CN109633688A - A kind of laser radar obstacle recognition method and device - Google Patents
A kind of laser radar obstacle recognition method and device Download PDFInfo
- Publication number
- CN109633688A CN109633688A CN201811533572.0A CN201811533572A CN109633688A CN 109633688 A CN109633688 A CN 109633688A CN 201811533572 A CN201811533572 A CN 201811533572A CN 109633688 A CN109633688 A CN 109633688A
- Authority
- CN
- China
- Prior art keywords
- identified
- barrier
- frame
- point cloud
- laser radar
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The application provides a kind of laser radar obstacle recognition method and device, and the method includes obtaining the information of the barrier to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle;Judge whether barrier to be identified enters laser radar blind area described in N+1 frame;The barrier laser point cloud to be identified in nth frame is truncated according to the length that the barrier to be identified enters laser radar blind area;It is matched according to the barrier laser point cloud to be identified after truncation with the barrier laser point cloud to be identified in N+1 frame;Completion is carried out to the barrier laser point cloud to be identified in N+1 frame;According to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.The barrier that laser radar blind area can be entered to part identify, avoid wrong identification its length, distance causes the risk of collision, effectively improve the driving safety of automatic driving vehicle.
Description
[technical field]
This application involves automation field more particularly to a kind of laser radar obstacle recognition methods and device.
[background technique]
In automatic driving vehicle, it is integrated with multiclass sensor: GPS-IMU (Inertial Measurement Unit, Inertial
Measurement Unit) sensors such as integrated navigation module, camera, laser radar, millimetre-wave radar.
In automatic driving vehicle driving process, relies primarily on laser radar and barrier is detected, laser radar is to barrier
Hinder object that accurate shape perception may be implemented.But since laser radar is installed on automatic driving vehicle center of top front end,
Visual field longitudinal extent is positive and negative 15 degree.It is blocked by automatic driving vehicle car body, there are blind areas, generally 6-7m range.
Therefore, the detection of obstacles of existing automatic driving vehicle is only able to detect the barrier appeared in the laser radar visual field.And with
The traveling of automatic driving vehicle, barrier be highly likely to enter the blind area of laser radar, cause obstacle recognition mistake or loss,
For example, when barrier is bus, after partially entering blind area, laser radar may to its length and with automatic driving vehicle away from
From identification mistake, the car being identified as except blind area.This will affect the Vehicle Decision Method control of automatic driving vehicle
The decision of module, and then lead to risk of collision.
[summary of the invention]
The many aspects of the application provide a kind of laser radar obstacle recognition method and device, to solve barrier portion
Divide the problem of obstacle recognition mistake caused by entering laser radar blind area.
The one side of the application provides a kind of laser radar obstacle recognition method, comprising:
Obtain the information of the barrier to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle;
According to the information of the barrier to be identified in each frame in the preceding N frame in the N+1 frame, judge in N+1 frame
Whether the barrier to be identified enters laser radar blind area;If into laser radar blind area, according to the barrier to be identified
The barrier laser point cloud to be identified in nth frame is truncated in length into laser radar blind area;
According to the barrier laser point cloud to be identified after truncation and the barrier laser to be identified in N+1 frame
Point cloud is matched;If successful match, completion is carried out to the barrier laser point cloud to be identified in N+1 frame;
According to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation obtains laser thunder
The information of barrier to be identified up to the continuous N+1 frame around scanning automatic driving vehicle includes:
The point cloud for obtaining the barrier to be identified in each frame in the preceding N frame in N+1 frame, in the preceding N frame in N+1 frame
Each frame in obstacle object point cloud to be identified matched, determine the corresponding relationship of the barrier to be identified in each frame.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, according to the N+1
Whether the information of the barrier to be identified in each frame in preceding N frame in frame judges the barrier to be identified described in N+1 frame
Include: into laser radar blind area
By point cloud of the barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in N
Position, movement speed and moving direction and laser radar blind area range in frame, determine obstacle to be identified described in N+1 frame
Object enters the length of laser radar blind area.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, according to it is described to
The length that cognitive disorders object enters laser radar blind area carries out truncation packet to the barrier laser point cloud to be identified in nth frame
It includes:
According to blind area threedimensional model and described enter the length of laser radar blind area to the institute in nth frame with cognitive disorders object
Barrier laser point cloud to be identified is stated to be truncated.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, in N+1 frame
The barrier laser point cloud to be identified carry out completion and include:
If the barrier to be identified in nth frame does not enter laser radar blind area, according to the obstacle to be identified in nth frame
Object laser point cloud mends the laser point cloud for the part that the barrier to be identified in N+1 frame enters laser radar blind area
Entirely;
If the barrier to be identified in nth frame has entered laser radar blind area, according to the obstacle to be identified in nth frame
Laser point cloud after object completion enters the laser point of the part of laser radar blind area to the barrier to be identified in N+1 frame
Cloud carries out completion.
The another aspect of the application provides a kind of laser radar obstacle recognition system, comprising:
Module is obtained, for obtaining the obstacle to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle
The information of object;
Truncation module is sentenced for the information according to the barrier to be identified in each frame in the preceding N frame in the N+1 frame
Whether the barrier to be identified described in N+1 frame that breaks enters laser radar blind area;If into laser radar blind area, according to described
The length that barrier to be identified enters laser radar blind area cuts the barrier laser point cloud to be identified in nth frame
It is disconnected;
Completion module, for according in the barrier laser point cloud to be identified and N+1 frame after truncation to
Cognitive disorders object laser point cloud is matched;If successful match, to the barrier laser point cloud to be identified in N+1 frame
Carry out completion;
Identification module, for carrying out obstacle recognition according to the barrier laser point cloud to be identified after completion.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the acquisition mould
Block is specifically used for:
The point cloud for obtaining the barrier to be identified in each frame in the preceding N frame in N+1 frame, in the preceding N frame in N+1 frame
Each frame in obstacle object point cloud to be identified matched, determine the corresponding relationship of the barrier to be identified in each frame.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the truncation mould
Block is specifically used for:
By point cloud of the barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in N
Position, movement speed and moving direction and laser radar blind area range in frame, determine obstacle to be identified described in N+1 frame
Object enters the length of laser radar blind area.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the truncation mould
Block is specifically also used to:
According to blind area threedimensional model and described enter the length of laser radar blind area to the institute in nth frame with cognitive disorders object
Barrier laser point cloud to be identified is stated to be truncated.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the completion mould
Block is specifically used for:
If the barrier to be identified in nth frame does not enter laser radar blind area, according to the obstacle to be identified in nth frame
Object laser point cloud mends the laser point cloud for the part that the barrier to be identified in N+1 frame enters laser radar blind area
Entirely;
If the barrier to be identified in nth frame has entered laser radar blind area, according to the obstacle to be identified in nth frame
Laser point cloud after object completion enters the laser point of the part of laser radar blind area to the barrier to be identified in N+1 frame
Cloud carries out completion.
Another aspect of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, described
Method as described above is realized when program is executed by processor.
By the technical solution it is found that the barrier that the embodiment of the present application can enter laser radar blind area to part carries out
Identification avoids wrong identification its length, distance causes the risk of collision.
[Detailed description of the invention]
It in order to more clearly explain the technical solutions in the embodiments of the present application, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is some realities of the application
Example is applied, it for those of ordinary skill in the art, without any creative labor, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is the flow diagram for the laser radar obstacle recognition method that one embodiment of the application provides;
Fig. 2 is the structural schematic diagram for the laser radar obstacle recognition system that one embodiment of the application provides;
Fig. 3 shows the frame for being suitable for the exemplary computer system/server 012 for being used to realize embodiment of the present invention
Figure.
[specific embodiment]
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Whole other embodiments obtained without creative efforts, shall fall in the protection scope of this application.
Fig. 1 is the schematic diagram for the laser radar obstacle recognition method that one embodiment of the application provides, as shown in Figure 1, packet
Include following steps:
Step S11, the letter of the barrier to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle is obtained
Breath;
Step S12, according to the information of the barrier to be identified in each frame in the preceding N frame in the N+1 frame, judge
Whether barrier to be identified described in N+1 frame enters laser radar blind area;If into laser radar blind area, according to described to be identified
The barrier laser point cloud to be identified in nth frame is truncated in the length that barrier enters laser radar blind area;
Step S13, according to the barrier laser point cloud to be identified after truncation and the barrier to be identified in N+1 frame
Object laser point cloud is hindered to be matched;If successful match, the barrier laser point cloud to be identified in N+1 frame is mended
Entirely;
Step S14, according to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.
In a kind of preferred implementation of step S11,
The obstacle recognition method of the present embodiment is applied in unmanned technical field.In unmanned, nothing is needed
People drive vehicle can the barrier in automatic identification road be convenient for vehicle to make a policy and control in time in vehicle traveling
Safety traffic.The executing subject of the obstacle recognition method of the present embodiment can be obstacle recognition system, the barrier
Identification device can be integrated using multiple modules and be obtained, which specifically can be set in automatic driving vehicle
In, to control unmanned vehicle.
What the information of the barrier to be identified of the present embodiment can be strafed using laser radar.The specification of laser radar
It can be using 16 lines, 32 lines or 64 lines etc..Wherein the higher unit energy density for indicating laser radar of line number is bigger.This reality
Apply in example, the laser radar on current vehicle rotates 360 times in each second, scan make a circle in current vehicle week wait know
The information of other barrier is the information of frame barrier to be identified.The information of barrier to be identified in the present embodiment
It may include the point cloud of barrier to be identified and the reflected value of barrier to be identified.It is to be identified around current vehicle
Barrier can have one, can also have multiple.It, can be using the centroid position of current vehicle as coordinate after laser radar scanning
The origin of system, and taking the both direction for being parallel to horizontal plane is respectively the direction x and the direction y, as length direction and width direction,
Direction perpendicular to ground is the direction z, as short transverse.It then can be according to each of the point cloud of barrier to be identified
Relative position and distance of the point with origin, identify barrier to be identified in a coordinate system.
Preferably, the barrier to be identified in each frame in the preceding N frame in N+1 frame is matched, is determined in each frame
The corresponding relationship of barrier to be identified, and the barrier to be identified in each frame is identified.It, can be to avoid by matching operation
(such as there are multiple barriers) the barrier tracking failure to be identified under complex scene, by the same barrier to be identified in different frame
The problem of hindering object to be identified as different barriers.
Preferably, the identification is the obstacle to be identified for obtaining each frame around laser radar scanning automatic driving vehicle
It is carried out respectively after the information of object.
In this way, in the point cloud of the barrier to be identified of each frame, it can be according to every in each barrier to be identified
Some relative position with current vehicle, obtains the point cloud of each barrier to be identified.In addition, laser radar can also detect that often
The reflected value that each in one barrier to be identified is put.In practical application, coordinate system can also be with the mass center position of laser radar
It is set to origin, other directions are constant.The numerical value of the N of the present embodiment can take according to actual needs.
In a kind of preferred implementation of step S12,
According to the information of the barrier to be identified in each frame in the preceding N frame in N+1 frame, judge described in N+1 frame
Whether barrier to be identified enters laser radar blind area;If it is blind that the barrier to be identified described in N+1 frame enters laser radar
Area enters the length of laser radar blind area to the barrier laser to be identified in nth frame according to the barrier to be identified
Point cloud is truncated;
Preferably, in each frame in preceding N frame, obtain in the point cloud, with former frame of each barrier to be identified described in
The point cloud of cognitive disorders object is matched, with point cloud of the same barrier to be identified of determination in each frame in preceding N frame.
By point cloud of the same barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in N
In frame, using the centroid position of current automatic driving vehicle as position, movement speed and the moving direction in the coordinate system of origin.
Judge whether the barrier to be identified described in N+1 frame enters laser radar blind area, in the present embodiment, with current
It is laser radar blind area that the centroid position of automatic driving vehicle, which is within the scope of the 8m of origin,.
If the barrier to be identified has been positioned at laser radar blind area edge in nth frame, and automatic driving vehicle with
The relative velocity of the barrier to be identified is positive value, then it is blind to enter laser radar for the barrier to be identified described in N+1 frame
Area.Since the laser radar scanning period is very fast, such as 360 times per second, then in 1/360 second, the barrier to be identified can only portion
Divide and enter laser radar blind area, this, which has resulted in laser radar, can only obtain the fraction of laser light point cloud of the barrier to be identified.
The partial dot cloud of barrier to be identified described in N+1 frame and the distribution of the point cloud of barrier to be identified described in nth frame have occurred
Variation, then carrying out matched meeting in the process, it fails to match, and barrier to be identified described in N+1 frame is determined as new obstacle
Object, rather than barrier section to be identified described in nth frame enters laser radar blind area.
Therefore, according to the barrier to be identified in nth frame using the centroid position of current automatic driving vehicle as origin
Coordinate system in position, movement speed and moving direction and laser radar blind area range, determine described in N+1 frame to
Cognitive disorders object enters the length of laser radar blind area.
The barrier to be identified according to N+1 frame enter the length of laser radar blind area to described in nth frame to
Cognitive disorders object laser point cloud is truncated, so as to in N+1 frame partially enter laser radar blind area the barrier to be identified
The laser point cloud of object is hindered to be matched.
Preferably, laser radar blanking length is entered to the barrier laser point cloud interception to be identified in nth frame
Part, the threedimensional model that the interception is blocked in view of laser radar by automatic driving vehicle car body, rather than simple vertical section
It takes.
In a kind of preferred implementation of step S13,
According to the barrier laser point cloud to be identified after truncation and the barrier laser to be identified in N+1 frame
Point cloud is matched;
Wherein, the laser point cloud barrier laser point cloud to be identified in nth frame being truncated is prediction
N+1 frame in the barrier laser point cloud to be identified, by with the barrier to be identified actual in N+1 frame swash
Luminous point cloud is matched, and matching precision and success rate can be improved.
If successful match, completion is carried out to the barrier laser point cloud to be identified in N+1 frame;I.e. to N+1
The laser point cloud that the barrier to be identified in frame enters the part of laser radar blind area carries out completion.
Preferably, the completion is according to the barrier laser point cloud to be identified in nth frame to the institute in N+1 frame
The laser point cloud for stating the part that barrier to be identified enters laser radar blind area carries out completion.By being the institute in N+1 frame
It states and carries out completion on the basis of barrier laser point cloud to be identified, the laser point cloud after completion more meets actual barrier
Shape.
In a kind of preferred implementation of step S14,
According to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.
Preferably, according to the laser point cloud of the barrier to be identified after completion, the available obstacle to be identified
The parameters such as the accurate length of object, distance, can provide more accurate laser point cloud for the obstacle recognition to be identified, guarantee
The accuracy of the obstacle recognition to be identified.
In another preferred implementation of the present embodiment, if the barrier to be identified comes into nth frame
Part enters laser radar blind area, and the relative velocity of automatic driving vehicle and the barrier to be identified is positive value, in N+1
Barrier to be identified described in frame continues to part and enters laser radar blind area.Since the laser radar scanning period is very fast, such as
360 times per second, then in 1/360 second, the barrier to be identified can only partially enter laser radar blind area, this has resulted in swashing
Optical radar can only obtain the fraction of laser light point cloud of the barrier to be identified.The part of barrier to be identified described in N+1 frame
The distribution of the point cloud of point cloud and barrier to be identified described in nth frame is changed, then carries out matched to match mistake in the process
Lose, barrier to be identified described in N+1 frame be determined as new barrier, rather than barrier to be identified described in nth frame after
It is continuous to enter laser radar blind area.Using mode same as the above embodiments of the present application, it is truncated, is matched and completion.Wherein,
The laser point cloud of barrier to be identified described in the nth frame be to the laser point cloud of barrier to be identified described in nth frame into
The laser point cloud of the barrier to be identified obtained after row completion.
In another preferred implementation of the present embodiment, if the barrier to be identified comes into nth frame
Part enters laser radar blind area, and the relative velocity of automatic driving vehicle and the barrier to be identified is negative value, in N+1
Barrier to be identified described in frame continue to part enter laser radar blind area (into the part of laser radar blind area it is less or
All exit laser radar blind area).Since the laser radar scanning period is very fast, such as 360 times per second, then described in 1/360 second
Barrier to be identified can only partially enter laser radar blind area, this, which has resulted in laser radar, can only obtain the obstacle to be identified
The fraction of laser light point cloud of object.Barrier to be identified described in the partial dot cloud and nth frame of barrier to be identified described in N+1 frame
Point cloud distribution changed, then carry out it is matched during can it fails to match, by barrier to be identified described in N+1 frame
It is determined as new barrier, rather than barrier to be identified described in nth frame goes successively to laser radar blind area.Using with the application
The same mode of above-described embodiment carries out completion by the laser point cloud to barrier to be identified described in nth frame, with N+1
The laser point cloud of the barrier to be identified in frame is matched, after successful match, to the barrier to be identified in N+1 frame
Hinder the laser point cloud of object to carry out completion, according to the barrier laser point cloud after completion, carries out obstacle recognition, and whether judge it
Influence the traveling of automatic driving vehicle.Wherein, the laser point cloud of barrier to be identified described in the nth frame is in nth frame
The laser point cloud of the barrier to be identified carries out the laser point cloud of the barrier to be identified obtained after completion.
Using technical solution provided by the above embodiment, the barrier that can enter laser radar blind area to part is known
, do not avoid wrong identification its length, distance causes the risk of collision, effectively improve the driving safety of automatic driving vehicle
Property.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application
It is necessary.
The introduction about embodiment of the method above, below by way of Installation practice, to scheme of the present invention carry out into
One step explanation.
Fig. 2 is the structural schematic diagram for the laser radar obstacle recognition system that one embodiment of the application provides, such as Fig. 2 institute
Show, comprising:
Module 21 is obtained, for obtaining the barrier to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle
Hinder the information of object;
Truncation module 22, for the information according to the barrier to be identified in each frame in the preceding N frame in the N+1 frame,
Judge whether barrier to be identified enters laser radar blind area described in N+1 frame;If into laser radar blind area, according to institute
It states barrier to be identified and enters the length of laser radar blind area and the barrier laser point cloud to be identified in nth frame is cut
It is disconnected;
Completion module 23, for according in the barrier laser point cloud to be identified and N+1 frame after truncation
Barrier laser point cloud to be identified is matched;If successful match, to the barrier laser point to be identified in N+1 frame
Cloud carries out completion;
Identification module 24, for carrying out obstacle recognition according to the barrier laser point cloud to be identified after completion.
In a kind of preferred implementation for obtaining module 21,
The obstacle recognition method of the present embodiment is applied in unmanned technical field.In unmanned, nothing is needed
People drive vehicle can the barrier in automatic identification road be convenient for vehicle to make a policy and control in time in vehicle traveling
Safety traffic.The executing subject of the obstacle recognition method of the present embodiment can be obstacle recognition system, the barrier
Identification device can be integrated using multiple modules and be obtained, which specifically can be set in automatic driving vehicle
In, to control unmanned vehicle.
What the information of the barrier to be identified of the present embodiment can be strafed using laser radar.The specification of laser radar
It can be using 16 lines, 32 lines or 64 lines etc..Wherein the higher unit energy density for indicating laser radar of line number is bigger.This reality
Apply in example, the laser radar on current vehicle rotates 360 times in each second, scan make a circle in current vehicle week wait know
The information of other barrier is the information of frame barrier to be identified.The information of barrier to be identified in the present embodiment
It may include the point cloud of barrier to be identified and the reflected value of barrier to be identified.It is to be identified around current vehicle
Barrier can have one, can also have multiple.It, can be using the centroid position of current vehicle as coordinate after laser radar scanning
The origin of system, and taking the both direction for being parallel to horizontal plane is respectively the direction x and the direction y, as length direction and width direction,
Direction perpendicular to ground is the direction z, as short transverse.It then can be according to each of the point cloud of barrier to be identified
Relative position and distance of the point with origin, identify barrier to be identified in a coordinate system.
Preferably, the barrier to be identified in each frame in the preceding N frame in N+1 frame is matched, is determined in each frame
The corresponding relationship of barrier to be identified, and the barrier to be identified in each frame is identified.It, can be to avoid by matching operation
(such as there are multiple barriers) the barrier tracking failure to be identified under complex scene, by the same barrier to be identified in different frame
The problem of hindering object to be identified as different barriers.
Preferably, the identification is the obstacle to be identified for obtaining each frame around laser radar scanning automatic driving vehicle
It is carried out respectively after the information of object.
In this way, in the point cloud of the barrier to be identified of each frame, it can be according to every in each barrier to be identified
Some relative position with current vehicle, obtains the point cloud of each barrier to be identified.In addition, laser radar can also detect that often
The reflected value that each in one barrier to be identified is put.In practical application, coordinate system can also be with the mass center position of laser radar
It is set to origin, other directions are constant.The numerical value of the N of the present embodiment can take according to actual needs.
In a kind of preferred implementation of truncation module 22,
According to the information of the barrier to be identified in each frame in the preceding N frame in N+1 frame, judge described in N+1 frame
Whether barrier to be identified enters laser radar blind area;If it is blind that the barrier to be identified described in N+1 frame enters laser radar
Area enters the length of laser radar blind area to the barrier laser to be identified in nth frame according to the barrier to be identified
Point cloud is truncated;
Preferably, in each frame in preceding N frame, obtain in the point cloud, with former frame of each barrier to be identified described in
The point cloud of cognitive disorders object is matched, with point cloud of the same barrier to be identified of determination in each frame in preceding N frame.
By point cloud of the same barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in N
In frame, using the centroid position of current automatic driving vehicle as position, movement speed and the moving direction in the coordinate system of origin.
Judge whether the barrier to be identified described in N+1 frame enters laser radar blind area, in the present embodiment, with current
It is laser radar blind area that the centroid position of automatic driving vehicle, which is within the scope of the 8m of origin,.
If the barrier to be identified has been positioned at laser radar blind area edge in nth frame, and automatic driving vehicle with
The relative velocity of the barrier to be identified is positive value, then it is blind to enter laser radar for the barrier to be identified described in N+1 frame
Area.Since the laser radar scanning period is very fast, such as 360 times per second, then in 1/360 second, the barrier to be identified can only portion
Divide and enter laser radar blind area, this, which has resulted in laser radar, can only obtain the fraction of laser light point cloud of the barrier to be identified.
The partial dot cloud of barrier to be identified described in N+1 frame and the distribution of the point cloud of barrier to be identified described in nth frame have occurred
Variation, then carrying out matched meeting in the process, it fails to match, and barrier to be identified described in N+1 frame is determined as new obstacle
Object, rather than barrier section to be identified described in nth frame enters laser radar blind area.
Therefore, according to the barrier to be identified in nth frame using the centroid position of current automatic driving vehicle as origin
Coordinate system in position, movement speed and moving direction and laser radar blind area range, determine described in N+1 frame to
Cognitive disorders object enters the length of laser radar blind area.
The barrier to be identified according to N+1 frame enter the length of laser radar blind area to described in nth frame to
Cognitive disorders object laser point cloud is truncated, so as to in N+1 frame partially enter laser radar blind area the barrier to be identified
The laser point cloud of object is hindered to be matched.
Preferably, laser radar blanking length is entered to the barrier laser point cloud interception to be identified in nth frame
Part, the threedimensional model that the interception is blocked in view of laser radar by automatic driving vehicle car body, rather than simple vertical section
It takes.
In a kind of preferred implementation of completion module 23,
According to the barrier laser point cloud to be identified after truncation and the barrier laser to be identified in N+1 frame
Point cloud is matched;
Wherein, the laser point cloud barrier laser point cloud to be identified in nth frame being truncated is prediction
N+1 frame in the barrier laser point cloud to be identified, by with the barrier to be identified actual in N+1 frame swash
Luminous point cloud is matched, and matching precision and success rate can be improved.
If successful match, completion is carried out to the barrier laser point cloud to be identified in N+1 frame;I.e. to N+1
The laser point cloud that the barrier to be identified in frame enters the part of laser radar blind area carries out completion.
Preferably, the completion is according to the barrier laser point cloud to be identified in nth frame to the institute in N+1 frame
The laser point cloud for stating the part that barrier to be identified enters laser radar blind area carries out completion.By being the institute in N+1 frame
It states and carries out completion on the basis of barrier laser point cloud to be identified, the laser point cloud after completion more meets actual barrier
Shape.
In a kind of preferred implementation of identification module 24,
According to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.
Preferably, according to the laser point cloud of the barrier to be identified after completion, the available obstacle to be identified
The parameters such as the accurate length of object, distance, can provide more accurate laser point cloud for the obstacle recognition to be identified, guarantee
The accuracy of the obstacle recognition to be identified.
In another preferred implementation of the present embodiment, if the barrier to be identified comes into nth frame
Part enters laser radar blind area, and the relative velocity of automatic driving vehicle and the barrier to be identified is positive value, in N+1
Barrier to be identified described in frame continues to part and enters laser radar blind area.Since the laser radar scanning period is very fast, such as
360 times per second, then in 1/360 second, the barrier to be identified can only partially enter laser radar blind area, this has resulted in swashing
Optical radar can only obtain the fraction of laser light point cloud of the barrier to be identified.The part of barrier to be identified described in N+1 frame
The distribution of the point cloud of point cloud and barrier to be identified described in nth frame is changed, then carries out matched to match mistake in the process
Lose, barrier to be identified described in N+1 frame be determined as new barrier, rather than barrier to be identified described in nth frame after
It is continuous to enter laser radar blind area.Using mode same as the above embodiments of the present application, it is truncated, is matched and completion.Wherein,
The laser point cloud of barrier to be identified described in the nth frame be to the laser point cloud of barrier to be identified described in nth frame into
The laser point cloud of the barrier to be identified obtained after row completion.
In another preferred implementation of the present embodiment, if the barrier to be identified comes into nth frame
Part enters laser radar blind area, and the relative velocity of automatic driving vehicle and the barrier to be identified is negative value, in N+1
Barrier to be identified described in frame continue to part enter laser radar blind area (into the part of laser radar blind area it is less or
All exit laser radar blind area).Since the laser radar scanning period is very fast, such as 360 times per second, then described in 1/360 second
Barrier to be identified can only partially enter laser radar blind area, this, which has resulted in laser radar, can only obtain the obstacle to be identified
The fraction of laser light point cloud of object.Barrier to be identified described in the partial dot cloud and nth frame of barrier to be identified described in N+1 frame
Point cloud distribution changed, then carry out it is matched during can it fails to match, by barrier to be identified described in N+1 frame
It is determined as new barrier, rather than barrier to be identified described in nth frame goes successively to laser radar blind area.Using with the application
The same mode of above-described embodiment carries out completion by the laser point cloud to barrier to be identified described in nth frame, with N+1
The laser point cloud of the barrier to be identified in frame is matched, after successful match, to the barrier to be identified in N+1 frame
Hinder the laser point cloud of object to carry out completion, according to the barrier laser point cloud after completion, carries out obstacle recognition, and whether judge it
Influence the traveling of automatic driving vehicle.Wherein, the laser point cloud of barrier to be identified described in the nth frame is in nth frame
The laser point cloud of the barrier to be identified carries out the laser point cloud of the barrier to be identified obtained after completion.
It can be to part using technical solution provided by the above embodiment using technical solution provided by the above embodiment
Barrier into laser radar blind area identified, avoids wrong identification its length, distance causes the risk of collision, effectively
Ground improves the driving safety of automatic driving vehicle.
In the described embodiment, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed method and apparatus can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.The integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
Fig. 3 shows the frame for being suitable for the exemplary computer system/server 012 for being used to realize embodiment of the present invention
Figure.The computer system/server 012 that Fig. 3 is shown is only an example, should not function and use to the embodiment of the present invention
Range band carrys out any restrictions.
As shown in figure 3, computer system/server 012 is showed in the form of universal computing device.Computer system/clothes
The component of business device 012 can include but is not limited to: one or more processor or processing unit 016, system storage
028, connect the bus 018 of different system components (including system storage 028 and processing unit 016).
Bus 018 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 012 typically comprises a variety of computer system readable media.These media, which can be, appoints
The usable medium what can be accessed by computer system/server 012, including volatile and non-volatile media, movably
With immovable medium.
System storage 028 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 030 and/or cache memory 032.Computer system/server 012 may further include other
Removable/nonremovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 034 can
For reading and writing immovable, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").Although in Fig. 3
It is not shown, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to can
The CD drive of mobile anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these situations
Under, each driver can be connected by one or more data media interfaces with bus 018.Memory 028 may include
At least one program product, the program product have one group of (for example, at least one) program module, these program modules are configured
To execute the function of various embodiments of the present invention.
Program/utility 040 with one group of (at least one) program module 042, can store in such as memory
In 028, such program module 042 includes --- but being not limited to --- operating system, one or more application program, other
It may include the realization of network environment in program module and program data, each of these examples or certain combination.Journey
Sequence module 042 usually executes function and/or method in embodiment described in the invention.
Computer system/server 012 can also with one or more external equipments 014 (such as keyboard, sensing equipment,
Display 024 etc.) communication, in the present invention, computer system/server 012 is communicated with outside radar equipment, can also be with
One or more enable a user to the equipment interacted with the computer system/server 012 communication, and/or with make the meter
Any equipment (such as network interface card, the modulation that calculation machine systems/servers 012 can be communicated with one or more of the other calculating equipment
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 022.Also, computer system/clothes
Being engaged in device 012 can also be by network adapter 020 and one or more network (such as local area network (LAN), wide area network (WAN)
And/or public network, such as internet) communication.As shown in figure 3, network adapter 020 by bus 018 and computer system/
Other modules of server 012 communicate.It should be understood that computer system/server 012 can be combined although being not shown in Fig. 3
Using other hardware and/or software module, including but not limited to: microcode, device driver, redundant processing unit, external magnetic
Dish driving array, RAID system, tape drive and data backup storage system etc..
The program that processing unit 016 is stored in system storage 028 by operation, thereby executing described in the invention
Function and/or method in embodiment.
Above-mentioned computer program can be set in computer storage medium, i.e., the computer storage medium is encoded with
Computer program, the program by one or more computers when being executed, so that one or more computers execute in the present invention
State method flow shown in embodiment and/or device operation.
With time, the development of technology, medium meaning is more and more extensive, and the route of transmission of computer program is no longer limited by
Tangible medium, can also be directly from network downloading etc..It can be using any combination of one or more computer-readable media.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium
Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or
Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN) is connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service
Quotient is connected by internet).
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (12)
1. a kind of laser radar obstacle recognition method characterized by comprising
Obtain the information of the barrier to be identified of the continuous N+1 frame around laser radar scanning automatic driving vehicle;
According to the information of the barrier to be identified in each frame in the preceding N frame in the N+1 frame, judge described in N+1 frame
Whether barrier to be identified enters laser radar blind area;If being entered into laser radar blind area according to the barrier to be identified
The barrier laser point cloud to be identified in nth frame is truncated in the length of laser radar blind area;
According to the barrier laser point cloud to be identified after truncation and the barrier laser point cloud to be identified in N+1 frame
It is matched;If successful match, completion is carried out to the barrier laser point cloud to be identified in N+1 frame;
According to the barrier laser point cloud to be identified after completion, obstacle recognition is carried out.
2. the method according to claim 1, wherein obtaining the company around laser radar scanning automatic driving vehicle
The information of the barrier to be identified of continuous N+1 frame includes:
The point cloud for obtaining the barrier to be identified in each frame in the preceding N frame in N+1 frame, to each in the preceding N frame in N+1 frame
Obstacle object point cloud to be identified in frame is matched, and determines the corresponding relationship of the barrier to be identified in each frame.
3. the method according to claim 1, wherein according in each frame in the preceding N frame in the N+1 frame to
The information of cognitive disorders object, judging whether barrier to be identified enters laser radar blind area described in N+1 frame includes:
By point cloud of the barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in nth frame
Position, movement speed and moving direction and laser radar blind area range, determine barrier to be identified described in N+1 frame into
Enter the length of laser radar blind area.
4. the method according to claim 1, wherein entering laser radar blind area according to the barrier to be identified
Length to the barrier laser point cloud to be identified in nth frame carry out truncation include:
According to blind area threedimensional model and it is described with cognitive disorders object enter the length of laser radar blind area to described in nth frame to
Cognitive disorders object laser point cloud is truncated.
5. the method according to claim 1, wherein to the barrier laser point to be identified in N+1 frame
Cloud carries out completion
If the barrier to be identified in nth frame does not enter laser radar blind area, swashed according to the barrier to be identified in nth frame
Luminous point cloud carries out completion to the laser point cloud for the part that the barrier to be identified in N+1 frame enters laser radar blind area;
If the barrier to be identified in nth frame has entered laser radar blind area, mended according to the barrier to be identified in nth frame
Laser point cloud after complete to the barrier to be identified in N+1 frame enter laser radar blind area part laser point cloud into
Row completion.
6. a kind of laser radar obstacle recognition system characterized by comprising
Module is obtained, for obtaining the barrier to be identified of continuous N+1 frame around laser radar scanning automatic driving vehicle
Information;
Truncation module judges for the information according to the barrier to be identified in each frame in the preceding N frame in the N+1 frame
Whether barrier to be identified described in N+1 frame enters laser radar blind area;If into laser radar blind area, according to described wait know
The barrier laser point cloud to be identified in nth frame is truncated in the length that other barrier enters laser radar blind area;
Completion module, for according to after truncation the barrier laser point cloud to be identified with it is described to be identified in N+1 frame
Barrier laser point cloud is matched;If successful match, the barrier laser point cloud to be identified in N+1 frame is carried out
Completion;
Identification module, for carrying out obstacle recognition according to the barrier laser point cloud to be identified after completion.
7. device according to claim 6, which is characterized in that the acquisition module is specifically used for:
The point cloud for obtaining the barrier to be identified in each frame in the preceding N frame in N+1 frame, to each in the preceding N frame in N+1 frame
Obstacle object point cloud to be identified in frame is matched, and determines the corresponding relationship of the barrier to be identified in each frame.
8. device according to claim 6, which is characterized in that the truncation module is specifically used for:
By point cloud of the barrier to be identified in each frame in preceding N frame, determine the barrier to be identified in nth frame
Position, movement speed and moving direction and laser radar blind area range, determine barrier to be identified described in N+1 frame into
Enter the length of laser radar blind area.
9. device according to claim 6, which is characterized in that the truncation module is specifically also used to:
According to blind area threedimensional model and it is described with cognitive disorders object enter the length of laser radar blind area to described in nth frame to
Cognitive disorders object laser point cloud is truncated.
10. device according to claim 6, which is characterized in that the completion module is specifically used for:
If the barrier to be identified in nth frame does not enter laser radar blind area, swashed according to the barrier to be identified in nth frame
Luminous point cloud carries out completion to the laser point cloud for the part that the barrier to be identified in N+1 frame enters laser radar blind area;
If the barrier to be identified in nth frame has entered laser radar blind area, mended according to the barrier to be identified in nth frame
Laser point cloud after complete to the barrier to be identified in N+1 frame enter laser radar blind area part laser point cloud into
Row completion.
11. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor is realized when executing described program as any in Claims 1 to 5
Method described in.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Such as method according to any one of claims 1 to 5 is realized when device executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811533572.0A CN109633688B (en) | 2018-12-14 | 2018-12-14 | Laser radar obstacle identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811533572.0A CN109633688B (en) | 2018-12-14 | 2018-12-14 | Laser radar obstacle identification method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109633688A true CN109633688A (en) | 2019-04-16 |
CN109633688B CN109633688B (en) | 2019-12-24 |
Family
ID=66073985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811533572.0A Active CN109633688B (en) | 2018-12-14 | 2018-12-14 | Laser radar obstacle identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109633688B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111374A (en) * | 2019-04-29 | 2019-08-09 | 上海电机学院 | Laser point cloud matching process based on grouping staged threshold decision |
CN110262504A (en) * | 2019-07-02 | 2019-09-20 | 吉林大学 | A kind of adjustable multilasered optical radar coupled system of structure and its control method |
CN110281838A (en) * | 2019-06-28 | 2019-09-27 | 上海理工大学 | A kind of car headlamp automatic switching method based on two-dimensional laser radar |
CN110428661A (en) * | 2019-08-12 | 2019-11-08 | 深圳成谷科技有限公司 | A kind of protection pedestrian crosses the method, apparatus and equipment of zebra stripes |
CN111326005A (en) * | 2020-03-04 | 2020-06-23 | 北京百度网讯科技有限公司 | Image processing method, apparatus, computer device and medium |
CN111798700A (en) * | 2020-06-30 | 2020-10-20 | 北京行易道科技有限公司 | Blind area monitoring alarm method and device |
CN112330702A (en) * | 2020-11-02 | 2021-02-05 | 蘑菇车联信息科技有限公司 | Point cloud completion method and device, electronic equipment and storage medium |
CN112528711A (en) * | 2019-09-19 | 2021-03-19 | 北京百度网讯科技有限公司 | Method and apparatus for processing information |
CN112558035A (en) * | 2019-09-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and apparatus for estimating ground |
CN112630799A (en) * | 2019-09-24 | 2021-04-09 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
CN112731449A (en) * | 2020-12-23 | 2021-04-30 | 深圳砺剑天眼科技有限公司 | Laser radar obstacle identification method and system |
WO2021134296A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Obstacle detection method and apparatus, and computer device and storage medium |
WO2022001322A1 (en) * | 2020-06-30 | 2022-01-06 | 上海商汤智能科技有限公司 | Vehicle control method and apparatus, and electronic device and storage medium |
CN114715024A (en) * | 2022-04-15 | 2022-07-08 | 东风柳州汽车有限公司 | Automobile acousto-optic reminding method, automobile acousto-optic reminding equipment, storage medium and automobile acousto-optic reminding device |
WO2023093056A1 (en) * | 2021-11-29 | 2023-06-01 | 上海商汤智能科技有限公司 | Vehicle control |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007274037A (en) * | 2006-03-30 | 2007-10-18 | Daihatsu Motor Co Ltd | Method and device for recognizing obstacle |
US8319949B2 (en) * | 2007-06-18 | 2012-11-27 | Leddartech Inc. | Method for detecting objects with visible light |
CN104899855A (en) * | 2014-03-06 | 2015-09-09 | 株式会社日立制作所 | Three-dimensional obstacle detection method and apparatus |
CN106774306A (en) * | 2016-11-30 | 2017-05-31 | 百度在线网络技术(北京)有限公司 | It is applied to startup detection method, device and the system of automatic driving vehicle |
CN108318895A (en) * | 2017-12-19 | 2018-07-24 | 深圳市海梁科技有限公司 | Obstacle recognition method, device and terminal device for automatic driving vehicle |
-
2018
- 2018-12-14 CN CN201811533572.0A patent/CN109633688B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007274037A (en) * | 2006-03-30 | 2007-10-18 | Daihatsu Motor Co Ltd | Method and device for recognizing obstacle |
US8319949B2 (en) * | 2007-06-18 | 2012-11-27 | Leddartech Inc. | Method for detecting objects with visible light |
CN104899855A (en) * | 2014-03-06 | 2015-09-09 | 株式会社日立制作所 | Three-dimensional obstacle detection method and apparatus |
CN106774306A (en) * | 2016-11-30 | 2017-05-31 | 百度在线网络技术(北京)有限公司 | It is applied to startup detection method, device and the system of automatic driving vehicle |
CN108318895A (en) * | 2017-12-19 | 2018-07-24 | 深圳市海梁科技有限公司 | Obstacle recognition method, device and terminal device for automatic driving vehicle |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111374B (en) * | 2019-04-29 | 2020-11-17 | 上海电机学院 | Laser point cloud matching method based on grouped stepped threshold judgment |
CN110111374A (en) * | 2019-04-29 | 2019-08-09 | 上海电机学院 | Laser point cloud matching process based on grouping staged threshold decision |
CN110281838B (en) * | 2019-06-28 | 2022-11-18 | 上海理工大学 | Automatic automobile headlamp conversion method based on two-dimensional laser radar |
CN110281838A (en) * | 2019-06-28 | 2019-09-27 | 上海理工大学 | A kind of car headlamp automatic switching method based on two-dimensional laser radar |
CN110262504B (en) * | 2019-07-02 | 2021-06-01 | 吉林大学 | Multi-laser radar coupling system with adjustable structure and control method thereof |
CN110262504A (en) * | 2019-07-02 | 2019-09-20 | 吉林大学 | A kind of adjustable multilasered optical radar coupled system of structure and its control method |
CN110428661A (en) * | 2019-08-12 | 2019-11-08 | 深圳成谷科技有限公司 | A kind of protection pedestrian crosses the method, apparatus and equipment of zebra stripes |
CN112528711A (en) * | 2019-09-19 | 2021-03-19 | 北京百度网讯科技有限公司 | Method and apparatus for processing information |
CN112558035B (en) * | 2019-09-24 | 2023-06-09 | 北京百度网讯科技有限公司 | Method and device for estimating the ground |
CN112630799B (en) * | 2019-09-24 | 2022-11-29 | 阿波罗智能技术(北京)有限公司 | Method and apparatus for outputting information |
CN112558035A (en) * | 2019-09-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and apparatus for estimating ground |
CN112630799A (en) * | 2019-09-24 | 2021-04-09 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
WO2021134296A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Obstacle detection method and apparatus, and computer device and storage medium |
CN113424079A (en) * | 2019-12-30 | 2021-09-21 | 深圳元戎启行科技有限公司 | Obstacle detection method, obstacle detection device, computer device, and storage medium |
CN113936493A (en) * | 2020-03-04 | 2022-01-14 | 北京百度网讯科技有限公司 | Image processing method, apparatus, computer device and medium for automatic driving |
CN113936493B (en) * | 2020-03-04 | 2022-11-04 | 北京百度网讯科技有限公司 | Image processing method, apparatus, computer device and medium for automatic driving |
CN111326005A (en) * | 2020-03-04 | 2020-06-23 | 北京百度网讯科技有限公司 | Image processing method, apparatus, computer device and medium |
CN111798700A (en) * | 2020-06-30 | 2020-10-20 | 北京行易道科技有限公司 | Blind area monitoring alarm method and device |
WO2022001322A1 (en) * | 2020-06-30 | 2022-01-06 | 上海商汤智能科技有限公司 | Vehicle control method and apparatus, and electronic device and storage medium |
CN112330702A (en) * | 2020-11-02 | 2021-02-05 | 蘑菇车联信息科技有限公司 | Point cloud completion method and device, electronic equipment and storage medium |
CN112731449A (en) * | 2020-12-23 | 2021-04-30 | 深圳砺剑天眼科技有限公司 | Laser radar obstacle identification method and system |
CN112731449B (en) * | 2020-12-23 | 2023-04-14 | 深圳砺剑天眼科技有限公司 | Laser radar obstacle identification method and system |
WO2023093056A1 (en) * | 2021-11-29 | 2023-06-01 | 上海商汤智能科技有限公司 | Vehicle control |
CN114715024A (en) * | 2022-04-15 | 2022-07-08 | 东风柳州汽车有限公司 | Automobile acousto-optic reminding method, automobile acousto-optic reminding equipment, storage medium and automobile acousto-optic reminding device |
Also Published As
Publication number | Publication date |
---|---|
CN109633688B (en) | 2019-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109633688A (en) | A kind of laser radar obstacle recognition method and device | |
CN109817021A (en) | A kind of laser radar trackside blind area traffic participant preventing collision method and device | |
CN109814112A (en) | A kind of ultrasonic radar and laser radar information fusion method and system | |
CN109927719B (en) | Auxiliary driving method and system based on obstacle trajectory prediction | |
CN109116374B (en) | Method, device and equipment for determining distance of obstacle and storage medium | |
CN109101861A (en) | Obstacle identity recognition methods, device, equipment and storage medium | |
CN109188438A (en) | Yaw angle determines method, apparatus, equipment and medium | |
CN112572424B (en) | Vehicle control method, device, equipment and medium based on obstacle recognition | |
CN109212530A (en) | Method and apparatus for determining barrier speed | |
CN109738904A (en) | A kind of method, apparatus of detection of obstacles, equipment and computer storage medium | |
CN109229109A (en) | Judge the method, apparatus, equipment and computer storage medium of vehicle heading | |
CN109870698A (en) | A kind of ultrasonic array detection of obstacles result processing method and system | |
CN109085620A (en) | Automatic driving vehicle positions abnormal calibration method, apparatus, equipment and storage medium | |
CN112526999A (en) | Speed planning method, device, electronic equipment and storage medium | |
CN112650300B (en) | Unmanned aerial vehicle obstacle avoidance method and device | |
CN112015178A (en) | Control method, device, equipment and storage medium | |
CN109814114A (en) | A kind of ultrasonic radar array, obstacle detection method and system | |
CN109765563A (en) | A kind of ultrasonic radar array, obstacle detection method and system | |
CN108268831A (en) | The robustness test method and system of a kind of unmanned vehicle vision-based detection | |
CN112613424A (en) | Rail obstacle detection method, rail obstacle detection device, electronic apparatus, and storage medium | |
CN110533940A (en) | Method, apparatus, equipment and the computer storage medium of abnormal traffic signal lamp identification | |
CN109901194A (en) | Onboard system, method, equipment and the storage medium of anticollision | |
CN110363193A (en) | Vehicle recognition methods, device, equipment and computer storage medium again | |
CN115147809A (en) | Obstacle detection method, device, equipment and storage medium | |
CN114565908A (en) | Lane line detection method and device, electronic device and storage medium |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20211019 Address after: 105 / F, building 1, No. 10, Shangdi 10th Street, Haidian District, Beijing 100085 Patentee after: Apollo Intelligent Technology (Beijing) Co.,Ltd. Address before: 2 / F, *** building, 10 Shangdi 10th Street, Haidian District, Beijing 100085 Patentee before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |