CN107364406A - The installation stand and its control method of a kind of vehicle-mounted binocular vision system - Google Patents
The installation stand and its control method of a kind of vehicle-mounted binocular vision system Download PDFInfo
- Publication number
- CN107364406A CN107364406A CN201710720969.XA CN201710720969A CN107364406A CN 107364406 A CN107364406 A CN 107364406A CN 201710720969 A CN201710720969 A CN 201710720969A CN 107364406 A CN107364406 A CN 107364406A
- Authority
- CN
- China
- Prior art keywords
- camera
- vehicle
- mrow
- msub
- height
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R11/04—Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R2011/0042—Arrangements for holding or mounting articles, not otherwise provided for characterised by mounting means
- B60R2011/008—Adjustable or movable supports
- B60R2011/0084—Adjustable or movable supports with adjustment by linear movement in their operational position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R11/00—Arrangements for holding or mounting articles, not otherwise provided for
- B60R2011/0042—Arrangements for holding or mounting articles, not otherwise provided for characterised by mounting means
- B60R2011/008—Adjustable or movable supports
- B60R2011/0085—Adjustable or movable supports with adjustment by rotation in their operational position
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of installation stand of vehicle-mounted binocular vision system, including:Base, its top are hollow structure;Support base, it is set in the base top and can be axially moved along the base;Rack, it is arranged on the base upper inside wall opposite sides;Motor, it connects the support base lower end, and the gear of the motor engages with the rack, for driving the support base to be axially moved along the base.The installation stand of vehicle-mounted binocular vision system of the present invention, the height of binocular camera can be adjusted in real time, improve measurement accuracy.The present invention also provides a kind of control method of vehicle-mounted binocular vision system installation stand, it uses BP neural network algorithm, adjust the height of binocular camera in real time in vehicle operation, make the vertical height of the camera lens of two cameras identical, realize the accurate measurement of road pavement information.
Description
Technical field
The present invention relates to road Identification technical field, and more particularly, the present invention relates to a kind of vehicle-mounted binocular vision system
Installation stand and its control method.
Background technology
With the fast development of China's economy, requirement more and more higher of the people to vehicle riding comfort, and road surface is recessed
Convex injustice directly influences the riding comfort of vehicle, is relaxed although can improve vehicle ride by the active control of suspension system
Adaptive, but the uneven detection of running car road surface ahead turns into the factor of limitation suspension system active control development.
In the prior art, binocular vision system can be used for Uneven road detection, utilizes binocular camera solid
With calculating, road surface depth information and threedimensional model can be obtained in real time, realizes the detection of road surface vertically profiling.But pacify on vehicle
Fill binocular vision system when, different automobile types then need different height and luffing angle preferably to realize pavement detection, also because
This results in the need for the binocular measuring system of different model, improves product cost;If measured using the binocular of same model
System, after being installed in different automobile types, larger measurement error can be produced when carrying out pavement detection, influences traffic safety;Work as road
When face injustice or carload change make the vertical height difference of two cameras, measurement can be equally set to produce larger error.
The content of the invention
The purpose of the present invention is to have designed and developed a kind of installation stand of vehicle-mounted binocular vision system, can be adjusted in real time double
The height of mesh camera, improve measurement accuracy.
Another object of the present invention is to design and develop a kind of control method of vehicle-mounted binocular vision system installation stand, energy
Enough height for adjusting binocular camera in real time in vehicle operation, make the vertical height of the camera lens of two cameras identical, satisfy the need
Face information carries out more accurate detection.
Technical scheme provided by the invention is:
A kind of installation stand of vehicle-mounted binocular vision system, including:
Base, its top are hollow structure;
Support base, it is set in the base top and can be axially moved along the base;
Rack, it is arranged on the base upper inside wall opposite sides;
Motor, it connects the support base lower end, and the gear of the motor engages with the rack, for driving the branch
Support seat is axially moved along the base.
Preferably, in addition to:
Slide rail, it includes two slideways be arrangeding in parallel, and the base bottom is connected with the slideway and being capable of edge
The slide rail is axially moved;
Camera carriage, itself and the support seat hinge, it can be along the slide rail radial rotary.
Preferably, the base includes:
Bolt hole, it is arranged on the base bottom corner;
Bolt, it passes through the slideway and bolt hole;
Nut, it screws in described bolt one end, for fastening the base and slideway.
Preferably, the camera carriage includes:
Supporting plate, it is arranged on the camera carriage upper end, for supporting camera;
Support bar, its be vertically set on below the supporting plate and with the support seat hinge, can the slide rail radially
Rotation, the support bar lower end is provided with blind hole;
Fixed plate, it is set in parallel in above the supporting plate and fastened with the supporting plate, for fixing the camera.
Preferably, the support base includes:
U-shaped groove, it is arranged on the support base upper end;
Through hole, it is arranged on the U-shaped groove side and corresponding with the blind hole;
Angular adjustment knob, it is screwed in the blind hole through the through hole.
Preferably, rubber blanket is correspondingly arranged on above the supporting plate and below fixed plate, for increasing the camera
Resistance to sliding.
Preferably, the base is two;The camera is ccd video camera.
Preferably, in addition to:
Vibrating sensor, it is arranged on each wheel hub of vehicle, for detecting amplitude and vibration frequency when vehicle travels;
Velocity sensor, it is arranged on wheel drive axle, for measuring Vehicle Speed;
Infrared sensor, it is separately positioned on the camera, for detecting the difference in height between camera;
Control system, it connects vibrating sensor, velocity sensor, infrared sensor and the motor, for receiving
State the detection data of vibrating sensor, velocity sensor and infrared sensor and control the motor to work.
Correspondingly, the present invention also provides a kind of control method of vehicle-mounted binocular vision system installation stand, when vehicle travels
When the height of two cameras is regulated and controled based on BP neural network, comprise the following steps:
Step 1: according to the sampling period, the difference in height Δ h between camera, the amplitude of vehicle traveling are gathered by sensor
A, vibration frequency H and vehicle velocity V;
Step 2: difference in height Δ h, amplitude A, vibration frequency H and the vehicle velocity V of vehicle traveling are standardized successively,
Determine input layer vector x={ x of three layers of BP neural network1,x2,x3,x4};Wherein, x1Difference in height coefficient between camera, x2
For the peak factor of vehicle traveling, x3For vehicle ride coefficient of frequency, x4For speed coefficient;
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to intermediate layer, the intermediate layer vector y={ y1,y2,…,ym};During m is
Interbed node number;
Step 4: obtain output layer vector z={ z1,z2};Wherein, z1For the height adjustment factor of first camera, z2For
The height adjustment factor of two cameras, makes
Wherein, z1 i、z2 iRespectively ith sample cycle output layer vector parameter, hmaxMaximum for the camera of setting is high
Degree,Respectively the i+1 sampling period when first camera and second camera height;And
In the step 2, difference in height Δ h, amplitude A, vibration frequency H and the vehicle velocity V of vehicle traveling are standardized
Formula is:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter Δ h, A, H, V, j=1,2,3,4;Xjmax
And XjminMaximum and minimum value in respectively corresponding measurement parameter.
Preferably, in the step 1, under initial operating state, the height of first camera and the height of second camera
Meet empirical value:
Wherein,The respectively elemental height of first camera and second camera;hmaxFor the maximum of the camera of setting
Highly;hcFor bodywork height;d0It is first camera and first camera along slide rail axial distance;θ is camera mirror plane and horizontal direction
Angle.
The present invention at least possesses following beneficial effect:
(1) the installation stand of vehicle-mounted binocular vision system of the present invention, the height of binocular camera can be adjusted in real time,
Improve measurement accuracy.
(2) adjustable, the angle of camera mirror plane and horizontal direction of the distance between two cameras of the installation stand
It is adjustable, more multi-vehicle-type is can adapt to, installation accuracy is improved while reducing production cost.
(3) control method of vehicle-mounted binocular vision system installation stand of the present invention, can be in vehicle operation
In, the difference in height between camera is gathered according to sensor, amplitude, vibration frequency and the speed of vehicle traveling adjust two in real time
The height of individual camera, realize that road pavement information more accurately detects.
Brief description of the drawings
Fig. 1 is the positive structure diagram of the installation stand of vehicle-mounted binocular vision system of the present invention.
Fig. 2 is the overlooking the structure diagram of the installation stand of vehicle-mounted binocular vision system of the present invention.
Fig. 3 is the side structure schematic view of the installation stand of vehicle-mounted binocular vision system of the present invention.
Fig. 4 is the base mounting structure schematic diagram of the installation stand of vehicle-mounted binocular vision system of the present invention.
Fig. 5 is that the motor gear of the installation stand of vehicle-mounted binocular vision system of the present invention and the structure of rack engagement are shown
It is intended to.
Fig. 6 is that the motor of the installation stand of vehicle-mounted binocular vision system of the present invention arranges schematic diagram.
Fig. 7 is the support base of installation stand and the attachment structure of camera carriage of vehicle-mounted binocular vision system of the present invention
Schematic diagram.
Fig. 8 is the partial enlarged drawing of a-quadrant in Fig. 7.
Fig. 9 is the camera carriage of installation stand and the attachment structure of fixed plate of vehicle-mounted binocular vision system of the present invention
Schematic diagram.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings, to make those skilled in the art with reference to specification text
Word can be implemented according to this.
The present invention can have many different forms to implement, and should not be construed as limited to the embodiment illustrated again, phase
Instead, there is provided these embodiments so that the disclosure will be thorough and complete.In the accompanying drawings, for clarity, structure can be exaggerated
With the size and relative size in region.
As shown in figs 1-9, the present invention provides a kind of installation stand of vehicle-mounted binocular vision system, including:Base 110, its
Top is hollow structure;Support base 120, it is set in the top of base 110 and can be axially moved along the base 110;
Rack 114, it is arranged on the upper inside wall opposite sides of base 110;Motor 121, it connects the lower end of support base 120,
The gear 1211 of the motor 121 engages with the rack 111, for driving the support base 120 along the axial direction of base 110
Motion.
In the present embodiment, in addition to slide rail 130, it includes two slideways be arrangeding in parallel 131, the bottom of base 110
It is connected and can be axially moved along the slide rail 130 with the slideway 131, the slide rail 130 is fixedly installed on the car
Top;Camera carriage 140, it is be hinged with the support base 120, and it can be along the radial rotary of slide rail 130.The base 110
Including:Bolt hole 111, it is arranged on the bottom four corners of base 110;Bolt 112, it passes through the slideway 131 and bolt hole
111;Nut 113, it screws in described one end of bolt 112, for fastening the base 110 and slideway 131, when needing to adjust two
During horizontal range between camera, outside loosening nut 113 so that base 120 can be axially moved along the slide rail 130, be adjusted
Save after needing position, tightening nut 113, because effect slide rail 130 and the base 110 of frictional force are fixed, to realize two cameras
The regulation and fixation of 200 horizontal cardinal distances.The camera carriage 140 includes:Supporting plate 141, it is arranged on the camera carriage 140
Upper end, for supporting camera 200;Support bar 142, its be vertically set on the lower section of the supporting plate 141 and with the support base 120
It is be hinged, can the radial rotary of slide rail 130, the lower end of support bar 142 is provided with blind hole 1421;Fixed plate 143, its is parallel
It is arranged on the top of the supporting plate 142 and is fastened with the supporting plate 142, for fixing the camera 200, in the present embodiment,
The supporting plate 142 and fixed plate 143 are fastened by screw bolt and nut, it should be appreciated that supporting plate 142 and fixed plate 143
Between fastener be not limited to said structure, as long as fastening requirements can be met.The support base 120 includes:It is U-shaped recessed
Groove 122, it is arranged on the upper end of support base 120;Through hole 123, its be arranged on the side of U-shaped groove 122 and with it is described blind
The correspondence of hole 1421;Angular adjustment knob 124, it is screwed in the blind hole 1421, it is necessary to adjust camera through the through hole 123
200 with the angle of horizontal direction when, unscrew angular adjustment knob 124, enable support bar 142 along the radial rotary of slide rail 130, rotation
Its end of thread is set to withstand in the blind hole 1421 of the lower end of support bar 142 to angular adjustment knob 124 when needing angle, is screwed, due to
The effect of frictional force, support bar 142 and support base 120 are relatively fixed, and realize the regulation of the minute surface of camera 200 and horizontal direction angle
With fixation.The top of supporting plate 141 and the lower section of fixed plate 143 are correspondingly arranged on rubber blanket 144, when fixed plate 143 is camera
After 200 are firmly pressed onto in supporting plate 141, the maximum static friction force between camera 200 and rubber blanket 144 is enough to ensure that camera
200 are firmly fixed in supporting plate 142, moreover it is possible to buffer the effect of vibration to camera 200.The base 110 is two, respectively
Corresponding 2 cameras 200;The camera 200 uses ccd video camera.
In the present embodiment, in addition to:Vibrating sensor, it is arranged on each wheel hub of vehicle, when being travelled for detecting vehicle
Amplitude and vibration frequency;Velocity sensor, it is arranged on wheel drive axle, for measuring Vehicle Speed;Infrared biography
Sensor, it is separately positioned on the camera, for detecting the difference in height between camera;Control system, it connects the vibration
Sensor, velocity sensor, infrared sensor and motor, for receiving the vibrating sensor, velocity sensor and infrared biography
The detection data of sensor simultaneously control the motor to work, and to adjust the height of two cameras, realize that road pavement information is more accurate
Detection.
The installation stand of vehicle-mounted binocular vision system of the present invention, the height of binocular camera can be adjusted in real time, is carried
High road surface measurement accuracy;And the distance between two cameras of the installation stand adjustable, camera mirror plane and horizontal direction
Angle also can adjust, can adapt to more multi-vehicle-type, installation accuracy improved while reducing production cost.
Present invention also offers a kind of control method of vehicle-mounted binocular vision system installation stand, it is based on when the vehicle is running
BP neural network specifically comprises the following steps to regulating and controlling to the height of two cameras:
Step 1: establish BP neural network model;
For the BP network architecture that the present invention uses by up of three layers, first layer is input layer, common n node, is corresponded to
N detection signal of equipment working state is represented, these signal parameters are provided by data preprocessing module.The second layer is hidden layer,
Common m node, determined in an adaptive way by the training process of network.Third layer is output layer, common p node, by system
Be actually needed output in response to determining that.
The mathematical modeling of the network is:
Input layer vector:X=(x1,x2,…,xn)T
Intermediate layer vector:Y=(y1,y2,…,ym)T
Output layer vector:Z=(z1,z2,…,zp)T
In the present invention, input layer number is n=4, and output layer nodes are p=2.Hidden layer nodes m is estimated by following formula
Draw:
According to the sampling period, 4 parameters of input are:x1Difference in height coefficient between camera, x2For shaking for vehicle traveling
Width coefficient, x3For vehicle ride coefficient of frequency, x4For speed coefficient;
Because the data that sensor obtains belong to different physical quantitys, its dimension is different.Therefore, in data input god
Through network before, it is necessary to which data requirement to be turned to the number between 0-1.
Specifically, for the difference in height Δ h between camera, after being standardized, the difference in height x between camera is obtained1:
Wherein, Δ hminWith Δ hmaxThe minimum value and maximum of difference in height respectively between camera.
Likewise, to the amplitude A of vehicle traveling, after being standardized, the peak factor coefficient x of vehicle traveling is obtained2:
Wherein, AminAnd AmaxPeak swing and minimum amplitude respectively in vehicle travel process.
To vehicle ride frequency H, after being standardized, vehicle ride coefficient of frequency x is obtained3:
Wherein, HminAnd HmaxMinimum vibration frequency and maximum vibration frequency respectively in vehicle travel process.
To vehicle velocity V, after being standardized, speed coefficient x is obtained4:
Wherein, VminAnd VmaxRespectively minimum speed and the max speed.
2 parameters of output signal are expressed as:z1For the height adjustment factor of first camera, z2For second camera
Height adjustment factor;
The height adjustment factor z of first camera1The first camera height being expressed as in next sampling period is with currently adopting
The ratio between maximum height set in the sample cycle, i.e., in the ith sample cycle, the first camera collected is highlyPass through
BP neural network exports the first camera height adjustment factor z in ith sample cycle1 iAfterwards, control the in the i+1 sampling period
One camera heights areMake its satisfaction
The height adjustment factor z of second camera2The second camera height being expressed as in next sampling period is with currently adopting
The ratio between maximum height set in the sample cycle, i.e., in the ith sample cycle, the second camera collected is highlyPass through
BP neural network exports the second camera height adjustment factor z in ith sample cycle2 iAfterwards, control the in the i+1 sampling period
Two camera heights areMake its satisfaction
Step 2:Carry out the training of BP neural network.
After establishing BP neural network nodal analysis method, you can carry out the training of BP neural network.According to the experience number of product
According to the sample for obtaining training, and give the connection weight w between input node i and hidden layer node jij, hidden node j and output
Connection weight w between node layer kjk, hidden node j threshold θj, output node layer k threshold value wij、wjk、θj、θkIt is -1
Random number between to 1.
In the training process, w is constantly correctedijAnd wjkValue, until systematic error is when being less than or equal to anticipation error, completion
The training process of neutral net.
As shown in table 1, given the value of each node in one group of training sample and training process.
Each nodal value of the training process of table 1
Step 3: gathered data operational factor input neutral net is regulated coefficient;
The artificial neural network trained is solidificated among chip, hardware circuit is possessed prediction and intelligent decision function,
So as to form Intelligent hardware.After Intelligent hardware power-up starts, vehicle-mounted binocular vision system installation stand brings into operation, first camera
Elemental height with second camera is:
Wherein,The respectively elemental height of first camera and second camera;hmaxFor the maximum of the camera of setting
Highly;hcFor bodywork height;d0It is first camera and first camera along slide rail axial distance;θ is camera mirror plane and horizontal direction
Angle;
It is expert at Chinese herbaceous peony, first camera and first camera is regulated along slide rail axial distance according to vehicle first so that first
Camera and second camera shoot with video-corder complete vehicle front, and two cameras to shoot with video-corder area at least tangent or overlapping one
Point;Camera mirror plane and the angle of horizontal direction are adjusted afterwards;Finally according to the distance between two cameras and camera and horizontal direction
Angle combination bodywork height regulation first camera and second camera elemental height so that first camera and second camera can
Preferably it is irradiated to the land area that vehicle front abuts vehicle head part so that the information of road surface of measurement is more accurate.
Meanwhile measure the difference in height Δ h between two cameras of original state using sensor0, the amplitude A of vehicle traveling0、
Vibration frequency H0And vehicle velocity V0, by the way that above-mentioned parameter is standardized, obtain the initial input vector of BP neural networkInitial output vector is obtained by the computing of BP neural network
Step 4:By the height of original state first camera and the height of second camera, initial output vector is obtainedAfterwards, you can adjust the height of first camera and the height of second camera, make next phase of sampling period first
The height of machine and the height of second camera are respectively:
The difference in height Δ h between two cameras in the ith sample cycle, the amplitude of vehicle traveling are obtained by sensor
A, vibration frequency H and vehicle velocity V, by being standardized to obtain the input vector x in ith sample cyclei=(x1 i,x2 i,x3 i,
x4 i), the output vector z in ith sample cycle is obtained by the computing of BP neural networki=(z1 i,z2 i), then control to adjust
The height of first camera and the height of second camera, the height of first camera and second camera when making the i+1 sampling period
Highly it is respectively:
By above-mentioned setting, the running status of vehicle, i.e. difference in height between camera, vehicle are monitored in real time by sensor
Amplitude, vibration frequency and the speed of traveling, by using BP neural network algorithm, to the height and second camera of first camera
Height constantly regulated and controled, make two cameras camera lens it is vertical highly identical, it is accurate to improve information of road surface measurement.
Although embodiment of the present invention is disclosed as above, it is not restricted in specification and embodiment listed
With it can be applied to various suitable the field of the invention completely, can be easily for those skilled in the art
Other modification is realized, therefore under the universal limited without departing substantially from claim and equivalency range, it is of the invention and unlimited
In specific details and shown here as the legend with description.
Claims (10)
- A kind of 1. installation stand of vehicle-mounted binocular vision system, it is characterised in that including:Base, its top are hollow structure;Support base, it is set in the base top and can be axially moved along the base;Rack, it is arranged on the base upper inside wall opposite sides;Motor, it connects the support base lower end, and the gear of the motor engages with the rack, for driving the support base It is axially moved along the base.
- 2. the installation stand of vehicle-mounted binocular vision system as claimed in claim 1, it is characterised in that also include:Slide rail, it includes two slideways be arrangeding in parallel, and the base bottom is connected with the slideway and can be along described Slide rail is axially moved;Camera carriage, itself and the support seat hinge, it can be along the slide rail radial rotary.
- 3. the installation stand of vehicle-mounted binocular vision system as claimed in claim 2, it is characterised in that the base includes:Bolt hole, it is arranged on the base bottom corner;Bolt, it passes through the slideway and bolt hole;Nut, it screws in described bolt one end, for fastening the base and slideway.
- 4. the installation stand of vehicle-mounted binocular vision system as claimed in claim 2, it is characterised in that the camera carriage bag Include:Supporting plate, it is arranged on the camera carriage upper end, for supporting camera;Support bar, its be vertically set on below the supporting plate and with the support seat hinge, can the slide rail radial rotary, The support bar lower end is provided with blind hole;Fixed plate, it is set in parallel in above the supporting plate and fastened with the supporting plate, for fixing the camera.
- 5. the installation stand of vehicle-mounted binocular vision system as claimed in claim 4, it is characterised in that the support base includes:U-shaped groove, it is arranged on the support base upper end;Through hole, it is arranged on the U-shaped groove side and corresponding with the blind hole;Angular adjustment knob, it is screwed in the blind hole through the through hole.
- 6. the installation stand of vehicle-mounted binocular vision system as claimed in claim 4, it is characterised in that above the supporting plate and Rubber blanket is correspondingly arranged on below fixed plate, for increasing the camera resistance to sliding.
- 7. the installation stand of vehicle-mounted binocular vision system as claimed in any one of claims 1 to 6, it is characterised in that the bottom Seat is two;The camera is ccd video camera.
- 8. the installation stand of vehicle-mounted binocular vision system as claimed in any one of claims 1 to 6, it is characterised in that also wrap Include:Vibrating sensor, it is arranged on each wheel hub of vehicle, for detecting amplitude and vibration frequency when vehicle travels;Velocity sensor, it is arranged on wheel drive axle, for measuring Vehicle Speed;Infrared sensor, it is separately positioned on the camera, for detecting the difference in height between camera;Control system, it connects vibrating sensor, velocity sensor, infrared sensor and the motor, for receiving described shake The detection data of dynamic sensor, velocity sensor and infrared sensor simultaneously control the motor to work.
- 9. a kind of control method of vehicle-mounted binocular vision system installation stand, it is characterised in that when the vehicle is running based on BP god The height of two cameras is regulated and controled through network, comprised the following steps:Step 1: according to the sampling period, the difference in height Δ h between camera is gathered by sensor, the amplitude A of vehicle traveling, shaken Dynamic frequency H and vehicle velocity V;Step 2: difference in height Δ h, amplitude A, vibration frequency H and the vehicle velocity V of vehicle traveling are standardized successively, it is determined that Input layer vector x={ x of three layers of BP neural network1,x2,x3,x4};Wherein, x1Difference in height coefficient between camera, x2For car Traveling peak factor, x3For vehicle ride coefficient of frequency, x4For speed coefficient;Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to intermediate layer, the intermediate layer vector y={ y1,y2,…,ym};M is intermediate layer Node number;Step 4: obtain output layer vector z={ z1,z2};Wherein, z1For the height adjustment factor of first camera, z2For the second phase The height adjustment factor of machine, makes<mrow> <msubsup> <mi>h</mi> <mn>1</mn> <mrow> <mi>i</mi> <mo>+</mo> <mn>1</mn> </mrow> </msubsup> <mo>=</mo> <msup> <msub> <mi>z</mi> <mn>1</mn> </msub> <mi>i</mi> </msup> <msub> <mi>h</mi> <mi>max</mi> </msub> </mrow><mrow> <msubsup> <mi>h</mi> <mn>2</mn> <mrow> <mi>i</mi> <mo>+</mo> <mn>1</mn> </mrow> </msubsup> <mo>=</mo> <msup> <msub> <mi>z</mi> <mn>2</mn> </msub> <mi>i</mi> </msup> <msub> <mi>h</mi> <mi>max</mi> </msub> </mrow>Wherein, z1 i、z2 iRespectively ith sample cycle output layer vector parameter, hmaxFor the maximum height of the camera of setting,Respectively the i+1 sampling period when first camera and second camera height;AndIn the step 2, difference in height Δ h, amplitude A, vibration frequency H and the vehicle velocity V of vehicle traveling carry out normalization formulae For:<mrow> <msub> <mi>x</mi> <mi>j</mi> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>X</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mi>min</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> </mrow> </mfrac> <mo>,</mo> <mi>j</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>3</mn> <mo>,</mo> <mn>4</mn> <mo>;</mo> </mrow>Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter Δ h, A, H, V, j=1,2,3,4;XjmaxAnd Xjmin Maximum and minimum value in respectively corresponding measurement parameter.
- 10. the control method of vehicle-mounted binocular vision system installation stand as claimed in claim 9, it is characterised in that described In step 1, under initial operating state, the height of first camera and the height of second camera meet empirical value:<mrow> <msubsup> <mi>h</mi> <mn>1</mn> <mn>0</mn> </msubsup> <mo>=</mo> <msubsup> <mi>h</mi> <mn>2</mn> <mn>0</mn> </msubsup> <mo>=</mo> <msup> <mrow> <mo>(</mo> <mfrac> <msub> <mi>h</mi> <mi>c</mi> </msub> <msub> <mi>d</mi> <mn>0</mn> </msub> </mfrac> <mo>)</mo> </mrow> <mfrac> <mn>2</mn> <mn>3</mn> </mfrac> </msup> <mo>&CenterDot;</mo> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mi>&theta;</mi> <mo>&CenterDot;</mo> <msub> <mi>h</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>,</mo> </mrow>Wherein,The respectively elemental height of first camera and second camera;hmaxFor the maximum height of the camera of setting; hcFor bodywork height;d0It is first camera and first camera along slide rail axial distance;θ is camera mirror plane and the angle of horizontal direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710720969.XA CN107364406A (en) | 2017-08-22 | 2017-08-22 | The installation stand and its control method of a kind of vehicle-mounted binocular vision system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710720969.XA CN107364406A (en) | 2017-08-22 | 2017-08-22 | The installation stand and its control method of a kind of vehicle-mounted binocular vision system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107364406A true CN107364406A (en) | 2017-11-21 |
Family
ID=60310361
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710720969.XA Withdrawn CN107364406A (en) | 2017-08-22 | 2017-08-22 | The installation stand and its control method of a kind of vehicle-mounted binocular vision system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107364406A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108189776A (en) * | 2018-03-12 | 2018-06-22 | 山西大众电子信息产业集团有限公司 | Vehicular display device fixing bracket |
CN108639065A (en) * | 2018-05-15 | 2018-10-12 | 辽宁工业大学 | A kind of vehicle safe driving control method of view-based access control model |
CN108664043A (en) * | 2018-03-28 | 2018-10-16 | 吉林大学 | Characteristics of Drivers ' Behavior point measuring device based on binocular vision and its control method |
CN108859998A (en) * | 2018-06-14 | 2018-11-23 | 辽宁工业大学 | A kind of front truck rear-end device and its control method |
CN109458947A (en) * | 2018-10-22 | 2019-03-12 | 深圳市立可自动化设备有限公司 | Accurate 3D detection system based on binocular vision |
CN109732648A (en) * | 2019-01-14 | 2019-05-10 | 北京工业大学 | A kind of binocular regulating mechanism connecting robot and filature |
CN110213563A (en) * | 2019-06-04 | 2019-09-06 | 深圳市华芯技研科技有限公司 | A kind of adaptive strain baseline binocular solid camera |
CN113334319A (en) * | 2021-05-31 | 2021-09-03 | 山东省科学院高新技术产业(中试)基地(山东省科学院留学人员创业园) | Sensor probe single-body rapid adjusting and assembling device based on automatic driving |
-
2017
- 2017-08-22 CN CN201710720969.XA patent/CN107364406A/en not_active Withdrawn
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108189776B (en) * | 2018-03-12 | 2023-07-04 | 山西大众电子信息产业集团有限公司 | Vehicle-mounted display fixing support |
CN108189776A (en) * | 2018-03-12 | 2018-06-22 | 山西大众电子信息产业集团有限公司 | Vehicular display device fixing bracket |
CN108664043A (en) * | 2018-03-28 | 2018-10-16 | 吉林大学 | Characteristics of Drivers ' Behavior point measuring device based on binocular vision and its control method |
CN108664043B (en) * | 2018-03-28 | 2024-05-07 | 吉林大学 | Binocular vision-based driver characteristic point measuring device and control method thereof |
CN108639065A (en) * | 2018-05-15 | 2018-10-12 | 辽宁工业大学 | A kind of vehicle safe driving control method of view-based access control model |
CN108859998A (en) * | 2018-06-14 | 2018-11-23 | 辽宁工业大学 | A kind of front truck rear-end device and its control method |
CN109458947A (en) * | 2018-10-22 | 2019-03-12 | 深圳市立可自动化设备有限公司 | Accurate 3D detection system based on binocular vision |
CN109458947B (en) * | 2018-10-22 | 2021-01-22 | 深圳市立可自动化设备有限公司 | Precise 3D detection system based on binocular vision |
CN109732648A (en) * | 2019-01-14 | 2019-05-10 | 北京工业大学 | A kind of binocular regulating mechanism connecting robot and filature |
CN109732648B (en) * | 2019-01-14 | 2021-04-02 | 北京工业大学 | Binocular adjusting mechanism for connecting robot and screw machine |
CN110213563A (en) * | 2019-06-04 | 2019-09-06 | 深圳市华芯技研科技有限公司 | A kind of adaptive strain baseline binocular solid camera |
CN110213563B (en) * | 2019-06-04 | 2021-05-11 | 深圳市华芯技研科技有限公司 | Self-adaptive variable-baseline binocular stereo camera |
CN113334319B (en) * | 2021-05-31 | 2022-12-23 | 山东省科学院高新技术产业(中试)基地(山东省科学院留学人员创业园) | Sensor probe monomer quick adjustment assembly quality based on autopilot |
CN113334319A (en) * | 2021-05-31 | 2021-09-03 | 山东省科学院高新技术产业(中试)基地(山东省科学院留学人员创业园) | Sensor probe single-body rapid adjusting and assembling device based on automatic driving |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107364406A (en) | The installation stand and its control method of a kind of vehicle-mounted binocular vision system | |
DE69731423T2 (en) | A suspension control device having a relative speed calculating device between a vehicle's sprung and unsprung structure. | |
CN106394561B (en) | A kind of method of estimation and device of longitudinal speed of vehicle | |
CN103963593B (en) | Adaptive active suspension system with road previewing | |
CN102897213B (en) | Electric power steering compensation for vehicle | |
DE102006001436B4 (en) | Method for determining at least one movement state of a vehicle body | |
DE602004008718T2 (en) | Method for controlling the damping force in an electronically controlled suspension device | |
CN108357595B (en) | Model-based self-balancing unmanned bicycle and model driving control method thereof | |
DE102016106703A1 (en) | Electric bicycle engine using a detected airspeed | |
US20180037081A1 (en) | Method for compensating for vertical movements | |
CN206068069U (en) | Scooter speed control system and scooter based on gyroscope | |
CN109017602B (en) | Self-adaptive center console based on human body gesture recognition and control method thereof | |
CN109238747A (en) | One kind being used for commercial vehicle vehicle performance index decomposition analysis platform and decomposition analysis method | |
CN108327841B (en) | Self-balancing unmanned bicycle and control method thereof | |
CN108639065A (en) | A kind of vehicle safe driving control method of view-based access control model | |
DE112014001259T5 (en) | Shock absorber control device | |
CN108664043B (en) | Binocular vision-based driver characteristic point measuring device and control method thereof | |
CN114148138B (en) | Vehicle shock absorber self-adaptive adjusting system and method based on road surface information detection | |
CN113183709A (en) | Automobile electric control suspension pre-aiming control method | |
CN110901321A (en) | Semi-active suspension of hillside orchard conveyor and simulation analysis method | |
CN106864461A (en) | A kind of method that vehicle movement behavior is judged based on acceleration transducer | |
DE10228813A1 (en) | Continuously variable semi-active suspension system using centrally located yaw rate and acceleration sensors | |
CN205898431U (en) | Car sun visor board upset torsion check out test set | |
CN108357596B (en) | Self-balancing unmanned bicycle based on behavior driving and behavior driving control method thereof | |
CN207173485U (en) | A kind of installation stand of vehicle-mounted binocular vision 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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171121 |
|
WW01 | Invention patent application withdrawn after publication |