CN105021126A - Truck side guard rail mounting size measurement system and method based on machine vision technology - Google Patents
Truck side guard rail mounting size measurement system and method based on machine vision technology Download PDFInfo
- Publication number
- CN105021126A CN105021126A CN201510344734.6A CN201510344734A CN105021126A CN 105021126 A CN105021126 A CN 105021126A CN 201510344734 A CN201510344734 A CN 201510344734A CN 105021126 A CN105021126 A CN 105021126A
- Authority
- CN
- China
- Prior art keywords
- image
- protective device
- coordinate
- tire
- side guard
- 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.)
- Pending
Links
Abstract
The invention relates to a truck side guard rail mounting size measurement system and a method based on a machine vision technology, so as to solve problems that as the truck guard rail is detected manually in the prior art, random errors such as a reading error and an environment error exist, the measurement result is influenced, and the measurement efficiency is low. The system comprises a ranging module, a graph acquisition module and a graph processing module, wherein the graph acquisition module comprises a camera unit, the ranging module is connected with the camera unit, the graph processing module comprises an image information processing unit, and the camera unit is connected with the image information processing unit. The system acquires two-dimensional image information of the side surface of the truck via the image acquisition module, the image is analyzed and processed via the image processing module, and mounting size information of the truck side guard rail is obtained. The system and the method of the invention have the advantages that a truck side guard device does not need to be touched, the mounting size of the truck side guard device can be quickly and effectively measured, and the detection efficiency is higher.
Description
Technical field
The present invention relates to a kind of truck protective guard detection technique, especially relate to a kind of based on machine vision technique truck side guard railing installation dimension measuring system and method.
Background technology
Truck body is longer, and the driver in pilothouse exists blind area, if there is traffic hazard when driving, easily causes car, battery truck, motorcycle etc. to pierce at the bottom of lorry car or pedestrian is scratched and is involved at the bottom of car, causes injury even dead.Lorry rigidity is large, and quality is large, when other objects, comprises battery truck, motorcycle etc. when clashing into it, and comparatively slightly, the injury that is subject to of the other side is more serious on the contrary in the injury that lorry itself and driver thereof are subject to.As preventive measure, within 2004, country has issued the national standard (GB7258-2004) of " motor vehicle safe and technical specification ", gross mass is greater than to the truck and trailer of 3500kg, must provides on request, adopts rear flank protective device.These preventive measure greatly reduce pedestrian in traffic hazard of knowing clearly and are rolled even dead quantity of causing injury.Common load-carrying vehicle side protection device is welded, and needs certain rigidity.When traffic hazard occurs, protective device can play barrier effect.Protective device should be greater than the minor increment required by relevant national standard to the distance on the forward and backward wheel of lorry, vehicle frame and ground.Current load-carrying vehicle protective device detects in motor vehicle safety inspection mechanism, vehicle administration office.The detection method of lorry side protection device installation dimension is mainly manually checked, steel tape or ruler is adopted to carry out measurement to judge whether meeting national standard, in measuring process, inevitably introduce the stochastic error such as reading error, environmental error, human factor ratio is easier to affect measurement result, and it is lower to measure efficiency.
Summary of the invention
The present invention mainly solves desk checking truck protective guard in prior art and there is the stochastic error such as reading error, environmental error, affect measurement result, measure the problem that efficiency is lower, provide a kind of without the need to contacting protective device, detect data more accurate, detection efficiency higher based on machine vision technique truck side guard railing installation dimension measuring system, present invention also offers a kind of based on machine vision technique truck side guard railing installation dimension measuring method.
Above-mentioned technical matters of the present invention is mainly solved by following technical proposals: a kind of based on machine vision technique truck side guard railing installation dimension measuring system, include range finder module, figure acquisition module and pattern process module, figure acquisition module comprises camera unit, range finder module is connected with camera unit, pattern process module comprises Image Information Processing unit, and camera unit is connected with Image Information Processing unit;
Range finder module: distance lorry being detected, whether detect and have lorry close, if detect, lorry is close, send instruction and start figure acquisition module;
Figure acquisition module: gather an image at interval of a period of time, until range finder module detects that lorry is left away, contrasts the image gathered, chooses the image of clear picture, moderate range;
Pattern process module: carry out pre-service to image, extracts object edge, calculates the size between object edge.
The present invention need not contact lorry side protection device, just effectively can measure the installation dimension of lorry side protection device fast, and compare artificial examination and detect data more accurately, detection efficiency is higher, measures in addition without the need to deliberately parking, right place.
As a kind of preferred version, described range finder module comprise connect successively ultrasonic transmission/reception unit, amplify shaping unit and compare processing unit, compare processing unit and be connected with camera unit.This programme range finder module adopts ultrasonic distance-measuring sensor, and ultrasonic transmission/reception unitary form, this programme equipment making is with low cost, and measuring accuracy is high, and metrical error is little.
As a kind of preferred version, be arranged on passage place, vehicle toll station, at porte-cochere setting surveyed area, the side of surveyed area be provided with Bracket for Inspection, described range finder module and camera unit are arranged on Bracket for Inspection respectively, and camera unit image pickup scope covers surveyed area.This programme mounts the system to vehicle toll station place, is not limited in vehicle toll station, also can be arranged on other local uses.When lorry Kai Guo charge station's porte-cochere, range finder module has detected lorry, then toggling camera unit is started working, and takes lorry side, obtains the image information of lorry side, then sends pattern process module to and process.
A kind of based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that comprising the following steps:
S1. camera unit setting different distance is demarcated;
S2. range finder module detects that controlling figure acquisition module after lorry enters surveyed area starts working, figure acquisition module gathers multiple lorry side images, until range finder module detects that lorry is left away, figure acquisition module is classified to the image gathered, and the image choosing wherein clear picture, moderate range sends to pattern process module; The image of protective device and rear tyre, protective device and the image of front tyre, the image of protective device are selected respectively to Images Classification, then chooses the image of clear picture in them, moderate range.This choosing method can adopt outline extraction technique to carry out image recognition.Figure acquisition module adopts a lorry side image every 3 seconds.
S3. pattern process module is to Image Segmentation Using, respectively the image of protective device part and Tire portions is carried out to pre-service and extracts edge, protective device border pixel data is gone out according to edge calculations, the tire center of circle and radius pixel data, calculate the pixel data of guard rail installation dimension according to these pixel datas;
S4. detect lorry to the distance of camera unit, choose the calibrating parameters of closest-approach distance, calculate the actual installation dimensional data of lorry side guard rail.
The present invention need not contact lorry side protection device, just effectively can measure the installation dimension of lorry side protection device fast, and compare artificial examination and detect data more accurately, detection efficiency is higher.
As a kind of preferred version, carrying out calibration process to camera unit in step S1 is: adopt scaling board to demarcate, by scaling board in camera unit operating distance setting range, once demarcate every constant spacing, obtain the camera interior and exterior parameter of each distance.Generally be set in operating distance 800 ~ 1500cm distance, once demarcate every 50cm.This programme adopts Halcan calibration algorithm to operate.
As a kind of preferred version, in step S3, Image Segmentation Using is comprised the following steps:
S301. gray processing, binary conversion treatment are carried out to the image gathered;
S302. on the basis of bianry image, carry out Hough transform process, detect the maximum radius of truck tire, export the row coordinate of tire maximum radius 0 degree or 180 degree direction pixel according to Images Classification; According to Images Classification, if the image of protective device and rear tyre, then export tire maximum radius 180 degree of direction pixel point range coordinates, if the image of protective device and front tyre, then export tire maximum radius 0 degree of direction pixel point range coordinate.Here coordinate, on image, based on image coordinate system, is all pixel coordinate.
S303. along this row coordinate continuation setting quantity pixel forward, as the reference position of automatic identification point, Iamge Segmentation is become to comprise protective device part and Tire portions.Setting number of pixels point can be 20 each pixels, as the reference position of automatic identification point, accurately can separate protective device and tire in advance.
As a kind of preferred version, in step S3, in image, the acquisition of protective device border pixel data specifically comprises the following steps:
S311. gray processing, image smoothing pre-service are carried out to the image of protective device part; This preprocess method is published technology, and particular content can see document: Liu Guangqi, Zheng Xiao gesture, Zhang Xiaobo.Based on the algorithm of locating license plate of vehicle [J] that image texture characteristic extracts.Journal of Image and Graphics, 2005,10 (11): 1419-1422.
S312. the Canny Operators Algorithm of improvement is adopted to extract the edge of protective device; The Canny Operators Algorithm of this improvement is known disclosed technology, and particular content can see document: Li Qingli, Zhang Shaojun, Li Zhongfu etc.A kind of sub-pix algorithm of subdivision [J] improved based on polynomial interpolation.University of Science & Technology, Beijing's journal, 2003,25 (3): 280-283.When edge is extracted to protective device, its Important Characteristic Points is distributed in horizontal direction and vertical direction, only need the gradient direction obtaining horizontal and vertical edge, the point in other direction is all need not main points, gradient direction does not need to obtain yet, and therefore employing level, vertical formwork direction carry out rim detection.The level, the vertical formwork that adopt.
S313. the some set of each boundary line, protective device edge is obtained,
Scan by column each pixel from top to bottom, run into white point output coordinate, then turn to next column to continue scanning, and export white point coordinates, until the end of scan, export all point sets in following boundary line;
According to Images Classification, each pixel of lining by line scan from right to left or from left to right, runs into white point output coordinate, then turns to lastrow to continue scanning, and exports white point coordinates, until the end of scan, exports boundary line, the right or all point sets in boundary line, the left side;
Scan by column each pixel from top to bottom, run into white point as current point, continue scanning, upward continuation 300 pixels, if without white point, this point is frontier point, and output coordinate point, turn to next column to continue scanning, and export white point coordinates, until the end of scan, export upper border line institute pointed set;
S314. carry out least square fitting to the point set of each boundary line respectively, matching obtains each boundary line, obtains the coordinate of upper angle point and lower angle point according to boundary line intersection point.The least square fitting algorithm adopted in this programme is known public technology, specifically can list of references: principle of least square method and simple application thereof.
As a kind of preferred version, in step S3, in image, the tire center of circle and the acquisition of radius pixel data specifically comprise the following steps:
S321. gray processing, image smoothing pre-service are carried out to the image of Tire portions, then carry out Threshold segmentation, mathematical morphology corrosion treatment; Due to the feature of image of tire self, threshold value reasonable in design divisible go out efficiency frontier, adopt segmentation threshold 40,140 time can preferably by truck tire edge segmentation out.In this step, preprocess method is published technology, and particular content can see document: Liu Guangqi, Zheng Xiao gesture, Zhang Xiaobo.Based on the algorithm of locating license plate of vehicle [J] that image texture characteristic extracts.Journal of Image and Graphics, 2005,10 (11): 1419-1422.
S322. the Canny Operators Algorithm of improvement is adopted to extract the edge of tire; The Canny Operators Algorithm of this improvement is known disclosed technology, and particular content can see document: Li Qingli, Zhang Shaojun, Li Zhongfu etc.A kind of sub-pix algorithm of subdivision [J] improved based on polynomial interpolation.University of Science & Technology, Beijing's journal, 2003,25 (3): 280-283.When edge is extracted to tire, because tire is circular, Important Characteristic Points is distributed in all directions, only has after segmenting gradient direction, obtain (45 °, 135 °, 180 °, 235 °, 270 °, 315 °) etc. 8 gradient directions, connective Single pixel edge preferably could be extracted, therefore adopt 8 template directions to carry out rim detection.The template in 8 directions adopted.
S323. Hough transform is carried out to the edge image extracted,
Extracting pixel value in image is all pixels of 1, and counts total number of pixels; Because image information content is large, comprising protective device and tyre rim, is not again adjacent element, for improving counting yield, does not travel through entire image, and only scanning the 1st row are to the 1300th row.
According to the scope (r of tire location setting radius in image
min, r
max), radius of circle r step-length, angle step and threshold value; For improving computing velocity, setting and can detect that radius of a circle scope is as (500,900).
According to formula
calculate center of circle horizontal ordinate a, in formula, b is ordinate, gets all over whole y value, thus determines effective a, b value;
According to effective a, b value, determine the index value of Hough numeral;
According to the index value obtained, by calculate accumulative, to construct the number of plies be r=r
max-r
minhough array;
Find out one deck that r is maximum, corresponding is exactly detects the maximum radius of circle;
Try to achieve all a, b values of radius layer, its mean value is central coordinate of circle (a
0, b
0).
As a kind of preferred version, the guard rail installation dimension pixel data calculated in step S3 comprises,
Protective device front and rear edge is to the pixel data of tire circumference tangent plane distance: calculate two angle point row coordinate mean values as protective device edge columns coordinate, record tire center of circle row coordinate again, namely the difference of two row coordinates obtains the pixel number of protective device end to the tire center of circle, then deducts radius length and obtain the pixel data of protective device front and rear edge to tire circumference tangent plane distance;
Protective device lower edge is to the pixel data of ground distance: choose lower angle point, record angle point row-coordinate as protective device lower edge row-coordinate, Hough transform process is carried out on the basis of bianry image, detect the maximum radius of truck tire, export the row-coordinate of tire maximum radius 270 degree of direction pixels, as the row-coordinate on ground, namely the difference of two row-coordinates obtains the pixel number of protective device lower edge to ground distance.
As a kind of preferred version, the actual installation dimensional data obtaining step of step S4 lorry side guard rail comprises:
S41: range finder module detects the distance of lorry to camera unit;
S42: pattern process module chooses the camera interior and exterior parameter obtained with the immediate distance calibration of distance that detects in step S41; Carry out at camera unit in calibration process, having have recorded the camera interior and exterior parameter carrying out demarcating under multiple distance, as long as now choose the camera interior and exterior parameter obtained to the immediate distance calibration of distance of camera unit with lorry, as being mapped to the parameter carrying out in world coordinate system calculating.
S43: the pixel data of guard rail installation dimension utilizes camera interior and exterior parameter to be mapped in world coordinate system to obtain the actual installation dimensional data of lorry side guard rail.
Therefore, advantage of the present invention is: need not contact lorry side protection device, just effectively can measure the installation dimension of lorry side protection device fast, and compare artificial examination and detect data more accurately, detection efficiency is higher; System results is simple, and volume is little, conveniently moving, and antijamming capability is strong, price economy; Measure without the need to deliberately parking, right place in addition.
Accompanying drawing explanation
Accompanying drawing 1 is a kind of electrical block diagram of the present invention;
Accompanying drawing 2 is a kind of mounting structure schematic diagram of the present invention;
Accompanying drawing 3 is a kind of schematic flow sheets of the present invention.
1-ultrasonic transmission/reception unit 2-amplifies shaping unit 3-and compares processing unit 4-camera unit 5-Image Information Processing unit 6-Bracket for Inspection
Embodiment
Below by embodiment, and by reference to the accompanying drawings, technical scheme of the present invention is described in further detail.
Embodiment:
The present embodiment is a kind of based on machine vision technique truck side guard railing installation dimension measuring system, as shown in Figure 1, includes range finder module, figure acquisition module and pattern process module.Apart from module comprise connect successively ultrasonic transmission/reception unit 1, amplify shaping unit 2 and compare processing unit 3.Figure acquisition module comprises camera unit 4, and pattern process module comprises Image Information Processing unit 5, compares processing unit and is connected with camera unit, and camera unit is connected with Image Information Processing unit.
System is applied in each toll station by the present embodiment.As shown in Figure 2, system is arranged on passage place, vehicle toll station to its mounting structure, at porte-cochere setting surveyed area, as dotted portion in figure.The side of surveyed area is provided with Bracket for Inspection 6, and range finder module and camera unit are arranged on Bracket for Inspection respectively, and camera unit image pickup scope covers surveyed area.
A kind of based on machine vision technique truck side guard railing installation dimension measuring method, as shown in Figure 3, comprise the following steps:
S1. camera unit setting different distance is demarcated;
S2. range finder module detects that controlling figure acquisition module after lorry enters surveyed area starts working, figure acquisition module gathers multiple lorry side images, can set and gather an image every 3 seconds, until range finder module detects that lorry is left away, figure acquisition module is classified to the image gathered, and the image choosing wherein clear picture, moderate range sends to pattern process module;
S3. pattern process module is to Image Segmentation Using, respectively the image of protective device part and Tire portions is carried out to pre-service and extracts edge, protective device border pixel data is gone out according to edge calculations, the tire center of circle and radius pixel data, calculate the pixel data of guard rail installation dimension according to these pixel datas;
S4. detect lorry to the distance of camera unit, choose the calibrating parameters of closest-approach distance, calculate the actual installation dimensional data of lorry side guard rail.
Wherein carrying out calibration process to camera unit in step S1 is: adopt scaling board to demarcate, by scaling board in camera unit operating distance setting range, once demarcate every constant spacing, obtain the camera interior and exterior parameter of each distance.Generally be set in operating distance 800 ~ 1500cm distance, once demarcate every 50cm.Demarcate and adopt Halcan calibration algorithm to operate.Exemplify one group of calibration result below, camera interior and exterior parameter value is:
Wherein, t
x, t
y, t
zunit be rice, α, the unit degree of being of beta, gamma, all the other are dimensionless.
The coordinate conversion of pixel on image just can be become the coordinate in world coordinate system by the inside and outside parameter according to video camera.
In step S3, Image Segmentation Using is comprised the following steps:
S301. gray processing, binary conversion treatment are carried out to the image gathered;
S302. on the basis of bianry image, carry out Hough transform process, detect the maximum radius of truck tire, export the row coordinate of tire maximum radius 0 degree or 180 degree direction pixel according to Images Classification; According to Images Classification, if the image of protective device and rear tyre, then export tire maximum radius 180 degree of direction pixel point range coordinates, if the image of protective device and front tyre, then export tire maximum radius 0 degree of direction pixel point range coordinate.
S303. along this row coordinate continuation setting quantity pixel forward, as the reference position of automatic identification point, Iamge Segmentation is become to comprise protective device part and Tire portions.
In step S3, in image, the acquisition of protective device border pixel data specifically comprises the following steps:
S311. gray processing, image smoothing pre-service are carried out to the image of protective device part;
S312. the Canny Operators Algorithm of improvement is adopted to extract the edge of protective device;
S313. the some set of each boundary line, protective device edge is obtained,
Scan by column each pixel from top to bottom, run into white point output coordinate, then turn to next column to continue scanning, and export white point coordinates, until the end of scan, export all point sets in following boundary line;
According to Images Classification, each pixel of lining by line scan from right to left or from left to right, runs into white point output coordinate, then turns to lastrow to continue scanning, and exports white point coordinates, until the end of scan, exports boundary line, the right or all point sets in boundary line, the left side;
Scan by column each pixel from top to bottom, run into white point as current point, continue scanning, upward continuation 300 pixels, if without white point, this point is frontier point, and output coordinate point, turn to next column to continue scanning, and export white point coordinates, until the end of scan, export upper border line institute pointed set;
S314. carry out least square fitting to the point set of each boundary line respectively, matching obtains each boundary line, obtains the coordinate of upper angle point and lower angle point according to boundary line intersection point.
In step S3, in image, the tire center of circle and the acquisition of radius pixel data specifically comprise the following steps:
S321. gray processing, image smoothing pre-service are carried out to the image of Tire portions, then carry out Threshold segmentation, mathematical morphology corrosion treatment;
S322. the Canny Operators Algorithm of improvement is adopted to extract the edge of tire;
S323. Hough transform is carried out to the edge image extracted,
Extracting pixel value in image is all pixels of 1, and counts total number of pixels;
According to the scope (r of tire location setting radius in image
min, r
max), radius of circle r step-length, angle step and threshold value;
According to formula
calculate center of circle horizontal ordinate a, in formula, b is ordinate, gets all over whole y value, thus determines effective a, b value;
According to effective a, b value, determine the index value of Hough numeral;
According to the index value obtained, by calculate accumulative, to construct the number of plies be r=r
max-r
minhough array;
Find out one deck that r is maximum, corresponding is exactly detects the maximum radius of circle;
Try to achieve all a, b values of radius layer, its mean value is central coordinate of circle (a
0, b
0).
Obtaining the coordinate of angle point and lower angle point on protective device, and after tire radius and central coordinate of circle, just can calculate the installation dimension pixel data of protective device, installation dimension pixel data comprises protective device front and rear edge to the pixel data of tire circumference tangent plane distance, protective device lower edge to the pixel data of ground distance.
Protective device front and rear edge to the pixel data acquisition process of tire circumference tangent plane distance is: calculate two angle point row coordinate mean values as protective device edge columns coordinate, record tire center of circle row coordinate again, namely the difference of two row coordinates obtains the pixel number of protective device end to the tire center of circle, then deducts radius length and obtain the pixel data of protective device front and rear edge to tire circumference tangent plane distance.
Protective device lower edge to the pixel data acquisition process of ground distance is: choose lower angle point, record angle point row-coordinate as protective device lower edge row-coordinate, Hough transform process is carried out on the basis of bianry image, detect the maximum radius of truck tire, export the row-coordinate of tire maximum radius 270 degree of direction pixels, as the row-coordinate on ground, namely the difference of two row-coordinates obtains the pixel number of protective device lower edge to ground distance.
Range finder module detects the distance of lorry to camera unit, and pattern process module is chosen with this apart from the camera interior and exterior parameter obtained in immediate distance calibration; The pixel data of guard rail installation dimension utilizes camera interior and exterior parameter to be mapped in world coordinate system to obtain the actual installation dimensional data of lorry side guard rail.
Specific embodiment described herein is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various amendment or supplement or adopt similar mode to substitute to described specific embodiment, but can't depart from spirit of the present invention or surmount the scope that appended claims defines.
Although more employ ultrasonic transmission/reception unit herein, amplify shaping unit, compare processing unit, the term such as camera unit, Image Information Processing unit, do not get rid of the possibility using other term.These terms are used to be only used to describe and explain essence of the present invention more easily; The restriction that they are construed to any one additional is all contrary with spirit of the present invention.
Claims (10)
1. one kind based on machine vision technique truck side guard railing installation dimension measuring system, it is characterized in that: include range finder module, figure acquisition module and pattern process module, figure acquisition module comprises camera unit (4), range finder module is connected with camera unit, pattern process module comprises Image Information Processing unit (5), and camera unit is connected with Image Information Processing unit;
Range finder module: distance lorry being detected, and whether detection has lorry close, if detect, lorry is close, sends instruction and starts figure acquisition module;
Figure acquisition module: gather an image at interval of a period of time, until range finder module detects that lorry is left away, contrasts the image gathered, chooses the image of clear picture, moderate range;
Pattern process module: carry out pre-service to image, extracts object edge, calculates the size between object edge.
2. according to claim 1 based on machine vision technique truck side guard railing installation dimension measuring system, it is characterized in that described range finder module comprise connect successively ultrasonic transmission/reception unit (1), amplify shaping unit (2) and compare processing unit (3), compare processing unit and be connected with camera unit (4).
3. according to claim 1 based on machine vision technique truck side guard railing installation dimension measuring system, it is characterized in that being arranged on passage place, vehicle toll station, at porte-cochere setting surveyed area, Bracket for Inspection (6) is provided with in the side of surveyed area, described range finder module and camera unit (4) are arranged on Bracket for Inspection respectively, and camera unit image pickup scope covers surveyed area.
4., based on a machine vision technique truck side guard railing installation dimension measuring method, adopt the system in any one of claim 1-3, it is characterized in that comprising the following steps:
S1. camera unit setting different distance is demarcated;
S2. range finder module detects that controlling figure acquisition module after lorry enters surveyed area starts working, figure acquisition module gathers multiple lorry side images, until range finder module detects that lorry is left away, figure acquisition module is classified to the image gathered, and the image choosing wherein clear picture, moderate range sends to pattern process module;
S3. pattern process module is to Image Segmentation Using, respectively the image of protective device part and Tire portions is carried out to pre-service and extracts edge, protective device border pixel data is gone out according to edge calculations, the tire center of circle and radius pixel data, calculate the pixel data of guard rail installation dimension according to these pixel datas;
S4. detect lorry to the distance of camera unit, choose the calibrating parameters of closest-approach distance, calculate the actual installation dimensional data of lorry side guard rail.
5. according to claim 4 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that carrying out calibration process to camera unit in step S1 is: adopt scaling board to demarcate, by scaling board in camera unit operating distance setting range, once demarcate every constant spacing, obtain the camera interior and exterior parameter of each distance.
6. according to claim 4 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that comprising the following steps Image Segmentation Using in step S3:
S301. gray processing, binary conversion treatment are carried out to the image gathered;
S302. on the basis of bianry image, carry out Hough transform process, detect the maximum radius of truck tire, export the row coordinate of tire maximum radius 0 degree or 180 degree direction pixel according to Images Classification;
S303. along this row coordinate continuation setting quantity pixel forward, as the reference position of automatic identification point, Iamge Segmentation is become to comprise protective device part and Tire portions.
7. according to claim 4 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that in step S3, in image, the acquisition of protective device border pixel data specifically comprises the following steps:
S311. gray processing, image smoothing pre-service are carried out to the image of protective device part;
S312. the Canny Operators Algorithm of improvement is adopted to extract the edge of protective device;
S313. the some set of each boundary line, protective device edge is obtained,
Scan by column each pixel from top to bottom, run into white point output coordinate, then turn to next column to continue scanning, and export white point coordinates, until the end of scan, export all point sets in following boundary line;
According to Images Classification, each pixel of lining by line scan from right to left or from left to right, runs into white point output coordinate, then turns to lastrow to continue scanning, and exports white point coordinates, until the end of scan, exports boundary line, the right or all point sets in boundary line, the left side;
Scan by column each pixel from top to bottom, run into white point as current point, continue scanning, upward continuation 300 pixels, if without white point, this point is frontier point, and output coordinate point, turn to next column to continue scanning, and export white point coordinates, until the end of scan, export upper border line institute pointed set;
S314. carry out least square fitting to the point set of each boundary line respectively, matching obtains each boundary line, obtains the coordinate of upper angle point and lower angle point according to boundary line intersection point.
8. according to claim 4 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that in step S3, in image, the tire center of circle and the acquisition of radius pixel data specifically comprise the following steps:
S321. gray processing, image smoothing pre-service are carried out to the image of Tire portions, then carry out Threshold segmentation, mathematical morphology corrosion treatment;
S322. the Canny Operators Algorithm of improvement is adopted to extract the edge of tire;
S323. Hough transform is carried out to the edge image extracted,
Extracting pixel value in image is all pixels of 1, and counts total number of pixels; According to the scope (r of tire location setting radius in image
min, r
max), radius of circle r step-length, angle step and threshold value;
According to formula
calculate center of circle horizontal ordinate a, in formula, b is ordinate, gets all over whole y value, thus determines effective a, b value;
According to effective a, b value, determine the index value of Hough numeral;
According to the index value obtained, by calculate accumulative, to construct the number of plies be r=r
max-r
minhough array;
Find out one deck that r is maximum, corresponding is exactly detects the maximum radius of circle;
Try to achieve all a, b values of radius layer, its mean value is central coordinate of circle (a
0, b
0).
9. according to claim 7 or 8 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that the guard rail installation dimension pixel data calculated in step S3 comprises,
Protective device front and rear edge is to the pixel data of tire circumference tangent plane distance: calculate two angle point row coordinate mean values as protective device edge columns coordinate, record tire center of circle row coordinate again, namely the difference of two row coordinates obtains the pixel number of protective device end to the tire center of circle, then deducts radius length and obtain the pixel data of protective device front and rear edge to tire circumference tangent plane distance;
Protective device lower edge is to the pixel data of ground distance: choose lower angle point, record angle point row-coordinate as protective device lower edge row-coordinate, Hough transform process is carried out on the basis of bianry image, detect the maximum radius of truck tire, export the row-coordinate of tire maximum radius 270 degree of direction pixels, as the row-coordinate on ground, namely the difference of two row-coordinates obtains the pixel number of protective device lower edge to ground distance.
10. according to any one of claim 4-8 based on machine vision technique truck side guard railing installation dimension measuring method, it is characterized in that the actual installation dimensional data obtaining step of step S4 lorry side guard rail comprises:
S41: range finder module detects the distance of lorry to camera unit;
S42: pattern process module chooses the camera interior and exterior parameter obtained with the immediate distance calibration of distance that detects in step S41;
S43: the pixel data of guard rail installation dimension utilizes camera interior and exterior parameter to be mapped in world coordinate system to obtain the actual installation dimensional data of lorry side guard rail.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510344734.6A CN105021126A (en) | 2015-06-18 | 2015-06-18 | Truck side guard rail mounting size measurement system and method based on machine vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510344734.6A CN105021126A (en) | 2015-06-18 | 2015-06-18 | Truck side guard rail mounting size measurement system and method based on machine vision technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105021126A true CN105021126A (en) | 2015-11-04 |
Family
ID=54411280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510344734.6A Pending CN105021126A (en) | 2015-06-18 | 2015-06-18 | Truck side guard rail mounting size measurement system and method based on machine vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105021126A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678768A (en) * | 2016-01-08 | 2016-06-15 | 杭州电子科技大学 | Machine vision-based tire tread detection method |
| CN106895781A (en) * | 2017-01-20 | 2017-06-27 | 大连理工大学 | A kind of hot part physical dimension Measurement and Control System of view-based access control model |
| CN107588732A (en) * | 2016-07-07 | 2018-01-16 | 苏州华兴致远电子科技有限公司 | Rail side Train Parts height measurement method and system |
| CN109532378A (en) * | 2018-12-19 | 2019-03-29 | 贵州长江汽车有限公司 | A kind of chassis automatic regulating system based on camera |
| CN110660226A (en) * | 2019-10-30 | 2020-01-07 | 浙江大华技术股份有限公司 | Method, system and equipment for detecting vehicle safety standard and storage device |
| CN111429505A (en) * | 2020-03-20 | 2020-07-17 | 长安大学 | Tire abnormal deformation amount detection method based on tire thickness measurement |
| CN111966857A (en) * | 2020-08-19 | 2020-11-20 | 南京英德利汽车有限公司 | Method and system for detecting modified vehicle |
| CN114199127A (en) * | 2021-12-07 | 2022-03-18 | 长春汽车工业高等专科学校 | Automobile part size detection system and method based on machine vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005322128A (en) * | 2004-05-11 | 2005-11-17 | Rikogaku Shinkokai | Calibration method for stereo three-dimensional measurement and three-dimensional position calculating method |
| CN102750698A (en) * | 2012-06-11 | 2012-10-24 | 上海大学 | Texture camera calibration device, texture camera calibration method and geometry correction method of texture image of texture camera |
| JP2012221261A (en) * | 2011-04-08 | 2012-11-12 | Nintendo Co Ltd | Information processing program, information processing method, information processor and information processing system |
| CN104423719A (en) * | 2013-08-27 | 2015-03-18 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and display content update method thereof |
-
2015
- 2015-06-18 CN CN201510344734.6A patent/CN105021126A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005322128A (en) * | 2004-05-11 | 2005-11-17 | Rikogaku Shinkokai | Calibration method for stereo three-dimensional measurement and three-dimensional position calculating method |
| JP2012221261A (en) * | 2011-04-08 | 2012-11-12 | Nintendo Co Ltd | Information processing program, information processing method, information processor and information processing system |
| CN102750698A (en) * | 2012-06-11 | 2012-10-24 | 上海大学 | Texture camera calibration device, texture camera calibration method and geometry correction method of texture image of texture camera |
| CN104423719A (en) * | 2013-08-27 | 2015-03-18 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and display content update method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 孔明等: "图像处理的货车侧面防护装置", 《中国计量学院学报》 * |
| 赵民: "《石材数控加工技术》", 31 August 2013, 辽宁科学技术出版社 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678768B (en) * | 2016-01-08 | 2018-11-02 | 杭州电子科技大学 | A kind of tyre surface detection method based on machine vision |
| CN105678768A (en) * | 2016-01-08 | 2016-06-15 | 杭州电子科技大学 | Machine vision-based tire tread detection method |
| CN107588732B (en) * | 2016-07-07 | 2024-03-26 | 苏州华兴致远电子科技有限公司 | Rail side train part height measurement method and system |
| CN107588732A (en) * | 2016-07-07 | 2018-01-16 | 苏州华兴致远电子科技有限公司 | Rail side Train Parts height measurement method and system |
| CN106895781A (en) * | 2017-01-20 | 2017-06-27 | 大连理工大学 | A kind of hot part physical dimension Measurement and Control System of view-based access control model |
| CN106895781B (en) * | 2017-01-20 | 2018-12-21 | 大连理工大学 | A kind of hot part geometric dimension Measurement and Control System of view-based access control model |
| CN109532378A (en) * | 2018-12-19 | 2019-03-29 | 贵州长江汽车有限公司 | A kind of chassis automatic regulating system based on camera |
| CN110660226A (en) * | 2019-10-30 | 2020-01-07 | 浙江大华技术股份有限公司 | Method, system and equipment for detecting vehicle safety standard and storage device |
| CN111429505B (en) * | 2020-03-20 | 2023-03-28 | 长安大学 | Tire abnormal deformation amount detection method based on tire thickness measurement |
| CN111429505A (en) * | 2020-03-20 | 2020-07-17 | 长安大学 | Tire abnormal deformation amount detection method based on tire thickness measurement |
| CN111966857A (en) * | 2020-08-19 | 2020-11-20 | 南京英德利汽车有限公司 | Method and system for detecting modified vehicle |
| CN111966857B (en) * | 2020-08-19 | 2023-09-29 | 南京英德利汽车有限公司 | Method and system for detecting refitted vehicle |
| CN114199127A (en) * | 2021-12-07 | 2022-03-18 | 长春汽车工业高等专科学校 | Automobile part size detection system and method based on machine vision |
| CN114199127B (en) * | 2021-12-07 | 2024-02-02 | 长春汽车工业高等专科学校 | Automobile part size detection system and method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105021126A (en) | Truck side guard rail mounting size measurement system and method based on machine vision technology | |
| CN107738612B (en) | Automatic parking space detection and identification system based on panoramic vision auxiliary system | |
| CN106951879B (en) | Multi-feature fusion vehicle detection method based on camera and millimeter wave radar | |
| CN104657735B (en) | Method for detecting lane lines, system, lane departure warning method and system | |
| CN107272021B (en) | Object detection using radar and visually defined image detection areas | |
| US8422737B2 (en) | Device and method for measuring a parking space | |
| CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
| CN101750049B (en) | Monocular vision vehicle distance measuring method based on road and vehicle information | |
| CN104916163B (en) | Parking space detection method | |
| WO2018105179A1 (en) | Vehicle-mounted image processing device | |
| US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN107462223B (en) | Automatic measuring device and method for sight distance of vehicle before turning on highway | |
| EP2237988B1 (en) | Object detection and recognition system | |
| CN110609274B (en) | Distance measurement method, device and system | |
| CN104236478A (en) | Automatic vehicle overall size measuring system and method based on vision | |
| CN101281022A (en) | Method for measuring vehicle distance based on single eye machine vision | |
| CN103559791A (en) | Vehicle detection method fusing radar and CCD camera signals | |
| CN110334678A (en) | A kind of pedestrian detection method of view-based access control model fusion | |
| CN103600707A (en) | Parking position detecting device and method of intelligent parking system | |
| CN103487034A (en) | Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target | |
| CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN110659552B (en) | Tramcar obstacle detection and alarm method | |
| CN106802144A (en) | A kind of vehicle distance measurement method based on monocular vision and car plate | |
| CN109827516B (en) | Method for measuring distance through wheel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: The town of Anping Road Wenling city Taizhou city Zhejiang province 317523 No. 120 Applicant after: CHINA JILIANG UNIVERSITY Address before: Hangzhou City, Zhejiang province 310018 Xiasha Higher Education Park source Street No. 258 Applicant before: China Jiliang University |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151104 |
|
| RJ01 | Rejection of invention patent application after publication |