CN109633685A - A kind of method and system based on laser radar obstruction detection state - Google Patents
A kind of method and system based on laser radar obstruction detection state Download PDFInfo
- Publication number
- CN109633685A CN109633685A CN201811396223.9A CN201811396223A CN109633685A CN 109633685 A CN109633685 A CN 109633685A CN 201811396223 A CN201811396223 A CN 201811396223A CN 109633685 A CN109633685 A CN 109633685A
- Authority
- CN
- China
- Prior art keywords
- laser radar
- default
- point cloud
- objective body
- state
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 31
- 238000012790 confirmation Methods 0.000 claims 3
- 230000003068 static effect Effects 0.000 claims 1
- 230000004888 barrier function Effects 0.000 abstract description 12
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005461 lubrication Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 208000010877 cognitive disease Diseases 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
Abstract
The present invention provides a kind of methods based on laser radar obstruction detection state, and to solve the problems, such as that barrier state recognition algorithm is complicated in the prior art, this method is comprising steps of S1: obtaining the point cloud data in default scanning range by laser radar；S2: the point cloud that will acquire is classified according to default clustering algorithm, and is divided into multiple objective bodies；S3: being scanned each objective body according to default sweep interval, obtains each objective body in the distance of each default sweep interval point to laser radar；S4: each objective body is obtained in the change rate of two adjacent default trace interval points to laser radar distance, if change rate is 1, the current state of the objective body is stationary state；If change rate is not 1, the current state of the objective body is motion state.This method is capable of the status information of determination barrier more accurately and quickly, without being calculated according to off-line data, analyzes fast speed.
Description
Technical field
The present invention relates to laser radar identification technology fields, more particularly to one kind to be based on laser radar obstruction detection state
System.
Background technique
Laser radar obtains the point cloud information of ambient enviroment by scanning ranging, and precision is high, and distance is remote, speed is fast, no
It is illuminated by the light influence etc. a little.Have wide practical use in automatic driving vehicle and robot field.
It is chiefly used in detection method and base based on high-precision UAN map currently based on the obstacle detection method of point cloud data
In the detection method of machine learning training pattern.
Detection method wherein based on high-precision environment map is to first pass through to splice the point cloud data acquired offline,
High-precision environmental map is obtained, then using the environmental map of acquisition as background, compares online point cloud data and environmental map difference,
Obtain sound state obstacle information.But this method, it needs laser radar and off-line data to be combined calculating, is not suitable for having
The environment for having voluminous object to move, calculating data volume is larger, handles slower.
Wherein based on and its learning training model detection method be by calculate extract point cloud key point and feature, adopt
With a large amount of training sample, the model of all kinds of barriers is obtained by various learning methods, passes through model prediction cognitive disorders object
Type, but need to be trained using a large amount of high-quality samples, the obstacle identity not occurred in training set can not be examined
It surveys.
Summary of the invention
To solve the above-mentioned problems, the present invention provides one kind without in conjunction with offline environment map and without using a large amount of
The method based on laser radar obstruction detection state that can quickly handle barrier state recognition that high-quality sample is trained
And system.
In order to achieve the above object, the invention adopts the following technical scheme:
A method of based on laser radar obstruction detection state, comprising steps of
S1: the point cloud data in default scanning range is obtained by laser radar；
S2: the point cloud that will acquire is classified according to default clustering algorithm, and is divided into multiple objective bodies；
S3: being scanned each objective body according to default sweep interval, obtains each objective body each default
Distance of the sweep interval point to laser radar；
S4: obtaining each objective body in the change rate of two adjacent default trace interval points to laser radar distance,
If change rate is 1, the current state of the objective body is stationary state；If change rate is not 1, the current state of the objective body
For motion state.
Further, step S1 includes:
S11: by laser radar to being scanned in default scanning range；
S12: the profile information of object in default scanning range is obtained；
S13: the profile information for the object that will acquire is converted into corresponding cloud；
S14: the corresponding point cloud data of contour of object information in default scanning range is obtained.
Further, step S2 includes:
S21: multiple initial point cloud objects are chosen in the point cloud in the default scanning range of acquisition；
S22: according to default clustering algorithm, the point cloud within the scope of each initial point cloud object pre-determined distance is obtained；
S23: by the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as mesh
Standard type.
Further, step S4 includes:
S41: each objective body is obtained in the corresponding distance to laser radar of two adjacent default trace interval points；
S42: by pre-determined distance algorithm, judge objective body to laser radar distance in two adjacent default sweep times
Whether change in spaced points；
S43: if so, confirming that the objective body current state is motion state；If it is not, then confirming that the objective body is worked as
Preceding state is stationary state.
A kind of system based on laser radar obstruction detection state, comprising:
Laser radar, for obtaining the point cloud data in default scanning range；
Cluster Classification module, the point cloud for will acquire are divided into multiple objective bodies according to default clustering algorithm；Obtain distance
Module obtains each objective body and sweeps in each preset for being scanned to each objective body according to default sweep interval
To the distance of laser radar when retouching interval time point；
Block of state is obtained, for obtaining each objective body in two adjacent default trace interval points to laser radar
The change rate of distance, if change rate is 1, the current state of the objective body is stationary state；If change rate is not 1, the mesh
The current state of standard type is motion state.
Further, laser radar includes:
Laser cell, for being scanned in default scanning range；
Profile unit is obtained, for obtaining the profile information of object in default scanning range；
Point Yun Danyuan is obtained, the profile information of the object for will acquire is converted into corresponding cloud；
Data cell is obtained, for obtaining the corresponding point cloud data of contour of object information in default scanning range.
Further, Cluster Classification module includes:
Initial object unit is chosen, for choosing multiple initial point clouds pair in the point cloud in the default scanning range of acquisition
As；
Cluster cell, for obtaining the point within the scope of each initial point cloud object pre-determined distance according to default clustering algorithm
Cloud, and by the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as objective body.
Further, obtaining block of state includes:
Distance unit is obtained, it is corresponding to sharp in two adjacent default trace interval points for obtaining each objective body
The distance of optical radar；
Judge distance unit, the distance for by pre-determined distance algorithm, judging objective body to laser radar is in two phases
Whether change in the default trace interval point of neighbour；If so, confirming that the objective body current state is motion state；If
It is not then to confirm that the objective body current state is stationary state.
The invention has the benefit that
(1) continue to obtain according to default sweep interval to being scanned in default scanning range by laser radar
The point cloud data information of object in default scanning range, and by presetting clustering algorithm for the point cloud minute in default scanning range
Class is multiple objective bodies, further according to multiple objective bodies two adjacent default sweep interval points to laser radar away from
It carries out judging the state that objective body is current from variation.Recognition efficiency is high, and accuracy of identification is higher.
(2) provided by the present application to be based on laser radar obstruction detection state, without passing through off-line data and a large amount of high-quality
Sample is trained；Only need to judge that objective body becomes in the distance of two neighboring default sweep interval point to laser radar
Change, the detecting of barrier state can be realized, the scene of various obstacle recognitions can be suitable for, the scope of application is wider.
Detailed description of the invention
Fig. 1 is the method flow diagram one based on laser radar obstruction detection state；
Fig. 2 is the method flow diagram two based on laser radar obstruction detection state；
Fig. 3 is laser radar range schematic diagram；
Fig. 4 is preferable scene figure in embodiment one；
Fig. 5 is the corresponding laser scanning figure of scene figure preferable in embodiment one；
Fig. 6 is the system construction drawing one based on laser radar obstruction detection state；
Fig. 7 is the system construction drawing two based on laser radar obstruction detection state.
Specific embodiment
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Embodiment one
A kind of method based on laser radar obstruction detection state is present embodiments provided, as shown in Figures 1 to 5, this
Method comprising steps of
A method of based on laser radar obstruction detection state, comprising steps of
S1: the point cloud data in default scanning range is obtained by laser radar；
S2: the point cloud that will acquire is classified according to default clustering algorithm, and is divided into multiple objective bodies；
S3: being scanned each objective body according to default sweep interval, obtains each objective body each default
Distance of the sweep interval point to laser radar；
S4: obtaining each objective body in the change rate of two adjacent default trace interval points to laser radar distance,
If change rate is 1, the current state of the objective body is stationary state；If change rate is not 1, the current state of the objective body
For motion state.
Further, step S1 includes:
S11: by laser radar to being scanned in default scanning range；
S12: the profile information of object in default scanning range is obtained；
S13: the profile information for the object that will acquire is converted into corresponding cloud；
S14: the corresponding point cloud data of contour of object information in default scanning range is obtained.
Wherein laser radar system is to realize to carry out profile spy to the object in default scanning range by transmitting laser beam
The acquisition of sign.As shown in figure 3, obtaining contour of object information in default scanning range by laser radar, then will acquire
The profile information of object is converted into corresponding cloud；Further, the corresponding point cloud data of point cloud is obtained.
Then the point cloud data of acquisition is identified and is classified according to default clustering algorithm.
Further, step S2 includes:
S21: multiple initial point cloud objects are chosen in the point cloud in the default scanning range of acquisition；
S22: according to default clustering algorithm, the point cloud within the scope of each initial point cloud object pre-determined distance is obtained；
S23: by the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as mesh
Standard type.
Point cloud in the default scanning range wherein obtained, the profile information of corresponding multiple objects, each object have oneself
Feature, including state.Therefore classify to the point cloud in the default scanning range of acquisition according to default clustering algorithm, specifically
Classification method are as follows: the point cloud in default scanning range is handled, multiple initial point cloud objects, each initial point are chosen
Cloud object represents a corresponding cluster center, and each initial point cloud object is the object indicated in default scanning range, into
One step, to preset a barrier in scanning range.
All point cloud datas are handled, the point cloud within the scope of each initial point cloud object pre-determined distance is acquired, from
And multiclass is divided into the point cloud in default scanning range according to initial point cloud object, each initial point cloud object and corresponding default
Point cloud in distance range is divided into an objective body, i.e. a barrier；There are multiple objective bodies in default scanning range, i.e., it is multiple
Barrier.
Each objective body is scanned according to default sweep interval, obtains each objective body in each default scanning
Distance of the interval time point to laser radar；
Further, step S4 includes:
S41: each objective body is obtained in the corresponding distance to laser radar of two adjacent default trace interval points；
S42: by pre-determined distance algorithm, judge objective body to laser radar distance in two adjacent default sweep times
Whether change in spaced points；
S43: if so, confirming that the objective body current state is motion state；If it is not, then confirming that the objective body is worked as
Preceding state is stationary state.
Preferably, swashing as shown in figure 4, have the multiple objects such as automobile, pillar and pedestrian in default scanning range in figure
Point cloud after optical scanning, as shown in figure 5, wherein automobile, pillar and pedestrian etc. obtain its corresponding profile under laser scanning
Information, and it is converted into a cloud, each object has the initial point cloud object of oneself, each initial point cloud object pre-determined distance range
Interior point cloud forms an objective body, and corresponding cloud of the automobile profile is an objective body, corresponding cloud of pillar profile
It is an objective body, corresponding cloud of pedestrian contour is an objective body.
Wherein the distance of each objective body to laser radar can be come out by laser measurement, as shown in figure 3, laser
Radar is scanned the objective body in default scanning range according to default sweep interval.
When therefore can receive default sweep interval point in real time, the distance of each objective body to laser radar,
It further can analyze two adjacent default sweep interval points, variation of the objective body to laser radar distance.
Wherein if objective body to laser radar distance two adjacent default trace interval points distance change
Rate is not 1, then illustrates, the distance of objective body to laser radar is different in two adjacent default trace interval points,
Changed, hence, it can be determined that, the state of current goal body is motion state；If objective body to laser radar away from
It is greater than 0 less than 1 from the change rate with a distance from two adjacent default trace interval points, then illustrates that the objective body is Xiang Jiguang
Radar is moved close to direction, if objective body to laser radar distance two adjacent default trace interval points distance
Change rate is greater than 1, then illustrates that the objective body is moved to laser radar and far from direction.
Wherein if objective body to laser radar distance two adjacent default trace interval points distance change
Rate is 1, then illustrates, the distance of objective body to laser radar is different in two adjacent default trace interval points, that is, is not had
It changes, hence, it can be determined that, the state of current goal body is stationary state.
A kind of preferred embodiment is provided in the present embodiment, wherein being based on laser radar detecting vehicle body peripheral obstacle barrier
Hinder the method for object state, wherein being provided with laser radar in roof predeterminated position, the laser radar being arranged by roof obtains vehicle
The contour of object point cloud that scanning range is preset around body is chosen first in the contour of object point cloud for presetting scanning range around vehicle body
Initial point cloud object, and according to default clustering algorithm, it obtains each initial point cloud object and each initial point cloud data collection is pre-
If the objective body that the point cloud in distance range is formed, thus according to the variation of the distance of laser radar on objective body to roof, really
Recognize the motion state of vehicle body surrounding objects.
Laser radar is placed on roof, can be improved general to the identification for presetting barrier in scanning range around vehicle body
Rate reduces automobile because of the probability of accident caused by lubrication groove difference, reduces bus lubrication groove difference and thrust into or the accident of bicycle, into one
Step ground, improves travel safety.
In conclusion the method provided in this embodiment based on laser radar obstruction detection state, it can be by default
Clustering algorithm is identified and is classified to the object in default scanning range, further, according to the object in default scanning range
Body judges the state of the object in default scanning range to the variation of laser radar distance.Its operation efficiency is high, can be less
Data handling conditions under, complete barrier state identification, improve the identification to barrier state in default scanning range
Rate improves safety.
Embodiment two
A kind of system based on laser radar obstruction detection state is present embodiments provided, as shown in Figure 6 to 7, this
System includes:
Laser radar, for obtaining the point cloud data in default scanning range；
Cluster Classification module, the point cloud for will acquire are divided into multiple objective bodies according to default clustering algorithm；Obtain distance
Module obtains each objective body and sweeps in each preset for being scanned to each objective body according to default sweep interval
To the distance of laser radar when retouching interval time point；
Block of state is obtained, for obtaining each objective body in two adjacent default trace interval points to laser radar
The change rate of distance, if change rate is 1, the current state of the objective body is stationary state；If change rate is not 1, the mesh
The current state of standard type is motion state.
Further, laser radar includes:
Laser cell, for being scanned in default scanning range；
Profile unit is obtained, for obtaining the profile information of object in default scanning range；
Point Yun Danyuan is obtained, the profile information of the object for will acquire is converted into corresponding cloud；
Data cell is obtained, for obtaining the corresponding point cloud data of contour of object information in default scanning range.
Further, Cluster Classification module includes:
Initial object unit is chosen, for choosing multiple initial point clouds pair in the point cloud in the default scanning range of acquisition
As；
Cluster cell, for obtaining the point within the scope of each initial point cloud object pre-determined distance according to default clustering algorithm
Cloud, and by the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as objective body.
Further, obtaining block of state includes:
Distance unit is obtained, it is corresponding to sharp in two adjacent default trace interval points for obtaining each objective body
The distance of optical radar；
Judge distance unit, the distance for by pre-determined distance algorithm, judging objective body to laser radar is in two phases
Whether change in the default trace interval point of neighbour；If so, confirming that the objective body current state is motion state；If
It is not then to confirm that the objective body current state is stationary state.
Preferably, the laser radar in the present embodiment is mounted on vehicle top, automobile in the process of moving, is placed in roof
Laser radar can emit laser beam into the default scanning range of motor vehicle environment, and laser beam is detecting in default scanning range
It can be reflected back toward laser radar when object, by laser distance measuring principle, can calculate in laser radar to default scanning range
The range information of object.
Wherein laser radar can be persistently to being scanned, to obtain default scanning model in scanning range default around vehicle body
The profile information of interior object is enclosed, point cloud is formed.After the point cloud data for obtaining vehicle body surrounding objects object, pass through Cluster Classification first
Module, the point cloud that will acquire are divided into multiple objective bodies according to default clustering algorithm；And between each objective body according to default scanning
It is scanned every the time, obtains each objective body in each default sweep interval point to the distance of laser radar；Then
By obtaining distance unit, each objective body is obtained in the corresponding laser radar that arrives of two adjacent default trace interval points
Distance；And judge distance unit, by pre-determined distance algorithm, judge that objective body is adjacent default at two to the distance of laser radar
Whether change in trace interval point；If so, confirming that the objective body current state is motion state；If it is not,
Then confirm that the objective body current state is stationary state.
Based on the system of laser radar obstruction detection state, identification is accurate, ensure that the knowledge of obstruction detection state
Other efficiency can be suitable for the obstacle recognition of several scenes.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (8)
1. a kind of method based on laser radar obstruction detection state, which is characterized in that comprising steps of
S1: the point cloud data in default scanning range is obtained by laser radar；
S2: the point cloud that will acquire is classified according to default clustering algorithm, and is divided into multiple objective bodies；
S3: being scanned each objective body according to default sweep interval, obtains each objective body in each default scanning
Distance of the interval time point to laser radar；
S4: obtaining each objective body in the change rate of two adjacent default trace interval points to laser radar distance, if becoming
Rate is 1, then the current state of the objective body is stationary state；If change rate is not 1, the current state of the objective body is fortune
Dynamic state.
2. a kind of method based on laser radar obstruction detection state according to claim 1, which is characterized in that step
S1 includes:
S11: by laser radar to being scanned in default scanning range；
S12: the profile information of object in default scanning range is obtained；
S13: the profile information for the object that will acquire is converted into corresponding cloud；
S14: the corresponding point cloud data of contour of object information in default scanning range is obtained.
3. a kind of method based on laser radar obstruction detection state according to claim 1, which is characterized in that step
S2 includes:
S21: multiple initial point cloud objects are chosen in the point cloud in the default scanning range of acquisition；
S22: according to default clustering algorithm, the point cloud within the scope of each initial point cloud object pre-determined distance is obtained；
S23: by the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as target
Body.
4. a kind of method based on laser radar obstruction detection state according to claim 1, which is characterized in that step
S4 includes:
S41: each objective body is obtained in the corresponding distance to laser radar of two adjacent default trace interval points；
S42: by pre-determined distance algorithm, judge objective body to laser radar distance in two adjacent default trace intervals
Whether change in point；
S43: if so, confirmation objective body current state is motion state；If it is not, then confirming that objective body current state is static
State.
5. a kind of system based on laser radar obstruction detection state characterized by comprising
Laser radar, for obtaining the point cloud data in default scanning range；
Cluster Classification module, the point cloud for will acquire are divided into multiple objective bodies according to default clustering algorithm；
It obtains spacing module and obtains each objective body for being scanned to each objective body according to default sweep interval
In each default sweep interval point to the distance of laser radar；
Block of state is obtained, for obtaining each objective body in two adjacent default trace interval points to laser radar distance
Change rate, if change rate be 1, the current state of the objective body be stationary state；If change rate is not 1, the objective body
Current state is motion state.
6. a kind of system based on laser radar obstruction detection state according to claim 5, which is characterized in that laser
Radar includes:
Laser cell, for being scanned in default scanning range；
Profile unit is obtained, for obtaining the profile information of object in default scanning range；
Point Yun Danyuan is obtained, the profile information of the object for will acquire is converted into corresponding cloud；
Data cell is obtained, for obtaining the corresponding point cloud data of contour of object information in default scanning range.
7. a kind of system based on laser radar obstruction detection state according to claim 5, which is characterized in that cluster
Categorization module includes:
Initial object unit is chosen, for choosing multiple initial point cloud objects in the point cloud in the default scanning range of acquisition；
Cluster cell, for obtaining the point cloud within the scope of each initial point cloud object pre-determined distance according to default clustering algorithm, and
By the point cloud within the scope of each initial point cloud object and each initial point cloud object pre-determined distance, it is labeled as objective body.
8. a kind of system based on laser radar obstruction detection state according to claim 5, which is characterized in that obtain
Block of state includes:
Distance unit is obtained, it is corresponding to laser thunder in two adjacent default trace interval points for obtaining each objective body
The distance reached；
Distance unit is judged, for judging that objective body is adjacent pre- at two to the distance of laser radar by pre-determined distance algorithm
If whether changing in trace interval point；If so, confirmation objective body current state is motion state；If it is not, then
Confirmation objective body current state is stationary state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811396223.9A CN109633685A (en) | 2018-11-22 | 2018-11-22 | A kind of method and system based on laser radar obstruction detection state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811396223.9A CN109633685A (en) | 2018-11-22 | 2018-11-22 | A kind of method and system based on laser radar obstruction detection state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109633685A true CN109633685A (en) | 2019-04-16 |
Family
ID=66068708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811396223.9A Pending CN109633685A (en) | 2018-11-22 | 2018-11-22 | A kind of method and system based on laser radar obstruction detection state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109633685A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109119A (en) * | 2019-06-04 | 2019-08-09 | 江苏新通达电子科技股份有限公司 | Blind monitoring system and blind monitoring method with self-learning function |
| CN111413964A (en) * | 2020-03-09 | 2020-07-14 | 上海理工大学 | Method for detecting moving state of obstacle in real time by mobile robot in environment |
| CN111665522A (en) * | 2020-05-19 | 2020-09-15 | 上海有个机器人有限公司 | Method, medium, terminal and device for filtering static object in laser scanning image |
| CN111856507A (en) * | 2020-07-28 | 2020-10-30 | 上海木木聚枞机器人科技有限公司 | Environment sensing implementation method, intelligent mobile device and storage medium |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN112015938A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Point cloud label transmission method, device and system |
| CN112487984A (en) * | 2020-11-30 | 2021-03-12 | 贵州北斗空间信息技术有限公司 | Point cloud data lightweight rapid generation method |
| CN112505720A (en) * | 2020-10-29 | 2021-03-16 | 北京全路通信信号研究设计院集团有限公司 | Multi-line laser radar-based slope disaster monitoring system and method |
| CN112753000A (en) * | 2020-04-27 | 2021-05-04 | 深圳市大疆创新科技有限公司 | Obstacle avoidance method, movable platform, control device and storage medium |
| CN112799397A (en) * | 2020-12-26 | 2021-05-14 | 广州小马慧行科技有限公司 | Object detection method, object detection device, vehicle control method, and vehicle system |
| CN113031005A (en) * | 2021-02-22 | 2021-06-25 | 江苏大学 | Crane dynamic obstacle identification method based on laser radar |
| CN112487984B (en) * | 2020-11-30 | 2024-04-26 | 贵州北斗空间信息技术有限公司 | Point cloud data lightweight rapid generation method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104931977A (en) * | 2015-06-11 | 2015-09-23 | 同济大学 | Obstacle identification method for smart vehicles |
| CN107632308A (en) * | 2017-08-24 | 2018-01-26 | 吉林大学 | A kind of vehicle front barrier profile testing method based on recurrence superposition algorithm |
| CN107728162A (en) * | 2017-10-16 | 2018-02-23 | 济南浪潮高新科技投资发展有限公司 | Pilotless automobile parking safety monitoring system based on laser radar |
| US20180067491A1 (en) * | 2016-09-08 | 2018-03-08 | Mentor Graphics Corporation | Event classification and object tracking |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
| CN108226895A (en) * | 2017-12-27 | 2018-06-29 | 吉林大学 | Static-obstacle thing identifying system and recognition methods based on laser radar |
| CN108594264A (en) * | 2018-04-28 | 2018-09-28 | 上海木木机器人技术有限公司 | Obstacle recognition method, system and the robot with obstacle recognition function |
| CN108629228A (en) * | 2017-03-15 | 2018-10-09 | 高德软件有限公司 | A kind of road object identifying method and device |
| CN108664841A (en) * | 2017-03-27 | 2018-10-16 | 郑州宇通客车股份有限公司 | A kind of sound state object recognition methods and device based on laser point cloud |
-
2018
- 2018-11-22 CN CN201811396223.9A patent/CN109633685A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104931977A (en) * | 2015-06-11 | 2015-09-23 | 同济大学 | Obstacle identification method for smart vehicles |
| US20180067491A1 (en) * | 2016-09-08 | 2018-03-08 | Mentor Graphics Corporation | Event classification and object tracking |
| CN108629228A (en) * | 2017-03-15 | 2018-10-09 | 高德软件有限公司 | A kind of road object identifying method and device |
| CN108664841A (en) * | 2017-03-27 | 2018-10-16 | 郑州宇通客车股份有限公司 | A kind of sound state object recognition methods and device based on laser point cloud |
| CN107632308A (en) * | 2017-08-24 | 2018-01-26 | 吉林大学 | A kind of vehicle front barrier profile testing method based on recurrence superposition algorithm |
| CN107728162A (en) * | 2017-10-16 | 2018-02-23 | 济南浪潮高新科技投资发展有限公司 | Pilotless automobile parking safety monitoring system based on laser radar |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
| CN108226895A (en) * | 2017-12-27 | 2018-06-29 | 吉林大学 | Static-obstacle thing identifying system and recognition methods based on laser radar |
| CN108594264A (en) * | 2018-04-28 | 2018-09-28 | 上海木木机器人技术有限公司 | Obstacle recognition method, system and the robot with obstacle recognition function |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112015938A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Point cloud label transmission method, device and system |
| CN110109119A (en) * | 2019-06-04 | 2019-08-09 | 江苏新通达电子科技股份有限公司 | Blind monitoring system and blind monitoring method with self-learning function |
| CN111413964A (en) * | 2020-03-09 | 2020-07-14 | 上海理工大学 | Method for detecting moving state of obstacle in real time by mobile robot in environment |
| WO2021217341A1 (en) * | 2020-04-27 | 2021-11-04 | 深圳市大疆创新科技有限公司 | Obstacle avoidance method, moveable platform, control device, and storage medium |
| CN112753000A (en) * | 2020-04-27 | 2021-05-04 | 深圳市大疆创新科技有限公司 | Obstacle avoidance method, movable platform, control device and storage medium |
| CN111665522A (en) * | 2020-05-19 | 2020-09-15 | 上海有个机器人有限公司 | Method, medium, terminal and device for filtering static object in laser scanning image |
| CN111665522B (en) * | 2020-05-19 | 2022-12-16 | 上海有个机器人有限公司 | Method, medium, terminal and device for filtering static object in laser scanning pattern |
| CN111856507A (en) * | 2020-07-28 | 2020-10-30 | 上海木木聚枞机器人科技有限公司 | Environment sensing implementation method, intelligent mobile device and storage medium |
| CN111856507B (en) * | 2020-07-28 | 2023-03-28 | 上海木木聚枞机器人科技有限公司 | Environment sensing implementation method, intelligent mobile device and storage medium |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN111932943B (en) * | 2020-10-15 | 2021-05-14 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN112505720A (en) * | 2020-10-29 | 2021-03-16 | 北京全路通信信号研究设计院集团有限公司 | Multi-line laser radar-based slope disaster monitoring system and method |
| CN112487984A (en) * | 2020-11-30 | 2021-03-12 | 贵州北斗空间信息技术有限公司 | Point cloud data lightweight rapid generation method |
| CN112487984B (en) * | 2020-11-30 | 2024-04-26 | 贵州北斗空间信息技术有限公司 | Point cloud data lightweight rapid generation method |
| CN112799397A (en) * | 2020-12-26 | 2021-05-14 | 广州小马慧行科技有限公司 | Object detection method, object detection device, vehicle control method, and vehicle system |
| CN113031005A (en) * | 2021-02-22 | 2021-06-25 | 江苏大学 | Crane dynamic obstacle identification method based on laser radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109633685A (en) | A kind of method and system based on laser radar obstruction detection state | |
| Zhang et al. | Vehicle tracking and speed estimation from roadside lidar | |
| CN109633676A (en) | A kind of method and system based on the laser radar obstruction detection direction of motion | |
| CN105892471A (en) | Automatic automobile driving method and device | |
| US8818702B2 (en) | System and method for tracking objects | |
| Barroso et al. | Number plate reading using computer vision | |
| McCall et al. | Lane change intent analysis using robust operators and sparse bayesian learning | |
| CN108780154A (en) | The processing method of 3D point cloud | |
| CN110018496A (en) | Obstacle recognition method and device, electronic equipment, storage medium | |
| CN104793202A (en) | Object fusion system of multiple radar imaging sensors | |
| CN109633686B (en) | Method and system for detecting ground obstacle based on laser radar | |
| CN107729843B (en) | Low-floor tramcar pedestrian identification method based on radar and visual information fusion | |
| JP2012221456A (en) | Object identification device and program | |
| Li et al. | An adaptive 3D grid-based clustering algorithm for automotive high resolution radar sensor | |
| CN112379674B (en) | Automatic driving equipment and system | |
| Kumar et al. | Indoor localization of vehicles using deep learning | |
| CN112487905A (en) | Method and system for predicting danger level of pedestrian around vehicle | |
| CN111856507A (en) | Environment sensing implementation method, intelligent mobile device and storage medium | |
| Tatebe et al. | Pedestrian detection from sparse point-cloud using 3DCNN | |
| Jwa et al. | Kalman filter based railway tracking from mobile Lidar data | |
| CN114155720B (en) | Vehicle detection and track prediction method for roadside laser radar | |
| Sengupta et al. | Automatic radar-camera dataset generation for sensor-fusion applications | |
| Wang et al. | Two-stage road terrain identification approach for land vehicles using feature-based and markov random field algorithm | |
| CN115630569A (en) | Millimeter wave radar sensor modeling method applied to automatic driving | |
| JP2016045767A (en) | Motion amount estimation device and program |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |