CN107757472A - Door opening alarm method, driving door alarm device and Vehicular system - Google Patents
Door opening alarm method, driving door alarm device and Vehicular system Download PDFInfo
- Publication number
- CN107757472A CN107757472A CN201710944161.XA CN201710944161A CN107757472A CN 107757472 A CN107757472 A CN 107757472A CN 201710944161 A CN201710944161 A CN 201710944161A CN 107757472 A CN107757472 A CN 107757472A
- Authority
- CN
- China
- Prior art keywords
- alarm
- target
- alarm target
- door
- type
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/8033—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for pedestrian protection
Abstract
The invention discloses a kind of door opening alarm method.Door opening alarm method includes processing environment image to determine the candidate region that alarm target be present；Establish the identification model of driving door alarm and the type for identifying alarm target from candidate region；Whether the type for judging alarm target is predefined type；Alarm target is tracked when alarm target is predefined type and calculates the distance of alarm target and the car door of vehicle and the speed of the relative car door of alarm target；Whether alert if is reached according to distance and velocity estimated；With control warning device to alarm when reaching alert and if prompt the type of alarm target.In addition, the invention also discloses a kind of driving door alarm device and Vehicular system.The door opening alarm method and device of embodiment of the present invention may recognize that the type of alarm target and accurately obtain position and the speed of alarm target, the type of user's alarm target is informed by warning device in alarm, alarm strategy is optimized, improves Consumer's Experience.
Description
Technical field
The present invention relates to automotive field, more particularly to a kind of door opening alarm method, driving door alarm device and vehicle system
System.
Background technology
If car door opening is improper, tricycle, electric car, the bicycle at car door rear may be bumped against on car door, may
Cause a traffic accident.Therefore it is typically provided with driving door alarm device on vehicle.Driving door alarm device in correlation technique uses thunder
Up to the moving object at detection vehicle side rear, yet with the distance and speed that can only detect moving object, easy false triggering
Alarm, poor user experience.
The content of the invention
Embodiments of the present invention provide a kind of door opening alarm method, driving door alarm device and Vehicular system.
The door opening alarm method of embodiment of the present invention is applied to Vehicular system, and the Vehicular system includes vehicle, figure
As harvester and warning device, described image harvester is used for the ambient image for gathering the vehicle periphery, the driving
Door alarm method comprises the following steps：
The ambient image is handled to determine the candidate region that alarm target be present；
Establish the identification model of driving door alarm and the class for identifying the alarm target from the candidate region
Type；
Whether the type for judging the alarm target is predefined type；
In the alarm target to track the alarm target during predefined type and calculate the alarm target and institute
State the distance of the car door of vehicle and the speed of the relatively described car door of the alarm target.
Whether alert if is reached according to the distance and the velocity estimated；With
Control the warning device to alarm when reaching the alert and if prompt the type of the alarm target.
The door opening alarm method of embodiment of the present invention may recognize that the type for the alarm target for appearing in candidate region
And accurately obtain position and the speed of alarm target.Door opening alarm method informs that user reports in alarm by warning device
The type of alert target pays attention to taking precautions against to remind during user's door opening, optimizes alarm strategy, improves Consumer's Experience.
In some embodiments, the processing ambient image is with the step for the candidate region for determining to have alarm target
Suddenly background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms are used.
In this way, by background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms to every
One frame ambient image carries out processing and provides the candidate region that alarm target be present.
In some embodiments, the identification model for establishing driving door alarm and for knowing from the candidate region
The step of not going out the type of the alarm target uses deep neural network algorithm.
In this way, the identification model of driving door alarm is established by deep neural network algorithm to identify the class of alarm target
Type.
In some embodiments, it is described to track the alarm target simultaneously when the alarm target is the predefined type
Calculate the alarm target and the car door of the vehicle distance and the relative car door of the alarm target speed the step of
Using Kalman filtering algorithm.
In this way, itself and the distance of car door and the speed of relative car door are calculated alarm target by Kalman filtering algorithm,
So as to judge whether to alarm.
In some embodiments, the predefined type includes " electric car ", " bicycle " or " tricycle ".
In this way, these three alarm targets are classified as predefined type by " electric car ", " bicycle " or " tricycle ", especially remind
User is to avoid its wrongful door opening behavior.
The driving door alarm device of embodiment of the present invention is applied to Vehicular system, and the Vehicular system includes vehicle, figure
As harvester and warning device, described image harvester is used for the ambient image for gathering the vehicle periphery.The driving
Door alarm device includes：
Processing unit, the processing unit are used to handle the ambient image to determine the candidate regions that alarm target be present
Domain；
Object-recognition unit, the object-recognition unit are used for the identification model for establishing driving door alarm and are used for from described
The type of the alarm target is identified in candidate region；
First judging unit, first judging unit are used to judge whether the type of the alarm target to be predetermined class
Type；
Tracking cell, the tracking cell are used to track the alarm target and calculate the alarm target and the vehicle
The distance of car door and the speed of the relatively described car door of the alarm target.
Second judging unit, second judging unit are used to whether reach report according to the distance and the velocity estimated
Alert condition；With
Control unit, described control unit are used to control the warning device to alarm when reaching the alert if.
The driving door alarm device of embodiment of the present invention may recognize that the type for the alarm target for appearing in candidate region
And accurately obtain position and the speed of alarm target.Driving door alarm device informs that user reports in alarm by warning device
The type of alert target pays attention to taking precautions against to remind during user's door opening, optimizes alarm strategy, improves Consumer's Experience.
In some embodiments, the processing unit uses background modeling algorithm and UNICOM's zone algorithm or light stream
Method and Meanshift clustering algorithms handle the ambient image to determine the candidate region that alarm target be present.
In this way, by background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms to every
One frame ambient image carries out processing and provides the candidate region that alarm target be present.
In some embodiments, the object-recognition unit establishes driving door alarm using deep neural network algorithm
Identification model and the type for identifying the alarm target from the candidate region.
In this way, the identification model of driving door alarm is established by deep neural network algorithm to identify the class of alarm target
Type.
In some embodiments, the tracking cell tracks the alarm target using Kalman filtering algorithm and calculated
The speed of the alarm target car door relative with the distance of the car door of the vehicle and the alarm target.
In this way, itself and the distance of car door and the speed of relative car door are calculated alarm target by Kalman filtering algorithm,
So as to judge whether to alarm.
In some embodiments, the predefined type includes " electric car ", " bicycle " or " tricycle ".
In this way, these three alarm targets are classified as predefined type by " electric car ", " bicycle " or " tricycle ", especially remind
User is to avoid its wrongful door opening behavior.
The Vehicular system of embodiment of the present invention, including：
Vehicle；
Image collecting device；
Warning device；With
Driving door alarm device described in any of the above-described embodiment.
The driving door alarm device of the Vehicular system of embodiment of the present invention may recognize that the alarm for appearing in candidate region
The type of target can accurately obtain position and the speed of alarm target simultaneously, and inform that user reports by warning device in alarm
The type of alert target pays attention to taking precautions against to remind during user's door opening, optimizes alarm strategy, improves Consumer's Experience.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention is from combining in description of the accompanying drawings below to embodiment by change
Obtain substantially and be readily appreciated that, wherein：
Fig. 1 is the schematic flow sheet of the door opening alarm method of embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the door opening alarm method of another embodiment of the present invention；
Fig. 3 is the module diagram of the driving door alarm device of embodiment of the present invention；
Fig. 4 is the module diagram of the Vehicular system of embodiment of the present invention.
Main element symbol description：
Vehicular system 10, vehicle 100, image collecting device 200, warning device 300, driving door alarm device 400, processing
Unit 410, object-recognition unit 420, the first judging unit 430, tracking cell 440, the second judging unit 450, control unit
460。
Embodiment
Embodiments of the present invention are described below in detail, the embodiment of the embodiment is shown in the drawings, wherein
Same or similar label represents same or similar element or the element with same or like function from beginning to end.Lead to below
It is exemplary to cross the embodiment being described with reference to the drawings, and is only used for explaining the present invention, and it is not intended that to limit of the invention
System.
Referring to Fig. 1, the door opening alarm method of embodiment of the present invention is applied to Vehicular system 10.Vehicular system 10 wraps
Include vehicle 100, image collecting device 200 and warning device 300.The ring that image collecting device 200 is used for around collection vehicle 100
Border image.Door opening alarm method comprises the following steps：
S110：Processing environment image is to determine the candidate region that alarm target be present；
S120：Establish the identification model of driving door alarm and the type for identifying alarm target from candidate region；
S130：Whether the type for judging alarm target is predefined type；
S140：Alarm target is tracked when alarm target is predefined type and calculates the car door of alarm target and vehicle 100
Distance and alarm target with respect to car door speed.
S150：Whether alert if is reached according to distance and velocity estimated；With
S160：Control warning device 300 to alarm when reaching alert and if prompt the type of alarm target.
The door opening alarm method of embodiment of the present invention may recognize that the type for the alarm target for appearing in candidate region
And accurately obtain position and the speed of alarm target.Door opening alarm method informs use in alarm by warning device 300
The type of family alarm target pays attention to taking precautions against to remind during user's door opening, optimizes alarm strategy, improves Consumer's Experience.
It is appreciated that the door opening alarm method of embodiment of the present invention, the environment map gathered to image collecting device 200
As being handled to obtain the candidate region that alarm target be present, the type of the alarm target in candidate region is then identified.
When alarm target is predefined type, tracks and calculate alarm target and the distance of car door and the speed of relative car door.According to away from
Determine the need for alarming from speed.When reaching alert if, control warning device 300, which issues the user with, to be alerted and prompts
The type of alarm target.
It should be strongly noted that when the distance and speed of alarm target are unsatisfactory for alert if, warning device 300 will not
Issue the user with warning, but alarm target image collecting device 200 can cover moved in the environmental area of collection it is whole
During individual, all-the-way tracking alarm target.
Specifically, alarm target can be understood as in the environmental area that image collecting device 200 can cover collection
Moving object.The image collecting device 200 that candidate region can be understood as existing moving object can cover the ambient zone of collection
Domain.
In some embodiments, referring to Fig. 2, door opening alarm method comprises the following steps：
S110：Processing environment image is to determine the candidate region that alarm target be present；
S120：Establish the identification model of driving door alarm and the type for identifying alarm target from candidate region；
S130：Whether the type for judging alarm target is predefined type；
S142：Alarm target is tracked when alarm target is not predefined type and calculates the car of alarm target and vehicle 100
Door distance and alarm target with respect to car door speed.
S150：Whether alert if is reached according to distance and velocity estimated；With
S162：Warning device 300 is controlled to alarm when reaching alert if.
It is appreciated that the door opening alarm method of embodiment of the present invention, the environment map gathered to image collecting device 200
As being handled to obtain the candidate region that alarm target be present, the type of the alarm target in candidate region is then identified.
When alarm target is not predefined type, tracks and calculate alarm target and the distance of car door and the speed of relative car door.According to
Distance and speed determine the need for alarming.When reaching alert if, control warning device 300 issues the user with warning.
It should be strongly noted that when the distance and speed of alarm target are unsatisfactory for alert if, warning device 300 will not
Issue the user with warning, but alarm target image collecting device 200 can cover moved in the environmental area of collection it is whole
During individual, all-the-way tracking alarm target.
In some embodiments, alert if is：Using the reflective mirror of vehicle 100 as 0 point, in 0 to 3 meters, fortune be present
Animal body is alarmed, and in 3 to 6 meters, the instantaneous velocity of moving object is more than 10 kilometer per hours or moving object moves to
Take time at car door and alarmed less than 1.5 seconds, in 6 to 10 meters, moving object is moved at car door and taken time less than 1.5
Second alarms.It is appreciated that the environmental area scope that image collecting device 200 can cover collection is more than 10 meters.Moving object
It can be understood as alarm target.
In some embodiments, processing environment image is adopted with the step S110 for the candidate region for determining to have alarm target
With background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms.
In this way, by background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms to every
One frame ambient image carries out processing and provides the candidate region that alarm target be present.
It is appreciated that using background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms
The each frame ambient image gathered to image collecting device 200 is handled, it is determined that the candidate region of alarm target be present.Specifically
Ground, background modeling algorithm are first split to the foreground and background of ambient image, then determine candidate regions with UNICOM's zone algorithm
Domain.Optical flow method directly calculates motion vector to the moving object in ambient image, and then Meanshift clustering algorithms are according to motion
The position and directional information of vector carry out cluster and provide candidate region.
In some embodiments, the identification model of driving door alarm is established and for identifying alarm from candidate region
The step S120 of the type of target uses deep neural network algorithm.
In this way, the identification model of driving door alarm is established by deep neural network algorithm to identify the class of alarm target
Type.
It is appreciated that the identification model of driving door alarm is established by big data training using depth network neural algorithm.
Specifically, depth network neural algorithm trains the feature of automatic study alarm target predefined type by big data, then establishes
The identification model of driving door alarm is to identify the type of alarm target.
In some embodiments, alarm target is tracked when alarm target is predefined type and calculates alarm target and car
The distance and alarm target of 100 car door use Kalman filtering algorithm with respect to the step S140 of the speed of car door.
In this way, itself and the distance of car door and the speed of relative car door are calculated alarm target by Kalman filtering algorithm,
So as to judge whether to alarm.
It is appreciated that image collecting device 200 includes camera, and after the inside and outside parameter demarcation of camera, image collecting device 200
The relation of image coordinate system and world coordinate system can be established, alarm target can be so obtained by image coordinate system in the world
The coordinate of coordinate system.Multiframe ambient image of the Kalman filtering algorithm based on corresponding candidate region obtains alarm target and sat in the world
The coordinate of system is marked, calculates alarm target and the distance of car door and the speed of its relative car door.World coordinate system can be understood as
The description camera and the reference frame of the position of object selected in environment.Image coordinate system can be understood as in camera
The image coordinate system formed.
In some embodiments, predefined type includes " electric car ", " bicycle " or " tricycle ".
In this way, these three alarm targets are classified as predefined type by " electric car ", " bicycle " or " tricycle ", especially remind
User is to avoid its wrongful door opening behavior.
Referring to Fig. 3, the driving door alarm device 400 of embodiment of the present invention is applied to Vehicular system 10.Vehicular system
10 include vehicle 100, image collecting device 200 and warning device 300.Image collecting device 200 is used for around collection vehicle 100
Ambient image.Driving door alarm device 400 include processing unit 410, object-recognition unit 420, the first judging unit 430,
Tracking cell 440, the second judging unit 450, control unit 460.
Processing unit 410 is used for processing environment image to determine the candidate region that alarm target be present.
Object-recognition unit 420 is used for the identification model for establishing driving door alarm and for identifying report from candidate region
The type of alert target.
First judging unit 430 is used to judge whether the type of alarm target to be predefined type.
Tracking cell 440 is used to track alarm target and calculates distance and the alarm of alarm target and the car door of vehicle 100
Speed of the target with respect to car door.
Second judging unit 450 is used to whether reach alert if according to distance and velocity estimated.
Control unit 460 is used to control warning device 300 to alarm when reaching alert if.
In other words, the door opening alarm method of embodiment of the present invention can be by the door opening report of embodiment of the present invention
Alarm device 400 realizes, wherein, step S110 can be realized that step S120 can be by object-recognition unit by processing unit 410
420 are realized, step S130 can be realized that step S140 or step S142 can be by tracking cell 440 by the first judging unit 430
Realize, step S150 can be realized by the second judging unit 450, and step S160 or step S162 can be real by control unit 460
It is existing.
The driving door alarm device 400 of embodiment of the present invention may recognize that the class for the alarm target for appearing in candidate region
Type and position and the speed for accurately obtaining alarm target.Driving door alarm device 400 is accused in alarm by warning device 300
Know that the type of user's alarm target pays attention to taking precautions against to remind during user's door opening, optimize alarm strategy, improve Consumer's Experience.
It is appreciated that the driving door alarm device 400 of embodiment of the present invention, processing unit 410 is to image collecting device
The ambient image of 200 collections is handled to obtain the candidate region that alarm target be present, and object-recognition unit 420 identifies time
The type of alarm target in favored area.When alarm target is predefined type, tracking cell 440 tracks and calculates alarm target
With the distance of car door and the speed of relative car door.Determine the need for alarming according to distance and speed.When reaching alert if,
Control unit 460 controls warning device 300 to issue the user with and alerts and prompt the type of alarm target.
When alarm target is not predefined type, tracking cell 440 track and calculate alarm target and the distance of car door and
With respect to the speed of car door.Determine the need for alarming according to distance and speed.When reaching alert if, control unit 460 is controlled
Warning device 300 processed issues the user with warning.
It should be strongly noted that when the distance and speed of alarm target are unsatisfactory for alert if, warning device 300 will not
Issue the user with warning, but alarm target image collecting device 200 can cover moved in the environmental area of collection it is whole
During individual, control unit 460 controls the all-the-way tracking alarm target of tracking cell 440.
In some embodiments, processing unit 410 uses background modeling algorithm and UNICOM's zone algorithm or optical flow method
With Meanshift clustering algorithm processing environment images to determine the candidate region that alarm target be present.
In this way, by background modeling algorithm and UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms to every
One frame ambient image carries out processing and provides the candidate region that alarm target be present.
It is appreciated that processing unit 410 using background modeling algorithm and UNICOM's zone algorithm or optical flow method and
Meanshift clustering algorithms are handled each frame ambient image that image collecting device 200 gathers, and are provided in the presence of alarm mesh
Target candidate region.Specifically, background modeling algorithm is first split to the foreground and background of ambient image, then with area of UNICOM
Domain algorithm determines candidate region.Optical flow method directly calculates motion vector to the moving object in ambient image, then Meanshift
Clustering algorithm carries out cluster according to the position of motion vector and directional information and provides candidate region.
In some embodiments, object-recognition unit 420 establishes driving door alarm using deep neural network algorithm
Identification model and the type for identifying alarm target from candidate region.
In this way, the identification model of driving door alarm is established by deep neural network algorithm to identify the class of alarm target
Type.
It is appreciated that the identification model of driving door alarm is established by big data training using depth network neural algorithm.
Specifically, depth network neural algorithm trains the feature of automatic study alarm target predefined type by big data, then establishes
The identification model of driving door alarm is to identify the type of alarm target.
In some embodiments, tracking cell 440 using Kalman filtering algorithm tracking alarm target and calculates alarm
The speed of target car door relative with the distance and alarm target of the car door of vehicle 100.
In this way, itself and the distance of car door and the speed of relative car door are calculated alarm target by Kalman filtering algorithm,
So as to judge whether to alarm.
It is appreciated that image collecting device 200 includes camera, and after the inside and outside parameter demarcation of camera, image collecting device 200
The relation of image coordinate system and world coordinate system can be established, alarm target can be so obtained by image coordinate system in the world
The coordinate of coordinate system.Tracking cell 440 is obtained using multiframe ambient image of the Kalman filtering algorithm based on corresponding candidate region
Alarm target calculates alarm target and the distance of car door and the speed of its relative car door in the coordinate of world coordinate system.The world is sat
Mark system can be understood as the reference frame of the position of a description camera and object selected in the environment.Image coordinate system can
To be interpreted as the image coordinate system formed in camera.
In some embodiments, predefined type includes " electric car ", " bicycle " or " tricycle ".
In this way, these three alarm targets are classified as predefined type by " electric car ", " bicycle " or " tricycle ", especially remind
User is to avoid its wrongful door opening behavior.
Referring to Fig. 4, the Vehicular system 10 of embodiment of the present invention, including vehicle 100, image collecting device 200, alarm
The driving door alarm device 400 of device 300 and any of the above-described embodiment.
The driving door alarm device 400 of the Vehicular system 10 of embodiment of the present invention, which may recognize that, appears in candidate region
The type of alarm target can accurately obtain position and the speed of alarm target simultaneously, and be accused in alarm by warning device 300
Know that the type of user's alarm target pays attention to taking precautions against to remind during user's door opening, optimize alarm strategy, improve Consumer's Experience.
In some embodiments, image collecting device 200 includes being arranged on the front end of vehicle 100, rear end, left end and right-hand member
Four cameras.
In this way, it is arranged on the front end of vehicle 100, rear end, left end, four cameras shooting video of right-hand member, collection vehicle 100 weeks
The ambient image enclosed.The ambient image that camera collects may be displayed in the vehicle-carrying display screen of vehicle 100.Specifically, vehicle
The camera collection front side ambient image of 100 front ends, the camera collection rear side ambient image of the rear end of vehicle 100, the left end of vehicle 100
Camera collection left side ambient image, the camera collection rear side ambient image of the rear end of vehicle 100.In embodiments of the present invention,
Left side ambient image, right side ambient image and rear side ambient image are transferred at processing unit 410 by image collecting device 200
Reason.
In some embodiments, camera includes fisheye camera.
In this way, fisheye camera angular field of view is big, being capable of a wide range of scenery of shooting at close range.
It is appreciated that fisheye camera refers to carry fish-eye camera.Fish eye lens is that a kind of focal length is extremely short and regard
Angle is close or equal to 180 ° of camera lens.Fish eye lens can cause transparent effect strongly when being shot close to object, by force
Adjust the near big and far smaller contrast of object.
In some embodiments, camera, which rotates, is set.
In this way, camera, which rotates setting, can increase coverage.
In the description of embodiments of the present invention, term " first ", " second " are only used for describing purpose, without being understood that
To indicate or implying relative importance or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ",
One or more feature can be expressed or be implicitly included to the feature of " second ".In embodiments of the present invention
In description, " multiple " are meant that two or more, unless otherwise specifically defined.
, it is necessary to illustrate in the description of embodiments of the present invention, unless otherwise clearly defined and limited, term
" installation ", " connected ", " connection " should be interpreted broadly, for example, it may be fixedly connected or be detachably connected, or one
Connect body；It can be mechanical connection or electrical connection or can mutually communicate；Can be joined directly together, can also lead to
Cross intermediary to be indirectly connected, can be connection or the interaction relationship of two elements of two element internals.For ability
For the those of ordinary skill in domain, it can understand that above-mentioned term in embodiments of the present invention specific contains as the case may be
Justice.
In the description of this specification, reference term " embodiment ", " some embodiments ", " schematically implementation
The description of mode ", " example ", " specific example " or " some examples " etc. means the tool with reference to the embodiment or example description
Body characteristicses, structure, material or feature are contained at least one embodiment or example of the present invention.In this manual,
Identical embodiment or example are not necessarily referring to the schematic representation of above-mentioned term.Moreover, the specific features of description, knot
Structure, material or feature can combine in an appropriate manner in any one or more embodiments or example.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processing module or other can be from instruction
The system of execution system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or
Equipment and use.For the purpose of this specification, " computer-readable medium " can be it is any can include, store, communicating, propagating or
Transmission program uses for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
Device.The more specifically example (non-exhaustive list) of computer-readable medium includes following：With one or more wiring
Electrical connection section (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon or other are suitable
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of embodiments of the present invention can be with hardware, software, firmware or combinations thereof come real
It is existing.In the above-described embodiment, multiple steps or method can use storage in memory and by suitable instruction execution system
The software or firmware of execution is realized.If for example, being realized with hardware, with another embodiment, ability can be used
Any one of following technology known to domain or their combination are realized：With for realizing logic function to data-signal
The discrete logic of logic gates, there is the application specific integrated circuit of suitable combinational logic gate circuit, programmable gate array
(PGA), field programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in various embodiments of the present invention can be integrated in a processing module, also may be used
To be that unit is individually physically present, can also two or more units be integrated in a module.It is above-mentioned integrated
Module can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module
If realized in the form of software function module and as independent production marketing or in use, a calculating can also be stored in
In machine read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (11)
1. a kind of door opening alarm method, applied to Vehicular system, it is characterised in that the Vehicular system includes vehicle, image
Harvester and warning device, described image harvester are used for the ambient image for gathering the vehicle periphery, the door opening
Alarm method comprises the following steps：
The ambient image is handled to determine the candidate region that alarm target be present；
Establish the identification model of driving door alarm and the type for identifying the alarm target from the candidate region；
Whether the type for judging the alarm target is predefined type；
The alarm target is tracked when the alarm target is the predefined type and calculates the alarm target and the car
The distance of car door and the speed of the relatively described car door of the alarm target；
Whether alert if is reached according to the distance and the velocity estimated；With
Control the warning device to alarm when reaching the alert and if prompt the type of the alarm target.
2. door opening alarm method as claimed in claim 1, it is characterised in that described to handle the ambient image to determine to deposit
The candidate region of alarm target the step of using background modeling algorithm and UNICOM's zone algorithm or optical flow method and
Meanshift clustering algorithms.
3. door opening alarm method as claimed in claim 1, it is characterised in that the identification model for establishing driving door alarm
And it is used to use deep neural network algorithm the step of identifying the type of the alarm target from the candidate region.
4. door opening alarm method as claimed in claim 1, it is characterised in that described to make a reservation in the alarm target to be described
The alarm target is tracked during type and calculates the distance of the alarm target and the car door of the vehicle and the alarm target
The step of speed of relatively described car door, uses Kalman filtering algorithm.
5. door opening alarm method as claimed in claim 1, it is characterised in that the predefined type includes " electric car ", " oneself
Driving " or " tricycle ".
6. a kind of driving door alarm device, applied to Vehicular system, it is characterised in that the Vehicular system includes vehicle, image
Harvester and warning device, described image harvester are used for the ambient image for gathering the vehicle periphery, the door opening
Warning device includes：
Processing unit, the processing unit are used to handle the ambient image to determine the candidate region that alarm target be present；
Object-recognition unit, the object-recognition unit are used for the identification model for establishing driving door alarm and are used for from the candidate
The type of the alarm target is identified in region；
First judging unit, first judging unit are used to judge whether the type of the alarm target to be predefined type；
Tracking cell, the tracking cell are used to track the alarm target and calculate the car of the alarm target and the vehicle
The speed of the relatively described car door of distance and the alarm target of door；
Second judging unit, second judging unit are used to whether reach alarm bar according to the distance and the velocity estimated
Part；With
Control unit, described control unit are used to control the warning device to alarm when reaching the alert if.
7. driving door alarm device as claimed in claim 6, it is characterised in that the processing unit uses background modeling algorithm
The ambient image is handled with UNICOM's zone algorithm or optical flow method and Meanshift clustering algorithms to determine to exist alarm mesh
Target candidate region.
8. driving door alarm device as claimed in claim 6, it is characterised in that the object-recognition unit is using depth nerve
Network algorithm establishes the identification model of driving door alarm and the class for identifying the alarm target from the candidate region
Type.
9. driving door alarm device as claimed in claim 6, it is characterised in that the tracking cell is calculated using Kalman filtering
Method track the alarm target and calculate the alarm target and the car door of the vehicle distance and the alarm target it is relative
The speed of the car door.
10. driving door alarm device as claimed in claim 6, it is characterised in that the predefined type include " electric car ",
" bicycle " or " tricycle ".
A kind of 11. Vehicular system, it is characterised in that including：
Vehicle；
Image collecting device；
Warning device；With
Driving door alarm device as described in claim 6-10 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710944161.XA CN107757472A (en) | 2017-09-30 | 2017-09-30 | Door opening alarm method, driving door alarm device and Vehicular system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710944161.XA CN107757472A (en) | 2017-09-30 | 2017-09-30 | Door opening alarm method, driving door alarm device and Vehicular system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107757472A true CN107757472A (en) | 2018-03-06 |
Family
ID=61268023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710944161.XA Pending CN107757472A (en) | 2017-09-30 | 2017-09-30 | Door opening alarm method, driving door alarm device and Vehicular system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107757472A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108394378A (en) * | 2018-03-29 | 2018-08-14 | 成都惠网远航科技有限公司 | The autocontrol method of vehicle switch door sensing device |
| CN110717365A (en) * | 2018-07-13 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Method and device for obtaining picture |
| CN111791897A (en) * | 2019-11-07 | 2020-10-20 | 丁敏 | Car door collision accident signal prevention system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201856703U (en) * | 2010-10-15 | 2011-06-08 | 长安大学 | Safety getting-off early warning device for automobiles |
| DE102014010654A1 (en) * | 2014-07-17 | 2015-01-15 | Daimler Ag | Vehicle and method for operating a door collision warning device |
| CN204998410U (en) * | 2015-07-03 | 2016-01-27 | 南京金龙新能源汽车研究院有限公司 | A automatic protection system for eliminating open door of car initiation accident |
| CN105930787A (en) * | 2016-04-16 | 2016-09-07 | 南京林业大学 | Vehicle door opening early-warning method |
| CN106183983A (en) * | 2016-07-29 | 2016-12-07 | 广州汽车集团股份有限公司 | A kind of opening door of vehicle CAS and method |
-
2017
- 2017-09-30 CN CN201710944161.XA patent/CN107757472A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201856703U (en) * | 2010-10-15 | 2011-06-08 | 长安大学 | Safety getting-off early warning device for automobiles |
| DE102014010654A1 (en) * | 2014-07-17 | 2015-01-15 | Daimler Ag | Vehicle and method for operating a door collision warning device |
| CN204998410U (en) * | 2015-07-03 | 2016-01-27 | 南京金龙新能源汽车研究院有限公司 | A automatic protection system for eliminating open door of car initiation accident |
| CN105930787A (en) * | 2016-04-16 | 2016-09-07 | 南京林业大学 | Vehicle door opening early-warning method |
| CN106183983A (en) * | 2016-07-29 | 2016-12-07 | 广州汽车集团股份有限公司 | A kind of opening door of vehicle CAS and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108394378A (en) * | 2018-03-29 | 2018-08-14 | 成都惠网远航科技有限公司 | The autocontrol method of vehicle switch door sensing device |
| CN110717365A (en) * | 2018-07-13 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Method and device for obtaining picture |
| CN110717365B (en) * | 2018-07-13 | 2022-05-31 | 杭州海康威视数字技术股份有限公司 | Method and device for obtaining picture |
| CN111791897A (en) * | 2019-11-07 | 2020-10-20 | 丁敏 | Car door collision accident signal prevention system and method |
| CN111791897B (en) * | 2019-11-07 | 2021-07-02 | 武汉楚之子文化传播有限公司 | Car door collision accident signal prevention system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106611512B (en) | Method, device and system for processing starting of front vehicle | |
| KR101891460B1 (en) | Method and apparatus for detecting and assessing road reflections | |
| CN102203837B (en) | System for monitoring the area around a vehicle | |
| US10703299B2 (en) | Rear view mirror simulation | |
| JP5096836B2 (en) | Method and system for imaging the surroundings of a vehicle | |
| US11798290B2 (en) | Obstacle detection and notification for motorcycles | |
| KR102623124B1 (en) | Device and method for monitoring a berthing | |
| CN108162858B (en) | Vehicle-mounted monitoring device and method thereof | |
| CN111932901B (en) | Road vehicle tracking detection apparatus, method and storage medium | |
| CN106485233A (en) | Drivable region detection method, device and electronic equipment | |
| CN102834853B (en) | Vehicle periphery monitoring device, vehicle periphery monitoring method, and vehicle device | |
| CN102792314A (en) | Cross traffic collision alert system | |
| CN110312639A (en) | Vehicle assistant drive device, vehicle and information processing method | |
| CN109153359A (en) | A kind of monitoring method and system of vehicle blind zone | |
| CN106809214A (en) | A kind of rear-end collision method for early warning, device and electronic equipment | |
| CN107757472A (en) | Door opening alarm method, driving door alarm device and Vehicular system | |
| CN109070882B (en) | Utilize the driving information providing method and device of camera image | |
| CN111507162A (en) | Blind spot warning method and device based on cooperation of communication between vehicles | |
| CN109591698A (en) | Blind area detection system, blind zone detection method and vehicle | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN106415662A (en) | Vehicle periphery monitoring device | |
| KR20180047149A (en) | Apparatus and method for risk alarming of collision | |
| SE536729C2 (en) | Procedure and system for monitoring a motor vehicle from the point of view of intrusion | |
| US10719718B2 (en) | Device for enabling a vehicle to automatically resume moving | |
| CN114084129A (en) | Fusion-based vehicle automatic driving control method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180306 |