CN113139933B - Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment - Google Patents

Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment Download PDF

Info

Publication number
CN113139933B
CN113139933B CN202110309271.5A CN202110309271A CN113139933B CN 113139933 B CN113139933 B CN 113139933B CN 202110309271 A CN202110309271 A CN 202110309271A CN 113139933 B CN113139933 B CN 113139933B
Authority
CN
China
Prior art keywords
image
escalator
straight line
edge
coordinates
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
Application number
CN202110309271.5A
Other languages
Chinese (zh)
Other versions
CN113139933A (en
Inventor
胡海洋
厉泽品
李忠金
李前辉
魏泽丰
陈振辉
潘健
刘翰文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Dianzi University
Original Assignee
Hangzhou Dianzi University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Dianzi University filed Critical Hangzhou Dianzi University
Priority to CN202110309271.5A priority Critical patent/CN113139933B/en
Publication of CN113139933A publication Critical patent/CN113139933A/en
Application granted granted Critical
Publication of CN113139933B publication Critical patent/CN113139933B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/168—Segmentation; Edge detection involving transform domain methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an escalator step staggered tooth alignment method based on improved Hough transformation in an industrial environment. Firstly, an escalator step image is obtained and converted into a binary image. And detecting straight lines where staggered teeth are positioned on the surface of the stair by improving Hough transformation, obtaining a coordinate set of all the straight lines, traversing all the coordinate points by taking the first stair as a reference, obtaining a value with the minimum distance difference between the straight line coordinate points of the front stair and the rear stair, and converting the value into a real distance. The invention has the advantages of high detection speed and higher precision, can reach 1mm, can be completed by no more than experienced workers in the production line production mode of a factory, can be judged by any worker according to the detected deviation, and then corrects the steps, thereby reducing the operation difficulty to the maximum extent and being more accurate than the former manual mode.

Description

Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment
Technical Field
The invention belongs to the field of stair mounting, and relates to a stair staggered tooth alignment method based on improved Hough transformation in an industrial environment.
Background
With the rapid development of computer vision technology in recent decades, precision measurement, object detection and other technologies are endless through computer vision, so that the computer vision technology is widely applied in industrial production environments, and helps people to finish a plurality of precision measurement works, and the computer vision technology cooperates with human beings, so that the production efficiency is remarkably improved.
The escalator is very common in real life, in each big mill, the escalator is produced in the form of a production line, a part of workers produce a frame, a part of workers embed the escalator into the frame, and finally the workers need to correct the embedded escalator step staggered teeth back and forth, so that the error between the front escalator step staggered teeth and the rear escalator step staggered teeth is ensured not to be too large, otherwise, the escalator cannot operate and is in a distorted shape. The surface of the escalator is provided with a plurality of staggered teeth, and the front escalator steps and the rear escalator steps are matched through the staggered teeth with different lengths, so that the alignment effect is achieved. In the correction stage of the staggered teeth of the escalator steps, a worker with rich experience is required to judge whether the staggered teeth of the front escalator steps and the rear escalator steps are aligned or not through feeling, if the staggered teeth of the front escalator steps and the rear escalator steps are not aligned, the worker passes through the correction stage if the staggered teeth of the front escalator steps and the rear escalator steps are not aligned, and if the staggered teeth of the front escalator steps and the rear escalator steps are not aligned, the worker judges whether the escalator steps are left or right, and the worker knocks the escalator to deviate a very small distance. It takes a lot of time and effort to recheck if a part of them is wrong.
The invention provides a method for detecting whether an escalator shifts or not through an improved Hough transformation technology, judging whether the escalator shifts left or right, and detecting a specific distance of the shift. The original Hough transformation has high delay due to large operand, and cannot meet the requirement of timely and accurate measurement of the steps in a rapid motion scene. The improved Hough transformation technology can rapidly finish tasks, accurately measure each step, judge through feeling is not needed, accuracy is improved, time and a large amount of manpower are saved, and workers only need to check the measured offset distance to correct.
Disclosure of Invention
It is an object of the present invention to overcome the above-mentioned deficiencies of the prior art by providing an improved hough transform based escalator step staggered tooth alignment method. Firstly, removing noise and impurities in the images by an image processing technology to obtain clear stair images of the escalator. Based on the earlier image processing technology, converting the picture into an HSV mode, judging through a color threshold value, converting the picture into a binary image, wherein the yellow area of the edge of the escalator is 255 in the binary image, and the rest is 0 black. And setting a nine-grid in a fixed position of an image shot by the camera, and performing improved Hough transformation straight line detection when the number of pixel values 255 in the nine-grid reaches a certain threshold value. The Hough transformation needs a binary image, so that the original image is firstly subjected to edge detection to obtain the binary image, then the straight line detected by the edge is corroded and expanded, a foundation is laid for obtaining accurate straight lines, finally, the Hough transformation detects the straight line where the staggered teeth on the surface of the stair are located, then a coordinate set of all the straight lines is obtained, all coordinate points are traversed by taking the first stair as a reference, the value with the minimum distance difference between the straight line coordinate points of the front stair and the rear stair is obtained, and the real distance is converted.
The specific steps of the invention are as follows:
and (1) arranging the camera at a fixed position, wherein the frame rate is 60FPS, the pixel value is 1280 x 720, performing image processing on the shot picture, and calculating the ratio of the pixel distance to the actual distance.
And (2) converting the picture into an HSV space, converting the picture into a binary picture through a threshold algorithm, setting a nine-square grid and a threshold at the same time, judging that all the colored edges of the steps of the escalator exist in the picture through the formula (2), if the colored edges reach the threshold, continuing to detect the edges of the steps of the escalator on the picture processed in the step (1) through a canny algorithm, extracting the whole step outline, and further obtaining the edge straight line of the steps of the escalator. Then, the straight line is detected by using improved Hough transformation on the contour map, and a (rho, theta) polar coordinate set is obtained. And (5) converting the linear coordinate point set into an edge linear coordinate point set of the current escalator step under a rectangular coordinate system.
And (3) judging whether the elevator is deviated according to the formula (6), if the relation between the X-axis coordinates is continuously judged, judging whether the elevator is leftwards or rightwards, and repeating the steps (2) to (3).
It is a further object of the present invention to provide an electronic device comprising a processor and a memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the above-described method.
It is a further object of the present invention to provide a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the above-described method.
The invention has the following beneficial effects:
the invention has the advantages of high detection speed and higher precision, can reach 1mm, can be completed by no more than experienced workers in the production line production mode of a factory, can be judged by any worker according to the detected deviation, and then corrects the steps, thereby reducing the operation difficulty to the maximum extent and being more accurate than the former manual mode.
Drawings
Fig. 1 is a specific flowchart of an escalator step staggered tooth alignment method based on improved hough transform.
Fig. 2 shows the positional relationship between the nine squares and the escalator steps.
Fig. 3 is a polar coordinate system of (ρ, θ).
Detailed Description
The invention will be further analyzed with reference to specific examples.
An escalator step staggered tooth alignment method based on improved Hough transformation in an industrial environment, as shown in figure 1, comprises the following steps:
step (1), acquiring each step image of the escalator in real time;
(1-1) placing the camera at a fixed position, adjusting the frame rate 60FPS and the pixel value 1280 by 720, measuring the actual distance which can be shot by the camera, and preparing for the conversion of the later pixel distance and the actual distance, wherein the formula is as follows:
L O ＝SP O (1)
Wherein P is O Is the pixel P in the image O Is of a size of (2); l (L) O Is P in actual environment O Corresponding actual size; s is the ratio of the actual ambient distance size to the image pixel value size.
(1-2) taking pictures, and performing Gaussian filtering on each frame of pictures to remove noise.
Step (2), extracting the step colored edges of the image processed in the step (1), and detecting the edges of the step colored edges;
(2-1) carrying out binarization processing on the image in the step (1) by adopting a threshold algorithm, judging whether the image processed in the step (1) has a step colored edge, if so, carrying out the step 2-2, otherwise, jumping to the step (1) to continuously acquire the image; the method comprises the following steps:
(2-1-1) converting the step (1) image into HSV space;
(2-1-2) converting the image into a binary image by a threshold algorithm, wherein the colored areas of the steps (the escalator edge basically adopts yellow areas) are 255, and the rest are 0;
and (2-1-3) setting a nine-square (as shown in figure 2) in the binary image, if the number of 255 values in the nine-square meets the formula (2), saving the image in the step (1), and otherwise, jumping to the step (1) to continuously shoot the image.
The nine-square grid is used for judging that all colored edges of the steps of the escalator exist in the image, so that the fixing position of the nine-square grid is set manually according to experience.
sum(P (x,y) =255). Gtoreq.v type (2)
Wherein P is (x,y) Pixel values with (X, Y) as coordinate points of the binary image; v is a threshold value set by a squared figure for triggering the subsequent Hough transformation operation; sum () is a sum function.
(2-2) detecting the stair edge of the escalator on the image processed in the step (1), extracting the whole stair outline, and further obtaining the edge straight line of the escalator; the method comprises the following steps:
(2-2-1) obtaining a preliminary contour map of the image processed in the step (1) by using an existing edge detection algorithm;
the existing edge detection algorithm can adopt a sobel operator, a laplacian operator, a canny operator and the like; the invention preferably adopts a canny algorithm, specifically, the image processed in the step (1) is firstly converted into a gray level image, and then the canny algorithm is utilized for edge detection to obtain a preliminary image contour image.
(2-2-2) performing image processing on the preliminary contour map through open operation, specifically, firstly corroding the preliminary contour map to remove irregular object boundaries, then expanding to obtain a contour map after secondary processing, and simultaneously removing noise around the object.
(2-3) extracting the edge straight line of the current escalator step from the contour map in the step (2-2-2) by utilizing an improved Hough transformation straight line detection algorithm; the method comprises the following steps:
the original Hough transformation straight line detection operation amount is large, the time delay is high, and the scene of the rapid movement of the steps cannot be met, so that the algorithm is improved.
(2-3-1) as in fig. 3, one coordinate point (ρ, θ) in the polar coordinate system corresponds to one straight line in the rectangular coordinate system, so that all the points on one straight line in the rectangular coordinate system have the same slope and intercept, and the same polar coordinate point (ρ, θ) corresponds to the polar coordinate system. One rectangular coordinate (X, Y) in the same rectangular coordinate system corresponds to one straight line in the polar coordinate system. Since a large number of edge points exist in the profile detected in the step (2-2-2), rectangular coordinates (X, Y) of the edge points correspond to a plurality of straight lines in a polar coordinate system, when an intersection point (ρ, θ) exists in different straight lines in the polar coordinate system, the conventional hough transform counts straight lines passing through the intersection point immediately, but the present invention firstly judges whether (ρ, θ) satisfies formulas (3) and (4) simultaneously, if satisfied, starts counting straight lines passing through the intersection point, and when the number of straight lines passing through the intersection point reaches a certain threshold value, judges that the intersection point (ρ, θ) of the polar coordinate system is the edge straight line existing in the rectangular coordinate system, otherwise, directly removes (ρ, θ).
ρ l <ρ<ρ r (3)
θ min <θ<θ max (4)
Wherein ρ is l A threshold value for which the vertical distance from the origin of coordinates to a straight line is minimum; ρ r A threshold value with the maximum vertical distance from the origin of coordinates to the straight line; θ min Is the minimum included angle between the vertical line of the straight line and the clockwise direction of the transverse axis; θ max Is the maximum angle between the vertical line of the straight line and the clockwise direction of the transverse axis. The book is provided withThe origin of coordinates is the upper left corner of the profile of step (2-2-2).
(2-3-2) the polar coordinates (ρ, θ) satisfying the condition in step (2-3-1) are converted into (X ',) (X ', ') in a rectangular coordinate system by formula (5).
Wherein (X) 0 ,Y 0 ) Is the intersection point of the origin of coordinates and the perpendicular line of the straight line and the straight line; (X ', Y'), (X ', Y') respectively represent coordinates of two end points of a straight line; d is a random value because sin θ and cos θ ensure X ', Y', X ", Y", are on the same straight line. Typically 1000, but a fixed value is determined.
(2-3-3) and a plurality of coordinates (X ', Y'), (X ', Y') obtained by screening form an edge linear coordinate point set of the current escalator step.
Step (3), judging whether the step is deviated or not
And traversing the coordinate point set of the straight line where the step staggered teeth are located, which is detected subsequently, by taking the coordinate point set detected by the first step as a standard, so as to obtain a value with the minimum distance between two step coordinate points. Obtaining the offset distance of the subsequent step in the actual scene compared with the first step through the proportion S of the pixel and the distance in the actual scene; and meanwhile, the offset distance is subjected to threshold comparison, and whether excessive offset occurs is judged. Finally, comparing the sizes of the horizontal coordinates between the two minimum values, and judging whether the horizontal coordinates are left-shifted or right-shifted; the method comprises the following steps:
(3-1) respectively traversing each detected step edge linear coordinate point set by taking the first step linear coordinate point set as a reference, obtaining the minimum pixel distance between the currently detected step edge linear coordinate point and the reference, and obtaining an actual offset value W according to a formula (6); then continuously judging whether the actual offset value W is smaller than the threshold value W according to the formula (7) 1 If not, jumping to the step (3-2), if not, considering that the currently detected step is not shifted, and meeting the requirements.
W≤W 1 (7)
Wherein the method comprises the steps ofAn ith coordinate point representing a first step straight line, +.>A j-th coordinate point representing an a-th step straight line.
(3-2) comparisonIf->A right shift occurs and a left shift occurs instead.
(3-3) repeating the steps (2) - (3).
Table 1 step detection speed and offset distance accuracy using existing hough transform straight line detection algorithm
Table 2 improving the step detection speed and offset distance accuracy of the hough transform straight line detection algorithm using the present invention
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above embodiments, and falls within the scope of the present invention as long as the present invention meets the requirements.

Claims (9)

1. The escalator step staggered tooth alignment method based on improved Hough transformation in an industrial environment is characterized by comprising the following steps of:
step (1), acquiring each step image of the escalator in real time, and removing noise;
step (2), extracting the step colored edges of the image processed in the step (1), and detecting the edges of the step colored edges;
(2-1) carrying out binarization processing on the image in the step (1) by adopting a threshold algorithm, judging whether the image processed in the step (1) has a step colored edge, if so, carrying out the step 2-2, otherwise, jumping to the step (1) to continuously acquire the image;
(2-2) detecting the stair edge of the escalator on the image processed in the step (1), and extracting the whole stair outline;
(2-3) extracting the edge straight line of the current escalator step from the contour map in the step (2-2-2) by utilizing an improved Hough transformation straight line detection algorithm; the method comprises the following steps:
(2-3-1) since the contour map of step (2-2-2) has a large number of edge points, rectangular coordinates (X, Y) of these edge points correspond to a plurality of straight lines in a polar coordinate system; judging whether the intersection points (rho, theta) exist in different straight lines under the polar coordinate system or not, if so, starting counting the straight lines passing through the intersection points, and if so, judging that the intersection points (rho, theta) of the polar coordinate system are edge straight lines existing under the rectangular coordinate system when the number of the straight lines passing through the intersection points reaches a certain threshold value; if not, directly removing (rho, theta);
ρ l <ρ<ρ r (3)
θ min <θ<θ max (4)
Wherein ρ is l A threshold value for which the vertical distance from the origin of coordinates to a straight line is minimum; ρ r A threshold value with the maximum vertical distance from the origin of coordinates to the straight line; θ min Is the minimum included angle between the vertical line of the straight line and the clockwise direction of the transverse axis; θ max Is the largest included angle between the vertical line of the straight line and the clockwise direction of the transverse axis;
(2-3-2) converting the polar coordinates (ρ, θ) satisfying the condition of step (2-3-1) into (X ', Y'), (X ", Y") under a rectangular coordinate system by formula (5);
(2-3-3) forming an edge linear coordinate point set of the current escalator step by the coordinates (X ', Y'), (X ', Y');
step (3), judging whether the step is deviated or not
Traversing the coordinate point set of the straight line where the step staggered teeth are located, which is detected subsequently, by taking the coordinate point set detected by the first step as a standard, so as to obtain a value with the minimum distance between two step coordinate points; obtaining the offset distance of the subsequent step in the actual scene compared with the first step through the proportion S of the pixel and the distance in the actual scene; meanwhile, threshold value comparison is carried out on the offset distance, and whether excessive offset occurs is judged; and finally comparing the horizontal coordinates of the two step coordinate points, and judging whether the two step coordinate points are shifted left or right.
2. The escalator step staggered tooth alignment method based on improved hough transform in industrial environment according to claim 1, wherein the relation between step (1) step image and actual environment:
L O ＝SP O (1)
Wherein P is O Is the pixel P in the image O Is of a size of (2); l (L) O Is P in actual environment O Corresponding actual size; s is the ratio of the actual ambient distance size to the image pixel value size.
3. The escalator step staggered tooth alignment method based on improved hough transform in industrial environment according to claim 1, wherein step (2-1) is specifically as follows:
(2-1-1) converting the step (1) image into HSV space;
(2-1-2) converting the image into a binary image by a thresholding algorithm, wherein the step colored area is 255 and the rest is 0;
(2-1-3) setting a nine-square lattice in the binary image, if the 255 numerical values in the nine-square lattice meet the formula (2), saving the image in the step (1), otherwise, jumping to the step (1) to continuously shoot the image;
sum(P (x,y) =255). Gtoreq.v type (2)
Wherein P is (x,y) Pixel values with (X, Y) as coordinate points of the binary image; v is triggering subsequent Hough transform operationA threshold value set by the nine squares; sum () is a sum function.
4. The escalator step staggered tooth alignment method based on improved hough transform in industrial environment according to claim 1, wherein step (2-2) is specifically as follows:
(2-2-1) obtaining a preliminary contour map by using an edge detection algorithm for the image processed in the step (1);
(2-2-2) performing image processing on the preliminary contour map through open operation, specifically, firstly corroding the preliminary contour map to remove irregular object boundaries, then expanding to obtain a contour map after secondary processing, and simultaneously removing noise around the object.
5. The method for aligning staggered teeth of escalator steps based on improved Hough transform in an industrial environment according to claim 1, wherein a canny algorithm is adopted in the edge detection algorithm in the step (2-2-1), specifically, the image processed in the step (1) is converted into a gray scale image, and then the canny algorithm is utilized for edge detection to obtain a preliminary image contour image.
6. The escalator step staggered tooth alignment method based on improved hough transform according to claim 1, wherein step (2-3-2) converts polar coordinates (ρ, θ) satisfying the condition of step (2-3-1) into rectangular coordinates (X ', Y'), (X ", Y") by formula (5);
wherein (X) 0 ,Y 0 ) Is the intersection point of the origin of coordinates and the perpendicular line of the straight line and the straight line; (X ', Y'), (X ', Y') respectively represent coordinates of two end points of a straight line; d is an artificially defined parameter.
7. The escalator step staggered tooth alignment method based on improved hough transform in industrial environment according to claim 1, wherein step (3) is specifically as follows:
(3-1) respectively traversing each detected step edge linear coordinate point set by taking the first step linear coordinate point set as a reference, obtaining the minimum pixel distance between the currently detected step edge linear coordinate point and the reference, and obtaining an actual offset value W according to a formula (6); then continuously judging whether the actual offset value W is smaller than the threshold value W according to the formula (7) 1 If not, jumping to the step (3-2), if not, considering that the currently detected step is not shifted, and meeting the requirements;
W≤W 1 (7)
Wherein the method comprises the steps ofAn ith coordinate point representing a first step straight line, +.>A j-th coordinate point representing an a-th step straight line;
(3-2) comparisonIf->Right shift occurs, otherwise left shift occurs;
(3-3) repeating the steps (2) - (3).
8. An electronic device comprising a processor and a memory, the memory storing machine-executable instructions executable by the processor, the processor executing the machine-executable instructions to implement the method of any one of claims 1-7.
9. A machine-readable storage medium storing machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any one of claims 1-7.
CN202110309271.5A 2021-03-23 2021-03-23 Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment Active CN113139933B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110309271.5A CN113139933B (en) 2021-03-23 2021-03-23 Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110309271.5A CN113139933B (en) 2021-03-23 2021-03-23 Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment

Publications (2)

Publication Number Publication Date
CN113139933A CN113139933A (en) 2021-07-20
CN113139933B true CN113139933B (en) 2024-02-06

Family

ID=76811621

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110309271.5A Active CN113139933B (en) 2021-03-23 2021-03-23 Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment

Country Status (1)

Country Link
CN (1) CN113139933B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463920A (en) * 2014-11-05 2015-03-25 西北工业大学 Two-level optimization Hough transformation rapid detection positioning method oriented to circular identifier
CN108287250A (en) * 2018-02-01 2018-07-17 中国计量大学 Escalator step speed-measuring method based on machine vision
CN111273052A (en) * 2020-03-03 2020-06-12 浙江省特种设备科学研究院 Escalator handrail speed measurement method based on machine vision

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463920A (en) * 2014-11-05 2015-03-25 西北工业大学 Two-level optimization Hough transformation rapid detection positioning method oriented to circular identifier
CN108287250A (en) * 2018-02-01 2018-07-17 中国计量大学 Escalator step speed-measuring method based on machine vision
CN111273052A (en) * 2020-03-03 2020-06-12 浙江省特种设备科学研究院 Escalator handrail speed measurement method based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于多特征融合与改进霍夫变换的电缆检测研究;于书盼;韩彦芳;;软件导刊(第11期);全文 *

Also Published As

Publication number Publication date
CN113139933A (en) 2021-07-20

Similar Documents

Publication Publication Date Title
US20220148213A1 (en) Method for fully automatically detecting chessboard corner points
US11551341B2 (en) Method and device for automatically drawing structural cracks and precisely measuring widths thereof
CN109961455B (en) Target detection method and device
CN107704801B (en) Curve lane line detection method based on segmented straight line and segmented Bezier curve
US8660349B2 (en) Screen area detection method and screen area detection system
CN102829735B (en) Machine vision based detection method of defect of geometrical shape of back surface of E type magnet
CN109583365B (en) Method for detecting lane line fitting based on imaging model constrained non-uniform B-spline curve
CN105744268A (en) Camera shielding detection method and device
CN105654097A (en) Method for detecting quadrangular marker in image
CN111126306A (en) Lane line detection method based on edge features and sliding window
CN110390306A (en) Detection method, vehicle and the computer readable storage medium of right angle parking stall
CN108571928A (en) A kind of intermediate plate anchorage dimensional defects detection method based on machine vision
CN100492396C (en) Method for identifying fabric grain image facing camara weft straightener
CN115096206A (en) Part size high-precision measurement method based on machine vision
CN111896541B (en) Flue gas on-line monitoring system based on block chain
CN112767359A (en) Steel plate corner detection method and system under complex background
CN106875430A (en) Single movement target method for tracing and device based on solid form under dynamic background
CN109242917A (en) One kind being based on tessellated camera resolution scaling method
CN106530273B (en) High-precision FPC (Flexible printed Circuit) linear line detection and defect positioning method
CN113607058B (en) Straight blade size detection method and system based on machine vision
CN108492306A (en) A kind of X-type Angular Point Extracting Method based on image outline
TWI383690B (en) Method for image processing
CN111667429B (en) Target positioning correction method for inspection robot
CN113139933B (en) Escalator step staggered tooth alignment method based on improved Hough transformation in industrial environment
CN104318555A (en) Accurate positioning method of center projection point in target image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant