CN117819160A - Automatic monitoring method and system for coal flow of belt conveyor based on image processing - Google Patents
Automatic monitoring method and system for coal flow of belt conveyor based on image processing Download PDFInfo
- Publication number
- CN117819160A CN117819160A CN202410238847.7A CN202410238847A CN117819160A CN 117819160 A CN117819160 A CN 117819160A CN 202410238847 A CN202410238847 A CN 202410238847A CN 117819160 A CN117819160 A CN 117819160A
- Authority
- CN
- China
- Prior art keywords
- value
- coal flow
- real
- coding
- frame
- 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.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 108
- 238000012544 monitoring process Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 238000004519 manufacturing process Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 description 16
- 238000007906 compression Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of image processing, and particularly relates to an automatic monitoring method and system for a coal flow of a belt conveyor based on image processing, wherein the method comprises the following steps: the method comprises the steps of collecting real-time coal flow monitoring videos, determining a first value range according to the frequency of gray values in I frames, determining a target divisor according to the approximate total coding length of the I frames corresponding to each divisor in the first value range, coding the I frames according to the target divisor, transmitting the coding results of the real-time coal flow monitoring videos formed by the coding results of the I frames and all P frames to a control center, decoding the coding results of the real-time coal flow monitoring videos by the control center, and automatically monitoring a belt conveyor through the real-time coal flow monitoring videos. When an emergency occurs, the invention ensures that the system can respond and intervene in time, thereby ensuring the normal operation of coal flow conveying work and improving the production efficiency.
Description
Technical Field
The invention relates to the technical field of image processing. More particularly, the invention relates to an automatic monitoring method and system for a coal flow of a belt conveyor based on image processing.
Background
In the process of conveying the coal flow by the belt conveyor, the control center automatically monitors the states of the conveyor and the coal flow through the monitoring video, can respond to emergency events such as belt deviation, faults, material leakage, coal flow blockage and the like of the conveyor, intervenes on the conveyor, ensures normal operation of the coal flow conveying work, and improves production efficiency.
In order to quickly respond and intervene in time at the first time of an emergency, the control center needs to be ensured to be capable of acquiring the coal flow monitoring video in real time, and the coal flow monitoring video acquired in real time puts higher requirements on the transmission speed, so that the coal flow monitoring video needs to be compressed before being transmitted.
Huffman coding is a conventional frequency-based compression method, and the compression efficiency of huffman coding depends on the kind and frequency of the coding object, and the smaller the kind of the coding object and the larger the frequency, the larger the compression efficiency; however, when encoding an image by huffman coding, usually, the gray values of pixels are used as the encoding objects, and the variety of the encoding objects is large, so that the frequency of each encoding object is small, and the compression efficiency of encoding an image by huffman coding is low.
Disclosure of Invention
To solve one or more of the above-described technical problems, the present invention provides aspects as follows.
In a first aspect, the present invention provides an image processing-based automatic monitoring method for a coal flow of a belt conveyor, comprising:
collecting a real-time coal flow monitoring video, and determining an I frame and a P frame of the real-time coal flow monitoring video through an inter-frame coding technology;
determining a maximum gray value according to the frequency of the gray value in the gray histogram of the I frame, and determining a first value range according to the difference value of adjacent maximum gray values and the frequency of the maximum gray value;
taking each integer in the first value range as a divisor, and for any divisor: determining a first value and a second value of each pixel point according to the gray value of each pixel point and the division operation result of the divisor, determining an encoding object according to the value range of the first value and the second value, and determining the approximate total encoding length of an I frame according to the frequency of the encoding object;
calculating the approximate total coding length of the I frame corresponding to each divisor, and taking the divisor corresponding to the minimum value of the approximate total coding length as a target divisor;
encoding an I frame through Huffman encoding according to all encoding objects corresponding to the target divisor, determining the encoding result of a real-time coal stream monitoring video according to the encoding results of the I frame and all P frames, and transmitting the encoding result of the real-time coal stream monitoring video to a control center;
the control center decodes the coding result of the real-time coal flow monitoring video, determines the real-time coal flow monitoring video, and automatically monitors the belt conveyor through the real-time coal flow monitoring video.
In one embodiment, the determining the maximum gray value according to the frequency of the gray value in the gray histogram of the I frame includes:
counting to obtain a gray level histogram of the I frame, wherein the gray level histogram comprises frequencies of all gray level values, determining maximum value points in all frequencies, taking gray level values corresponding to all the maximum value points as the maximum gray level values, and numbering all the maximum gray level values according to the sequence from small to large.
In one embodiment, the determining the first value range according to the difference between the adjacent maximum gray values and the frequency of the maximum gray values includes:
determining the average interval R according to the difference between adjacent maximum gray values and the frequency of the maximum gray valuesAs a first value range, R represents an average interval, & lt/L>Representing a rounding down.
In one embodiment, the average interval R satisfies the expression:
wherein R represents an average interval, G represents the number of all the maximum gray values, i and w are the serial numbers of the maximum gray values,、/>frequency of the ith maximum gray value and the ith-1 th maximum gray value, respectively, +.>、/>Respectively representing the ith maximum gray value and the ith-1 th maximum gray value,/->、/>Frequency of w-th maximum gray value and w-1 th maximum gray value, respectively, +.>、/>The w-th maximum gray value and the w-1 st maximum gray value are respectively represented.
In one embodiment, the first and second values of the pixel point refer to a quotient and a remainder in a result of a division operation of the gray value and the divisor of the pixel point, respectively.
In one embodiment, the first and second values are respectively in the range ofAnd [0, k-1 ]]Wherein k represents a divisor, +.>Representing a rounding down.
In one embodiment, the approximate total coding length of the I-frame satisfies the expression:
wherein B represents the approximate total coding length of the I frame, n represents the sequence number of the coding object, and n is taken over [0, K ]]All integers in the range are within the range,representing the frequency of the nth code object, +.>Represents a logarithmic function with 2 as a base, K represents the maximum value in the range of values of the encoding object, and N represents the number of all pixel points in the I frame.
In one embodiment, determining the encoding object according to the value ranges of the first value and the second value includes:
the value range of the first value and the value of the second value are takenThe union of the value ranges is used as the value range [0, K ] of the coding object]Wherein, the method comprises the steps of, wherein,k represents the maximum value in the range of values of the encoding object, max () represents the maximum value, ++>Represents the maximum value of the range of values of the first value, k-1 represents the maximum value of the range of values of the second value, k represents the divisor,/o>Representing a downward rounding; the union [0, K]All integers in (a) are used as coding objects, and all the coding objects are numbered in the order from small to large.
In one embodiment, the automatic monitoring of the belt conveyor by the real-time coal flow monitoring video comprises:
the real-time coal flow monitoring video is identified through the trained two-class neural network, whether an emergency exists in the real-time coal flow monitoring video is determined, when the emergency exists in the real-time coal flow monitoring video, the real-time coal flow monitoring video is early-warned to a worker of a control center, the worker further judges the emergency existing in the real-time coal flow monitoring video, the emergency is identified as the condition that the conveyor is subject to any one of belt deviation, faults, material leakage and coal flow blockage, and corresponding measures are adopted to intervene the conveyor, so that the normal operation of the coal flow conveying work is ensured, and the production efficiency is improved.
In a second aspect, the invention provides an automatic monitoring system for coal flow of a belt conveyor based on image processing, which adopts the following technical scheme:
automatic monitoring system of belt conveyor coal flow based on image processing includes: the system comprises a processor and a memory, wherein the memory stores computer program instructions which when executed by the processor realize the automatic monitoring method of the coal flow of the belt conveyor based on image processing.
By adopting the technical scheme, the automatic monitoring method for the coal flow of the belt conveyor based on image processing generates a computer program, and the computer program is stored in the memory to be loaded and executed by the processor, so that terminal equipment is manufactured according to the memory and the processor, and the automatic monitoring method is convenient to use.
The invention has the beneficial effects that: according to the method, the first numerical value and the second numerical value of each pixel point are determined according to the division operation result of the gray value and the divisor of each pixel point, the first numerical value and the second numerical value of each pixel point are used as coding objects, the types of the coding objects are reduced, the frequency of each coding object is increased, the compression efficiency when I frames are coded through Huffman coding is further improved, in the process of conveying coal flows by a belt conveyor, a control center is guaranteed to acquire the coal flow monitoring video in real time, and timely response and intervention are guaranteed when emergency occurs, so that normal operation of coal flow conveying work is guaranteed, and production efficiency is improved.
Further, the invention calculates the approximate total coding length of the I frame corresponding to each divisor according to the frequency of the coding object corresponding to each divisor in the first value range, takes the divisor corresponding to the minimum value of the approximate total coding length as a target divisor, codes the I frame through Huffman coding according to all the coding objects corresponding to the target divisor, and at the moment, the approximate total coding length of the I frame is shortest, so that the compression efficiency when the I frame is coded through Huffman coding is maximized.
Further, the invention determines the maximum gray value according to the frequency of the gray value in the gray histogram of the I frame, and determines the first value range according to the difference value of the adjacent maximum gray values and the frequency of the maximum gray value, thereby shortening the first value range, reducing the number of divisors required to be traversed and improving the efficiency of determining the target divisor.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flow chart schematically showing a method for automatically monitoring a coal flow of a belt conveyor based on image processing in the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
With the rapid development of computer vision technology, the control center automatically monitors the states of the conveyor and the coal flow through the monitoring video, and in the process of conveying the coal flow by the belt conveyor, the control center needs to acquire the coal flow monitoring video in real time so as to timely respond and intervene when the conveyor has emergency events such as belt deviation, faults, material leakage, coal flow blockage and the like, thereby ensuring the normal operation of the coal flow conveying work and improving the production efficiency.
The real-time acquisition of the coal flow monitoring video puts higher requirements on the transmission speed, so that the coal flow monitoring video needs to be compressed before being transmitted; huffman coding is a conventional frequency-based compression method, and the compression efficiency of huffman coding depends on the kind and frequency of the coding object, and the smaller the kind of the coding object and the larger the frequency, the larger the compression efficiency; however, when the video is encoded by huffman coding, the gray values of the pixels are usually used as the encoding objects, and since the scenes in the video are complex, the number of the gray values of the pixels in the video is large, the number of the encoding objects is large, resulting in a small frequency of each encoding object, and thus in a small compression efficiency when the video is encoded by huffman coding.
In summary, the invention determines the maximum gray value according to the frequency of the gray value in the gray histogram of the I frame of the real-time coal stream monitoring video, determines the first value range according to the difference value of the adjacent maximum gray values and the frequency of the maximum gray value, takes each integer in the first value range as a divisor, and for any divisor: according to the result of division operation of gray values and divisors of each pixel point, determining a first numerical value and a second numerical value of each pixel point, determining an encoding object according to the value range of the first numerical value and the second numerical value, determining the approximate total encoding length of an I frame according to the frequency of the encoding object, calculating the approximate total encoding length of the I frame corresponding to each divisor, taking the divisor corresponding to the minimum value of the approximate total encoding length as a target divisor, encoding the I frame through Huffman encoding according to all encoding objects corresponding to the target divisor, determining the encoding result of the real-time coal flow monitoring video according to the encoding results of the I frame and all P frames, transmitting the encoding result of the real-time coal flow monitoring video to a control center, decoding the encoding result of the real-time coal flow monitoring video by the control center, determining the real-time coal flow monitoring video, and automatically monitoring the belt conveyor by the real-time coal flow monitoring video.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
The embodiment of the invention discloses an automatic monitoring method for a coal flow of a belt conveyor based on image processing, which comprises the following steps of S1-S4 with reference to FIG. 1:
s1, acquiring a real-time coal flow monitoring video.
Optionally, a real-time coal flow monitoring video of the belt conveyor during coal transportation is collected through an installed monitoring camera, and an I frame and a P frame of the real-time coal flow monitoring video are determined through an inter-frame coding technology.
The specific value of the sampling period of the real-time coal flow monitoring video can be set according to the actual application scene and the requirement, and the sampling period of the real-time coal flow monitoring video is set to be 5 seconds.
S2, determining a first value range according to the frequency of gray values in the I frames, and determining a target divisor according to the approximate total coding length of the I frames corresponding to each divisor in the first value range.
When the real-time video is encoded by huffman coding, the scene in the video is complex, so that the variety of gray values of pixels in the video is large, and the gray values of pixels are used as coding objects, so that the variety of the coding objects is large, and the frequency of each coding object is small, which affects the compression efficiency when the real-time video is encoded by huffman coding.
It should be further noted that, in the present invention, the division result of the gray value and the divisor of the pixel point is determined, the quotient and the remainder in the division result are taken as the encoding objects, the value ranges of the quotient and the remainder overlap, and the union of the value ranges of the quotient and the remainder is smaller than the value range of the gray value, compared with the case that the gray value is taken as the encoding object, the variety of the encoding object is reduced, the frequency of each encoding object is increased, and the compression efficiency when the I frame is encoded by huffman encoding is improved.
In order to maximize compression efficiency when encoding an I frame by huffman coding, a target divisor that minimizes the approximate total encoding length of the I frame is determined by traversing each divisor in the first range of values.
Optionally, when determining the first value range, determining that the first value range is [2, H ] according to the maximum gray value in the I frame, where H represents the maximum gray value in the I frame.
In order to shorten the first value range, reduce the number of divisors to be traversed, and increase the efficiency of determining the target divisor, in the present invention, in order to increase the frequency of each encoding object, the remainder in the result of the division operation of the gray value that is the maximum point in terms of frequency needs to be made the same by the divisor, so the first value range is determined according to the difference between adjacent maximum gray values and the frequency of the maximum gray value.
Preferably, the maximum gray value is determined according to the frequency of the gray value in the gray histogram of the I frame, and the first value range is determined according to the difference between adjacent maximum gray values and the frequency of the maximum gray value.
The determining the maximum gray value according to the frequency of the gray value in the gray histogram of the I frame comprises: counting to obtain a gray level histogram of the I frame, wherein the gray level histogram comprises frequencies of all gray level values, determining maximum value points in all frequencies, taking gray level values corresponding to all the maximum value points as the maximum gray level values, and numbering all the maximum gray level values according to the sequence from small to large.
The determining the first value range according to the difference value of the adjacent maximum gray values and the frequency of the maximum gray values comprises the following steps: determining the average interval R according to the difference between adjacent maximum gray values and the frequency of the maximum gray valuesAs a first value range, R represents an average interval, & lt/L>Representing a rounding down.
The average interval R satisfies the expression:
wherein R represents an average interval, G represents the number of all the maximum gray values, i and w are the serial numbers of the maximum gray values,、/>frequency of the ith maximum gray value and the ith-1 th maximum gray value, respectively, +.>、/>Respectively representing the ith maximum gray value and the ith-1 th maximum gray value,/->、/>Frequency of w-th maximum gray value and w-1 th maximum gray value, respectively, +.>、/>The w-th maximum gray value and the w-1 st maximum gray value are respectively represented.
It should be noted that the number of the substrates,representing the difference between adjacent maximum gray values, i.e. the interval between adjacent maximum gray values, +.>The larger the value is, the more likely the interval of the adjacent maximum gray values is the target divisor, so the average interval is determined by weighting the interval of the adjacent maximum gray values by the sum of the frequencies of the adjacent maximum gray values.
Specifically, each integer in the first value range is used as a divisor, for any divisor, a first value and a second value of each pixel point are determined according to the result of division operation of the gray value of each pixel point and the divisor, and the coding object is determined according to the value ranges of the first value and the second value.
The first value of the pixel point is the quotient of the gray value of the pixel point and the result of the division operation of the divisor, and the second value of the pixel point is the remainder of the result of the division operation of the gray value of the pixel point and the divisor, therefore, the value range of the first value of the pixel point isBecause the remainder is smaller than the divisor, the second value of the pixel point has a value range of [0, k-1 ]]K represents a divisor->Representing a rounding down.
In the subsequent encoding process, the first value and the second value of the pixel point are used as the encoding targets, so that the union of the value range of the first value and the value range of the second value is used as the value range of the encoding targets.
The determining the coding object according to the value ranges of the first value and the second value comprises the following steps: taking the union of the value range of the first numerical value and the value range of the second numerical value as the value range [0, K ] of the coding object]Wherein, the method comprises the steps of, wherein,max () means taking the maximum value,/>Representing the maximum value of the value range of the first value, and k-1 represents the maximum value of the value range of the second value; the union [0, K]All integers in (a) are used as coding objects, and all the coding objects are numbered in the order from small to large.
In order to maximize compression efficiency when encoding an I frame by huffman coding, a target divisor that minimizes the approximate total encoding length of the I frame is determined by traversing each divisor in the first range of values.
Specifically, according to the frequencies of all the encoding objects, determining the approximate total encoding length of the I frame, wherein the approximate total encoding length of the I frame meets the expression:
wherein B represents the approximate total coding length of the I frame, n represents the sequence number of the coding object, and n is taken over [0, K ]]All integers in the range are within the range,representing the frequency of the nth code object, +.>Represents a logarithmic function with 2 as a base, K represents the maximum value in the range of values of the encoding object, and N represents the number of all pixel points in the I frame.
When the first value and the second value of the pixel point are used as the coding objects, each pixel point has two objects to be coded, so that the number of all the objects to be coded in the I frame is 2N; in huffman coding, the entropy of information obtained by the frequencies of all the coded objects can approximate the average coding length of the object to be coded, and therefore,the method can represent the approximate average coding length of each object to be coded when the I frame is coded by Huffman coding and the first numerical value and the second numerical value of the pixel point are taken as the coding objects; then->The smaller this value, the higher the compression efficiency of encoding the I frame by huffman coding, which represents the approximate total encoding length of the I frame.
Further, the approximate total coding length of the I frame corresponding to each divisor is calculated, and the divisor corresponding to the minimum value of the approximate total coding length is taken as the target divisor.
S3, encoding the I frame through Huffman encoding according to all encoding objects corresponding to the target divisor, determining the encoding result of the real-time coal stream monitoring video according to the encoding results of the I frame and all P frames, and transmitting the encoding result of the real-time coal stream monitoring video to a control center.
Specifically, a Huffman tree is constructed according to the frequencies of all the coding objects corresponding to the target divisor, and a Huffman coding table is constructed according to the Huffman tree, wherein the Huffman coding table comprises the coding results of all the coding objects; and encoding the first numerical value and the second numerical value of each pixel point according to the Huffman tree, wherein the encoding results of the first numerical value and the second numerical value of all the pixel points form the encoding result of the I frame.
Construction of huffman trees is a well-known technique and will not be described in detail herein.
Coding the P frames in sequence by utilizing an inter-frame coding technology according to the I frames according to the time sequence; and taking the coding results of the I frames and all the P frames as the coding results of the real-time coal flow monitoring video.
Taking a Huffman coding table as auxiliary information; and transmitting the real-time coding result and auxiliary information of the coal flow monitoring video to a control center.
S4, decoding the coding result of the real-time coal flow monitoring video by the control center, determining the real-time coal flow monitoring video, and automatically monitoring the belt conveyor through the real-time coal flow monitoring video.
The control center decodes the coding result of the real-time coal flow monitoring video to determine the real-time coal flow monitoring video, and the method comprises the following steps: decoding an I frame encoding result in the encoding result of the real-time coal stream monitoring video according to the auxiliary information to determine an I frame; sequentially decoding all P frames in the real-time coal stream monitoring video coding results by utilizing an inter-frame compression technology according to the I frames to determine the P frames; the I-frames and all P-frames constitute a real-time coal stream surveillance video.
The automatic monitoring of the belt conveyor through the real-time coal flow monitoring video comprises the following steps: the real-time coal flow monitoring video is identified through the trained two-class neural network, whether an emergency exists in the real-time coal flow monitoring video is determined, when the emergency exists in the real-time coal flow monitoring video, the real-time coal flow monitoring video is early-warned to a worker of a control center, at the moment, the worker further judges the emergency existing in the real-time coal flow monitoring video, the emergency is identified as the type of the belt deviation, the fault, the material leakage and the coal flow blockage of the conveyor, and corresponding measures are adopted to intervene the conveyor, so that the normal operation of the coal flow conveying work is ensured, and the production efficiency is improved.
The embodiment of the invention also discloses an automatic monitoring system of the belt conveyor coal flow based on image processing, which comprises a processor and a memory, wherein the memory stores computer program instructions, and the automatic monitoring method of the belt conveyor coal flow based on the image processing is realized when the computer program instructions are executed by the processor.
The above system further comprises other components well known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and therefore are not described in detail herein.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (10)
1. The automatic monitoring method for the coal flow of the belt conveyor based on the image processing is characterized by comprising the following steps of:
collecting a real-time coal flow monitoring video, and determining an I frame and a P frame of the real-time coal flow monitoring video through an inter-frame coding technology;
determining a maximum gray value according to the frequency of the gray value in the gray histogram of the I frame, and determining a first value range according to the difference value of adjacent maximum gray values and the frequency of the maximum gray value;
taking each integer in the first value range as a divisor, and for any divisor: determining a first value and a second value of each pixel point according to the gray value of each pixel point and the division operation result of the divisor, determining an encoding object according to the value range of the first value and the second value, and determining the approximate total encoding length of an I frame according to the frequency of the encoding object;
calculating the approximate total coding length of the I frame corresponding to each divisor, and taking the divisor corresponding to the minimum value of the approximate total coding length as a target divisor;
encoding an I frame through Huffman encoding according to all encoding objects corresponding to the target divisor, determining the encoding result of a real-time coal stream monitoring video according to the encoding results of the I frame and all P frames, and transmitting the encoding result of the real-time coal stream monitoring video to a control center;
the control center decodes the coding result of the real-time coal flow monitoring video, determines the real-time coal flow monitoring video, and automatically monitors the belt conveyor through the real-time coal flow monitoring video.
2. The method for automatically monitoring a coal flow of a belt conveyor based on image processing according to claim 1, wherein the determining a maximum gray value according to a frequency of gray values in a gray histogram of the I frame comprises:
counting to obtain a gray level histogram of the I frame, wherein the gray level histogram comprises frequencies of all gray level values, determining maximum value points in all frequencies, taking gray level values corresponding to all the maximum value points as the maximum gray level values, and numbering all the maximum gray level values according to the sequence from small to large.
3. The method for automatically monitoring a coal flow of a belt conveyor based on image processing according to claim 1, wherein the determining the first value range according to the difference between the adjacent maximum gray values and the frequency of the maximum gray values comprises:
determining the average interval R according to the difference between adjacent maximum gray values and the frequency of the maximum gray valuesAs a first value range, R represents an average interval, & lt/L>Representing a rounding down.
4. The image processing-based automatic monitoring method for a coal flow of a belt conveyor according to claim 3, wherein the average interval R satisfies the expression:
wherein R represents an average interval, G represents the number of all the maximum gray values, i and w are the serial numbers of the maximum gray values,、frequency of the ith maximum gray value and the ith-1 th maximum gray value, respectively, +.>、/>Respectively representing the ith maximum gray value and the ith-1 th maximum gray value,/->、/>Frequency of w-th maximum gray value and w-1 th maximum gray value, respectively, +.>、/>The w-th maximum gray value and the w-1 st maximum gray value are respectively represented.
5. The method for automatically monitoring the coal flow of the belt conveyor based on the image processing according to claim 1, wherein the first numerical value and the second numerical value of the pixel point refer to a quotient and a remainder in a result of division operation of a gray value and a divisor of the pixel point, respectively.
6. The method for automatically monitoring the coal flow of the belt conveyor based on the image processing according to claim 1, wherein the value ranges of the first value and the second value are respectivelyAnd [0, k-1 ]]Wherein k represents a divisor, +.>Representing a rounding down.
7. The image processing-based automatic monitoring method for a coal flow of a belt conveyor according to claim 1, wherein the approximate total code length of the I-frame satisfies the expression:
wherein B represents the approximate total coding length of the I frame, n represents the sequence number of the coding object, and n is taken over [0, K ]]All integers in the range are within the range,representing the frequency of the nth code object, +.>Represents a logarithmic function with 2 as a base, K represents the maximum value in the range of values of the encoding object, and N represents the number of all pixel points in the I frame.
8. The method for automatically monitoring the coal flow of the belt conveyor based on the image processing according to claim 1, wherein the determining the coding object according to the value ranges of the first value and the second value comprises:
taking the union of the value range of the first numerical value and the value range of the second numerical value as the value of the coding objectRange [0, K]Wherein, the method comprises the steps of, wherein,k represents the maximum value in the range of values of the encoding object, max () represents the maximum value, ++>Represents the maximum value of the range of values of the first value, k-1 represents the maximum value of the range of values of the second value, k represents the divisor,/o>Representing a downward rounding; the union [0, K]All integers in (a) are used as coding objects, and all the coding objects are numbered in the order from small to large.
9. The method for automatically monitoring the coal flow of the belt conveyor based on the image processing according to claim 1, wherein the method for automatically monitoring the belt conveyor by a real-time coal flow monitoring video comprises the following steps:
the real-time coal flow monitoring video is identified through the trained two-class neural network, whether an emergency exists in the real-time coal flow monitoring video is determined, when the emergency exists in the real-time coal flow monitoring video, the real-time coal flow monitoring video is early-warned to a worker of a control center, the worker further judges the emergency existing in the real-time coal flow monitoring video, the emergency is identified as the condition that the conveyor is subject to any one of belt deviation, faults, material leakage and coal flow blockage, and corresponding measures are adopted to intervene the conveyor, so that the normal operation of the coal flow conveying work is ensured, and the production efficiency is improved.
10. Automatic monitoring system of belt conveyor coal flow based on image processing, its characterized in that includes: a processor and a memory storing computer program instructions which, when executed by the processor, implement the image processing based belt conveyor coal flow automatic monitoring method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410238847.7A CN117819160B (en) | 2024-03-04 | 2024-03-04 | Automatic monitoring method and system for coal flow of belt conveyor based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410238847.7A CN117819160B (en) | 2024-03-04 | 2024-03-04 | Automatic monitoring method and system for coal flow of belt conveyor based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117819160A true CN117819160A (en) | 2024-04-05 |
| CN117819160B CN117819160B (en) | 2024-06-25 |
Family
ID=90508237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410238847.7A Active CN117819160B (en) | 2024-03-04 | 2024-03-04 | Automatic monitoring method and system for coal flow of belt conveyor based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117819160B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040004666A1 (en) * | 2001-08-01 | 2004-01-08 | Chikako Sano | Image pick-up apparatus and image pickup method |
| JP2008104121A (en) * | 2006-10-20 | 2008-05-01 | Canon Inc | Image encoding device and control method thereof |
| CN101360184A (en) * | 2008-09-22 | 2009-02-04 | 腾讯科技（深圳）有限公司 | System and method for extracting key frame of video |
| CN101547352A (en) * | 2008-03-26 | 2009-09-30 | 中华映管股份有限公司 | Method for compressing and decompressing image |
| US20150332444A1 (en) * | 2012-10-25 | 2015-11-19 | Mitsubishi Electric Corporation | Image processing device and image processing method |
| CN105450929A (en) * | 2015-12-09 | 2016-03-30 | 安徽海聚信息科技有限责任公司 | Information identification and communication method for smart wearable devices |
| CN113499553A (en) * | 2021-06-25 | 2021-10-15 | 上海东普信息科技有限公司 | Fire extinguishing method, device and equipment based on portable unmanned aerial vehicle and storage medium |
| CN113911629A (en) * | 2021-10-19 | 2022-01-11 | 精基科技有限公司 | Intelligent coal flow conveying system |
| CN115862131A (en) * | 2022-11-17 | 2023-03-28 | 天翼云科技有限公司 | Video data screening method for human motion recognition |
| CN115866251A (en) * | 2023-02-22 | 2023-03-28 | 浙江鼎立实业有限公司 | Semantic segmentation based image information rapid transmission method |
| CN116170027A (en) * | 2023-04-26 | 2023-05-26 | 北京索斯克科技开发有限公司 | Data management system and processing method for poison detection equipment |
| CN116405574A (en) * | 2023-06-08 | 2023-07-07 | 中国人民解放军总医院第二医学中心 | Remote medical image optimization communication method and system |
| CN116475089A (en) * | 2023-04-25 | 2023-07-25 | 西安科技大学 | Coordinated control device and method for intelligent video image recognition of mine belt conveyor |
| CN116760952A (en) * | 2023-08-17 | 2023-09-15 | 山东欣晖电力科技有限公司 | Unmanned aerial vehicle-based electric power iron tower maintenance inspection method |
| CN116828210A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Intelligent transmission method and system for submerged video acquisition |
-
2024
- 2024-03-04 CN CN202410238847.7A patent/CN117819160B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040004666A1 (en) * | 2001-08-01 | 2004-01-08 | Chikako Sano | Image pick-up apparatus and image pickup method |
| JP2008104121A (en) * | 2006-10-20 | 2008-05-01 | Canon Inc | Image encoding device and control method thereof |
| CN101547352A (en) * | 2008-03-26 | 2009-09-30 | 中华映管股份有限公司 | Method for compressing and decompressing image |
| CN101360184A (en) * | 2008-09-22 | 2009-02-04 | 腾讯科技（深圳）有限公司 | System and method for extracting key frame of video |
| US20150332444A1 (en) * | 2012-10-25 | 2015-11-19 | Mitsubishi Electric Corporation | Image processing device and image processing method |
| CN105450929A (en) * | 2015-12-09 | 2016-03-30 | 安徽海聚信息科技有限责任公司 | Information identification and communication method for smart wearable devices |
| CN113499553A (en) * | 2021-06-25 | 2021-10-15 | 上海东普信息科技有限公司 | Fire extinguishing method, device and equipment based on portable unmanned aerial vehicle and storage medium |
| CN113911629A (en) * | 2021-10-19 | 2022-01-11 | 精基科技有限公司 | Intelligent coal flow conveying system |
| CN115862131A (en) * | 2022-11-17 | 2023-03-28 | 天翼云科技有限公司 | Video data screening method for human motion recognition |
| CN115866251A (en) * | 2023-02-22 | 2023-03-28 | 浙江鼎立实业有限公司 | Semantic segmentation based image information rapid transmission method |
| CN116475089A (en) * | 2023-04-25 | 2023-07-25 | 西安科技大学 | Coordinated control device and method for intelligent video image recognition of mine belt conveyor |
| CN116170027A (en) * | 2023-04-26 | 2023-05-26 | 北京索斯克科技开发有限公司 | Data management system and processing method for poison detection equipment |
| CN116405574A (en) * | 2023-06-08 | 2023-07-07 | 中国人民解放军总医院第二医学中心 | Remote medical image optimization communication method and system |
| CN116760952A (en) * | 2023-08-17 | 2023-09-15 | 山东欣晖电力科技有限公司 | Unmanned aerial vehicle-based electric power iron tower maintenance inspection method |
| CN116828210A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Intelligent transmission method and system for submerged video acquisition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117819160B (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220058775A1 (en) | Video denoising method and apparatus, and storage medium | |
| CN105472205B (en) | Real-time video noise reduction method and device in encoding process | |
| JPH10304374A (en) | Moving image encoding device | |
| JP2012520025A (en) | System and method for processing motion vectors of video data | |
| CN103957341A (en) | Image transmission method and related device | |
| US6748114B1 (en) | Moving picture encoding method and moving picture encoding apparatus | |
| CN112351280A (en) | Video coding method and device, electronic equipment and readable storage medium | |
| CN103020138A (en) | Method and device for video retrieval | |
| CN101102504B (en) | A mixing motion detection method combining with video encoder | |
| CN111385571B (en) | Method and device for controlling code rate of ultra-long image group | |
| CN117819160B (en) | Automatic monitoring method and system for coal flow of belt conveyor based on image processing | |
| CN114157870A (en) | Encoding method, medium, and electronic device | |
| CN107431809B (en) | Image processing method and device | |
| CN117880520A (en) | Data management method for locomotive crewmember value multiplication standardized monitoring | |
| CN1292596C (en) | Motion vector detecting device and motion vector detecting program | |
| US20080267284A1 (en) | Moving picture compression apparatus and method of controlling operation of same | |
| CN113422959A (en) | Video encoding and decoding method and device, electronic equipment and storage medium | |
| CN111770334A (en) | Data encoding method and device, and data decoding method and device | |
| CN116016937A (en) | Sample self-adaptive compensation method and device in video coding | |
| CN105357494A (en) | Video encoding and decoding method and apparatus, and computer program product | |
| CN108990108B (en) | Self-adaptive real-time spectrum data compression method and system | |
| CN112383774B (en) | Encoding method, encoder and server | |
| US7706440B2 (en) | Method for reducing bit rate requirements for encoding multimedia data | |
| CN113660487B (en) | Parameter determination method and device for distributing corresponding bit number for frame image | |
| US11223834B2 (en) | Method for intra refresh encoding of a plurality of image frames using convex and concave distribution functions |
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 |