CN109409368A - Mine leather belt is vertical to tear detection device and detection method - Google Patents
Mine leather belt is vertical to tear detection device and detection method Download PDFInfo
- Publication number
- CN109409368A CN109409368A CN201811310349.XA CN201811310349A CN109409368A CN 109409368 A CN109409368 A CN 109409368A CN 201811310349 A CN201811310349 A CN 201811310349A CN 109409368 A CN109409368 A CN 109409368A
- Authority
- CN
- China
- Prior art keywords
- image
- interest
- striation
- area
- mine
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
It is indulged the present invention relates to a kind of mine leather belt and tears detection device and detection method, be based on mining linear laser transmitter and mining visual sensor platform, comprising: obtained linear laser and be radiated at the laser optical strip image on belt as area-of-interest;It creates the image process target on mining visual sensor platform and copies the image data of area-of-interest;The image of area-of-interest is enhanced and denoised;Obtain striation segmentation threshold;Optical strip image is obtained by Threshold segmentation;Obtain linear light center striation;Judge linear light center striation feature, judges whether that belt longitudinal tearing occurs.The mine leather belt is vertical to tear detection device and detection method, realize that video acquisition, image algorithm analysis, control signal export integrated treatment on embedded platform, simplify hardware configuration, optimization algorithm, algorithm complexity is reduced on the basis of not reducing algorithm accuracy rate substantially, realizes the on-line real-time measuremen of belt longitudinal tear and exports control signal.
Description
Technical field:
The present invention relates to mine monitoring technical field, more particularly to a kind of based on mining video sensor and mining linear swash
The mine leather belt of light device is vertical to tear detection device and detection method.
Background technique:
Research [D] the Liaoning Technology University .2015 that document [1] Lee congratulates coal feed belt surface crack testing technology is mentioned
It has supplied a kind of utilization Otsu dividing method to divide crackle from background, then crack image has been carried out using framework extraction method thin
The method of crack size is calculated after change to judge.This method accuracy rate is established on the basis of extracting crackle accuracy, but by
It is low in underground coal mine illumination, dust is more, steam is big and shade, strong light interference it is more so that segmentation crackle difficulty greatly increase, standard
True rate is badly damaged, thus the method is very high to environmental requirement, and otherwise it is easy to appear erroneous judgements, it is difficult to practical.
The Xi'an research [D] the science and technology of conveyer belt longitudinal ripping detecting device of document [2] the Li Zhaokun based on machine vision
University .2013 provides a kind of hardware platform built using DM642 processor+EPC2FPGA chip, acquires belt image, leads to
It crosses after edge extracting and Hough transform algorithm process and judges the device of belt longitudinal tear feature.The defect of this device is to calculate
Method Detection accuracy is low, is easy to be caused to report by mistake by sewage, sundries interference, and hardware is complicated, processing speed is low.
Belt tearing vision detection technology research [D] the University On The Mountain Of Swallows that document [3] Zhang Chunming is assisted based on line laser
.2012 a kind of line laser auxiliary visible detection method based on computer analysis is provided.This method is adopted by high-speed figure image
Truck collection of coal mine belt conveyor image is sent in computer and utilizes the threshold based on variance within clusters and target and background difference in areas
Value carries out the segmentation of line laser striped, and seeks method using the striation segmentation threshold that iterative method and search approximatioss combine and divide
Optical strip image is obtained, after extracting optical losses using gravity model appoach, using gaussian curve approximation method to light in striation normal direction
Center carries out sub-pixel precision extraction.By being deviated to optical losses adjacent pixel spacing, optical losses curvature and striation
Degree signature analysis completes tearing detection.The method is analyzed using high-speed figure image pick-up card+computer mode operation algorithm,
Relatively high to acquisition, transmission, the operational capability requirement of hardware, hardware is bulky, and power consumption is high, it is difficult in colliery scene application.
Summary of the invention:
It is a kind of based on mining video sensor and mining linear the purpose of the present invention is in view of the drawbacks of the prior art, providing
The mine leather belt of laser is vertical to tear detection device and detection method, and video acquisition, image algorithm point are realized on embedded platform
Analysis, control signal export integrated treatment, simplify hardware configuration, and optimization algorithm is not reducing algorithm accuracy rate basis substantially
Upper reduction algorithm complexity realizes the on-line real-time measuremen of belt longitudinal tear and exports control signal.
The present invention is achieved through the following technical solutions:
The present invention provides that a kind of mine leather belt is vertical to tear detection device, including the mining line to mine leather belt transmitting linear laser
Property laser emitter and for capturing reflected light and being converted to the mining visual sensor platform of video image;
The mining linear laser transmitter includes Mine-used I. S laser emitter shell and is arranged in Mine-used I. S
Linear laser transmitter and intrinsic safety electric source in laser emitter shell, the intrinsic safety electric source are electrically connected with linear laser transmitter
It connects;
The mining visual sensor platform includes that Mine-used I. S video camera shell and setting are imaged in Mine-used I. S
Filter glass, SDI mould group, embedded core board, interface board and intrinsic safety electric source in instrument shell, the filter glass is for filtering out
Visible light, the intrinsic safety electric source are electrically connected with interface board, and for powering to it, the interface board is electrically connected with embedded core board
It connects, is expanded for realizing coffret, data exchange and signal isolation, the SDI mould group are correspondingly arranged at filter glass side
And be electrically connected with embedded core board, image is captured by cmos image sensor, electric signal is converted into, after being digitized processing
It is input to embedded core board.
Preferably, the embedded core board uses the core board for thinking Hi3516A chip based on sea.
It is indulged the present invention also provides a kind of mine leather belt and tears detection method, torn detection device using above-mentioned mine leather belt is vertical, wrap
Include following steps:
A, it obtains linear laser and is radiated at the laser optical strip image on belt as area-of-interest (hereinafter referred to as ROI);
B, it creates the image process target on mining visual sensor platform and copies the image data of ROI;
C, the image of ROI is enhanced and is denoised;
D, striation segmentation threshold is obtained;
E, optical strip image is obtained by Threshold segmentation;
F, linear light center striation is obtained;
G, judge linear light center striation feature, judge whether that belt longitudinal tearing occurs.
The acquisition linear laser is radiated at the area image on belt as area-of-interest, comprising:
Video sensor internal server, which is browsed, by web mode gets real time video image;
On real time video image, the optical strip image region quadrangle of linear laser is selected by user;
Video sensor internal profile is written as parameter in the quadrangle coordinate data that user is selected;
Algorithm routine reads this parameter for image analysis from internal profile.
Image process target on the creation platform simultaneously copies ROI image data, comprising:
According to the processing unit structure of the parameter initialization platform intelligent video engine (hereinafter referred to as IVE) of area-of-interest
Body simultaneously distributes memory space;
By dma mode by ROI image data copy into IVE memory space.
It is described that image enhancement and denoising are carried out to ROI image, comprising:
ROI image in IVE physical memory is mapped to virtual memory, operation is for ROI image in virtual memory below
Data manipulation;
ROI image is converted into gray level image;
Enhance image in ROI in the part that changes over time;
Histogram equalization is carried out to ROI gray level image;
Median filtering is carried out to ROI gray level image.
The acquisition striation segmentation threshold, comprising:
ROI image is divided into m subgraph, each subgraph column data containing n;
Segmentation threshold is obtained by the following method to each subgraph:
Calculate the number of pixels of each gray level in subgraph;
Calculate the ratio that each gray-level pixels number accounts for subgraph total pixel number;
Calculate the gray average of subgraph;
Subgraph gray level is traversed, suitable striation segmentation threshold Ti is found;
Striation segmentation threshold function T (x) is determined using Gauss curve fitting.
The Threshold segmentation obtains optical strip image, comprising:
ROI image is split according to threshold function table T (x) using platform IVE operator.
Acquisition linear light center striation, comprising:
General center striation position is extracted using extremum method;
Judge light stripe centric line ordinate fluctuation, the column beyond fluctuation range find next extreme point, repeat this step
Until light stripe centric line ordinate fluctuates all within the set range;
Increase by 20 pixels respectively up and down in rough optical losses line position to include complete striation;
Light stripe centric line is extracted using grey scale centre of gravity method.
The judgement line light stripe centric line feature judges whether that belt longitudinal tearing occurs, comprising:
Light stripe centric line is obtained along the coordinate minimum value and maximum value in striation direction;
Light stripe centric line is traversed along the coordinate in striation direction, from minimum value to maximum value, given threshold p is calculated in striation
Euclidean distance d, d on heart line between consecutive points are more than p, then it is assumed that belt longitudinal tearing occurs.
Mine leather belt of the present invention is vertical tear detection device and detection method using embedded integrated design completion video acquisition,
Video analysis, signal output, real-time detection, the judgement, output of belt longitudinal tear are realized in a manner of video sensing, judges standard
On the basis of true property does not reduce, greatly reducing data transfer delay, reduces energy consumption, practical function is ideal, it is mainly characterized by:
1, video enters SDI video acquisition mould group by filter glass, and most of visible light is filtered out, and retains infrared light,
Interference of the visible light such as mine lamp, head lamp to image is dispelled by physical means;
2, algorithm operation quantity can be reduced as analytical unit by setting area-of-interest, improves algorithm performance and closes effect
Rate;
3, using the IVE framework on embedded platform, a small amount of master cpu is cooperated to participate in realizing that complicated intellectual analysis is calculated
Method can reduce demand of the system to master cpu performance, to reduce sensor on the basis of meeting algorithm analysis demand
Power consumption reduces equipment volume, to reduce the cost of equipment;
4, segmentation threshold is set using Gaussian function, meets linear light distribution feature, had than fixed threshold preferably suitable
Ying Xing;
5, gray scale extremum method combination grey scale centre of gravity method obtains light stripe centric line, simpler than single algorithm, but accuracy rate is higher.
Detailed description of the invention:
Fig. 1 is the structural schematic diagram of the vertical mining linear laser transmitter for tearing detection device of mine leather belt of the present invention;
Fig. 2 is the structural schematic diagram of the vertical mining visual sensor platform for tearing detection device of mine leather belt of the present invention;
Fig. 3 is the vertical flow chart for tearing detection method of mine leather belt of the invention;
Fig. 4 is the vertical implementation flow chart for tearing detection method of mine leather belt of the invention.
Specific embodiment:
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy
It is easier to be understood by those skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
The present invention provides that a kind of mine leather belt is vertical to tear detection device, including the mining line to mine leather belt transmitting linear laser
Property laser emitter and for capturing reflected light and being converted to the mining visual sensor platform of video image.
As shown in Figure 1, the mining linear laser transmitter includes that Mine-used I. S laser emitter shell and setting exist
Linear laser transmitter and intrinsic safety electric source in Mine-used I. S laser emitter shell, the intrinsic safety electric source and linear laser are sent out
Emitter electrical connection, using Mine-used I. S laser emitter shell, is applied in underground coal mine environment, can be with water proof and dust proof, line
Property laser emitter can emit "-" type linear laser, be radiated on belt formation laser striation, intrinsic safety electric source is realized to line
Property laser emitter power supply.
As shown in Fig. 2, the mining visual sensor platform includes Mine-used I. S video camera shell and is arranged mining
Filter glass, SDI mould group, embedded core board, interface board and intrinsic safety electric source in intrinsic safety type video camera shell.Observe window segment
Using 850~950nm filter glass is used, its effect of SDI mould group is to capture extraneous reflected light or infrared floor light reflected light,
Electric signal is converted optical signals to, to obtain real-time video image, sdi signal is output to insertion after digitized processing
Formula core board, embedded core board are used the core board for being thought Hi3516A chip based on sea, run a set of embedded software completion figure
As analysis, Video coding compression, network transmission, control signal output function, interface board realization expands coffret, is counted
According to exchange, signal isolation, intrinsic safety electric source and related conversion module realize that intrinsic safety electric source is powered to video sensor, control video
It is detected under sensor soft start and power down mode.
A kind of mine leather belt is vertical to tear detection method, detection device is torn using above-mentioned mine leather belt is vertical, as shown in figure 3, including
Following steps:
A, it obtains linear laser and is radiated at the laser optical strip image on belt as area-of-interest (hereinafter referred to as ROI);
B, it creates the image process target on mining visual sensor platform and copies the image data of ROI;
C, the image of ROI is enhanced and is denoised;
D, striation segmentation threshold is obtained;
E, optical strip image is obtained by Threshold segmentation;
F, linear light center striation is obtained;
G, judge linear light center striation feature, judge whether that belt longitudinal tearing occurs.
The implementing procedure of this detection method is as shown in Figure 4:
Step 01: choosing suitable position, installation mining intelligent video sensor and mining linear laser;
Specifically, coal, the water etc. that can be transported in view of mine leather belt front cover zone face tearing position, so equipment is solid
Dingan County is mounted in belt back, sensor and linear laser towards belt back.
Step 02: real-time video browsing draws area-of-interest.
Specifically, opening mining intelligent video sensor and mining linear laser equipment, sensing is browsed by web mode
The real-time video that device is got draws laser striation image-region as area-of-interest, storage zone coordinate on web video
To algorithm configuration file.
Step 03: starting to carry out algorithm analysis to video frame.
1, image preprocessing is carried out to area-of-interest first, including image enhancement and image filter are made an uproar, image enhancement uses
Histogram equalization realizes that histogram equalization is to carry out " adjustment " to gray value by cumulative function to realize that contrast enhances
Method, gray accumulation function is as follows:
Wherein, n is the summation of pixel in image, and nj is the number of pixels of current gray level grade, and L is possible gray scale in image
Grade sum.
Image filter is made an uproar to be realized by the way of median filtering.Median filtering method is a kind of nonlinear smoothing technology, it will be every
The gray value of one pixel is set as the intermediate value of all pixels point gray value in the point neighborhood window.
2, area-of-interest image grayscale Threshold segmentation function T (x) is secondly sought.Since linear light brightness distribution meets height
This distribution characteristics, intermediate luminance is high, and both sides brightness is slightly lower.Area-of-interest is divided into N along striation direction (it is assumed that x-axis direction)
Part, every part arranges containing n, wherein n=width/N, and width is the width of ROI region, and height is the height of ROI region.Due to light
Item accounted in image area it is smaller, so using each sub-image based on variance within clusters and prospect background difference in areas square
Ratio seeks segmentation threshold Tm (m=1,2 ... ..N).N number of separate division threshold value is found out, is constructed using Gaussian function fitting
Threshold segmentation function T (x).
An initial threshold Th=Th0 is given, this sub-image is divided into C1, two class of C2;
Find out the variance of two classesWith gray average μ1, μ2And sub-image population mean μ;
Gray variance:
Gray average:
Sub-image population mean:
Wherein, m indicates m-th of sub-block.(1,2 is shared along the x-axis direction ... N number of sub-block)
The distribution probability of two class images:
Wherein KciFor Ci class number of pixels
Variance within clusters:
It asks and optimal threshold T (i) is obtained with the minimum value of lower threshold value:
Other sub-images are all made of the method and seek segmentation threshold Tm (m=1,2,3 ... .., N).
Discrete Threshold segmentation point Gauss curve fitting at threshold function table T (x).
3, optical strip image then is obtained using Threshold segmentation function segmented image.
If ROI image is f (x, y), the image after Threshold segmentation is g (x, y), and g (x, y) is bianry image, then has:
4, optical losses lines are extracted using the method that gray scale extremum method is combined with grey scale centre of gravity method.
Light stripe centric line rough position is extracted using extremum method first.The each column of optical strip image are traversed, find gray value most
Big point constitutes a curve.But due to the high disturbing factor of other gray values on image (such as head lamp, mine lamp, picture text
Word etc.) presence, the range of gray value is (0,255), so first extreme point found, i.e. the point of gray scale 255 may be simultaneously
It is not the point on the lines of center.The point ordinate of judgement at this time is compared with previous center lines point ordinate, if difference exceeds wave
Dynamic range, then find next extreme point.Repeat this step until all the points on curve fluctuation within the set range.Pass through
This operation removes pseudo- maximum, step point is eliminated, to guarantee that curve is substantially smooth.
In order to further accurately extract optical losses, above-mentioned optical losses line position respectively increases by 20 pixels up and down and constitutes light
Band extracts light stripe centric line using grey scale centre of gravity method again.Grey scale centre of gravity method is to scan by column above-mentioned striation band, each column
Calculated striation band grey scale centre of gravity ordinate is as light stripe centric line corresponding points ordinate.Assuming that striation band kth column coordinate bit
It is set to (xk, yi), wherein i=1,2,3 ... .a, a are striation bandwidth.Grey scale centre of gravity ordinate calculation formula is as follows:
5, judge light stripe centric line feature, judge whether there is vertical feature of tearing and occur.
Specifically, traversal light stripe centric line, calculates the Euclidean distance between consecutive points, it is assumed that adjacent two on light stripe centric line
Point is (x1,y1)(x2,y2), then Euclidean distance between two o'clock are as follows:
Given threshold p, as distance d > p, it is believed that occur indulging and tear feature.
Step 04: detect it is vertical tear feature after, alarm signal and control signal are exported by output interface, and in Web page
Information alert is provided on face.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.
Claims (10)
1. a kind of mine leather belt is vertical to tear detection device, it is characterised in that: including the mining line to mine leather belt transmitting linear laser
Property laser emitter and for capturing reflected light and being converted to the mining visual sensor platform of video image;
The mining linear laser transmitter includes Mine-used I. S laser emitter shell and is arranged in Mine-used I. S laser
Linear laser transmitter and intrinsic safety electric source in launcher shell, the intrinsic safety electric source are electrically connected with linear laser transmitter;
The mining visual sensor platform includes Mine-used I. S video camera shell and is arranged outside Mine-used I. S video camera
Filter glass, SDI mould group, embedded core board, interface board and intrinsic safety electric source in shell, the filter glass are visible for filtering out
Light, the intrinsic safety electric source are electrically connected with interface board, and for powering to it, the interface board is electrically connected with embedded core board, are used
In realize coffret expand, data exchange and signal isolation, the SDI mould group be correspondingly arranged at filter glass side and with it is embedding
Enter the electrical connection of formula core board, for capturing image, is converted into electric signal, is input to embedded core board after being digitized processing.
2. mine leather belt according to claim 1 is vertical to tear detection device, it is characterised in that: the embedded core board uses
The core board of Hi3516A chip is thought based on sea.
3. a kind of mine leather belt is vertical to tear detection method, detection device is torn using mine leather belt as claimed in claim 1 or 2 is vertical,
It is characterized by comprising the following steps:
A, it obtains linear laser and is radiated at the laser optical strip image on belt as area-of-interest;
B, it creates the image process target on mining visual sensor platform and copies the image data of area-of-interest;
C, the image of area-of-interest is enhanced and is denoised;
D, striation segmentation threshold is obtained;
E, optical strip image is obtained by Threshold segmentation;
F, linear light center striation is obtained;
G, judge linear light center striation feature, judge whether that belt longitudinal tearing occurs.
4. mine leather belt according to claim 3 is vertical to tear detection method, which is characterized in that described to obtain linearly in step A
Laser optical strip image of the laser irradiation on belt is as area-of-interest, comprising:
Video sensor internal server, which is browsed, by web mode gets real time video image;
On real time video image, the optical strip image region quadrangle of linear laser is selected by user;
Video sensor internal profile is written as parameter in the quadrangle coordinate data that user is selected;
Algorithm routine reads this parameter for image analysis from internal profile.
5. mine leather belt according to claim 4 is vertical to tear detection method, which is characterized in that in step B, the creation is mining
Image process target on visual sensor platform and the image data for copying area-of-interest, comprising:
According to the processing unit structural body of the parameter initialization platform intelligent video engine of area-of-interest and distribute memory space;
In the memory space that area-of-interest image data is copied to platform intelligent video engine by dma mode.
6. mine leather belt according to claim 5 is vertical to tear detection method, which is characterized in that described to interested in step C
The image in region carries out image enhancement and denoising, comprising:
Region of interest area image in platform intelligent video engine physical memory is mapped to virtual memory;
Region of interest area image in virtual memory is converted into gray level image;
Enhance image in area-of-interest in the part that changes over time;
Histogram equalization is carried out to area-of-interest gray level image;
Median filtering is carried out to area-of-interest gray level image.
7. mine leather belt according to claim 6 is vertical to tear detection method, which is characterized in that in step D, the acquisition striation
Segmentation threshold, comprising:
Image of interest is divided into m subgraph, each subgraph column data containing n;
Segmentation threshold is obtained to each subgraph by the following method: calculating the pixel number of each gray level in subgraph;It calculates each
Gray-level pixels number accounts for the ratio of subgraph total pixel number;Calculate the gray average of subgraph;Subgraph gray level is traversed, it is suitable to find
Striation segmentation threshold Ti;Striation segmentation threshold function T (x) is determined using Gauss curve fitting.
8. mine leather belt according to claim 7 is vertical to tear detection method, which is characterized in that in step E, the Threshold segmentation
Obtain optical strip image, comprising:
Region of interest area image is split according to threshold function table T (x) using platform intelligent video engine operator.
9. mine leather belt according to claim 8 is vertical to tear detection method, which is characterized in that described to obtain linearly in step F
Light center striation, comprising:
General center striation position is extracted using extremum method;
Judge light stripe centric line ordinate fluctuation, column beyond fluctuation range find next extreme point, repeat this step until
Light stripe centric line ordinate fluctuates all within the set range;
Increase by 20 pixels respectively up and down in rough optical losses line position to include complete striation;
Light stripe centric line is extracted using grey scale centre of gravity method.
10. mine leather belt according to claim 9 is vertical to tear detection method, which is characterized in that in step G, the judgement line
Property light stripe centric line feature, judge whether occur belt longitudinal tearing, comprising:
Light stripe centric line is obtained along the coordinate minimum value and maximum value in striation direction;
Light stripe centric line is traversed along the coordinate in striation direction, from minimum value to maximum value, given threshold p calculates light stripe centric line
Euclidean distance d, d between upper consecutive points are more than p, then it is assumed that belt longitudinal tearing occurs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811310349.XA CN109409368A (en) | 2018-11-06 | 2018-11-06 | Mine leather belt is vertical to tear detection device and detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811310349.XA CN109409368A (en) | 2018-11-06 | 2018-11-06 | Mine leather belt is vertical to tear detection device and detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409368A true CN109409368A (en) | 2019-03-01 |
Family
ID=65471584
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811310349.XA Pending CN109409368A (en) | 2018-11-06 | 2018-11-06 | Mine leather belt is vertical to tear detection device and detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409368A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134151A (en) * | 2019-05-31 | 2019-08-16 | 华中科技大学 | A kind of bus type vision levelling control system based on laser aiming |
CN110211107A (en) * | 2019-05-28 | 2019-09-06 | 太原理工大学 | A kind of mining adhesive tape damage detecting method based on dual-band infrared image |
CN111646146A (en) * | 2020-05-14 | 2020-09-11 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
CN112991292A (en) * | 2021-03-12 | 2021-06-18 | 天津工业大学 | Method and device for detecting longitudinal tear of conveying belt |
CN113120555A (en) * | 2021-04-28 | 2021-07-16 | 中国矿业大学 | Conveying belt longitudinal tearing detection method based on line structured light |
CN113344891A (en) * | 2021-06-21 | 2021-09-03 | 南京北新智能科技有限公司 | Belt detection algorithm based on machine vision |
CN113989286A (en) * | 2021-12-29 | 2022-01-28 | 深圳江行联加智能科技有限公司 | Deep learning method, device, equipment and storage medium for belt tearing strength |
CN115171051A (en) * | 2022-09-06 | 2022-10-11 | 合肥金星智控科技股份有限公司 | Online detection method and system for tearing of edge of conveying belt |
CN115947066A (en) * | 2023-03-14 | 2023-04-11 | 合肥金星智控科技股份有限公司 | Belt tearing detection method, device and system |
CN116142727A (en) * | 2023-04-14 | 2023-05-23 | 合肥金星智控科技股份有限公司 | Conveyor belt tearing detection method and system based on laser stripe defect identification |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106315162A (en) * | 2016-10-24 | 2017-01-11 | 天津工业大学 | Longitudinal tear detection device of conveyer belt |
CN107465858A (en) * | 2017-09-13 | 2017-12-12 | 苏州科可瑞尔航空技术有限公司 | Video shooting device and video camera transmission method |
US9861319B2 (en) * | 2015-03-23 | 2018-01-09 | University Of Kentucky Research Foundation | Noncontact three-dimensional diffuse optical imaging of deep tissue blood flow distribution |
CN108629790A (en) * | 2018-04-26 | 2018-10-09 | 大连理工大学 | A kind of optical strip image threshold segmentation method based on depth residual error network |
-
2018
- 2018-11-06 CN CN201811310349.XA patent/CN109409368A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9861319B2 (en) * | 2015-03-23 | 2018-01-09 | University Of Kentucky Research Foundation | Noncontact three-dimensional diffuse optical imaging of deep tissue blood flow distribution |
CN106315162A (en) * | 2016-10-24 | 2017-01-11 | 天津工业大学 | Longitudinal tear detection device of conveyer belt |
CN107465858A (en) * | 2017-09-13 | 2017-12-12 | 苏州科可瑞尔航空技术有限公司 | Video shooting device and video camera transmission method |
CN108629790A (en) * | 2018-04-26 | 2018-10-09 | 大连理工大学 | A kind of optical strip image threshold segmentation method based on depth residual error network |
Non-Patent Citations (3)
Title |
---|
张春明: "基于线激光辅助的皮带撕裂视觉检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
李现国 等: "基于线激光和ARM的输送带纵向撕裂监控系统设计", 《煤炭科学技术》 * |
杨蒙超: "基于Hi3516的矿井运动目标检测系统的设计与实现", 《中国煤炭》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110211107A (en) * | 2019-05-28 | 2019-09-06 | 太原理工大学 | A kind of mining adhesive tape damage detecting method based on dual-band infrared image |
CN110134151A (en) * | 2019-05-31 | 2019-08-16 | 华中科技大学 | A kind of bus type vision levelling control system based on laser aiming |
CN110134151B (en) * | 2019-05-31 | 2020-07-28 | 华中科技大学 | Bus type vision leveling control system based on laser guide |
CN111646146A (en) * | 2020-05-14 | 2020-09-11 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
CN111646146B (en) * | 2020-05-14 | 2021-03-02 | 精英数智科技股份有限公司 | Intelligent belt tearing detection method and device |
CN112991292A (en) * | 2021-03-12 | 2021-06-18 | 天津工业大学 | Method and device for detecting longitudinal tear of conveying belt |
CN113120555A (en) * | 2021-04-28 | 2021-07-16 | 中国矿业大学 | Conveying belt longitudinal tearing detection method based on line structured light |
CN113344891A (en) * | 2021-06-21 | 2021-09-03 | 南京北新智能科技有限公司 | Belt detection algorithm based on machine vision |
CN113989286A (en) * | 2021-12-29 | 2022-01-28 | 深圳江行联加智能科技有限公司 | Deep learning method, device, equipment and storage medium for belt tearing strength |
CN115171051A (en) * | 2022-09-06 | 2022-10-11 | 合肥金星智控科技股份有限公司 | Online detection method and system for tearing of edge of conveying belt |
CN115947066A (en) * | 2023-03-14 | 2023-04-11 | 合肥金星智控科技股份有限公司 | Belt tearing detection method, device and system |
CN116142727A (en) * | 2023-04-14 | 2023-05-23 | 合肥金星智控科技股份有限公司 | Conveyor belt tearing detection method and system based on laser stripe defect identification |
CN116142727B (en) * | 2023-04-14 | 2023-09-19 | 合肥金星智控科技股份有限公司 | Conveyor belt tearing detection method and system based on laser stripe defect identification |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409368A (en) | Mine leather belt is vertical to tear detection device and detection method | |
Zhang et al. | CCTSDB 2021: a more comprehensive traffic sign detection benchmark | |
CN106548182B (en) | Pavement crack detection method and device based on deep learning and main cause analysis | |
Song et al. | Real-time tunnel crack analysis system via deep learning | |
CN109101871A (en) | A kind of living body detection device based on depth and Near Infrared Information, detection method and its application | |
Ye et al. | Text detection and restoration in natural scene images | |
CN101944267B (en) | Smoke and fire detection device based on videos | |
CN106128121B (en) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis | |
CN109801265B (en) | Real-time transmission equipment foreign matter detection system based on convolutional neural network | |
EP1107179A3 (en) | Method for detecting sky in images | |
CN109145742A (en) | A kind of pedestrian recognition method and system | |
CN109359577B (en) | System for detecting number of people under complex background based on machine learning | |
CN106529530A (en) | Monocular vision-based ahead vehicle detection method | |
EP3905104B1 (en) | Living body detection method and device | |
CN104408780A (en) | Face recognition attendance system | |
CN105046808A (en) | Banknote multi-spectral high-resolution image acquisition system and acquisition method | |
CN204039886U (en) | A kind of pavement damage crack detection system based on multiple stage camera stereoscopic shooting | |
CN205721986U (en) | A kind of cable visual defects detection and character recognition device | |
CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
CN110674672A (en) | Multi-scene people counting method based on tof camera | |
CN101930540A (en) | Video-based multi-feature fusion flame detecting device and method | |
CN109784145B (en) | Target detection method based on depth map and storage medium | |
CN102982308A (en) | Palm print collecting and positioning method in long distance on-line authentication research | |
CN104715250A (en) | Cross laser detection method and device | |
WO2024037408A1 (en) | Underground coal mine pedestrian detection method based on image fusion and feature enhancement |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190301 |