CN110899147B - A method for on-line sorting of conveyor belt stones based on laser scanning - Google Patents
A method for on-line sorting of conveyor belt stones based on laser scanning Download PDFInfo
- Publication number
- CN110899147B CN110899147B CN201911194863.6A CN201911194863A CN110899147B CN 110899147 B CN110899147 B CN 110899147B CN 201911194863 A CN201911194863 A CN 201911194863A CN 110899147 B CN110899147 B CN 110899147B
- Authority
- CN
- China
- Prior art keywords
- image
- laser
- dimensional
- stone
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000004575 stone Substances 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 30
- 230000033001 locomotion Effects 0.000 claims abstract description 16
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 239000012535 impurity Substances 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000005065 mining Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3425—Sorting according to other particular properties according to optical properties, e.g. colour of granular material, e.g. ore particles, grain
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
本发明公开了一种基于激光扫描的传输带石头在线分拣方法，包括以下步骤：实时采集激光线照射在传输带石头上的图像；进行色彩空间模型转换；通道拉伸变换处理；通道增强处理；模版差分处理与提取曲率特征处理，计算激光的中心位置，得到激光的单像素结果图；对单像素结果去除噪点；获取激光线的图像二维坐标；计算出帧与帧之间的距离，即为运动方向上的距离；将图像二维坐标对应的点转换为三维空间坐标；形成三维空间模型；进行空间点云滤波去除杂质；提取石头的高度和面积信息，设定阈值，判断是否为目标形状的石头，并输出目标石头的坐标信息。本发明能够自动、准确提取生产线传送带上石头的形态信息，将目标尺寸石头的坐标信息实时输出。
The invention discloses an on-line sorting method for conveying belt stones based on laser scanning, comprising the following steps: collecting images of laser lines irradiated on conveying belt stones in real time; performing color space model conversion; channel stretching and transformation processing; channel enhancement processing ; Template difference processing and extraction of curvature feature processing, calculate the center position of the laser, and obtain the single-pixel result map of the laser; remove noise from the single-pixel result; obtain the two-dimensional coordinates of the image of the laser line; calculate the distance between frames, That is, the distance in the direction of movement; convert the points corresponding to the two-dimensional coordinates of the image into three-dimensional space coordinates; form a three-dimensional space model; perform spatial point cloud filtering to remove impurities; extract the height and area information of the stone, set a threshold, and determine whether it is a The stone of the target shape, and output the coordinate information of the target stone. The invention can automatically and accurately extract the shape information of the stones on the conveyor belt of the production line, and output the coordinate information of the target size stones in real time.
Description
Technical Field
The invention relates to the technical field of image processing and automatic monitoring, in particular to a laser scanning-based online stone sorting method for a conveyor belt.
Background
Under the new trend of the current scientific and technological economic development and the requirement of local development, the reform of the mining technology must face the economic construction main battlefield, and the real problems in the mining industry are solved by the necessary technical reserves of the mining development strategy in China. At present, the working environment of mining industry is severe, the health of workers is greatly influenced by environments such as high temperature, high pressure, dustiness and the like, a large number of casualties can be caused by sudden accidents, and a large amount of economic loss is brought to companies. At present, in actual production, the method mainly depends on manual intervention, the abnormal samples in the conveyer belt are always kept, the conveyer belt is manually removed, the requirement on manual work is high, the conveyer belt needs to be shut down under special conditions, and the production efficiency is greatly reduced.
Disclosure of Invention
The invention aims to solve the technical problem of providing an online stone sorting method based on laser scanning for a conveyor belt, aiming at the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the invention provides a laser scanning-based online stone sorting method for a conveyor belt, which comprises the following steps:
s1, adjusting camera parameters including acquired contrast, camera exposure and gain, and acquiring images of laser rays irradiated on a transmission belt stone in real time; recording time information corresponding to the image and the fixed movement speed of the conveying belt;
s2, carrying out color space model conversion on the acquired image by adopting multithreading, and converting the RGB color space into an LAB color space;
s3, performing channel stretching transformation processing on the image converted into the LAB color space, stretching the L component to 0-100, stretching the A component to 0-255 and stretching the B component to 0-255;
s4, performing different processing according to the color of laser emitted by the laser, wherein the color of the laser comprises red, green and blue, and extracting the result of the channel enhancement through a weighting coefficient on the image after the channel stretching transformation;
s5, calculating the center position of the laser through template difference and curvature feature extraction on the image subjected to channel enhancement processing to obtain a single-pixel result graph of the laser;
s6, carrying out projection transformation on the single-pixel result image and removing noise;
s7, traversing the denoised single-pixel result image to obtain two-dimensional coordinates (X, Y) of the image of the laser line;
s8, calculating the distance between frames according to the time information corresponding to the image acquired in the step S1 and the fixed movement speed of the transmission belt, wherein the distance is the distance in the movement direction;
s9, converting the point (X, Y) corresponding to the two-dimensional coordinate of each image in the step S7 into a three-dimensional space coordinate (X, Y, Z) through a laser line deformation rule and the distance in the movement direction;
s10, performing three-dimensional point cloud management by adopting a PCL point cloud library according to the three-dimensional space coordinates of all the points to form a three-dimensional space model;
s11, carrying out spatial point cloud filtering on the three-dimensional point cloud in the three-dimensional space model to remove impurities;
and S12, extracting height and area information of the stone according to the three-dimensional space model, comparing the height and area information with a set threshold value, judging whether the stone is a target-shaped stone, and outputting coordinate information of the target stone.
Further, the method for performing the channel enhancement processing in step S4 of the present invention is:
according to different laser colors, the coefficients of enhanced channel extraction are: m is0、m1And m is0+m1＝1；
Enhancing a point P in the processed image(i，j)Corresponding to LAB channelsThe values are l, a, b, respectively; then the processing enhancement channel results in: p'(i，j)＝m1*a+m2*b。
Further, the method of performing template difference processing in step S5 of the present invention is:
s51, carrying out template difference on m columns of the image after channel enhancement processing, carrying out three-order backward difference on the pixels of the columns, adopting templates (3, -1, -1, -1) to carry out template difference on the current point P(i，m)The starting processing formula is as follows:
s52, for all f on the row(i，m)Forming a one-dimensional array F in the direction of increasing imI.e. the difference curve;
s53, pair difference curve FmCarrying out curvature transformation to find the maximum peak value fmaxAnd maximum valley peak fmin，Two points are at FmThe middle subscripts are p and q respectively;
s54, the center position of the laser is Indexm＝(p+q)/2；
S55, using the center position (Index) of each columnmM) single pixel extraction result map of the constituent lasers.
Further, the method for performing projective transformation in step S6 of the present invention is:
s61, projecting the M multiplied by N single-pixel result graph in the Y direction, and calculating a formula:
wherein f (i, j) represents the ith column and the jth row of the single-pixel result diagram;
s62, finding out the left and right boundaries Y of the area where the laser line is located by searching the projected gray value curveminAnd Ymax；
S63, setting the ordinate in the image between 0 and YminAnd YmaxAnd setting all gray values of the region between N to be zero, and removing noise points.
Further, the method for traversing the single-pixel result image to obtain the two-dimensional coordinates of the image in step S7 of the present invention is as follows:
s71, traversing the single-pixel result graph according to columns, wherein each column only has at most one non-zero value;
s72, when the ith column is traversed, recording a row number j corresponding to a value which is not zero;
and S73, storing the (i, j) into an array, and continuing traversing the next column until the whole image is searched, and acquiring the two-dimensional coordinates of the image is completed.
Further, the method for calculating the distance between frames in step S8 of the present invention is as follows:
s81, the time of the last frame of image collected by the system is T0The moment of acquiring the current frame image is T1The fixed moving speed of the transmission belt shaft is V0(ii) a The distance in the direction of motion is then: deltad＝(T1-T0)*V0。
Further, the method for converting the two-dimensional coordinates into the three-dimensional space coordinates in step S9 of the present invention is:
s91, the laser is installed to form an angle theta with the camera, and the calibration value of the current laser line is HbaseThe Pixel resolution of the camera is Pixel, and the two-dimensional coordinate of the current conversion point is (x)0，y0) The coordinates after the conversion is successful are (X, Y, Z);
s92, the coordinate of the current point in the moving direction is X ═ Δd；
S93, the coordinate Y of the current point is x0；
S94, height Z of current point is ((H)base-y0)*Pixel)/tanθ；
S95、(x0，y0) The coordinates after the conversion are (X, Y, Z).
Further, the method for extracting the height and area information of the stone and setting the threshold value for comparison and judgment in step S12 of the present invention is:
s121, setting a height threshold value HtScreening the whole point cloud space dataThe current point A coordinate is (x)0，y0，z0)；
S122, if z0Greater than HtThen x of point A is added0，y0Stored in the depth map M with the corresponding gray value z0(ii) a If z is0Is less than HtIf yes, no treatment is carried out;
s123, detecting a connected domain in the depth map M, and enabling the area of the connected domain to be larger than a threshold value StArea block mark of (1);
and S124, outputting the center position of the marked area block, and displaying the corresponding point on the three-dimensional point cloud in a pseudo color mode.
The invention has the following beneficial effects: according to the laser scanning-based online stone sorting method for the conveyor belt, the stone area information can be detected online in real time while the conveyor belt runs at a high speed; the area information of the stone passing through the laser line and the high-speed camera at high speed can be detected; the invention has simple hardware, does not need manual operation and is very simple and convenient; the measured target ore information can be fed back to the target stone grabbing machine in real time, so that the target stone can be grabbed in real time, and the production line can be guaranteed to be smoothly carried out; the problem that personnel cannot watch for a long time under a severe environment is solved; the casualty problem caused by sudden accidents is solved; the problem that the follow-up process cannot continue to operate after different samples are met is solved, and the problem of low production efficiency is solved.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of an on-line stone sorting algorithm based on laser scanning according to an embodiment of the present invention;
FIG. 2 is a laser imaging image acquired by a camera in real time according to an embodiment of the present invention;
FIG. 3 is a LAB color space conversion diagram according to an embodiment of the present invention;
FIG. 4 is a graph illustrating the results of channel stretching and strengthening processes performed on FIG. 3 according to an embodiment of the present invention;
FIG. 5 is a graph of a row of difference curves calculated based on FIG. 4 according to an embodiment of the present invention;
FIG. 6 shows the result of single-pixel laser extraction based on FIG. 5 according to an embodiment of the present invention;
FIG. 7 is a diagram of convex hull detection input in accordance with an embodiment of the present invention;
fig. 8 is a diagram of the result of the detection algorithm identifying the target stone on the basis of fig. 7.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the method for sorting stones on line by using a conveyor belt based on laser scanning according to an embodiment of the present invention includes: the system comprises a laser transmitter, an industrial high-speed camera, a computer and an acquisition system bracket; the camera is vertically installed downwards, and the laser and the camera are installed at an angle beta; the laser irradiates the surface of the transmission belt, and the camera acquires an imaging result in real time through callback and transmits the imaging result to a computer application program through a serial port line; the application adopts multiple threads to process data in real time; and analyzing and comparing the processing result, and outputting a detection result at the terminal.
The method comprises the following steps:
s1, adjusting camera parameters, improving the acquired contrast, reducing the exposure and gain of the camera, and acquiring images of laser rays irradiated on a transmission belt stone in real time; recording time information corresponding to the image and the fixed movement speed of the conveying belt;
s2, carrying out color space model conversion on the acquired image by adopting multithreading, and converting the RGB color space into an LAB color space;
s3, performing channel stretching transformation processing on the image converted into the LAB color space, stretching the L component to 0-100, stretching the A component to 0-255 and stretching the B component to 0-255;
s4, performing different processing according to the color of laser emitted by the laser, wherein the color of the laser comprises red, green and blue, and extracting the result of the channel enhancement through a weighting coefficient on the image after the channel stretching transformation;
the method for performing the channel enhancement processing in step S4 includes:
according to different laser colors, the coefficients of enhanced channel extraction are: m is0、m1And m is0+m1＝1；
Enhancing a point P in the processed image(i，j)The values corresponding to the LAB channel are 1, a, b, respectively; then the processing enhancement channel results in: p'(i，j)＝m1*a+m2*b。
S5, calculating the center position of the laser through template difference and curvature feature extraction on the image subjected to channel enhancement processing to obtain a single-pixel result graph of the laser;
the method of performing template difference processing in step S5 is:
s51, carrying out template difference on m columns of the image after channel enhancement processing, carrying out three-order backward difference on the pixels of the columns, adopting templates (3, -1, -1, -1) to carry out template difference on the current point P(i，m)The starting processing formula is as follows:
s52, for all f on the row(i，m)Forming a one-dimensional array F in the direction of increasing imI.e. the difference curve;
s53, pair difference curve FmCarrying out curvature transformation to find the maximum peak value fmaxAnd maximum valley peak fmin，Two points are at FmThe middle subscripts are p and q respectively;
s54, the center position of the laser is Indexm＝(p+q)/2；
S55, using the center position (Index) of each columnmM) single pixel extraction result map of the constituent lasers.
S6, carrying out projection transformation on the single-pixel result image to remove noise;
the method for performing projective transformation in step S6 includes:
s61, projecting the M multiplied by N single-pixel result graph in the Y direction, and calculating a formula:
wherein f (i, j) represents the ith column and the jth row of the single-pixel result diagram;
s62, finding out the left and right boundaries Y of the area where the laser line is located by searching the projected gray value curveminAnd Ymax；
S63, setting the ordinate in the image between 0 and YminAnd YmaxAnd setting all gray values of the region between N to be zero, and removing noise points.
S7, traversing the denoised single-pixel result image to obtain two-dimensional coordinates (X, Y) of the image of the laser line;
the method for traversing the single-pixel result image to acquire the two-dimensional coordinates of the image in the step S7 includes:
s71, traversing the single-pixel result graph according to columns, wherein each column only has at most one non-zero value;
s72, when the ith column is traversed, recording a row number j corresponding to a value which is not zero;
and S73, storing the (i, j) into an array, and continuing traversing the next column until the whole image is searched, and acquiring the two-dimensional coordinates of the image is completed.
S8, calculating the distance between frames according to the time information corresponding to the image acquired in the step S1 and the fixed movement speed of the transmission belt, wherein the distance is the distance in the movement direction;
the method for calculating the distance between frames in step S8 includes:
s81, the time of the last frame of image collected by the system is T0The moment of acquiring the current frame image is T1The fixed moving speed of the transmission belt shaft is V0(ii) a The distance in the direction of motion is then: deltad＝(T1-T0)*V0。
S9, converting the point (X, Y) corresponding to the two-dimensional coordinate of each image in the step S7 into a three-dimensional space coordinate (X, Y, Z) through a laser line deformation rule and the distance in the movement direction;
the method for converting the two-dimensional coordinates into the three-dimensional space coordinates in step S9 includes:
s91, the laser is installed to form an angle theta with the camera, and the calibration value of the current laser line is HbaseThe Pixel resolution of the camera is Pixel, and the two-dimensional coordinate of the current conversion point is (x)0，y0) The coordinates after the conversion is successful are (X, Y, Z);
s92, the coordinate of the current point in the moving direction is X ═ Δd；
S93, the coordinate Y of the current point is x0；
S94, height Z of current point is ((H)base-y0)*Pixel)/tanθ；
S95、(x0，y0) The coordinates after the conversion are (X, Y, Z).
S10, performing three-dimensional point cloud management by adopting a PCL point cloud library according to the three-dimensional space coordinates of all the points to form a three-dimensional space model;
s11, carrying out spatial point cloud filtering on the three-dimensional point cloud in the three-dimensional space model to remove impurities;
and S12, extracting height and area information of the stone according to the three-dimensional space model, comparing the height and area information with a set threshold value, judging whether the stone is a target-shaped stone, and outputting coordinate information of the target stone.
The method for extracting the height and area information of the stone and setting the threshold value for comparison and judgment in the step S12 is as follows:
s121, setting a height threshold value HtScreening the whole point cloud space data, wherein the coordinate of the current point A is (x)0，y0，z0)；
S122, if z0Greater than HtThen x of point A is added0，y0Stored in the depth map M with the corresponding gray value z0(ii) a If z is0Is less than HtIf yes, no treatment is carried out;
s123, detecting a connected domain in the depth map M, and enabling the area of the connected domain to be larger than a threshold value StArea block mark of (1);
and S124, outputting the center position of the marked area block, and displaying the corresponding point on the three-dimensional point cloud in a pseudo color mode.
The laser scanning-based online stone sorting method for the conveyor belt has the following advantages:
1. the ore area information can be detected on line in real time while the conveyor belt runs at a high speed;
2. the area information of ore passing through a laser line and a high-speed camera at high speed can be detected; the hardware is simple, manual operation is not needed, and the operation is very simple and convenient;
3. can give the target ore machine of snatching with the target ore information real-time feedback of measurement to this snatchs target ore in real time, guarantees going on smoothly of production line.
4. The problem that personnel cannot watch for a long time under a severe environment is solved;
5. the casualty problem caused by sudden accidents is solved;
6. the problem that the follow-up process cannot continue to operate after different samples are met is solved, and the problem of low production efficiency is solved.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (5)
1. The laser scanning-based online stone sorting method is characterized by comprising the following steps:
s1, adjusting camera parameters including acquired contrast, camera exposure and gain, and acquiring images of laser rays irradiated on a transmission belt stone in real time; recording time information corresponding to the image and the fixed movement speed of the conveying belt;
s2, carrying out color space model conversion on the acquired image by adopting multithreading, and converting the RGB color space into an LAB color space;
s3, performing channel stretching transformation processing on the image converted into the LAB color space, stretching the L component to 0-100, stretching the A component to 0-255 and stretching the B component to 0-255;
s4, performing different processing according to the color of laser emitted by the laser, wherein the color of the laser comprises red, green and blue, and extracting the result of the channel enhancement through a weighting coefficient on the image after the channel stretching transformation;
s5, calculating the center position of the laser through template difference and curvature feature extraction on the image subjected to channel enhancement processing to obtain a single-pixel result graph of the laser;
the method of performing template difference processing in step S5 is:
s51, carrying out template difference on m columns of the image after channel enhancement processing, carrying out three-order backward difference on the pixels of the columns, adopting templates (3, -1, -1, -1) to carry out template difference on the current point P(i，m)The starting processing formula is as follows:
s52, for all f on the row(i，m)Forming a one-dimensional array F in the direction of increasing imI.e. the difference curve;
s53, pair difference curve FmCarrying out curvature transformation to find the maximum peak value fmaxAnd maximum valley peak fminTwo points are at FmThe middle subscripts are p and q respectively;
s54, the center position of the laser is Indexm＝(p+q)/2；
S55, using the center position (Index) of each columnmM) a single-pixel extraction result graph of the constituent lasers;
s6, carrying out projection transformation on the single-pixel result image and removing noise;
s7, traversing the denoised single-pixel result image to obtain two-dimensional coordinates (X, Y) of the image of the laser line;
s8, calculating the distance between frames according to the time information corresponding to the image acquired in the step S1 and the fixed movement speed of the transmission belt, wherein the distance is the distance in the movement direction;
s9, converting the point (X, Y) corresponding to the two-dimensional coordinate of each image in the step S7 into a three-dimensional space coordinate (X, Y, Z) through a laser line deformation rule and the distance in the movement direction;
the method for converting the two-dimensional coordinates into the three-dimensional space coordinates in step S9 includes:
s91, the laser is installed to form an angle theta with the camera, and the calibration value of the current laser line is HbaseThe Pixel resolution of the camera is Pixel, and the two-dimensional coordinate of the current conversion point is (x)0，y0) The coordinates after the conversion is successful are (X, Y, Z);
s92, the coordinate of the current point in the moving direction is X ═ Δd；
S93, the coordinate Y of the current point is x0；
S94, height Z of current point is ((H)base-y0)*Pixel)/tanθ；
S95、(x0，y0) The coordinates after the conversion is successful are (X, Y, Z);
s10, performing three-dimensional point cloud management by adopting a PCL point cloud library according to the three-dimensional space coordinates of all the points to form a three-dimensional space model;
s11, carrying out spatial point cloud filtering on the three-dimensional point cloud in the three-dimensional space model to remove impurities;
s12, extracting height and area information of the stone according to the three-dimensional space model, comparing the height and area information with a set threshold value, judging whether the stone is a target-shaped stone or not, and outputting coordinate information of the target stone;
the method for extracting the height and area information of the stone and setting the threshold value for comparison and judgment in the step S12 is as follows:
s121, setting a height threshold value HtScreening the whole point cloud space data, wherein the coordinate of the current point A is (x)0，y0，z0)；
S122, if z0Greater than HtThen x of point A is added0，y0Stored in the depth map M with the corresponding gray value z0(ii) a If z is0Is less than HtIf yes, no treatment is carried out;
s123, detecting a connected domain in the depth map M, and enabling the area of the connected domain to be larger than a threshold value StArea block mark of (1);
and S124, outputting the center position of the marked area block, and displaying the corresponding point on the three-dimensional point cloud in a pseudo color mode.
2. The laser scanning based on-line sorting method for the conveyor belt stones as claimed in claim 1, wherein the method for performing the channel enhancement processing in step S4 is as follows:
according to different laser colors, the coefficients of enhanced channel extraction are: m is0、m1And m is0+m1＝1；
Enhancing a point P in the processed image(i，j)The values corresponding to the LAB channel are 1, a, b, respectively; then the processing enhancement channel results in: p'(i，j)＝m1*a+m2*b。
3. The laser scanning based on-line sorting method for the conveyor stones according to claim 1, wherein the projection transformation in step S6 is performed by:
s61, projecting the M multiplied by N single-pixel result graph in the Y direction, and calculating a formula:
wherein f (i, j) represents the ith column and the jth row of the single-pixel result diagram;
s62, finding out the left and right boundaries Y of the area where the laser line is located by searching the projected gray value curveminAnd Ymax；
S63, setting the ordinate in the image between 0 and YminAnd YmaxAnd setting all gray values of the region between N to be zero, and removing noise points.
4. The laser scanning based on-line sorting method for the conveyor stones according to claim 3, wherein the step S7 of traversing the single-pixel result graph to obtain the two-dimensional coordinates of the image comprises:
s71, traversing the single-pixel result graph according to columns, wherein each column only has at most one non-zero value;
s72, when the ith column is traversed, recording a row number j corresponding to a value which is not zero;
and S73, storing the (i, j) into an array, and continuing traversing the next column until the whole image is searched, and acquiring the two-dimensional coordinates of the image is completed.
5. The laser scanning based on-line stone sorting method on the conveyor belt according to claim 1, wherein the method for calculating the distance between frames in the step S8 is as follows:
s81, the time of the last frame of image collected by the system is T0The moment of acquiring the current frame image is T1The fixed moving speed of the transmission belt shaft is V0(ii) a The distance in the direction of motion is then: deltad＝(T1-T0)*V0。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194863.6A CN110899147B (en) | 2019-11-28 | 2019-11-28 | A method for on-line sorting of conveyor belt stones based on laser scanning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194863.6A CN110899147B (en) | 2019-11-28 | 2019-11-28 | A method for on-line sorting of conveyor belt stones based on laser scanning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110899147A CN110899147A (en) | 2020-03-24 |
| CN110899147B true CN110899147B (en) | 2021-10-08 |
Family
ID=69820343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911194863.6A Active CN110899147B (en) | 2019-11-28 | 2019-11-28 | A method for on-line sorting of conveyor belt stones based on laser scanning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110899147B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111812671A (en) * | 2020-06-24 | 2020-10-23 | 北京佳力诚义科技有限公司 | Artificial intelligence ore recognition device and method based on laser imaging |
| CN114998621B (en) * | 2022-05-26 | 2024-04-16 | 嘉兴学院 | SERS quantitative analysis method based on coffee ring concentration effect and image processing technology |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676696A (en) * | 2008-09-17 | 2010-03-24 | 中茂电子(深圳)有限公司 | Optical testing system for testing early-period confirmation contrast sample of solar cell and method |
| CN105631881A (en) * | 2015-12-30 | 2016-06-01 | 四川华雁信息产业股份有限公司 | Target detection method and apparatus |
| CN106238350A (en) * | 2016-09-12 | 2016-12-21 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of solar battery sheet method for separating based on machine vision and system |
| CN107185854A (en) * | 2017-05-17 | 2017-09-22 | 河北工业大学 | The algorithm of photovoltaic cell acetes chinensis and color classification based on RGB channel |
| CN107462182A (en) * | 2017-09-19 | 2017-12-12 | 电子科技大学 | A kind of cross section profile deformation detecting method based on machine vision and red line laser |
| CN108230273A (en) * | 2018-01-05 | 2018-06-29 | 西南交通大学 | A kind of artificial compound eye camera three dimensional image processing method based on geological information |
| JP2019136828A (en) * | 2018-02-13 | 2019-08-22 | Ｋｙｏｔｏ Ｒｏｂｏｔｉｃｓ株式会社 | Box-shaped object picking device and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11273553B2 (en) * | 2017-06-05 | 2022-03-15 | Autodesk, Inc. | Adapting simulation data to real-world conditions encountered by physical processes |
-
2019
- 2019-11-28 CN CN201911194863.6A patent/CN110899147B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676696A (en) * | 2008-09-17 | 2010-03-24 | 中茂电子(深圳)有限公司 | Optical testing system for testing early-period confirmation contrast sample of solar cell and method |
| CN105631881A (en) * | 2015-12-30 | 2016-06-01 | 四川华雁信息产业股份有限公司 | Target detection method and apparatus |
| CN106238350A (en) * | 2016-09-12 | 2016-12-21 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of solar battery sheet method for separating based on machine vision and system |
| CN107185854A (en) * | 2017-05-17 | 2017-09-22 | 河北工业大学 | The algorithm of photovoltaic cell acetes chinensis and color classification based on RGB channel |
| CN107462182A (en) * | 2017-09-19 | 2017-12-12 | 电子科技大学 | A kind of cross section profile deformation detecting method based on machine vision and red line laser |
| CN108230273A (en) * | 2018-01-05 | 2018-06-29 | 西南交通大学 | A kind of artificial compound eye camera three dimensional image processing method based on geological information |
| JP2019136828A (en) * | 2018-02-13 | 2019-08-22 | Ｋｙｏｔｏ Ｒｏｂｏｔｉｃｓ株式会社 | Box-shaped object picking device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110899147A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110286126B (en) | Wafer surface defect regional detection method based on visual image | |
| CN111539935B (en) | An online detection method for cable surface defects based on machine vision | |
| CN112330628A (en) | Metal workpiece surface defect image detection method | |
| CN109872300B (en) | Visual saliency detection method for appearance defects of friction plate | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN104992449B (en) | Information identification and surface defect online test method based on machine vision | |
| CN104680519B (en) | Seven-piece puzzle recognition methods based on profile and color | |
| CN113034399A (en) | Binocular vision based autonomous underwater robot recovery and guide pseudo light source removing method | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN107256547A (en) | A kind of face crack recognition methods detected based on conspicuousness | |
| CN115791801B (en) | 3D glass online monitoring platform based on machine vision | |
| CN110899147B (en) | A method for on-line sorting of conveyor belt stones based on laser scanning | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN109781737A (en) | A detection method and detection system for surface defects of hoses | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| Dong et al. | A rapid detection method for the surface defects of mosaic ceramic tiles | |
| CN110186929A (en) | A kind of real-time product defect localization method | |
| CN110728286A (en) | Abrasive belt grinding material removal rate identification method based on spark image | |
| CN112338898B (en) | Image processing method and device of object sorting system and object sorting system | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| TWI543117B (en) | Method for recognizing and locating object | |
| CN113705487B (en) | Precision workpiece identification and technological parameter association system and identification method | |
| CN113610185B (en) | Wood color selection method based on main color recognition | |
| CN115184362A (en) | Rapid defect detection method based on structured light projection |
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 |