CN102662402B - Intelligent camera tracking car model for racing tracks - Google Patents
Intelligent camera tracking car model for racing tracks Download PDFInfo
- Publication number
- CN102662402B CN102662402B CN201210182070.4A CN201210182070A CN102662402B CN 102662402 B CN102662402 B CN 102662402B CN 201210182070 A CN201210182070 A CN 201210182070A CN 102662402 B CN102662402 B CN 102662402B
- Authority
- CN
- China
- Prior art keywords
- image
- line
- racing track
- car model
- car
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to an intelligent camera tracking car model for racing tracks. The intelligent camera tracking car model comprises an energy supply system, a signal collecting system, a central processing system and an executing system; and the central processing system comprises the following processing steps: 1. performing binaryzation on a gray level image collected from the signal collecting system; 2. performing side boundary extraction on the binaryzed image; 3. identifying the racing track according to the extracted side boundary and determining the advancing direction of the car model; 4. calculating the included angle between the optimal advancing direction of the car model and the actual advancing direction of the car model to control a steering engine so as to control the direction; and 5. obtaining the expected speed of the car model through offset, namely, the distance between the axial wire of the car and the axial wire of the racing track, and controlling a drive motor to control the speed. The intelligent camera tracking car model disclosed by the invention fully utilizes the information of a whole frame of image to extract the racing track, thereby overcoming the image fuzzy distortion problem and determining the optimal advancing direction of the car model in real time to realize intelligent tracking of the car model.
Description
Technical field
The present invention relates to a kind of car mould, particularly a kind of camera Intelligent tracking car mould for racing track.
Background technology
Intelligent tracking car mould divides and generally can be divided into photoelectricity, camera and electromagnetism (need to connect up specially) tracking car mould according to sensor.The alternating magnetic field that car mould is produced by racing track center wire by induction carries out the electromagnetic sensor mode that belongs to of path detection; Car mould carries out the camera mode that belongs to of path detection by gathering the mode of racing track image (one dimension, two dimension) or continuous sweep racing track reflection spot; Car mould carries out the photoelectric sensor mode that belongs to of path detection by minority isolated point reflecting brightness on collection racing track.
For camera tracking car mould, can be divided into energy supplying system, signal acquiring system, central processing system, executive system.Wherein energy supplying system is other system power supply; Signal acquiring system passes through camera collection image information, and is transferred to central processing system; Central processing system is processed image information, generally, by a fixing threshold value, gray level image is changed into the image of binaryzation, and binary image is processed, and calculates the speed of a motor vehicle and the direction of expectation, controls the rotating speed of motor and the corner of steering wheel; Executive system comprises wheel, steering wheel and CD-ROM drive motor, and steering wheel is controlled front wheel angle, and CD-ROM drive motor is controlled rear wheel rotation speed.
For existing camera tracking car mould, there is following problem:
1, use fixing prediction, the data of every width image being got to same a line are calculated side-play amount, control motor and steering wheel, do not give full play to the advantage that camera collection contains much information, for the bend bad adaptability of different curvature.
2, entire image adopts a fixing threshold value to carry out binaryzation, thereby easily occurs that a long way off obscurity boundary affects racecourse information and extracts.
3, for image clearly, deal with reliability higher, once fuzzy but image border occurs, just easily erroneous judgement is disconnected to lose the situation of line, causes the run chaotically situation of outlet of car, for the place that distant place distortion is serious, can not well process.
4, adopt traditional PID to control, by an a set of pid parameter of equipment debugging being realized to the control of steering wheel and motor, this method is too general, and the selected adjusting of parameter is very difficult, does not have careful analytical model just to apply mechanically formula, controls redundancy.
Summary of the invention
The object of the present invention is to provide a kind of improved camera Intelligent tracking car mould for racing track.
The object of the invention is to be achieved through the following technical solutions:
A camera Intelligent tracking car mould for racing track, comprises energy supplying system, signal acquiring system, central processing system, executive system; Wherein energy supplying system is other system power supply; Signal acquiring system passes through camera collection image information, and is transferred to central processing system; Central processing system is processed image information, by side-play amount, is the distance control rotating speed of motor and the corner of steering wheel between car axis and racing track axis, and then controls speed and the direction of car; Executive system comprises wheel, steering wheel and CD-ROM drive motor, and steering wheel is controlled front wheel angle, and CD-ROM drive motor is controlled rear wheel rotation speed; Described central processing system comprises following treatment step:
One, to the Binary Sketch of Grey Scale Image of collecting from signal acquiring system;
Two, the image after binaryzation is carried out to sideline extraction;
Three, according to the sideline of extracting, carry out racing track type identification, and definite car mould direction of advancing:
(1) width between the inward flange in racing track left and right in overall width and entire image first relatively, if the width between the inward flange of racing track left and right is larger than overall width, can straight-line pass, the optimum orientation of selecting the line at inward flange mid point He Chemo center, racing track left and right to advance as car mould;
(2) if can not straight-line pass, carry out optimal route selection, from a line of image farthest to searching for nearby: pass through racing track feature modeling racing track centre coordinate a line, the line at racing track centre coordinate He Chemo center is compensated to car Mould Breadth degree to both sides, if the region after compensation has surpassed the border of racing track, search for next line, thereby can be by being no more than the row on border from far and closely finding first to meet car mould, the line at this line racing track centre coordinate He Chemo center is the optimum orientation that car mould advances;
Four, the angle advancing between optimum orientation and the actual working direction of Che Mo by calculating car mould, controls steering wheel and realizes the control to direction;
Five, by side-play amount, obtain the desired speed of car mould, control CD-ROM drive motor and realize the control to speed.
Beneficial effect
The invention provides a kind of improved camera Intelligent tracking car mould for racing track, the information that can make full use of entire image is carried out racing track extraction, overcome the problem of image blurring distortion, determine in real time the best working direction of car mould, thereby make car mould realize Intelligent tracking.
Accompanying drawing explanation
Fig. 1 is the processing flow chart of the single-chip microcomputer in embodiment;
Fig. 2 is the process flowchart that in embodiment, single-chip microcomputer is carried out each width image information;
Fig. 3 is the optimal route selection schematic diagram of car mould.
Embodiment
Below in conjunction with accompanying drawing, illustrate the preferred embodiment of the present invention.
The car mould of the present embodiment can be divided into energy supplying system, signal acquiring system, central processing system, executive system.
(1) energy supplying system
This dolly adopts the chargeable Ni-Cd battery of 7.2V/2000mAh as power supply, and by voltage boosting and stabilizing circuit, to single-chip microcomputer, steering wheel, the first-class power supply of shooting, wherein camera is 12V, and single-chip microcomputer is 5V, and steering wheel is supply voltage-0.7V.
(2) signal acquiring processing system
This dolly adopts the CCD of Sony camera collection image information with an automatic light meter, gets the image array of 46 row 134 row.In addition, Ben Chemo has also installed scrambler at the same time on hind axle, carries out speed acquisition.
(3) central processing system
This dolly processor adopting Freescale MC9S12XS12816 position single-chip microcomputer, processes image information, by side-play amount, controls the rotating speed of motor and the corner of steering wheel, and then controls speed and the direction of car.
(4) executive system
The executive system of this dolly is FUTABA S3010 steering wheel, RS-380-ST3545 CD-ROM drive motor, and steering wheel is controlled front wheel angle, adopts horizontal mounting means, and CD-ROM drive motor is controlled rear wheel rotation speed.
Accompanying drawing 1 is the processing flow chart of single-chip microcomputer in embodiment.
First single-chip microcomputer carries out initialization, then by toggle switch, obtains control data, such as the minimax speed of car mould, the coefficient etc. that brakes, then controls and dispatches a car.In the process of travelling at dolly, single-chip microcomputer is processed image information in real time, the about every 17ms transmission piece image information of camera.
The processing procedure that single-chip microcomputer is carried out for each width image information as shown in Figure 2.Concrete processing procedure is:
One, to the Binary Sketch of Grey Scale Image of collecting from signal acquiring system;
The method of traditional binary image is normally taked a fixing threshold value to entire image.The method of taking in the present embodiment is: the maximal value and the minimum value that search out every row gradation of image value, for every a line arranges a threshold value, this threshold value is (maximal value-(maximal value-minimum value)/3), for entire image, obtain an array consisting of the threshold value of every a line, this array is constantly updated along with the input of every piece image.The advantage of the method is: no matter how how the light of racing track changes, as long as have gap between black and white, so just can find a suitable threshold value that racing track and marginal line area are separated.
Set after threshold value, what for gray-scale value, be greater than threshold value gets 1, and what gray-scale value was less than to threshold value gets 0.The storage mode of gray level image is before for to deposit by word, 0 and 1 representative be exactly 0 and 1 these two numerals, account for a word, a word can be deposited eight, each 1 is saved as 00000001.The data that obtain after binaryzation only have 0 and 1 two kind, therefore change into and all according to position, depositing 0 and 1, thereby storage space is reduced to original 1/8th.
Two, extract in sideline
For the image after binaryzation, from nearest a line, from the close-by examples to those far off carry out:
(1) from this interline, start respectively search to the left and right sides, after occurring one 1, follow the situation (in binary image herein, 1 represents white, and 0 represents black) of two 0, first left side of 0 is designated as to boundary coordinate; If the first row is not followed the situation of two 0 after occurring one 1, continue to process next line until find effective the first row;
(2), after finding effective the first row, the point that row below starts search is that lastrow frontier point moves 5 some places to center line; Because racing track is continuous in adjacent row, so by the efficiency that can improve search is set like this;
(3) in certain a line, there is not finding the situation on border, by the view data of the first six row, carry out valuation; So just the fuzzy point of some loss in image can be supplemented out.
Three, according to the sideline of extracting, carry out racing track type identification:
(1) width between the inward flange in racing track left and right in overall width and entire image first relatively, if the width between the inward flange of racing track left and right is larger than overall width, can straight-line pass, the optimum orientation of selecting the line at inward flange mid point He Chemo center, racing track left and right to advance as car mould; Under can the situation of straight-line pass, continuing judgement racing track type be little S or straight way, if side-play amount is the constantly variation of distance between car axis and racing track axis, is little S racing track, otherwise is straight way, at little s racing track, gets on the bus and will slow down;
(2) if can not straight-line pass, carry out optimal route selection, from a line of image farthest to searching for nearby: pass through racing track feature modeling racing track centre coordinate a line, the line at racing track centre coordinate He Chemo center is compensated to car Mould Breadth degree to both sides, if the region after compensation has surpassed the border of racing track, search for next line, thereby can be by being no more than the row on border from far and closely finding first to meet car mould, the line at this line racing track centre coordinate He Chemo center is the optimum orientation that car mould advances.
As shown in Figure 3, S Wei Chemo center, A, B are respectively the racing track centre coordinate in different two row.For BS line, to both sides compensation car Mould Breadth degree, the region after compensation does not surpass the border of racing track; And AS line compensates car Mould Breadth degree to both sides, the region after compensation has surpassed the border of racing track.
Four, the angle advancing between optimum orientation and the actual working direction of Che Mo by calculating car mould, realizes the control to direction;
Five, by side-play amount, be the desired speed that distance between car axis and racing track axis obtains car mould, control CD-ROM drive motor and realize the control to speed.By being arranged on scrambler on hind axle, can return to the actual speed of car mould, thereby realize PD closed-loop control:
Desired speed=side-play amount * (minimum speed-maximal rate)/A+ maximal rate, wherein A is the variation range of side-play amount absolute value.
When steering wheel and CD-ROM drive motor are controlled, traditional PID controls by an a set of pid parameter of equipment debugging being realized to the control of steering wheel and motor, and this method is too general, and parameter selected regulate very difficult.The present embodiment is divided into side-play amount different interval, and speed is also divided into different interval, between each offset field and the combination of speed interval, debugs a suitable pid value.Use the method, can improve greatly the performance of car mould.
The present invention is not limited only to above embodiment, everyly utilizes mentality of designing of the present invention, does the design of some simple change, within all should counting protection scope of the present invention.
Claims (1)
1. for a camera Intelligent tracking car mould for racing track, comprise energy supplying system, signal acquiring system, central processing system, executive system; Wherein energy supplying system is other system power supply; Signal acquiring system passes through camera collection image information, and is transferred to central processing system; Central processing system is processed image information, by side-play amount, is the distance control rotating speed of motor and the corner of steering wheel between car axis and racing track axis, and then controls speed and the direction of car; Executive system comprises wheel, steering wheel and CD-ROM drive motor, and steering wheel is controlled front wheel angle, and CD-ROM drive motor is controlled rear wheel rotation speed; It is characterized in that, described central processing system comprises following treatment step:
One, to the Binary Sketch of Grey Scale Image of collecting from signal acquiring system;
Two, the image after binaryzation is carried out to sideline extraction;
Three, according to the sideline of extracting, carry out racing track type identification, and definite car mould direction of advancing:
(1) width between the inward flange in racing track left and right in overall width and entire image first relatively, if the width between the inward flange of racing track left and right is larger than overall width, can straight-line pass, the optimum orientation of selecting the line at inward flange mid point He Chemo center, racing track left and right to advance as car mould;
(2) if can not straight-line pass, carry out optimal route selection, from a line of image farthest to searching for nearby: pass through racing track feature modeling racing track centre coordinate a line, the line at racing track centre coordinate He Chemo center is compensated to car Mould Breadth degree to both sides, if the region after compensation has surpassed the border of racing track, search for next line, thereby can be by being no more than the row on border from far and closely finding first to meet car mould, the line at this line racing track centre coordinate He Chemo center is the optimum orientation that car mould advances;
Four, the angle advancing between optimum orientation and the actual working direction of Che Mo by calculating car mould, controls steering wheel and realizes the control to direction;
Five, by side-play amount, obtain the desired speed of car mould, control CD-ROM drive motor and realize the control to speed;
Wherein, during to Binary Sketch of Grey Scale Image, search out maximal value and the minimum value of every row gradation of image value, for every a line arranges a threshold value, this threshold value is (great Zhi – (great Zhi – minimum value)/3), for entire image, obtain an array being formed by the threshold value of every a line, this array is constantly updated along with the input of every piece image;
During to Binary Sketch of Grey Scale Image, set after threshold value, what for gray-scale value, be greater than threshold value gets 1, and what gray-scale value was less than to threshold value gets 0, and gray level image is changed into according to position and being deposited;
The method that extract in sideline is, for the image after binaryzation, from nearest a line, from the close-by examples to those far off to carry out:
(1) from this interline, start respectively search to the left and right sides, after occurring one 1, follow the situation of two 0, first left side of 0 is designated as to boundary coordinate; If the first row is not followed the situation of two 0 after occurring one 1, continue to process next line until find effective the first row; In binary image herein, 1 represents white, and 0 represents black;
(2), after finding effective the first row, the point that row below starts search is that lastrow frontier point moves 5 some places to center line;
In certain a line, there is not finding the situation on border, by the view data of the first six row, carry out valuation; So just the fuzzy point of some loss in image can be supplemented out;
In step 5, by side-play amount, obtain the desired speed of car mould,
Desired speed=side-play amount * (minimum Su Du – maximal rate)/A+ maximal rate, wherein A is the variation range of side-play amount absolute value;
When steering wheel and CD-ROM drive motor are controlled, side-play amount is divided into different interval, speed is also divided into different interval, between each offset field and the combination of speed interval, debugs a suitable pid value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210182070.4A CN102662402B (en) | 2012-06-05 | 2012-06-05 | Intelligent camera tracking car model for racing tracks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210182070.4A CN102662402B (en) | 2012-06-05 | 2012-06-05 | Intelligent camera tracking car model for racing tracks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102662402A CN102662402A (en) | 2012-09-12 |
| CN102662402B true CN102662402B (en) | 2014-04-09 |
Family
ID=46771907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210182070.4A Expired - Fee Related CN102662402B (en) | 2012-06-05 | 2012-06-05 | Intelligent camera tracking car model for racing tracks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102662402B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123535A (en) * | 2014-07-01 | 2014-10-29 | 北京联合大学 | Monocular vision robot rapid tracking method based on road correction |
| CN106055745B (en) * | 2016-05-20 | 2019-02-19 | 浙江大学 | A method of linear CCD carriage simulation model is established based on MATLAB |
| US10215576B2 (en) * | 2016-08-25 | 2019-02-26 | GM Global Technology Operations LLC | Energy-optimized vehicle route selection |
| CN106950950A (en) * | 2017-03-02 | 2017-07-14 | 广东工业大学 | A kind of automobile doubling accessory system and control method based on camera |
| CN106990786A (en) * | 2017-05-12 | 2017-07-28 | 中南大学 | The tracking method of intelligent carriage |
| US10140530B1 (en) * | 2017-08-09 | 2018-11-27 | Wipro Limited | Method and device for identifying path boundary for vehicle navigation |
| CN108549273B (en) * | 2018-02-13 | 2020-11-03 | 杭州电子科技大学 | Pull racing driver operation prediction and road book auxiliary generation system and implementation method |
| CN109033932B (en) * | 2018-05-23 | 2020-11-10 | 华南师范大学 | Track identification method, track identification system, intelligent vehicle track patrol method and track patrol system |
| CN109871014B (en) * | 2019-02-14 | 2021-09-03 | 南京师范大学 | Intelligent trolley tracking method based on electromagnetic sensor electromotive force center value partition |
| CN110008895B (en) * | 2019-04-01 | 2023-01-17 | 中南林业科技大学 | Track characteristic identification method and intelligent racing car |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5661472A (en) * | 1993-01-31 | 1997-08-26 | Isuzu Motors Limited | Off-lane alarm apparatus |
| CN101067557A (en) * | 2007-07-03 | 2007-11-07 | 北京控制工程研究所 | Environment sensing one-eye visual navigating method adapted to self-aid moving vehicle |
| CN102201054A (en) * | 2011-01-07 | 2011-09-28 | 南京理工大学 | Method for detecting street lines based on robust statistics |
| CN102269595A (en) * | 2010-06-02 | 2011-12-07 | 东北大学 | Embedded monocular vision guidance system based on guidance line identification |
-
2012
- 2012-06-05 CN CN201210182070.4A patent/CN102662402B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5661472A (en) * | 1993-01-31 | 1997-08-26 | Isuzu Motors Limited | Off-lane alarm apparatus |
| CN101067557A (en) * | 2007-07-03 | 2007-11-07 | 北京控制工程研究所 | Environment sensing one-eye visual navigating method adapted to self-aid moving vehicle |
| CN102269595A (en) * | 2010-06-02 | 2011-12-07 | 东北大学 | Embedded monocular vision guidance system based on guidance line identification |
| CN102201054A (en) * | 2011-01-07 | 2011-09-28 | 南京理工大学 | Method for detecting street lines based on robust statistics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102662402A (en) | 2012-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102662402B (en) | Intelligent camera tracking car model for racing tracks | |
| CN109435942A (en) | A kind of parking stall line parking stall recognition methods and device based on information fusion | |
| CN110210389B (en) | Multi-target identification tracking method for road traffic scene | |
| CN101840507B (en) | Target tracking method based on character feature invariant and graph theory clustering | |
| CN112498367B (en) | Driving track planning method and device, automobile, controller and computer readable storage medium | |
| CN104008387A (en) | Lane line detection method based on feature point piecewise linear fitting | |
| CN203063940U (en) | Pilotless automobile device | |
| CN102810250A (en) | Video based multi-vehicle traffic information detection method | |
| CN104111651A (en) | Automatic walking equipment and method for automatic walking equipment to return to stop station | |
| CN104008645A (en) | Lane line predicating and early warning method suitable for city road | |
| CN102269595A (en) | Embedded monocular vision guidance system based on guidance line identification | |
| CA2950791A1 (en) | Binocular visual navigation system and method based on power robot | |
| CN104751151A (en) | Method for identifying and tracing multiple lanes in real time | |
| CN114596712B (en) | Vehicle following control method and system | |
| CN103839264A (en) | Detection method of lane line | |
| CN110009029A (en) | Feature matching method based on point cloud segmentation | |
| CN108459600A (en) | A kind of vision navigation system of AGV trolleies | |
| CN103544714A (en) | Visual tracking system and method based on high-speed image sensor | |
| CN111038488A (en) | Energy optimization control method and device for hybrid electric vehicle | |
| CN103065325A (en) | Target tracking method based on color distance of multicolors and image dividing and aggregating | |
| CN112819864A (en) | Driving state detection method and device and storage medium | |
| CN102592290A (en) | Method for detecting moving target region aiming at underwater microscopic video | |
| CN109284731A (en) | A kind of parking stall kind identification method of the inclined parking stall for automated parking system | |
| CN114495066A (en) | Method for assisting backing | |
| CN110533692A (en) | A kind of automatic tracking method towards target mobile in unmanned plane video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140409 Termination date: 20180605 |