CN113343835B - Object identification method and system suitable for emergency rescue and storage medium - Google Patents
Object identification method and system suitable for emergency rescue and storage medium Download PDFInfo
- Publication number
- CN113343835B CN113343835B CN202110616866.5A CN202110616866A CN113343835B CN 113343835 B CN113343835 B CN 113343835B CN 202110616866 A CN202110616866 A CN 202110616866A CN 113343835 B CN113343835 B CN 113343835B
- Authority
- CN
- China
- Prior art keywords
- dimensional data
- data point
- point set
- emergency rescue
- calculation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Alarm Systems (AREA)
Abstract
The invention belongs to the technical field of emergency rescue, and particularly relates to an object identification method, a system and a storage medium suitable for emergency rescue, wherein the object identification method comprises the following steps: s1, acquiring a three-dimensional data set of an object in an emergency rescue scene; s2, performing clustering analysis processing on the three-dimensional data set; s3, carrying out segmentation processing on the three-dimensional data point group obtained through the clustering analysis processing; s4, calculating the three-dimensional data point set obtained by the segmentation processing; s5, object identification processing is carried out according to the result data of calculation processing of the three-dimensional data point set, the three-dimensional data of the object in the emergency rescue site are collected according to the laser radar technology, and the purpose of quickly identifying the distressed person in the complex emergency rescue site is achieved through processing and analyzing the collected three-dimensional data.
Description
Technical Field
The invention belongs to the technical field of emergency rescue, and particularly relates to an object identification method, system and storage medium suitable for emergency rescue.
Background
Emergency rescue generally refers to a rescue aiming at sudden and destructiveEmergency eventBy adopting activities and plans of prevention, preparation, response and recovery, according to different types of emergencies, emergency rescue is divided into traffic emergency rescue, fire emergency rescue, earthquake emergency rescue, factory and mine emergency rescue, family emergency rescue and the like, emergency rescue sites under various conditions often need to quickly identify and locate the persons in distress in complex environments, for example, outdoor sports enthusiasts are in danger in the field, when outdoor rescue teams search and rescue the persons in distress in the field, the positions of the persons in distress are usually determined by a manual carpet type search mode or a rescue helicopter search mode, when the manual carpet type search is carried out, the range needing to be searched is often large, a large amount of manpower and material resources are spent, rescue persons in partial areas in the field can not arrive, when the rescue helicopter searches, the positions of the persons in distress need to be observed manually, so that the problem of low search and rescue efficiency exists.
Disclosure of Invention
The invention aims to provide an object identification method, system and storage medium suitable for emergency rescue, which collect three-dimensional data of an object in an emergency rescue site by means of a laser radar technology and achieve the purpose of quickly identifying a person in distress in a complex emergency rescue site by processing and analyzing the collected three-dimensional data.
In order to achieve the purpose, the invention provides the following technical scheme:
an object identification method suitable for emergency rescue is realized by the following steps:
s1, acquiring a three-dimensional data set of an object in an emergency rescue scene;
s2, performing clustering analysis processing on the three-dimensional data set;
s3, carrying out segmentation processing on the three-dimensional data point group obtained through the clustering analysis processing;
s4, calculating the three-dimensional data point set obtained by the segmentation processing;
and S5, performing object recognition processing by depending on the result data of the calculation processing of the three-dimensional data point set.
As a preferred technical solution of the present invention, in step S2, the three-dimensional data set of the object in the emergency rescue scene is subjected to cluster analysis, and the three-dimensional data point groups of different objects are obtained by performing cluster analysis on the three-dimensional data set.
As a preferred embodiment of the present invention, the step S3 of segmenting the three-dimensional data point group obtained by the cluster analysis processing specifically includes the following steps:
s31, establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
s32, dividing the data layer of the data cube;
and S33, dividing the data areas of the data layers of the data cube.
As a preferable embodiment of the present invention, the step S4 of performing calculation processing on each three-dimensional data point set obtained by dividing the three-dimensional data point group of the object specifically includes the following steps:
s41, calculating the size of the three-dimensional data point set;
s42, calculating the position of the three-dimensional data point set;
s43, calculating the position relation of the three-dimensional data point set;
the invention also provides an object identification system suitable for emergency rescue, which comprises the following modules:
the emergency rescue system comprises a first module, a second module and a third module, wherein the first module is used for acquiring a three-dimensional data set of an object in an emergency rescue scene;
the second module is used for carrying out clustering analysis processing on the three-dimensional data set;
the third module is used for segmenting the three-dimensional data point group obtained by clustering analysis, and specifically comprises the following units:
the first unit is used for establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
the second unit is used for dividing the data layer of the data cube;
a third unit, configured to perform calculation of a positional relationship for the three-dimensional data point set;
a fourth module, configured to perform calculation processing on the three-dimensional data point set obtained through the segmentation processing, and specifically include the following units:
a fourth unit, configured to perform size calculation on the three-dimensional data point set;
a fifth unit, configured to perform center position calculation on the three-dimensional data point set;
a sixth unit, configured to perform calculation of a positional relationship on the three-dimensional data point set;
and the fifth module is used for identifying the object by depending on the result data of the calculation processing of the three-dimensional data point set.
The present invention also provides a storage medium having stored therein instructions executable by an object identification system for emergency rescue, the instructions being executable by a processor included in an object identification system for emergency rescue to implement an object identification method for emergency rescue as described in any one of the above.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides an object identification method suitable for emergency rescue, which can realize the purpose of quickly identifying the distressed persons in a complicated emergency rescue site, and solves the problems that in the prior art, when artificial carpet type search is carried out, the required search range is often large, a large amount of manpower and material resources are consumed, rescue workers in partial areas of the emergency rescue site cannot reach, when the rescue helicopter is used for searching, the positions of the distressed persons need to be observed manually, the search and rescue efficiency is low, and the like.
2. The invention obtains three-dimensional data sets of different objects in an emergency rescue site through a laser radar scanning technology, carries out cluster analysis on the three-dimensional data sets to obtain three-dimensional data point groups of the different objects, then establishes a data cube of the three-dimensional data point groups, and carries out data layer division on the data cube in order to improve the identification precision of the three-dimensional data point groups of the objects, divides each data layer into each data area, namely each three-dimensional data point set, then carries out calculation processing on the three-dimensional data point sets to obtain characteristic data of the three-dimensional data point sets for subsequent identification of object types, particularly calculates the size data, the position data and the position relation data of the three-dimensional data point sets adjacent to the three-dimensional data point sets, wherein the size of the three-dimensional data point sets is calculated by calculating the standard deviation value of the three-dimensional data points on a coordinate axis, the method can ensure that the size data of the three-dimensional data point set can be calculated with higher accuracy even if the three-dimensional data point set contains less three-dimensional data points. On the whole, the invention can realize the purpose of quickly identifying the distressed person in a complex emergency rescue site, and has high identification precision and good reliability.
Drawings
Fig. 1 is an overall step flow diagram of an object identification method suitable for emergency rescue according to the present invention;
FIG. 2 is a flowchart illustrating the steps of the present invention for segmenting a three-dimensional data point group;
FIG. 3 is a flow chart of the steps of the present invention for performing a computational process on a three-dimensional data point set.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides an object identification method suitable for emergency rescue, which is specifically implemented by the following steps:
s1, acquiring a set of three-dimensional data of objects in the emergency rescue scene;
s2, carrying out cluster analysis processing on the three-dimensional data set;
s3, carrying out segmentation processing on the three-dimensional data point group obtained through the clustering analysis processing;
s4, calculating the three-dimensional data point set obtained by the segmentation processing;
and S5, performing object recognition processing according to the result data of the calculation processing of the three-dimensional data point set.
Further, in step S1, three-dimensional data of an object in the emergency rescue scene is collected by a laser radar technology, and the three-dimensional data of a plurality of different types of objects form a set of three-dimensional data, wherein the laser radar device uses laser as a signal source, pulse laser emitted by a laser device strikes various objects such as trees, roads, bridges, buildings and the like on the ground to cause the pulse laser to be scattered, a part of scattered light waves are reflected to a receiver of the laser radar, the distance from the laser radar to a target point is obtained by calculation according to a laser ranging principle, coordinate data of the target can be obtained by using the radar as an origin, and the pulse laser constantly scans the target to obtain three-dimensional data of all target points on the target.
Further, in step S2, the three-dimensional data of the object in the emergency rescue scene is collected and analyzed, and the three-dimensional data of the same object is collected together by performing cluster analysis on the three-dimensional data to form a three-dimensional data point group, and the three-dimensional data point group is used for identifying the type of the object subsequently to determine the location of the victim, wherein a plurality of different clustering algorithms may be selected to perform cluster analysis, for example, three-dimensional data points having distances between three-dimensional data points smaller than a specific value are divided into one class, and further, a K-Means clustering algorithm, a mean shift clustering algorithm, a density-based clustering algorithm, a maximum expectation algorithm using a gaussian mixture model, and the like may be selected to perform cluster analysis on the three-dimensional data.
Further, as shown in fig. 2, in order to improve the accuracy of identifying the three-dimensional data point group of the object, the step S3 of performing segmentation processing on the three-dimensional data point group obtained through the cluster analysis processing specifically includes the following steps:
s31, establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
s32, dividing a data layer of the data cube;
and S33, dividing the data areas of the data layers of the data cube.
Wherein, in step S31, a three-dimensional coordinate system is established, and a three-dimensional data point group of the object is mapped to the three-dimensional coordinate system, and an external cuboid of the three-dimensional data point group is determined using coordinate value data of a three-dimensional data point having a maximum coordinate value on each coordinate axis and coordinate value data of a three-dimensional data point having a minimum coordinate value on each coordinate axis, that is, all three-dimensional data points constituting the object are distributed inside the external cuboid; in step S32, according to the difference in height of the object, the external cuboid of the three-dimensional data point group is divided into a plurality of different data layers in the horizontal direction, and three-dimensional data points constituting the object are distributed on each data layer; in step S33, the data area division is continued for each data layer according to the number of data layers divided for the circumscribed cuboid, and a plurality of three-dimensional data point sets are formed.
Further, as shown in fig. 3, the step S4 of performing calculation processing on each three-dimensional data point set obtained by the segmentation processing on the three-dimensional data point group of the object specifically includes the following steps:
s41, calculating the size of the three-dimensional data point set;
s42, calculating the position of the three-dimensional data point set;
and S43, calculating the position relation of the three-dimensional data point set.
Wherein, in step S41, based on each three-dimensional data point set obtained in step S3, a standard deviation value of each three-dimensional data point included therein on the X coordinate axis and the Y coordinate axis is calculated, a rectangular area defined by the standard deviation value on the X coordinate axis and the standard deviation value on the Y coordinate axis represents a different distribution of the three-dimensional data points as a result of the size calculation of the three-dimensional data point set, i.e., a larger rectangular area means a more dispersed three-dimensional data point, a smaller rectangular area means a more dense three-dimensional data point, the size of the three-dimensional data point set is calculated by calculating the standard deviation value of the three-dimensional data points on the coordinate axis, so that the size of the three-dimensional data point set can be calculated with high accuracy even if the three-dimensional data point set contains less three-dimensional data points, and the three-dimensional data point set is used for identifying the type of an object subsequently;
in step S42, based on each three-dimensional data point set obtained in step S3, the barycentric coordinates of each three-dimensional data point included therein on the plane defined by the X coordinate axis and the Y coordinate axis are calculated as the result of position calculation for the three-dimensional data point set, and used for the subsequent identification processing of the type of the object;
in step S43, the positional relationship between the three-dimensional data point sets is calculated to further improve the accuracy of recognition of the three-dimensional data point groups of the object, first, a calculation basis rectangle for each three-dimensional data point set is constructed based on the standard deviation values of the three-dimensional data points included in each three-dimensional data point set calculated in step S41 on the X coordinate axis and the Y coordinate axis, that is, a calculation basis rectangle is associated with each three-dimensional data point set on each data layer of the data cube of the three-dimensional data point group of the object at this time to calculate the positional relationship between the three-dimensional data point sets, and then, one vertex of the calculation basis rectangle for the one three-dimensional data point set is connected to the corresponding vertex of the calculation basis rectangle for the three-dimensional data point set adjacent to the three-dimensional data point set above or below the Z coordinate axis by a straight line, and calculating the included angle between the straight line and the normal of the plane where the three-dimensional data point set is located, wherein the included angle represents the position relationship between different three-dimensional data point sets, and finally, respectively calculating the position relationship between other vertexes of the calculation basic rectangle of the three-dimensional data point set and the three-dimensional data point set adjacent to the vertexes, and calculating the position relationship between other three-dimensional data point sets by using the method for subsequently identifying the type of the object.
Further, in step S5, the object recognition processing is performed based on the result data of the calculation processing performed on the three-dimensional data point set, and first, a standard model to be used for object recognition is selected, the number of data layers of the standard model is matched with the number of data layers of the data cube of the three-dimensional data point group of the object divided in step S3, and then, the size data, the position data, and the positional relationship data of the three-dimensional data point set adjacent thereto calculated in step S4 are subjected to data conversion processing, and the degree of matching with the standard model of the object recognition is calculated, and when the calculation result is larger than a set threshold value, it is possible to determine the article type corresponding to the three-dimensional data point group.
In summary, the invention obtains three-dimensional data sets of different objects in an emergency rescue scene through a laser radar scanning technology, performs cluster analysis on the three-dimensional data sets to obtain three-dimensional data point groups of the different objects, then establishes a data cube of the three-dimensional data point groups, and in order to improve the identification precision of the three-dimensional data point groups of the objects, the invention divides data layers of the data cube, divides each data layer into each data area, namely each three-dimensional data point set, then performs calculation processing on the three-dimensional data point sets to obtain characteristic data of the three-dimensional data point sets for subsequent identification of object types, specifically calculates size data, position data and position relation data of the three-dimensional data point sets adjacent to the three-dimensional data point sets, wherein the size of the three-dimensional data point sets is calculated by calculating standard deviation values of the three-dimensional data points on coordinate axes, the method can ensure that the size data of the three-dimensional data point set can be calculated with higher accuracy even if the three-dimensional data point set contains less three-dimensional data points. On the whole, the invention can realize the purpose of quickly identifying the distressed person in a complex emergency rescue site, and has high identification precision and good reliability.
It should be noted that the object identification method suitable for emergency rescue provided by the invention can be used in emergency rescue sites under various different conditions such as traffic emergency rescue, fire emergency rescue, earthquake emergency rescue, plant emergency rescue and the like.
The invention also provides an object identification system suitable for emergency rescue, which comprises the following modules:
the emergency rescue system comprises a first module, a second module and a third module, wherein the first module is used for acquiring a three-dimensional data set of an object in an emergency rescue scene;
the second module is used for carrying out clustering analysis processing on the three-dimensional data set;
the third module is used for segmenting the three-dimensional data point group obtained by clustering analysis, and specifically comprises the following units:
the first unit is used for establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
the second unit is used for dividing the data layer of the data cube;
the third unit is used for calculating the position relation of the three-dimensional data point set;
a fourth module, configured to perform calculation processing on the three-dimensional data point set obtained through the segmentation processing, and specifically include the following units:
a fourth unit, configured to perform size calculation on the three-dimensional data point set;
a fifth unit, configured to perform center position calculation on the three-dimensional data point set;
a sixth unit, configured to calculate a positional relationship of the three-dimensional data point set;
and the fifth module is used for identifying the object by depending on the result data of the calculation processing of the three-dimensional data point set.
The present invention also provides a storage medium having stored therein instructions executable by an object identification system for emergency rescue, the instructions being executable by a processor included in an object identification system for emergency rescue to implement an object identification method for emergency rescue as described in any one of the above.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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.
It will be appreciated by those skilled in the art that the foregoing method embodiments of the invention may be implemented as a computer program product. Thus, for example, 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.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. An object identification method suitable for emergency rescue is characterized by comprising the following steps:
s1, acquiring a three-dimensional data set of an object in an emergency rescue scene;
s2, performing clustering analysis processing on the three-dimensional data set;
s3, carrying out segmentation processing on the three-dimensional data point group obtained through the clustering analysis processing;
s4, calculating the three-dimensional data point set obtained by the segmentation processing;
s5, depending on the result data of the calculation processing of the three-dimensional data point set, carrying out object identification processing;
in S4, the calculating process of each three-dimensional data point set obtained by segmenting the three-dimensional data point group of the object specifically includes the following steps:
s41, calculating the size of the three-dimensional data point set;
s42, calculating the position of the three-dimensional data point set;
s43, calculating the position relation of the three-dimensional data point set;
in step S41, based on each three-dimensional data point set obtained in step S3, a standard deviation value of each three-dimensional data point included in the three-dimensional data point set on the X coordinate axis and the Y coordinate axis is calculated, and a rectangular area defined by the standard deviation value on the X coordinate axis and the standard deviation value on the Y coordinate axis is a result of performing size calculation on the three-dimensional data point set;
in step S42, based on each three-dimensional data point set obtained in step S3, the barycentric coordinates of each three-dimensional data point included in the three-dimensional data point set on the plane defined by the X coordinate axis and the Y coordinate axis are calculated as the result of calculating the position of the three-dimensional data point set;
in step S43, the positional relationship between the three-dimensional data point sets is calculated, first, a calculation basis rectangle for each three-dimensional data point set is constructed based on the standard deviation values of the three-dimensional data points included in each three-dimensional data point set calculated in step S41 on the X coordinate axis and the Y coordinate axis, that is, a calculation basis rectangle is associated with each three-dimensional data point set on each data layer of the data cube of the three-dimensional data point cluster of the object at that time, then, one vertex of the calculation basis rectangle for one three-dimensional data point set is connected to the corresponding vertex of the calculation basis rectangle for the three-dimensional data point set adjacent to the vertex above or below the Z coordinate axis by a straight line, and the included angle between the straight line and the normal line of the plane in which the one three-dimensional data point set is located is calculated, the included angle represents the positional relationship between different three-dimensional data point sets, and finally, respectively calculating the position relation between other vertexes of the calculation basic rectangle of the three-dimensional data point set and the three-dimensional data point sets adjacent to the vertexes.
2. The object identification method suitable for emergency rescue according to claim 1, wherein in S2, the obtained three-dimensional data set of the object in the emergency rescue scene is subjected to cluster analysis, and the three-dimensional data point groups of different objects are obtained by performing cluster analysis on the three-dimensional data set.
3. The object recognition method suitable for emergency rescue according to claim 1, wherein the step of segmenting the three-dimensional data point group obtained by the clustering analysis in S3 specifically comprises the following steps:
s31, establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
s32, dividing the data layer of the data cube;
and S33, dividing the data areas of the data layers of the data cube.
4. An object identification system suitable for emergency rescue for implementing a method according to any one of claims 1-3, characterized in that it comprises the following modules:
the emergency rescue system comprises a first module, a second module and a third module, wherein the first module is used for acquiring a three-dimensional data set of an object in an emergency rescue scene;
the second module is used for carrying out clustering analysis processing on the three-dimensional data set;
the third module is used for segmenting the three-dimensional data point group obtained by clustering analysis, and specifically comprises the following units:
the first unit is used for establishing a data cube of the three-dimensional data point group according to the three-dimensional data point group;
the second unit is used for dividing the data layer of the data cube;
a third unit, configured to perform calculation of a positional relationship for the three-dimensional data point set;
a fourth module, configured to perform calculation processing on the three-dimensional data point set obtained through the segmentation processing, and specifically include the following units:
a fourth unit, configured to perform size calculation on the three-dimensional data point set;
a fifth unit, configured to perform center position calculation on the three-dimensional data point set;
a sixth unit, configured to perform calculation of a positional relationship on the three-dimensional data point set;
and the fifth module is used for identifying the object by depending on the result data of the calculation processing of the three-dimensional data point set.
5. A storage medium having stored therein instructions executable by the system of claim 4, wherein the instructions are adapted to implement an object identification method suitable for emergency rescue according to any one of claims 1-3 when executed by a processor comprised by the system of claim 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110616866.5A CN113343835B (en) | 2021-06-02 | 2021-06-02 | Object identification method and system suitable for emergency rescue and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110616866.5A CN113343835B (en) | 2021-06-02 | 2021-06-02 | Object identification method and system suitable for emergency rescue and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113343835A CN113343835A (en) | 2021-09-03 |
| CN113343835B true CN113343835B (en) | 2022-04-15 |
Family
ID=77472886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110616866.5A Active CN113343835B (en) | 2021-06-02 | 2021-06-02 | Object identification method and system suitable for emergency rescue and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343835B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107192994A (en) * | 2016-03-15 | 2017-09-22 | 山东理工大学 | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method |
| CN108983248A (en) * | 2018-06-26 | 2018-12-11 | 长安大学 | It is a kind of that vehicle localization method is joined based on the net of 3D laser radar and V2X |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239299B (en) * | 2013-06-06 | 2017-05-10 | 富士通株式会社 | Three-dimensional model retrieval method and apparatus |
| CN105866790B (en) * | 2016-04-07 | 2018-08-10 | 重庆大学 | A kind of laser radar obstacle recognition method and system considering lasing intensity |
| CN106570454B (en) * | 2016-10-10 | 2019-06-11 | 同济大学 | Pedestrian traffic parameter extracting method based on mobile laser scanning |
| US10108867B1 (en) * | 2017-04-25 | 2018-10-23 | Uber Technologies, Inc. | Image-based pedestrian detection |
| CN107239746B (en) * | 2017-05-16 | 2020-08-14 | 东南大学 | Obstacle identification and tracking method for road rescue safety monitoring |
| CN109993192B (en) * | 2018-01-03 | 2024-07-19 | 北京京东乾石科技有限公司 | Target object identification method and device, electronic equipment and storage medium |
| JP7196412B2 (en) * | 2018-04-09 | 2022-12-27 | 株式会社デンソー | Object recognition device and object recognition method |
| US11514682B2 (en) * | 2019-06-24 | 2022-11-29 | Nvidia Corporation | Determining weights of points of a point cloud based on geometric features |
| CN111580131B (en) * | 2020-04-08 | 2023-07-07 | 西安邮电大学 | Method for identifying vehicles on expressway by three-dimensional laser radar intelligent vehicle |
| CN111540201B (en) * | 2020-04-23 | 2021-03-30 | 山东大学 | Vehicle queuing length real-time estimation method and system based on roadside laser radar |
| CN112150501A (en) * | 2020-09-18 | 2020-12-29 | 浙江吉利控股集团有限公司 | Target detection method, device and equipment based on laser radar and storage medium |
-
2021
- 2021-06-02 CN CN202110616866.5A patent/CN113343835B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107192994A (en) * | 2016-03-15 | 2017-09-22 | 山东理工大学 | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method |
| CN108983248A (en) * | 2018-06-26 | 2018-12-11 | 长安大学 | It is a kind of that vehicle localization method is joined based on the net of 3D laser radar and V2X |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113343835A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108801268B (en) | Target object positioning method and device and robot | |
| Forlani et al. | C omplete classification of raw LIDAR data and 3D reconstruction of buildings | |
| Chen et al. | Rapid urban roadside tree inventory using a mobile laser scanning system | |
| US20210274358A1 (en) | Method, apparatus and computer program for performing three dimensional radio model construction | |
| CN110794413B (en) | Method and system for detecting power line of point cloud data of laser radar segmented by linear voxels | |
| CN112305559A (en) | Power transmission line distance measuring method, device and system based on ground fixed-point laser radar scanning and electronic equipment | |
| Kim et al. | Urban scene understanding from aerial and ground LIDAR data | |
| CN112344869B (en) | Iron tower deformation monitoring method and system based on side fitting | |
| US11734883B2 (en) | Generating mappings of physical spaces from point cloud data | |
| Lamon et al. | Environmental modeling with fingerprint sequences for topological global localization | |
| Zheng et al. | Pole-like object extraction from mobile lidar data | |
| Xu et al. | Separation of wood and foliage for trees from ground point clouds using a novel least-cost path model | |
| CN110276379B (en) | Disaster information rapid extraction method based on video image analysis | |
| KR101221755B1 (en) | Method for identifying reflectivity cells associated with severe weather | |
| Yin et al. | A failure detection method for 3D LiDAR based localization | |
| CN113343835B (en) | Object identification method and system suitable for emergency rescue and storage medium | |
| KR102548786B1 (en) | System, method and apparatus for constructing spatial model using lidar sensor(s) | |
| Zhao et al. | Scalable building height estimation from street scene images | |
| Ghosh et al. | Heuristical feature extraction from LiDAR data and their visualization | |
| Hu et al. | Trunk model establishment and parameter estimation for a single tree using multistation terrestrial laser scanning | |
| CN112669461A (en) | Airport clearance safety detection method and device, electronic equipment and storage medium | |
| Hujebri et al. | Automatic building extraction from lidar point cloud data in the fusion of orthoimage | |
| Ahmed et al. | Modeling complex building structure (LoD2) using image-based point cloud | |
| US11320519B2 (en) | Method and system for processing LiDAR data | |
| Reddy | Automated Estimation of Forest Inventories using Terrestrial LiDAR |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |