CN113296088A - Dynamic target tracking method and device for vehicle and vehicle - Google Patents
Dynamic target tracking method and device for vehicle and vehicle Download PDFInfo
- Publication number
- CN113296088A CN113296088A CN202110510799.9A CN202110510799A CN113296088A CN 113296088 A CN113296088 A CN 113296088A CN 202110510799 A CN202110510799 A CN 202110510799A CN 113296088 A CN113296088 A CN 113296088A
- Authority
- CN
- China
- Prior art keywords
- target
- data
- vehicle
- state
- dynamic target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000003068 static effect Effects 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 14
- 238000012216 screening Methods 0.000 claims abstract description 13
- 230000002596 correlated effect Effects 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
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
- G01S13/66—Radar-tracking systems; Analogous systems
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 application discloses a dynamic target tracking method and device for a vehicle and the vehicle, wherein the method comprises the following steps: respectively acquiring millimeter wave data and image data of a dynamic target around a vehicle at the current moment to obtain initial obstacle state data of the dynamic target; screening static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data; aligning the final obstacle state data by using a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system; and associating with the target information of the vehicle at the previous moment to obtain the target state of the dynamic target, and obtaining the tracking state of the dynamic target by using a Kalman filter. Therefore, the problem of dynamic target tracking of fusion of the vehicle-mounted camera and the millimeter wave radar is solved.
Description
Technical Field
The application relates to the technical field of intelligent vehicle environment perception, in particular to a dynamic target tracking method and device for a vehicle and the vehicle.
Background
The intelligent automobile is a comprehensive system, and the whole system can be divided into environment perception, decision planning and motion control. The environment perception is used as a key link for information exchange between the intelligent automobile and the surrounding environment, so that the intelligent automobile can know the environment where the intelligent automobile is located, and the environment perception is very important for subsequent decision, planning and control.
In the related technology, the millimeter wave radar and the camera are calibrated in a combined mode, information of the millimeter wave radar is back projected to a camera image, a correlation judgment strategy is set to correlate a visual tracking target with a vehicle target by means of the projected information again, and visual detection information is corrected.
However, camera information is fused with millimeter wave target information, and image information is corrected by machine learning, so that the calculation process is complex, the requirement on hardware is high, and a solution is urgently needed.
Content of application
The application provides a dynamic target tracking method and device of a vehicle and the vehicle, and aims to solve the problem of dynamic target tracking of fusion of a vehicle-mounted camera and a millimeter wave radar.
An embodiment of a first aspect of the present application provides a dynamic target tracking method for a vehicle, including the following steps:
respectively acquiring millimeter wave data and image data of a dynamic target around a vehicle at the current moment to obtain initial obstacle state data of the dynamic target;
screening out static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data;
aligning the final obstacle state data by using a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system; and
and associating with the target information of the vehicle at the previous moment to obtain the target state of the dynamic target, and obtaining the tracking state of the dynamic target by using a Kalman filter.
Optionally, the screening out static obstacle data and clutter data in the obstacle status data comprises:
and eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the number of times of occurrence is smaller than the preset number, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the previous frame and the next frame are smaller than corresponding preset values.
Optionally, the obtaining the target state of the dynamic target in association with the target information of the vehicle at the previous time includes:
and predicting the state of the dynamic target at any moment by using the motion model, and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
Optionally, the associating with the target information of the vehicle at the previous time to obtain the target state of the dynamic target further includes:
and initializing the data which do not fall into the associated gate as a new target for updating the target state.
Optionally, the obtaining, by using a kalman filter, a tracking state of the dynamic target includes:
and sequentially carrying out iterative processing on the target state at each moment, so that the target information acquired each time is used as the output of the previous moment, and the continuous tracking state of the dynamic target at the current moment is generated.
An embodiment of a second aspect of the present application provides a dynamic target tracking apparatus for a vehicle, including:
the first acquisition module is used for respectively acquiring millimeter wave data and image data of a dynamic target around a vehicle at the current moment to obtain initial obstacle state data of the dynamic target;
the screening module is used for screening static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data;
the control module is used for aligning the final obstacle state data by utilizing a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system; and
and the second acquisition module is used for associating with the target information of the vehicle at the previous moment to acquire the target state of the dynamic target, and acquiring the tracking state of the dynamic target by using a Kalman filter.
Optionally, the sifting module comprises:
and the eliminating unit is used for eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the occurrence frequency is smaller than the preset frequency, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the front frame and the rear frame are smaller than the corresponding preset values.
Optionally, the second obtaining module includes:
and the prediction unit is used for predicting the state of the dynamic target at any moment by using the motion model and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
Optionally, the second obtaining module further includes:
and the processing unit is used for initializing data which does not fall into the associated gate as a new target for updating the target state.
Optionally, the second obtaining module includes:
and sequentially carrying out iterative processing on the target state at each moment, so that the target information acquired each time is used as the output of the previous moment, and the continuous tracking state of the dynamic target at the current moment is generated.
An embodiment of a third aspect of the present application provides a vehicle, which includes the above dynamic target tracking device for a vehicle.
Therefore, millimeter wave data and image data of a dynamic target around a vehicle at the current moment can be acquired respectively, initial obstacle state data of the dynamic target is acquired, static obstacle data and clutter data in the obstacle state data are screened out, final obstacle state data are acquired, the final obstacle state data are aligned through a preset coordinate transformation matrix, target information under a vehicle coordinate system is acquired and is associated with target information of the vehicle at the previous moment, a target state of the dynamic target is acquired, a Kalman filter is used for acquiring a tracking state of the dynamic target, and the problem of dynamic target tracking of fusion of a vehicle-mounted camera and a millimeter wave radar is solved.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for dynamic target tracking of a vehicle according to an embodiment of the present application;
FIG. 2 is a flow diagram of millimeter wave radar data preprocessing according to one embodiment of the present application;
FIG. 3 is a flow diagram of a camera and millimeter wave radar spatial alignment according to one embodiment of the present application;
FIG. 4 is a flow diagram of sensor association tracking according to one embodiment of the present application;
FIG. 5 is a flow chart of a method of dynamic target tracking for a vehicle according to one embodiment of the present application;
FIG. 6 is an exemplary diagram of a dynamic object tracking device of a vehicle according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The following describes a dynamic target tracking method and device for a vehicle and the vehicle according to an embodiment of the present application with reference to the drawings. Aiming at the problem of dynamic target tracking of fusion of a vehicle-mounted camera and a millimeter wave radar mentioned in the background center, the application provides a dynamic target tracking method of a vehicle, in the method, millimeter wave data and image data of the dynamic target around the vehicle at the current moment can be respectively obtained to obtain initial obstacle state data of the dynamic target, screening out static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data, and aligning the final obstacle state data by using a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system, and is associated with the target information of the vehicle at the previous moment to obtain the target state of the dynamic target, and a Kalman filter is utilized to obtain the tracking state of the dynamic target, so that the problem of dynamic target tracking by fusing a vehicle-mounted camera and a millimeter wave radar is solved.
Specifically, fig. 1 is a schematic flowchart of a dynamic target tracking method for a vehicle according to an embodiment of the present disclosure.
As shown in fig. 1, the dynamic target tracking method of the vehicle includes the steps of:
in step S101, millimeter wave data and image data of the dynamic target around the vehicle at the current time are acquired, respectively, to obtain initial obstacle state data of the dynamic target.
Specifically, according to the embodiment of the application, a camera and a millimeter wave radar are required to be mounted on a vehicle, the directions of three coordinate systems of the camera, the millimeter wave radar and the vehicle are determined, a vehicle-mounted camera coordinate system and a millimeter wave radar coordinate system are calibrated to the vehicle coordinate system according to a preset calibration method, and transformation matrixes M1 and M2 from the camera and the millimeter wave radar to the vehicle coordinate system are obtained respectively.
Further, target information output by the millimeter wave radar and the camera at the moment K +1 is obtained, namely time synchronization, and first frame dynamic obstacle state information (namely initial obstacle state data) of the camera and the millimeter wave radar is obtained.
In step S102, static obstacle data and clutter data in the obstacle state data are filtered out to obtain final obstacle state data.
Optionally, in some embodiments, screening out static obstacle data and clutter data in the obstacle status data comprises: and eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the occurrence times are smaller than the preset times, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the front frame and the rear frame are smaller than corresponding preset values.
Specifically, as shown in fig. 2, after the initial obstacle state data of the dynamic target, the embodiment of the present application may set a preset speed threshold V1 to remove static data, further remove a false target (i.e., a false module number) whose occurrence number is less than a preset number n, remove a relative distance between frames before and after being not satisfied is less than a preset value r1, remove a relative angle between frames before and after being not satisfied is less than a preset value a1, and remove clutter data whose relative speed between frames before and after being not satisfied is less than a preset value V2, so as to obtain processed information, that is, final obstacle state data.
In step S103, the final obstacle state data is aligned by using a preset coordinate transformation matrix, so as to obtain target information in a vehicle coordinate system.
Specifically, as shown in fig. 3, fig. 3 is a camera and millimeter wave radar space alignment flowchart, where M1 is a conversion matrix from a camera coordinate system to a vehicle coordinate system, and M2 is a conversion matrix from a radar coordinate system to a vehicle coordinate system.
Specifically, after the camera/radar target information is acquired, the camera coordinate system analyzes the data X1, and the camera target is in the vehicle coordinate system Y1 — M1X 1; analyzing data X2 in a radar coordinate system, wherein a radar target is in a vehicle coordinate system Y2-M2-X2; and carrying out space alignment to obtain data after coordinate transformation.
In step S104, the target state of the dynamic target is obtained in association with the target information of the vehicle at the previous time, and the tracking state of the dynamic target is obtained using the kalman filter.
Optionally, in some embodiments, the obtaining the target state of the dynamic target in association with the target information of the vehicle at the previous time includes: and predicting the state of the dynamic target at any moment by using the motion model, and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
That is to say, the embodiment of the present application may acquire the motion state information X of the target at time K: establishing the state K + 1' of the motion model prediction target at the moment K +1, establishing a target association gate, setting a preset threshold gamma, satisfying < gamma, and considering effective association.
As shown in fig. 4, fig. 4 is a flowchart of sensor association tracking. Wherein σ2Is the sensor error variance. Specifically, the state prediction value K + 1' at the moment of K +1 is established, a tracking gate is established, and an association threshold γ is set to satisfy:
and establishing an incidence relation of effective data in the incidence gate, and performing Kalman filtering analysis.
Optionally, in some embodiments, the obtaining the target state of the dynamic target in association with the target information of the vehicle at the previous time further includes: and initializing the data which do not fall into the associated gate as a new target for updating the target state.
Specifically, the embodiment of the application may determine whether the target is initialized, and if not, select the obstacle information of the camera of the first frame as the initial values of the target states T11, T12, …, and T1n, and establish and initialize the kalman filter according to the initial values of the states;
and time synchronization is carried out, the state information of the dynamic obstacles of the second frame of the camera and the millimeter wave radar is obtained, and if the number of the dynamic obstacles is m: TK-21, TK-22, …, TK-2 m;
and predicting in a second frame according to the initial state value of the target, establishing an association gate of n targets, setting an association threshold, processing the association relation between the camera and millimeter wave radar data falling into the association gate and the target state of the previous frame according to the newly added target, and initializing.
Therefore, Kalman filtering can be performed according to the acquired incidence relation, the state of the target of the second frame is updated by using the camera information of the second frame, the state of the target of the second frame is updated by using the millimeter wave radar information, and finally complete information of the dynamically tracked target of the second frame is obtained
Optionally, in some embodiments, obtaining the tracking state of the dynamic target by using a kalman filter includes: and sequentially carrying out iterative processing on the target state at each moment, so that the target information acquired each time is used as the output of the previous moment, and the continuous tracking state of the dynamic target at the current moment is generated.
That is to say, in the embodiment of the present application, iteration processing is performed sequentially at each time, and the target information obtained each time is output as data of a previous frame, so as to obtain a continuous tracking state of the dynamic target at the current time.
Further, in order to enable those skilled in the art to further understand the dynamic target tracking method of the vehicle according to the embodiment of the present application, the following detailed description is made with reference to fig. 5.
Specifically, as shown in fig. 5, in the embodiment of the present application, information of a sensor (a camera and a millimeter wave radar) at the time K +1 is acquired, data acquired by the millimeter wave radar is preprocessed, static obstacles and clutter are removed, final obstacle state data is aligned by using a preset coordinate transformation matrix, target information in a vehicle coordinate system is obtained, and a target state at the time K +1 is further updated through kalman filtering and a preset threshold. The method and the device for establishing the association gate can obtain the target state K at the moment K, predict the state, the distance and the speed similarity at the moment K +1 according to the state, and establish the association gate (namely the preset gate).
According to the dynamic target tracking method for the vehicle, millimeter wave data and image data of a dynamic target around the vehicle at the current moment can be obtained respectively, initial obstacle state data of the dynamic target are obtained, static obstacle data and clutter data in the obstacle state data are screened out, final obstacle state data are obtained, the final obstacle state data are aligned through a preset coordinate transformation matrix, target information under a vehicle coordinate system is obtained and is associated with target information of the vehicle at the previous moment, the target state of the dynamic target is obtained, a Kalman filter is used for obtaining the tracking state of the dynamic target, and the problems that machine learning is needed to be used for correcting the image information in the related technology, the calculating process is complex, and the requirement on hardware is high are solved.
Next, a dynamic target tracking apparatus of a vehicle according to an embodiment of the present application is described with reference to the drawings.
Fig. 6 is a block diagram schematically illustrating a dynamic object tracking device of a vehicle according to an embodiment of the present application.
As shown in fig. 6, the dynamic target tracking device 10 of the vehicle includes: a first capture module 100, a sift module 200, a control module 300, and a second capture module 400.
The first obtaining module 100 is configured to obtain millimeter wave data and image data of a dynamic target around a vehicle at a current moment, respectively, to obtain initial obstacle state data of the dynamic target;
the screening module 200 is configured to screen static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data;
the control module 300 is configured to align the final obstacle state data by using a preset coordinate transformation matrix to obtain target information in a vehicle coordinate system; and
the second obtaining module 400 is configured to associate with target information of a vehicle at a previous time to obtain a target state of the dynamic target, and obtain a tracking state of the dynamic target by using a kalman filter.
Optionally, a screening module comprising:
and the eliminating unit is used for eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the occurrence times are smaller than the preset times, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the front frame and the rear frame are smaller than the corresponding preset values.
Optionally, the second obtaining module includes:
and the prediction unit is used for predicting the state of the dynamic target at any moment by using the motion model and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
Optionally, the second obtaining module further includes:
and the processing unit is used for initializing data which does not fall into the associated gate as a new target for updating the target state.
Optionally, the second obtaining module includes:
and sequentially carrying out iterative processing on the target state at each moment, so that the target information acquired each time is used as the output of the previous moment, and the continuous tracking state of the dynamic target at the current moment is generated. It should be noted that the foregoing explanation of the embodiment of the dynamic target tracking method for a vehicle is also applicable to the dynamic target tracking device for a vehicle in this embodiment, and details are not repeated here.
According to the dynamic target tracking device of the vehicle, millimeter wave data and image data of a dynamic target around the vehicle at the current moment can be respectively obtained, initial obstacle state data of the dynamic target are obtained, static obstacle data and clutter data in the obstacle state data are screened out, final obstacle state data are obtained, the final obstacle state data are aligned through a preset coordinate transformation matrix, target information under a vehicle coordinate system is obtained and is associated with target information of the vehicle at the previous moment, the target state of the dynamic target is obtained, a Kalman filter is used, the tracking state of the dynamic target is obtained, and the problem of dynamic target tracking of fusion of a vehicle-mounted camera and a millimeter wave radar is solved.
In addition, the embodiment of the application also provides a vehicle, and the vehicle comprises the dynamic target tracking device of the vehicle.
According to the vehicle provided by the embodiment of the application, the problem of dynamic target tracking of fusion of the vehicle-mounted camera and the millimeter wave radar is solved through the dynamic target tracking device of the vehicle.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, Programmable Gate Arrays (PGAs), Field Programmable Gate Arrays (FPGAs), etc.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware that can be related to instructions of a program, which can be stored in a computer-readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
Claims (10)
1. A method for dynamic target tracking of a vehicle, comprising the steps of:
respectively acquiring millimeter wave data and image data of a dynamic target around a vehicle at the current moment to obtain initial obstacle state data of the dynamic target;
screening out static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data;
aligning the final obstacle state data by using a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system; and
and associating with the target information of the vehicle at the previous moment to obtain the target state of the dynamic target, and obtaining the tracking state of the dynamic target by using a Kalman filter.
2. The method of claim 1, wherein the screening out static obstacle data and clutter data in the obstacle status data comprises:
and eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the occurrence times are smaller than the preset times, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the front frame and the rear frame are smaller than the corresponding preset values.
3. The method of claim 1, wherein the obtaining the goal state of the dynamic goal in association with the goal information of the vehicle at the previous time comprises:
and predicting the state of the dynamic target at any moment by using the motion model, and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
4. The method of claim 3, wherein the obtaining the goal state of the dynamic goal in association with goal information of a vehicle at a previous time further comprises:
and initializing the data which do not fall into the associated gate as a new target for updating the target state.
5. The method according to claim 1, wherein the obtaining the tracking state of the dynamic target by using the kalman filter includes:
and sequentially carrying out iterative processing on the target state at each moment, so that the target information acquired each time is used as the output of the previous moment, and the continuous tracking state of the dynamic target at the current moment is generated.
6. A dynamic target tracking device for a vehicle, comprising:
the first acquisition module is used for respectively acquiring millimeter wave data and image data of a dynamic target around a vehicle at the current moment to obtain initial obstacle state data of the dynamic target;
the screening module is used for screening static obstacle data and clutter data in the obstacle state data to obtain final obstacle state data;
the control module is used for aligning the final obstacle state data by utilizing a preset coordinate transformation matrix to obtain target information under a vehicle coordinate system; and
and the second acquisition module is used for associating with the target information of the vehicle at the previous moment to acquire the target state of the dynamic target, and acquiring the tracking state of the dynamic target by using a Kalman filter.
7. The apparatus of claim 6, wherein the sifting module comprises:
and the eliminating unit is used for eliminating static data smaller than a preset speed threshold value from the initial obstacle state data, eliminating false mode numbers meeting the condition that the occurrence frequency is smaller than the preset frequency, and eliminating clutter data not meeting the condition that the relative distance, the relative angle and the relative speed of the front frame and the rear frame are smaller than the corresponding preset values.
8. The apparatus of claim 6, wherein the second obtaining module comprises:
and the prediction unit is used for predicting the state of the dynamic target at any moment by using the motion model and establishing a correlation gate of the dynamic target so as to judge that the dynamic target is correlated when the correlation threshold of the dynamic target and the correlation threshold is smaller than a preset threshold.
9. The apparatus of claim 8, wherein the second obtaining module further comprises:
and the processing unit is used for initializing data which does not fall into the associated gate as a new target for updating the target state.
10. A vehicle, characterized by comprising: a dynamic object tracking apparatus of a vehicle as claimed in any one of claims 6 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510799.9A CN113296088A (en) | 2021-05-11 | 2021-05-11 | Dynamic target tracking method and device for vehicle and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510799.9A CN113296088A (en) | 2021-05-11 | 2021-05-11 | Dynamic target tracking method and device for vehicle and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113296088A true CN113296088A (en) | 2021-08-24 |
Family
ID=77321323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110510799.9A Pending CN113296088A (en) | 2021-05-11 | 2021-05-11 | Dynamic target tracking method and device for vehicle and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113296088A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08124080A (en) * | 1994-10-20 | 1996-05-17 | Honda Motor Co Ltd | Obstacle detector of vehicle |
| CN109212521A (en) * | 2018-09-26 | 2019-01-15 | 同济大学 | A kind of method for tracking target merged based on forward sight camera with millimetre-wave radar |
| CN111417869A (en) * | 2017-11-20 | 2020-07-14 | 三菱电机株式会社 | Obstacle recognition device and obstacle recognition method |
| CN111505623A (en) * | 2020-04-24 | 2020-08-07 | 中南大学 | Method and system for detecting obstacle in driving process of unmanned vehicle and vehicle |
| CN112363167A (en) * | 2020-11-02 | 2021-02-12 | 重庆邮电大学 | Extended target tracking method based on fusion of millimeter wave radar and monocular camera |
-
2021
- 2021-05-11 CN CN202110510799.9A patent/CN113296088A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08124080A (en) * | 1994-10-20 | 1996-05-17 | Honda Motor Co Ltd | Obstacle detector of vehicle |
| CN111417869A (en) * | 2017-11-20 | 2020-07-14 | 三菱电机株式会社 | Obstacle recognition device and obstacle recognition method |
| CN109212521A (en) * | 2018-09-26 | 2019-01-15 | 同济大学 | A kind of method for tracking target merged based on forward sight camera with millimetre-wave radar |
| CN111505623A (en) * | 2020-04-24 | 2020-08-07 | 中南大学 | Method and system for detecting obstacle in driving process of unmanned vehicle and vehicle |
| CN112363167A (en) * | 2020-11-02 | 2021-02-12 | 重庆邮电大学 | Extended target tracking method based on fusion of millimeter wave radar and monocular camera |
Non-Patent Citations (1)
| Title |
|---|
| 匡定波等: "红外光电技术", 31 March 2004, 《中国科学技术出版社》, pages: 397 - 406 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109212521B (en) | Target tracking method based on fusion of forward-looking camera and millimeter wave radar | |
| CN109871763B (en) | Specific target tracking method based on YOLO | |
| CN110264495B (en) | Target tracking method and device | |
| US10929719B2 (en) | Adversarial attack on black box object detection algorithm | |
| US10748013B2 (en) | Method and apparatus for detecting road lane | |
| CN110414526A (en) | Training method, training device, server and the storage medium of semantic segmentation network | |
| EP3671272A1 (en) | Vehicle sensor fusion based on fuzzy sets | |
| CN111209956A (en) | Sensor data fusion method, and vehicle environment map generation method and system | |
| US11703596B2 (en) | Method and system for automatically processing point cloud based on reinforcement learning | |
| CN115063454B (en) | Multi-target tracking matching method, device, terminal and storage medium | |
| CN114170303A (en) | Combined calibration method, device, system, equipment and medium for radar and camera | |
| CN114973195A (en) | Vehicle tracking method, device and system based on multi-information fusion | |
| CN118247359A (en) | Automatic calibration method and device for fish-eye camera, computer equipment and storage medium | |
| CN113253269B (en) | SAR self-focusing method based on image classification | |
| CN104616317A (en) | Video vehicle tracking validity checking method | |
| CN114255450A (en) | Near-field vehicle jamming behavior prediction method based on forward panoramic image | |
| Ebert et al. | Deep radar sensor models for accurate and robust object tracking | |
| CN116580182B (en) | Method, system, equipment and storage medium for automatically-adjusted target detection | |
| CN117789146A (en) | Visual detection method for vehicle road running under automatic driving scene | |
| CN113296088A (en) | Dynamic target tracking method and device for vehicle and vehicle | |
| CN116740145A (en) | Multi-target tracking method, device, vehicle and storage medium | |
| CN116630216A (en) | Target fusion method, device, equipment and storage medium based on radar and image | |
| CN110781730A (en) | Intelligent driving sensing method and sensing device | |
| CN114239706A (en) | Target fusion method and system based on multiple cameras and laser radar | |
| CN114354209A (en) | Automatic driving lane line and target combined simulation method and system |
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 |