CN205540783U - It is preceding to vehicle operation people's driving action prediction system - Google Patents
It is preceding to vehicle operation people's driving action prediction system Download PDFInfo
- Publication number
- CN205540783U CN205540783U CN201620067133.5U CN201620067133U CN205540783U CN 205540783 U CN205540783 U CN 205540783U CN 201620067133 U CN201620067133 U CN 201620067133U CN 205540783 U CN205540783 U CN 205540783U
- Authority
- CN
- China
- Prior art keywords
- video
- forward direction
- information
- vehicle
- acquisition camera
- 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.)
- Active
Links
Abstract
The utility model discloses an it is preceding to vehicle operation people's driving action prediction system belongs to intelligent automotive filed, and this it is preceding to vehicle operation people's driving action prediction system gathers camera, front truck by the road environment and traveles information acquisition camera and a video processor hardware platform and constitute. The road environment is gathered the camera and is responsible for gathering signal lamp, road warning mark in the road environment. The front truck travel the information acquisition camera be responsible for gathering before to vehicle, preceding to taillight, preceding to vehicle in the vehicle adjacent lane. Video processor hardware platform comprises two video processor, respectively signal lamp and road warning mark information and preceding to the relevant video information of vehicle operation in the responsible processing road environment. Through to road environmental parameter, precedingly drive action forecasting model to vehicle operation people to vehicle travel parameter and preceding analysis to vehicle information in the vehicle adjacent lane before establishhing, realize foreseeing to vehicle operation people's driving action preceding.
Description
Technical field
The present invention relates to intelligent automobile field, be specially a kind of forward direction vehicle drive people's driving behavior prognoses system.
Background technology
Along with the quick growth of China's automobile pollution, the number of non-professional driver is also being stepped up, and indirectly result in friendship
The frequent generation of interpreter's event.The reason occurred for accident, research worker is devoted to how to be reduced by effective measures always
The generation of accident, wherein the system such as collaborative, the driving safety auxiliary of bus or train route is to improve vehicle to run a kind of effective ways of safety.
Wherein, how according to road information reasonable prediction driving behavior, and to remind driver to make science decision be that driving safety is auxiliary
The key issue of auxiliary system.But Chinese scholars is predicted just for from car driver's driving behavior at present, but,
Rear car can be driven by the driving behaviors lack of standardization such as in vehicle travel process, forward direction vehicle is braked suddenly, turned to suddenly, unexpected lane-change
Sail safety to have a major impact.By contrast, there is not yet the achievement in research for forward direction vehicle drive people's driving behavior prediction.With
Time, the different algorithm and model shortage provided currently for driver's Activity recognition carries out reality to the driving intention of multiple complexity
Time, the unified algorithm identified.Along with development and the extensively application of safe assisting system for automobiles, pre-for driver's driving behavior
The real time problems surveyed will become problem in the urgent need to address.By inspection information, at present, forward direction vehicle drive people is driven
Sail in the application in terms of behavior prediction and there is not yet report.
Summary of the invention
In order to solve the problems referred to above, the present invention proposes a kind of forward direction vehicle drive people's driving behavior prognoses system, uses TI public
Department video processor DM6437 is hardware platform, based on machine vision method, with forward direction vehicle drive people when driving
Suddenly braking, turn to suddenly (including left steering and right turn), unexpected lane-change (including left lane-change and right lane-change) to drive
Behavior of sailing, as prediction object, sets up forward direction vehicle driver's driving behavior prediction based on HMM theoretical (HMM)
Model, carries out forward direction vehicle driver's driving behavior prediction.The concrete technical scheme used is as follows:
A kind of forward direction vehicle drive people's driving behavior prognoses system, adopts including road environment acquisition camera, front truck driving information
Collection photographic head, message handler;Described road environment acquisition camera for gathering signal lights in road environment, road refers to
Show flag information, and give described message handler by the information of collection;Described front truck driving information acquisition camera is used for adopting
Information of vehicles in collection forward direction vehicle, forward direction light for vehicle, forward direction vehicle adjacent lane, and give described letter by the information of collection
Breath processor;Described message handler is by the signal lights in road environment, road Warning Mark information parameter, forward direction car
, the analyzing and processing of information of vehicles in forward direction light for vehicle and forward direction vehicle adjacent lane, set up forward direction vehicle drive people and drive
Sail behavior prediction model, it is achieved forward direction vehicle drive people's driving behavior is predicted.
Preferably, described road environment acquisition camera, described front truck driving information acquisition camera all use CCD
Installed video night vision cam, is installed on vehicle front windshield.
Preferably, described message handler uses video processing hardware platform to realize, including the first video decoding electricity
Road, the first video processing circuits, the second video decoding circuit, the second video processing circuits and power circuit;
Described first video decoding circuit passes through road environment acquisition camera video line and described road environment acquisition camera phase
Even, the information to road environment acquisition camera collection is decoded processing;Described first video processing circuits is to described first
The decoded video information of video decoding circuit processes, and mutual with the second video processing circuits;
Described second video decoding circuit is gathered with described front truck driving information by front truck driving information acquisition camera video line
Photographic head is connected, and is decoded processing to the information of described front truck driving information acquisition camera collection;At described second video
The described second decoded video information of video decoding circuit is processed by reason circuit, and by setting up forward direction vehicle drive
Forward direction vehicle drive people's driving behavior is predicted by people's driving behavior forecast model;
Vehicle-mounted 12V Power convert is 3.3V, 1.8V, 1.2V by described power circuit, for system power supply.
Preferably, described first video decoding circuit, described second video decoding circuit all include decoding chip
TVP5150 and peripheral circuit;Described first video processing circuits, described second video processing circuits all include video processor
DM6437, DDR2 memorizer MT47H64M16BT, FLASH memory SG29GL256N, described DDR2 deposits
Reservoir MT47H64M16BT, described FLASH memory SG29GL256N all with described video processor DM6437
It is connected.
Preferably, described power circuit includes LM2940, TPS54310;Vehicle-mounted 12V power supply is through LM2940
Chip is converted to 5V power supply, and 5V power supply is respectively converted into 3.3V, 1.8V, 1.2V power supply through 3 TPS54310 again;
Described 3.3V is I/O port and the 3.3V system power supply of video processor DM6437, and 1.8V is DDR2 memorizer
MT47H64M16BT powers, and 1.2V is that the kernel of video processor DM6437 is powered.
Preferably, described first video decoding circuit, the first video processing circuits, the second video decoding circuit,
Two video processing circuitss and power circuit are arranged on one piece of circuit board, and described circuit board is arranged in a cuboid shell
Portion, described cuboid shell is arranged over 1 road environment acquisition camera video line input groove and 1 front truck travels letter
Breath acquisition camera video line input groove, described road environment acquisition camera video line, described front truck driving information gather
Camera video line inputs groove, front truck driving information acquisition camera video from road environment acquisition camera video line respectively
Line input groove passes.
Based on above-mentioned prognoses system, the invention allows for a kind of forward direction vehicle drive people's driving behavior Forecasting Methodology, including such as
Lower step:
1) road environment acquisition camera is utilized to gather the signal lights in road environment, road Warning Mark information;Utilize front truck
Driving information acquisition camera gathers information of vehicles in forward direction vehicle, forward direction light for vehicle, forward direction vehicle adjacent lane;
2) utilize video processing hardware platform that road environment acquisition camera, front truck driving information acquisition camera are gathered
Information is analyzed processing;
The method of described process includes: for the imperfect and noise jamming of acquired vehicle running orbit point sequence, uses base
The method removing imperfect track sets in path length;Based on the vehicle running orbit point sequence with time order and function relation
Feature, sets up vehicle running orbit point sequence polar vehicle running orbit eigenvalue method for expressing;Utilize the information gathered
Build forward direction vehicle drive people's driving behavior forecast model based on HMM.
Preferably, described forecast model uses based on HMM the Theory Construction, and model expression is:
λ=(N, M, π, A, B), wherein:
S: forward direction vehicle drive people's driving behavior state, S=(S1,S2,…SN), t status is qt, qt∈ S,
This project status number N=5, wherein, S1For braking action, S2For left steering behavior, S3For right turn behavior, S4For a left side
Lane-change behavior, S5For right-hand rotation lane-change behavior;
V: observation sequence, V=(v1,v2,…vM), t observed events is Ot, this project observation number M=11, its
In, v1For footpath, forward direction vehicle pole, v2For forward direction vehicle polar angle, v3For forward direction vehicle left steering lamp, v4Turn right for forward direction vehicle
To lamp, v5For forward direction vehicle braking lamp, v6For signal lights red light, v7For signal lights green light, v8For signal lights amber light, v9For
Road left steering mark, v10For road right turn mark, v11Keep straight on for road and indicate;
π: forward direction vehicle drive people's driving behavior initial state probabilities vector, π=(π1,π2,…πN), wherein
πi=P (q1=Si);
A: state-transition matrix, i.e. forward direction vehicle drive people driving behavior state-transition matrix, A={aij}N′N, wherein,
aij=P (qt+1=Sj|qt=Si), 1≤i, j≤N;
B: observed events probability distribution matrix, i.e. different forward direction vehicle drive people drive row each observer state under at S to be occurred
Probability, B={bjk}N′M, wherein, bjk=P [Ot=vk|qt=Sj], 1≤j≤N, 1≤k≤M.
Preferably, described based on path length remove imperfect track sets method particularly as follows:
Vehicle run rail use vehicle multiple frame of video center-of-mass coordinate point (x, y) represents, for forward direction vehicle, if the i-th frame
Time its centroid position coordinate be (xi,yi), can be obtained by an initiation sequence being made up of l coordinate points after l frame
Linitial={ (x1,y1),(x2,y2)…,(xl,yl)};Then the center-of-mass coordinate point waiting frame period sampling to obtain vehicle is carried out, then
Track sets L translates into a point sequence with time order and function relation;During vehicle runs the tracking of rail, statistics
Number l of tracing point on acquired track sets L0If, l0Less than the threshold value set, then regard this sequence as imperfect
Track sets, abandon it is carried out follow-up process.
Preferably, described vehicle running orbit point sequence polar vehicle running orbit eigenvalue method for expressing is concrete
For:
It is located at the track of vehicle point sequence l of acquisition0In a certain tracing point coordinate be (xi,yi), by polar coordinate transform, should
Tracing point coordinate is transformed to (ρi,θi), wherein ρiContain forward direction vehicle and the spacing information from car, θiContain forward direction vehicle
Relative to from the deflection information of car vehicle;Utilize (ρi,θi) forward direction vehicle movement parameter is described;According to sampling time interval
With sequence l0In two neighboring pole coordinate vehicle running orbit characteristic value sequence value [ρi,ρi+1] and [θi,θi+1] (i ∈ [1, l-1]), i.e.
Forward direction vehicle movement parameter can be tried to achieve.
Beneficial effects of the present invention:
(1) based on machine vision method, to forward direction vehicle drive people brake suddenly when driving, turn to suddenly, dash forward
So lane-change driving behavior is predicted, and carries out early warning for rear car driver, it is to avoid the generation of vehicle accident.
(2) based on having the vehicle running orbit point sequence feature of time order and function relation, a kind of vehicle running orbit point sequence is proposed
Arrange polar vehicle running orbit eigenvalue method for expressing, run rail according to frame of video sampling time interval and polar coordinate vehicle
Mark point sequence calculates forward direction vehicle movement parameter, solves forward direction vehicle movement parameter identification main gene and cannot pass through sensor
The problem of extracting directly.
(3) for imperfect problem and the noise jamming problem of vehicle running orbit point sequence, propose a kind of long based on track
The removal imperfect track sets method of degree, improves precision and efficiency that system processes.
(4), during the processor device of the present invention is placed on a cuboid shell, modularity and integrated level are higher, it is simple to install and
Popularization and application.
(5) HMM (HMM) is utilized to set up driver's forecast model, it is possible to prediction front vehicles is driven exactly
Sail the driving behavior of people.
Accompanying drawing explanation
Fig. 1 is present system structural representation.
Fig. 2 is video processing hardware platform distribution schematic diagram of the present invention.
Fig. 3 is video processing hardware platform circuitry structural representation of the present invention.
Fig. 4 is video processing hardware platform circuitry schematic diagram of the present invention.
Labelling in figure: 1 is road environment acquisition camera, 2 is front truck driving information acquisition camera, and 3 is video processor
Hardware platform, 4 is road environment acquisition camera video line, and 5 is front truck driving information acquisition camera video line, and 6 are
Road environment acquisition camera video line input groove, 7 is that front truck driving information acquisition camera video line inputs groove, and 8 for long
Cube shell.
Detailed description of the invention
The present invention proposes a kind of forward direction vehicle drive people's driving behavior prognoses system, and this forward direction vehicle drive people's driving behavior is pre-
Examining system is by road environment acquisition camera 1, front truck driving information acquisition camera 2 and a video processing hardware platform 3
Composition.Road environment acquisition camera 1 is responsible for signal lights, the road Warning Mark gathering in road environment.Front truck travels letter
Breath acquisition camera 2 is responsible for gathering vehicle in forward direction vehicle, forward direction light for vehicle, forward direction vehicle adjacent lane.Video processing
Device hardware platform 3 is made up of two video processors, is each responsible for processing signal lights and road Warning Mark letter in road environment
Breath and forward direction vehicle run associated video information.By to road environment parameter, forward direction vehicle driving parameters and forward direction vehicle
The analysis of information of vehicles in adjacent lane, sets up forward direction vehicle drive people's driving behavior forecast model, it is achieved drive forward direction vehicle
Sail people's driving behavior to be predicted.
The present invention is directed to the imperfect and noise jamming of acquired vehicle running orbit point sequence, it is also proposed that a kind of long based on track
The removal imperfect track sets method of degree.Directly cannot be carried by sensor for forward direction vehicle movement parameter identification main gene
The problem taken, based on the vehicle running orbit point sequence feature with time order and function relation, it is also proposed that a kind of vehicle running orbit
Point sequence polar vehicle running orbit eigenvalue method for expressing, transports according to frame of video sampling time interval and polar coordinate vehicle
Row tracing point sequence calculates forward direction vehicle movement parameter.The present invention is with footpath, forward direction vehicle pole, forward direction vehicle polar angle, forward direction car
Left steering lamp, forward direction vehicle right turn lamp, forward direction vehicle braking lamp, signal lights red light, signal lights green light, signal lights are yellow
Lamp, road left steering mark, road right turn mark, road are kept straight on and are indicated as identification main gene, with forward direction vehicle drive
Member braking action, left steering behavior, right turn behavior, left lane-change behavior, right-hand rotation lane-change behavior occur probability as output,
Build forward direction vehicle drive people's driving behavior forecast model based on HMM.
In describing the invention, it is to be understood that term " " center ", " longitudinally ", " laterally ", " on ", D score,
"front", "rear", "left", "right", " vertically ", " level ", " top ", " end ", " interior ", " outward " etc. instruction orientation or
Position relationship is based on orientation shown in the drawings or position relationship, is for only for ease of the description present invention and simplifies description, and not
It is to indicate or imply that the device of indication or element must have specific orientation, with specific azimuth configuration and operation, the most not
It is understood that as limitation of the present invention.
With reference to the accompanying drawings and combine example and the design of the present invention, specific works process row are understood be fully described by.Obviously,
Described embodiment is a part of embodiment of the present invention rather than whole embodiment, based on the embodiment of the present invention, this
Other embodiments that skilled person is obtained on the premise of not paying creative work, belong to scope.
As shown in Figures 1 to 4, a kind of forward direction vehicle drive people's driving behavior prognoses system that the present invention proposes is by road environment
Acquisition camera 1, front truck driving information acquisition camera 2 and a video processing hardware platform 3 form.
Described road environment acquisition camera: use CCD installed video night vision cam, be arranged on vehicle front windshield,
It is responsible for gathering signal lights, road Warning Mark in road environment.
Described front truck driving information acquisition camera: use CCD installed video night vision cam, be arranged on vehicle front windshield glass
On glass, it is responsible for gathering vehicle in forward direction vehicle, forward direction light for vehicle, forward direction vehicle adjacent lane.
Described video processing hardware platform: have the shell of 1 cuboid, as video processing hardware platform shell 8,
It is arranged over 1 road environment acquisition camera video line input groove 6 and 1 at video processing hardware platform shell 8
Front truck driving information acquisition camera video line 5 inputs groove 7.
1 video processing circuit board it is provided with in video processing hardware platform shell 8.This video processing circuit board is by first
Video decoding circuit, the first video processing circuits, the second video decoding circuit, the second video processing circuits composition.
The first video decoding circuit on this video processing circuit board is provided with 1 road environment acquisition camera video line input
Interface, is connected with road environment acquisition camera 1 by road environment acquisition camera video line 4, and this road environment gathers
Camera video line input interface is positioned at the road environment acquisition camera video line above video processing hardware platform shell 8
At input groove 7.
The first video processing circuits on this video processing circuit board is by the first video processor DM6437 and peripheral circuit group thereof
Become, be responsible for the video information of road environment acquisition camera collection is processed.
The second video decoding circuit on this video processing circuit board is provided with 1 front truck driving information acquisition camera video line
Input interface, is connected with front truck driving information acquisition camera 2 by front truck driving information acquisition camera video line 5, should
Front truck driving information acquisition camera video line input interface is positioned at the front truck above video processing hardware platform shell and travels letter
At breath acquisition camera video line input groove 7.
The second video processing circuits on this video processing circuit board is by the second video processor DM6437 and peripheral circuit group thereof
Become, be responsible for the video information of front truck driving information acquisition camera collection being processed, simultaneously by forward direction vehicle drive people
Forward direction vehicle drive people's driving behavior is predicted by driving behavior forecast model.
Power circuit on this video processing circuit board be responsible for by vehicle-mounted 12V Power convert be 3.3V needed for video processor,
1.8V, 1.2V power supply, for system power supply.
The first video decoding circuit on this video processing circuit board is by the first video decoding chip TVP5150 and peripheral circuit thereof
Composition, is responsible for being decoded the analog video signals such as the signal lights of road environment acquisition camera collection, road Warning Mark,
Being converted to digital video signal, output is to the first video video processor DM6437, by the first video video processor
Video image is processed by DM6437.
The first video processing circuits on this video processing circuit board by a DDR2 memorizer MT47H64M16BT,
One FLASH memory SG29GL256N and the first video processor DM6437 composition.Oneth DDR2 memorizer
MT47H64M16BT is for storing the data in road environment information gathering algorithm, the first FLASH memory
SG29GL256N is used for storing road environment information gathering algorithm routine, and the first video processor DM6437 is responsible for road
The video information of environment acquisition camera collection processes.
The second video decoding circuit on this video processing circuit board is by the second video decoding chip TVP5150 and peripheral circuit thereof
Composition, is responsible for being decoded the forward direction vehicle traveling information analog video signal of front truck driving information acquisition camera collection,
Being converted to digital video signal, output is to the second video video processor DM6437, by the second video video processor
Video image is processed by DM6437.
The second video processing circuits on this video processing circuit board by the 2nd DDR2 memorizer MT47H64M16BT,
Two FLASH memory SG29GL256N and the second video processor DM6437 composition.2nd DDR2 memorizer
MT47H64M16BT is used for storing forward direction vehicle information collection algorithm and forward direction vehicle drive people's driving behavior is calculated in advance
Data in method.Second FLASH memory SG29GL256N is used for storing forward direction vehicle information collection algorithm and front
To vehicle drive people's driving behavior prediction algorithm program.Second video processor DM6437 is responsible for gathering front truck driving information
The forward direction automobile video frequency information of camera collection processes, simultaneously by forward direction vehicle drive people's driving behavior forecast model pair
Forward direction vehicle drive people's driving behavior is predicted.
Power circuit on this video processing circuit board is made up of LM2940, TPS54310, and vehicle-mounted 12V power supply passes through
LM2940 chip, is converted to 5V power supply, and 5V power supply is being converted to 3.3V, 1.8V, 1.2V through 3 TPS54310
Power supply.Wherein 3.3V is video processor I/O port and 3.3V system power supply, and 1.8V is DDR2 storage chip
MT47H64M16BT powers, and 1.2V is that video processor kernel is powered.
The imperfect track sets method of removal based on path length that the present invention proposes is as follows:
Operation rail can at the center-of-mass coordinate point of multiple frame of video, (x y) represents vehicle with vehicle.For forward direction vehicle, if the
During i frame, the coordinate of its centroid position is (xi,yi), can be obtained by an initiation sequence being made up of l coordinate points after l frame
Linitial={ (x1,y1),(x2,y2)…,(xl,yl), carry out the center-of-mass coordinate point waiting frame period sampling to obtain vehicle, then track
Sequence L translates into a point sequence with time order and function relation.During vehicle runs the tracking of rail, statistics is obtained
Number l of tracing point on the track sets L taken0If, l0Less than the threshold value set, then regard this sequence as incomplete rail
Mark sequence, abandons it is carried out process subsequently.
Vehicle running orbit point sequence polar coordinate eigenvalue method for expressing of the present invention is as follows:
Video has time order and function relation vehicle running orbit point sequence produce directional information and with the range information from car
Forward direction vehicle movement parameter can be described well, be located at tracing point sequence l of acquisition0In a certain tracing point coordinate be
(xi,yi), by polar coordinate transform, this tracing point coordinate is transformed to (ρi,θi), wherein ρiFor footpath, vehicle pole, before containing
To vehicle and the spacing relevant information from car, θiFor vehicle polar angle, contain forward direction vehicle relative to the deflection from car vehicle
Information.According to sampling time interval and sequence l0In two neighboring pole coordinate vehicle running orbit characteristic value sequence value [ρi,ρi+1] and
[θi,θi+1], (i ∈ [1, l-1]), forward direction vehicle movement parameter can be tried to achieve.
Forward direction vehicle drive people's driving behavior forecast model based on HMM of the present invention is as follows:
Theoretical based on HMM, set up forward direction vehicle driver driving behavior HMM forecast model λ=(N, M, π, A, B),
Wherein:
Forward direction vehicle drive people driving behavior state S:S=(S1,S2,…SN), t status is qt, qt∈ S, this
Project status number N=5, wherein, S1For braking action, S2For left steering behavior, S3For right turn behavior, S4Change for a left side
Road behavior, S5For right-hand rotation lane-change behavior;
Observation sequence V:V=(v1,v2,…vM), t observed events is Ot, this project observation number M=11, wherein,
v1For footpath, forward direction vehicle pole, v2For forward direction vehicle polar angle, v3For forward direction vehicle left steering lamp, v4For forward direction vehicle right turn lamp,
v5For forward direction vehicle braking lamp, v6For signal lights red light, v7For signal lights green light, v8For signal lights amber light, v9Left for road
Turn marking, v10For road right turn mark, v11Keep straight on for road and indicate;
π: forward direction vehicle drive people's driving behavior initial state probabilities vector, π=(π1,π2,…πN), wherein
πi=P (q1=Si);
A: state-transition matrix, i.e. forward direction vehicle drive people driving behavior state-transition matrix, A={aij}N′N, wherein,
aij=P (qt+1=Sj|qt=Si), 1≤i, j≤N;
B: observed events probability distribution matrix, i.e. different forward direction vehicle drive people drive row each observer state under at S to be occurred
Probability, B={bjk}N′M, wherein, bjk=P [Ot=vk|qt=Sj], 1≤j≤N, 1≤k≤M.
The above is only used for describing technical solution of the present invention and specific embodiment, the protection domain being not intended to limit the present invention,
Should be appreciated that on the premise of flesh and blood of the present invention and principle, changed, improve or equivalent etc.
Fall within protection scope of the present invention.
Claims (6)
1. forward direction vehicle drive people's driving behavior prognoses system, it is characterised in that include road environment acquisition camera (1),
Front truck driving information acquisition camera (2), message handler;Described road environment acquisition camera (1) is used for gathering road
Signal lights in environment, road Warning Mark information, and give described message handler by the information of collection;Described front garage
Sail information gathering photographic head (2) to be used for gathering information of vehicles in forward direction vehicle, forward direction light for vehicle, forward direction vehicle adjacent lane,
And give described message handler by the information of collection;Described message handler is by the signal lights in road environment, road
In Warning Mark information parameter, forward direction vehicle, forward direction light for vehicle and forward direction vehicle adjacent lane at the analysis of information of vehicles
Reason, sets up forward direction vehicle drive people's driving behavior forecast model, it is achieved be predicted forward direction vehicle drive people's driving behavior.
A kind of forward direction vehicle drive people's driving behavior prognoses system the most according to claim 1, it is characterised in that described
Road environment acquisition camera (1), described front truck driving information acquisition camera (2) all use CCD installed video night vision
Photographic head, is installed on vehicle front windshield.
A kind of forward direction vehicle drive people's driving behavior prognoses system the most according to claim 1, it is characterised in that described
Message handler uses video processing hardware platform (3) to realize, including the first video decoding circuit, the first Video processing electricity
Road, the second video decoding circuit, the second video processing circuits and power circuit;
Described first video decoding circuit is imaged with described road environment collection by road environment acquisition camera video line (4)
Head (1) is connected, and the information gathering road environment acquisition camera (1) is decoded processing;Described first Video processing
The described first decoded video information of video decoding circuit is processed by circuit, and mutual with the second video processing circuits;
Described second video decoding circuit is by front truck driving information acquisition camera video line (5) and described front truck driving information
Acquisition camera (2) is connected, and the information gathering described front truck driving information acquisition camera (2) is decoded processing;
The described second decoded video information of video decoding circuit is processed by described second video processing circuits, and by building
Forward direction vehicle drive people's driving behavior is predicted by vertical forward direction vehicle drive people's driving behavior forecast model;
Vehicle-mounted 12V Power convert is 3.3V, 1.8V, 1.2V by described power circuit, for system power supply.
A kind of forward direction vehicle drive people's driving behavior prognoses system the most according to claim 3, it is characterised in that described
First video decoding circuit, described second video decoding circuit all include decoding chip TVP5150 and peripheral circuit;Described
One video processing circuits, described second video processing circuits all include video processor DM6437, DDR2 memorizer
MT47H64M16BT, FLASH memory SG29GL256N, described DDR2 memorizer MT47H64M16BT, institute
State FLASH memory SG29GL256N to be all connected with described video processor DM6437.
A kind of forward direction vehicle drive people's driving behavior prognoses system the most according to claim 4, it is characterised in that described
Power circuit includes LM2940, TPS54310;Vehicle-mounted 12V power supply is converted to 5V power supply, 5V through LM2940 chip
Power supply is respectively converted into 3.3V, 1.8V, 1.2V power supply through 3 TPS54310 again;Described 3.3V is video processor
The I/O port of DM6437 and 3.3V system power supply, 1.8V is that DDR2 memorizer MT47H64M16BT powers, and 1.2V is
The kernel of video processor DM6437 is powered.
6., according to a kind of forward direction vehicle drive people's driving behavior prognoses system described in claim 3 or 4 or 5, its feature exists
In, described first video decoding circuit, the first video processing circuits, the second video decoding circuit, the second video processing circuits
Being arranged on one piece of circuit board with power circuit, described circuit board is arranged on a cuboid enclosure, described cuboid
Shell is arranged over 1 road environment acquisition camera video line input groove (6) and 1 front truck driving information collection shooting
Head video line input groove (7), described road environment acquisition camera video line (4), described front truck driving information collection are taken the photograph
As head video line (5) respectively from road environment acquisition camera video line input groove (6), front truck driving information collection shooting
Head video line input groove (7) passes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620067133.5U CN205540783U (en) | 2016-01-22 | 2016-01-22 | It is preceding to vehicle operation people's driving action prediction system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620067133.5U CN205540783U (en) | 2016-01-22 | 2016-01-22 | It is preceding to vehicle operation people's driving action prediction system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN205540783U true CN205540783U (en) | 2016-08-31 |
Family
ID=56769137
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201620067133.5U Active CN205540783U (en) | 2016-01-22 | 2016-01-22 | It is preceding to vehicle operation people's driving action prediction system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN205540783U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105528593A (en) * | 2016-01-22 | 2016-04-27 | 江苏大学 | Forward vehicle driver driving behavior prediction system and prediction method |
CN106600427A (en) * | 2016-12-22 | 2017-04-26 | 安徽保腾网络科技有限公司 | Novel vehicle insurance system |
-
2016
- 2016-01-22 CN CN201620067133.5U patent/CN205540783U/en active Active
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105528593A (en) * | 2016-01-22 | 2016-04-27 | 江苏大学 | Forward vehicle driver driving behavior prediction system and prediction method |
CN105528593B (en) * | 2016-01-22 | 2020-03-31 | 江苏大学 | Forward vehicle driver driving behavior prediction system and prediction method |
CN106600427A (en) * | 2016-12-22 | 2017-04-26 | 安徽保腾网络科技有限公司 | Novel vehicle insurance system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105528593A (en) | Forward vehicle driver driving behavior prediction system and prediction method | |
CN110688992B (en) | Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle | |
CN109242251B (en) | Driving behavior safety detection method, device, equipment and storage medium | |
CN105711586A (en) | Front collision avoiding system based on driving behavior of front vehicle driver and vehicle collision avoiding algorithm | |
CN110356325B (en) | Urban traffic passenger vehicle blind area early warning system | |
CN107139919B (en) | Self-protection method for vehicle anti-rear collision early warning | |
CN102541061B (en) | Micro intelligent vehicle based on visual and auditory information | |
CN205573939U (en) | It is preceding to collision avoidance system based on it is preceding to action of driving of vehicle operation people | |
CN108133644A (en) | A kind of evaluation system and evaluation method of automobile driver examination | |
CN113487874B (en) | System and method for collecting, identifying and classifying following behavior scene data | |
CN101941438B (en) | Intelligent detection control device and method of safe interval | |
CN105225474A (en) | Based on the traffic collision early warning system of intelligent wearable device | |
CN207624060U (en) | A kind of automated driving system scene floor data acquisition system | |
CN110060547A (en) | A kind of intelligent control and evaluation system and method driving the examination vehicle of subject three | |
CN105530061A (en) | Driving behavior prediction system of forward direction vehicle driver based on fusion of vehicle networking and image | |
CN103308056A (en) | Road marking detection method | |
CN101016052A (en) | Warning method and system for preventing deviation for vehicle on high standard highway | |
CN203332106U (en) | Automobile warning anti-collision system based on monocular vision | |
CN207301793U (en) | A kind of unmanned intelligent vehicle of image recognition processing | |
CN102778223A (en) | License number cooperation target and monocular camera based automobile anti-collision early warning method | |
CN108819938A (en) | Parking system and automobile | |
CN108791038A (en) | A kind of intelligent automotive light system and control method based on shadow casting technique | |
CN105438183A (en) | Recognition device and method for radical driving state of driver | |
CN203172620U (en) | Device for lane changing safety judging and forewarning for driver | |
CN115311633B (en) | Method and device for detecting illegal boarding and alighting of vehicle, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |