CN108062868A - For the bicycle detecting system and method and vehicle of vehicle - Google Patents
For the bicycle detecting system and method and vehicle of vehicle Download PDFInfo
- Publication number
- CN108062868A CN108062868A CN201610984676.8A CN201610984676A CN108062868A CN 108062868 A CN108062868 A CN 108062868A CN 201610984676 A CN201610984676 A CN 201610984676A CN 108062868 A CN108062868 A CN 108062868A
- Authority
- CN
- China
- Prior art keywords
- bicycle
- vehicle
- processor
- movement
- frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/62—Hybrid vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The present disclosure discloses a kind of bicycle detecting system and method and the vehicles equipped with the system.System includes:Image acquisition units are configured as the image of collection vehicle ambient enviroment;Processor is configured as:Bicycle is identified from acquired image;Detection bicycle tramples state;And the state of trampling is at least partially based on to predict the movement of bicycle.The program can allow the movement to bicycle more accurately to predict, and can thus reduce the collision with bicycle.
Description
Technical field
This disclosure relates to vehicular field, and more particularly, to the bicycle detecting system and method for vehicle, with
And the vehicle equipped with the system.
Background technology
There are the equipment or system of the object that can be used for detecting vehicle periphery on vehicle, so as to during contributing to driving
Operation.In general, detection is by being adopted to the sensor (for example, camera or ultrasonic sensor) by being mounted on vehicle
The data related with the ambient enviroment of vehicle of collection are handled what is completed.Based on such detection, the movement of object can be with
It is predicted, and driver can obtain the warning to possible collision as a result, so that it is true that suitable action can be taken
Ensure safety driving.
One example of object is the bicycle in riding, be to certainly compared to other objects (for example, vehicles or pedestrians)
The movement of driving is predicted, possible much more difficult.
The content of the invention
Embodiment of the disclosure is provided, for solving issue discussed above.In fact, embodiment of the disclosure is given
A kind of bicycle detecting system and method are gone out, being better anticipated for the movement to bicycle can be provided.Set forth below is
To the brief overview of the one or more aspects of the disclosure, in order to provide to the basic comprehension in terms of these.
In an exemplary embodiment of the disclosure, a kind of bicycle detecting system for vehicle is provided, including:
Image acquisition units are configured as the image of collection vehicle ambient enviroment;Processor is configured as:From acquired image
Identify bicycle;That detects the bicycle tramples state;And be at least partially based on the state of trampling come to it is described from
The movement of driving is predicted.
Optionally, processing be configured to be at least partially based on bicycle the variation for trampling frequency come to it is described from
The movement of driving is predicted.
Optionally, processor is configured to:The structure feature of the bicycle is identified from described image;It is based on
The structure feature of identification determines the classification based on gear of the bicycle;And based on the variation for trampling frequency and institute
Classification is stated to predict the movement of the bicycle.Optionally, processor be configured to identification with it is described voluntarily
The gear of vehicle, flywheel, brake assemblies, or any combination thereof associated structure feature.
Optionally, the classification based on gear of bicycle includes single speed bicycle, multi-speed bicycle and extremely flies voluntarily
Vehicle.
Optionally, processor is configured to:If recognizing single backgear, the bicycle is determined
For single speed bicycle;If recognizing multiple backgears, the bicycle is determined as multi-speed bicycle;And if do not have
Flywheel and/or brake assemblies are recognized, then are identified as the bicycle extremely flying bicycle.
Optionally, processor is configured to:If detect that the described of the bicycle tramples frequency and drop to
Zero, then predict the sliding state of the bicycle.
Optionally, processor is configured to:For single speed bicycle, if trampling frequency described in detecting
Decline, then predict the deceleration of the bicycle, and trample frequency described in if detected increasing, predict the bicycle
Accelerate;For multi-speed bicycle, if detecting the unexpected decline for trampling frequency, the acceleration of the bicycle is predicted, and
And if detecting the unexpected increase for trampling frequency, predict the deceleration of the bicycle.
Optionally, processor is configured to by calculating trampling frequency and detecting for the multiple images in time window
The variation for trampling frequency.
Optionally, processor is configured to riding for pedal by detecting the bicycle or the bicycle
The movement of the leg or foot of passerby changes to detect the variation for trampling frequency.
Optionally, system further includes one or more sensors, for obtaining and the vehicle and/or the bicycle
Travel associated data;The processor is configured to based on the data and to the pre- of the movement of the bicycle
It surveys to aid in the driving of the vehicle.
Optionally, processor is configured to based on the data and the prediction of the movement of the bicycle is estimated
The possibility of potential collision is counted, and estimates to send alarm based on described.
In another exemplary embodiment, a kind of vehicle is provided, equipped with above-mentioned system.
In another exemplary embodiment, a kind of bicycle detection method of user's vehicle is provided, including:From acquisition
The vehicle ambient enviroment image in identify bicycle;That detects the bicycle tramples state;And at least portion
It point tramples state based on described the movement of the bicycle is predicted.
Optionally, detecting the state of trampling of the bicycle includes detecting the variation for trampling frequency of the bicycle.
Optionally, method further includes:The structure feature of the bicycle is identified from described image;And based on identification
Structure feature determines the classification based on gear of the bicycle;The prediction of the movement of bicycle is further comprised:It is based on
Variation and the classification of frequency are trampled to predict the movement of the bicycle.
Optionally, identifying the mechanism characteristics of the bicycle includes identification and the gear, flywheel, brake group of the bicycle
Part, or any combination thereof associated structure feature.
In the further exemplary embodiment of the disclosure, a kind of voluntarily car detector is provided, including:Identification is single
Member, for identifying bicycle from the image of the ambient enviroment of the vehicle of acquisition;Detection unit, for detecting the bicycle
Trample state;And predicting unit, carry out the progress of the movement to the bicycle for being at least partially based on the state of trampling
Prediction.
According to some embodiments of the present disclosure, based on the bicycle identified trample state come the movement to bicycle into
The collision with bicycle is more accurately predicted and can thus reduced to row prediction so that can obtain.
Description of the drawings
In order to be clearly shown the technical solution in embodiment of the disclosure, the institute in the description to embodiment is given below
The brief introduction of the attached drawing needed.It should be evident that drawings described below is some embodiments of the present disclosure, it is attached based on these
Figure, those of ordinary skill in the art can obtain other attached drawings, without any performing creative labour.
Fig. 1 is the schematic diagram for showing exemplary self car test examining system in accordance with an embodiment of the present disclosure.
Fig. 2 is the schematic diagram for showing the exemplary self car test examining system according to another embodiment of the disclosure.
Fig. 3 is the schematic flow diagram for showing bicycle detection method in accordance with an embodiment of the present disclosure.
Fig. 4 is the block diagram for showing the voluntarily car detector according to some embodiments of the present disclosure.
Specific embodiment
The description to various configurations is intended as below in conjunction with the specific embodiment that attached drawing illustrates rather than to represent this
The concept and feature of text description are only capable of the configuration realized wherein.Following description includes concrete details, for offer pair
Each conception of species is fully understood.It will be apparent, however, to one skilled in the art that these concepts can be in these no tools
It is realized in the case of body details.
Driving assistance system (DAS) can be identified for example from the image of the ambient enviroment of the vehicle captured by camera
Object (for example, pedestrian, other vehicles and barrier) near vehicle.It is in addition, various on vehicle by being mounted on
Sensor, various data (for example, position, size and speed) associated with these objects can be acquired, and therefore
The movement of these objects can be predicted.Further, based on the prediction, alarm or guiding can be provided to avoid such as
Collision or scrape etc. accident.For the object of vehicle etc., the program can work well, still, when applied to pair
During the prediction of the bicycle in riding, it is understood that there may be challenge.
Usually, as required by traffic rules, vehicle travels on some track on road, and its movement and row
To be rule and stablizing.In addition, if necessary, car light can be blown a whistle or be opened to vehicle, to provide to its next action
Instruction.With reference to image as described above and various sensing datas, the behavior of vehicle is easily predicted.However, from
The behavior of driving can not be so easily determined.For example, in riding, bicyclist may optionally change its route or speed
Degree even ignores traffic rules sometimes.The simple collection of the data of distance and position etc. may be not enough to pre- exactly
Survey the behavior of bicycle.
Embodiment is intended to provide the prediction of the movement to bicycle, and such prediction is at least partially based on trampling for bicycle
State.
Each conception of species provided in the entire disclosure can realize in various vehicles, including sports car, car,
Multi-function vehicle (SUV), hybrid electric vehicle (HEV), battery truck, truck etc..It will be understood by those skilled in the art, however, that these
Be provided for illustration purposes only, and the one or more aspects of the disclosure can realize or be included in it is one or more other
In the vehicle of type.
Fig. 1 shows the bicycle detecting system for vehicle of one embodiment according to the disclosure.The system can be with
A part as the driving assistance system (DAS) on vehicle.As shown in fig. 1, system includes being coupling in by In-vehicle networking 13
Image acquisition units 11 together and processor 12.The example of In-vehicle networking 13 can include CAN or Flexray.
Image acquisition units 11 can be configured as the image of collection vehicle ambient enviroment.In some embodiments of the present disclosure
In, image acquisition units 11 can be mounted in the camera on vehicle, for example, RGB or infrared camera.
Processor 12 can be such as central processing unit (CPU), micro-control unit (MCU), digital signal processor
(DSP) etc. general processor is configured as being stored in the program instruction in data storage medium by performing and realizing this
Literary described function it is part or all of.Additionally or alternatively, processor 12 can also include programmable hardware element,
Such as application-specific integrated circuit (ASIC), field programmable gate array (FPGA) etc..
Data storage medium can be such as by memory 23 shown in figure 2.Memory 23 can such as be deposited at random
The volatile memory of access to memory (RAM), static state RAM (SRAM), dynamic ram (DRAM) etc. or such as read-only storage
The nonvolatile memory of device (ROM), flash memory, magnetic, photoelectricity storage device etc., or both certain combination.Memory
23 can be used for storage can be by the program instruction of processor 12.
In embodiment of the disclosure, processor 12 is configured as identifying from the image gathered by image acquisition units 11
Bicycle with bicyclist.Optionally, processor 12 can also identify one or more portions with bicycle from image
The associated structure feature of part.The identification of bicycle and its structure feature can be known by using computer vision or pattern
Other technology realizes that the process of these technologies is well known to the skilled person, and be thus omitted herein
The details of these technologies, in order to be unnecessarily disclosure indigestion.
In embodiment of the disclosure, the structure feature that identifies can be used for determining by processor 12 bicycle based on
The classification of gear.
The classification based on gear of bicycle can include single speed, speed change and extremely fly.It is shown below to each classification
The brief description of structure feature is in order to providing fully understanding to the concept of the disclosure.
Extremely (or fixed wheel bicycle, it is to have not having to be also referred to as " permanent tooth (fixie) " in some cases for winged bicycle
The bicycle of the power train of flywheel mechanism.One appreciable main attraction of dead winged bicycle is low weight.Without such as
Speed changer dials the add-on parts such as handle, brake cable, coil holder, multiple, flywheel hub, and extremely other bicycles of the winged weight ratio of bicycle are light.
In addition, extremely winged bicycle is typically without brake.In other words, there is no such as various types of on dead winged bicycle
The brake assemblies of brake, brake cable or the cable of type etc..As a result, extremely winged bicycle may have than other kinds of bicycle
Longer braking distance, and therefore may be more dangerous.
Single speed bicycle is the bicycle of such type, with single gear ratio and without speed changer.Change speech
It, in riding, bicyclist cannot change gear ratio.Generally, due to without speed changer or other speed change systems, single speed is certainly
Driving is mechanically simpler than multi-speed bicycle.Particularly, single speed bicycle only has single rear tooth on wheel behind
Wheel.
Multi-speed bicycle is the bicycle of the type with multiple gear ratios.In riding, bicyclist can pass through one
Or multiple speed changers carry out change gear ratio.To enable being switched between different gear ratios, have on rear wheel
Multiple (for example, 7 to 10) backgears and at least one speed changer.In general, it there may also be multiple (for example, 3) on bicycle
Front gear.
In addition, single speed bicycle and multi-speed bicycle generally have brake assemblies and flywheel on it.
In short, each type, which has, can differentiate it from other kinds of unique structure feature.Based on to such
The identification of one or more of structure feature, processor 12 can determine the classification based on gear of bicycle.
In some embodiments, processor 12 be configured as based on structure feature associated with the backgear of bicycle come
Determine the classification of bicycle.Backgear refers to one or more gears in the wheel hub of the trailing wheel of bicycle.Particularly, such as
Fruit recognizes single backgear, then the bicycle can be determined as single speed bicycle by processor, also, if be recognized more
The bicycle can be then identified as multi-speed bicycle by a backgear.
Alternatively or additionally, processor is also based on feature associated with speed changer to determine bicycle
Classification.If for example, having recognized speed changer on bicycle, which can be determined as multi-speed bicycle.Another
In one example, if bicycle does not have speed changer, it can be determined that single speed bicycle or extremely fly bicycle.
In some other embodiments, processor 12 is configured as identifying based on structure feature associated with flywheel dead
Fly the bicycle of type.Specifically, if not recognizing flywheel on bicycle, processor 12 can be true by the bicycle
It is set to extremely winged bicycle.
Alternatively or additionally, processor can determine dead fly based on structure feature associated with brake assemblies
Bicycle.Brake assemblies can include various parts, such as disc brake/V- brakes, sneek, brake cable or cable etc..If it for example, does not examine
Any one in these components is measured, then the bicycle can be determined as extremely flying bicycle by processor 12.
In addition, various structure features can be used with any combinations.For example, with flywheel without speed changer from
Driving can be identified as single speed bicycle by processor 12, and the bicycle for both not having flywheel or not having speed change gas will be known
Bicycle Wei not flown extremely.
It should be understood that various structure features above are provided for illustrating purpose and unrestricted purpose.It can be with
Based on other component (for example, front gear, handlebar, dial, or any combination thereof) associated structure feature determines voluntarily
The classification of vehicle.
In some embodiments, processor 12 can be configured as identifies from the image gathered by image acquisition units 11
Bicycle tramples state.
" trampling state " herein refers to the motion state of pedal.For example, under steam, pedal is usually by bicyclist
Foot step on forward, however, pedal can also be stepped on or the remains stationary in the sliding state of bicycle backward sometimes.
In addition, pedal state can also include some physical representations of the movement of reflection pedal, such as the frequency or angular speed of pedal.
In the exemplary embodiment, processor 12 is configured to from the image gathered by image acquisition units 11
It is middle to detect the variation for trampling frequency.And therefore pedal is generally driven by the leg or foot of bicyclist, and, the variation for trampling frequency can be with
Reflected by the motion change of leg or foot.
Particularly, processor 12 can be configured to by being stepped on according to multiple consecutive images calculating in time window
Frequency is stepped on to detect the variation for trampling frequency.
Identified according to the classification to bicycle based on gear described above and the state of trampling.Exemplary
Embodiment in, processor 12 is configured to predict the movement of bicycle based on classifying and trampling state.
For example, it is contemplated that multi-speed bicycle.When being switched to higher gear ratio, it can detect and step on from multiple consecutive images
The unexpected decline of frequency is stepped on, which may reflect the acceleration intentions of bicyclist.On the contrary, when being switched to relatively low gear ratio, it can
To detect the unexpected increase for trampling frequency, which may reflect the intentions of deceleration.However, being gradually reduced or increasing for frequency is led to
It often does not indicate to switch, and reflects the intention of deceleration or acceleration respectively.
For single speed bicycle or extremely fly bicycle, due to only there are one gear ratio, trample frequency decline (or
Increase), whether unexpected or gradual, only expression bicyclist is being slowed down (acceleration).
In some embodiments, processor 12 can be configured to:For single speed bicycle, stepped on if detected
It steps on frequency declining, then predicts the deceleration of the bicycle, and increasing if detecting and trampling frequency, prediction should be certainly
The acceleration of driving;For multi-speed bicycle, if detecting the unexpected decline for trampling frequency, the acceleration of the bicycle is predicted,
And if detecting the unexpected increase for trampling frequency, predict the deceleration of the bicycle.
To any classification, if detecting pedal remains stationary in time window, bicycle will be in sliding state.Place
Device 12 is managed it is possible thereby to be configured as, if detecting that pedal frequency is zero, predicts the sliding state of bicycle.
Referring now to Fig. 2, the exemplary self car test examining system according to another embodiment of the disclosure is shown.
As shown in Figure 2, system 200 includes image acquisition units 21, processor 22, memory 23 and one or more sensings
Device.
Image acquisition units 21 are configured as the image of the ambient enviroment of collection vehicle, and processor 22 is configured as root
The prediction of the movement to bicycle is obtained according to the operation described with reference to the processor 12 in Fig. 1.For brevity, herein no longer
Repeat its details.
One or more sensors 24 can include for obtain vehicle various running datas sensor (for example, plus
Velocity sensor, velocity sensor and/or the steering angle sensor on turning-bar).Processor 22 can be configured
To determine the driving condition of vehicle or intention based on the data obtained by these sensors.
Additionally or alternatively, one or more sensors 24 can include obtaining associated with the traveling of bicycle
Exercise data (for example, position, distance, speed etc.) sensor.Such sensor can include laser sensor, radar
One or more of sensor or acoustic sensor.
In this embodiment, processor 22 can be configured to the prediction based on the movement to bicycle, vehicle
Driving intention and associated with bicycle exercise data aid in the driving of vehicle.In a further embodiment, locate
Reason device 22 can estimate the possibility of the potential collision between bicycle and vehicle based on prediction and various sensing datas.
In further embodiment, processor 22 can by screen, audio, obtain his interactive device and send vision, the sense of hearing or tactile
Alarm.Additionally or alternatively, in some instances, processor 22 can be driven in response to the possibility of the collision of estimation to activate
Sail the automatic Pilot operation of auxiliary system (DAS).
According to some embodiments of the present disclosure, state is trampled to predict the movement of bicycle based on bicycle.
Such mode can allow the more accurately prediction of the movement to bicycle, and be touched thus, it is possible to reduce with bicycle
It hits.
In another aspect of the disclosure, a kind of vehicle is provided, equipped with above-described bicycle detecting system
100 or 200.
Fig. 3 is the schematic flow diagram for showing bicycle detection method in accordance with an embodiment of the present disclosure.Method 300 can be with
It is performed in system 100 shown in FIG. 1.Method 300 comprises the following steps.
In step 301, bicycle is identified from the image of the ambient enviroment of vehicle.
In some embodiments, the structure feature of bicycle can be identified from image, and can be based on identification
Structure feature determines the classification based on gear of bicycle.
In some embodiments, structure feature can be associated with one or more components of bicycle, the component bag
It includes but is not limited to gear, flywheel and brake assemblies.
In embodiment of the disclosure, the classification based on gear can include single speed bicycle, multi-speed bicycle or dead winged
Bicycle.
In a realization of the embodiment, if recognizing single backgear, the bicycle is determined as list
Fast bicycle.In another realization, if recognizing multiple backgears, the bicycle is determined as multi-speed bicycle.
In another realization, if not recognizing flywheel, the bicycle is identified as extremely to fly bicycle.
In step 302, that detects bicycle tramples state.
In some embodiments, trample the variation of frequency by being detected from image and detect the state of trampling.Specifically, it is right
The identification for trampling the variation of frequency can be by trampling frequency and realizing according to the multiple images in time window to calculate.
In step 303, at least the movement of bicycle is predicted based on the state of trampling.
If be gradually reduced for example, detecting and trampling frequency, the acceleration of bicycle can be predicted, and if detect
It is gradually reduced, then can predict the deceleration of bicycle.In another example, zero when trampling frequency is dropped to when detecting,
It can predict the sliding state of bicycle.
In some embodiments, in order to make prediction more accurate, based on the state of trampling, come with reference to the classification of bicycle to certainly
The movement of driving is predicted.Specifically, for single speed bicycle, declining if trampling frequency described in detecting, in advance
The deceleration of the bicycle is surveyed, and tramples frequency described in if detected increasing, predicts the acceleration of the bicycle;And pin
To multi-speed bicycle, if detecting the unexpected decline for trampling frequency, the acceleration of the bicycle, and if inspection are predicted
The unexpected increase for trampling frequency is measured, then predicts the deceleration of the bicycle.
Fig. 4 is the block diagram for showing the voluntarily car detector according to some embodiments of the present disclosure.As shown in Figure 4
, device 400 includes recognition unit 41, detection unit 42 and predicting unit 43.Device 400 can be software entity, hardware
Entity or its combination.It can be included in the system 100 with reference to Fig. 1 descriptions.Alternatively or additionally, device 400
Can be the entity or application performed by processor 12.
Recognition unit 41 may be adapted to identify bicycle from the image of the ambient enviroment of the vehicle of acquisition.
In a further embodiment, recognition unit 41 may be adapted to the structure feature for identifying bicycle.
Detection unit 42, which may be adapted to detect bicycle, tramples state.
Specifically, described above, detection unit 42 can detect the variation for trampling frequency of bicycle.
In a further embodiment, detection unit 42 can be further adapted for based on the structure identified by recognition unit 41
Feature determines the classification based on gear of bicycle.
Predicting unit 43 may be adapted to be at least partially based on the state of trampling to predict the movement of bicycle.
In a further embodiment, predicting unit 43 may be adapted to based on the state of trampling and the classification come to bicycle
Movement predicted.
It will be understood by those skilled in the art that the equipment that the unit in devices disclosed herein can be distributed in embodiment
In, and can also alternatively be located in one or more equipment different from those equipment in embodiment.Foregoing embodiments
Unit can be integrated into a unit or can be further divided into multiple subelements.
The disclosure, those skilled in the art are described although having been combined and being considered most practical and preferred embodiment
It should be understood that such limitation is not limited to the disclosed embodiments, and it is intended to cover included various arrangements, without
Deviation most widely understands scope, in order to cover all such modifications and equivalent arrangements.
Claims (18)
1. a kind of bicycle detecting system for vehicle, including:
Image acquisition units are configured as the image of collection vehicle ambient enviroment;
Processor is configured as:
Bicycle is identified from acquired image;
That detects the bicycle tramples state;And
State is trampled to predict the movement of the bicycle described in being at least partially based on.
2. system according to claim 1, wherein, the processor be configured to be at least partially based on it is described from
The movement of the bicycle is predicted in the variation for trampling frequency of driving.
3. system according to claim 2, wherein, the processor is configured to:
The structure feature of the bicycle is identified from described image;
The classification based on gear of the bicycle is determined based on the structure feature of identification;And
The movement of the bicycle is predicted based on the variation for trampling frequency and the classification.
4. system according to claim 3, wherein, the processor is configured to identification and the bicycle
Gear, flywheel, brake assemblies, or any combination thereof associated structure feature.
5. the system according to claim 3 or 4, wherein, the classification based on gear of the bicycle includes single speed voluntarily
Vehicle, multi-speed bicycle and extremely winged bicycle.
6. system according to claim 5, wherein, the processor is configured to:
If recognizing single backgear, the bicycle is determined as single speed bicycle;
If recognizing multiple backgears, the bicycle is determined as multi-speed bicycle;And
If not recognizing flywheel and/or brake assemblies, the bicycle is identified as extremely to fly bicycle.
7. according to the system any one of claim 1-6, wherein, the processor is configured to:If inspection
It measures the described of the bicycle to trample frequency and drop to zero, then predicts the sliding state of the bicycle.
8. system according to claim 3, wherein, the processor is configured to:
For single speed bicycle, declining if trampling frequency described in detecting, predicting the deceleration of the bicycle, and such as
Fruit detect it is described trample frequency and increasing, then predict the acceleration of the bicycle;
For multi-speed bicycle, if detecting the unexpected decline for trampling frequency, the acceleration of the bicycle is predicted, and
If detecting the unexpected increase for trampling frequency, the deceleration of the bicycle is predicted.
9. system according to claim 2, wherein, the processor is configured to by calculating in time window
Multiple images trample frequency to detect the variation for trampling frequency.
10. the system according to claim 2 or 9, wherein, the processor is configured to described certainly by detection
The movement of the leg or foot of the bicyclist of the pedal of driving or the bicycle changes to detect the variation for trampling frequency.
11. according to the system any one of claim 1-10, one or more sensors are further included, for acquisition and institute
State the associated data of traveling of vehicle and/or the bicycle;
The processor is configured to based on the data and described to aid in the prediction of the movement of the bicycle
The driving of vehicle.
12. system according to claim 11, wherein, the processor is configured to based on data and right
The prediction of the movement of the bicycle is estimated to send alarm to estimate the possibility of potential collision based on described.
13. a kind of vehicle, equipped with according to the system any one of claim 1-12.
14. a kind of bicycle detection method for vehicle, including:
Bicycle is identified from the image of the ambient enviroment of the vehicle of acquisition;
That detects the bicycle tramples state;And
State is trampled to predict the movement of the bicycle described in being at least partially based on.
15. according to the method for claim 14, wherein, detecting the state of trampling of the bicycle is included described in detection voluntarily
The variation for trampling frequency of vehicle.
16. it according to the method for claim 15, further includes:
The structure feature of the bicycle is identified from described image;And
The classification based on gear of the bicycle is determined based on the structure feature of identification;
The prediction of the movement of the bicycle is further comprised:Based on the variation for trampling frequency and the classification come to institute
The movement for stating bicycle is predicted.
17. according to the method for claim 16, wherein, identify the bicycle mechanism characteristics include identification with it is described from
The gear of driving, flywheel, brake assemblies, or any combination thereof associated structure feature.
18. a kind of voluntarily car detector, including:
Recognition unit, for identifying bicycle from the image of the ambient enviroment of the vehicle of acquisition;
Detection unit tramples state for detect the bicycle;And
Predicting unit described trample state the movement of the bicycle is predicted for being at least partially based on.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610984676.8A CN108062868B (en) | 2016-11-09 | 2016-11-09 | Bicycle detection system and method for vehicle and vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610984676.8A CN108062868B (en) | 2016-11-09 | 2016-11-09 | Bicycle detection system and method for vehicle and vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108062868A true CN108062868A (en) | 2018-05-22 |
CN108062868B CN108062868B (en) | 2021-06-29 |
Family
ID=62137894
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610984676.8A Active CN108062868B (en) | 2016-11-09 | 2016-11-09 | Bicycle detection system and method for vehicle and vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108062868B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111081011A (en) * | 2018-11-28 | 2020-04-28 | 南京航空航天大学 | Bicycle driving assisting method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011079388A (en) * | 2009-10-06 | 2011-04-21 | Suzuki Motor Corp | Control device for vehicle |
CN102473281A (en) * | 2009-09-03 | 2012-05-23 | 本田技研工业株式会社 | Vehicle vicinity monitoring apparatus |
JP2012198656A (en) * | 2011-03-18 | 2012-10-18 | Toyota Motor Corp | Bicycle detection device and irradiation device |
CN103370249A (en) * | 2010-10-05 | 2013-10-23 | 谷歌公司 | System and method for predicting behaviors of detected objects |
CN104251993A (en) * | 2010-03-17 | 2014-12-31 | 本田技研工业株式会社 | Vehicle surroundings monitoring device |
US20150146918A1 (en) * | 2013-11-26 | 2015-05-28 | National Chung Cheng University | Video device for realtime pedaling frequency estimation |
CN105448136A (en) * | 2014-09-23 | 2016-03-30 | 福特全球技术公司 | E-bike to infrastructure or vehicle communication |
CN105644557A (en) * | 2015-12-30 | 2016-06-08 | 苏州安智汽车零部件有限公司 | Braking and steering assisting system and method considering collision avoidance intention of driver |
-
2016
- 2016-11-09 CN CN201610984676.8A patent/CN108062868B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102473281A (en) * | 2009-09-03 | 2012-05-23 | 本田技研工业株式会社 | Vehicle vicinity monitoring apparatus |
JP2011079388A (en) * | 2009-10-06 | 2011-04-21 | Suzuki Motor Corp | Control device for vehicle |
CN104251993A (en) * | 2010-03-17 | 2014-12-31 | 本田技研工业株式会社 | Vehicle surroundings monitoring device |
CN103370249A (en) * | 2010-10-05 | 2013-10-23 | 谷歌公司 | System and method for predicting behaviors of detected objects |
JP2012198656A (en) * | 2011-03-18 | 2012-10-18 | Toyota Motor Corp | Bicycle detection device and irradiation device |
US20150146918A1 (en) * | 2013-11-26 | 2015-05-28 | National Chung Cheng University | Video device for realtime pedaling frequency estimation |
CN105448136A (en) * | 2014-09-23 | 2016-03-30 | 福特全球技术公司 | E-bike to infrastructure or vehicle communication |
CN105644557A (en) * | 2015-12-30 | 2016-06-08 | 苏州安智汽车零部件有限公司 | Braking and steering assisting system and method considering collision avoidance intention of driver |
Non-Patent Citations (1)
Title |
---|
PAUL E.HEMEREN 等: "The Use of Visual Cues to Determine the Intent of Cyclists in Traffic", 《2014 IEEE INTERNATIONAL INTER-DISCIPLINARY CONFERENCE ON COGNITIVE METHODS IN SITUATION AWARENESS AND DECISION SUPPORT》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111081011A (en) * | 2018-11-28 | 2020-04-28 | 南京航空航天大学 | Bicycle driving assisting method |
CN111081011B (en) * | 2018-11-28 | 2022-04-22 | 南京航空航天大学 | Bicycle driving assisting method |
Also Published As
Publication number | Publication date |
---|---|
CN108062868B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11390276B2 (en) | Control device, control method, and non-transitory storage medium | |
CN111033510B (en) | Method and device for operating a driver assistance system, driver assistance system and motor vehicle | |
US8952799B2 (en) | Method and system for warning a driver of a vehicle about potential obstacles behind the vehicle | |
US9092977B1 (en) | Leveraging of behavior of vehicles to detect likely presence of an emergency vehicle | |
KR101891460B1 (en) | Method and apparatus for detecting and assessing road reflections | |
KR20180069274A (en) | Vehicle and method for controlling thereof | |
US20140176714A1 (en) | Collision prevention warning method and device capable of tracking moving object | |
CN108859938A (en) | The method and system that automotive vehicle emergency light for automatic driving vehicle controls | |
US20160084669A1 (en) | Vehicle and method of controlling the same | |
JP2007047914A (en) | Danger reaction point recording system and operation support system | |
JP4622749B2 (en) | Vehicle data collection device, vehicle driving support device, and vehicle safe driving support system | |
CN110481543A (en) | A kind of method and device for coping with vehicle running collision | |
US20170091872A1 (en) | Apparatus and method for evaluating driving ability, and program for causing computer to perform method | |
KR20190126024A (en) | Traffic Accident Handling Device and Traffic Accident Handling Method | |
WO2018190362A1 (en) | Method and device for detecting pedestrian around vehicle | |
CA3056611A1 (en) | Automatic warning generation system intended for the users of a road | |
CN111081045A (en) | Attitude trajectory prediction method and electronic equipment | |
US11631328B2 (en) | Determination device, determination method, and non-transitory computer readable storage medium storing determining program | |
CN105946578A (en) | Accelerator pedal control method and device and vehicle | |
US11804128B2 (en) | Target classification | |
CN109195849B (en) | Image pickup apparatus | |
CN108062868A (en) | For the bicycle detecting system and method and vehicle of vehicle | |
CN113650607A (en) | Automatic driving method and system for low-speed scene and automobile | |
JP5747593B2 (en) | Standard vehicle speed calculation device and program | |
US20230103670A1 (en) | Video analysis for efficient sorting of event data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |