CN118068286B - Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning - Google Patents
Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning Download PDFInfo
- Publication number
- CN118068286B CN118068286B CN202410452128.5A CN202410452128A CN118068286B CN 118068286 B CN118068286 B CN 118068286B CN 202410452128 A CN202410452128 A CN 202410452128A CN 118068286 B CN118068286 B CN 118068286B
- Authority
- CN
- China
- Prior art keywords
- point
- cloud
- millimeter wave
- dadian
- lei
- 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
- 230000015556 catabolic process Effects 0.000 title claims abstract description 46
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000000513 principal component analysis Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 54
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 239000006185 dispersion Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 239000012535 impurity Substances 0.000 claims description 3
- 230000000593 degrading effect Effects 0.000 claims 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Abstract
The invention relates to a method for realizing degradation environment detection aiming at influencing 4D millimeter wave Lei Dadian cloud positioning, which comprises the following steps: preprocessing the point cloud obtained by the 4D millimeter wave radar, removing outliers in the point cloud, and filtering the mixed points which cannot be filtered to obtain two clusters of point clouds which are distinguished by demarcation; projecting the two clusters of point clouds onto the same plane for principal component analysis, and extracting point cloud features from the principal component analysis; and comparing the acquired point cloud characteristic values according to a preset degradation environment judgment threshold value, and evaluating the possibility of degradation of the current positioning environment. The invention also relates to a corresponding device, processor and computer readable storage medium thereof. By adopting the method, the device, the processor and the storage medium for realizing the detection of the degradation environment aiming at the influence of the 4D millimeter wave Lei Dadian cloud positioning, the vehicle positioning system for automatic driving can be helped to improve the robustness, and the influence of the degradation environment on positioning is reduced.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to the technical field of 4D millimeter wave radar point cloud matching, and specifically relates to a method, a device, a processor and a computer readable storage medium for realizing degradation environment detection aiming at influencing 4D millimeter wave Lei Dadian cloud positioning.
Background
Under the characteristic degradation environment, the unmanned vehicle positioned by adopting 4D millimeter wave radar point cloud matching can have the problems of positioning errors, large positioning errors and the like. In order to prevent the collision of the vehicle due to the positioning deviation, many works have been proposed for the lidar to reduce the influence of the degraded environment on the positioning. The 4D millimeter wave radar, which is a sensor with all-weather and all-day characteristics, is becoming one of hot researches on how to replace the laser radar in the field of automatic driving. Compared with a laser radar, a 4D millimeter wave radar capable of providing similar point clouds also suffers from the problem of characteristic degradation environment. Therefore, a method for distinguishing and positioning the degraded scene according to the characteristics of the point cloud provided by the 4D millimeter wave radar is necessary for improving the robustness of automatic driving positioning.
Disclosure of Invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and to provide a method, apparatus, processor and computer readable storage medium thereof for implementing degradation environment detection for influencing 4D millimeter wave Lei Dadian cloud positioning.
To achieve the above object, the method, apparatus, processor and computer readable storage medium thereof for realizing degradation environment detection for influencing 4D millimeter wave Lei Dadian cloud positioning according to the present invention are as follows:
The method for realizing degradation environment detection aiming at influencing 4D millimeter wave Lei Dadian cloud positioning is mainly characterized by comprising the following steps:
(1) Preprocessing the point cloud obtained by the 4D millimeter wave radar, removing outliers in the point cloud, and filtering the mixed points which cannot be filtered to obtain two clusters of point clouds which are distinguished by demarcation;
(2) Projecting the two clusters of point clouds onto the same plane for principal component analysis, and extracting point cloud features from the principal component analysis;
(3) And comparing the acquired point cloud characteristic values according to a preset degradation environment judgment threshold value, and evaluating the possibility of degradation of the current positioning environment.
Preferably, the step (1) specifically includes the following steps:
(1.1) obtaining a Gaussian distribution modeling distance parameter d ij by searching all fields of each point P i and calculating the distance from each point to a point P j adjacent to each point, and obtaining a corresponding mean mu and a variance sigma according to the distance;
(1.2) traversing each point P i in turn, and calculating the mean value of the Gaussian distribution modeling distance parameter d ij;
(1.3) when the mean value of the gaussian modeling distance parameter d ij is greater than the confidence specified by the gaussian, then the current point is considered to be an outlier, which is removed.
Preferably, the step (1.1) is specifically to calculate the mean μ and the variance σ as follows:
；
；
Where n is the number of point clouds, m is the number of points to be traversed, k is the number of adjacent points to be traversed, i is the ith point to be traversed, and j is the jth point of the adjacent points to be traversed.
Preferably, the step (1) further comprises the steps of:
(1.4) filtering the impurity points which cannot be filtered in the outlier process;
(1.5) limiting a frame of point cloud to a preset range taking a vehicle as a center according to the measurement range and the detection characteristic of the 4D millimeter wave radar, and dividing the point cloud into a left cluster of point cloud and a right cluster of point cloud by taking the forward direction of the vehicle center as a limit;
(1.6) through the above operation, the pretreatment of the point cloud is completed.
Preferably, the step (2) specifically includes the following steps:
(2.1) assuming that each point cloud in the set of point clouds P i＝{P1,P2,...,Pn contains two-dimensional position information (x, y) relative to the radar body position, the mean value of each dimension of data is found as follows Sum of variances：
；
；
Wherein n is the number of point clouds, i is the ith point to be traversed;
(2.2) covariance of different dimensions Expressed in the following manner:
；
Wherein, Representing the coordinates of the point cloud P i,Representing the mean valueThe value in the x and y directions;
(2.3) representing the covariance matrix X by the point cloud P i＝{P1,P2,...,Pn as follows:
；
Wherein, A transpose of the P i determinant;
(2.4) obtaining a covariance matrix Y in the following manner:
；
Wherein Q is a matrix obtained by performing base conversion on the base conversion matrix R by P, i.e., q=rp, Is the transposed matrix of Q and,Is the transposed matrix of P and,A transposed matrix of R;
(2.5) the basis transformation matrix R converts the covariance matrix X into a diagonal matrix, namely a covariance matrix Y, and the values on the diagonal of the diagonal matrix are eigenvalues of the covariance matrix Y, specifically:
；
Where λ 1 and λ 2 represent the degree of data dispersion in different directions, respectively.
Preferably, the step (3) specifically includes the following steps:
(3.1) taking a straight line ax+by+c=0 represented by a basis vector (a, b) in the basis transformation matrix R, wherein c is a constant term;
(3.2) if more than two point clouds are found to satisfy the straight line equation of step (3.1) at this time, the straight line parallel determination process is performed as follows:
；
wherein a1 and b1 represent parameters of a first straight line, a2 and b2 represent parameters of a second straight line, m is a ratio result of the two, and a maximum threshold value and a minimum threshold value are determined by empirical values;
(3.3) if the result m is within the threshold range, the location environment is considered to have a possibility of degradation.
The device for realizing degradation environment detection aiming at influencing 4D millimeter wave Lei Dadian cloud positioning is mainly characterized by comprising the following components:
A processor configured to execute computer-executable instructions;
And a memory storing one or more computer-executable instructions which, when executed by the processor, implement the steps of the method for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning described above.
The processor for realizing the degradation environment detection aiming at the influence 4D millimeter wave Lei Dadian cloud positioning is mainly characterized in that the processor is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for realizing the degradation environment detection aiming at the influence 4D millimeter wave Lei Dadian cloud positioning are realized.
The computer readable storage medium is mainly characterized in that the computer program is stored thereon, and the computer program can be executed by a processor to implement the steps of the method for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning.
Compared with the prior art, the method, the device, the processor and the computer readable storage medium for realizing degradation environment detection aiming at the influence of 4D millimeter wave Lei Dadian cloud positioning adopt a Gaussian distribution model to remove outliers on the processing of the point cloud aiming at the characteristics of the 4D millimeter wave Lei Dadian cloud, and adopt simple filtering and boundary dividing to divide left and right point clouds so as to finish the preprocessing of the point cloud. Meanwhile, principal component analysis is adopted to obtain the distribution characteristics of the point cloud to obtain characteristic values and characteristic vectors, a judging formula is finally designed to confirm whether the environment where the vehicle is located is degraded or not, and a warning can be provided for a positioning system through identification of degraded scenes, so that the vehicle positioning system for automatic driving is helped to improve robustness, and the influence of the degraded environment on positioning is reduced.
Drawings
Fig. 1 is a flow chart of a method of the present invention for implementing degraded environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning.
Detailed Description
In order to more clearly describe the technical contents of the present invention, a further description will be made below in connection with specific embodiments.
Before describing in detail embodiments that are in accordance with the present invention, it should be observed that 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.
Referring to fig. 1, the method for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning includes the following steps:
(1) Preprocessing the point cloud obtained by the 4D millimeter wave radar, removing outliers in the point cloud, and filtering the mixed points which cannot be filtered to obtain two clusters of point clouds which are distinguished by demarcation;
(2) Projecting the two clusters of point clouds onto the same plane for principal component analysis, and extracting point cloud features from the principal component analysis;
(3) And comparing the acquired point cloud characteristic values according to a preset degradation environment judgment threshold value, and evaluating the possibility of degradation of the current positioning environment.
As a preferred embodiment of the present invention, the step (1) specifically includes the steps of:
(1.1) obtaining a Gaussian distribution modeling distance parameter d ij by searching all fields of each point P i and calculating the distance from each point to a point P j adjacent to each point, and obtaining a corresponding mean mu and a variance sigma according to the distance;
(1.2) traversing each point P i in turn, and calculating the mean value of the Gaussian distribution modeling distance parameter d ij;
(1.3) when the mean value of the gaussian modeling distance parameter d ij is greater than the confidence specified by the gaussian, then the current point is considered to be an outlier, which is removed.
As a preferred embodiment of the present invention, the step (1.1) is specifically to calculate the mean μ and the variance σ as follows:
；
；
Where n is the number of point clouds, m is the number of points to be traversed, k is the number of adjacent points to be traversed, i is the ith point to be traversed, and j is the jth point of the adjacent points to be traversed.
As a preferred embodiment of the present invention, the step (1) further includes the steps of:
(1.4) filtering the impurity points which cannot be filtered in the outlier process;
(1.5) limiting a frame of point cloud to a preset range taking a vehicle as a center according to the measurement range and the detection characteristic of the 4D millimeter wave radar, and dividing the point cloud into a left cluster of point cloud and a right cluster of point cloud by taking the forward direction of the vehicle center as a limit;
(1.6) through the above operation, the pretreatment of the point cloud is completed.
As a preferred embodiment of the present invention, the step (2) specifically includes the following steps:
(2.1) assuming that each point cloud in the set of point clouds P i＝{P1,P2,...,Pn contains two-dimensional position information (x, y) relative to the radar body position, the mean value of each dimension of data is found as follows Sum of variances：
；
；
Where n is the number of point clouds, i is the i-th point to be traversed, and cov (x, x) =var (x).
(2.2) Covariance of different dimensionsExpressed in the following manner:
；
Wherein, Representing the coordinates of the point cloud P i,Representing the mean valueThe value in the x and y directions;
(2.3) representing the covariance matrix X by the point cloud P i＝{P1,P2,...,Pn as follows:
；
Wherein, A transpose of the P i determinant;
(2.4) obtaining a covariance matrix Y in the following manner:
；
Wherein Q is a matrix obtained by performing base conversion on the base conversion matrix R by P, i.e., q=rp, Is the transposed matrix of Q and,Is the transposed matrix of P and,A transposed matrix of R;
(2.5) the basis transformation matrix R converts the covariance matrix X into a diagonal matrix, namely a covariance matrix Y, and the values on the diagonal of the diagonal matrix are eigenvalues of the covariance matrix Y, specifically:
；
Where λ 1 and λ 2 represent the degree of data dispersion in different directions, respectively.
As a preferred embodiment of the present invention, the step (3) specifically includes the following steps:
(3.1) taking a straight line ax+by+c=0 represented by a basis vector (a, b) in the basis transformation matrix R, wherein c is a constant term;
(3.2) if more than two point clouds are found to satisfy the straight line equation of step (3.1) at this time, the straight line parallel determination process is performed as follows:
；
wherein a1 and b1 represent parameters of a first straight line, a2 and b2 represent parameters of a second straight line, m is a ratio result of the two, and a maximum threshold value and a minimum threshold value are determined by empirical values;
(3.3) if the result m is within the threshold range, the location environment is considered to have a possibility of degradation.
In practical application, for the identification method in the degradation characteristic environment, the degradation environment most frequently encountered in the unmanned vehicle is a similar long straight road, such as a tunnel and other scenes. The characteristic that long straight channels exist is parallel planes, so the main principle of detecting the degradation characteristic environment is to rely on the identification of plane characteristic points Yun Qun in the point cloud.
The following further details the present technical solution:
(1) Firstly, the point cloud obtained from the 4D millimeter wave radar needs to be preprocessed, and the specific operation steps are as follows:
1. Because of the characteristics of the 4D millimeter wave radar, the point cloud has clutter, so in order to better distinguish the degradation characteristic environment, outlier removal of the point cloud is required. The principle is that by searching all fields of each point P i and calculating the distance d ij from each point to the adjacent point P j, the distance parameter d ij is modeled according to Gaussian distribution, and the following formula is shown:
；
；
Where n is the number of point clouds, m is the number of points to be traversed, k is the number of adjacent points to be traversed, i represents the ith point to be traversed, j is the jth point of the adjacent points to be traversed, after the mean μ and the variance σ are obtained, the traversing of each point P i is continued, and d ij mean is calculated, and if the point mean is greater than the confidence specified by Gaussian distribution, the point mean can be regarded as an outlier and removed.
2. And then, carrying out simple filtering treatment on the point cloud, and treating the outlier which cannot be treated by the outlier filtering. And meanwhile, according to the measurement range and detection characteristics of the millimeter wave radar, one frame of point cloud is limited to be within a range of 50m in front and back and 10m in left and right directions by taking a vehicle as a center. Finally, the vehicle center is used as a boundary to divide into a left cluster point cloud and a right cluster point cloud. Through the operation, the pretreatment of the point cloud is completed.
(2) The two clusters of point clouds are projected onto the same plane, and generally, the projection is performed without considering the elevation value of the point cloud coordinates. Principal component analysis is performed on the projected 2D planar points. Assuming that the group of point cloud data is P i={P1,P2,...,Pn }, each point cloud in the point cloud P i contains two-dimensional position information (x, y) relative to the radar body position, and the average value of each dimensional data is obtainedSum of variancesThe method comprises the following steps of:
；
；
Covariance of data of different dimensions, taking x and y as examples, can be expressed as:
；
The covariance matrix X of a set of two-dimensional point cloud data P i={P1,P2,...,Pn is:
；
Because the covariance X is a real symmetric matrix, according to the special property that feature vectors corresponding to different feature values are necessarily orthogonal, q=rp, Q is set as data obtained by performing base transformation on the base transformation matrix R by P, and the covariance matrix of Q is set as Y, which can be obtained by:
；
Wherein Q is the data obtained by performing base conversion on the base conversion matrix R by P, Is the transposed matrix of Q. P and the sameR andAre the corresponding matrix and transpose matrix.
The matrix R is such that the covariance matrix X becomes a diagonal matrix Y, and the values on the diagonal are eigenvalues of Y, as follows:
；
At this time, the basis vectors in the matrix R represent the direction of data distribution, and the corresponding eigenvalues λ represent the degree of dispersion of data in that direction, and λ 1 and λ 2 represent the degree of dispersion of data in different directions, respectively.
(3) The degraded scene can be analyzed according to the result of the point cloud characteristic value lambda. When one eigenvalue is far greater than another (typically greater than 10 times empirically), it is shown that the degree of dispersion of the data in the direction of the eigenvalue is far greater than in the other direction, which proves that the point cloud is in a straight line distribution. Taking the straight line ax+by+c=0 represented by the basis vector (a, b) in R. If more than two point clouds are found to be in the situation, the straight line parallel judgment formula is adopted:
；
Wherein a1 and b1 represent parameters of a first straight line, a2 and b2 represent parameters of a second straight line, and m is a ratio of the two. The maximum and minimum thresholds are determined by empirical values. If the m result is within the threshold, then the location environment may be considered to be potentially degraded.
The device for realizing degradation environment detection aiming at the influence of 4D millimeter wave Lei Dadian cloud positioning comprises:
A processor configured to execute computer-executable instructions;
And a memory storing one or more computer-executable instructions which, when executed by the processor, implement the steps of the method for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning described above.
The processor for realizing the detection of the degradation environment for the influence 4D millimeter wave Lei Dadian cloud positioning is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for realizing the detection of the degradation environment for the influence 4D millimeter wave Lei Dadian cloud positioning are realized.
The computer readable storage medium having stored thereon a computer program executable by a processor to perform the steps of the method for performing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning described above.
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 executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention 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 the present invention.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution device.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, and the program may be stored in a computer readable storage medium, where the program when executed includes one or a combination of the steps of the method embodiments.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "examples," "specific examples," or "embodiments," etc., means 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 invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Compared with the prior art, the method, the device, the processor and the computer readable storage medium for realizing degradation environment detection aiming at the influence of 4D millimeter wave Lei Dadian cloud positioning adopt a Gaussian distribution model to remove outliers on the processing of the point cloud aiming at the characteristics of the 4D millimeter wave Lei Dadian cloud, and adopt simple filtering and boundary dividing to divide left and right point clouds so as to finish the preprocessing of the point cloud. Meanwhile, principal component analysis is adopted to obtain the distribution characteristics of the point cloud to obtain characteristic values and characteristic vectors, a judging formula is finally designed to confirm whether the environment where the vehicle is located is degraded or not, and a warning can be provided for a positioning system through identification of degraded scenes, so that the vehicle positioning system for automatic driving is helped to improve robustness, and the influence of the degraded environment on positioning is reduced.
In this specification, the invention has been described with reference to specific embodiments thereof. It will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (7)
1. A method for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning, the method comprising the steps of:
(1) Preprocessing the point cloud obtained by the 4D millimeter wave radar, removing outliers in the point cloud, and filtering the mixed points which cannot be filtered to obtain two clusters of point clouds which are distinguished by demarcation;
(2) Projecting the two clusters of point clouds onto the same plane for principal component analysis, and extracting point cloud features from the principal component analysis;
(3) Comparing the acquired point cloud characteristic values according to a preset degradation environment judgment threshold value, and evaluating the possibility of degradation of the current positioning environment according to the comparison result;
the step (2) specifically comprises the following steps:
(2.1) assuming that each point cloud in the set of point clouds P i＝{P1,P2,...,Pn contains two-dimensional position information (x, y) relative to the radar body position, the mean value of each dimension of data is found as follows Sum of variances：
；
；
Wherein n is the number of point clouds, i is the ith point to be traversed;
(2.2) covariance of different dimensions Expressed in the following manner:
；
Wherein, Representing the coordinates of the point cloud P i,Representing the mean valueThe value in the x and y directions;
(2.3) representing the covariance matrix X by the point cloud P i＝{P1,P2,...,Pn as follows:
；
Wherein, A transpose of the P i determinant;
(2.4) obtaining a covariance matrix Y in the following manner:
；
wherein Q is a matrix obtained by performing base conversion on the base conversion matrix R by P, i.e., q=rp, Is the transposed matrix of Q and,Is the transposed matrix of P and,A transposed matrix of R;
(2.5) the basis transformation matrix R converts the covariance matrix X into a diagonal matrix, namely a covariance matrix Y, and the values on the diagonal of the diagonal matrix are eigenvalues of the covariance matrix Y, specifically:
；
Wherein λ 1 and λ 2 represent the degree of data dispersion in different directions, respectively;
the step (3) specifically comprises the following steps:
(3.1) taking a straight line ax+by+c=0 represented by a basis vector (a, b) in the basis transformation matrix R, wherein c is a constant term;
(3.2) if more than two point clouds are found to satisfy the straight line equation of step (3.1) at this time, the straight line parallel determination process is performed as follows:
；
wherein a1 and b1 represent parameters of a first straight line, a2 and b2 represent parameters of a second straight line, m is a ratio result of the two, and a maximum threshold value and a minimum threshold value are determined by empirical values;
(3.3) if the result m is within the threshold range, the location environment is considered to have a possibility of degradation.
2. The method for realizing degradation environment detection for influencing 4D millimeter wave Lei Dadian cloud positioning according to claim 1, wherein the step (1) specifically comprises the following steps:
(1.1) obtaining a Gaussian distribution modeling distance parameter d ij by searching all fields of each point P i and calculating the distance from each point to a point P j adjacent to each point, and obtaining a corresponding mean mu and a variance sigma according to the distance;
(1.2) traversing each point P i in turn, and calculating the mean value of the Gaussian distribution modeling distance parameter d ij;
(1.3) when the mean value of the gaussian modeling distance parameter d ij is greater than the confidence specified by the gaussian, then the current point is considered to be an outlier, which is removed.
3. The method for realizing degradation environment detection for influencing 4D millimeter wave Lei Dadian cloud positioning according to claim 2, wherein the step (1.1) is specifically to calculate the mean μ and variance σ as follows:
；
；
Where n is the number of point clouds, m is the number of points to be traversed, k is the number of adjacent points to be traversed, i is the ith point to be traversed, and j is the jth point of the adjacent points to be traversed.
4. The method for realizing degradation environment detection for influencing 4D millimeter wave Lei Dadian cloud positioning according to claim 2, wherein the step (1) further comprises the steps of:
(1.4) filtering the impurity points which cannot be filtered in the outlier process;
(1.5) limiting a frame of point cloud to a preset range taking a vehicle as a center according to the measurement range and the detection characteristic of the 4D millimeter wave radar, and dividing the point cloud into a left cluster of point cloud and a right cluster of point cloud by taking the forward direction of the vehicle center as a limit;
(1.6) through the above operation, the pretreatment of the point cloud is completed.
5. An apparatus for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning, the apparatus comprising:
A processor configured to execute computer-executable instructions;
a memory storing one or more computer-executable instructions which, when executed by the processor, perform the steps of the method of any one of claims 1 to 4 for implementing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning.
6. A processor for implementing detection of a degrading environment for affecting 4D millimeter wave Lei Dadian cloud positioning, characterized in that the processor is configured to execute computer executable instructions that, when executed by the processor, implement the steps of the method for implementing detection of a degrading environment for affecting 4D millimeter wave Lei Dadian cloud positioning as claimed in any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program executable by a processor to perform the steps of the method of any one of claims 1 to 4 for performing degradation environment detection for affecting 4D millimeter wave Lei Dadian cloud positioning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452128.5A CN118068286B (en) | 2024-04-16 | Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452128.5A CN118068286B (en) | 2024-04-16 | Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118068286A CN118068286A (en) | 2024-05-24 |
| CN118068286B true CN118068286B (en) | 2024-07-05 |
Family
ID=
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116299535A (en) * | 2023-03-06 | 2023-06-23 | 上海交通大学 | Laser radar SLAM degradation detection method and system based on geometric information |
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116299535A (en) * | 2023-03-06 | 2023-06-23 | 上海交通大学 | Laser radar SLAM degradation detection method and system based on geometric information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9378463B2 (en) | System and method for fusing outputs from multiple LiDAR sensors | |
| US9128185B2 (en) | Methods and apparatus of fusing radar/camera object data and LiDAR scan points | |
| US11474204B2 (en) | Localization method and robot using the same | |
| KR101822185B1 (en) | Method and apparatus for poi detection in 3d point clouds | |
| US20190340781A1 (en) | Obstacle detecting method and obstacle detecting apparatus based on unmanned vehicle, and device, and storage medium | |
| CN115049700A (en) | Target detection method and device | |
| CN109948635B (en) | Target identification method and device based on laser scanning | |
| CN113835102B (en) | Lane line generation method and device | |
| CN112991389A (en) | Target tracking method and device and mobile robot | |
| CN113128272B (en) | Collision prediction method, device, storage medium and server | |
| US20220171975A1 (en) | Method for Determining a Semantic Free Space | |
| CN109635641B (en) | Method, device and equipment for determining road boundary line and storage medium | |
| US11415698B2 (en) | Point group data processing device, point group data processing method, point group data processing program, vehicle control device, and vehicle | |
| CN114001706A (en) | Course angle estimation method and device, electronic equipment and storage medium | |
| CN118068286B (en) | Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning | |
| CN113496199A (en) | Histogram-based L-shaped detection of target objects | |
| CN115601435B (en) | Vehicle attitude detection method, device, vehicle and storage medium | |
| CN118068286A (en) | Method for realizing degradation environment detection aiming at influence of 4D millimeter wave Lei Dadian cloud positioning | |
| CN116703979A (en) | Target tracking method, device, terminal and storage medium | |
| Lee et al. | Vehicle tracking iterative by Kalman-based constrained multiple-kernel and 3-D model-based localization | |
| EP3779880A1 (en) | Object identification device, object identification method, and non-temporary computer readable medium storing control program | |
| US20230059883A1 (en) | Identification of planar points in lidar point cloud obtained with vehicle lidar system | |
| CN108917768B (en) | Unmanned aerial vehicle positioning navigation method and system | |
| CN115147813A (en) | Object space feature-based sparse point cloud processing method, system, device and medium | |
| CN114693862A (en) | Three-dimensional point cloud data model reconstruction method, target re-identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |