point trace fusion is to effectively combine the point traces of the tracking targets with very close distance, motion direction, motion speed and turning rate, so as to prevent the error phenomenon that a plurality of target point traces are scanned due to the fact that the same target object is scanned to different parts, and mainly comprises the following steps: the combined range, the combined azimuth angle and the combined trace points are defined (circled) into an entity, and the size, the number of pixels and the like of the entity are new, so that the reliability of automatic tracking and event classification information is higher.
After the point trace is extracted, the point trace is associated next, if the point trace is not associated, the obtained radar data and the target objects corresponding to the point trace to the bottom cannot be judged, and the same object cannot be continuously tracked, so that the same moving object can be continuously tracked through a point trace association technology, continuous point trace information can be obtained, and effective continuous point trace information is the basis for judging the state of the moving target object.
Referring to fig. 8, the automatic tracking of the system is a continuous judgment of the same target motion, the accuracy of the automatic tracking directly determines the key of the system for realizing the functions of detecting the abnormal event accident and acquiring the traffic data, and the inaccuracy of the automatic tracking, even the low stability, can cause the defects of the whole system, such as low detection precision, high false alarm, more missed reports, poor data acquisition precision, low system stability and the like, so that it is very important for the system to have a set of stable and reliable automatic tracking algorithm and an implementation mechanism. However, in actual traffic, the conditions that can be continuously tracked and detected by radar are rare, and undesirable conditions such as: vehicle occlusion (large car occlusion with small car), obstacle occlusion, etc., sometimes even the tracked target object is continuously occluded. The tracked vehicle is lost in the system and cannot be effectively identified and tracked, and further, any abnormal condition of the target cannot be timely alarmed and correct traffic data cannot be acquired.
In step S400, it is determined whether the detected click information is associated or excluded according to the speed, acceleration, and turning rate information in the click information parameter.
Where for speed we cannot set the speed setting to 50 km/h if the point-trace correlation is detected only for pedestrians, and 3 km/h if for normally driving vehicles, as this is not really true. Therefore, a suitable and accurate target is selected for detection.
For acceleration, acceleration is defined as the degree to which a target acceleration or deceleration is determined.
For the turning rate, the turning rate is defined as the degree to which the target changes the direction of the motion.
The detected trace information can be effectively judged to be associated or excluded by setting three data.
Referring to fig. 9, in step S401, a minimum speed and a maximum speed of a normal traveling vehicle are set, and a minimum speed and a maximum speed of a normal traveling pedestrian are set;
in step S402, a minimum acceleration and a maximum acceleration of the normal travel vehicle are set, and a minimum acceleration and a maximum acceleration of the normal walking pedestrian are set;
in step S403, a minimum turning rate and a maximum turning rate of the normal running vehicle are set;
in step S404, a value of the speed/turning rate of the normal-travel vehicle, a value of the speed/turning rate of the normal-travel pedestrian are generated;
the higher the set speed/turn rate value is, the easier it is to correlate the appearing targets, but may correlate the unrelated targets, leading to triggering false alarms;
the lower the set speed/turn rate value, the less inaccurate association, the possibility of associating related objects, and the inability to form a track.
Referring to fig. 10, when setting the speed and turning rate parameters of the normal-running vehicle and the pedestrian, matching values are set according to the type of the moving object to be tracked. Because the following conclusions can be drawn according to the normal motion state of the automobile, the pedestrian and the throwing object:
under the condition of not causing the loss of automatic tracking, the smaller the value of the speed/turning rate is, the better the value is, and the specific setting is carried out according to the actual condition;
the speed of the pedestrian is very slow (< 10 m/s), but the direction of the pedestrian is very fast;
the vehicle changes direction slower (but the vehicle is traveling faster);
if both the vehicle and the pedestrian are to be tracked, a compromise in the values of speed/turning rate needs to be set.
In step S405, acquiring the speed, the acceleration and the turning rate of a plurality of trace information parameters, and judging whether the speed/turning rate value and the acceleration value of the trace information parameters are matched with the corresponding values of the normally running vehicle or pedestrian;
in step S406, if the determination result is that the vehicle is matched with a vehicle that normally travels, performing vehicle track-marking association on the plurality of track information to exclude pedestrian track-marking information;
in step S407, if the determination result is that the vehicle matches a pedestrian walking normally, the pedestrian trace point association is performed on the plurality of trace point information, and the vehicle trace point information is excluded.
In step S500, the acquired at least two trace information points are associated. Since only one piece of trace information cannot be judged, a prediction area can be created by the above three parameters. The prediction area is an area range where a next position where the trace point appears is predicted, wherein the next position is formed before the trace point, and the area range is formed by speed, acceleration and turning rate.
In step S600, a prediction area is created according to the associated trace point information, where the prediction area is an area range where a next position where the trace point appears is predicted, and the prediction area is formed before the trace point.
In step S700, continuous scanning acquisition of the trace points is performed within the predicted region of the trace points.
In practical application, due to the occlusion of a running vehicle or an obstacle or other reasons, a detected target is likely to disappear, so that continuous point track association cannot be formed, and effective automatic tracking cannot be formed. As shown in fig. 11, the blank point is point location information of the trace of the target object, and based on the inertial phenomenon and principle of the motion of the object, although the trace of the object is sometimes lost, the position of the trace of the object can be successfully predicted by using the inertial principle, and when the trace of the object appears again, the trace can be kept, and this process is called tracking inertial prediction. Although some trace point information is lost, 1, 2 or even more pieces of ' simulated ' trace point information can be obtained in the future of the target after calculation by the computer inertial model, when the trace point is detected again as true ' and the obtained trace point information is consistent with the simulated trace point information, the trace point can be determined to be the previously lost trace point, the same target can be continuously tracked, and the result of automatic filling of the automatically lost trace point realized by the inertial trace point prediction and point filling technology is shown in fig. 12.
Referring to FIG. 13, in one embodiment of the present invention, the inertial prediction fix technique is as follows:
in step S800, it is determined whether the moving target point trace has a non-continuous association;
in step S900, if the determination result is yes, performing inertial prediction to compensate the missing trace point;
referring to fig. 14, the complementary points of the inertial prediction include:
in step S901, movement direction information, velocity information, and acceleration information before the target point trace disappears are acquired;
in step S902, generating a plurality of future simulated trace point information of the target trace point according to the moving direction information, the speed information and the acceleration information of the target trace point;
in step S903, re-appearing trace information is acquired, matched with the simulated trace information, and whether the re-appearing trace information is consistent with the simulated trace information is determined;
in step S904, if the determination result is yes, it is determined that the trace information is the trace information lost before, and the target continues to be tracked.
It should be noted that the technology for automatically filling the inertia prediction point location is false point location information which is simulated according to the previous motion rule and motion state when the target point location information is lost, and the information is not real point location information and is dummy point location information. Therefore, the trace information is not excessive, which may result in a decrease in system accuracy and may result in erroneous tracking and erroneous alarm information. The method is expressed by a model, wherein Z is real trace point information, X is trace point information of inertia simulation, the fact that the larger the Z value is equivalent to the larger the detection information of a real target is, but a longer distance is needed to acquire tracking, the larger the X value is, the lower the detection precision and reliability of the system is, the Z value is generally set to be 5,X value to be 2 according to empirical values, namely five pieces of trace point information which are continuously tracked allow 2 trace points to disappear.
When the conditions are met, an effective automatic tracking model is established, the same target can be continuously tracked, and the subsequent data interface can process, analyze, judge and calculate the continuous trace point information to detect and alarm the abnormal event accident of the target object represented by the trace point, acquire traffic data, analyze the trace and track and check the target object by a camera.
The clutter map is an adaptive processing method in the time domain. The method is mainly used for recording clutter distribution and intensity change of the surrounding environment of the radar array in real time. The method is based on processing multiple sweep values of the same space unit to estimate the average amplitude of clutter of the unit, thereby providing layered information of the surrounding environment of a radar array. Referring to fig. 15, the clutter map records and identifies static objects within the operating range of the radar sensor. The clutter map is used as a reference point for the radar sensor and tracking thereof, which is helpful for focusing on a moving object more, and is a basis for further effectively filtering interference. After the initial installation of the system is completed, a clutter map needs to be newly established for each radar sensor, and in the actual operation process, the clutter map of each radar device is preferably continuously updated so as to filter out a fixed and unchangeable interference source in the background and update a temporarily moving object into the clutter map. In addition, unnecessary processing loss can be reduced by utilizing the clutter map, and the detection capability of the target, especially a small target with low speed (less than 5 km/h) is improved. There are also objects such as lawns, trees, road signs, etc. that will also give a powerful signal, and for this case a real-time clutter map is needed to limit the occurrence of this. Clutter maps are background noise for stationary objects. The clutter map works as follows: the clutter map is updated once for each new scan of the multi-element omni-directional tracking detection radar sensor. The data information obtained by the system is sent to the clutter maps to be processed as a completely new background, and the update frequency of the clutter maps is changed through parameter setting. Once the first clutter map is built up, each new scan clutter map data is then continuously superimposed with the first clutter map data, the more new data the first clutter map absorbs, the less data that needs to be analysed later into tracks. It is important that the system processes the data to remove reflections from stationary objects that are reflected in the clutter map. Once the clutter map is built, we see a picture of a stationary object, the clutter map can be saved in a database and reused as background (floor) data. The processed data is compared with the clutter map base map to prevent the clutter map data in the shadow from being processed.
Each time a clutter map is extracted from the new data, stationary objects can be eliminated from the data processing, i.e. no analysis of the data of the clutter map is required, thereby reducing the throughput of the system data.
Fig. 16 is a flow chart of system interference filtering. The radar detection is provided with a detection and alarm core module, after acquiring set rule data information/control instructions sent by a server, the radar detection adjusts the signal intensity of a target according to corresponding information, judges whether the target is in a detection area, if so, further judges whether the target is detecting in a lane, establishes an initial track and calls an algorithm model, including an intuitive algorithm model, a logic algorithm model and a correction algorithm model, judges whether the motion direction/motion included angle of the tracked target is in an allowed range, if so, establishes a base number capable of meeting the continuous tracking identification of the target, generates a clutter map, filters the interference of a background (map) fixed target, further filters other irregular signal interference, and filters the interference of external electromagnetic signals.
Referring to fig. 17, in one embodiment of the invention, interference filtering is as follows:
in step S1000, a clutter map is newly created;
in step S1100, the scanning information result is sent to the clutter map as a new background for processing through the first scanning of the radar sensor;
in step S1200, each new scan of the radar sensor is tracked and detected, and the scan information result is sent to the clutter map and is continuously displayed in an overlapping manner with the previous data;
in step S1300, a picture of a stationary object in the clutter map is acquired;
in step S1400, removing the reflected wave of the stationary object according to the picture of the stationary object in the clutter map;
in step S1500, the clutter map is saved in a database and reused as a base map.
Referring to fig. 18, in detail, in step S1501, a clutter map is extracted from the new data;
in step S1502, stationary objects are removed from the data processing based on the clutter map.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, system, and method may be implemented in other ways. The apparatus, system, and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
Alternatively, all or part of the implementation may be in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The technical solutions protected by the present invention are not limited to the above embodiments, and it should be noted that the combination of the technical solution of any embodiment and the technical solution of one or more other embodiments is within the protection scope of the present invention.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (7)
1. A continuous tracking and associating method for a moving target and a static target by a radar detection device is characterized by comprising the following steps:
acquiring trace point information parameters of a plurality of moving targets;
screening trace point information corresponding to the parameter difference value smaller than a preset threshold value, and defining the trace point information as similar trace point information;
fusing similar traces according to the trace point information parameters;
judging whether the detected trace point information is associated or excluded according to the speed, acceleration and turning rate information in the trace point information parameters;
associating the acquired trace point information at least two positions;
creating a prediction area according to the associated trace point information, wherein the prediction area is an area range where the next position where the trace point appears is predicted and is formed before the trace point;
continuously scanning and acquiring the trace points in the predicted region of the trace points;
the acquiring of the trace point information parameters of a plurality of moving targets includes:
acquiring the moving track, direction, speed and signal strength information of a plurality of target point tracks;
classifying the acquired track, direction, speed and signal intensity information;
the screening of the trace point information with the corresponding parameter difference value smaller than the preset threshold value is defined as similar trace point information, and comprises the following steps:
acquiring track information of a first trace and a second trace nearby the first trace;
judging whether the track information of the first trace and the second trace is consistent;
if the judgment result is yes, continuously acquiring the direction information of the first trace and the second trace;
judging whether the direction information of the first trace and the second trace is consistent;
if the judgment result is yes, continuously acquiring the speed information of the first trace point and the second trace point;
setting a speed difference threshold value, and judging whether the difference value of the speed information of the first trace and the second trace is smaller than the set threshold value or not;
if the judgment result is yes, continuously acquiring the signal intensity information of the first trace and the second trace;
setting a signal intensity difference threshold, and judging whether the difference of the signal intensities of the first trace and the second trace is smaller than the set threshold or not;
and if so, defining the first trace point and the second trace point as similar trace points.
2. The radar detection device continuous tracking and associating method for the moving and static targets according to claim 1, wherein the judgment of whether the detected trace point information is associated or excluded according to the speed, acceleration and turning rate information in the trace point information parameters comprises:
setting the minimum speed and the maximum speed of a vehicle which normally runs, and setting the minimum speed and the maximum speed of a pedestrian which normally runs;
setting the minimum acceleration and the maximum acceleration of a vehicle which normally runs, and setting the minimum acceleration and the maximum acceleration of a pedestrian who normally walks;
setting a minimum turning rate and a maximum turning rate of a vehicle which normally runs;
generating a value of a speed/turning rate of a normal-running vehicle, a value of a speed/turning rate of a normal-running pedestrian;
acquiring speed, acceleration and turning rate in the multiple trace information parameters, and judging whether the speed/turning rate value and the acceleration value of the trace information parameters are matched with corresponding values of normally running vehicles or pedestrians;
if the judgment result is that the vehicle is matched with a normally running vehicle, performing vehicle point correlation on the multiple point information, and excluding pedestrian point information;
and if the judgment result is that the pedestrian is matched with the pedestrian walking normally, carrying out pedestrian trace point association on the multiple trace information, and excluding the vehicle trace point information.
3. The radar detection device continuous tracking correlation method for the moving and static targets according to claim 2, characterized in that when setting the speed and turning rate parameters of normal running vehicles and pedestrians, the matching value is set according to the type of the moving target to be tracked.
4. The correlation method for the continuous tracking of the moving and static targets by the radar detection equipment as claimed in claim 3, wherein a prediction area is created according to the correlated trace point information, the prediction area is an area range where a next position where the trace point appears is predicted, the area range is formed before the trace point, and the area range is formed by speed, acceleration and turning rate.
5. The radar detection device correlation method for continuous tracking of moving and stationary targets according to claim 1, further comprising:
judging whether the moving target point trace has non-continuous correlation;
if the judgment result is yes, performing inertial prediction point compensation on the disappeared trace points;
the inertial prediction supplementary points include:
acquiring moving direction information, speed information and acceleration information before a target point trace disappears;
generating a plurality of future simulation trace point information of the target trace point according to the moving direction information, the speed information and the acceleration information of the target trace point;
acquiring recurrent tracing information, matching the recurrent tracing information with the simulated tracing information, and judging whether the recurrent tracing information is consistent with the simulated tracing information or not;
if the judgment result is yes, the trace point information is confirmed to be the trace point information lost before, and the target is continuously tracked.
6. The association method for continuous tracking of moving and static targets by radar detection equipment according to claim 1, further comprising interference filtering, wherein the interference filtering comprises:
newly building a clutter map;
sending a scanning information result to a clutter map as a new background for processing through the first scanning of the radar sensor;
tracking and detecting each new scanning of the radar sensor, sending a scanning information result to a clutter map, and continuously overlapping and displaying the result with previous data;
acquiring a picture of a static object in the clutter map;
clearing reflected waves of the static object according to the picture of the static object in the clutter map;
and storing the clutter maps in a database, and reusing the clutter maps as base maps.
7. The radar detection device correlation method for continuous tracking of moving and static targets according to claim 6, wherein when the clutter map is repeatedly used as a base map, the method comprises the following steps:
extracting a clutter map from the new data;
stationary objects are removed from the data processing based on the clutter maps.
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 CN109212514A (en) | 2019-01-15 |
| CN109212514B true 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) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10726640B2 (en) * | 2016-11-15 | 2020-07-28 | At&T Mobility Ii Llc | Facilitation of smart communications hub to support driverless vehicles in 5G networks or other next generation networks |
| 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 |
| 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 |
| CN110412516B (en) * | 2019-08-20 | 2021-05-07 | 河北德冠隆电子科技有限公司 | Method and device for detecting stationary object and slowly-changing object by millimeter wave radar |
| 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 |
| 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 |
| CN111091148B (en) * | 2019-12-10 | 2021-07-27 | 成都纳雷科技有限公司 | Vehicle-mounted radar target tracking method and device based on target prior information |
| CN111257864B (en) * | 2020-01-17 | 2021-12-10 | 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 |
| CN111157008B (en) * | 2020-03-05 | 2022-06-21 | 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 |
| CN112356845B (en) * | 2020-11-19 | 2022-02-18 | 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 |
| 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 |
| CN114187328B (en) * | 2022-02-15 | 2022-07-05 | 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 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2844643B2 (en) * | 1989-03-13 | 1999-01-06 | 日本電気株式会社 | Target tracking method |
| US9229102B1 (en) * | 2009-12-18 | 2016-01-05 | L-3 Communications Security And Detection Systems, Inc. | Detection of movable objects |
| US9255988B2 (en) * | 2014-01-16 | 2016-02-09 | GM Global Technology Operations LLC | 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 |
| CN105353368B (en) * | 2015-11-09 | 2017-11-24 | 中国船舶重工集团公司第七二四研究所 | A kind of adaptive variable structure radar based on policy determination is to extra large method for tracking target |
| CN105487061B (en) * | 2015-12-01 | 2018-04-17 | 中国人民解放军海军航空工程学院 | The multicharacteristic information fusion method of target data association |
| 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
Also Published As
| Publication number | Publication date |
|---|---|
| CN109212514A (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109212514B (en) | Continuous tracking and associating method for moving and static targets by radar detection equipment | |
| CN109212520B (en) | Road condition sensing abnormal event detection alarm system and method for omnibearing detection radar | |
| US11009364B2 (en) | Vehicular communications network and methods of use and manufacture thereof | |
| Messelodi et al. | Intelligent extended floating car data collection | |
| US11836985B2 (en) | Identifying suspicious entities using autonomous vehicles | |
| US6173231B1 (en) | Method and system for collecting data concerning thermal properties of roads for a geographic database and use thereof in a vehicle safety system | |
| CN111383480B (en) | Method, apparatus, device and medium for hazard warning of vehicles | |
| CN112106124A (en) | System and method for using V2X and sensor data | |
| JP2005038381A (en) | Data analyzing apparatus, data analyzing program, and mobile terminal | |
| CN113706737A (en) | Road surface inspection system and method based on automatic driving vehicle | |
| US20210383686A1 (en) | Roadside computing system for predicting road user trajectory and assessing travel risk | |
| JP5522475B2 (en) | Navigation device | |
| CN110688943A (en) | Method and device for automatically acquiring image sample based on actual driving data | |
| US20220234588A1 (en) | Data Recording for Advanced Driving Assistance System Testing and Validation | |
| CN117130010A (en) | Obstacle sensing method and system for unmanned vehicle and unmanned vehicle | |
| CN116142178A (en) | Vehicle auxiliary driving method, system, medium and electronic equipment | |
| CN116165655A (en) | Global vehicle track tracking system based on millimeter wave radar group | |
| CN115755026A (en) | Vehicle guiding method and vehicle | |
| CN113220805B (en) | Map generation device, recording medium, and map generation method | |
| US11423661B2 (en) | Object recognition apparatus | |
| Dorrazehi et al. | A Warning System Design for Camel-Vehicle Collisions Mitigation | |
| CN109147328B (en) | Traffic flow detection method based on video virtual coil | |
| KR102616571B1 (en) | System and method for providing road traffic information based on image analysis using artificial intelligence | |
| CN117238143B (en) | Traffic data fusion method, system and device based on radar double-spectrum camera | |
| CN115394099B (en) | Road traffic guidance method, system, equipment and traffic guidance sign |
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 |