CN109001757B - Parking space intelligent detection method based on 2D laser radar - Google Patents
Parking space intelligent detection method based on 2D laser radar Download PDFInfo
- Publication number
- CN109001757B CN109001757B CN201810549473.5A CN201810549473A CN109001757B CN 109001757 B CN109001757 B CN 109001757B CN 201810549473 A CN201810549473 A CN 201810549473A CN 109001757 B CN109001757 B CN 109001757B
- Authority
- CN
- China
- Prior art keywords
- parking space
- point
- line segment
- distance
- vehicle
- 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
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a parking space intelligent detection method based on a 2D laser radar, which comprises the following steps: step 1, obtaining environment position information including distance information and angle information; step2, preprocessing the environmental position information acquired in the step 1; step 3, carrying out segmentation clustering on the environment position information preprocessed in the step 2; step 4, extracting the vehicle boundary line segment from the clustering result obtained in the step 3; step 5, extracting a line segment from the vehicle contour obtained in the step 4, establishing a parking space model and obtaining the minimum width of the parking space; and 6, judging whether the parking space size meets the requirement or not according to the minimum width of the parking space. According to the method, the angle and distance information of the 2D laser radar is considered, and a parking space model is established through a clustering analysis and line segment fitting method. On the basis, a multi-input multi-rule fuzzy reasoning system is introduced into parking space detection, so that the parking space detection accuracy and the intelligent level in the parking environment are improved.
Description
Technical Field
The invention belongs to the field of parking space detection of automatic parking and auxiliary parking, and particularly relates to a parking space detection method based on a 2D laser radar in parking space detection.
Background
The parking space detection is a necessary component of an automatic parking and auxiliary parking system, and accurate and effective parking space detection is the basis for realizing automatic parking and auxiliary parking. Modern parking space detection usually depends on collocation of various sensors, and a proper sensor information processing algorithm is selected to sense a scene, so that a corresponding decision is made. For the detection of a parking space for automatic parking, there are three main types from the sensor point of view: the parking space detection method comprises the following steps of parking space detection by utilizing ultrasonic waves, parking space detection by utilizing a laser radar and parking space detection by utilizing multi-sensor fusion such as a camera.
The ultrasonic radar sensor is used for detecting the parking space, the vehicle is required to have a specific initial posture, only regular parking spaces can be detected, and the length and the width of the regular parking spaces are measured. If meet irregular and narrower parking stall, then can not detected by the system, cause the waste of parking stall resource. Utilize vision sensor and ultrasonic sensor to discern the parking stall, need multi-sensor information such as vision sensor, a plurality of ultrasonic sensor, pulse sensor to fuse, the system is complicated, and the cost is expensive, and needs clear car position line and reference thing. In contrast, the lidar sensor has the functions of ranging and environment sensing, has a large detection angle, stable data and good adaptability, and is widely applied to automatic driving, indoor and outdoor positioning and automatic parking.
In recent years, many people have made many relevant researches on the parking space detection using the laser radar, and most of the researches use a method of measuring the parking space width information in the environment to obtain the size of the parking space. Such as: in 2010, the parking space is detected by applying a laser radar by a method similar to an ultrasonic sensor, such as the early morning of the Shanghai university of traffic. The method comprises the steps that an author divides an interest area, analyzes local laser radar data to obtain depth information of a parking space, measures parking space length information by tracking a vehicle boundary so as to identify the parking space, and designs corresponding parking space detection methods for vertical parking and parallel parking respectively; in 2014, the Wangyu and the like of the university at the same Ji have designed a parking space dynamic detection method based on a laser radar, and authors have designed a contour fitting method based on an optimal external rectangle to fit the contour of a vehicle under the conditions that obstacle data points are positioned through corresponding coordinate transformation aiming at parking environments such as parallel parking spaces and the like and the contour of the vehicle is not perfectly fitted in the parking space identification process, so as to realize the dynamic detection of the parallel parking spaces. However, the current research on detecting parking spaces by using laser radar still remains on the basis of detecting parking spaces according to planning rules and parking rules, the detection method refers to the detection method of an ultrasonic sensor, the environment sensing function of the laser radar sensor is not utilized, the detection mode needs to be manually selected and switched according to different parking space types, and the intelligent degree is not high.
Disclosure of Invention
In view of the above, in order to solve the above problems, the invention provides a parking space intelligent detection method based on a 2D laser radar, so as to solve the problems of low accuracy and low intelligence level of parking space detection in the prior art.
In order to achieve the above and other objects, the present invention provides a parking space intelligent detection method based on 2D laser radar, including the following steps:
step2, preprocessing the environmental position information acquired in the step 1;
step 4, extracting the vehicle boundary line segment from the clustering result obtained in the step 3;
step 5, extracting a line segment from the vehicle contour obtained in the step 4, establishing a parking space model and obtaining the minimum width of the parking space;
and 6, judging whether the parking space size meets the requirement or not according to the minimum width of the parking space.
Preferably, the specific method for performing segmentation clustering on the environmental location information is as follows:
calculating the Euclidean distance D between two points:
|p n -p n-1 |＞D max
wherein, | p n -p n-1 Is the point p n To point p n-1 Of between, euclidean distance D max Is the distance threshold between any adjacent points, if point p n To point p n-1 Has a Euclidean distance smaller than D max If not, the group is set as a breakpoint.
Preferably, the distance threshold D between any adjacent points max The calculating method comprises the following steps:
wherein l n-1 Is a point p n-1 Distance to the lidar, Δ φ is the resolution of the lidar, φ n-1 Is a point p n-1 Polar angle in polar coordinates, λ is the parameter value.
Preferably, the specific calculation method of the parameter value λ is as follows:
set point p n And p n-1 The included angle between the connecting line and the x axis is beta, then:
wherein (x) n ,y n )，(x n-1 ,y n-1 ) Are respectively a data point p n And p n-1 When the incident angle γ is:
γ＝90°-(β-φ n-1 )
if the incident angle gamma is larger than K, a larger parameter lambda is corresponded; if the incident angle gamma is less than or equal to K, the smaller parameter lambda is corresponded.
Preferably, said step 4 comprises the following sub-steps:
step 41, segmenting the data point set to obtain breakpoints and primarily distributing the breakpoints;
42, eliminating abnormal data sets from all the segmented data sets;
step 43. Calculate the boundary point p j+1 Performing redistribution and comparing the boundary points p j+1 Distance d from adjacent line segments j By determining the distance d j Whether a given threshold is met to reassign the boundary point;
step 44. Calculate the neighbor set { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i ) L is the straight line l fitted to i = m +1, \8230;, k } c,m And l m+1,k Angle of (2)
And is in conjunction with a threshold value gamma thd In comparison, if
Step 45 is performed, otherwise, the merging of the two straight lines is ended, the next adjacent line segment is traversed, and step 44 is continued until all sets are traversed.
Step 45, set of neighbors { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i ) I = m +1, \ 8230;, k }, merging, fitting straight line by using least square method, and calculating fitting error square sum E 2 And is in conjunction with a threshold value
By comparison, ifIf the value is less than the threshold value, the straight line combination is carried out, otherwise, the next adjacent line segment is traversed, and the step 44 is returned.
Preferably, said step 5 comprises the following sub-steps:
step 51, calculating the boundary point of the first vehicle target
And boundary points of vehicle object two
Step 52, extracting the minimum width D _ Wide of the parking space min ；
Step 53, calculating the boundary point of the first vehicle target
To line segment
The shortest distance D 1t o 2 Boundary point with vehicle object two
To line segment
The shortest distance of the parking space is the minimum width D _ Wide of the parking space min ＝min{D 1t o 2 ,D 2t o 1 }。
Due to the adoption of the technical scheme, the invention has the following advantages:
according to the method, the angle and distance information of the 2D laser radar is considered, and a parking space model is established through a clustering analysis and line segment fitting method. And on the basis, a multi-input multi-rule fuzzy inference system is introduced into parking space detection, so that the parking space detection accuracy and the intelligent level in a parking environment are improved.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings:
FIG. 1 is a schematic diagram of an improved adaptive threshold algorithm;
FIG. 2 is a schematic diagram of quadratic clustering;
FIG. 3 is a flow chart of a line segment extraction algorithm;
FIG. 4 is a schematic view of a parking space model;
FIG. 5 is a flow chart of the method of the present invention;
FIG. 6 is a diagram of different vectors in the present embodiment.
Detailed Description
The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
Please refer to fig. 1 to 6. It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
As shown in fig. 5, this embodiment provides a parking space intelligent detection method based on a 2D laser radar, and the method includes the following steps:
step 1: connecting two-dimensional scanning laserThe sensor is used for acquiring environment data and storing the environment data in the computer in an array form, and the acquired environment position information comprises distance information D = { D = { (D) } 1 ,d 2 ,d 3 ,...,d N And angle information S = { a = } 1 ,a 2 ,a 3 ,...,a N }。
Step 2: and (3) preprocessing the environmental position information acquired in the step (1), including removing data points outside an effective range, filtering isolated noise points and compensating defects of a laser radar measuring mechanism.
And 3, step 3: and (3) carrying out segmentation clustering analysis on the environmental position information obtained in the step (2), wherein the specific method is as follows:
the Euclidean distance is used as the basis of clustering, and the formula is as follows:
|p n -p n-1 |＞D max
wherein, | p n -p n-1 L is a point p n To point p n-1 European distance between, D max Is the distance threshold between any adjacent points, if point p n To point p n-1 Has a Euclidean distance smaller than D max If not, the group is set as a breakpoint. Wherein D max And also the distance l between the lidar and the point n-1 It is relevant. D max And l n-1 The relationship of (a) to (b) is as follows:
wherein l n And l n-1 Are respectively a point p n And p n-1 Distance to the lidar, Δ φ is the resolution of the lidar, φ n And phi n-1 Are respectively a point p n And p n-1 The polar angle in the polar coordinate, λ, is a parameter value, and its magnitude directly affects the magnitude of the threshold.
In the clustering process, the point p is connected first n And point p n-1 Calculating a point p n-1 When the incident angle γ becomes larger, the parameter λ takes a larger value, and the distance threshold becomes larger. The parameter lambda is set to be constant when the incident angle gamma is continuously reducedThe distance threshold is reduced when the distance threshold is smaller. The specific calculation method of the parameter lambda is as follows:
set point p n And p n-1 The included angle between the connecting line and the x axis is beta, then:
wherein (x) n ,y n )，(x n-1 ,y n-1 ) Are respectively a point p n And p n-1 When the incident angle γ is:
γ＝90°-(β-φ n-1 )
if the incident angle gamma is larger than K, a larger parameter lambda is corresponded; if the angle of incidence γ < = K, a smaller parameter λ is corresponded. Due to the fact that the scanning data are due to material reflectivity, partial data are still absent, and secondary clustering is needed according to the vehicle outline characteristics.
As shown in FIG. 2, two points with the closest distance between the adjacent clusters (1) and (2) are searched for and are set as m n-1 And m n Calculating the distance D between two points n ＝|d n -d n-1 L. the method is used for the preparation of the medicament. If the distance D between two points n And if the distance is exactly equal to the end point of the cluster (1) and the start point of the cluster (2), the two clusters are regrouped into one cluster according to the continuity of the vehicle outline, namely secondary clustering is carried out. Meanwhile, in order to avoid the situation that clustering fails due to excessively large cluster spacing, distance thresholds xi and d need to be set n Less than a quadratic distance threshold ξ, i.e. when | d n -d n-1 |＞ξ(d n ) And the cluster is still considered as two clusters, and secondary clustering is not performed any more.
And 4, step 4: and (4) extracting the vehicle boundary line segment from the clustering result obtained in the step (3). Specifically, the segment extraction is divided into a segmentation stage and a merging stage.
(1) Segmentation stage
Step 1: according to the IEPF algorithm principle, a set of connected data points { p (x) i ,y i ) A starting point p of | i =1,2, \8230;, n } 1 And end point p n At this point, traverse the data set { p (x) i ,y i ) I =1,2, \ 8230;, n }, finding the largest distancePoint p m If point p m To a straight line
Distance d of m Greater than a given threshold
Then point p will be reached m Set as a break point and divide the break point into p (x) i ,y i )|i＝1,2,…,m-1}，{p(x i ,y i ) I = m +1, \8230 |, n } two sets of points. And by the formula:
determining a breakpoint p m To which data set it belongs. The entire data set is then recursively traversed until all data points satisfy the requirements. f is a preset constant.
Step 2: and removing abnormal data sets from all the segmented data sets, wherein the abnormal data sets comprise repeated data sets and data sets only containing one point.
Step 3: according to the LT algorithm idea, a set of adjacent data points { p (x) i ,y i )|i＝k,…,j}，{p(x i ,y i ) Boundary point p of | i = j +1, \8230;, q } j+1 And carrying out redistribution. Decision point p j+1 And set of data points { p (x) } i ,y i ) Distance d of the straight line fitted with i = k, \8230;, j } j Whether a threshold range is met. If yes, point p is added j+1 Add into data Point set { p (x) } i ,y i ) I = k, \ 8230;, j }, and is in { p (x) i ,y i ) I = j +1, \8230;, q } is deleted. All data sets are traversed and updated in this way.
Step 4: and repeating the Step 3 operation.
(2) Merging phases
Step 1: first calculate the neighbor set { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i )| i Linear line l fitting (k) = m +1, \8230;, k } c , m And l m+1,k Angle of (2)
And is in conjunction with a threshold value gamma thd In comparison, if
And Step2 is carried out, otherwise, the two straight lines are merged, the next adjacent line segment is traversed, and Step 1 is continued until all the sets are traversed.
Step 2: set adjacent data { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i ) I = m +1, \ 8230;, k }, merging, fitting straight line by using least square method, and calculating fitting error square sum E 2 And is in conjunction with a threshold value
And comparing, if the sum is less than the threshold value, performing straight line combination. Otherwise, the next adjacent line segment is traversed and the Step 1 is returned.
And 5: and (4) extracting a line segment from the vehicle contour obtained in the step (4), establishing a parking space model and obtaining the minimum width of the parking space.
Specifically, boundary points of a vehicle object one are calculated
And boundary points of vehicle object two
And vehicle body attitude angle
Then extracting the minimum width D _ Wide of the parking space min 。
Minimum width D _ Wide for parking space min Firstly, the boundary point of a vehicle object I is calculated
To line segment
The vector algorithm has directivity and is simple to calculate, so that the shortest distance between a point and a line segment is calculated by adopting the vector algorithm.
According to the vector calculation method, there are:
then:
order to
Because the vectors have directionality, there are: if the case of FIG. 6 (a) is true, 0 < r < 1; if the case is shown in FIG. 6 (b), r.gtoreq.1; in the case of FIG. 6 (c), r.ltoreq.0.
Boundary point of vehicle object one
To line segment
The shortest distance of (c) is:
similarly, the boundary point of the vehicle target two can be obtained
To line segment
The shortest distance of (c) is:
wherein m is
On line segment
The projection on the parking space is the minimum width D _ Wide of the parking space min ＝min{D 1to2 ,D 2to1 }。
Step 6: judging whether the parking space size meets the requirement according to the minimum width of the parking space, and when the parking space size meets the requirement, judging whether the parking space size meets the requirement according to the minimum width of the parking space min And D _ car + delta D, the parking condition is satisfied.
Where Δ D is the minimum width of the extra vehicle body required for parking of the vehicle, and D _ car represents the width of the vehicle body. Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered in the protection scope of the present invention.
Claims (2)
1. The parking space intelligent detection method based on the 2D laser radar is characterized by comprising the following steps:
step 1, obtaining environment position information including distance information and angle information;
step2, preprocessing the environmental position information acquired in the step 1, including removing data points outside an effective range, filtering isolated noise points and compensating defects of a laser radar measuring mechanism;
and 3, carrying out segmentation clustering on the environmental position information preprocessed in the step2, wherein the specific method for segmentation clustering comprises the following steps:
calculating the Euclidean distance between two points:
|p n -p n-1 |＞D max
wherein, | p n -p n-1 Is the point p n To point p n-1 European distance between, D max Is the distance threshold between any adjacent points, if point p n To point p n-1 Has a Euclidean distance smaller than D max If the current is not the same as the current, the current is collected as a group, otherwise, the current is set as a breakpoint;
distance threshold D between any adjacent points max The calculation method comprises the following steps:
wherein l n-1 Is a point p n-1 Distance to the lidar, Δ φ is the resolution of the lidar, φ n-1 Is a point p n-1 Polar angle in polar coordinates, lambda is a parameter value, delta represents a Gaussian random noise parameter, and delta is a standard deviation;
the specific calculation method of the parameter value lambda is as follows:
set point p n And p n-1 The included angle between the connecting line and the x axis is beta, then:
wherein (x) n ,y n )，(x n-1 ,y n-1 ) Are respectively data points p n And p n-1 When the incident angle γ is:
γ＝90°-(β-φ n-1 )
then, a value lambda is obtained through gamma calculation;
and 4, extracting the vehicle boundary line segment from the clustering result obtained in the step 3, and extracting the vehicle boundary line segment:
step 41, segmenting the data point set to obtain breakpoints and primarily distributing the breakpoints;
42, eliminating abnormal data sets from all the segmented data sets;
step 43. Calculate the boundary point p j+1 Performing reallocation, comparing boundary points p j+1 Distance d from adjacent line segments j By determining the distance d j Whether a given threshold is met to reassign the boundary point;
step 44. Calculate the neighbor set { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i ) L is the straight line l fitted to i = m +1, \8230;, k } c,m And l m+1,k Angle of (2)
And is in conjunction with a threshold value gamma thd In comparison, if
Step 45 is carried out, otherwise, the combination of the two straight lines is ended, the next adjacent line segment is traversed, and step 44 is continued until the traversal of all the sets is ended;
step 45, set of neighbors { p (x) i ,y i ) I = c, c +1, \ 8230;, m } and { p (x) i ,y i ) I = m +1, \ 8230;, k }, merging, fitting straight line by using least square method, and calculating fitting error square sum E 2 And is in conjunction with a threshold value
Comparing, if the value is less than the threshold value, performing straight line merging, otherwise traversing the next adjacent line segment, and returning to the step 44;
step 5, extracting a line segment from the vehicle contour obtained in the step 4, restoring the position and the attitude of the vehicle, establishing a parking space model and obtaining the minimum width of the parking space;
and 6, judging whether the parking space size meets the requirement or not according to the minimum width of the parking space.
2. The method for intelligently detecting the parking space based on the 2D laser radar as claimed in claim 1, wherein the step 5 comprises the following substeps:
step 51, calculating the boundary point of the first vehicle target
And boundary points of vehicle object two
Step 52, extracting the minimum width D _ Wide of the parking space min ；
Step 53, calculating the boundary point of the first vehicle target
To line segment
The shortest distance D 1to2 Boundary point with vehicle object two
To line segment
The shortest distance of the parking space is the minimum width D _ Wide of the parking space min ＝min{D 1to2 ，D 2to1 }，D 1to2 Right boundary vertex representing vehicle object one
To line segment
The shortest distance of (a); d 2to1 Left boundary vertex representing similarly available vehicle object two
To line segment
The shortest distance of (c).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810549473.5A CN109001757B (en) | 2018-05-31 | 2018-05-31 | Parking space intelligent detection method based on 2D laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810549473.5A CN109001757B (en) | 2018-05-31 | 2018-05-31 | Parking space intelligent detection method based on 2D laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109001757A CN109001757A (en) | 2018-12-14 |
| CN109001757B true CN109001757B (en) | 2022-12-20 |
Family
ID=64574051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810549473.5A Active CN109001757B (en) | 2018-05-31 | 2018-05-31 | Parking space intelligent detection method based on 2D laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109001757B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109591850A (en) * | 2018-12-24 | 2019-04-09 | 郑州畅想高科股份有限公司 | A kind of track foreign matter detecting method and device |
| CN110335282B (en) * | 2018-12-25 | 2023-04-18 | 广州启明星机器人有限公司 | Contour line segment feature extraction method based on grids |
| CN109799513B (en) * | 2019-01-04 | 2023-06-23 | 广西大学 | Indoor unknown environment positioning method based on linear characteristics in two-dimensional laser radar data |
| CN110705385B (en) * | 2019-09-12 | 2022-05-03 | 深兰科技（上海）有限公司 | Method, device, equipment and medium for detecting angle of obstacle |
| CN111311925B (en) | 2020-01-21 | 2022-02-11 | 阿波罗智能技术(北京)有限公司 | Parking space detection method and device, electronic equipment, vehicle and storage medium |
| CN112612281A (en) * | 2020-12-24 | 2021-04-06 | 奇瑞汽车股份有限公司 | Parking control method and device for automobile and computer storage medium |
| CN112776797A (en) * | 2021-02-27 | 2021-05-11 | 重庆长安汽车股份有限公司 | Original parking space parking establishment method and system, vehicle and storage medium |
| CN112799096B (en) * | 2021-04-08 | 2021-07-13 | 西南交通大学 | Map construction method based on low-cost vehicle-mounted two-dimensional laser radar |
| CN114999215A (en) * | 2022-05-27 | 2022-09-02 | 北京筑梦园科技有限公司 | Vehicle information acquisition method and device and parking management system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065519B (en) * | 2012-12-28 | 2015-04-01 | 苏州苏迪智能系统有限公司 | Detecting system of ramp fixed point stopping and starting and detecting method of ramp fixed point stopping and starting |
| CN103197323B (en) * | 2013-04-17 | 2014-11-26 | 清华大学 | Scanning data matching method and device for laser distance measuring machine |
| CN103600707B (en) * | 2013-11-06 | 2016-08-17 | 同济大学 | A kind of parking position detection device and method of Intelligent parking system |
| CN104880160B (en) * | 2015-05-27 | 2017-05-17 | 西安交通大学 | Two-dimensional-laser real-time detection method of workpiece surface profile |
| CN105701479B (en) * | 2016-02-26 | 2019-03-08 | 重庆邮电大学 | Intelligent vehicle multilasered optical radar fusion identification method based on target signature |
| CN106952496B (en) * | 2017-04-11 | 2019-08-16 | 苏州梦伯乐信息科技有限公司 | Pilotless automobile intelligent car-searching position method |
| CN106997688B (en) * | 2017-06-08 | 2020-03-24 | 重庆大学 | Parking lot parking space detection method based on multi-sensor information fusion |
| CN107657812B (en) * | 2017-08-29 | 2021-10-29 | 耀灵人工智能(浙江)有限公司 | Method for dynamically planning parking space according to traffic flow prediction |
| CN107776570B (en) * | 2017-09-19 | 2020-09-01 | 广州汽车集团股份有限公司 | Full-automatic parking method and full-automatic parking system |
| CN207233218U (en) * | 2017-09-27 | 2018-04-13 | 重庆大学 | Parking lot empty parking space inspection device based on 2D laser radars |
-
2018
- 2018-05-31 CN CN201810549473.5A patent/CN109001757B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109001757A (en) | 2018-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109001757B (en) | Parking space intelligent detection method based on 2D laser radar | |
| CN111337941B (en) | Dynamic obstacle tracking method based on sparse laser radar data | |
| Kang et al. | Automatic targetless camera–lidar calibration by aligning edge with gaussian mixture model | |
| JP5539680B2 (en) | Object tracking using linear features | |
| CN108958282B (en) | Three-dimensional space path planning method based on dynamic spherical window | |
| Muhovič et al. | Obstacle tracking for unmanned surface vessels using 3-D point cloud | |
| Huber et al. | A new approach to 3-d terrain mapping | |
| CN116129376A (en) | Road edge detection method and device | |
| CN108280840B (en) | Road real-time segmentation method based on three-dimensional laser radar | |
| CN112513679B (en) | Target identification method and device | |
| JP2006510097A (en) | A method for recognizing and tracking objects | |
| US10444398B2 (en) | Method of processing 3D sensor data to provide terrain segmentation | |
| CN111308500A (en) | Obstacle sensing method and device based on single-line laser radar and computer terminal | |
| CN110736456A (en) | Two-dimensional laser real-time positioning method based on feature extraction in sparse environment | |
| CN111354022A (en) | Target tracking method and system based on kernel correlation filtering | |
| Morris et al. | A view-dependent adaptive matched filter for ladar-based vehicle tracking | |
| Wei et al. | Building a local floor map by use of ultrasonic and omni-directional vision sensors | |
| Nitsch et al. | 3d ground point classification for automotive scenarios | |
| CN109917418B (en) | Method for measuring non-reflection area of laser radar | |
| CN111474560A (en) | Obstacle positioning method, device and equipment | |
| CN114217641B (en) | Unmanned aerial vehicle power transmission and transformation equipment inspection method and system in non-structural environment | |
| Liu et al. | Natural landmark extraction in 2D laser data based on local curvature scale for mobile robot navigation | |
| CN111239761B (en) | Method for indoor real-time establishment of two-dimensional map | |
| CN114489050A (en) | Obstacle avoidance route control method, device, equipment and storage medium for straight line driving | |
| EP3229173B1 (en) | Method and apparatus for determining a traversable path |
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 |