CN206086717U - Intelligent car is from saying early warning system based on monocular vision principle - Google Patents
Intelligent car is from saying early warning system based on monocular vision principle Download PDFInfo
- Publication number
- CN206086717U CN206086717U CN201620994991.4U CN201620994991U CN206086717U CN 206086717 U CN206086717 U CN 206086717U CN 201620994991 U CN201620994991 U CN 201620994991U CN 206086717 U CN206086717 U CN 206086717U
- Authority
- CN
- China
- Prior art keywords
- module
- image
- signal
- bus
- sent
- 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
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The utility model provides an intelligent car is from saying early warning system based on monocular vision principle and method relate to car technical field, a serial communication port, the system includes: memory, internal processing ware, deposit outward, outside treater, bus, interrupt request input module, serial peripheral interface, triaxial accelerator, chronogenesis production module, survey drive module, image sensor, alarm unit and electrical unit. The utility model has the advantages of accuracy height, intellectuality and early warning are promptly and accurately.
Description
Technical field
The utility model is related to automobile technical field, more particularly to a kind of intelligent vehicle based on monocular vision principle from
Road early warning system.
Background technology
As automation and the high speed development of microelectric technique, Modern Traffic aid are more and more intelligent, GPS leads
It is boat, point of interest prompting, multi-functional supplementary controlled system, even unmanned, incorporate from military vehicle and spread to family expenses
The type vehicles, particularly most common family-sized car has formed a kind of irreversible intelligent streamlining.
There are several domestic and international car manufactures to employ different tracks at present and keep accessory system（Such as Audi
Q5, the popular generation of golf 7）, such system set up on the basis of digital image video is processed, then by detecting track
It is modeled etc. information and early warning.Although the system for putting it into commercial operation is very ripe perfect, the logic judgment of early warning mechanism（Start
Condition, give warning in advance）It is more thorough to consider, but nearly all have ignored camera because automobile carrying is different and road surfacing and send out
The inclined situation of life, adds in the algorithm the amendment of this factor actual for following precise control and assisting vehicle travel have
Meaning.
Utility model content
In consideration of it, the utility model provides a kind of intelligent vehicle based on monocular vision principle from road early warning system,
The utility model has the advantages that high accuracy, intellectuality, early warning promptly and accurately.
The technical solution adopted in the utility model is as follows：
A kind of intelligent vehicle based on monocular vision principle is from road early warning system, it is characterised in that the system includes：
Internal memory, internal processor, external memory, ppu, bus, interrupt requests input module, Serial Peripheral Interface (SPI), three axles accelerate
Device, sequence generation module, detection drive module, imageing sensor, alarm unit and power subsystem；The internal memory signal is connected to
Internal processor；Respectively signal is connected to external memory and bus to affiliated internal processor；The external memory signal is connected to external treatment
Device；Respectively signal is connected to interrupt requests input module and Serial Peripheral Interface (SPI) to the three axles accelerator；The interrupt requests are defeated
Enter module by signal and be connected to bus；The Serial Peripheral Interface (SPI) signal is connected to bus；Described image sensor difference signal connects
It is connected to detection drive module and bus；The detection drive module signal is connected to sequence generation module；The sequential produces mould
Block signal is connected to bus；The alarm unit signal is connected to bus；The power subsystem signal is connected to bus.
Described image sensor is installed on hull axis front, and the optical axis of the sensor is parallel with hull；Described image
Sensor signal is connected to internal memory, the image information for photographing is sent in internal memory and is stored.
Using above-mentioned technical proposal, imageing sensor is arranged on hull axis front, and its optical axis is parallel with hull；Due to car
Axle centre-to-centre spacing or so divided lane has certain distance, according to the general principle of perspective projection, left and right in the projected image of camera road surface
At an angle, this angle can change lines meeting shape because of the change in location of car, when car is in the middle of two lines, institute
The angle for obtaining two or so lines in image is maximum, and its slope one positive one is negative, when vehicle shift center line, this angle meeting
Taper into, when the angle information is less than this minimum angle in road presence one minimum angle, but image, report to the police
Mechanism will send alarm.
The internal processor includes：Image sharpening module, threshold skirt detection module, optical distortion rectification module, incline
Angle rotational correction module, Hough algoritic modules, lines extraction module and warning module；Described image sharpening module signal connects
Threshold skirt detection module is connected to, for being sharpened process to image, original gray level image is obtained, gray level image is sent
To threshold skirt detection module；The threshold skirt detection module signal is connected to optical distortion rectification module, for gray scale
Image carries out rim detection, and the image after detection is sent to optical distortion rectification module；The optical distortion rectification module letter
Number inclination angle rotational correction module is connected to, for carrying out optical distortion correction to the image information for receiving, by the figure after correction
As sending to inclination angle rotational correction module；The inclination angle rotational correction module by signal is connected to Hough algoritic modules, for docking
The image information for receiving carries out dip correction, and his image after correction is sent to Hough algoritic modules；The Hough algorithms
Module by signal is connected to lines extraction module, for carrying out Hough transform to the image for receiving, the image after conversion is sent out
Deliver to lines extraction module；The lines extraction module signal is connected to warning module, for entering to the image for receiving
Row and shunting line drawing, and carry out alarm and set out condition judgment, will determine that result is sent to warning module；The warning module letter
Number bus is connected to, for sending alarm command, is reported to the police alarm unit is triggered after bus transfer.
Using above-mentioned technical proposal, imageing sensor intake pavement image data, store to RAM in plate；Rectified by distortion
Just, it is ensured that the divided lane of display is as live as possible；Then, by triaxial accelerometer rectification so that image x-axis and actual road
Face is parallel；Finally by the algorithm of threshold values separation, rim detection and Hough transform, recreate pavement image and set up
Lines angle-data is sent to early warning logic state machine.
The three axles accelerator, for obtaining vehicle traveling process in three reference axis data message, data are believed
Breath is sent to internal processor；The sequence generation module, for generation time instruction；The detection drive module, for supervising
Whether the driving of each hardware is normal in examining system, if having driving disappearance, result of detection is sent to internal processor.
Using above technical scheme, the utility model generates following beneficial effect：
1st, accuracy is high：Early warning system of the present utility model add triaxial accelerometer to inclining with regard to camera lens after image procossing
Correction, break through due to the nonlinear transformation problem of the optical characteristics of wide-angle camera, improve the accuracy and accurately of identification
Degree.Additionally, on the original image pretreatment to adopt Hough transform algorithm after edge binary images again, robustness and anti-interference
Property it is higher, replace existing DSP video frequency processing chips, real time video processing is realized more quickly.
2nd, it is intelligent：Need not artificially be operated in early warning system of the present utility model and method for early warning, system is automatic
Identification running status, is reported to the police automatically according to running status, and intelligence degree is high.
Description of the drawings
Fig. 1 is that a kind of intelligent vehicle based on monocular vision principle of the present utility model is tied from the system of road early warning system
Structure schematic diagram.
Specific embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine by any way.
This specification（Including any accessory claim, summary）Disclosed in any feature, unless specifically stated otherwise,
Equivalent by other or with similar purpose alternative features are replaced.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalent or similar characteristics.
Provide in the utility model embodiment 1 and plant the intelligent vehicle for being based on monocular vision principle from road early warning system,
System architecture is as shown in Figure 1：
A kind of intelligent vehicle based on monocular vision principle is from road early warning system, it is characterised in that the system includes：
Internal memory, internal processor, external memory, ppu, bus, interrupt requests input module, Serial Peripheral Interface (SPI), three axles accelerate
Device, sequence generation module, detection drive module, imageing sensor, alarm unit and power subsystem；The internal memory signal is connected to
Internal processor；Respectively signal is connected to external memory and bus to affiliated internal processor；The external memory signal is connected to external treatment
Device；Respectively signal is connected to interrupt requests input module and Serial Peripheral Interface (SPI) to the three axles accelerator；The interrupt requests are defeated
Enter module by signal and be connected to bus；The Serial Peripheral Interface (SPI) signal is connected to bus；Described image sensor difference signal connects
It is connected to detection drive module and bus；The detection drive module signal is connected to sequence generation module；The sequential produces mould
Block signal is connected to bus；The alarm unit signal is connected to bus；The power subsystem signal is connected to bus.
Described image sensor is installed on hull axis front, and the optical axis of the sensor is parallel with hull；Described image
Sensor signal is connected to internal memory, the image information for photographing is sent in internal memory and is stored.
Using above-mentioned technical proposal, imageing sensor is arranged on hull axis front, and its optical axis is parallel with hull；Due to car
Axle centre-to-centre spacing or so divided lane has certain distance, according to the general principle of perspective projection, left and right in the projected image of camera road surface
At an angle, this angle can change lines meeting shape because of the change in location of car, when car is in the middle of two lines, institute
The angle for obtaining two or so lines in image is maximum, and its slope one positive one is negative, when vehicle shift center line, this angle meeting
Taper into, when the angle information is less than this minimum angle in road presence one minimum angle, but image, report to the police
Mechanism will send alarm.
The internal processor includes：Image sharpening module, threshold skirt detection module, optical distortion rectification module, incline
Angle rotational correction module, Hough algoritic modules, lines extraction module and warning module；Described image sharpening module signal connects
Threshold skirt detection module is connected to, for being sharpened process to image, original gray level image is obtained, gray level image is sent
To threshold skirt detection module；The threshold skirt detection module signal is connected to optical distortion rectification module, for gray scale
Image carries out rim detection, and the image after detection is sent to optical distortion rectification module；The optical distortion rectification module letter
Number inclination angle rotational correction module is connected to, for carrying out optical distortion correction to the image information for receiving, by the figure after correction
As sending to inclination angle rotational correction module；The inclination angle rotational correction module by signal is connected to Hough algoritic modules, for docking
The image information for receiving carries out dip correction, and his image after correction is sent to Hough algoritic modules；The Hough algorithms
Module by signal is connected to lines extraction module, for carrying out Hough transform to the image for receiving, the image after conversion is sent out
Deliver to lines extraction module；The lines extraction module signal is connected to warning module, for entering to the image for receiving
Row and shunting line drawing, and carry out alarm and set out condition judgment, will determine that result is sent to warning module；The warning module letter
Number bus is connected to, for sending alarm command, is reported to the police alarm unit is triggered after bus transfer.
Using above-mentioned technical proposal, imageing sensor intake pavement image data, store to RAM in plate；Rectified by distortion
Just, it is ensured that the divided lane of display is as live as possible；Then, by triaxial accelerometer rectification so that image x-axis and actual road
Face is parallel；Finally by the algorithm of threshold values separation, rim detection and Hough transform, recreate pavement image and set up
Lines angle-data is sent to early warning logic state machine.
The three axles accelerator, for obtaining vehicle traveling process in three reference axis data message, data are believed
Breath is sent to internal processor；The sequence generation module, for generation time instruction；The detection drive module, for supervising
Whether the driving of each hardware is normal in examining system, if having driving disappearance, result of detection is sent to internal processor.
Provide in the utility model embodiment 2 and plant the intelligent vehicle for being based on monocular vision principle from road method for early warning：
A kind of intelligent vehicle based on monocular vision principle is from road method for early warning, it is characterised in that methods described includes
Following steps：
Step 1：Automobile starting, system initialization, alarm unit is in not enabled state, and imageing sensor starts to take in road
Face view data, stores in internal memory；
Step 2：Processor is sharpened first process to image；Again by threshold values rim detection, edge binary map is obtained
Picture；Then, by the data message obtained from three axle accelerators, optical distortion correction and inclination angle rotational correction are carried out, obtains school
Positive back edge bianry image, Hough algorithm computings are carried out to the image, obtain it is transformed after parameter plane, finally extracting should
The lines of image, according to the lines for extracting motoring condition is judged；
Step 3：If judged result is, automobile normal running is in the middle of two lines and is not switched on steering indicating light, then report to the police single
Unit is switched to the state of enabling；
Step 4：In alarm unit in enabling under state, if image assigns to angle less than warning minimum angle, report
Alert unit enters alarm condition, and alarm is triggered immediately.
Using above-mentioned technical proposal, the original-gray image of intake is passed to that internal processor by imageing sensor, most
Threshold values rim detection is first passed through, edge binary images data are obtained；After inclining occurs in car, the image of intake occurs that perspective is abnormal
Become, so needing to be corrected by optical distortion, the edge binary images data being consistent with fact after being corrected；At this moment, install
Gyroscope relevant parameter can be provided, inclination angle rotational correction is carried out to image, obtain horizontal edge binary image data；Passing through
Hough algorithms are converted into parameter plane data, therefrom extract lines；With the fact that car is travelled, at any time to alarm trigger
Condition is judged occur from road, and after alarm trigger condition meets, internal processor is pulled up a horse early warning logic relevant information is defeated
Go out, control triggering alarm.
The alarm unit has three kinds of running statuses：Not enabled, enable and report to the police;During automobile starting, at warning system
In not enabled state, when early warning entry condition meets, i.e., normal vehicle operation is in the middle of two lines and is not switched on steering indicating light
When, alarm unit is switched to the state of enabling；Under the state that enables, if car run-off-road, processor is in the result of image procossing
Obtain lines angle-data meet from road condition, i.e. image shunting angle be less than alarm minimum angle when, then into warning shape
State, alarm is triggered immediately；Meanwhile, alarm trigger has a shorter lasting buffer time, and automobile meets again within the time
Then warning system reenters the state of enabling to early warning entry condition, if still being not detected by meeting the shunting line angle of the state of enabling
Degree then enters not enabled state；If alarm unit angle-data of gained lines in setting time threshold value is in safe model
When enclosing interior, even if there is small range to swing, car is also considered as without departing from track, alarm will not be triggered；When motor turning, open in advance
Steering indicating light, warning system also will be in not enabled state.
The method of the threshold skirt detection is comprised the following steps：
Step 1：Pending image is mapped as by a fuzzy matrix using membership function；
Step 2：Note imageHaveIndividual gray level, image size is, fuzzy matrixUnit
ElementMembership function for image is：；
Parameter F=2；WithShape it is relevant；
Step 3：It is rightNonlinear transformation is carried out, is obtained：
;
Step 4：It is rightInverse transformation is carried out, the image after enhanced fuzzy is obtained
Step 5：The edge for obtaining image is：
。
Provide in the utility model embodiment 3 and plant the intelligent vehicle for being based on monocular vision principle from road early warning system,
System construction drawing is as shown in Figure 1：
A kind of intelligent vehicle based on monocular vision principle is from road early warning system, it is characterised in that the system includes：
Internal memory, internal processor, external memory, ppu, bus, interrupt requests input module, Serial Peripheral Interface (SPI), three axles accelerate
Device, sequence generation module, detection drive module, imageing sensor, alarm unit and power subsystem；The internal memory signal is connected to
Internal processor；Respectively signal is connected to external memory and bus to affiliated internal processor；The external memory signal is connected to external treatment
Device；Respectively signal is connected to interrupt requests input module and Serial Peripheral Interface (SPI) to the three axles accelerator；The interrupt requests are defeated
Enter module by signal and be connected to bus；The Serial Peripheral Interface (SPI) signal is connected to bus；Described image sensor difference signal connects
It is connected to detection drive module and bus；The detection drive module signal is connected to sequence generation module；The sequential produces mould
Block signal is connected to bus；The alarm unit signal is connected to bus；The power subsystem signal is connected to bus.
Described image sensor is installed on hull axis front, and the optical axis of the sensor is parallel with hull；Described image
Sensor signal is connected to internal memory, the image information for photographing is sent in internal memory and is stored.
Using above-mentioned technical proposal, imageing sensor is arranged on hull axis front, and its optical axis is parallel with hull；Due to car
Axle centre-to-centre spacing or so divided lane has certain distance, according to the general principle of perspective projection, left and right in the projected image of camera road surface
At an angle, this angle can change lines meeting shape because of the change in location of car, when car is in the middle of two lines, institute
The angle for obtaining two or so lines in image is maximum, and its slope one positive one is negative, when vehicle shift center line, this angle meeting
Taper into, when the angle information is less than this minimum angle in road presence one minimum angle, but image, report to the police
Mechanism will send alarm.
The internal processor includes：Image sharpening module, threshold skirt detection module, optical distortion rectification module, incline
Angle rotational correction module, Hough algoritic modules, lines extraction module and warning module；Described image sharpening module signal connects
Threshold skirt detection module is connected to, for being sharpened process to image, original gray level image is obtained, gray level image is sent
To threshold skirt detection module；The threshold skirt detection module signal is connected to optical distortion rectification module, for gray scale
Image carries out rim detection, and the image after detection is sent to optical distortion rectification module；The optical distortion rectification module letter
Number inclination angle rotational correction module is connected to, for carrying out optical distortion correction to the image information for receiving, by the figure after correction
As sending to inclination angle rotational correction module；The inclination angle rotational correction module by signal is connected to Hough algoritic modules, for docking
The image information for receiving carries out dip correction, and his image after correction is sent to Hough algoritic modules；The Hough algorithms
Module by signal is connected to lines extraction module, for carrying out Hough transform to the image for receiving, the image after conversion is sent out
Deliver to lines extraction module；The lines extraction module signal is connected to warning module, for entering to the image for receiving
Row and shunting line drawing, and carry out alarm and set out condition judgment, will determine that result is sent to warning module；The warning module letter
Number bus is connected to, for sending alarm command, is reported to the police alarm unit is triggered after bus transfer.
Using above-mentioned technical proposal, imageing sensor intake pavement image data, store to RAM in plate；Rectified by distortion
Just, it is ensured that the divided lane of display is as live as possible；Then, by triaxial accelerometer rectification so that image x-axis and actual road
Face is parallel；Finally by the algorithm of threshold values separation, rim detection and Hough transform, recreate pavement image and set up
Lines angle-data is sent to early warning logic state machine.
The three axles accelerator, for obtaining vehicle traveling process in three reference axis data message, data are believed
Breath is sent to internal processor；The sequence generation module, for generation time instruction；The detection drive module, for supervising
Whether the driving of each hardware is normal in examining system, if having driving disappearance, result of detection is sent to internal processor.
A kind of intelligent vehicle based on monocular vision principle is from road method for early warning, it is characterised in that methods described includes
Following steps：
Step 1：Automobile starting, system initialization, alarm unit is in not enabled state, and imageing sensor starts to take in road
Face view data, stores in internal memory；
Step 2：Processor is sharpened first process to image；Again by threshold values rim detection, edge binary map is obtained
Picture；Then, by the data message obtained from three axle accelerators, optical distortion correction and inclination angle rotational correction are carried out, obtains school
Positive back edge bianry image, Hough algorithm computings are carried out to the image, obtain it is transformed after parameter plane, finally extracting should
The lines of image, according to the lines for extracting motoring condition is judged；
Step 3：If judged result is, automobile normal running is in the middle of two lines and is not switched on steering indicating light, then report to the police single
Unit is switched to the state of enabling；
Step 4：In alarm unit in enabling under state, if image assigns to angle less than warning minimum angle, report
Alert unit enters alarm condition, and alarm is triggered immediately.
Using above-mentioned technical proposal, the original-gray image of intake is passed to that internal processor by imageing sensor, most
Threshold values rim detection is first passed through, edge binary images data are obtained；After inclining occurs in car, the image of intake occurs that perspective is abnormal
Become, so needing to be corrected by optical distortion, the edge binary images data being consistent with fact after being corrected；At this moment, install
Gyroscope relevant parameter can be provided, inclination angle rotational correction is carried out to image, obtain horizontal edge binary image data；Passing through
Hough algorithms are converted into parameter plane data, therefrom extract lines；With the fact that car is travelled, at any time to alarm trigger
Condition is judged occur from road, and after alarm trigger condition meets, internal processor is pulled up a horse early warning logic relevant information is defeated
Go out, control triggering alarm.
The alarm unit has three kinds of running statuses：Not enabled, enable and report to the police;During automobile starting, at warning system
In not enabled state, when early warning entry condition meets, i.e., normal vehicle operation is in the middle of two lines and is not switched on steering indicating light
When, alarm unit is switched to the state of enabling；Under the state that enables, if car run-off-road, processor is in the result of image procossing
Obtain lines angle-data meet from road condition, i.e. image shunting angle be less than alarm minimum angle when, then into warning shape
State, alarm is triggered immediately；Meanwhile, alarm trigger has a shorter lasting buffer time, and automobile meets again within the time
Then warning system reenters the state of enabling to early warning entry condition, if still being not detected by meeting the shunting line angle of the state of enabling
Degree then enters not enabled state；If alarm unit angle-data of gained lines in setting time threshold value is in safe model
When enclosing interior, even if there is small range to swing, car is also considered as without departing from track, alarm will not be triggered；When motor turning, open in advance
Steering indicating light, warning system also will be in not enabled state.
The method of the threshold skirt detection is comprised the following steps：
Step 1：Pending image is mapped as by a fuzzy matrix using membership function；
Step 2：Note imageHaveIndividual gray level, image size is, fuzzy matrixUnit
ElementMembership function for image is：；
Parameter F=2；WithShape it is relevant；
Step 3：It is rightNonlinear transformation is carried out, is obtained：
;
Step 4：It is rightInverse transformation is carried out, the image after enhanced fuzzy is obtained
Step 5：The edge for obtaining image is：
。
Early warning system of the present utility model add triaxial accelerometer to inclining with regard to camera lens after image procossing correction, break through
Due to the nonlinear transformation problem of the optical characteristics of wide-angle camera, accuracy and the degree of accuracy of identification are improved.Additionally, in original
To adopt Hough transform algorithm after edge binary images again, robustness and anti-interference are higher, replace existing for pretreatment on beginning image
Some DSP video frequency processing chips, realize more quickly real time video processing.
Need not artificially be operated in early warning system of the present utility model and method for early warning, system automatic identification operation shape
State, is reported to the police automatically according to running status, and intelligence degree is high.Using special custom algorithm, it is ensured that final result
Accuracy.
Alarm unit in early warning system of the present utility model and method for early warning employs the alarm mechanism of uniqueness, divides three
State：Not enabled, enables, and reports to the police;When vehicle just starts, warning system is in not enabled state, once meet early warning trip bar
Part（Normal vehicle operation is in the middle of two lines and is not switched on steering indicating light）Afterwards, warning system is switched to the state of enabling；Enabling
Under state, if car run-off-road, image-processing operations obtain lines angle-data and meet from road condition（Image shunting angle
Less than alarm minimum angle）, then into alarm condition, alarm is triggered immediately；When alarm trigger has a shorter lasting buffering
Between, automobile meets early warning entry condition then warning system reenters the state of enabling again within the time, if still do not examined
The lines angle for meeting the state that enables is measured then into not enabled state.If recently the angle-data of gained lines is in
When in safe range, even if there is small range to swing, but car is thought without departing from track, alarm will not be triggered；Or, car will be turned to,
Steering indicating light is opened in advance, then warning system is in not enabled state.System carries out alarm condition identification automatically, without manually entering
Row operation, possesses the intellectuality of height.
The utility model is not limited to aforesaid specific embodiment.The utility model expands to any in this specification
The new feature of middle disclosure or any new combination, and the arbitrary new method that discloses or the step of process or any new group
Close.
Claims (4)
1. a kind of intelligent vehicle based on monocular vision principle is from road early warning system, it is characterised in that the system includes：It is interior
Deposit, internal processor, external memory, ppu, bus, interrupt requests input module, Serial Peripheral Interface (SPI), three axle accelerators,
Sequence generation module, detection drive module, imageing sensor, alarm unit and power subsystem；In the internal memory signal is connected to
Portion's processor；Respectively signal is connected to external memory and bus to affiliated internal processor；The external memory signal is connected to ppu；
Respectively signal is connected to interrupt requests input module and Serial Peripheral Interface (SPI) to the three axles accelerator；The interrupt requests are input into mould
Block signal is connected to bus；The Serial Peripheral Interface (SPI) signal is connected to bus；Respectively signal is connected to described image sensor
Detection drive module and bus；The detection drive module signal is connected to sequence generation module；The sequence generation module letter
Number it is connected to bus；The alarm unit signal is connected to bus；The power subsystem signal is connected to bus.
2. the intelligent vehicle based on monocular vision principle as claimed in claim 1 is from road early warning system, it is characterised in that institute
State imageing sensor and be installed on hull axis front, the optical axis of the sensor is parallel with hull；Described image sensor signal
Internal memory is connected to, the image information for photographing is sent in internal memory and is stored.
3. the intelligent vehicle based on monocular vision principle as claimed in claim 2 is from road early warning system, it is characterised in that institute
Stating internal processor includes：Image sharpening module, threshold skirt detection module, optical distortion rectification module, inclination angle rotational correction
Module, Hough algoritic modules, lines extraction module and warning module；Described image sharpening module signal is connected to threshold value side
Edge detection module, for being sharpened process to image, obtains original gray level image, and gray level image is sent to threshold skirt
Detection module；The threshold skirt detection module signal is connected to optical distortion rectification module, for carrying out side to gray level image
Edge detects, the image after detection is sent to optical distortion rectification module；The optical distortion rectification module signal is connected to and inclines
Angle rotational correction module, for carrying out optical distortion correction to the image information for receiving, the image after correction is sent to inclining
Angle rotational correction module；The inclination angle rotational correction module by signal is connected to Hough algoritic modules, for the image for receiving
Information carries out dip correction, and his image after correction is sent to Hough algoritic modules；The Hough algoritic modules signal connects
Lines extraction module is connected to, for carrying out Hough transform to the image for receiving, the image after conversion is sent to lines
Extraction module；The lines extraction module signal is connected to warning module, for carrying out to the image for receiving and lines
Extract, and carry out alarm and set out condition judgment, will determine that result is sent to warning module；The warning module signal is connected to always
Line, for sending alarm command, is reported to the police alarm unit is triggered after bus transfer.
4. the intelligent vehicle based on monocular vision principle as claimed in claim 3 is from road early warning system, it is characterised in that institute
State three axle accelerators, for obtaining vehicle traveling process in three reference axis data message, data message is sent to interior
Portion's processor；The sequence generation module, for generation time instruction；The detection drive module, for each in monitoring system
Whether the driving of individual hardware is normal, if having driving disappearance, result of detection is sent to internal processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620994991.4U CN206086717U (en) | 2016-08-31 | 2016-08-31 | Intelligent car is from saying early warning system based on monocular vision principle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620994991.4U CN206086717U (en) | 2016-08-31 | 2016-08-31 | Intelligent car is from saying early warning system based on monocular vision principle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206086717U true CN206086717U (en) | 2017-04-12 |
Family
ID=58477290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620994991.4U Active CN206086717U (en) | 2016-08-31 | 2016-08-31 | Intelligent car is from saying early warning system based on monocular vision principle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206086717U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106184206B (en) * | 2016-08-31 | 2018-12-14 | 威马汽车科技集团有限公司 | A kind of intelligent vehicle based on monocular vision principle is from road early warning system and method |
-
2016
- 2016-08-31 CN CN201620994991.4U patent/CN206086717U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106184206B (en) * | 2016-08-31 | 2018-12-14 | 威马汽车科技集团有限公司 | A kind of intelligent vehicle based on monocular vision principle is from road early warning system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102785661B (en) | Lane departure control system and lane departure control method | |
| CN109460699B (en) | Driver safety belt wearing identification method based on deep learning | |
| CN104952122B (en) | The drive recorder and system of evidence obtaining violating the regulations can be carried out automatically | |
| CN109636924B (en) | Vehicle-mounted multi-mode augmented reality system based on real road condition information three-dimensional modeling | |
| CN104573646B (en) | Chinese herbaceous peony pedestrian detection method and system based on laser radar and binocular camera | |
| CN109117709A (en) | Collision avoidance system for automatic driving vehicle | |
| US20170300763A1 (en) | Road feature detection using a vehicle camera system | |
| CN104408878B (en) | Vehicle fleet fatigue driving early warning monitoring system and method | |
| CN104021677B (en) | A kind of vehicle board turning detection method and device | |
| CN104902261B (en) | Apparatus and method for the road surface identification in low definition video flowing | |
| CN108243623A (en) | Vehicle anticollision method for early warning and system based on binocular stereo vision | |
| CN108604405A (en) | The object being locally blocked is detected using environment and depth order | |
| US20200234191A1 (en) | Travel model generation system, vehicle in travel model generation system, and processing method | |
| CN106537180A (en) | Method for mitigating radar sensor limitations with video camera input for active braking for pedestrians | |
| CN104157160B (en) | Vehicle travel control method, device and vehicle | |
| CN108764108A (en) | A kind of Foregut fermenters method based on Bayesian inference | |
| US9842283B2 (en) | Target object detection system and a method for target object detection | |
| WO2024016386A1 (en) | Multi-agent federated reinforcement learning-based vehicle-road collaborative control system and method under complex intersection | |
| WO2020199173A1 (en) | Localization method and localization device | |
| CN110930323A (en) | Method and device for removing light reflection of image | |
| US11620522B2 (en) | Vehicular system for testing performance of headlamp detection systems | |
| CN115205813A (en) | Multi-view road vehicle matching system and method based on convolutional neural network | |
| US11691566B2 (en) | Intelligent vehicle systems and control logic for surround view augmentation with object model recognition | |
| CN206086717U (en) | Intelligent car is from saying early warning system based on monocular vision principle | |
| CN106184206A (en) | A kind of intelligent vehicle based on monocular vision principle is from road early warning system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Leng Zhenwang Inventor before: Hu Qiang |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170614 Address after: The middle Tianfu Avenue in Chengdu city Sichuan province 610000 No. 1 Patentee after: Sichuan wanwang Xincheng Mdt InfoTech Ltd Address before: Chengdu Wuhou District City, Sichuan province 610015 Ring Road West Section of Gaosheng Bridge Road No. 2, 2-2 building 10 No. D Patentee before: CHENGDU PEACE TECHNOLOGY CO., LTD. |