CN106845412A - Obstacle recognition method and device, computer equipment and computer-readable recording medium - Google Patents
Obstacle recognition method and device, computer equipment and computer-readable recording medium Download PDFInfo
- Publication number
- CN106845412A CN106845412A CN201710049464.5A CN201710049464A CN106845412A CN 106845412 A CN106845412 A CN 106845412A CN 201710049464 A CN201710049464 A CN 201710049464A CN 106845412 A CN106845412 A CN 106845412A
- Authority
- CN
- China
- Prior art keywords
- barrier
- identified
- layering
- point cloud
- cloud
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The present invention provides a kind of obstacle recognition method and device, computer equipment and computer-readable recording medium.Its method includes:The point cloud of barrier to be identified is divided into the layering of the specified number of plies in height;Obtain maximum, minimum value and the included points of all directions of the point cloud of barrier to be identified in each layering;Point the cloud maximum of all directions, minimum value and included points in each layering according to barrier to be identified, generate the layered characteristic vector of barrier to be identified;The layered characteristic vector of sorter model and barrier to be identified according to training in advance, recognizes the classification of barrier to be identified.Technical scheme is dissected by the point cloud to barrier to be identified, so that the information comprising more abundant barrier to be identified in the layered characteristic vector of barrier to be identified, the recognition accuracy to barrier to be identified can be effectively improved such that it is able to effectively improve the recognition efficiency to barrier to be identified.
Description
【Technical field】
Set the present invention relates to automatic Pilot technical field, more particularly to a kind of obstacle recognition method and device, computer
Standby and computer-readable recording medium.
【Background technology】
In existing automatic Pilot technology, the information of obstacle recognition output to be identified as control and can plan
The input of information, therefore, to barrier to be identified accurately and quickly recognize to be a very crucial technology.
In the prior art, barrier to be identified is identified using camera and laser radar generally.Wherein image
Head scheme can apply very sufficient in illumination, under the more stable scene of environment.But it is mixed in bad weather and road environment
In the case of unrest, the vision of camera scheme is all not sufficiently stable always, causes the information of the barrier to be identified of collection to be forbidden
Really.And laser radar is although very expensive, but highly stable during the barrier to be identified of laser radar scheme identification and peace
Entirely.In the prior art, when recognizing barrier to be identified using laser radar, according to the barrier that Laser Radar Scanning is to be identified
The point cloud size and local feature of acquired barrier to be identified judge the classification of barrier to be identified.For example,
Whether can be whether the head portrait of people judges barrier to be identified according to the local feature of the point cloud of barrier to be identified
It is people;According to barrier to be identified point cloud local feature whether be bicycle headstock feature it is to be identified to judge
Whether barrier is bicycle etc..
But in the prior art, the local feature of the point cloud of barrier to be identified in the point cloud of Laser Radar Scanning is usual
It is not so substantially, to cause, recognition efficiency poor to the recognition accuracy of barrier to be identified relatively low.
【The content of the invention】
The invention provides a kind of obstacle recognition method and device, computer equipment and computer-readable recording medium, for improving certainly
The recognition accuracy of barrier to be identified and recognition efficiency in dynamic driving.
The present invention provides a kind of obstacle recognition method, and methods described includes:
The point cloud of barrier to be identified is divided into the layering of the specified number of plies in height;The specified number of plies is included extremely
Few two-layer;
Obtain maximum, minimum value and the institute of all directions of the point cloud of the barrier to be identified in each layering
Including points;
The maximum for putting all directions of the cloud in each layering, minimum value and institute according to the barrier to be identified
Including points, generate the layered characteristic vector of the barrier to be identified;
The layered characteristic of sorter model and the barrier to be identified according to training in advance is vectorial, is treated described in identification
The classification of the barrier of identification.
Still optionally further, in method as described above, the point cloud according to the barrier to be identified is each described
The maximum of all directions in layering, minimum value and included points, generate the layered characteristic of the barrier to be identified
Vector, specifically includes:
The maximum for putting all directions of the cloud in each layering, minimum value and institute according to the barrier to be identified
Including points, and with reference to the barrier to be identified point cloud barycenter coordinate information and the barrier to be identified
Point cloud included by least one of total points, generate the layered characteristic vector of the barrier to be identified.
Still optionally further, in method as described above, also include:
The coordinate information of the barycenter of the point cloud according to the barrier to be identified, determines the barrier phase to be identified
For the position of Current vehicle.
Still optionally further, in method as described above, the point cloud according to the barrier to be identified is each described
The maximum of all directions in layering, minimum value and included points, generate the layered characteristic of the barrier to be identified
Vector, specifically includes:
According to the maximum and minimum value of putting length direction of the cloud in each layering of the barrier to be identified,
Obtain length information of the point cloud of the barrier to be identified in each layering;
According to the maximum and minimum value of putting width of the cloud in each layering of the barrier to be identified,
Obtain width information of the point cloud of the barrier to be identified in each layering;
The length information, the width information of the cloud in each layering are put according to the barrier to be identified
With included points, the layered characteristic vector of the barrier to be identified is generated.
Still optionally further, in method as described above, sorter model according to training in advance and described to be identified
Barrier layered characteristic vector, before recognizing the classification of the barrier to be identified, methods described also includes:
Collection multiple has marked the point cloud information of the default barrier of classification, dyspoiesis thing training set;
The point cloud information of the multiple default barrier in the barrier training set, trains the grader mould
Type.
Still optionally further, it is the multiple default in the barrier training set in method as described above
The point cloud information of barrier, trains the sorter model, specifically includes:
The point cloud of each default barrier is divided into the layering of the specified number of plies in height;Obtain each described pre-
If the maximum of all directions of the point cloud of barrier in each layering, minimum value and included points;
The maximum for putting all directions of the cloud in each layering, minimum value and bag according to each default barrier
The points for including, generate the layered characteristic vector of each default barrier;
Layered characteristic respectively according to each default barrier is vectorial and classification of each default barrier, training
Sorter model, so that it is determined that the sorter model.
The present invention also provides a kind of obstacle recognition system, and described device includes:
Division module, the layering for the point cloud of barrier to be identified to be divided into the specified number of plies in height;It is described
Specifying the number of plies includes at least two-layer;
Acquisition module, the maximum for obtaining all directions of the point cloud of the barrier to be identified in each layering
Value, minimum value and included points;
Feature vector generation module, for each side according to the point cloud of the barrier to be identified in each layering
To maximum, minimum value and included points, generate the layered characteristic vector of the barrier to be identified;
Identification module, for the sorter model according to training in advance and the barrier to be identified layered characteristic to
Amount, recognizes the classification of the barrier to be identified.
Still optionally further, in device as described above, the feature vector generation module, specifically for according to described
The maximum of the point all directions of the cloud in each layering of barrier to be identified, minimum value and included points, and join
Examine included by the coordinate information of the barycenter of the point cloud of the barrier to be identified and the point cloud of the barrier to be identified
At least one of total points, generate the layered characteristic vector of the barrier to be identified.
Still optionally further, in device as described above, also include:
Determining module, for the coordinate information of the barycenter of the point cloud according to the barrier to be identified, it is determined that described treat
Position of the barrier of identification relative to Current vehicle.
Still optionally further, in device as described above, the feature vector generation module, specifically for:
According to the maximum and minimum value of putting length direction of the cloud in each layering of the barrier to be identified,
Obtain length information of the point cloud of the barrier to be identified in each layering;
According to the maximum and minimum value of putting width of the cloud in each layering of the barrier to be identified,
Obtain width information of the point cloud of the barrier to be identified in each layering;
The length information, the width information of the cloud in each layering are put according to the barrier to be identified
With included points, the layered characteristic vector of the barrier to be identified is generated.
Still optionally further, in device as described above, also include:
Acquisition module, the point cloud information for gathering multiple default barriers for having marked barrier classification to be identified,
Dyspoiesis thing training set;
Training module, for the point cloud information of the multiple default barrier in the barrier training set, instruction
The white silk sorter model.
Still optionally further, in device as described above, the training module, specifically for:
The point cloud of each default barrier is divided into the layering of the specified number of plies in height;Obtain each described pre-
If the maximum of all directions of the point cloud of barrier in each layering, minimum value and included points;
The maximum for putting all directions of the cloud in each layering, minimum value and bag according to each default barrier
The points for including, generate the layered characteristic vector of each default barrier;Layering respectively according to each default barrier is special
The classification of vectorial and each default barrier is levied, sorter model is trained, so that it is determined that the sorter model.
The present invention also provides a kind of computer equipment, including memory, processor and storage on a memory and can located
The computer program run on reason device, realizes obstacle recognition method as described above during the computing device described program.
The present invention also provides a kind of computer-readable medium, is stored thereon with computer program, and the program is held by processor
Obstacle recognition method as described above is realized during row.
Obstacle recognition method of the invention and device, computer equipment and computer-readable recording medium, by by obstacle to be identified
The point cloud of thing is divided into the layering of the specified number of plies in height;Obtain each side of the point cloud of barrier to be identified in each layering
To maximum, minimum value and included points;All directions are most in each layering for point cloud according to barrier to be identified
Big value, minimum value and included points, generate the layered characteristic vector of barrier to be identified;According to the classification of training in advance
The layered characteristic vector of device model and barrier to be identified, recognizes the classification of barrier to be identified.With it is of the prior art
According to the size and local feature of obstacle object point cloud to be identified, recognize that the recognition methods of barrier to be identified is compared, this hair
Bright technical scheme, is dissected so that the layered characteristic of barrier to be identified by the point cloud to barrier to be identified
Comprising the information of more abundant barrier to be identified in vector, and according to the sorter model of training in advance to be identified
The characteristic vector of barrier is identified, and to determine the classification of barrier to be identified, can effectively improve to be identified
The recognition accuracy of barrier such that it is able to effectively improve the recognition efficiency to barrier to be identified.
【Brief description of the drawings】
Fig. 1 is the flow chart of obstacle recognition method embodiment of the invention.
Fig. 2 is the structure chart of obstacle recognition system embodiment one of the invention.
Fig. 3 is the structure chart of obstacle recognition system embodiment two of the invention.
Fig. 4 is the structure chart of computer equipment of the invention.
【Specific embodiment】
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with the accompanying drawings with specific embodiment pair
The present invention is described in detail.
Fig. 1 is the flow chart of obstacle recognition method embodiment of the invention.As shown in figure 1, the barrier of the present embodiment
Recognition methods, specifically may include steps of:
100th, the point cloud of barrier to be identified is divided into the layering of the specified number of plies in height;
The obstacle recognition method of the present embodiment is applied in automatic Pilot technical field., it is necessary to car in automatic Pilot
Barrier that can be in automatic identification road, makes a policy and control in time with being travelled in vehicle, is easy to the safety of vehicle
Traveling.The executive agent of the obstacle recognition method of the present embodiment can be obstacle recognition system, the obstacle recognition system
Multiple modules can be used integrated and obtained, the obstacle recognition system can be specifically arranged in the vehicle of automatic Pilot, with right
The vehicle of automatic Pilot is controlled.
The point cloud of the barrier to be identified of the present embodiment can strafe what is obtained using laser radar.The rule of laser radar
Lattice can be using 16 lines, 32 lines or 64 lines etc..The wherein line number unit energy density for representing laser radar higher is bigger.This
The specified number of plies in embodiment includes at least two-layer, specifically can according to the height of the point cloud of barrier come minute, the point of barrier
The height of cloud is higher, and the number of plies that can suitably divide is more, and comparatively the height of the point cloud of barrier is lower, point the number of plies can be with
It is fewer.Because the present embodiment is by the layering that cloud is divided into the specified number of plies in height of putting of barrier to be identified, so originally
In embodiment, when dividing, it can be understood as using multiple x/y planes parallel to horizontal plane by the point cloud of barrier in height
Cutting is carried out on direction.Preferably, in the present embodiment, the point cloud of barrier to be identified is in height to draw in an uniform manner
Point, that is, put the highly equal of cloud in each layering after dividing.
101st, the maximum of all directions of the point cloud of barrier to be identified in each layering, minimum value and included are obtained
Points;
Each point has coordinate in the point cloud of the barrier to be identified in the present embodiment.Corresponding used coordinate
The origin of system is the centroid position of the vehicle for being currently loaded with laser radar.So, the point cloud of the barrier to be identified that detection is obtained
In each point, can with the centroid position of vehicle as origin, correspondence mark a coordinate points.According to the point of barrier
In cloud coordinate a little, can therefrom determine the point cloud of barrier maximum ymax in the longitudinal direction and minimum value
Ymin, maximum xmax and minimum value xmin on width, and maximum zmax and minimum value in short transverse
Zmin, the length that then can take the barrier subtracts minimum ymax-ymin long equal to length maximum in point cloud, the width of the barrier
Maximum width in equal to a cloud subtracts minimum width xmax-xmin, and the high maximum height in a cloud of the barrier subtracts minimum
Zmax-zmin high.In the same way, after being layered to the point cloud of barrier using above-mentioned steps 100, can obtain
Maximum length value, the minimum length value of length direction in each layering of the point cloud of the barrier, and width is most
Big width value, minimum width value.At the same time it can also points included in the point cloud for getting each layering.
102nd, the maximum of all directions, the minimum value and included in each layering of the point cloud according to barrier to be identified
Points, generate the layered characteristic vector of barrier to be identified;
In the present embodiment, can be directly according to the maximum of all directions, minimum value and included points in each layering raw
Into the layered characteristic vector of barrier to be identified.For example when obstacle object point cloud to be identified includes 10 layerings, each point
Layer includes maximum, minimum value, the maximum of width of length direction, the point that minimum value and the demixing point cloud include
Count, totally 5 features;So 10 layerings, can include 50 features altogether, and this 50 features can be arranged in a row, common group
Into the layered characteristic vector of the barrier to be identified.
Further optionally, in the present embodiment, the step 102 can also comprise the following steps:
(a1) maximum and minimum value of length direction of the point cloud according to barrier to be identified in each layering, obtain
Length information of the point cloud of barrier to be identified in each layering;
Specifically, length of the point cloud of barrier to be identified in each layering exists equal to the point cloud of barrier to be identified
The maximum of the length direction in the layering subtracts minimum value.
(a2) maximum and minimum value of width of the point cloud according to barrier to be identified in each layering, obtain
Width information of the point cloud of barrier to be identified in each layering;
Specifically, width of the point cloud of barrier to be identified in each layering exists equal to the point cloud of barrier to be identified
The maximum of the width in the layering subtracts minimum value.
(a3) length information of the point cloud in each layering according to barrier to be identified, width information and included point
Number, generates the layered characteristic vector of barrier to be identified.
Now, according to barrier to be identified length of the point cloud in each layering, width and included points,
The layered characteristic vector of barrier to be identified can be generated.Similarly, when obstacle object point cloud to be identified includes 10 layerings,
Each layering only includes 3 features.So 10 layerings, can include 30 features altogether, and this 30 features can be arranged in
A line, collectively constitutes the layered characteristic vector of the barrier to be identified.
Still optionally further, the step 102 in the present embodiment, can also be specifically:According to the point of barrier to be identified
The maximum of all directions of the cloud in each layering, minimum value and included points, and with reference to the point cloud of barrier to be identified
The coordinate information of barycenter and the point cloud of barrier to be identified included by least one of total points, generate to be identified
The layered characteristic vector of barrier.
That is, on the basis of above-mentioned technical proposal, generating the layered characteristic vector of barrier to be identified
When, the coordinate information of barycenter and the point cloud of barrier to be identified that can also add the point cloud of barrier to be identified are wrapped
At least one of total points for including.So, " all directions of the cloud in each layering are put according to barrier to be identified in step
Maximum, minimum value and included points, and with reference to barrier to be identified point cloud barycenter coordinate information and treat
At least one of total points included by the point cloud of the barrier of identification, generate the layered characteristic of barrier to be identified to
, it is necessary to first obtain the coordinate information and the point cloud of barrier to be identified of the barycenter of the point cloud of barrier to be identified before amount "
Included total points.Specifically, when laser radar detects the point cloud of barrier to be identified, this can be got to be identified
Barrier point cloud center-of-mass coordinate, the center-of-mass coordinate can include the barrier to be identified barycenter in current coordinate system
In length and width and value high.In addition, the total points included by the point cloud of the barrier to be identified are the obstacle to be identified
Thing before being layered, total points of the point cloud of whole barrier to be identified.It is total included by the point cloud of the barrier to be identified
Points should be equal to the quantity sum of the point cloud included by each layering.The point cloud of barrier to be identified is being detected in laser radar
When, it is also possible to get the total points included by the point cloud of the barrier to be identified.
For example, directly according to the maximum of all directions, minimum value and included points in each layering, generating to be identified
During the layered characteristic vector of barrier, the layered characteristic vector of barrier to be identified is generated, except the length including each layering
5 features of points that the maximum in direction, minimum value, the maximum of width, minimum value and the demixing point cloud include it
Outward, the length and width and 3 features high of the barycenter of the barrier to be identified can also be included, so, when barrier to be identified
When point cloud includes 10 layerings altogether, the layered characteristic vector of the barrier to be identified of generation can include above 5*10+3=53 altogether
Individual feature.Or the layered characteristic vector of generation barrier to be identified, in addition to 5 features including each layering, may be used also
With the total points included by the point cloud including the barrier to be identified.So, when the point cloud of barrier to be identified includes altogether
During 10 layerings, the layered characteristic vector of the barrier to be identified of generation can include 5*10+1=51 feature of the above altogether.Or
Person, generates the layered characteristic vector of barrier to be identified, and in addition to 5 features including each layering, also including simultaneously should
The length and width of the barycenter of barrier to be identified and 3 features high, and the total point included by the point cloud of the barrier to be identified
Number.So, when the point cloud of barrier to be identified includes 10 layerings altogether, the layered characteristic of the barrier to be identified of generation to
Amount can include 5*10+3+1=54 feature of the above altogether.
In addition, when by above-mentioned steps (a1), (a2) and (a3), the point cloud according to barrier to be identified is in each layering
Length, width and included points, when just can generate the layered characteristic vector of barrier to be identified, generate and wait to know
The layered characteristic vector of other barrier, except the points 3 that the length including each layering, width and the demixing point cloud include
Outside feature, the length and width and 3 features high of the barycenter of the barrier to be identified can also be included, so, when barrier to be identified
When hindering the point cloud of thing to be layered including 10 altogether, the layered characteristic vector of the barrier to be identified of generation can include above 3*10 altogether
+ 3=33 feature.Or generate the layered characteristic vector of barrier to be identified, except 3 features including each layering it
Outward, the total points included by the point cloud of the barrier to be identified can also be included.So, when the point cloud of barrier to be identified
When including 10 layerings altogether, the layered characteristic vector of the barrier to be identified of generation can altogether include that above 3*10+1=31 is special
Levy.Or, the layered characteristic vector of barrier to be identified is generated, in addition to 3 features including each layering, also wrap simultaneously
The length and width and 3 features high of the barycenter of the barrier to be identified are included, and included by the point cloud of the barrier to be identified
Total points.So, when the point cloud of barrier to be identified includes 10 layerings altogether, the layering of the barrier to be identified of generation is special
Levying vector can include 3*10+3+1=34 feature of the above altogether.
In actually used, the layered characteristic vector of barrier to be identified is generated in addition to including aforesaid way, may be used also
With the further feature information according to barrier to be identified, such as apart from the distance of Current vehicle, respective extension barrier to be identified
Hinder the quantity of the feature included by the layered characteristic vector of thing, can equally realize being identified barrier to be identified.
Still optionally further, in the present embodiment, in the coordinate information of the barycenter of the point cloud for getting barrier to be identified
Afterwards, the obstacle distance coordinate system to be identified can also be calculated according to the coordinate information of the barycenter of the barrier to be identified
Origin is the distance of the centroid position of vehicle, may thereby determine that position of the barrier to be identified relative to Current vehicle,
That is the barrier to be identified at which orientation distance how far of Current vehicle, according to this treat by the vehicle for being easy to oneself to drive
The barrier of identification makes control in time relative to the position of Current vehicle, it is ensured that the driving safety of vehicle.
103rd, according to training in advance sorter model and the layered characteristic vector of barrier to be identified, recognize to be identified
Barrier classification.
In the present embodiment, training in advance has sorter model, and the input of the sorter model can be the layering of barrier
Characteristic vector, output can be the classification of barrier.So, it is input into the to be identified of above-described embodiment acquisition to the sorter model
Barrier layered characteristic vector, the classification of sorter model output is the classification of the barrier to be identified.It is optional
Ground, in the present embodiment, can by the classification of barrier to be identified be divided into pedestrian, bicycle, car, big automobile or other
Classification.When being identified to barrier, the classification of uncertain barrier is all identified as other classifications.And answered according to actual
In, the new vehicles occurred in road can also be stepped up the classification of barrier, and according to without several categories
The point cloud information of barrier is updated training to sorter model so that the sorter model after renewal can also be to newly increasing
The barrier of classification is identified.
The sorter model can be believed in advance training using the point cloud of some barriers for being labelled with classification
Breath is trained, for example, before the step 103, specifically may include steps of:
(b1) the point cloud information that multiple has marked the default barrier of classification, dyspoiesis thing training set are gathered;
(b2) the point cloud information of the default barrier of the multiple in barrier training set, trains sorter model.
The bar number of the point cloud information of the default barrier that barrier training set includes in the present embodiment can be a lot, for example
More than 5000 is up to ten thousand or more, and the bar number of the point cloud information of the default barrier that barrier training set includes is more,
During the sorter model of training, it is determined that sorter model parameter it is more accurate, subsequently according to sorter model recognize it is to be identified
Barrier classification it is just more accurate.
For example, the step (b2), specifically may include steps of:
(c1) the point cloud of each default barrier is divided into the layering of the specified number of plies in height;
(c2) maximum of all directions of the point cloud of each default barrier in each layering, minimum value and included are obtained
Points;
(c3) maximum of point all directions of the cloud in each layering according to each default barrier, minimum value and included
Points, generate the layered characteristic vector of each default barrier;
(c4) layered characteristic respectively according to each default barrier is vectorial and classification of each default barrier, training classification
Device model, so that it is determined that sorter model.
In the present embodiment, the implementation process of step (c1)-(c3) may be referred to the implementation of above-mentioned steps 100-102 in detail
Journey.It is and upper that is, when sorter model is trained, generate the generating mode of the layered characteristic vector of each default barrier
State generated during recognizing barrier classification to be identified using sorter model the layered characteristic of barrier to be identified to
The generating mode of amount is identical;The quantity of feature that the layered characteristic vector of the default barrier for obtaining is included with it is to be identified
The quantity of feature that is included of layered characteristic vector of barrier be identical.And in practical application, preset dividing for barrier
The quantity of the feature that layer characteristic vector is included is more, and the feature of corresponding default barrier is abundanter, the grader mould for obtaining
Type is more accurate, and when being identified to barrier to be identified, the layered characteristic vector of the barrier to be identified of acquisition is also needed
To include same amount of feature, so, the feature of barrier to be identified is also relatively abundanter, and knowledge is treated using sorter model
The identification of other barrier is also relatively more accurate., wherein it is desired to it is noted that recognize barrier to be identified when, will be to be identified
The point specified number of plies that divides in height of cloud of barrier, and when sorter model is trained, by the point cloud of each default barrier
The specified number of plies for dividing in height must be identical.And when barrier to be identified is recognized, obtain obstacle to be identified
The specification of the laser radar that the point cloud of thing is used, it is also desirable to being adopted for the point cloud of each default barrier obtained in training
The specification of laser radar is identical, can otherwise cause the points included by a cloud not in a rank, it is impossible to to be identified
Barrier is recognized exactly.
Finally, the classification of each default barrier of layered characteristic vector sum according to each default barrier is entered to sorter model
Row training so that sorter model can export default barrier when the layered characteristic vector of input default barrier
Classification.During training, because it is known that the classification of pre- barrier, if the layered characteristic vector of the default barrier of input, output
The classification of default barrier do not meet the classification of the pre- barrier being known a priori by, the parameter of the model of grader can be carried out
Adjustment so that the classification of the default barrier of sorter model output is consistent with the classification of the default barrier being known a priori by.
It is right using above-mentioned steps (c1)-(c4) by the point cloud information using nothing several the default barrier in barrier training set
The sorter model is trained, it may be determined that the parameter of the sorter model, so that it is determined that the sorter model.If now will
In layered characteristic vector input to the sorter model having determined of barrier to be identified, the sorter model just can be with standard
Really it is input into the classification of the barrier to be identified.
The sorter model of the present embodiment can for Random Forest model, decision-tree model, Logic Regression Models, support
Vector machine (Support Vector Machine;SVM) any one in model and neural network model, does not limit herein
It is fixed.
By the obstacle recognition method using the present embodiment, the vehicle of automatic Pilot is by Laser Radar Scanning to waiting to know
After the point cloud of other barrier, just barrier to be identified can be identified according to above-mentioned obstacle recognition method,
The traveling of vehicle can be further controlled according to the classification of barrier, for example, controls vehicle to avoid barrier, so as to effectively increase
The driving safety of the vehicle of automatic Pilot is added.
The obstacle recognition method of the present embodiment, it is specified by the way that the point cloud of barrier to be identified is divided into height
The layering of the number of plies;Obtain the maximum of all directions of the point cloud of barrier to be identified in each layering, minimum value and included
Points;Point the cloud maximum of all directions, minimum value and included points in each layering according to barrier to be identified,
The layered characteristic vector of generation barrier to be identified;Sorter model and barrier to be identified according to training in advance point
Layer characteristic vector, recognizes the classification of barrier to be identified.With of the prior art according to the big of obstacle object point cloud to be identified
Small and local feature, recognizes that the recognition methods of barrier to be identified is compared, the technical scheme of the present embodiment, by to be identified
The point cloud of barrier dissected so that comprising more abundant to be identified in the layered characteristic vector of barrier to be identified
Barrier information, and the characteristic vector of barrier to be identified is identified according to the sorter model of training in advance,
To determine the classification of barrier to be identified, the recognition accuracy to barrier to be identified can be effectively improved, so as to
Enough effectively improve the recognition efficiency to barrier to be identified.
Fig. 2 is the structure chart of obstacle recognition system embodiment one of the invention.As shown in Fig. 2 the obstacle of the present embodiment
Thing identifying device, can specifically include:Division module 10, acquisition module 11, feature vector generation module 12 and identification module 13.
Wherein division module 10 is used in height be divided into the point cloud of barrier to be identified the layering of the specified number of plies;
The specified number of plies includes at least two-layer;Acquisition module 11 is used to obtaining after division module 10 divides, barrier to be identified
Put maximum, minimum value and the included points of all directions of the cloud in each layering;Feature vector generation module 12 is used for root
According to the maximum for putting all directions of the cloud in each layering of the barrier to be identified of the acquisition of acquisition module 11, minimum value and bag
The points for including, generate the layered characteristic vector of barrier to be identified;Identification module 13 is used for the grader according to training in advance
The layered characteristic vector of model and the barrier to be identified of the generation of feature vector generation module 12, recognizes barrier to be identified
Classification.
The obstacle recognition system of the present embodiment, is known by using the realization of above-mentioned module to barrier to be identified
Not, the realization principle with above-mentioned related method embodiment is identical with technique effect, above-mentioned correlation technique is may be referred in detail and is implemented
The record of example, will not be repeated here.
Fig. 3 is the structure chart of obstacle recognition system embodiment two of the invention.As shown in figure 3, the obstacle of the present embodiment
Thing identifying device, on the basis of the technical scheme of above-mentioned embodiment illustrated in fig. 2, is further described more fully of the invention
Technical scheme.
In the obstacle recognition system of the present embodiment, feature vector generation module 12 according to acquisition module 11 specifically for obtaining
The maximum of the point all directions of the cloud in each layering of the barrier to be identified for taking, minimum value and included points, and join
In the coordinate information of barycenter and the total points put included by cloud of barrier to be identified of the point cloud for examining barrier to be identified
At least one, generate the layered characteristic vector of barrier to be identified.
Still optionally further, also include in the obstacle recognition system of the present embodiment:Determining module 14.
Wherein acquisition module 11 is additionally operable to obtain the coordinate information of the barycenter of the point cloud of barrier to be identified and to be identified
Barrier point cloud included by total points;
Corresponding, feature vector generation module 12 is specifically for the barrier to be identified that is obtained according to acquisition module 11
Maximum, minimum value and the included points of all directions of the cloud in each layering are put, and with reference to treating that acquisition module 11 is obtained
In total points included by the coordinate information of the barycenter of the point cloud of the barrier of identification and the point cloud of barrier to be identified extremely
It is few one, generate the layered characteristic vector of barrier to be identified.
Determining module 14 is used for the coordinate letter of the barycenter of the point cloud of the barrier to be identified obtained according to acquisition module 11
Breath, determines the position of barrier to be identified relative to Current vehicle.
Still optionally further, in the obstacle recognition system of the present embodiment feature vector generation module 12 specifically for:
According to the maximum and minimum value of putting length direction of the cloud in each layering of barrier to be identified, obtain and wait to know
Length information of the point cloud of other barrier in each layering;
According to the maximum and minimum value of putting width of the cloud in each layering of barrier to be identified, obtain and wait to know
Width information of the point cloud of other barrier in each layering;
Length information of the point cloud in each layering, width information and included points according to barrier to be identified,
The layered characteristic vector of generation barrier to be identified.
Still optionally further, in the obstacle recognition system of the present embodiment, also include:
Acquisition module 15 is used to gather the point cloud information of multiple default barriers for having marked barrier classification to be identified,
Dyspoiesis thing training set;
The point of the default barrier of multiple that training module 16 is used in the barrier training set gathered according to acquisition module 15
Cloud information, trains sorter model.
Accordingly, identification module 13 is used to be generated according to the sorter model and characteristic vector of the training in advance of training module 16
The layered characteristic vector of the barrier to be identified of the generation of module 12, recognizes the classification of barrier to be identified.
Still optionally further, in the obstacle recognition system of the present embodiment, training module 16 specifically for:
The point cloud of each default barrier is divided into the layering of the specified number of plies in height;Obtain the point of each default barrier
The maximum of all directions of the cloud in each layering, minimum value and included points;
The maximum for putting all directions of the cloud in each layering, minimum value and included point according to each default barrier
Number, generates the layered characteristic vector of each default barrier;Layered characteristic respectively according to each default barrier is vectorial and each pre-
If the classification of barrier, sorter model is trained, so that it is determined that sorter model.
The obstacle recognition system of the present embodiment, is known by using the realization of above-mentioned module to barrier to be identified
Not, the realization principle with above-mentioned related method embodiment is identical with technique effect, above-mentioned correlation technique is may be referred in detail and is implemented
The record of example, will not be repeated here.
The present invention also provides a kind of computer equipment, including memory, processor and storage on a memory and can located
The computer program run on reason device, realizes the obstacle recognition method as shown in above-mentioned embodiment during computing device program.
For example, a kind of structure chart of computer equipment that Fig. 4 is provided for the present invention.Fig. 4 shows and is suitable to for realizing this
The block diagram of the exemplary computer device 12a of invention embodiment.The computer equipment 12a that Fig. 4 shows is only an example,
Any limitation should not be carried out to the function of the embodiment of the present invention and using range band.
As shown in figure 4, computer equipment 12a is showed in the form of universal computing device.The component of computer equipment 12a can
To include but is not limited to:One or more processor or processor 16a, system storage 28a connect different system component
The bus 18a of (including system storage 28a and processor 16a).
Bus 18a represents one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, AGP, processor or the local bus using any bus structures in various bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Computer equipment 12a typically comprises various computing systems computer-readable recording medium.These media can be it is any can
The usable medium accessed by computer equipment 12a, including volatibility and non-volatile media, moveable and immovable Jie
Matter.
System storage 28a can include the computer system readable media of form of volatile memory, for example, deposit at random
Access to memory (RAM) 30a and/or cache memory 32a.Computer equipment 12a may further include that other are removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34a can be used for reading
Write immovable, non-volatile magnetic media (Fig. 4 do not show, commonly referred to " hard disk drive ").Although not shown in Fig. 4,
Can provide for the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-easy
The CD drive of the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 18a.Memory 28a can include at least one
Program product, the program product has one group of (for example, at least one) program module, and these program modules are configured to perform this
Invent the function of above-mentioned each embodiments of Fig. 1-Fig. 3.
With the one group of program of (at least one) program module 42a/utility 40a, can store in such as memory
In 28a, such program module 42a include --- but being not limited to --- operating system, one or more application program, other
Program module and routine data, potentially include the realization of network environment in each or certain combination in these examples.Journey
Sequence module 42a generally performs the function and/or method in above-mentioned each embodiments of Fig. 1-Fig. 3 described in the invention.
Computer equipment 12a can also be with one or more external equipments 14a (such as keyboard, sensing equipment, display
24a etc.) communication, also the equipment communication that is interacted with computer equipment 12a can be enabled a user to one or more, and/or
(such as network interface card is adjusted with any equipment for computer equipment 12a is communicated with one or more of the other computing device
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 22a.Also, computer equipment
12a can also by network adapter 20a and one or more network (such as LAN (LAN), wide area network (WAN) and/or
Public network, such as internet) communication.As illustrated, network adapter 20a passes through its of bus 18a and computer equipment 12a
Its module communicates.It should be understood that although not shown in, can combine computer equipment 12a use other hardware and/or software
Module, including but not limited to:Microcode, device driver, redundant processor, external disk drive array, RAID system, tape
Driver and data backup storage system etc..
Processor 16a by running program of the storage in system storage 28a so that perform various function application and
Data processing, for example, realize the obstacle recognition method shown in above-described embodiment.
The present invention also provides a kind of computer-readable medium, is stored thereon with computer program, and the program is held by processor
The obstacle recognition method as shown in above-mentioned embodiment is realized during row.
The computer-readable medium of the present embodiment can be included in the system storage 28a in above-mentioned embodiment illustrated in fig. 4
RAM30a, and/or cache memory 32a, and/or storage system 34a.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, can also directly from net
Network is downloaded, or is obtained using other modes.Therefore, the computer-readable medium in the present embodiment can not only include tangible
Medium, can also include invisible medium.
The computer-readable medium of the present embodiment can be using any combination of one or more computer-readable media.
Computer-readable medium can be computer-readable signal media or computer-readable recording 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
Combination more than person is any.The more specifically example (non exhaustive list) of computer-readable recording medium includes:With one
Or the electrical connection of multiple wires, portable computer diskette, hard disk, random access memory (RAM), read-only storage (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable recording medium can
Be it is any comprising or storage program tangible medium, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media can include the data-signal propagated in a base band or as a carrier wave part,
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 beyond computer-readable recording medium, the computer-readable medium can send, propagate or
Transmit for being used or program in connection by instruction execution system, device or device.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but do not limit
In --- wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
Computer for performing present invention operation can be write with one or more programming language or its combination
Program code, described program design language includes object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform on the user computer, partly perform on the user computer, performed as an independent software kit, portion
Part on the user computer is divided to perform on the remote computer or performed on remote computer or server completely.
Be related in the situation of remote computer, remote computer can be by the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (is for example carried using Internet service
Come by Internet connection for business).
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can store and be deposited in an embodied on computer readable
In storage media.Above-mentioned SFU software functional unit storage is in a storage medium, including some instructions are used to so that a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the present invention each
The part steps of embodiment methods described.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. it is various
Can be with the medium of store program codes.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention
Within god and principle, any modification, equivalent substitution and improvements done etc. should be included within the scope of protection of the invention.
Claims (14)
1. a kind of obstacle recognition method, it is characterised in that methods described includes:
The point cloud of barrier to be identified is divided into the layering of the specified number of plies in height;The specified number of plies includes at least two
Layer;
Obtain the maximum of the point all directions of the cloud in each layering of the barrier to be identified, minimum value and included
Points;
The maximum of point all directions of the cloud in each layering according to the barrier to be identified, minimum value and included
Points, generate the layered characteristic vector of the barrier to be identified;
The layered characteristic vector of sorter model and the barrier to be identified according to training in advance, recognizes described to be identified
Barrier classification.
2. method according to claim 1, it is characterised in that the point cloud according to the barrier to be identified is each described
The maximum of all directions in layering, minimum value and included points, generate the layered characteristic of the barrier to be identified
Vector, specifically includes:
The maximum of point all directions of the cloud in each layering according to the barrier to be identified, minimum value and included
Points, and with reference to the barrier to be identified point cloud barycenter coordinate information and the point of the barrier to be identified
At least one of total points included by cloud, generate the layered characteristic vector of the barrier to be identified.
3. method according to claim 2, it is characterised in that methods described also includes:
According to the barrier to be identified point cloud barycenter coordinate information, determine the barrier to be identified relative to
The position of Current vehicle.
4. method according to claim 1, it is characterised in that the point cloud according to the barrier to be identified is each described
The maximum of all directions in layering, minimum value and included points, generate the layered characteristic of the barrier to be identified
Vector, specifically includes:
According to the maximum and minimum value of putting length direction of the cloud in each layering of the barrier to be identified, obtain
Length information of the point cloud of the barrier to be identified in each layering;
According to the maximum and minimum value of putting width of the cloud in each layering of the barrier to be identified, obtain
Width information of the point cloud of the barrier to be identified in each layering;
The length information of the point cloud in each layering, the width information and institute according to the barrier to be identified
Including points, generate the layered characteristic vector of the barrier to be identified.
5. according to any described methods of claim 1-4, it is characterised in that sorter model according to training in advance and described
The layered characteristic vector of barrier to be identified, before recognizing the classification of the barrier to be identified, methods described also includes:
Collection multiple has marked the point cloud information of the default barrier of classification, dyspoiesis thing training set;
The point cloud information of the multiple default barrier in the barrier training set, trains the sorter model.
6. method according to claim 5, it is characterised in that the multiple default in the barrier training set
The point cloud information of barrier, trains the sorter model, specifically includes:
The point cloud of each default barrier is divided into the layering of the specified number of plies in height;Obtain each described pre- place obstacles
Hinder maximum, minimum value and the included points of all directions of the point cloud of thing in each layering;
The maximum of point all directions of the cloud in each layering according to each default barrier, minimum value and included
Points, generate the layered characteristic vector of each default barrier;
Layered characteristic respectively according to each default barrier is vectorial and classification of each default barrier, training classification
Device model, so that it is determined that the sorter model.
7. a kind of obstacle recognition system, it is characterised in that described device includes:
Division module, the layering for the point cloud of barrier to be identified to be divided into the specified number of plies in height;It is described to specify
The number of plies includes at least two-layer;
Acquisition module, the maximum of point all directions of the cloud in each layering for obtaining the barrier to be identified,
Minimum value and included points;
Feature vector generation module, for all directions according to the point cloud of the barrier to be identified in each layering
Maximum, minimum value and included points, generate the layered characteristic vector of the barrier to be identified;
Identification module, for the layered characteristic vector of the sorter model according to training in advance and the barrier to be identified,
Recognize the classification of the barrier to be identified.
8. device according to claim 7, it is characterised in that the feature vector generation module, specifically for according to institute
Maximum, minimum value and the included points of all directions of the point cloud of barrier to be identified in each layering are stated, and
With reference to included by the coordinate information of barycenter and the point cloud of the barrier to be identified of the point cloud of the barrier to be identified
At least one of total points, generate the layered characteristic vector of the barrier to be identified.
9. device according to claim 8, it is characterised in that described device also includes:
Determining module, for the coordinate information of the barycenter of the point cloud according to the barrier to be identified, determines described to be identified
Position of the barrier relative to Current vehicle.
10. device according to claim 7, it is characterised in that the feature vector generation module, specifically for:
According to the maximum and minimum value of putting length direction of the cloud in each layering of the barrier to be identified, obtain
Length information of the point cloud of the barrier to be identified in each layering;
According to the maximum and minimum value of putting width of the cloud in each layering of the barrier to be identified, obtain
Width information of the point cloud of the barrier to be identified in each layering;
The length information of the point cloud in each layering, the width information and institute according to the barrier to be identified
Including points, generate the layered characteristic vector of the barrier to be identified.
11. according to any described devices of claim 7-10, it is characterised in that described device also includes:
Acquisition module, the point cloud information for gathering multiple default barriers for having marked barrier classification to be identified, generation
Barrier training set;
Training module, for the point cloud information of the multiple default barrier in the barrier training set, trains institute
State sorter model.
12. devices according to claim 11, it is characterised in that the training module, specifically for:
The point cloud of each default barrier is divided into the layering of the specified number of plies in height;Obtain each described pre- place obstacles
Hinder maximum, minimum value and the included points of all directions of the point cloud of thing in each layering;
The maximum of point all directions of the cloud in each layering according to each default barrier, minimum value and included
Points, generate the layered characteristic vector of each default barrier;Respectively the layered characteristic according to each default barrier to
The classification of amount and each default barrier, trains sorter model, so that it is determined that the sorter model.
A kind of 13. computer equipments, including memory, processor and storage are on a memory and the meter that can run on a processor
Calculation machine program, it is characterised in that the side as described in any in claim 1-6 is realized during the computing device described program
Method.
A kind of 14. computer-readable mediums, are stored thereon with computer program, it is characterised in that the program is executed by processor
Methods of the Shi Shixian as described in any in claim 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710049464.5A CN106845412B (en) | 2017-01-20 | 2017-01-20 | Obstacle identification method and device, computer equipment and readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710049464.5A CN106845412B (en) | 2017-01-20 | 2017-01-20 | Obstacle identification method and device, computer equipment and readable medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106845412A true CN106845412A (en) | 2017-06-13 |
CN106845412B CN106845412B (en) | 2020-07-10 |
Family
ID=59121130
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710049464.5A Active CN106845412B (en) | 2017-01-20 | 2017-01-20 | Obstacle identification method and device, computer equipment and readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106845412B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108501954A (en) * | 2018-04-03 | 2018-09-07 | 北京瑞特森传感科技有限公司 | A kind of gesture identification method, device, automobile and storage medium |
CN108733065A (en) * | 2017-09-29 | 2018-11-02 | 北京猎户星空科技有限公司 | A kind of barrier-avoiding method of robot, device and robot |
CN109145680A (en) * | 2017-06-16 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information |
CN109215135A (en) * | 2018-09-07 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | A kind of Obstacle Position emulation mode, device and terminal based on statistics |
CN109901567A (en) * | 2017-12-08 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Method and apparatus for exporting obstacle information |
CN110271006A (en) * | 2019-07-19 | 2019-09-24 | 北京农业智能装备技术研究中心 | Mechanical arm visual guide method and device |
CN111626314A (en) * | 2019-02-28 | 2020-09-04 | 深圳市速腾聚创科技有限公司 | Point cloud data classification method and device, computer equipment and storage medium |
US10984588B2 (en) | 2018-09-07 | 2021-04-20 | Baidu Online Network Technology (Beijing) Co., Ltd | Obstacle distribution simulation method and device based on multiple models, and storage medium |
US11047673B2 (en) | 2018-09-11 | 2021-06-29 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device, apparatus and storage medium for detecting a height of an obstacle |
US11126875B2 (en) | 2018-09-13 | 2021-09-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium |
US11205289B2 (en) | 2018-09-07 | 2021-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device and terminal for data augmentation |
US11307302B2 (en) | 2018-09-07 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and device for estimating an absolute velocity of an obstacle, and non-volatile computer-readable storage medium |
US11718318B2 (en) | 2019-02-22 | 2023-08-08 | Apollo Intelligent Driving (Beijing) Technology Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
US11780463B2 (en) | 2019-02-19 | 2023-10-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus and server for real-time learning of travelling strategy of driverless vehicle |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
CN104091321A (en) * | 2014-04-14 | 2014-10-08 | 北京师范大学 | Multi-level-point-set characteristic extraction method applicable to ground laser radar point cloud classification |
US9383753B1 (en) * | 2012-09-26 | 2016-07-05 | Google Inc. | Wide-view LIDAR with areas of special attention |
CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术(北京)有限公司 | Road barrier identification method and device |
CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
-
2017
- 2017-01-20 CN CN201710049464.5A patent/CN106845412B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
US9383753B1 (en) * | 2012-09-26 | 2016-07-05 | Google Inc. | Wide-view LIDAR with areas of special attention |
CN104091321A (en) * | 2014-04-14 | 2014-10-08 | 北京师范大学 | Multi-level-point-set characteristic extraction method applicable to ground laser radar point cloud classification |
CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术(北京)有限公司 | Road barrier identification method and device |
CN106056659A (en) * | 2016-05-27 | 2016-10-26 | 山东科技大学 | Building corner space position automatic extraction method in vehicle laser scanning point cloud |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145680A (en) * | 2017-06-16 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information |
CN109145680B (en) * | 2017-06-16 | 2022-05-27 | 阿波罗智能技术(北京)有限公司 | Method, device and equipment for acquiring obstacle information and computer storage medium |
CN108733065A (en) * | 2017-09-29 | 2018-11-02 | 北京猎户星空科技有限公司 | A kind of barrier-avoiding method of robot, device and robot |
CN108733065B (en) * | 2017-09-29 | 2021-06-04 | 北京猎户星空科技有限公司 | Obstacle avoidance method and device for robot and robot |
CN109901567A (en) * | 2017-12-08 | 2019-06-18 | 百度在线网络技术(北京)有限公司 | Method and apparatus for exporting obstacle information |
CN108501954A (en) * | 2018-04-03 | 2018-09-07 | 北京瑞特森传感科技有限公司 | A kind of gesture identification method, device, automobile and storage medium |
US11205289B2 (en) | 2018-09-07 | 2021-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device and terminal for data augmentation |
CN109215135A (en) * | 2018-09-07 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | A kind of Obstacle Position emulation mode, device and terminal based on statistics |
US11354461B2 (en) | 2018-09-07 | 2022-06-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device for simulating a distribution of obstacles |
CN109215135B (en) * | 2018-09-07 | 2019-11-08 | 百度在线网络技术(北京)有限公司 | A kind of Obstacle Position emulation mode, device and terminal based on statistics |
US10984588B2 (en) | 2018-09-07 | 2021-04-20 | Baidu Online Network Technology (Beijing) Co., Ltd | Obstacle distribution simulation method and device based on multiple models, and storage medium |
US11307302B2 (en) | 2018-09-07 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and device for estimating an absolute velocity of an obstacle, and non-volatile computer-readable storage medium |
US11047673B2 (en) | 2018-09-11 | 2021-06-29 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device, apparatus and storage medium for detecting a height of an obstacle |
US11519715B2 (en) | 2018-09-11 | 2022-12-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device, apparatus and storage medium for detecting a height of an obstacle |
US11126875B2 (en) | 2018-09-13 | 2021-09-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium |
US11780463B2 (en) | 2019-02-19 | 2023-10-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus and server for real-time learning of travelling strategy of driverless vehicle |
US11718318B2 (en) | 2019-02-22 | 2023-08-08 | Apollo Intelligent Driving (Beijing) Technology Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
CN111626314A (en) * | 2019-02-28 | 2020-09-04 | 深圳市速腾聚创科技有限公司 | Point cloud data classification method and device, computer equipment and storage medium |
CN111626314B (en) * | 2019-02-28 | 2023-11-07 | 深圳市速腾聚创科技有限公司 | Classification method and device for point cloud data, computer equipment and storage medium |
CN110271006A (en) * | 2019-07-19 | 2019-09-24 | 北京农业智能装备技术研究中心 | Mechanical arm visual guide method and device |
Also Published As
Publication number | Publication date |
---|---|
CN106845412B (en) | 2020-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106845412A (en) | Obstacle recognition method and device, computer equipment and computer-readable recording medium | |
CN106709475A (en) | Obstacle recognition method and device, computer equipment and readable storage medium | |
CN106845416A (en) | Obstacle recognition method and device, computer equipment and computer-readable recording medium | |
CN106919908A (en) | Obstacle recognition method and device, computer equipment and computer-readable recording medium | |
CN106934347A (en) | Obstacle recognition method and device, computer equipment and computer-readable recording medium | |
CN111123735B (en) | Automatic driving simulation operation method and device | |
CN108319907A (en) | A kind of vehicle identification method, device and storage medium | |
WO2021249071A1 (en) | Lane line detection method, and related apparatus | |
CN106952303A (en) | Vehicle distance detecting method, device and system | |
CN109211574A (en) | Field test method, apparatus, equipment and the readable medium of pilotless automobile | |
CN107153363A (en) | The emulation test method and device of pilotless automobile, equipment and computer-readable recording medium | |
CN109901574A (en) | Automatic Pilot method and device | |
CN107038478A (en) | Road condition predicting method and device, computer equipment and computer-readable recording medium | |
CN107918753A (en) | Processing Method of Point-clouds and device | |
CN107665353A (en) | Model recognizing method, device, equipment and computer-readable recording medium based on convolutional neural networks | |
CN110471411A (en) | Automatic Pilot method and servomechanism | |
CN108230421A (en) | A kind of road drawing generating method, device, electronic equipment and computer storage media | |
CN110458854A (en) | A kind of road edge detection method and device | |
KR20180028442A (en) | Context-based fryers for object detection in images | |
CN103150774B (en) | A kind of highway green channel vehicle identification system and method | |
CN109145982A (en) | The personal identification method and device of driver, storage medium, terminal | |
CN109815884A (en) | Unsafe driving behavioral value method and device based on deep learning | |
CN111508252B (en) | Method and device for updating high-definition map by using V2X information integration technology | |
CN108470174A (en) | Method for obstacle segmentation and device, computer equipment and readable medium | |
CN106476697A (en) | A kind of driving indicating means and device |
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 |