CN115372995A - Laser radar target detection method and system based on European clustering - Google Patents
Laser radar target detection method and system based on European clustering Download PDFInfo
- Publication number
- CN115372995A CN115372995A CN202210892986.2A CN202210892986A CN115372995A CN 115372995 A CN115372995 A CN 115372995A CN 202210892986 A CN202210892986 A CN 202210892986A CN 115372995 A CN115372995 A CN 115372995A
- Authority
- CN
- China
- Prior art keywords
- clustering
- distance
- point cloud
- cloud data
- euclidean
- 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
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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention belongs to the technical field of intelligent driving, and provides a laser radar target detection method and a system based on Euclidean clustering, wherein the method comprises the following steps: acquiring point cloud data of obstacles in a vehicle detection range based on a laser radar; dividing the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance section areas; determining the optimal clustering distance in the different distance segment intervals as a clustering distance threshold value according to the different distance segment intervals; performing neighborhood search based on a clustering distance threshold value in a corresponding distance segment interval according to the distance segment interval of the obstacle point cloud data; performing target detection on an obstacle in front of the vehicle based on the neighborhood search result; according to the invention, the point cloud clustering threshold in the current distance interval is calculated according to the point cloud data actually shot on the obstacle, so that the clustering thresholds in different distance intervals can be flexibly changed, the problem of uneven distribution of the point cloud data is solved, and the near and far obstacles can be quickly and accurately detected.
Description
Technical Field
The invention belongs to the technical field of intelligent driving, and particularly relates to a laser radar target detection method and system based on Euclidean clustering.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In the process of identifying the obstacle in front of the vehicle by using the three-dimensional laser radar, the whole point cloud can be searched and clustered by using the KD-tree according to the distance index after the distance index is determined by using the traditional Euclidean clustering segmentation, so that a high requirement is put forward for selecting the distance threshold, that is, the traditional Euclidean clustering method cannot accurately detect the obstacle at far and near at the same time, so that an error clustering result is caused, and the condition of false detection or missing detection of the obstacle is easy to occur.
The traditional Euclidean clustering algorithm has applicability to measurement data obtained by different means, and has good point cloud segmentation effect, but because a fixed distance threshold needs to be set, and most data acquired by vehicles are uneven in density, the detection accuracy of the algorithm on obstacles is low when the algorithm processes point clouds acquired by a vehicle-mounted three-dimensional laser radar.
Disclosure of Invention
Aiming at the defects of the traditional Euclidean clustering algorithm in processing three-dimensional laser radar point clouds, obstacles are arranged in different detection distances of a laser radar, and point cloud clustering thresholds in current distance intervals are analyzed and calculated according to point cloud data actually shot on the obstacles, so that the clustering thresholds in different distance intervals can be flexibly changed, the problem of non-uniform point cloud data distribution is solved, and near and far obstacles can be quickly and accurately detected.
According to some embodiments, a first aspect of the present invention provides a laser radar target detection method based on euclidean clustering, which adopts the following technical solutions:
a laser radar target detection method based on Euclidean clustering comprises the following steps:
acquiring point cloud data of obstacles in a vehicle detection range based on a laser radar;
dividing the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance sections;
determining the optimal clustering distance in the different distance segment intervals as a clustering distance threshold value according to the different distance segment intervals;
performing neighborhood search based on a clustering distance threshold value in a corresponding distance segment interval according to the distance segment interval of the obstacle point cloud data;
and performing target detection on the obstacle in front of the vehicle based on the neighborhood search result.
Further, the determining the optimal clustering distance in the different distance segment intervals according to the different distance segment intervals as a clustering distance threshold includes:
determining an adjusting parameter through detecting and analyzing the effectiveness of targets in different distance section intervals of the laser radar;
and determining a clustering distance threshold according to the adjusting parameters and the position of the obstacle.
Further, determining a clustering distance threshold according to the adjustment parameter and the position of the obstacle, specifically:
in the formula: d is a clustering distance threshold, X i And Y i The coordinate of the point is under a vehicle coordinate system carrying the laser radar; delta is a regulating parameter.
Furthermore, the selection of the adjusting parameters is realized through the effectiveness detection analysis of targets in different distance intervals of the laser radar, the larger the detection distance of the laser radar is, the worse the effectiveness detection of the laser radar is, the larger the value of the adjusting parameters is, and the larger the clustering distance threshold is.
Further, the performing neighborhood search according to the distance segment interval of the obstacle point cloud data based on the clustering distance threshold in the corresponding distance segment interval includes:
establishing a KD-tree data structure based on point cloud data of obstacles in different distance intervals;
establishing an empty clustering list and a queue to be processed;
adding each point in the point cloud data of the obstacles in the different distance intervals into a queue to be processed;
performing neighborhood search on each point in the queue to be processed to obtain all clustering points of the point;
and calculating the Euclidean distance between each clustering point and the point, and dividing the clustering points of which the Euclidean distances are smaller than the clustering distance threshold value into the same class to obtain a complete clustering list.
Further, according to the complete cluster list, all categories are screened to obtain a final neighborhood search result, which includes:
calculating Euclidean distances between all clusters in the complete cluster list;
merging clusters with Euclidean distances smaller than a clustering distance threshold into the same class;
and obtaining a final cluster list after neighborhood searching.
Further, the euclidean distances between all clusters in the cluster list after the neighborhood search are all greater than the cluster distance threshold.
According to some embodiments, a second aspect of the present invention provides a laser radar target detection system based on euclidean clustering, which adopts the following technical solutions:
a laser radar target detection system based on Euclidean clustering comprises:
a data acquisition module configured to acquire point cloud data of an obstacle within a vehicle detection range based on a laser radar;
the data segmentation module is configured to segment the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance section areas;
the clustering threshold determining module is configured to determine the optimal clustering distance in different distance segment intervals according to the different distance segment intervals as a clustering distance threshold;
the neighborhood searching module is configured to perform neighborhood searching based on a clustering distance threshold value in a corresponding distance section interval according to the distance section interval of the obstacle point cloud data;
and the target detection module is configured to perform target detection on the obstacle in front of the vehicle based on the neighborhood search result.
According to some embodiments, a third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, realizes the steps of a method for detecting an object in a lidar based on euclidean clustering as described above with respect to the first aspect.
According to some embodiments, a fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of a method for detecting an object in a lidar based on euclidean clustering as defined in the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, aiming at the defects of the traditional Euclidean clustering algorithm in processing the three-dimensional laser radar point cloud, the obstacles are arranged in different detection distances of the laser radar, and the clustering distance threshold is analyzed according to the point cloud data actually shot on the obstacles, so that the clustering distance threshold in different distance intervals can be flexibly changed, the problem of uneven point cloud data distribution is solved, the obstacles at near and far positions are quickly and accurately detected, and the probability of misjudgment is reduced.
The Euclidean clustering algorithm for partitioning based on the distance solves the problem that the obstacle detection success rate is low due to uneven point cloud density in the Euclidean clustering algorithm.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flowchart of a laser radar target detection method based on euclidean clustering according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Interpretation of terms
Laser radar: a radar system for detecting characteristic quantities such as position, speed and the like of a target by emitting a laser beam;
euclidean clustering: a clustering algorithm based on Euclidean distance measurement.
Example one
As shown in fig. 1, this embodiment provides a laser radar target detection method based on euclidean clustering, which includes the following steps:
acquiring point cloud data of obstacles in a vehicle detection range based on a laser radar;
dividing the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance sections;
determining the optimal clustering distance in the different distance segment intervals as a clustering distance threshold value according to the different distance segment intervals;
performing neighborhood search based on a clustering distance threshold value in a corresponding distance segment interval according to the distance segment interval of the obstacle point cloud data;
and performing target detection on the obstacle in front of the vehicle based on the neighborhood search result.
Specifically, the method described in this embodiment specifically includes:
step S1: acquiring point cloud data of obstacles in a detection range based on a laser radar;
step S2: dividing the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance sections;
and step S3: determining the optimal clustering distance in different distance segment intervals according to the different distance segment intervals as a clustering distance threshold, wherein the optimal clustering distance comprises the following steps:
determining an adjusting parameter through detecting and analyzing the effectiveness of targets in different distance section intervals of the laser radar;
determining a clustering distance threshold according to the adjusting parameters and the position of the obstacle, specifically:
in the formula: d is a clustering distance threshold, X i And Y i The coordinate of the point is under a vehicle coordinate system carrying the laser radar; delta is a regulating parameter.
The selection of the adjusting parameters is based on the effectiveness detection analysis of targets in different distance intervals of the laser radar, the larger the detection distance of the laser radar is, the worse the effectiveness detection of the laser radar is, the larger the value of the adjusting parameters is, and the larger the clustering distance threshold is.
And step S4: after a distance index is determined, searching and clustering are carried out on the whole point cloud by using a KD-tree according to the index in the traditional Euclidean clustering segmentation, a high requirement is put on the selection of a distance threshold, misjudgment or missed judgment is often caused by dense point cloud at a near position and sparse at a far position, the problem is solved by a threshold-changing segmentation method based on a detection distance interval, and the specific process is as follows:
according to the distance segment interval of the obstacle point cloud data, based on the clustering distance threshold value in the corresponding distance segment interval, performing neighborhood search, including:
inputting the collected laser radar point cloud Q and establishing a KD-tree data structure;
establishing an empty clustering list D and a queue L to be processed, and setting each point Q in Q i Adding the queue into a queue L;
for each Q i E.g. I, making neighborhood search, storing the searched points
In (1). For the
Are calculated from each of the points and point Q is calculated i The Euclidean distance of (d) is smaller than the point of the clustering distance threshold value d and Q i After being divided into the same type, the cluster list D' is stored into D;
after the above operations are performed for each point in L, and for any Q i ∈L：Q i E.g. D ', calculating Euclidean distance between all clusters in D', merging the clusters smaller than the distance threshold into the same cluster until the Euclidean distance between all clusters is larger than the cluster distance threshold D, deleting the clusters with the data point number exceeding the limit value in the point cloud to obtain the final neighborhoodSearched cluster list D' Terminal 。
For a point a in the point cloud, a clustering distance threshold d of a certain property needs to be defined, points smaller than the threshold are combined into one class, and the distances between the remaining classes are continuously calculated in an iterative manner until the distances between all the classes are larger than the threshold, so that the whole clustering process is completed.
In this embodiment, the euclidean distance is used as the distance index, and the euclidean distance between the ith class and the jth class containing n interior points is:
X i1 representing position coordinates representing the 1 st point in the ith class; x j1 Representing the position coordinates representing the 1 st point in the jth class; x in Representing the position coordinates of the nth point in the ith class; x in Indicating the position coordinates of the nth point in the jth class.
Step S5: and performing target detection on the obstacle in front of the vehicle based on the neighborhood search result.
Example two
The embodiment provides a laser radar target detection system based on european style clustering, includes:
a data acquisition module configured to acquire point cloud data of an obstacle within a vehicle detection range based on a laser radar;
the data segmentation module is configured to segment the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance section zones;
the clustering threshold determining module is configured to determine the optimal clustering distance in different distance segment intervals according to the different distance segment intervals as a clustering distance threshold;
the neighborhood searching module is configured to perform neighborhood searching based on a clustering distance threshold value in a corresponding distance section interval according to the distance section interval of the obstacle point cloud data;
and the target detection module is configured to perform target detection on the obstacle in front of the vehicle based on the neighborhood search result.
The modules are the same as the corresponding steps in the implementation example and application scenarios, but are not limited to the disclosure of the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the description of each embodiment has an emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions in other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in a method for detecting a laser radar target based on euclidean clustering as described in the first embodiment above.
Example four
The present embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps in the method for detecting a lidar target based on euclidean clustering as described in the first embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A laser radar target detection method based on Euclidean clustering is characterized by comprising the following steps:
acquiring point cloud data of obstacles in a vehicle detection range based on a laser radar;
dividing the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance sections;
determining the optimal clustering distance in the different distance segment intervals as a clustering distance threshold value according to the different distance segment intervals;
according to the distance segment interval of the obstacle point cloud data, based on the clustering distance threshold value in the corresponding distance segment interval, performing neighborhood search;
and performing target detection on the obstacle in front of the vehicle based on the neighborhood search result.
2. The method for detecting the laser radar target based on the euclidean clustering as claimed in claim 1, wherein the determining the optimal clustering distance within the different distance segment intervals as the clustering distance threshold according to the different distance segment intervals comprises:
determining an adjusting parameter through detecting and analyzing the effectiveness of targets in different distance section intervals of the laser radar;
and determining a clustering distance threshold according to the adjusting parameters and the position of the obstacle.
3. The method for detecting the lidar target based on the euclidean cluster as claimed in claim 2, wherein the clustering distance threshold is determined according to the adjustment parameter and the position of the obstacle, and specifically comprises:
in the formula: d is a clustering distance threshold, X i And Y i The coordinate of the point is under a vehicle coordinate system carrying the laser radar; delta is a regulating parameter.
4. The method as claimed in claim 2, wherein the adjustment parameter is selected by performing validity detection analysis on the targets in the range of different distances of the lidar, and the larger the detection distance of the lidar is, the worse the validity detection of the lidar is, the larger the value of the adjustment parameter is, and thus the larger the threshold value of the clustering distance is.
5. The laser radar target detection method based on Euclidean clustering as claimed in claim 1, wherein the performing of neighborhood search according to the distance segment interval of the obstacle point cloud data based on the clustering distance threshold in the corresponding distance segment interval comprises:
establishing a KD-tree data structure based on point cloud data of obstacles in different distance intervals;
establishing an empty clustering list and a queue to be processed;
adding each point in the point cloud data of the obstacles in the different distance intervals into a queue to be processed;
performing neighborhood search on each point in the queue to be processed to obtain all clustering points of the point;
and calculating the Euclidean distance between each clustering point and the point, and dividing the clustering points of which the Euclidean distances are smaller than the clustering distance threshold value into the same class to obtain a complete clustering list.
6. The method for lidar target detection based on euclidean clustering of claim 5, wherein screening all categories according to the complete cluster list to obtain a final neighborhood search result comprises:
calculating Euclidean distances between all clusters in the complete cluster list;
merging clusters with Euclidean distances smaller than a cluster distance threshold value into the same class;
and obtaining a final cluster list after neighborhood searching.
7. The method of claim 6, wherein Euclidean distance between all clusters in the cluster list after neighborhood search is greater than a cluster distance threshold.
8. A laser radar target detection system based on Euclidean clustering is characterized by comprising:
a data acquisition module configured to acquire point cloud data of an obstacle within a vehicle detection range based on a laser radar;
the data segmentation module is configured to segment the point cloud data of the obstacles in the detection range according to the distance to obtain the point cloud data of the obstacles in different distance section zones;
the clustering threshold value determining module is configured to determine the optimal clustering distance in different distance segment intervals according to the different distance segment intervals as a clustering distance threshold value;
the neighborhood searching module is configured to perform neighborhood searching based on a clustering distance threshold value in a corresponding distance section interval according to the distance section interval of the obstacle point cloud data;
and the target detection module is configured to perform target detection on the obstacle in front of the vehicle based on the neighborhood search result.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of a method for euclidean cluster based lidar target detection as defined in any of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps in a method for euclidean cluster based lidar target detection according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210892986.2A CN115372995A (en) | 2022-07-27 | 2022-07-27 | Laser radar target detection method and system based on European clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210892986.2A CN115372995A (en) | 2022-07-27 | 2022-07-27 | Laser radar target detection method and system based on European clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115372995A true CN115372995A (en) | 2022-11-22 |
Family
ID=84064331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210892986.2A Pending CN115372995A (en) | 2022-07-27 | 2022-07-27 | Laser radar target detection method and system based on European clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115372995A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110046A (en) * | 2023-04-11 | 2023-05-12 | 北京五一视界数字孪生科技股份有限公司 | Method, device and equipment for determining data manifold instance |
| CN117148315A (en) * | 2023-10-31 | 2023-12-01 | 上海伯镭智能科技有限公司 | Unmanned automobile operation detection method and system |
-
2022
- 2022-07-27 CN CN202210892986.2A patent/CN115372995A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110046A (en) * | 2023-04-11 | 2023-05-12 | 北京五一视界数字孪生科技股份有限公司 | Method, device and equipment for determining data manifold instance |
| CN117148315A (en) * | 2023-10-31 | 2023-12-01 | 上海伯镭智能科技有限公司 | Unmanned automobile operation detection method and system |
| CN117148315B (en) * | 2023-10-31 | 2024-01-26 | 上海伯镭智能科技有限公司 | Unmanned automobile operation detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112526513B (en) | Millimeter wave radar environment map construction method and device based on clustering algorithm | |
| CN112308881B (en) | Ship multi-target tracking method based on remote sensing image | |
| CN115372995A (en) | Laser radar target detection method and system based on European clustering | |
| CN110161464B (en) | Radar multi-target clustering method and device | |
| CN111045008B (en) | Vehicle millimeter wave radar target identification method based on widening calculation | |
| CN113344019A (en) | K-means algorithm for improving decision value selection initial clustering center | |
| CN115496796B (en) | Method and system for measuring trunk volume through laser point cloud | |
| CN112034426B (en) | Radar signal processing method, device, computer equipment and storage medium | |
| CN112949519A (en) | Target detection method, device, equipment and storage medium | |
| CN117495891B (en) | Point cloud edge detection method and device and electronic equipment | |
| CN116310849A (en) | Tree point cloud monomerization extraction method based on three-dimensional morphological characteristics | |
| CN113008296A (en) | Method and vehicle control unit for detecting a vehicle environment by fusing sensor data on a point cloud plane | |
| CN112462442B (en) | Gravity magnetic potential field source position estimation method, system, medium, and electronic device | |
| CN112700469A (en) | Visual target tracking method and device based on ECO algorithm and target detection | |
| CN113077473A (en) | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| KR102361816B1 (en) | Method for detecting target and readable medium | |
| CN112508970B (en) | Point cloud data segmentation method and device | |
| CN110781963B (en) | K-means clustering-based aerial target clustering method | |
| CN116863325A (en) | Method for multiple target detection and related product | |
| CN111723797B (en) | Method and system for determining bounding box of three-dimensional target | |
| CN110363834B (en) | Point cloud data segmentation method and device | |
| CN114067224A (en) | Unmanned aerial vehicle cluster target number detection method based on multi-sensor data fusion | |
| CN112907574A (en) | Method, device and system for searching landing point of aircraft and storage medium | |
| CN110609561A (en) | Pedestrian tracking method and device, computer readable storage medium and robot |
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 |