CN110726993A - Obstacle detection method using single line laser radar and millimeter wave radar - Google Patents
Obstacle detection method using single line laser radar and millimeter wave radar Download PDFInfo
- Publication number
- CN110726993A CN110726993A CN201910840854.3A CN201910840854A CN110726993A CN 110726993 A CN110726993 A CN 110726993A CN 201910840854 A CN201910840854 A CN 201910840854A CN 110726993 A CN110726993 A CN 110726993A
- Authority
- CN
- China
- Prior art keywords
- image
- obstacle
- pixel
- obj
- value
- 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.)
- Granted
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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for detecting obstacles by using a single-line laser radar and a millimeter-wave radar, which comprises the steps of obtaining single-line laser radar obstacle data and millimeter-wave radar obstacle data, obtaining an obstacle list, obtaining obstacle outline information, obtaining longitudinal relative speed and transverse relative speed information of obstacles and outputting obstacle information; the invention comprehensively utilizes the advantages of the single-line laser radar and the millimeter wave radar, uses the point cloud information of the single-line laser radar to generate the outline information of the obstacle, and uses the longitudinal relative speed and the transverse relative speed in the obstacle information of the millimeter wave radar to generate the longitudinal relative speed and the transverse relative speed of the obstacle. After the method is adopted to synthesize the single-line laser radar obstacle information and the millimeter wave radar obstacle information, the obtained obstacle information can simultaneously contain the accurate outline and the accurate speed, and the cost of the scheme is greatly reduced compared with the cost of the method adopting a four-line laser radar.
Description
Technical Field
The invention belongs to the technical field of road traffic, and particularly relates to a method for detecting an obstacle in automatic driving.
Background
In the automatic driving process, the automatic driving system needs to acquire surrounding obstacle information so as to achieve the purpose of safely driving on a road.
The automatic driving system needs to control the vehicle so that the vehicle can run smoothly on the lane and does not collide with the obstacle. The obstacles refer to objects which influence the running of the automatic driving vehicle, such as pedestrians, motor vehicles, bicycles, cone barrels, garbage cans and the like on the road. Obstacles include both moving obstacles and stationary obstacles.
The sixteen-line laser radar on the market at present has the characteristics of high price, poor reliability, high position precision of obstacles in output data and no speed information output. The four-wire laser radar has the characteristics of high price, poor reliability, high position precision of obstacles in output data and speed information output. The single-line laser radar has the characteristics of high price, high reliability, high position precision of obstacles in output data and no speed information output. The obstacle detected by the millimeter wave radar has the characteristics of poor position precision and high speed precision.
In the automatic driving process, in order to better follow the vehicle running to the vehicle running ahead, the automatic driving system needs to acquire accurate speed information of the vehicle running ahead; in order to avoid obstacles such as other vehicles stopped on the road, it is necessary to acquire accurate contour information of the obstacles. That is, the automatic driving system needs to acquire accurate speed information and accurate contour information of the obstacle at the same time.
How to more economically and effectively acquire obstacle information is an important issue facing the automatic driving industry at present.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for detecting obstacles by using a single-line laser radar and a millimeter-wave radar.
The purpose of the invention is realized by the following technical scheme.
An obstacle detection method using a single line laser radar and a millimeter wave radar, comprising the steps of:
s1, establishing a rectangular coordinate system with the unit of meter, wherein the central point of a rear axle of the vehicle body is taken as an origin, the right direction of the horizontal direction is taken as the positive direction of an x-axis, and the front direction of the horizontal direction is taken as the positive direction of a y-axis, and taking the coordinate system as a coordinate system of the vehicle body;
acquiring data of the obstacle through a single-line laser radar and a millimeter-wave radar respectively, and establishing an obstacle coordinate system;
converting the obstacle coordinate system to be below the body coordinate system;
s2, projecting each point cloud data of the obtained single-line laser radar onto a two-dimensional plane to obtain an image with pixel width and height, representing the size of a single pixel point of the image as GridSize meter and GridSize meter, wherein the representable detection range of the image is GridFront meter in front of a vehicle, GridBack meter in back of the vehicle, GridSide meter on left side of the vehicle and GridSide meter on right side of the vehicle, and the pixel size of the image is ImageW ImageH, so that the pixel size function is as follows:
the coordinate of the center point of the rear axle of the vehicle body is set as
An image coordinate system in units of pixels;
setting coordinates of points under a vehicle body coordinate system as (x, y), and coordinates of pixel points under a corresponding image coordinate system as (x ', y'); the conversion formula from the vehicle body coordinate system to the image coordinate system is as follows:
the conversion formula from the image coordinate system to the vehicle body coordinate system is as follows:
and recording a conversion formula from the image coordinate system to the vehicle body coordinate system as follows:
(x，y)＝ImageUV2CarXY(x′，y′)
setting the initial value of each pixel point in the image to be 0; converting the point in the single-line laser radar point cloud into a coordinate point in an image coordinate system, taking the point in the image range and setting the value of a pixel point of the corresponding coordinate to be 1; when the pixel points corresponding to the plurality of laser radar points are the same, the value of the pixel point is still set to be 1;
converting all the laser radar point cloud data to obtain a binary image with the pixel size ImageW and ImageH;
expanding the binary image, and then analyzing a communicating body to obtain a barrier list and a profile of the expanded barrier;
s3, recording an image before expansion as Img, recording an image after expansion as imgdialate, and performing communication body analysis on the imgdialate to obtain a plurality of obstacles, wherein the number of the obtained obstacles is an integer n, and each obstacle is respectively recorded as Obj1, Obj2, and Obj, and the expanded outlines corresponding to each obstacle are respectively con _ dilate1, con _ dilate2, contour _ dilate and contour _ dilate;
creating an image ImgDilateid with the same size as the ImgDilate, and setting the initial value of each pixel point in the image ImgDilateid to be 0; taking the 1 st dilated contour _ scale 1, and filling the contour _ scale 1 with a value of 1 in the image ImgDilateId; taking the 2 nd dilated contour _ scale 2, and filling the contour _ scale 2 with a value of 2 in the image ImgDilateId; in analogy, the ith expanded contour contourj dilatei is taken, and the contour contourj dilatei is filled with a value i in the image imgdilated; wherein i is an integer from 3 to n;
creating an image ImgId with the same size as imgdilatid, setting the initial value of each pixel point in the image ImgId to be 0, and then updating the value of ImgId by using the following formula:
ImgId＝ImgDilateId·Img
the specific meaning of the image dot multiplication in the above formula is: the value of each pixel point in the image ImgId is the value of the pixel point corresponding to the image ImgDilateId multiplied by the value of the pixel point corresponding to the image Img, that is:
ImgId(i，j)＝ImgDilateId(i，j)×Img(i，j)
in the above formula, ImgId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image ImgId, ImgDilateId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image imgdilad, Img (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image Img, i is an integer greater than or equal to 0 and less than ImageH, and j is an integer greater than or equal to 0 and less than ImageW;
taking the positions of all pixel points with the pixel values equal to 1 in the image ImgId as a 1 st contour contourr 1; taking the positions of all pixel points with the pixel values equal to 2 in the image ImgId as a 2 nd contour contourr 2; and so on, taking the positions of all pixel points with the pixel values equal to i in the image ImgId as the ith contour contouri, wherein i is an integer from 3 to n; can be expressed by the following formula:
contouri＝{(x，y)|(x，y)＝ImageUV2CarXY(x′，y′)，ImgId(x′，y′)＝i，
0≤x′＜ImageH，0≤y′＜ImageW}
the contour obtained by the above formula is a few disordered position points;
calculating the center point, length and width of each obstacle;
s4, extracting corresponding information from the information of the millimeter wave radar obstacle, wherein the information comprises a position, a longitudinal relative speed and a transverse relative speed;
and S5, outputting the information of the outline, the center point, the length, the width, the longitudinal relative speed and the transverse relative speed of each obstacle.
According to the above scheme, the value of each pixel point on the binary image in step S2 is 1 or 0: when the value of the pixel point is 1, the fact that a real obstacle exists at the actual position corresponding to the pixel point is represented；When the value of the pixel point is 0, the fact that no real obstacle exists at the actual position corresponding to the pixel point is represented;
the method for expanding the binary image comprises the step of expanding non-0 pixel points in the image by 0.5 meter, namely expanding the pixel points to the periphery
A pixel, wherein
Represents an integer obtained by rounding down the real number 0.5/GridSize.
According to the scheme, the value range of the x coordinate value of the pixel point in the step S2 is [0, ImageW-1], and the value range of the y coordinate value of the pixel point is [0, ImageH-1 ]; and the x coordinate value and the y coordinate value of the pixel point are integers.
According to the scheme, the method for extracting the longitudinal relative speed and the transverse relative speed in the step S4 specifically comprises the following steps:
s41, recording the millimeter wave radar obstacle as objRaar, and recording the obstacle extracted from the point cloud of the laser radar obstacle information as Obj;
s42, sequentially taking each objRadar, calculating the Obj closest to the objRadar, and matching the objRadar with the Obj;
s43, sequentially taking each Obj, if a certain Obj radar is matched with the Obj, judging the distance between the Obj and the Obj radar, assigning the longitudinal relative speed of the Obj radar to the longitudinal relative speed of the Obj and assigning the transverse relative speed of the Obj radar to the transverse relative speed of the Obj when the distance is less than MatchDist meters; if no Obj radar is matched with the Obj, or the distance between the matched Obj radar and the Obj is greater than or equal to MatchDist meters, considering the Obj as a relatively static target, and setting the longitudinal relative speed and the transverse relative speed of the relative target as 0; wherein, the MatchDist is a given positive real number.
According to the above scheme, the method for calculating the distance between Obj and Obj in step S42 includes: and taking each contour point of the Obj contour, calculating the distance between the contour point and the Obj radar, and taking the minimum value in each distance as the distance between the Obj radar and the Obj.
According to the scheme, in the information of the millimeter wave radar obstacle in the step S4, the units of the x coordinate and the y coordinate of the position are both meters, and the units of the longitudinal relative speed and the transverse relative speed are both meters/second.
According to the scheme, the contour of the obstacle in the step S5 is composed of a plurality of unordered points, the unordered points are called contour points of each contour, the unit of x coordinate and y coordinate of each contour point in the contour of the obstacle is meter, the unit of x coordinate and y coordinate of the center point of the obstacle is meter, the unit of length and width of the obstacle is meter, and the unit of longitudinal relative speed and transverse relative speed of the obstacle is meter/second.
According to the invention, the single-line laser radar barrier information and the millimeter wave radar barrier information are integrated, the obtained barrier information can simultaneously comprise an accurate outline and an accurate speed, and the cost of the scheme is greatly reduced compared with that of a scheme adopting a four-line laser radar.
Drawings
Fig. 1 is a schematic flow chart of an obstacle detection method using a single line laser radar and a millimeter wave radar according to the present invention.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the embodiment of the invention includes acquiring single line laser radar obstacle data and millimeter wave radar obstacle data, acquiring an obstacle list, acquiring obstacle profile information, acquiring longitudinal relative speed and transverse relative speed information of an obstacle, and outputting obstacle information.
The method specifically comprises the following steps:
s1, acquiring single-line laser radar obstacle data and millimeter wave radar obstacle data:
and establishing a rectangular coordinate system with the right direction as the positive direction of the x axis, the forward direction as the positive direction of the y axis, the central point of the rear axle of the vehicle body as the original point and the unit of meter. The coordinate system is used as the coordinate system of the vehicle body adopted by the method.
And acquiring data of the single-line laser radar obstacle and acquiring data of the millimeter-wave radar obstacle.
And converting the coordinate systems of the single-line laser radar barrier and the millimeter-wave radar barrier into the vehicle body coordinate system.
S2, obtaining an obstacle list:
the data of the single-line laser radar obstacle is point cloud data, namely a plurality of points with x coordinate values and y coordinate values under a vehicle body coordinate system. And projecting the laser radar point cloud onto a two-dimensional plane to obtain an image with the pixel width and the pixel height.
When the image is generated, the size of a single pixel point is GridSize meter and GridSize meter, and the detection range which can be represented by the image is GridFront meter in front of the vehicle, GridBack meter behind the vehicle, GridSide meter on the left side of the vehicle and GridSide meter on the right side of the vehicle. The pixel size of the image is ImageW ImageH, wherein,
the coordinate of the center point of the rear axle of the vehicle body is set as
The unit is the image coordinate system of the pixel. The value range of the x coordinate value of the pixel point in the image is [0, ImageW-1]]The value range of the y coordinate value of the pixel point is [0, ImageH-1]]. And the x coordinate value and the y coordinate value of the pixel points in the image are integers.
Setting coordinates of points under a vehicle body coordinate system as (x, y), and coordinates of pixel points under a corresponding image coordinate system as (x ', y'); the conversion formula from the vehicle body coordinate system to the image coordinate system is as follows:
the conversion formula from the image coordinate system to the vehicle body coordinate system is as follows,
and recording a conversion formula from the image coordinate system to the vehicle body coordinate system as follows:
(x，y)＝ImageUV2CarXY(x′，y′)
in the image, the initial value of each pixel point is set to 0. When converting a point in the single-line laser radar point cloud into a coordinate point in an image coordinate system, if the point is in an image range, setting the value of a pixel point of the corresponding coordinate to be 1. When the pixel points corresponding to the plurality of laser radar points are the same, the value of the pixel point is still set to be 1.
After all the lidar point cloud data are converted, a binary image with the pixel size of ImageW ImageH is obtained, and the value of each pixel point on the image is either 1 or 0.
When the value of the pixel point is 1, the fact that a real obstacle exists at the actual position corresponding to the pixel point is represented; when the value of the pixel point is 0, it indicates that there is no real obstacle at the actual position corresponding to the pixel point.
The generated image is dilated, and then the connected body analysis is carried out to obtain an obstacle list and the outline of the dilated obstacle.
The image is dilated to solve the problem that when a real obstacle is far away, the real obstacle may be extracted as a plurality of obstacles. For example, when a car is far away, it may be detected as two obstacles. In the actual project, the adopted method is to expand the non-0 pixel points in the image by 0.5 m, namely to expand to the surrounding areasAnd (4) a pixel.
S3, obtaining obstacle contour information:
recording an image before inflation as Img, recording an image after inflation as imgdialate, performing communication body analysis on the imgdialate to obtain a plurality of obstacles, setting the number of the obtained obstacles as an integer n, and recording each obstacle as Obj1, Obj2, and Objn, wherein expanded outlines corresponding to each obstacle are respectively a constant _ dilate1, a constant _ dilate2, and a constant _ dilate.
Creating an image ImgDilateid with the same size as the ImgDilate, and setting the initial value of each pixel point in the image ImgDilateid to be 0; taking the 1 st dilated contour _ scale 1, and filling the contour _ scale 1 with a value of 1 in the image ImgDilateId; taking the 2 nd dilated contour _ scale 2, and filling the contour _ scale 2 with a value of 2 in the image ImgDilateId; in analogy, the ith expanded contour contourj dilatei is taken, and the contour contourj dilatei is filled with a value i in the image imgdilated; wherein i is an integer from 3 to n;
creating an image ImgId with the same size as imgdilatid, setting the initial value of each pixel point in the image ImgId to be 0, and then updating the value of ImgId by using the following formula:
ImgId＝ImgDilateId·Img
the specific meaning of the image dot multiplication in the above formula is: the value of each pixel point in the image ImgId is the value of the pixel point corresponding to the image ImgDilateId multiplied by the value of the pixel point corresponding to the image Img, that is:
ImgId(i，j)＝ImgDilateId(i，j)×Img(i，j)
in the above formula, ImgId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image ImgId, ImgDilateId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image imgdilad, Img (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image Img, i is an integer greater than or equal to 0 and less than ImageH, and j is an integer greater than or equal to 0 and less than ImageW;
taking the positions of all pixel points with the pixel values equal to 1 in the image ImgId as a 1 st contour contourr 1; taking the positions of all pixel points with the pixel values equal to 2 in the image ImgId as a 2 nd contour contourr 2; and so on, taking the positions of all pixel points with the pixel values equal to i in the image ImgId as the ith contour contouri, wherein i is an integer from 3 to n; can be expressed by the following formula:
contouri＝{(x，y)|(x，y)＝ImageUV2CarXY(x′，y′)，ImgId(x′，y′)＝i，
0≤x′＜ImageH，0≤y′＜ImageW}
the contour obtained by the formula is a plurality of disordered position points which can basically represent real obstacles due to the dense point cloud of the single-line laser radar.
The center point, length and width of each obstacle are calculated.
S4, acquiring longitudinal relative speed and transverse relative speed information of the obstacle:
the obstacle extracted from the point cloud information of the laser radar obstacle does not contain a longitudinal relative speed and a transverse relative speed, and in order to set correct values for the longitudinal relative speed and the transverse relative speed of the obstacle, corresponding information needs to be extracted from the information of the millimeter wave radar obstacle. The information of the millimeter wave radar obstacle includes a position (both in units of x-coordinate and y-coordinate are meters), a longitudinal relative velocity (unit: m/sec), and a lateral relative velocity (unit: m/sec).
For convenience of description, the millimeter wave radar obstacle is referred to as Obj, and the obstacle extracted from the point cloud of the laser radar obstacle information is referred to as Obj.
And sequentially taking each objRadar, calculating the Obj closest to the objRadar, and considering the objRadar to be matched with the Obj.
And sequentially taking each Obj, judging the distance between the Obj and the Obj if a certain Obj radar is matched with the Obj, assigning the longitudinal relative speed of the Obj radar to the longitudinal relative speed of the Obj and assigning the transverse relative speed of the Obj radar to the transverse relative speed of the Obj when the distance is less than MatchDist meters. If no Obj radar is matched with the Obj, or the distance between the matched Obj radar and the Obj is greater than or equal to MatchDist meters, the Obj is considered as a relatively static target, and the longitudinal relative speed and the transverse relative speed are set to be zero. Where MatchDist is some given positive real number.
The method for calculating the distance between the Obj and the Obj comprises the steps of taking each point of the Obj outline, calculating the distance between the outline point and the Obj, and taking the minimum distance in the distances as the distance between the Obj and the Obj.
S5, outputting obstacle information:
and outputting the information of the outline of each obstacle (the unit of the x coordinate and the unit of the y coordinate of each point are both meters), the center point (the unit of the x coordinate and the unit of the y coordinate are both meters), the length (the unit: meters), the width (the unit: meters), the longitudinal relative speed (the unit: meters/second) and the transverse relative speed (the unit: meters/second).
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (8)
1. A method for detecting an obstacle using a single line laser radar and a millimeter wave radar, comprising the steps of:
s1, establishing a rectangular coordinate system with the unit of meter, wherein the central point of a rear axle of the vehicle body is taken as an origin, the right direction of the horizontal direction is taken as the positive direction of an x-axis, and the front direction of the horizontal direction is taken as the positive direction of a y-axis, and taking the coordinate system as a coordinate system of the vehicle body;
acquiring data of the obstacle through a single-line laser radar and a millimeter-wave radar respectively, and establishing an obstacle coordinate system;
converting the obstacle coordinate system to be below the body coordinate system;
s2, projecting each point cloud data of the obtained single-line laser radar onto a two-dimensional plane to obtain an image with pixel width and height, representing the size of a single pixel point of the image as GridSize meter and GridSize meter, wherein the representable detection range of the image is GridFront meter in front of a vehicle, GridBack meter in back of the vehicle, GridSide meter on left side of the vehicle and GridSide meter on right side of the vehicle, and the pixel size of the image is ImageW ImageH, so that the pixel size function is as follows:
the coordinate of the center point of the rear axle of the vehicle body is set as
An image coordinate system in units of pixels;
setting coordinates of points under a vehicle body coordinate system as (x, y), and coordinates of pixel points under a corresponding image coordinate system as (x ', y'); the conversion formula from the vehicle body coordinate system to the image coordinate system is as follows:
the conversion formula from the image coordinate system to the vehicle body coordinate system is as follows:
and recording a conversion formula from the image coordinate system to the vehicle body coordinate system as follows:
(x，y)＝ImageUV2CarXY(x′，y′)
setting the initial value of each pixel point in the image to be 0; converting the point in the single-line laser radar point cloud into a coordinate point in an image coordinate system, taking the point in the image range and setting the value of a pixel point of the corresponding coordinate to be 1; when the pixel points corresponding to the plurality of laser radar points are the same, the value of the pixel point is still set to be 1;
converting all the laser radar point cloud data to obtain a binary image with the pixel size ImageW and ImageH;
expanding the binary image, and then analyzing a communicating body to obtain a barrier list and a profile of the expanded barrier;
s3, recording an image before expansion as Img, recording an image after expansion as imgdialate, and performing communication body analysis on the imgdialate to obtain a plurality of obstacles, wherein the number of the obtained obstacles is an integer n, and each obstacle is respectively recorded as Obj1, Obj2, and Obj, and the expanded outlines corresponding to each obstacle are respectively con _ dilate1, con _ dilate2, contour _ dilate and contour _ dilate;
creating an image ImgDilateid with the same size as the ImgDilate, and setting the initial value of each pixel point in the image ImgDilateid to be 0; taking the 1 st dilated contour _ scale 1, and filling the contour _ scale 1 with a value of 1 in the image ImgDilateId; taking the 2 nd dilated contour _ scale 2, and filling the contour _ scale 2 with a value of 2 in the image ImgDilateId; in analogy, the ith expanded contour contourj dilatei is taken, and the contour contourj dilatei is filled with a value i in the image imgdilated; wherein i is an integer from 3 to n;
acquiring position points of each contour;
calculating the center point, length and width of each obstacle;
s4, extracting corresponding information from the information of the millimeter wave radar obstacle, wherein the information comprises a position, a longitudinal relative speed and a transverse relative speed;
and S5, outputting the information of the outline, the center point, the length, the width, the longitudinal relative speed and the transverse relative speed of each obstacle.
2. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 1, wherein the value of each pixel point on the binary image in step S2 is 1 or 0: when the value of the pixel point is 1, indicating that a real obstacle exists at the actual position corresponding to the pixel point; when the value of the pixel point is 0, the fact that no real obstacle exists at the actual position corresponding to the pixel point is represented;
the method for expanding the binary image comprises the step of expanding non-0 pixel points in the image by 0.5 meter, namely expanding the pixel points to the periphery
A pixel, wherein
Represents an integer obtained by rounding down the real number 0.5/GridSize.
3. The obstacle detection method using the single line laser radar and the millimeter wave radar according to claim 1, wherein the x-coordinate value of the pixel in step S2 is in a range of [0, ImageW-1], and the y-coordinate value of the pixel is in a range of [0, ImageH-1 ]; and the x coordinate value and the y coordinate value of the pixel point are integers.
4. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 1, wherein the method of acquiring the position point of each contour in step S3 is specifically:
creating an image ImgId with the same size as imgdilatid, setting the initial value of each pixel point in the image ImgId to be 0, and then updating the value of ImgId by using the following formula:
ImgId＝ImgDilateId·Img
the specific meaning of the image dot multiplication in the above formula is: the value of each pixel point in the image ImgId is the value of the pixel point corresponding to the image ImgDilateId multiplied by the value of the pixel point corresponding to the image Img, that is:
ImgId(i，j)＝ImgDilateId(i，j)×Img(i，j)
in the above formula, ImgId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image ImgId, ImgDilateId (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image imgdilad, Img (i, j) represents a pixel value of a pixel at a position of an ith row and a jth column in the image Img, i is an integer greater than or equal to 0 and less than ImageH, and j is an integer greater than or equal to 0 and less than ImageW;
taking the positions of all pixel points with the pixel values equal to 1 in the image ImgId as a 1 st contour contourr 1; taking the positions of all pixel points with the pixel values equal to 2 in the image ImgId as a 2 nd contour contourr 2; and so on, taking the positions of all pixel points with the pixel values equal to i in the image ImgId as the ith contour contouri, wherein i is an integer from 3 to n; can be expressed by the following formula:
contouri＝{(x，y)|(x，y)＝ImageUV2CarXY(x′，y′)，ImgId(x′，y′)＝i，
0≤x′＜ImageH，0≤y′＜ImageW}
the profile obtained by the above equation is a few disordered location points.
5. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 1, wherein the method of extracting the longitudinal relative velocity and the lateral relative velocity in step S4 specifically comprises:
s41, recording the millimeter wave radar obstacle as objRaar, and recording the obstacle extracted from the point cloud of the laser radar obstacle information as Obj;
s42, sequentially taking each objRadar, calculating the Obj closest to the objRadar, and matching the objRadar with the Obj;
s43, sequentially taking each Obj, if a certain Obj radar is matched with the Obj, judging the distance between the Obj and the Obj radar, assigning the longitudinal relative speed of the Obj radar to the longitudinal relative speed of the Obj and assigning the transverse relative speed of the Obj radar to the transverse relative speed of the Obj when the distance is less than MatchDist meters; if no Obj radar is matched with the Obj, or the distance between the matched Obj radar and the Obj is greater than or equal to MatchDist meters, considering the Obj as a relatively static target, and setting the longitudinal relative speed and the transverse relative speed of the relative target as 0; wherein, the MatchDist is a given positive real number.
6. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 5, wherein the method of calculating the distance between Obj and radar in step S42 is: and taking each contour point of the Obj contour, calculating the distance between the contour point and the Obj radar, and taking the minimum value in each distance as the distance between the Obj radar and the Obj.
7. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 1, wherein in the information of the millimeter wave radar obstacle in step S4, both the x coordinate and the y coordinate of the position are in meters, and both the longitudinal relative velocity and the lateral relative velocity are in meters/second.
8. The obstacle detection method using the singlet laser radar and the millimeter wave radar according to claim 1, wherein the profile of the obstacle in step S5 is composed of a plurality of disordered points, the disordered points are referred to as profile points of each profile, x-and y-coordinates of each profile point in the obstacle profile are both in meters, x-and y-coordinates of the center point of the obstacle are both in meters, length and width of the obstacle are both in meters, and longitudinal and transverse relative speeds of the obstacle are both in meters/second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840854.3A CN110726993B (en) | 2019-09-06 | 2019-09-06 | Obstacle detection method using single-line laser radar and millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840854.3A CN110726993B (en) | 2019-09-06 | 2019-09-06 | Obstacle detection method using single-line laser radar and millimeter wave radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110726993A true CN110726993A (en) | 2020-01-24 |
| CN110726993B CN110726993B (en) | 2023-07-04 |
Family
ID=69217888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910840854.3A Active CN110726993B (en) | 2019-09-06 | 2019-09-06 | Obstacle detection method using single-line laser radar and millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110726993B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111708016A (en) * | 2020-08-03 | 2020-09-25 | 北京理工大学 | Vehicle front collision early warning method with integration of millimeter wave radar and laser radar |
| 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 |
| CN112083441A (en) * | 2020-09-10 | 2020-12-15 | 湖南大学 | Obstacle detection method and system based on deep fusion of laser radar and millimeter wave radar |
| CN113296116A (en) * | 2021-05-14 | 2021-08-24 | 汤恩智能科技(苏州)有限公司 | Obstacle detection method, driving device, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000131432A (en) * | 1998-10-23 | 2000-05-12 | Honda Motor Co Ltd | Method for detecting obstruction to vehicle |
| CN106405555A (en) * | 2016-09-23 | 2017-02-15 | 百度在线网络技术（北京）有限公司 | Obstacle detecting method and device used for vehicle-mounted radar system |
| CN108037515A (en) * | 2017-12-27 | 2018-05-15 | 清华大学苏州汽车研究院（吴江） | A kind of laser radar and ultrasonic radar information fusion system and method |
| US20180172825A1 (en) * | 2016-12-16 | 2018-06-21 | Automotive Research & Testing Center | Environment recognition system using vehicular millimeter wave radar |
| CN108509972A (en) * | 2018-01-16 | 2018-09-07 | 天津大学 | A kind of barrier feature extracting method based on millimeter wave and laser radar |
| 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 |
| US20190011550A1 (en) * | 2017-07-04 | 2019-01-10 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for determing obstacle speed |
| CN109633676A (en) * | 2018-11-22 | 2019-04-16 | 浙江中车电车有限公司 | A kind of method and system based on the laser radar obstruction detection direction of motion |
-
2019
- 2019-09-06 CN CN201910840854.3A patent/CN110726993B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000131432A (en) * | 1998-10-23 | 2000-05-12 | Honda Motor Co Ltd | Method for detecting obstruction to vehicle |
| CN106405555A (en) * | 2016-09-23 | 2017-02-15 | 百度在线网络技术（北京）有限公司 | Obstacle detecting method and device used for vehicle-mounted radar system |
| US20180172825A1 (en) * | 2016-12-16 | 2018-06-21 | Automotive Research & Testing Center | Environment recognition system using vehicular millimeter wave radar |
| US20190011550A1 (en) * | 2017-07-04 | 2019-01-10 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for determing obstacle speed |
| CN109212530A (en) * | 2017-07-04 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining barrier speed |
| CN108037515A (en) * | 2017-12-27 | 2018-05-15 | 清华大学苏州汽车研究院（吴江） | A kind of laser radar and ultrasonic radar information fusion system and method |
| CN108509972A (en) * | 2018-01-16 | 2018-09-07 | 天津大学 | A kind of barrier feature extracting method based on millimeter wave and laser radar |
| 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 |
| CN109633676A (en) * | 2018-11-22 | 2019-04-16 | 浙江中车电车有限公司 | A kind of method and system based on the laser radar obstruction detection direction of motion |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111708016A (en) * | 2020-08-03 | 2020-09-25 | 北京理工大学 | Vehicle front collision early warning method with integration of millimeter wave radar and laser radar |
| CN112083441A (en) * | 2020-09-10 | 2020-12-15 | 湖南大学 | Obstacle detection method and system based on deep fusion of laser radar and millimeter wave radar |
| CN112083441B (en) * | 2020-09-10 | 2023-04-21 | 湖南大学 | Obstacle detection method and system for depth fusion of laser radar and millimeter wave radar |
| CN113296116A (en) * | 2021-05-14 | 2021-08-24 | 汤恩智能科技(苏州)有限公司 | Obstacle detection method, driving device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110726993B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110726993A (en) | Obstacle detection method using single line laser radar and millimeter wave radar | |
| US11106893B1 (en) | System and method for evaluating the perception system of an autonomous vehicle | |
| US11087186B2 (en) | Fixation generation for machine learning | |
| Zhao et al. | A cooperative vehicle-infrastructure based urban driving environment perception method using a DS theory-based credibility map | |
| CN110738121A (en) | front vehicle detection method and detection system | |
| Huang et al. | Robust inter-vehicle distance estimation method based on monocular vision | |
| EP2639781A1 (en) | Vehicle with improved traffic-object position detection | |
| CN110632617B (en) | Laser radar point cloud data processing method and device | |
| US11783507B2 (en) | Camera calibration apparatus and operating method | |
| CN108830159A (en) | A kind of front vehicles monocular vision range-measurement system and method | |
| CN108177524B (en) | ARHUD system and lane line drawing method thereof | |
| CN109917359B (en) | Robust vehicle distance estimation method based on vehicle-mounted monocular vision | |
| CN114419098A (en) | Moving target trajectory prediction method and device based on visual transformation | |
| CN111007534A (en) | Obstacle detection method and system using sixteen-line laser radar | |
| Zhang et al. | A novel vehicle reversing speed control based on obstacle detection and sparse representation | |
| US20220215561A1 (en) | Semantic-assisted multi-resolution point cloud registration | |
| CN114419143A (en) | Depth measuring method, depth measuring apparatus, and storage medium | |
| CN114919584A (en) | Motor vehicle fixed point target distance measuring method and device and computer readable storage medium | |
| Leu et al. | High speed stereo vision based automotive collision warning system | |
| CN108454619B (en) | Driving assistance method and system | |
| CN111857469B (en) | Road environment information reconstruction method, device and equipment | |
| CN115704907A (en) | Object recognition device, object recognition method, and recording medium | |
| CN115331482A (en) | Vehicle early warning prompting method and device, base station and storage medium | |
| CN109703556B (en) | Driving assistance method and apparatus | |
| Klappstein | Optical-flow based detection of moving objects in traffic scenes |
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 |