CN109682388A - Follow the determination method in path - Google Patents
Follow the determination method in path Download PDFInfo
- Publication number
- CN109682388A CN109682388A CN201811572841.4A CN201811572841A CN109682388A CN 109682388 A CN109682388 A CN 109682388A CN 201811572841 A CN201811572841 A CN 201811572841A CN 109682388 A CN109682388 A CN 109682388A
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- image information
- target
- distance
- 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
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of determination methods for following path, comprising: obtains the location information of vehicle；According to the location information of vehicle, map datum is obtained；In preset duration, the multiple image information for following target that vehicle is followed is obtained；Every frame image information includes the temporal information for obtaining image information；According to temporal information, processing is fitted to multiple image information and map datum, obtains the location information for following target corresponding with each temporal information；When the difference of first angle information and second angle information is greater than the range of deflection of the holder of vehicle, according to corresponding first image information of first angle information and corresponding second image information of second angle information, predict the first prediction locus between the first image information and the second image information, spliced, obtains the initial trace for following target；It is generated after smoothing processing and follows path.Hereby it is achieved that when following target to be in outside cloud platform rotation range, it is also predicted that following the track of target.
Description
Technical field
The present invention relates to image and data processing field more particularly to a kind of determination methods for following path.
Background technique
With the development of economy and the emergence of artificial intelligence technology, autonomous driving vehicle is also increasingly by the pass in market
Note.Autonomous driving vehicle refers to closing by artificial intelligence, vision calculating, radar, monitoring device and global positioning system collaboration
Make, computer is allowed can to operate motor vehicles to automatic safe under the operation of nobody class active.Market prediction is driven automatically
Sailing the universal of automobile may be implemented to reduce traffic accident incidence, reduces traffic congestion degree, reduces investment traffic infrastructure
Cost and reduce pollution and other effects to environment.
In the prior art, the relevant technologies in automatic Pilot field are also and immature.Specifically how tracking target is being determined
Later, it is followed by automatic driving vehicle, and the track for following target is predicted, and guarantee that target is followed to leave figure
Picture capture range is no more than certain time, and there is no corresponding solutions for the prior art.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of determination method for following path is provided, it is existing in the prior art to solve
Problem.
To solve the above problems, the present invention provides a kind of determination methods for following path, which comprises
Obtain the location information of vehicle；
According to the location information of the vehicle, map datum is obtained；
In preset duration, the multiple image information for following target that vehicle is followed is obtained；Every frame described image information
Temporal information including obtaining described image information；
According to the temporal information, processing is fitted to the multiple image information and the map datum, obtain and
The corresponding location information for following target of each temporal information；
When the difference of first angle information and second angle information is greater than the range of deflection of the holder of vehicle, according to described
Corresponding first image information of first angle information and corresponding second image information of the second angle information predict described the
The first prediction locus between one image information and second image information；The first angle information be the vehicle with it is described
Follow the angle of the first location information in multiple location informations of target, the second angle information be the vehicle with it is described
The angle of the adjacent position information of first location information, the first image information and the first location information are corresponding, described
Second image information is corresponding with the adjacent position information of the first location information；
By the other positions information in addition to the adjacent position information of the first location information and the first location information
Spliced with first prediction locus, obtains the initial trace for following target；
The initial trace is smoothed, generation follows path.
In one possible implementation, after the method further include:
When the vehicle follows route according to, according to the current location information of the vehicle, present speed
With the real-time image information for following target described in acquisition, the vehicle and the time apart for following target are calculated；
When it is described at a distance of the time be not more than preset time threshold when, according to the real time environment perception data of the vehicle,
The obstacle information in path is followed described in determination；The obstacle information includes the type and size of the barrier；
According to the type and size, path is followed described in update.
In one possible implementation, before the method further include:
Obtain the first image information of vehicle periphery；
The first image information is handled, face characteristic is extracted；
The face characteristic and the image library prestored are matched；
When successful match, determine that the corresponding face of the face characteristic is to follow target.
In one possible implementation, before the method further include:
Obtain the second image information of vehicle periphery；
Second image information is handled, license board information is extracted；
The license board information and preset license board information library are matched；
When successful match, determine that the corresponding vehicle of the license plate of successful match is to follow target.
In one possible implementation, described according to the temporal information, to the multiple image information and described
Map datum is fitted processing, obtains the location information for following target corresponding with each temporal information, specifically
Include:
Every frame described image information is handled, the environmental data in every frame described image information is obtained；
The environmental data and preset map datum are fitted；
According to fitting result, the location information of target is followed described in determination.
In one possible implementation, described that the initial trace is smoothed, generation follow path it
Before, the method also includes:
When in the initial trace including broken line, the first curvature of the broken line is calculated；
When the first curvature is greater than the inverse of the minimum transition radius of the vehicle, the broken line is smoothly located
Reason；And/or
When in the initial trace including curve, the torsion of the curve is calculated；
When the torsion is greater than the inverse of the minimum transition radius of the vehicle, the curve is smoothly located
Reason.
In one possible implementation, described according to the type and size, path is followed described in update, it is specific to wrap
It includes:
When the barrier is fixed obstacle, according to the size of the fixed obstacle, path is followed described in update；
Alternatively,
When the barrier is moving obstacle, according to environment sensing data, update follows path.
In one possible implementation, after the method further include:
According to the real-time image information, the vehicle and the second distance for following target are calculated；
When the second distance is greater than preset second distance threshold value, the first notification message is generated；
By first notification message be sent to it is described follow target so that described follow target according to first notice
Message is in halted state；
The vehicle continues to travel, and when the second distance is not more than preset second distance threshold value, it is logical to generate second
Know message；
By the second notification message be sent to it is described follow target so that described follow target according to second notice
Message changes the halted state.
In one possible implementation, after the method further include:
According to the real-time image information, the vehicle and the second distance for following target are calculated；
When the second distance is greater than preset second threshold, third notice message is generated；The third notice message
Estimated waiting time including following target；
By the third notice message be sent to it is described follow target so that described follow target according to the third notice
Messages-Waiting estimated waiting time.
In one possible implementation, according to the second distance, the safety for following target Yu the vehicle
Distance, the real-time image information calculate estimated waiting time.
By applying the determination method provided in an embodiment of the present invention for following path, when following target to be in cloud platform rotation model
When enclosing outer, the track for following target can be predicted, and after splicing, obtain initial trace, after smoothing processing, obtain following road
Diameter, and ensure that and target is followed to leave image capture range no more than regular hour threshold value.
Detailed description of the invention
Fig. 1 is the determination method flow schematic diagram provided in an embodiment of the present invention for following path.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that for just
Part relevant to related invention is illustrated only in description, attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Before application method provided by the invention, tracking target is first determined, track target about determining, can pass through
The method of image feature comparison, for example, in the memory of vehicle, being stored with suspicion when applying the method in suspicion tracking
Doubt license plate number, the facial characteristics of suspicion personnel, suspicion personnel image information.When apply the method in follow cleaning when, can
To be stored with the feature of cleanup crew in the memory of vehicle, or it is previously stored with the license plate number of cleaning vehicle.
Fig. 1 is the determination method flow schematic diagram provided in an embodiment of the present invention for following path.This method is applied automatic
Vehicle is driven to be followed by the scene for following target travel.The executing subject of this method can be the control list of automatic driving vehicle
Member.Control unit for vehicle can be understood as the control module for controlling vehicle driving.As shown in Figure 1, this method includes following
Step:
Step 101, the location information of vehicle is obtained.
Specifically, the locating module on vehicle, such as global positioning system (Global Positioning can be passed through
System, GPS) obtain vehicle itself location information.It can also be by sending query messages, resolution server hair to server
After the response message of the carrying location information sent, location information is obtained.
Wherein, it follows target to can be people, such as suspicion person, cleaner, is also possible to vehicle, such as cleaning vehicle, suspicion
Vehicle etc. is doubted, when following target is suspicion person or suspected vehicles, can be used for tracking suspect, when following target to be cleaning
Worker or when cleaning vehicle, can be used for following cleaning or for cleaning Vehicular charging etc., the application does not limit this.
Wherein, location information may include longitude and latitude data and temporal information.
Step 102, according to the location information of vehicle, map datum is obtained.
Specifically, the map of the position can be loaded when vehicle is in a certain location information, for example, vehicle is in the street A
Road can be loaded the upper level unit in the street A, the map in the city A.As to how load, can be under server
It carries, is also possible to vehicle and loads in advance, the application does not limit this.
Step 103, in preset duration, the multiple image information for following target that vehicle is followed is obtained.
Wherein, every frame image information includes the temporal information for obtaining image information.
Specifically, vehicle, which has had predetermined that, follows target before acquisition follows the image information of target.Example and
Non-limiting, vehicle can predefine according to following method and follow target.
In one example, when follow target be cleanup crew when, can by the matched method of face characteristic, determine with
With the ID of target.
Firstly, obtaining the image information of vehicle periphery；
Then, image information is handled, extracts face characteristic；
Then, face characteristic and the image library prestored are matched；
Finally, determining that the corresponding face of face characteristic is to follow target when successful match.
Specifically, control unit for vehicle can be handled the image information of acquisition, image information is therefrom extracted.Again
By face recognition algorithms, image information is handled, extracts face characteristic.Further, in addition to being equipped on vehicle
Binocular camera is also equipped with various radars, for example, laser radar, laser radar can collect laser point cloud data.It can be with
By the laser point cloud data of radar, face characteristic is modified, to further increase the precision of image.
Specifically, obtaining point cloud segmentation result firstly, be split and track to laser point cloud data；
Then, point cloud segmentation result is handled, obtains the first face characteristic；
Then, by Face datection algorithm, video data is handled, after extracting image information, can identify figure
As the human face region in information；
Then, it is extracted by face characteristic, the second face characteristic is extracted from human face region；
Finally, on a timeline, being modified by the first face characteristic to the second face characteristic, obtaining face characteristic.
Makeover process, as judge point cloud segmentation with tracking object whether with feature identification object match, for example, point cloud segmentation
With by object identification be pedestrian in tracking result, the identification of face characteristic object also identifies as pedestrian, then both to this object
Recognition result coincide, when identical, the second face characteristic is enhanced or is supplemented using the first face characteristic.Such as fruit dot cloud
Segmentation with by object identification be pedestrian in tracking result, face characteristic object recognition and tracking result identifies as vehicle, then two
Person's recognition result is misfitted.
When the two is coincide, enhances scheduling algorithm using details, the image information comprising face characteristic is enhanced.
When the quantity of camera is multiple, then multiple video datas are corresponded to, Face datection algorithm is can use, detects
Human face region in each video data.For each human face region, Face datection algorithm can use, extract it to deserved
Second face characteristic.For multiple second face characteristics, existing algorithm can use, rejected or merged, obtain people
Face feature.Finally, can judge whether to match by preset matching threshold, for example, matching threshold can be set to
90%, when calculating matching degree not less than 90%, it is considered as successful match.When determine the corresponding face of face characteristic be with
When with target, the ID of face as follows the ID of target.
It in another example, is vehicle when following target, for example, license plate ratio can be passed through when another cleaning vehicle
Right, determination follows target.
It is possible, firstly, to obtain the second image information of vehicle periphery；
Then, the second image information is handled, extracts license board information；
Then, license board information and preset license board information library are matched；
Finally, determining that the corresponding vehicle of the license plate of successful match is to follow target when successful match.
Successful match herein, can be setting matching threshold is 100%, to guarantee in collected second image information
License board information and the license board information in preset license board information library it is completely the same.
Step 104, according to temporal information, processing is fitted to multiple image information and map datum, is obtained and each
The corresponding location information for following target of temporal information.
It wherein, include environmental data, such as building mark, traffic mark, road markings etc. in image information.
After environmental data and map datum are fitted, the same characteristic features in the two can be carried out with integrated treatment, meter
Calculate the location information for following target.
When follow target be suspicion person perhaps suspected vehicles or follow target do not have locating module, such as signal send out
It, can not actively or therefore can be by believing acquired image with vehicle interaction locations information whens raw device, GPS etc.
Breath is handled, to obtain the location information for following target.
Specifically, can first handle image information, the environmental data in every frame image information is obtained；
Then environmental data and preset map datum are fitted；
Finally, determining the multiple location informations for following target according to fitting result.
Wherein, due to including temporal information in image information, the location information for following target finally determined can also
To include temporal information, which can be the temporal information in image information.
Step 105, when the difference of first angle information and second angle information is greater than the range of deflection of the holder of vehicle,
According to corresponding first image information of first angle information and corresponding second image information of second angle information, the first figure is predicted
As the first prediction locus between information and the second image information.
Wherein, first angle information is vehicle and the folder that follows the first location information in multiple location informations of target
Angle, second angle information are the angle of the adjacent position information of vehicle and first location information, the first image information and first
Confidence breath corresponds to, and the second image information is corresponding with the adjacent position information of first location information.
Specifically, being equipped with holder on vehicle, acquisition device is installed on holder, acquisition device, which can be, obtains above-mentioned figure
As the camera of information.The revolving speed and circle number of motor can be controlled, by electric machine controller to realize that motor drives holder to carry out
Rotation.But holder range of deflection be it is preset, such as 5 ° to 355 °, when phase of the holder from first position to first position
When ortho position is set, if the angle information of cloud platform rotation is not in holder range of deflection, target is followed to be in image capture range
Except, track when target being followed to be in except image capture range can be predicted by trajectory predictions.
Wherein, example and it is non-limiting, can use gauss hybrid models predict two positions between track.
Step 106, by the other positions information in addition to the adjacent position information of first location information and first location information
Spliced with the first prediction locus, obtains the initial trace for following target.
Specifically, in addition to the adjacent position information of first location information and first location information, if there is other adjacent
The distance of two location informations is more than first threshold, and can carry out trajectory predictions according to the above method can for other positions
To be spliced according to time sequencing, and spliced with the first prediction locus, obtains the initial trace for following target.
Specifically, control unit gets a series of location information in certain duration, those location informations can be with
A discrete path point is constituted, after this discrete path point connection, is properly termed as initial trace.
It is understood that including any one in straight line, curve and broken line or any combination thereof in initial trace.
Step 107, initial trace is smoothed, generation follows path.
Specifically, after being smoothed, can also calculate each path point first is bent for broken line therein
Rate can calculate the torsion of each path point for curve therein.
Further, before step 107, further includes:
When in initial trace including broken line, the first curvature of broken line is calculated；
When first curvature is greater than the inverse of the minimum transition radius of vehicle, broken line is smoothed；And/or
When in initial trace including curve, the torsion of calculated curve；
When torsion is greater than the inverse of the minimum transition radius of vehicle, curve is smoothed.
Wherein, it is known that the minimum of vehicle, which turns radius this parameter, for example, minimum transition radius can be 1.5m.
Specifically, in the parameter information of cleaning vehicle, including minimum transition radius, by interpolation method, broken line carries out smooth
After processing, the first curvature of broken line is obtained.Inverse by first curvature, torsion respectively with minimum transition radius compares
Compared with when first curvature or torsion are greater than the inverse of minimum transition radius, which meets the requirements, when first curvature or the
When two curvature are greater than the inverse of minimum transition radius, the broken line after corresponding curve or smoothing processing is continued smoothly to locate
Reason.
Further, after step 107, this method further include:
Step 108, it when vehicle is according to route is followed, according to the current location information of vehicle, present speed and obtains
What is taken follows the real-time image information of target, calculates vehicle and follows the time apart of target.
Specifically, the present speed of vehicle can be calculated by differential GPS.Acquisition device can be binocular camera, can
To calculate vehicle according to real-time image information using the binocular range measurement principle of binocular camera and follow at a distance from target.
At the same time it can also calculate the speed for following target according to real-time image information.
According to following the speed of target, the speed of vehicle, vehicle and following at a distance from target, vehicle can be calculated and followed
The time apart of target.
Step 109, when at a distance of the time preset time threshold is not more than, according to the real time environment perception data of vehicle,
Determine the obstacle information followed in path；Obstacle information includes the type and size of barrier.
Specifically, illustrating to follow target also in image capture model when at a distance of the time preset time threshold is not more than
In enclosing, at this point it is possible to be followed.
It is possible, firstly, to calculate obstacle information according to image information and preset map datum.
Barrier herein, can be building on fixed obstacle, such as map, fixed traffic sign (for example, with
In the bar of fixed traffic lights), fixed object (for example, static vehicle, pedestrian, curb).These barriers can pass through image
Information and map datum, directly obtain.
Then, the current perception data and obstacle information of sensing module acquisition is handled, generates target disorders
Object information.
Sensing module can be the laser radar, ultrasonic radar, vision module etc. installed on vehicle, these sensing modules
It can obtain in vehicle travel process in real time, obstacle information of surrounding, such as lane line, the barrier of movement etc., variation
Traffic lights, the obstacle information perceived in driving process in conjunction with above-mentioned obstacle information and herein can after fusion treatment
To obtain final obstacle information, referred to as target obstacle information.
Step 110, according to type and size, update follows path.
Further, after step 107, further includes:
According to real-time image information, calculates vehicle and follow the second distance of target；
When second distance is greater than preset second distance threshold value, the first notification message is generated；
First notification message is sent to and follows target, so that following target to be according to the first notification message stops shape
State；
Vehicle continues to travel, and when second distance is not more than preset second distance threshold value, generates second notification message；
Second notification message is sent to and follows target, so that following target to be changed according to second notification message stops shape
State.
Specifically, when vehicle with follow excessive at a distance from target when, vehicle can be made by way of sending a notification message
Target must be followed to be in halted state, when distance reaches requirement, and can be by way of sending a notification message, so that following
Target changes current halted state, continues to move ahead.
Further, after step 107, further includes:
According to real-time image information, calculates vehicle and follow the second distance of target；
When second distance is greater than preset second threshold, third notice message is generated；Third notice message includes following
The estimated waiting time of target；
Third notice message is sent to and follows target, so as to which target is followed to wait according to third notice Messages-Waiting is estimated
Duration.
Wherein it is possible to according to second distance, follow the safe distance of target and vehicle, real-time image information is calculated estimated
Waiting time.
Specifically, vehicle, when sending a notification message, which may include estimated waiting time, so that following mesh
After mark stops, and after estimated waiting time, continue to move ahead.
By applying the determination method provided in an embodiment of the present invention for following path, when following target to be in cloud platform rotation model
When enclosing outer, the track for following target can be predicted, and after splicing, obtain initial trace, after smoothing processing, obtain following road
Diameter, and ensure that and target is followed to leave image capture range no more than regular hour threshold value.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above specific embodiment has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Illustrate, it should be understood that the above is only a specific embodiment of the invention, the protection model that is not intended to limit the present invention
It encloses, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in the present invention
Protection scope within.
Claims (10)
1. a kind of determination method for following path, which is characterized in that the described method includes:
Obtain the location information of vehicle；
According to the location information of the vehicle, map datum is obtained；
In preset duration, the multiple image information for following target that vehicle is followed is obtained；Every frame described image information includes
Obtain the temporal information of described image information；
According to the temporal information, processing is fitted to the multiple image information and the map datum, is obtained and each
The corresponding location information for following target of the temporal information；
When the difference of first angle information and second angle information is greater than the range of deflection of the holder of vehicle, according to described first
Corresponding first image information of angle information and corresponding second image information of the second angle information predict first figure
As the first prediction locus between information and second image information；The first angle information is that the vehicle is followed with described
The angle of first location information in multiple location informations of target, the second angle information are the vehicle and described first
The angle of the adjacent position information of location information, the first image information and the first location information are corresponding, and described second
Image information is corresponding with the adjacent position information of the first location information；
By in addition to the adjacent position information of the first location information and the first location information other positions information and institute
It states the first prediction locus to be spliced, obtains the initial trace for following target；
The initial trace is smoothed, generation follows path.
2. the method according to claim 1, wherein after the method further include:
When the vehicle follows route according to, according to the current location information of the vehicle, present speed and obtain
The real-time image information for following target taken calculates the vehicle and the time apart for following target；
When it is described at a distance of the time be not more than preset time threshold when, according to the real time environment perception data of the vehicle, determine
The obstacle information followed in path；The obstacle information includes the type and size of the barrier；
According to the type and size, path is followed described in update.
3. the method according to claim 1, wherein before the method further include:
Obtain the first image information of vehicle periphery；
The first image information is handled, face characteristic is extracted；
The face characteristic and the image library prestored are matched；
When successful match, determine that the corresponding face of the face characteristic is to follow target.
4. the method according to claim 1, wherein before the method further include:
Obtain the second image information of vehicle periphery；
Second image information is handled, license board information is extracted；
The license board information and preset license board information library are matched；
When successful match, determine that the corresponding vehicle of the license plate of successful match is to follow target.
5. the method according to claim 1, wherein described according to the temporal information, to the multiple image
Information and the map datum are fitted processing, obtain the position for following target corresponding with each temporal information
Information specifically includes:
Every frame described image information is handled, the environmental data in every frame described image information is obtained；
The environmental data and preset map datum are fitted；
According to fitting result, the location information of target is followed described in determination.
6. being generated the method according to claim 1, wherein described be smoothed the initial trace
Before following path, the method also includes:
When in the initial trace including broken line, the first curvature of the broken line is calculated；
When the first curvature is greater than the inverse of the minimum transition radius of the vehicle, the broken line is smoothed；
And/or
When in the initial trace including curve, the torsion of the curve is calculated；
When the torsion is greater than the inverse of the minimum transition radius of the vehicle, the curve is smoothed.
7. being followed described in update the method according to claim 1, wherein described according to the type and size
Path specifically includes:
When the barrier is fixed obstacle, according to the size of the fixed obstacle, path is followed described in update；Or
Person,
When the barrier is moving obstacle, according to environment sensing data, update follows path.
8. the method according to claim 1, wherein after the method further include:
According to the real-time image information, the vehicle and the second distance for following target are calculated；
When the second distance is greater than preset second distance threshold value, the first notification message is generated；
By first notification message be sent to it is described follow target so that described follow target according to first notification message
In halted state；
The vehicle continues to travel, and when the second distance is not more than preset second distance threshold value, generates the second notice and disappears
Breath；
By the second notification message be sent to it is described follow target so that described follow target according to the second notification message
Change the halted state.
9. the method according to claim 1, wherein after the method further include:
According to the real-time image information, the vehicle and the second distance for following target are calculated；
When the second distance is greater than preset second threshold, third notice message is generated；The third notice message includes
Follow the estimated waiting time of target；
By the third notice message be sent to it is described follow target so that described follow target according to the third notice message
Wait estimated waiting time.
10. according to the method described in claim 9, it is characterized in that, according to the second distance, it is described follow target with it is described
The safe distance of vehicle, the real-time image information calculate estimated waiting time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572841.4A CN109682388B (en) | 2018-12-21 | 2018-12-21 | Method for determining following path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572841.4A CN109682388B (en) | 2018-12-21 | 2018-12-21 | Method for determining following path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109682388A true CN109682388A (en) | 2019-04-26 |
| CN109682388B CN109682388B (en) | 2020-12-25 |
Family
ID=66188128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811572841.4A Active CN109682388B (en) | 2018-12-21 | 2018-12-21 | Method for determining following path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109682388B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428603A (en) * | 2019-07-26 | 2019-11-08 | 北京主线科技有限公司 | Following Car travel control method and device in container truck formation |
| CN111337941A (en) * | 2020-03-18 | 2020-06-26 | 中国科学技术大学 | Dynamic obstacle tracking method based on sparse laser radar data |
| CN111479063A (en) * | 2020-04-15 | 2020-07-31 | 上海摩象网络科技有限公司 | Holder driving method and device and handheld camera |
| CN112802066A (en) * | 2021-01-26 | 2021-05-14 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
| CN113741506A (en) * | 2020-05-28 | 2021-12-03 | 华为技术有限公司 | Method and device for unmanned aerial vehicle to follow vehicle |
| CN114566052A (en) * | 2022-04-27 | 2022-05-31 | 华南理工大学 | Method for judging rotation of highway traffic flow monitoring equipment based on traffic flow direction |
| WO2024021340A1 (en) * | 2022-07-27 | 2024-02-01 | 东莞市本末科技有限公司 | Robot following method and apparatus, and robot and computer-readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010072996A1 (en) * | 2008-12-22 | 2010-07-01 | Qinetiq Limited | Aircraft landing monitoring system |
| CN102508246A (en) * | 2011-10-13 | 2012-06-20 | 吉林大学 | Method for detecting and tracking obstacles in front of vehicle |
| CN105678809A (en) * | 2016-01-12 | 2016-06-15 | 湖南优象科技有限公司 | Handheld automatic follow shot device and target tracking method thereof |
| CN106155065A (en) * | 2016-09-28 | 2016-11-23 | 上海仙知机器人科技有限公司 | A kind of robot follower method and the equipment followed for robot |
| CN107010066A (en) * | 2015-12-07 | 2017-08-04 | 株式会社斯巴鲁 | The travel controlling system of vehicle |
| US20170277392A1 (en) * | 2016-03-24 | 2017-09-28 | The Boeing Company | Vehicle map icon |
| CN108549410A (en) * | 2018-01-05 | 2018-09-18 | 灵动科技（北京）有限公司 | Active follower method, device, electronic equipment and computer readable storage medium |
-
2018
- 2018-12-21 CN CN201811572841.4A patent/CN109682388B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010072996A1 (en) * | 2008-12-22 | 2010-07-01 | Qinetiq Limited | Aircraft landing monitoring system |
| CN102508246A (en) * | 2011-10-13 | 2012-06-20 | 吉林大学 | Method for detecting and tracking obstacles in front of vehicle |
| CN107010066A (en) * | 2015-12-07 | 2017-08-04 | 株式会社斯巴鲁 | The travel controlling system of vehicle |
| CN105678809A (en) * | 2016-01-12 | 2016-06-15 | 湖南优象科技有限公司 | Handheld automatic follow shot device and target tracking method thereof |
| US20170277392A1 (en) * | 2016-03-24 | 2017-09-28 | The Boeing Company | Vehicle map icon |
| CN106155065A (en) * | 2016-09-28 | 2016-11-23 | 上海仙知机器人科技有限公司 | A kind of robot follower method and the equipment followed for robot |
| CN108549410A (en) * | 2018-01-05 | 2018-09-18 | 灵动科技（北京）有限公司 | Active follower method, device, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张瑞成: "基于图像识别的多智能车跟随与防撞控制系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428603A (en) * | 2019-07-26 | 2019-11-08 | 北京主线科技有限公司 | Following Car travel control method and device in container truck formation |
| CN111337941A (en) * | 2020-03-18 | 2020-06-26 | 中国科学技术大学 | Dynamic obstacle tracking method based on sparse laser radar data |
| CN111337941B (en) * | 2020-03-18 | 2022-03-04 | 中国科学技术大学 | Dynamic obstacle tracking method based on sparse laser radar data |
| CN111479063A (en) * | 2020-04-15 | 2020-07-31 | 上海摩象网络科技有限公司 | Holder driving method and device and handheld camera |
| CN111479063B (en) * | 2020-04-15 | 2021-04-06 | 上海摩象网络科技有限公司 | Holder driving method and device and handheld camera |
| CN113741506A (en) * | 2020-05-28 | 2021-12-03 | 华为技术有限公司 | Method and device for unmanned aerial vehicle to follow vehicle |
| CN112802066A (en) * | 2021-01-26 | 2021-05-14 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
| CN112802066B (en) * | 2021-01-26 | 2023-12-15 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
| CN114566052A (en) * | 2022-04-27 | 2022-05-31 | 华南理工大学 | Method for judging rotation of highway traffic flow monitoring equipment based on traffic flow direction |
| CN114566052B (en) * | 2022-04-27 | 2022-08-12 | 华南理工大学 | Method for judging rotation of highway traffic flow monitoring equipment based on traffic flow direction |
| WO2024021340A1 (en) * | 2022-07-27 | 2024-02-01 | 东莞市本末科技有限公司 | Robot following method and apparatus, and robot and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109682388B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109682388A (en) | Follow the determination method in path | |
| CN109686031A (en) | Identification follower method based on security protection | |
| US11967230B2 (en) | System and method for using V2X and sensor data | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| KR20200123474A (en) | Framework of navigation information for autonomous navigation | |
| CN110114253A (en) | Controller of vehicle, control method for vehicle and program | |
| CN109448439B (en) | Vehicle safe driving method and device | |
| JP2019536184A (en) | Road detection using traffic sign information | |
| US11042159B2 (en) | Systems and methods for prioritizing data processing | |
| CN109739267A (en) | Follow the determination method in path | |
| JP7110996B2 (en) | Vehicle information processing device and vehicle information processing method | |
| CN109740462A (en) | The identification follower method of target | |
| US11403947B2 (en) | Systems and methods for identifying available parking spaces using connected vehicles | |
| JP7194130B2 (en) | A method and apparatus for detecting emergency vehicles in real time and planning driving routes to deal with situations expected to be caused by emergency vehicles. | |
| CN109740461A (en) | Target is with subsequent processing method | |
| US11260875B2 (en) | Systems and methods for road surface dependent motion planning | |
| CN108958264A (en) | Road traffic checking method and vehicle based on automatic Pilot technology | |
| WO2021010083A1 (en) | Information processing device, information processing method, and information processing program | |
| CN112937582A (en) | System, non-transitory computer readable medium, and method for improving lane change detection | |
| Damerow et al. | Intersection warning system for occlusion risks using relational local dynamic maps | |
| CN109709953A (en) | Vehicle follower method in road cleaning operation | |
| CN112519799A (en) | Motor vehicle road auxiliary driving device and method | |
| CN114973644B (en) | Road information generating device | |
| CN113741458B (en) | Robot on-site help following or gesture guiding driving method and system | |
| US11851088B2 (en) | Method for determining capability boundary and associated risk of a safety redundancy autonomous system in real-time |
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: 20220808 Address after: 401122 No.1, 1st floor, building 3, No.21 Yunzhu Road, Yubei District, Chongqing Patentee after: Chongqing landshipu Information Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Patentee before: Beijing Idriverplus Technology Co.,Ltd. |