CN109740462A - The identification follower method of target - Google Patents
The identification follower method of target Download PDFInfo
- Publication number
- CN109740462A CN109740462A CN201811572824.0A CN201811572824A CN109740462A CN 109740462 A CN109740462 A CN 109740462A CN 201811572824 A CN201811572824 A CN 201811572824A CN 109740462 A CN109740462 A CN 109740462A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- vehicle
- image information
- followed
- 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
Abstract
The present invention provides a kind of identification follower methods of target, comprising: obtains within the scope of inspection, the multiple image information in the preset duration of the acquisition device acquisition of vehicle；Determine suspect object；When state is moving condition, determine that suspect object is to follow target；Data according to the map, determine follow the mode select information for fixed heel with or at random follow；It at any time, according to multiple image information and map datum, determines the multiple location informations for following target when for fixed heel and generation first follows path；When vehicle with follow at a distance from target no more than preset distance threshold when, calculate angle information；After cloud platform rotation, path is followed to be followed according to first；When at random at any time, prediction second follows path；When time difference is not more than preset time threshold, path is followed according to second, is followed.The data of automatic driving vehicle are utilized as a result, and have reached security effect, save security protection investment.
Description
Technical field
The present invention relates to the identification follower methods of field of security technology more particularly to a kind of target.
Background technique
In the prior art, in order to carry out security protection, often through arrangement camera, the data acquired by camera are carried out
Recognition of face, to identify abnormal personnel.But often there is costly, monitoring the defects of dead angle for this mode.
Unmanned equipment is to perceive road environment by vehicle-mounted sensor-based system, and automatic planning travelling line simultaneously controls vehicle
Reach the smart machine of predeterminated target.It can use onboard sensor to perceive vehicle-periphery, and is obtained according to perception
Road, vehicle location and the obstacle information obtained, controls the steering and speed of vehicle, to enable the vehicle to reliably and securely
It is travelled on road.
Existing automatic driving vehicle in the process of walking, can generate a large amount of data, these data are only used as nobody
The assessment of vehicle performance is driven, but without other purposes.
Therefore, the data of unmanned equipment how are utilized, and save the cost of city security protection, and combine by the two
When getting up, can also intelligence the mode that follows of generation, be a problem to be solved.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of data processing method is provided, to solve problems of the prior art.
To solve the above problems, the present invention provides a kind of identification follower methods of target, which comprises
It obtains within the scope of inspection, the multiple image information in the preset duration of the acquisition device acquisition of vehicle；Described in every frame
Image information includes obtaining the temporal information of the image information；
Described image information is handled, determines suspect object；The suspect object includes suspicious object or suspicious
The implementer of event；
According to the temporal information, the state of the suspect object is determined；The state includes moving condition or static shape
State；
When the state is moving condition, determine that the suspect object is to follow target；
Obtain the corresponding map datum of location information of the location information and the vehicle of the vehicle；
According to the map datum, determine follow the mode select information for fixed heel with or at random follow；
When the follow the mode select information for fixed heel at any time, according to the multiple image information and the map number
According to, determine described in follow multiple location informations of target；
According to the multiple location informations for following target, generates first and follow path；
When following target to carry out at any time to described, according to the current location information of the vehicle, the target that follows
Multiple location informations and described first follow path, calculate the vehicle and follow at a distance from target with described；
When the distance is not more than preset distance threshold, the position that follows path and the vehicle according to described first
Information calculates the vehicle and the angle information for following target；
According to the current location information of the angle information and the vehicle, control signal is generated；
The control signal is sent to the electric machine controller on the holder for being used to drive the acquisition device rotation, so that
The electric machine controller is rotated according to the revolving speed for controlling signal control motor, and by the motor to drive the holder
On acquisition device rotated；
After rotation, path is followed according to described first, is followed；
When the follow the mode selects information at random at any time, according to the multiple image information, following described in determination
Multiple location informations of target；
According to the multiple image information and the map datum, the second of target is followed to follow path described in prediction；
According to the location information of the multiple location informations for following target and the vehicle, calculate the vehicle with it is described
Follow the time difference of target；
When the time difference is not more than preset time threshold, path is followed according to described second, is followed.
In one possible implementation, described that described image information is handled, determine suspect object, it is specific to wrap
It includes:
Respectively by described image information feature and suspicious object feature database, suspicion image library match；
When with the suspicious object feature database successful match, determine that suspect object is suspicious object；
When with the suspicion image library successful match, determine that suspect object is the implementer of suspicious event.
In one possible implementation, described after rotation, path is followed according to described first, is carried out with therewith
Before, the method also includes:
When the difference of first angle information and second angle information is greater than the range of deflection of the holder, according to described the
The corresponding first location information of one angle information and the corresponding second location information of the second angle information, prediction described first
Prediction locus between location information and the second location information；The first angle information follows mesh with described for the vehicle
The angle of first location information in the multiple location informations of target, the second angle information are the vehicle and described first
The angle of the adjacent position information of confidence breath, the first image information and the first location information are corresponding, second figure
As 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 the prediction locus, obtains described following the first of target to follow path.
In one possible implementation, described according to the multiple image information and the map datum, predict institute
It states and follows the second of target to follow path, specifically include:
Described image information is handled, the movement and/or facial tiny characteristic of target are followed described in determination；
The next step of target is followed to act according to the movement and/or facial tiny characteristic, prediction；
According to next step movement and the map datum, track of the target in preset duration is followed described in prediction.
In one possible implementation, when following path according to described first or second path followed to be followed
When, the method also includes:
The real-time image information of target is followed described in acquisition；
By in the real-time image information feature and suspicious object feature database, suspicion characteristics of image library match, it is raw
At matching result；
The matching result is analyzed, when in the suspicious object feature database or suspicion characteristics of image library extremely
When a kind of few successful match, the current location information of the real-time image information, the matching result and the vehicle is sent
To third-party server.
In one possible implementation, it is described when the follow the mode select information for fixed heel at any time, according to institute
Multiple image information and the map datum are stated, multiple location informations of target are followed described in determination, are specifically included:
The multiple image information is handled, the ring in every frame image information in the multiple image information is obtained
Border data；
The environmental data and the map datum are fitted, according to fitting result, follow target described in determination
Location information.
In one possible implementation, the method also includes:
When the state is stationary state, described image information, the suspect object are sent to third-party server.
In one possible implementation, described after acquisition device rotation, path is followed according to described, is carried out
After following, further includes:
When the distance is not less than preset distance threshold, generate warning message, the warning message include it is current it
Preceding image information；
The warning message is sent to server and/or third-party server, so that server and/or third party's service
Device to it is described it is current before image information handle.
By the identification follower method of application target provided by the invention, in unmanned equipment, filled using its acquisition
The image information for setting acquisition determines suspicion object, and determines that the suspicion object of moving condition is to follow target, follows mesh in locking
Mark, data, generate different follow the mode, and under each follow the mode according to the map, to following target to follow, by
This, is utilized the data of automatic driving vehicle, and has reached security effect, saves security protection investment.
Detailed description of the invention
Fig. 1 is the identification follower method flow diagram of target provided in an embodiment of the present invention.
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.
Fig. 1 is the identification follower method flow diagram of target provided in an embodiment of the present invention.The executing subject of this method
It can be the control unit of automatic driving vehicle.Control unit for vehicle can be understood as the control mould for controlling vehicle driving
Block.Wherein, control unit is the data processing centre of the automatic driving vehicle, can make decisions on one's own with path planning etc..
The identification follower method is applied in unmanned scene, especially in automatic driving vehicle, especially city (non-closed loop garden
Area) automatic driving vehicle.The data of unmanned equipment can be utilized as a result, and save the cost of city security protection.
As shown in Figure 1, method includes the following steps:
Step 101, it obtains within the scope of inspection, the multiple image information in the preset duration of the acquisition device acquisition of vehicle；
Every frame image information includes the temporal information for obtaining the image information.
Specifically, can use automatic driving vehicle in order to save human resources and carry out cleaning works, in automatic cleaning
When, it can use the structure of vehicle itself, take into account and inspection is carried out to the safety in section.Example and it is non-limiting, some special
Period, for example, the period progress cleaning works that this group traveling together of 00:00-5:00 is fewer, is cleaned same in cleaning vehicle
When, inspection can be carried out to section is cleaned.
Specifically, having acquisition device on vehicle, acquisition device can be binocular camera.It can use binocular camera
Get vehicle the video information through section, video data is handled, multiple image information is therefrom extracted.Every frame figure
As information all includes temporal information.
Step 102, image information is handled, determines suspect object；Suspect object includes suspicious object or suspicious
The implementer of event.
Specifically, carrying out certain processing, such as feature extraction to image information.By the feature extracted respectively with it is suspicious
Article characteristics library and suspicion characteristics of image library are matched, and the matching result of generation can be matching degree, when matching degree is greater than
When preset threshold, it can determine that successful match, i.e. suspicious object in image information are confirmed to be suspicious object or suspicious thing
The implementer of part is a suspect in suspicion characteristics of image library.
Wherein, example and it is non-limiting, suspicious object can be certain control utensils, be carried package walked etc., suspicious row
Children etc. are embraced away by force for that can be suspected to be.
Further, various radars are also equipped with, for example, laser radar, swashs in addition to being equipped with binocular camera on vehicle
Optical radar can collect laser point cloud data.By the laser point cloud data of radar, can determine suspicious object profile or
The profile of person's face matches the feature in the profile and image information of the profile of suspicious object or face, with into one
Step improves the precision of image.
Wherein, suspicious object and suspicious event be may be simultaneously present in image information.
Further, in order to improve matched accuracy, after above-mentioned successful match, Secondary Match can also be carried out, than
Such as, can by the successful image information of current matching, suspicious object feature database suspicious object and/or suspicion characteristics of image library
In a suspect, it is matched with the feature database in another more accurate vehicle, or be sent to server, by
Server is matched, and after Secondary Match success, determines suspect object.
Step 103, according to temporal information, the state of suspect object is determined.
Wherein, state includes moving condition or stationary state.According to the temporal information of every frame image, determine at suspect object
In motion state or stationary state.When suspect object is stationary state, can directly to server report it is above-mentioned twice
The image information of the information and acquisition matched.
Server can be third-party server, and third-party server can be the server of certain mechanisms, for example manage
The management organization of missing crew.Those information are utilized convenient for third-party server as a result, carry out security protection work.Both peace had been saved
Anti- expense, and expand the range of security protection, even if security protection protection can also be carried out in the region that camera is not laid.
Step 104, when state is moving condition, determine that suspect object is to follow target.
Step 105, the corresponding map datum of the location information of the location information and vehicle that obtain vehicle.
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.
When vehicle is in a certain position, the map of the position can be loaded, it, can should for example, vehicle is in the street A
The upper level unit in the street A, the map in the city A are loaded.As to how load, can be and download from server, be also possible to
Vehicle loads in advance, and the application does not limit this.
Wherein, location information includes longitude and latitude data, transmits information and temporal information.
Step 106, data according to the map, determine follow the mode select information for fixed heel with or at random follow.
Specifically, control unit is automatically analyzed according to the landform in diagram data over the ground, for example it can analyze out and track
The tracking difficulty is matched with the table of difficulty prestored, automatically selects follow the mode by difficulty.For example, diagram data carries out over the ground
Analysis, the position being presently in are Plain, and road is flat, and building is few, and tracking difficulty is 50%, in table of difficulty, the difficulty
Corresponding follow the mode be fixed heel with, then export fixed heel with, it is subsequent, can be followed by the way of using fixed heel.
The position being presently in is that the gradient is big, and bends that there are many road, and building also more street, tracking difficulty is 70%, then passes through
Search table of difficulty, the corresponding follow the mode of the difficulty be follow at random, then output follow at random, it is subsequent, can use at random with
With mode followed.
Step 107, when follow the mode select information for fixed heel at any time, according to multiple image information and map datum, really
Surely multiple location informations of target are followed.
Specifically, can be by handling acquired image information, to obtain the location information for following target.
First every frame image information can be handled, obtain the environmental data in every frame image information；
Environmental data and preset map datum are fitted afterwards, according to fitting result, determination follows the multiple of target
Location information.
It 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.
Step 108, it according to the multiple location informations for following target, generates first and follows path.
Specifically, spliced according to temporal information to multiple location informations, generation follow original first of target with
With path.
Wherein, original first path is followed, it may be possible to any one or its any group of straight line, curve or broken line
It closes, for curve and broken line, after curvature being calculated, curvature is compared with the inverse of vehicle minimum transition radius, when
When curvature is greater than the inverse of vehicle minimum transition radius, be smoothed, show that first follows path, vehicle can according to
It is travelled with path.
Wherein, the minimum transition radius of vehicle is known parameter in vehicle.It can use interpolation method, smoothly located
Reason, details are not described herein again.
Step 109, when to following target to carry out at any time, according to the current location information of vehicle, following the multiple of target
Location information and first follows path, calculates vehicle and follows at a distance from target.
Specifically, can use image information, the multiple location informations for following target are determined, can combine vehicle at this time
Location information and first follow path, determine vehicle and follow at a distance from target.
Step 110, when distance is not more than preset distance threshold, path and the position of vehicle is followed to believe according to first
Breath calculates vehicle and follows the angle information of target.
Step 111, according to the current location information of angle information and vehicle, control signal is generated.
Specifically, then explanation follows when vehicle is with following the distance between target to be less than preset distance threshold
Target can follow in range, at this point it is possible to which the location information for following path according to first, following target, calculates vehicle in real time
With the angle information for following target.The angle information can be using vehicle as origin, to follow target as terminal, origin and terminal
Line and by vehicle center of gravity horizontal angle.
Vehicle in the process of moving, can get the current velocity information of vehicle, can pass through mesh by differential GPS
Obstacle information is marked, carries out decision, and then generate direction information.
In known vehicle and after following the angle information of target, in conjunction with current direction information and velocity information, counted
It calculates, obtains the control signal comprising motor speed and turnning circle.
Step 112, the electric machine controller on the holder for driving acquisition device to rotate is sent control signals to, so that
Electric machine controller and drives the acquisition device on holder to carry out according to the revolving speed of control signal control motor by motor rotation
Rotation.
Specifically, holder can drive acquisition device to rotate, holder driven by the motor, is rotated, to drive acquisition
Device rotation can control the revolving speed and circle number of motor, by electric machine controller according to control signal to realize that motor drives cloud
Platform, holder drive acquisition device to be rotated, and guarantee follows target to be constantly in the capture range of acquisition device.
Wherein, acquisition device can have binocular camera, and holder can be the camera pan-tilt with binocular camera.
Specifically, vehicle follows path along first when motor drives cloud platform rotation to ideal angle, carry out with
With.
It is understood that when vehicle is along following path to advance, in real time according to image information calculate itself with
With the distance between target, and cloud platform rotation is carried out in real time, to guarantee the capture model for following target to be constantly in acquisition device
In enclosing.
Further, when the difference of first angle information and second angle information is greater than the range of deflection of holder, according to
The corresponding first location information of first angle information and the corresponding second location information of second angle information, prediction first position letter
Prediction locus between breath and second location information；First angle information be vehicle with follow in multiple location informations of target the
The angle of one location information, second angle information are the angle of the adjacent position information of vehicle and first location information, the first figure
Picture information and first location information are corresponding, and the second image information is corresponding with the adjacent position information of first location information；
By the other positions information and prediction rail in addition to the adjacent position information of first location information and first location information
Mark is spliced, and obtains following the first of target to follow path.
Specifically, in holder actual rotation, there are dead angle, the i.e. limited problem of cloud platform rotation range, such as holder
Slewing area is 5 ° to 355 °, if the angle information of cloud platform rotation is not in holder range of deflection, target is followed to be in figure
As track when target being followed to be in except image capture range can be predicted by trajectory predictions except capture range.
Wherein, example and it is non-limiting, can use gauss hybrid models predict two positions between track.
Step 113, after rotation, path is followed according to first, is followed.
Specifically, vehicle is followed along path is followed when motor drives cloud platform rotation to ideal angle.
It is understood that when vehicle is along following path to advance, in real time according to image information calculate itself with
With the distance between target, and cloud platform rotation is carried out in real time, to guarantee the capture model for following target to be constantly in acquisition device
In enclosing.
Step 114, when follow the mode selects information at random at any time, according to multiple image information, determination follows target
Multiple location informations.
Step 115, according to multiple image information and map datum, prediction follows the second of target to follow path.
Specifically, vehicle can be analyzed and processed according to the image information of acquisition, the movement for following target is obtained, such as
The amplitude of fluctuation of hand, walking are still run, facial tiny characteristic, such as the deflection direction of sight direction, head, and then basis should
A little movements and facial tiny characteristic, prediction follow the next step of target to act, finally, according to next step movement and map number
According to prediction follows track of the target in certain time length, those tracks may be constructed second and follow path.
Step 116, it according to multiple location informations of target and the location information of vehicle is followed, calculates vehicle and follows target
Time difference.
Specifically, the location information current according to vehicle, the velocity information of vehicle, and the above-mentioned prediction of combination follow target
In the track of certain time length, the time difference between vehicle and prediction locus is calculated, i.e. vehicle reaches each of prediction locus
The estimated duration of point.
Step 117, when time difference is not more than preset time threshold, path is followed according to second, is followed.
Specifically, when vehicle and target is followed to be in regular hour difference range, it can be according to the track of prediction, vehicle
Travelled, and during the track traveling along prediction, and obtain environment sensing data in real time, carry out with
With.
This method can also be applied in other mobile devices, such as robot, which can also carry out sweeper
Make, when applying the method in robot, process is similar with above-mentioned process, and details are not described herein again.
Further, after step 117, further includes:
When distance is not less than preset distance threshold, generate warning message, warning message include it is current before image
Information；
Warning message is sent to server and/or third-party server, so that server and/or third-party server pair
Image information before current is handled.
Specifically, warning message can be generated in vehicle, and will if following target at a distance from vehicle beyond distance threshold
Warning message is sent to server and/or third-party server, when which may include beyond distance threshold, acquisition
Image information, server or third-party server can carry out processing analysis to the image information and location information.
By the identification follower method of application target provided by the invention, in unmanned equipment, filled using its acquisition
The image information for setting acquisition determines suspicion object, and determines that the suspicion object of moving condition is to follow target, follows mesh in locking
Mark, data, generate different follow the mode, and under each follow the mode according to the map, to following target to follow, by
This, is utilized the data of automatic driving vehicle, and has reached security effect, saves security protection investment.
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 (8)
1. a kind of identification follower method of target, which is characterized in that the described method includes:
It obtains within the scope of inspection, the multiple image information in the preset duration of the acquisition device acquisition of vehicle；Every frame described image
Information includes obtaining the temporal information of the image information；
Described image information is handled, determines suspect object；The suspect object includes suspicious object or suspicious event
Implementer；
According to the temporal information, the state of the suspect object is determined；
When the state is moving condition, determine that the suspect object is to follow target；
Obtain the corresponding map datum of location information of the location information and the vehicle of the vehicle；
According to the map datum, determine follow the mode select information for fixed heel with or at random follow；
When the follow the mode select information for fixed heel at any time, according to the multiple image information and the map datum, really
The fixed multiple location informations for following target；
According to the multiple location informations for following target, generates first and follow path；
When following target to carry out at any time to described, according to the current location information of the vehicle, described the multiple of target are followed
Location information and described first follows path, calculates the vehicle and follows at a distance from target with described；
When the distance is not more than preset distance threshold, path and the position of the vehicle is followed to believe according to described first
Breath, calculates the vehicle and the angle information for following target；
According to the current location information of the angle information and the vehicle, control signal is generated；
The control signal is sent to the electric machine controller on the holder for being used to drive the acquisition device rotation, so that described
Electric machine controller is rotated according to the revolving speed for controlling signal control motor, and by the motor to drive on the holder
Acquisition device is rotated；
Path is followed according to described first, is followed；
When the follow the mode selects information at random at any time, according to the multiple image information, following target described in determination
Multiple location informations；
According to the multiple image information and the map datum, the second of target is followed to follow path described in prediction；
According to the location information of the multiple location informations for following target and the vehicle, calculates the vehicle and followed with described
The time difference of target；
When the time difference is not more than preset time threshold, path is followed according to described second, is followed.
2. being determined suspicious the method according to claim 1, wherein described handle described image information
Object specifically includes:
Respectively by described image information feature and suspicious object feature database, suspicion image library match；
When with the suspicious object feature database successful match, determine that suspect object is suspicious object；
When with the suspicion image library successful match, determine that suspect object is the implementer of suspicious event.
3. the method according to claim 1, wherein it is described when rotation after, follow path according to described first, into
Before row follows, the method also includes:
When the difference of first angle information and second angle information is greater than the range of deflection of the holder, according to described first jiao
The corresponding first location information of information and the corresponding second location information of the second angle information are spent, predicts the first position
Prediction locus between information and the second location information；The first angle information is the vehicle and the target that follows
The angle of first location information in multiple location informations, the second angle information are that the vehicle and the first position are believed
The angle of the adjacent position information of breath, the first image information and the first location information are corresponding, the second image letter
It ceases 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 prediction locus to be spliced, obtains described following the first of target to follow path.
4. the method according to claim 1, wherein described according to the multiple image information and the map number
According to following the second of target to follow path described in prediction, specifically include:
Described image information is handled, the movement and/or facial tiny characteristic of target are followed described in determination；
The next step of target is followed to act according to the movement and/or facial tiny characteristic, prediction；
According to next step movement and the map datum, track of the target in preset duration is followed described in prediction.
5. the method according to claim 1, wherein when following path according to described first or second following road
Diameter is carried out at any time, the method also includes:
The real-time image information of target is followed described in acquisition；
By in the real-time image information feature and suspicious object feature database, suspicion characteristics of image library match, generate
With result；
The matching result is analyzed, when at least one in the suspicious object feature database or suspicion characteristics of image library
When kind of successful match, the current location information of the real-time image information, the matching result and the vehicle is sent to the
Tripartite's server.
6. the method according to claim 1, wherein it is described when the follow the mode select information for fixed heel with
When, according to the multiple image information and the map datum, multiple location informations of target are followed described in determination, it is specific to wrap
It includes:
The multiple image information is handled, the environment number in every frame image information in the multiple image information is obtained
According to；
The environmental data and the map datum are fitted, according to fitting result, the position of target is followed described in determination
Information.
7. the method according to claim 1, wherein the method also includes:
When the state is stationary state, described image information, the suspect object are sent to third-party server.
8. the method according to claim 1, wherein it is described when the acquisition device rotation after, according to it is described with
With path, after being followed, further includes:
When the distance is not less than preset distance threshold, warning message is generated, before the warning message includes current
Image information；
The warning message is sent to server and/or third-party server, so that server and/or third-party server pair
It is described it is current before image information handled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572824.0A CN109740462B (en) | 2018-12-21 | 2018-12-21 | Target identification following method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572824.0A CN109740462B (en) | 2018-12-21 | 2018-12-21 | Target identification following method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109740462A true CN109740462A (en) | 2019-05-10 |
| CN109740462B CN109740462B (en) | 2020-10-27 |
Family
ID=66361065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811572824.0A Active CN109740462B (en) | 2018-12-21 | 2018-12-21 | Target identification following method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740462B (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 |
| CN110515095A (en) * | 2019-09-29 | 2019-11-29 | 北京智行者科技有限公司 | Data processing method and system based on multiple laser radars |
| CN111160420A (en) * | 2019-12-13 | 2020-05-15 | 北京三快在线科技有限公司 | Map-based fault diagnosis method and device, electronic equipment and storage medium |
| CN112215209A (en) * | 2020-11-13 | 2021-01-12 | 中国第一汽车股份有限公司 | Car following target determining method and device, car and storage medium |
| CN112319472A (en) * | 2019-08-01 | 2021-02-05 | 本田技研工业株式会社 | Following target recognition system and following target recognition method |
| WO2022082440A1 (en) * | 2020-10-20 | 2022-04-28 | 深圳市大疆创新科技有限公司 | Method, apparatus and system for determining target following strategy, and device and storage medium |
| CN114699046A (en) * | 2022-04-25 | 2022-07-05 | 深圳市华屹医疗科技有限公司 | Sleep monitoring method, monitor and monitoring system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN103389733A (en) * | 2013-08-02 | 2013-11-13 | 重庆市科学技术研究院 | Vehicle line walking method and system based on machine vision |
| CN105023429A (en) * | 2014-04-24 | 2015-11-04 | 上海汽车集团股份有限公司 | Vehicle-used vehicle tracking method and device |
| CN106326240A (en) * | 2015-06-18 | 2017-01-11 | 中兴通讯股份有限公司 | An object moving path identifying method and system |
| CN106529466A (en) * | 2016-11-03 | 2017-03-22 | 中国兵器工业计算机应用技术研究所 | Unmanned vehicle path planning method and unmanned vehicle path planning system based on bionic eye |
| CN107544506A (en) * | 2017-09-27 | 2018-01-05 | 上海有个机器人有限公司 | Robot follower method, robot and storage medium |
| CN108958264A (en) * | 2018-08-03 | 2018-12-07 | 北京智行者科技有限公司 | Road traffic checking method and vehicle based on automatic Pilot technology |
| EP3486131A1 (en) * | 2016-07-13 | 2019-05-22 | Mobile Appliance, Inc. | Vehicle driving assistance device |
-
2018
- 2018-12-21 CN CN201811572824.0A patent/CN109740462B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN103389733A (en) * | 2013-08-02 | 2013-11-13 | 重庆市科学技术研究院 | Vehicle line walking method and system based on machine vision |
| CN105023429A (en) * | 2014-04-24 | 2015-11-04 | 上海汽车集团股份有限公司 | Vehicle-used vehicle tracking method and device |
| CN106326240A (en) * | 2015-06-18 | 2017-01-11 | 中兴通讯股份有限公司 | An object moving path identifying method and system |
| EP3486131A1 (en) * | 2016-07-13 | 2019-05-22 | Mobile Appliance, Inc. | Vehicle driving assistance device |
| CN106529466A (en) * | 2016-11-03 | 2017-03-22 | 中国兵器工业计算机应用技术研究所 | Unmanned vehicle path planning method and unmanned vehicle path planning system based on bionic eye |
| CN107544506A (en) * | 2017-09-27 | 2018-01-05 | 上海有个机器人有限公司 | Robot follower method, robot and storage medium |
| CN108958264A (en) * | 2018-08-03 | 2018-12-07 | 北京智行者科技有限公司 | Road traffic checking method and vehicle based on automatic Pilot technology |
Non-Patent Citations (1)
| Title |
|---|
| 钱堃等: "《基于平滑ND算法的服务机器人运动目标跟随》", 《华中科技大学学报（自然科学版）》 * |
Cited By (9)
| 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 |
| CN112319472A (en) * | 2019-08-01 | 2021-02-05 | 本田技研工业株式会社 | Following target recognition system and following target recognition method |
| CN110515095A (en) * | 2019-09-29 | 2019-11-29 | 北京智行者科技有限公司 | Data processing method and system based on multiple laser radars |
| CN111160420A (en) * | 2019-12-13 | 2020-05-15 | 北京三快在线科技有限公司 | Map-based fault diagnosis method and device, electronic equipment and storage medium |
| CN111160420B (en) * | 2019-12-13 | 2023-10-10 | 北京三快在线科技有限公司 | Map-based fault diagnosis method, map-based fault diagnosis device, electronic equipment and storage medium |
| WO2022082440A1 (en) * | 2020-10-20 | 2022-04-28 | 深圳市大疆创新科技有限公司 | Method, apparatus and system for determining target following strategy, and device and storage medium |
| CN112215209A (en) * | 2020-11-13 | 2021-01-12 | 中国第一汽车股份有限公司 | Car following target determining method and device, car and storage medium |
| CN112215209B (en) * | 2020-11-13 | 2022-06-21 | 中国第一汽车股份有限公司 | Car following target determining method and device, car and storage medium |
| CN114699046A (en) * | 2022-04-25 | 2022-07-05 | 深圳市华屹医疗科技有限公司 | Sleep monitoring method, monitor and monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109740462B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740462A (en) | The identification follower method of target | |
| CN109686031A (en) | Identification follower method based on security protection | |
| US11131990B1 (en) | Method for transferring control to an operator | |
| CN109740461A (en) | Target is with subsequent processing method | |
| US20210035442A1 (en) | Autonomous Vehicles and a Mobility Manager as a Traffic Monitor | |
| US11702070B2 (en) | Autonomous vehicle operation with explicit occlusion reasoning | |
| US11836985B2 (en) | Identifying suspicious entities using autonomous vehicles | |
| CN110371112A (en) | A kind of intelligent barrier avoiding system and method for automatic driving vehicle | |
| CN109682388A (en) | Follow the determination method in path | |
| RU2759975C1 (en) | Operational control of autonomous vehicle with visual salence perception control | |
| CN106503622A (en) | A kind of vehicle antitracking method and device | |
| US11403947B2 (en) | Systems and methods for identifying available parking spaces using connected vehicles | |
| CN109739267A (en) | Follow the determination method in path | |
| JPWO2019237031A5 (en) | ||
| EP4097550A1 (en) | Artificial intelligence methods and systems for remote monitoring and control of autonomous vehicles | |
| CN113324554A (en) | Automatic driving route planning method and device, readable storage medium and electronic equipment | |
| CN114530058A (en) | Collision early warning method, device and system | |
| CN106023338B (en) | A kind of unmanned vehicle vehicle condition detection method and device | |
| CN115140034A (en) | Collision risk detection method, device and equipment | |
| CN109709953A (en) | Vehicle follower method in road cleaning operation | |
| CN109653140A (en) | Vehicle follower method in road cleaning operation | |
| CN108769594A (en) | A kind of data monitoring method | |
| CN109344776B (en) | Data processing method | |
| CN110497906A (en) | Control method for vehicle, device, equipment and medium | |
| US11755008B2 (en) | Using plays for human-AI decision-making in remote autonomous vehicle support |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Patentee after: Beijing Idriverplus 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. |