CN109515315A - Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle - Google Patents
Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle Download PDFInfo
- Publication number
- CN109515315A CN109515315A CN201811072479.4A CN201811072479A CN109515315A CN 109515315 A CN109515315 A CN 109515315A CN 201811072479 A CN201811072479 A CN 201811072479A CN 109515315 A CN109515315 A CN 109515315A
- Authority
- CN
- China
- Prior art keywords
- environment inside
- inside car
- perception data
- passenger
- interior
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/593—Recognising seat occupancy
Abstract
The present invention provides object identification method, system, terminal and storage medium in a kind of automatic driving vehicle, comprising the following steps: S01: capturing interior perception data;S02: according to interior perception data, judging whether interior current environment has exception, when determining environment inside car exception, then determines abnormal attribute;S03: corresponding alarm is made according to abnormal attribute, coordinates passenger, link up passenger or notifies the item of related operators processing.The present invention solves under the scene that automatic driving vehicle does shared trip, timesharing lease, the problems such as environment inside car, the monitoring of interior residue, alarm, the service quality for improving shared trip service provider, enhances the efficiency of operation of shared in-trips vehicles, also improves shared trip user experience.
Description
Technical field
The present invention relates to technical field of automotive electronics, more particularly to object identification method in a kind of automatic driving vehicle,
System, terminal and storage medium.
Background technique
Pilotless automobile is one kind of intelligent automobile, relies primarily on vehicle-mounted sensor-based system perception road environment, automatic to advise
Sliding bicycle route simultaneously controls vehicle arrival intended destination.It perceives vehicle-periphery using onboard sensor, and according to
Road, vehicle location and obstacle information obtained are perceived, the steering and speed of vehicle are controlled, to enable the vehicle to pacify
Entirely, it is reliably travelled on road.
Shared trip is used as a huge market, contains unlimited commercial opportunity, as Internet technology application becomes
Leather gos deep into, and does the visual field that shared trip service also progresses into service provider using automatic driving vehicle.
Summary of the invention
In order to solve above-mentioned and other potential technical problems, the present invention provides objects in a kind of automatic driving vehicle
Body recognition methods, system, terminal and storage medium solve under the scene that automatic driving vehicle does shared trip, timesharing lease,
The problems such as environment inside car, the monitoring of interior residue, alarm, improves the service quality of shared trip service provider, enhances altogether
The efficiency of operation for enjoying in-trips vehicles also improves shared trip user experience.
Object identification method in a kind of automatic driving vehicle, comprising the following steps:
S01: interior perception data is captured;
S02: according to interior perception data, judging whether interior current environment has exception, when determining environment inside car exception,
Abnormal attribute is determined again;
S03: corresponding alarm is made according to abnormal attribute, coordinates passenger, link up passenger or notifies related operators processing
Item.
Further, in the step S01, the interior data of the capture include but is not limited within the scope of operating seat
The perception data of perception data and remaining interior range within the scope of perception data, passenger-seat.
Further, in the step S01, the car perception data includes but is not limited to visual perception data, sound wave
Perception data, millimeter wave perception data, infrared perception data and visual perception data, sound wave perception data, millimeter wave perception
The data that one or more of fusions obtain in data, infrared perception data.
Further, in the step S02, according to interior perception data, judge interior current environment whether Yi Chang tool
Body step:
S021: the several situation of setting environment inside car exception, and mark these environment inside cars abnormal respectively with sequence number
Situation;
S022: each car abnormal case is set into a kind of corresponding abnormal case distinguished number or is set a kind of logical
Crossing deep learning is that mode trains classifier, is input with interior perception data, obtains preliminary judging result;
S023: by preliminary judging result by the way that machine learning/depth is manually checked or passed through to environment inside car abnormal case
The mode of study is checked to environment inside car abnormal case, and underproof environment inside car abnormal case is checked in filtering, is obtained review and is closed
Output of the environment inside car abnormal case of lattice as this step.
Further, described different when determining environment inside car exception, and then determining abnormal attribute again in the step S02
Normal attribute include but is not limited to environment inside car there are residue, that there are passengers is exceeded for environment inside car, environment inside car air quality is poor,
Environment inside car needs to clean, invoice of calling a taxi does not take out, occupant it is dangerous movement one or more of.
Further, in the step S02, when assert environment inside car there are when residue, when invoice of calling a taxi does not take out, vehicle
Short message prompt or telephone prompts are issued to passenger;That there are passengers is exceeded when environment inside car, environment inside car air quality difference when, to
Passenger issues warning note, is selected to stop service of cars on hire or selection alternative scheme by passenger;When environment inside car needs to clean,
System is issued to cleaning service operator corresponding to the vehicle and is requested;When the dangerous movement of occupant, system to this
The police strength resource that vehicle is currently located region sends request.
Further, in the step S021, when environment inside car abnormal case be environment inside car there are when residue, leave
The corresponding abnormal case distinguished number of the identification of object are as follows: take environment inside car and after passenger getting off car time point before carrying passenger's time point
The environment inside car at time point, compares difference between the two, obtains judging result, and sort out abnormal category before next list passenger loading
Property.
Further, in the step S021, when environment inside car abnormal case be environment inside car there are when residue, leave
The deep learning that is identified by of object is the classifier that mode trains identification object, then by next list after passenger getting off car time point
The environment inside car perception data at time point inputs classifier before passenger loading, the object candidate frame of classification where obtaining residue,
Manually met again or machine learning/deep learning mode is checked, obtains judging result, and sort out abnormal attribute.
Further, in the step S021, when environment inside car abnormal case is that environment inside car is exceeded there are passenger, it is
System determines the quantity of passenger in vehicle by the quantity and/or gross combination weight that identify people, when the quantity of vehicle occupant is greater than vehicle core
When determining number, recognition result is compared with rated value, obtains judging result, and sort out abnormal attribute, passenger is exceeded if it exists
When, vehicle itself alarm.
Further, in the step S021, when environment inside car abnormal case is environment inside car air quality difference, system
Incude interior inert gas content and granularity density by inert gas sensor or particle size sensor, will induction result with
Rated value compares, and obtains judging result, and sort out abnormal attribute, when content, density are exceeded if it exists, vehicle itself alarm.
Further, in the step S021, when environment inside car abnormal case is that environment inside car needs to clean, system is logical
It crosses interior perception data or when behavioural analysis determines that environment inside car needs to clean, sorts out abnormal attribute, and will determine that information uploads
To Cloud Server, and it is responsible for dispatching cleaning service operator idle within the scope of the vehicle region by Cloud Server, is being referred to
It fixes time and does cleaning service to the vehicle with designated place.
Further, in the step S021, when environment inside car abnormal case is not taken out for invoice of calling a taxi, system detection
Environment inside car abnormal case occurs on the vehicle after a single passenger getting off car, before next single passenger loading, and system passes through vehicle
Interior perception data perceives the invoice printed, and the information is communicated to upper one single passenger.
Further, in the step S021, when the movement dangerous for occupant of environment inside car abnormal case, it is
Perception data is to measure car with the dynamic variable quantity of each characteristic portion of dynamic object under some time interval in system collecting cart
The standard of personnel hazard's movement, when the dynamic variable quantity overrate of dynamic object characteristic portion, system concludes vehicle occupant
The dangerous movement of member.
It further, all include the step that judging result, abnormal attribute are uploaded to cloud server in above-mentioned steps S021
Suddenly.
Further, in the step S022, each car abnormal case is set into a kind of corresponding abnormal case
The interior perception data of distinguished number processing, when obtaining preliminary judging result, it is local eventually that abnormal case distinguished number is loaded in vehicle
Complete the task in end.
Further, in the step S022, each car abnormal case is set into one kind by deep learning as side
Formula trains classifier and handles interior perception data, when obtaining preliminary judging result, the training deep learning network structure process
Server completes the task beyond the clouds, and trained classifier is downloaded to the vehicle termination.
Further, in the step S023, when the review of environment inside car abnormal case is manual review, manual review's mistake
Server carries out journey beyond the clouds;When environment inside car abnormal case review be machine review when, compound nucleus process beyond the clouds server or
Vehicle termination carries out.
Object identification system in a kind of automatic driving vehicle, including interior perception data trapping module, interior current environment
Abnormal determination module, abnormal attribute determination module;And one of cloud server, scheduler module, alarm and Coordination module
Or it is several;
The car perception data trapping module includes but is not limited to visual sensor, radar sensing for capturing interior
The Various types of data that device, infrared sensor capture;
The perception number that the car current environment abnormal determination module is used to be obtained according to interior perception data trapping module
According to judging whether interior current environment is abnormal;
The abnormal attribute determination module is for after learning interior current environment exception, further determining interior abnormal category
Property, the abnormal attribute includes but is not limited to environment inside car there are residue, that there are passengers is exceeded for environment inside car, environment inside car is empty
Gas is of poor quality, environment inside car needs to clean, invoice of calling a taxi does not take out, occupant it is dangerous movement one or more of;
The cloud server is used for when judging interior current environment exception, the exception information of collecting and reporting;
When the scheduler module needs to dispatch related operators processing for solving interior current environment abnormal attribute, scheduling
The schedulable resource of module analysis operator, and provide rational management strategy;
When the alarm and Coordination module need corresponding alarm, coordinate passenger for current environment abnormal attribute, link up
When passenger, alarm planning issues corresponding alarm command by alarm module, and corresponding warning device is made to alarm;Coordinate, link up passenger
Planning is made a phone call by cloud server coordinates passenger.
Further, the range of the interior perception data trapping module capture perception data includes but is not limited to driver
The perception data of the perception data within the scope of perception data, passenger-seat within the scope of seat and remaining interior range.
Further, the type of the interior perception data trapping module capture data includes but is not limited to visual perception number
According to, sound wave perception data, millimeter wave perception data, infrared perception data and visual perception data, sound wave perception data, millimeter
The data that one or more of fusions obtain in wave perception data, infrared perception data.
Further, when abnormal attribute determination module assert environment inside car there are when residue, when invoice of calling a taxi does not take out,
Vehicle issues short message prompt or telephone prompts to passenger;That there are passengers is exceeded when environment inside car, environment inside car air quality difference when,
Warning note is issued to passenger, is selected to stop service of cars on hire or selection alternative scheme by passenger;When environment inside car needs to clean
When, system is issued to cleaning service operator corresponding to the vehicle and is requested;When the dangerous movement of occupant, system to
The police strength resource that the vehicle is currently located region sends request.
Further, when abnormal attribute determination module determines environment inside car, there are when residue, take carrying passenger's time point
Preceding environment inside car and after passenger getting off car time point it is next list passenger loading before time point environment inside car, compare difference between the two
Not, it obtains judging result, and sorts out abnormal attribute.
Further, when abnormal attribute determination module determines environment inside car abnormal case, for environment inside car, there are residues
When, the deep learning that is identified by of residue is the classifier that mode trains identification object, then by passenger getting off car time point
The environment inside car perception data at time point inputs classifier before next single passenger loading afterwards, the object of classification where obtaining residue
Candidate frame, then manually met or machine learning/deep learning mode is checked, obtain judging result, and sort out abnormal category
Property.
Further, when abnormal attribute determination module determines that environment inside car is exceeded there are passenger, system passes through identification people
Quantity and/or gross combination weight determine the quantity of passenger in vehicle, when the quantity of vehicle occupant, which is greater than vehicle, appraises and decides number, will know
Other result obtains judging result compared with rated value, and sorts out abnormal attribute, when passenger is exceeded if it exists, vehicle itself report
It is alert.
Further, when abnormal attribute determination module determines that environment inside car abnormal case is poor for environment inside car air quality
When, system incudes interior inert gas content and granularity density by inert gas sensor or particle size sensor, will feel
It answers result compared with rated value, obtains judging result, and sort out abnormal attribute, when content, density are exceeded if it exists, vehicle itself
Alarm.
Further, when abnormal attribute determination module determines that environment inside car abnormal case needs to clean for environment inside car,
When system determines that environment inside car needs to clean by interior perception data or behavioural analysis, sort out abnormal attribute, and will determine to believe
Breath is uploaded to Cloud Server, and is responsible for dispatching cleaning service operation idle within the scope of the vehicle region by Cloud Server
Quotient at the appointed time does cleaning service to the vehicle with designated place.
Object identification terminal in a kind of automatic driving vehicle, which is characterized in that including processor and memory, the storage
Device is stored with program instruction, and the processor operation program instruction realizes the step in above-mentioned method.
A kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is by processor
The step in above-mentioned method is realized when execution.
As described above, of the invention has the advantages that
It solves under the scene that automatic driving vehicle does shared trip, timesharing lease, the prison of environment inside car, interior residue
The problems such as control, alarm, improves the service quality of shared trip service provider, enhances the efficiency of operation of shared in-trips vehicles,
Improve shared trip user experience.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is shown as flow chart of the invention.
Fig. 2 is shown as the schematic diagram that the present invention captures interior data.
Fig. 3 is shown as capturing the schematic diagram of interior data in another embodiment of the present invention.
Fig. 4 be shown as the present invention judge car current environment whether Yi Chang flow chart.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be clear that this specification structure depicted in this specification institute accompanying drawings, ratio, size etc., only to cooperate specification to be taken off
The content shown is not intended to limit the invention enforceable qualifications so that those skilled in the art understands and reads, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the present invention
Under the effect of can be generated and the purpose that can reach, it should all still fall in disclosed technology contents and obtain the model that can cover
In enclosing.Meanwhile cited such as "upper" in this specification, "lower", "left", "right", " centre " and " one " term, be also only
Convenient for being illustrated for narration, rather than to limit the scope of the invention, relativeness is altered or modified, in no essence
It changes under technology contents, when being also considered as the enforceable scope of the present invention.
Referring to figs. 1 to 4,
Object identification method in a kind of automatic driving vehicle, comprising the following steps:
S01: interior perception data is captured;
S02: according to interior perception data, judging whether interior current environment has exception, when determining environment inside car exception,
Abnormal attribute is determined again;
S03: corresponding alarm is made according to abnormal attribute, coordinates passenger, link up passenger or notifies related operators processing
Item.
As a preferred embodiment, further, in the step S01, the interior data of the capture include but is not limited to drive
The perception data of the perception data within the scope of perception data, passenger-seat within the scope of the person of sailing seat and remaining interior range.
As a preferred embodiment, in the step S01, the car perception data includes but is not limited to visual perception number
According to, sound wave perception data, millimeter wave perception data, infrared perception data and visual perception data, sound wave perception data, millimeter
The data that one or more of fusions obtain in wave perception data, infrared perception data.
As a preferred embodiment, in the step S02, according to interior perception data, judge whether interior current environment is different
Normal specific steps:
S021: the several situation of setting environment inside car exception, and mark these environment inside cars abnormal respectively with sequence number
Situation;
S022: each car abnormal case is set into a kind of corresponding abnormal case distinguished number or is set a kind of logical
Crossing deep learning is that mode trains classifier, is input with interior perception data, obtains preliminary judging result;
S023: by preliminary judging result by the way that machine learning/depth is manually checked or passed through to environment inside car abnormal case
The mode of study is checked to environment inside car abnormal case, and underproof environment inside car abnormal case is checked in filtering, is obtained review and is closed
Output of the environment inside car abnormal case of lattice as this step.
As a preferred embodiment, in the step S02, when determining environment inside car exception, and then determining abnormal attribute again,
The abnormal attribute includes but is not limited to environment inside car, and there are residues, environment inside car there are passengers exceeded, environment inside car air
Of poor quality, environment inside car needs to clean, invoice of calling a taxi does not take out, occupant it is dangerous movement one or more of.
As a preferred embodiment, in the step S02, when assert environment inside car there are when residue, invoice of calling a taxi do not take
When out, vehicle issues short message prompt or telephone prompts to passenger;When environment inside car there are passengers exceeded, environment inside car air quality
When poor, warning note is issued to passenger, is selected to stop service of cars on hire or selection alternative scheme by passenger;When environment inside car needs
When cleaning, system is issued to cleaning service operator corresponding to the vehicle and is requested;When the dangerous movement of occupant, it is
It unites and sends request to the police strength resource that the vehicle is currently located region.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that there are residues for environment inside car
When, the corresponding abnormal case distinguished number of the identification of residue are as follows: take environment inside car and passenger getting off car before carrying passenger's time point
After time point it is next list passenger loading before time point environment inside car, compare difference between the two, obtain judging result, and return
Class abnormal attribute.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that there are residues for environment inside car
When, the deep learning that is identified by of residue is the classifier that mode trains identification object, then by passenger getting off car time point
The environment inside car perception data at time point inputs classifier before next single passenger loading afterwards, the object of classification where obtaining residue
Candidate frame, then manually met or machine learning/deep learning mode is checked, obtain judging result, and sort out abnormal category
Property.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that there are passengers to surpass for environment inside car
When mark, system determines the quantity of passenger in vehicle by the quantity and/or gross combination weight that identify people, when the quantity of vehicle occupant is greater than
When vehicle appraises and decides number, recognition result is compared with rated value, judging result is obtained, and sort out abnormal attribute, multiplies if it exists
When visitor is exceeded, vehicle itself alarm.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that environment inside car air quality is poor
When, system incudes interior inert gas content and granularity density by inert gas sensor or particle size sensor, will feel
It answers result compared with rated value, obtains judging result, and sort out abnormal attribute, when content, density are exceeded if it exists, vehicle itself
Alarm.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that environment inside car needs to clean,
When system determines that environment inside car needs to clean by interior perception data or behavioural analysis, sort out abnormal attribute, and will determine to believe
Breath is uploaded to Cloud Server, and is responsible for dispatching cleaning service operation idle within the scope of the vehicle region by Cloud Server
Quotient at the appointed time does cleaning service to the vehicle with designated place.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is not taken out for invoice of calling a taxi, it is
System detection environment inside car abnormal case occurs on the vehicle after a single passenger getting off car, before next single passenger loading, system
The invoice printed is perceived by interior perception data, and the information is communicated to upper one single passenger.
As a preferred embodiment, in the step S021, when environment inside car abnormal case is that occupant is dangerous dynamic
When making, perception data is weighing apparatus with the dynamic variable quantity of each characteristic portion of dynamic object under some time interval in system collecting cart
The standard of occupant's dangerous play is measured, when the dynamic variable quantity overrate of dynamic object characteristic portion, system is concluded
The dangerous movement of occupant.
It as a preferred embodiment, all include that judging result, abnormal attribute are uploaded to cloud service in above-mentioned steps S021
The step of device.
As a preferred embodiment, in the step S022, each car abnormal case is set a kind of corresponding different
The interior perception data of reason shape distinguished number processing, when obtaining preliminary judging result, abnormal case distinguished number is loaded in vehicle
Complete the task in local terminal.
As a preferred embodiment, in the step S022, each car abnormal case is set into one kind by depth
Practise is that mode trains the interior perception data of classifier processing, when obtaining preliminary judging result, the training deep learning network knot
Server completes the task to structure process beyond the clouds, and trained classifier is downloaded to the vehicle termination.
As a preferred embodiment, in the step S023, when the review of environment inside car abnormal case is manual review, manually
Server carries out compound nucleus process beyond the clouds;When the review of environment inside car abnormal case is machine review, compound nucleus process takes beyond the clouds
Business device or vehicle termination carry out.
Object identification system in a kind of automatic driving vehicle, including interior perception data trapping module, interior current environment
Abnormal determination module, abnormal attribute determination module;And one of cloud server, scheduler module, alarm and Coordination module
Or it is several;
The car perception data trapping module includes but is not limited to visual sensor, radar sensing for capturing interior
The Various types of data that device, infrared sensor capture;
The perception number that the car current environment abnormal determination module is used to be obtained according to interior perception data trapping module
According to judging whether interior current environment is abnormal;
The abnormal attribute determination module is for after learning interior current environment exception, further determining interior abnormal category
Property, the abnormal attribute includes but is not limited to environment inside car there are residue, that there are passengers is exceeded for environment inside car, environment inside car is empty
Gas is of poor quality, environment inside car needs to clean, invoice of calling a taxi does not take out, occupant it is dangerous movement one or more of;
The cloud server is used for when judging interior current environment exception, the exception information of collecting and reporting;
When the scheduler module needs to dispatch related operators processing for solving interior current environment abnormal attribute, scheduling
The schedulable resource of module analysis operator, and provide rational management strategy;
When the alarm and Coordination module need corresponding alarm, coordinate passenger for current environment abnormal attribute, link up
When passenger, alarm planning issues corresponding alarm command by alarm module, and corresponding warning device is made to alarm;Coordinate, link up passenger
Planning is made a phone call by cloud server coordinates passenger.
As a preferred embodiment, the range of the interior perception data trapping module capture perception data includes but is not limited to
The perception data of the perception data within the scope of perception data, passenger-seat within the scope of operating seat and remaining interior range.
As a preferred embodiment, the type of the interior perception data trapping module capture data includes but is not limited to vision
Perception data, sound wave perception data, millimeter wave perception data, infrared perception data and visual perception data, sound wave perceive number
According to, data that one or more of fusions obtain in millimeter wave perception data, infrared perception data.
As a preferred embodiment, when abnormal attribute determination module assert environment inside car there are when residue, call a taxi invoice not
When taking-up, vehicle issues short message prompt or telephone prompts to passenger;When environment inside car there are passengers exceeded, environment inside car air matter
When amount difference, warning note is issued to passenger, is selected to stop service of cars on hire or selection alternative scheme by passenger;When environment inside car needs
When cleaning, system is issued to cleaning service operator corresponding to the vehicle and is requested;When the dangerous movement of occupant,
System sends request to the police strength resource that the vehicle is currently located region.
As a preferred embodiment, when abnormal attribute determination module determines environment inside car, there are when residue, take carrying passenger
Before time point environment inside car and after passenger getting off car time point it is next list passenger loading before time point environment inside car, compare the two
Between difference, obtain judging result, and sort out abnormal attribute.
As a preferred embodiment, it is lost when abnormal attribute determination module determines that environment inside car abnormal case exists for environment inside car
When staying object, the deep learning that is identified by of residue is the classifier that mode trains identification object, then when by passenger getting off car
Between put after before next single passenger loading the environment inside car perception data at time point input classifier, classification where obtaining residue
Object candidate frame, then manually met or machine learning/deep learning mode is checked, obtain judging result, and sort out different
Normal attribute.
As a preferred embodiment, when abnormal attribute determination module determines that environment inside car is exceeded there are passenger, system passes through
The quantity and/or gross combination weight of identification people determine the quantity of passenger in vehicle, appraise and decide number when the quantity of vehicle occupant is greater than vehicle
When, recognition result is compared with rated value, obtains judging result, and sort out abnormal attribute, when passenger is exceeded if it exists, vehicle
Itself alarm.
As a preferred embodiment, when abnormal attribute determination module determines that environment inside car abnormal case is environment inside car air matter
When amount difference, system incudes interior inert gas content and granularity density by inert gas sensor or particle size sensor,
Induction result is obtained into judging result compared with rated value, and sorts out abnormal attribute, when content, density are exceeded if it exists, vehicle
Itself alarm.
As a preferred embodiment, when abnormal attribute determination module determines that environment inside car abnormal case needs clearly for environment inside car
When clean, when system determines that environment inside car needs to clean by interior perception data or behavioural analysis, sort out abnormal attribute, and will sentence
Determine information and be uploaded to Cloud Server, and is responsible for dispatching cleaning service idle within the scope of the vehicle region by Cloud Server and transports
Quotient is sought, at the appointed time does cleaning service to the vehicle with designated place.
Object identification terminal in a kind of automatic driving vehicle, which is characterized in that including processor and memory, the storage
Device is stored with program instruction, and the processor operation program instruction realizes the step in above-mentioned method.
As a preferred embodiment, the present embodiment also provides a kind of terminal device, can such as execute the smart phone of program, put down
Plate computer, laptop, desktop computer, rack-mount server, blade server, tower server or cabinet-type service
Device (including server cluster composed by independent server or multiple servers) etc..The terminal device of the present embodiment is extremely
It is few to include but is not limited to: memory, the processor of connection can be in communication with each other by system bus.It should be pointed out that having group
The terminal device of part memory, processor can substitute it should be understood that being not required for implementing all components shown
Implementation is more or less component.
As a preferred embodiment, memory (i.e. readable storage medium storing program for executing) includes flash memory, hard disk, multimedia card, card-type storage
Device (for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only storage
Device (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD etc..In some embodiments, memory can be the internal storage unit of computer equipment, such as the computer is set
Standby 20 hard disk or memory.In further embodiments, memory is also possible to the External memory equipment of computer equipment, such as
The plug-in type hard disk being equipped in the computer equipment, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card) etc..Certainly, memory can also both include computer equipment
Internal storage unit also include its External memory equipment.In the present embodiment, memory is installed on computer commonly used in storage
Object identification program code etc. in the operating system and types of applications software of equipment, such as automatic driving vehicle in embodiment.
In addition, memory can be also used for temporarily storing the Various types of data that has exported or will export.
Processor can be central processing unit (Central Processing Unit, CPU), control in some embodiments
Device, microcontroller, microprocessor or other data processing chips processed.The processor is total commonly used in control computer equipment
Gymnastics is made.In the present embodiment, program code or processing data of the processor for being stored in run memory, such as operation nothing
People drives object identification program in vehicle, to realize the function of object identification system in automatic driving vehicle in embodiment.
A kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is by processor
The step in above-mentioned method is realized when execution.
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.
Answer function.The computer readable storage medium of the present embodiment is processed for storing object identification program in automatic driving vehicle
Object identification method in the automatic driving vehicle in embodiment is realized when device executes.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, includes that institute is complete without departing from the spirit and technical ideas disclosed in the present invention for usual skill in technical field such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (15)
1. object identification method in a kind of automatic driving vehicle, which comprises the following steps:
S01: interior perception data is captured;
S02: according to interior perception data, judging whether interior current environment has exception, when determining environment inside car exception, then sentences
Determine abnormal attribute;
S03: corresponding alarm is made according to abnormal attribute, coordinates passenger, link up passenger or notifies the thing of related operators processing
?.
2. object identification method in automatic driving vehicle according to claim 1, which is characterized in that in the step S01,
The interior data of the capture include but is not limited to the perception data within the scope of operating seat, the perception number within the scope of passenger-seat
According to the perception data with remaining interior range.
3. object identification method in automatic driving vehicle according to claim 2, which is characterized in that in the step S01,
The car perception data includes but is not limited to visual perception data, sound wave perception data, millimeter wave perception data, infrared perception
Data and visual perception data, sound wave perception data, millimeter wave perception data, one or more of fusions in infrared perception data
Obtained data.
4. object identification method in automatic driving vehicle according to claim 3, which is characterized in that in the step S02,
According to interior perception data, judge interior current environment whether Yi Chang specific steps:
S021: the several situation of setting environment inside car exception, and mark these environment inside car abnormal cases respectively with sequence number;
S022: each car abnormal case is set a kind of corresponding abnormal case distinguished number or sets one kind pass through depth
Degree study is that mode trains classifier, is input with interior perception data, obtains preliminary judging result;
S023: by preliminary judging result by the way that machine learning/deep learning is manually checked or passed through to environment inside car abnormal case
Mode give the review of environment inside car abnormal case, filtering checks underproof environment inside car abnormal case, and it is qualified to obtain review
Output of the environment inside car abnormal case as this step.
5. object identification method in automatic driving vehicle according to claim 4, which is characterized in that in the step S02,
When determining environment inside car exception, and then determining abnormal attribute again, the abnormal attribute includes but is not limited to that environment inside car exists
That there are passengers is exceeded for residue, environment inside car, environment inside car air quality is poor, environment inside car needs to clean, invoice of calling a taxi does not take
Out, one or more of dangerous movement of occupant.
6. object identification method in automatic driving vehicle according to claim 5, which is characterized in that in the step S02,
When assert environment inside car there are when residue, when invoice of calling a taxi does not take out, vehicle issues short message prompt or telephone prompts to passenger;
That there are passengers is exceeded when environment inside car, environment inside car air quality difference when, issue warning note to passenger, select to stop by passenger
Service of cars on hire or selection alternative scheme;When environment inside car needs to clean, system is transported to cleaning service corresponding to the vehicle
It seeks quotient and issues request;When the dangerous movement of occupant, system is sent to the police strength resource that the vehicle is currently located region
Request;In the step S02, when assert environment inside car there are when residue, when invoice of calling a taxi does not take out, vehicle is issued to passenger
Short message prompt or telephone prompts;That there are passengers is exceeded when environment inside car, environment inside car air quality difference when, issue and alarm to passenger
Prompt is selected to stop service of cars on hire or selection alternative scheme by passenger;When environment inside car needs to clean, system is to the vehicle
Corresponding cleaning service operator issues request;When the dangerous movement of occupant, system is currently located to the vehicle
The police strength resource in region sends request.
7. object identification method in automatic driving vehicle according to claim 4, which is characterized in that
In the step S021, when environment inside car abnormal case is environment inside car there are when residue, the identification of residue is corresponding
Abnormal case distinguished number are as follows: take carrying passenger's time point before environment inside car and after passenger getting off car time point it is next list passenger on
The environment inside car at Chinese herbaceous peony time point compares difference between the two, obtains judging result, and sort out abnormal attribute;The step
In S021, when environment inside car abnormal case is environment inside car there are when residue, the deep learning that is identified by of residue is
Mode train identification object classifier, then by after passenger getting off car time point it is next list passenger loading before time point interior ring
Border perception data inputs classifier, the object candidate frame of classification where obtaining residue, then manually met or machine learning/
The mode of deep learning is checked, and obtains judging result, and sort out abnormal attribute;
In the step S021, when environment inside car abnormal case is that environment inside car is exceeded there are passenger, system passes through identification people
Quantity and/or gross combination weight determine the quantity of passenger in vehicle, when the quantity of vehicle occupant, which is greater than vehicle, appraises and decides number, will know
Other result obtains judging result compared with rated value, and sorts out abnormal attribute, when passenger is exceeded if it exists, vehicle itself report
It is alert;In the step S021, when environment inside car abnormal case is environment inside car air quality difference, system is passed by inert gas
Sensor or particle size sensor incude interior inert gas content and granularity density, by induction result compared with rated value, obtain
Judging result out, and sort out abnormal attribute, when content, density are exceeded if it exists, vehicle itself alarm;
In the step S021, when environment inside car abnormal case is that environment inside car needs to clean, system perceives number by interior
According to or behavioural analysis determine environment inside car need to clean when, sort out abnormal attribute, and by determine information be uploaded to Cloud Server, and
It is responsible for dispatching cleaning service operator idle within the scope of the vehicle region by Cloud Server, at the appointed time and specifiedly
Point does cleaning service to the vehicle;
In the step S021, when environment inside car abnormal case is not taken out for invoice of calling a taxi, system detection environment inside car is abnormal
Situation occurs on the vehicle after a single passenger getting off car, before next single passenger loading, and system passes through interior perception data sense
Know the invoice printed, and the information is communicated to upper one single passenger;
In the step S021, when the movement dangerous for occupant of environment inside car abnormal case, system collecting cart inner sense
Primary data is to measure occupant's dangerous play with the dynamic variable quantity of each characteristic portion of dynamic object under some time interval
Standard, when the dynamic variable quantity overrate of dynamic object characteristic portion, system concludes that occupant is dangerous dynamic
Make.
8. object identification method in automatic driving vehicle according to claim 7, which is characterized in that above-mentioned steps S021
In, all include the steps that judging result, abnormal attribute being uploaded to cloud server.
9. object identification method in automatic driving vehicle according to claim 4, which is characterized in that the step S022
In, each car abnormal case is set into a kind of corresponding interior perception data of abnormal case distinguished number processing, is obtained
When preliminary judging result, abnormal case distinguished number is loaded in vehicle local terminal and completes the task;It, will in the step S022
Each interior abnormal case sets one kind and trains the interior perception data of classifier processing as mode by deep learning, obtains
When preliminary judging result, training the deep learning network structure process, server completes the task beyond the clouds, by trained point
Class device is downloaded to the vehicle termination.
10. object identification method in automatic driving vehicle according to claim 4, which is characterized in that the step S023
In, when the review of environment inside car abnormal case is manual review, server carries out manual review's process beyond the clouds;Work as environment inside car
When abnormal case review is machine review, server or vehicle termination carry out compound nucleus process beyond the clouds.
11. object identification system in a kind of automatic driving vehicle, which is characterized in that including interior perception data trapping module, vehicle
Interior current environment abnormal determination module, abnormal attribute determination module;And cloud server, scheduler module, alarm and coordination mould
One or more of block;
The car perception data trapping module for capture it is interior include but is not limited to visual sensor, it is radar sensor, red
The Various types of data of outer sensor capture;
The perception data that the car current environment abnormal determination module is used to be obtained according to interior perception data trapping module, sentences
Whether disconnected car current environment is abnormal;
The abnormal attribute determination module is for further determining interior abnormal attribute, institute after learning interior current environment exception
Abnormal attribute is stated to include but is not limited to environment inside car there are residues, environment inside car there are passengers exceeded, environment inside car air matter
Measure it is poor, environment inside car needs to clean, invoice of calling a taxi does not take out, occupant it is dangerous act one or more of;
The cloud server is used for when judging interior current environment exception, the exception information of collecting and reporting;
When the scheduler module needs to dispatch related operators processing for solving interior current environment abnormal attribute, scheduler module
The schedulable resource of operator is analyzed, and provides rational management strategy;
When the alarm and Coordination module need corresponding alarm, coordinate passenger for current environment abnormal attribute, link up passenger
When, alarm planning issues corresponding alarm command by alarm module, and corresponding warning device is made to alarm;Coordinate, link up passenger's planning
It is made a phone call by cloud server and coordinates passenger.
12. object identification system in automatic driving vehicle according to claim 11, which is characterized in that the interior perception
The range of data capture module capture perception data includes but is not limited to perception data, passenger-seat within the scope of operating seat
The perception data of perception data and remaining interior range in range.
13. object identification system in automatic driving vehicle according to claim 11, which is characterized in that the interior perception
The type of data capture module capture data includes but is not limited to visual perception data, sound wave perception data, millimeter wave perception number
According in, infrared perception data and visual perception data, sound wave perception data, millimeter wave perception data, infrared perception data one
The data that kind or several fusions obtain.
14. object identification terminal in a kind of automatic driving vehicle, which is characterized in that including processor and memory, the storage
Device is stored with program instruction, and the processor operation program instruction is realized as described in claims 1 to 10 any claim
Step in method.
15. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is by processor
The step in the method as described in claims 1 to 10 any claim is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811072479.4A CN109515315A (en) | 2018-09-14 | 2018-09-14 | Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811072479.4A CN109515315A (en) | 2018-09-14 | 2018-09-14 | Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109515315A true CN109515315A (en) | 2019-03-26 |
Family
ID=65770917
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811072479.4A Pending CN109515315A (en) | 2018-09-14 | 2018-09-14 | Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109515315A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110704A (en) * | 2019-05-21 | 2019-08-09 | 北京首汽智行科技有限公司 | A kind of vehicle sanitation monitoring method and system |
CN113313087A (en) * | 2021-07-28 | 2021-08-27 | 江西科技学院 | Passenger behavior supervision method and device for unmanned automobile |
CN114025040A (en) * | 2021-11-06 | 2022-02-08 | 安徽中科美络信息技术有限公司 | Method and system for intercepting incoming call of driver |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937609A (en) * | 2010-09-20 | 2011-01-05 | 奇瑞汽车股份有限公司 | Method and device for reminding passengers of losing goods |
KR20150046979A (en) * | 2013-10-23 | 2015-05-04 | (주) 비앤디 | Apparatus and method for notifying danger in vehicle |
CN105974912A (en) * | 2016-04-28 | 2016-09-28 | 百度在线网络技术(北京)有限公司 | Alarm method of unmanned vehicle and apparatus thereof |
CN106560836A (en) * | 2015-10-02 | 2017-04-12 | Lg电子株式会社 | Apparatus, Method And Mobile Terminal For Providing Object Loss Prevention Service In Vehicle |
CN107358484A (en) * | 2017-05-27 | 2017-11-17 | 上海与德科技有限公司 | A kind of net about car monitoring method and system |
CN107357194A (en) * | 2016-05-10 | 2017-11-17 | 通用汽车环球科技运作有限责任公司 | Heat monitoring in autonomous land vehicle |
CN108340882A (en) * | 2016-01-26 | 2018-07-31 | 通用汽车环球科技运作有限责任公司 | Clean system and method for promoting delivery vehicle |
CN108449571A (en) * | 2018-01-30 | 2018-08-24 | 深圳市元征软件开发有限公司 | A kind of car monitoring method and equipment |
-
2018
- 2018-09-14 CN CN201811072479.4A patent/CN109515315A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937609A (en) * | 2010-09-20 | 2011-01-05 | 奇瑞汽车股份有限公司 | Method and device for reminding passengers of losing goods |
KR20150046979A (en) * | 2013-10-23 | 2015-05-04 | (주) 비앤디 | Apparatus and method for notifying danger in vehicle |
CN106560836A (en) * | 2015-10-02 | 2017-04-12 | Lg电子株式会社 | Apparatus, Method And Mobile Terminal For Providing Object Loss Prevention Service In Vehicle |
CN108340882A (en) * | 2016-01-26 | 2018-07-31 | 通用汽车环球科技运作有限责任公司 | Clean system and method for promoting delivery vehicle |
CN105974912A (en) * | 2016-04-28 | 2016-09-28 | 百度在线网络技术(北京)有限公司 | Alarm method of unmanned vehicle and apparatus thereof |
CN107357194A (en) * | 2016-05-10 | 2017-11-17 | 通用汽车环球科技运作有限责任公司 | Heat monitoring in autonomous land vehicle |
CN107358484A (en) * | 2017-05-27 | 2017-11-17 | 上海与德科技有限公司 | A kind of net about car monitoring method and system |
CN108449571A (en) * | 2018-01-30 | 2018-08-24 | 深圳市元征软件开发有限公司 | A kind of car monitoring method and equipment |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110704A (en) * | 2019-05-21 | 2019-08-09 | 北京首汽智行科技有限公司 | A kind of vehicle sanitation monitoring method and system |
CN113313087A (en) * | 2021-07-28 | 2021-08-27 | 江西科技学院 | Passenger behavior supervision method and device for unmanned automobile |
CN114025040A (en) * | 2021-11-06 | 2022-02-08 | 安徽中科美络信息技术有限公司 | Method and system for intercepting incoming call of driver |
CN114025040B (en) * | 2021-11-06 | 2023-06-20 | 中科美络科技股份有限公司 | Method and system for intercepting incoming call of driver |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021135653A1 (en) | Method and system for identifying abnormal stay of vehicle | |
CN111319629B (en) | Team forming method, device and system for automatically driving fleet | |
CN110235152A (en) | Vehicle service system | |
CN109515315A (en) | Object identification method, system, terminal and storage medium in a kind of automatic driving vehicle | |
CN105930771A (en) | Driving behavior grading method and device | |
CN106643747B (en) | Navigation method and device | |
CN109358614A (en) | Automatic Pilot method, system, device and readable storage medium storing program for executing | |
CN109508580A (en) | Traffic lights recognition methods and device | |
CN108475406A (en) | Software application for asking and controlling autonomous vehicle service | |
CN105894669A (en) | Method, device and system for automatically oiling unmanned vehicle | |
CN106652515A (en) | Vehicle automatic control method, vehicle automatic control device, and vehicle automatic control system | |
CN103871200A (en) | Safety warning system and method used for automobile driving | |
US20180334176A1 (en) | Method and system for providing driving guidance | |
CN108932832A (en) | Vehicle dispatching method, device and system | |
US20200160708A1 (en) | Method and apparatus for adaptively managing a vehicle | |
CN108765244A (en) | Vehicle monitoring method, device and computer readable storage medium | |
CN109754595A (en) | Appraisal procedure, device and the interface equipment of vehicle risk | |
CN109858470A (en) | Method and apparatus for output information | |
CN108268653A (en) | A kind of traffic data processing method and device | |
US11727694B2 (en) | System and method for automatic assessment of comparative negligence for one or more vehicles involved in an accident | |
CN105844903A (en) | Vehicle positioning method and device | |
CN110853184A (en) | Analysis processing method, device, equipment and storage medium for vehicle-mounted computing information | |
CN113593256B (en) | Unmanned aerial vehicle intelligent driving-away control method and system based on city management and cloud platform | |
CN114677848B (en) | Perception early warning system, method, device and computer program product | |
CN113052397B (en) | Method and device for determining boarding information, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |
|
RJ01 | Rejection of invention patent application after publication |