CN116342644A - Intelligent monitoring method and system suitable for coal yard - Google Patents
Intelligent monitoring method and system suitable for coal yard Download PDFInfo
- Publication number
- CN116342644A CN116342644A CN202310111512.4A CN202310111512A CN116342644A CN 116342644 A CN116342644 A CN 116342644A CN 202310111512 A CN202310111512 A CN 202310111512A CN 116342644 A CN116342644 A CN 116342644A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- suspected
- detection
- moving object
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 89
- 230000000877 morphologic effect Effects 0.000 claims abstract description 13
- 230000004044 response Effects 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 29
- 238000010606 normalization Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- -1 fire Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/223—Analysis of motion using block-matching
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an intelligent monitoring method and system suitable for a coal yard, which relate to the field of computers and comprise the following steps: enhancing a target frame image acquired by utilizing a camera to acquire a video image to obtain a first frame image; based on morphological operation, a detection image obtained by detecting the moving object of the first frame image is segmented to obtain a suspected moving area and detected, if the suspected moving object exists, detection information of a corresponding sensor is called, the detection information is sent out together with alarm information, if the suspected moving object does not exist, a background image is updated, and whether the moving object exists or not is detected again. Image quality is improved by preprocessing an image acquired with a camera; detecting a moving target and dividing the region of the improved image to obtain a suspected moving region; and detecting whether a motion target exists in the suspected motion area, and making a relevant response by combining sensor detection information, so that intelligent monitoring is effectively realized, and the safety early warning capability of a coal yard is further improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent monitoring method and system suitable for coal yards.
Background
Coal is known as black gold, and is still one of the energy sources necessary for our human production and life for a long time at present and in the future. The supply of coal is related to the stability of industrial and even whole social aspects of China, and the safety problem is the most important one in the energy safety of China.
The coal yard is used as an important place for exploiting and storing coal, the safety problem is important, but spontaneous combustion of the coal, personnel poisoning or other loss events often occur in the coal storage process, and currently, a sensor is generally selected for monitoring, but because some coal yards do not accord with the installation condition, the safety guarantee work is difficult to perfect, and loopholes exist.
Therefore, the invention provides an intelligent monitoring method and system for coal storage safety, which are suitable for coal yards.
Disclosure of Invention
The invention provides an intelligent monitoring method and system suitable for a coal yard, which are used for improving the image quality by preprocessing an image acquired by a camera; detecting a moving target and dividing the region of the improved image to obtain a suspected moving region; and detecting whether a motion target exists in the suspected motion area, and making a relevant response by combining detection information of the sensor, so that intelligent monitoring is effectively realized, and the safety early warning capability of a coal yard is improved.
The invention provides an intelligent monitoring method suitable for a coal yard, which comprises the following steps:
step 1: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
step 2: performing enhancement processing on the target frame image to obtain a first frame image;
step 3: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
step 4: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
step 5: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
Preferably, the preset position refers to an optimal mounting point for shooting at an indoor and outdoor coal storage pile.
Preferably, the target frame image enhancement processing is performed to obtain a first frame image, including:
step 11: converting the target frame image from RGB to YUV format;
step 12: performing enhancement processing on the Y component of the target frame image in the YUV format by using weighting, and performing self-adaptive correction on the U, V component;
step 13: and converting the target frame image in the YUV format after the components are adjusted into an RGB space to obtain a first frame image.
Preferably, the detecting the moving object of the first frame image by using video continuity to obtain a detected image includes:
J i (x,y)＝D i (x,y)-B i (x,y)
wherein J is i (x, y) is expressed as a detection image; d (D) i (x, y) being represented as the current ith first frame image; b (B) i (x, y) is represented as a background image;
analysis detection image J i (x, Y) mean and variance of the corresponding histogram to obtain a threshold Y;
if the gray value of the detection image is larger than Y, determining that the detection image is a motion foreground image;
otherwise, it is defined as a background image.
Preferably, analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion region image includes:
step 21: carrying out corrosion and re-expansion on the detection image, and combining with connected domain analysis processing to obtain a first image;
step 22: acquiring target characteristic information of different moving targets to be detected;
step 23: according to the obtained target characteristic information, target pixel points are screened from the first image and reserved;
step 24: and collecting the target pixel points to obtain a suspected motion area.
Preferably, the step of selecting and retaining the target pixel point from the first image according to the obtained target feature information includes:
based on different target characteristic information, acquiring an important value of each first pixel point in the first image, and collecting according to different moving targets to obtain a plurality of first sets D= { D cj J=1, 2,3,..n }, where d cj The important value is expressed as a j-th first pixel point aiming at a c-th moving object, and n represents the total number of the first pixel points corresponding to the c-th moving object;
wherein N is 1j The first pixel point denoted as j is based on the maximum value in the R, G, B channel; n (N) 2j The first pixel point denoted as j is based on the minimum value in the R, G, B channel; n (N) 3j The first pixel point denoted as j is based on the average value of R, G, B channels; Δ1 is expressed as an influence coefficient of the corresponding first pixel point on the important value of the first pixel point based on the difference value between the maximum value and the minimum value in the R, G, B channel; Δ2 is expressed as the average value of R, G, B channels for the corresponding first pixel pointInfluence coefficients of pixel importance values; p (P) c A target feature value expressed as a class c moving target; Δ3 is expressed as a contrast coefficient corresponding to the importance value of the first pixel point matched by the target feature value pair, and Δ3>Δ2>Δ1；
A loss factor expressed as a calculated first pixel point importance value;
determining the duty ratio results of the important values larger than a preset threshold value in all the first sets D;
selecting a first set with the duty ratio result larger than a preset duty ratio threshold as a target set according to the obtained duty ratio result;
and extracting pixel points corresponding to all important values larger than a preset threshold value in the target set from the first image, and reserving the pixel points as suspected motion areas.
Preferably, detecting the suspected moving area, if a suspected moving object exists, effectively responding according to the alarm condition and detection information of the corresponding sensor, if no suspected moving object exists, updating a background image, and re-detecting whether the moving object exists, including:
calculating a gradient of each pixel in the suspected motion region;
dividing the suspected motion area into image blocks with preset sizes;
defining the image block as a window, comparing the gray value magnitude relation of the central pixel point and the surrounding pixel points of the window,
if the surrounding pixel values are all larger than the central pixel value, marking the position of the pixel point as 1, otherwise marking the position as 0, and sequentially arranging generated binary numbers to obtain binary numbers in the window;
converting the obtained binary digits into decimal digits, and taking the decimal digits as a first characteristic value of the central pixel point of the window;
determining the occurrence frequency of each first characteristic value, and carrying out normalization processing to obtain a statistical histogram;
connecting the obtained statistical histograms of each window to obtain a first feature vector;
counting a gradient histogram of each image block;
forming a communication interval by the preset number of image blocks, and normalizing the corresponding gradient histograms to obtain intra-interval gradient histograms;
collecting all the obtained intra-interval gradient histograms to obtain a second feature vector;
comparing the key feature information reflected by the first feature vector and the second feature vector with the target feature information of the suspected moving target to obtain a similarity result;
if the similarity result is larger than a preset comparison threshold, determining that a suspected moving object exists in the suspected moving area, calling relevant detection information of a corresponding sensor to carry out data feedback at the moment, and starting an alarm action;
otherwise, updating the background image, and extracting the motion foreground according to the corresponding detection image to re-detect whether the motion target exists.
Preferably, the effective response according to the alarm condition and the detection information of the corresponding sensor includes:
step 31: after determining that the suspected moving object exists in the suspected moving area, combining the preset position of the camera set, and calling the key position information of the adjacent position sensor for confirming the existence of the suspected moving object;
step 32: selecting an associated first sensor according to the form category of the suspected moving target, and acquiring key data information and alarm information;
step 33: and analyzing the alarm information of the first sensor, and if no history alarm record exists before a preset time period, carrying out the return transmission of the key position information and the key data information to the server, and timely taking corresponding effective measures for processing.
The invention provides an intelligent monitoring system suitable for a coal yard, which comprises:
and an image acquisition module: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
an image processing module: performing enhancement processing on the target frame image to obtain a first frame image;
the target detection module: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
a motion region segmentation module: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
and an alarm module: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of an intelligent monitoring method suitable for a coal yard in an embodiment of the invention;
fig. 2 is a block diagram of an intelligent monitoring system suitable for a coal yard in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which is shown in fig. 1 and comprises the following steps:
step 1: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
step 2: performing enhancement processing on the target frame image to obtain a first frame image;
step 3: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
step 4: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
step 5: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
In the embodiment, the preset position refers to an optimal mounting point for shooting at the coal storage pile inside and outside the room; the target frame image is acquired by a camera.
In this embodiment, the enhancement processing is to improve the image acquisition quality, and improve the contrast and visibility of the moving object in the image, where the moving object includes smoke, fire, and a vehicle; the first frame image is obtained after the target frame image enhancement processing.
In this embodiment, the moving object detection refers to extracting a moving object such as displacement, deformation, etc. from a background on the premise that the camera is not understood; the detection image is an image for detecting a moving object of the first frame image and is mainly used for subsequently dividing a suspected moving area by using morphological operation, wherein the morphological operation mainly comprises two operation methods of expansion and corrosion.
In this embodiment, the suspected moving region refers to a region highly similar to the feature information of a suspected moving object, where the suspected moving object is a moving object to be detected; the sensor comprises a position sensor, a temperature sensor, a gas sensor and the like, and can select a related sensor according to the type of a suspected moving target, analyze alarm information of the sensor and upload detection information.
In the embodiment, the alarm information comprises an alarm time record and an alarm source; different sensors have different detection information, for example, the detection information of the position sensor comprises position coordinate information; the detection information of the gas sensor comprises a gas name and a gas concentration, and the detection information of the temperature sensor comprises a current temperature.
The beneficial effects of the technical scheme are as follows: image quality is improved by preprocessing an image acquired with a camera; detecting a moving target and dividing the region of the improved image to obtain a suspected moving region; and detecting whether a motion target exists in the suspected motion area, and making a relevant response by combining detection information of the sensor, so that intelligent monitoring is effectively realized, and the safety early warning capability of a coal yard is improved.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which is used for enhancing and processing a target frame image to obtain a first frame image and comprises the following steps:
step 11: converting the target frame image from RGB to YUV format;
step 12: performing enhancement processing on the Y component of the target frame image in the YUV format by using weighting, and performing self-adaptive correction on the U, V component;
step 13: and converting the target frame image in the YUV format after the components are adjusted into an RGB space to obtain a first frame image.
In this embodiment, the Y component refers to a luminance component in the YUV color space, and weighting is performed so as to emphasize the relative importance of the Y component to thereby realize enhancement processing of the Y component; the U, V component then represents the chrominance component of the image; the adaptive correction is to ensure that the Y-component enhanced image is not distorted.
The beneficial effects of the technical scheme are as follows: the Y component of the target frame image in the YUV space is enhanced, the U, V component is adaptively corrected and converted into the RGB space, so that a first frame image is obtained, the chromaticity of the target frame image is reserved, the contrast and the visibility of a moving target in the image are improved, and the detection of the subsequent moving target is facilitated.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which utilizes video continuity to detect a moving target of a first frame image to obtain a detection image, and comprises the following steps:
J i (x,y)＝D i (x,y)-B i (x,y)
wherein J is i (x, y) is expressed as a detection image; d (D) i (x, y) being represented as the current ith first frame image; b (B) i (x, y) is represented as a background image;
analysis detection image J i (x, Y) mean and variance of the corresponding histogram to obtain a threshold Y;
if the gray value of the detection image is larger than Y, determining that the detection image is a motion foreground image;
otherwise, it is defined as a background image.
In this embodiment, the histogram reflects the gray distribution rule in the image, and the quality of the image can be inferred from the form of the histogram.
In this embodiment, the threshold Y is not greater than 35.
In this embodiment, for example, there is a detection image a having a gray value of 55, which is greater than the threshold value Y, so the detection image a is determined to be a motion foreground image.
The beneficial effects of the technical scheme are as follows: and detecting the moving target by the first frame of image to obtain a detection image, and laying a foundation for the subsequent segmentation of the suspected moving region, thereby realizing the effective detection of the moving target.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which is used for analyzing a detection image and obtaining a suspected motion area image by morphological operation segmentation, and comprises the following steps:
step 21: carrying out corrosion and re-expansion on the detection image, and combining with connected domain analysis processing to obtain a first image;
step 22: acquiring target characteristic information of different moving targets to be detected;
step 23: according to the obtained target characteristic information, target pixel points are screened from the first image and reserved;
step 24: and collecting the target pixel points to obtain a suspected motion area.
In this embodiment, erosion is used to shrink the image boundaries, eliminating small, meaningless objects; the expansion serves to fill some of the voids within the target region and to eliminate small particle noise contained in the target region; the connected domain analysis refers to searching for adjacent pixels with the same pixel value in the image and marking; the target feature information includes shape, appearance and texture information.
In this embodiment, the suspected motion region is composed of target pixels, wherein the target pixels are screened and retained from the first image based on the target feature information.
The beneficial effects of the technical scheme are as follows: obtaining a first image by carrying out morphological operation and connected domain analysis on the detection image; and screening target pixel points in the first image and reserving the target pixel points based on the target characteristic information to accurately obtain a suspected motion area, so as to lay a foundation for subsequent motion target detection.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which screens and reserves target pixel points from a first image according to obtained target characteristic information, and comprises the following steps:
based on different target characteristic information, acquiring an important value of each first pixel point in the first image, and collecting according to different moving targets to obtain a plurality of first sets D= { D cj J=1, 2,3,..n }, where d cj The important value is expressed as a j-th first pixel point aiming at a c-th moving object, and n represents the total number of the first pixel points corresponding to the c-th moving object;
wherein N is 1j The first pixel point denoted as j is based on the maximum value in the R, G, B channel; n (N) 2j The first pixel point denoted as j is based on the minimum value in the R, G, B channel; n (N) 3j The first pixel point denoted as j is based on the average value of R, G, B channels; Δ1 is expressed as corresponding to the first pixel pointBased on the influence coefficient of the difference value between the maximum value and the minimum value in the R, G, B channel on the important value of the first pixel point; Δ2 is an influence coefficient of the average value of R, G, B channels on the importance value of the first pixel point corresponding to the first pixel point; p (P) c A target feature value expressed as a class c moving target; Δ3 is expressed as a contrast coefficient corresponding to the importance value of the first pixel point matched by the target feature value pair, and Δ3>Δ2>Δ1；
A loss factor expressed as a calculated first pixel point importance value;
determining the duty ratio results of the important values larger than a preset threshold value in all the first sets D;
selecting a first set with the duty ratio result larger than a preset duty ratio threshold as a target set according to the obtained duty ratio result;
and extracting and reserving all pixel points corresponding to the important values larger than a preset threshold value in the target set from the first image.
In this embodiment, the range of the important value of the first pixel point is (0, 1), and the preset threshold is set in advance, typically 0.6.
In this embodiment, for example, there are first sets D1, D2, and D3, and the corresponding significant value duty ratio results greater than the preset threshold are 55%, 60%, and 89%, respectively, and according to the preset duty ratio threshold being 70%, the first set D3 is used as the target set, and the pixel points corresponding to the significant value greater than the preset threshold in the first set are extracted and reserved as the target pixel points.
The beneficial effects of the technical scheme are as follows: acquiring important values of each first pixel point in different first images based on different target characteristic information, and collecting according to different moving targets to obtain a first set; analyzing the important value duty ratio result of the first set, screening the important value duty ratio result to obtain a target set, and reserving all pixel points corresponding to the important values larger than a preset threshold in the target set to effectively obtain a suspected motion area.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which is used for detecting a suspected moving area, effectively responding according to the alarm condition and detection information of a corresponding sensor if the suspected moving object exists, updating a background image if the suspected moving object does not exist, and re-detecting whether the moving object exists or not, and comprises the following steps:
calculating a gradient of each pixel in the suspected motion region;
dividing the suspected motion area into image blocks with preset sizes;
defining the image block as a window, comparing the gray value magnitude relation of the central pixel point and the surrounding pixel points of the window,
if the surrounding pixel values are all larger than the central pixel value, marking the position of the pixel point as 1, otherwise marking the position as 0, and sequentially arranging generated binary numbers to obtain binary numbers in the window;
converting the obtained binary digits into decimal digits, and taking the decimal digits as a first characteristic value of the central pixel point of the window;
determining the occurrence frequency of each first characteristic value, and carrying out normalization processing to obtain a statistical histogram;
connecting the obtained statistical histograms of each window to obtain a first feature vector;
counting a gradient histogram of each image block;
forming a communication interval by the preset number of image blocks, and normalizing the gradient histograms corresponding to the image blocks to obtain intra-interval gradient histograms;
collecting all the obtained intra-interval gradient histograms to obtain a second feature vector;
comparing the key feature information reflected by the first feature vector and the second feature vector with the target feature information of the suspected moving target to obtain a similarity result;
if the similarity result is larger than a preset comparison threshold, determining that a suspected moving object exists in the suspected moving area, calling relevant detection information of a corresponding sensor to carry out data feedback at the moment, and starting an alarm action;
otherwise, updating the background image, and extracting the motion foreground according to the corresponding detection image to re-detect whether the motion target exists.
In this embodiment, the gradient refers to a vector, including magnitude and direction, and the gradient of each pixel is calculated mainly to capture contour information and mitigate interference of illumination.
In this embodiment, for example, the gray value of the center pixel of the window B1 is 80, the gray values corresponding to the neighboring pixels B1, B2, and B3 are 87, 92, and 50, respectively, and the position marks corresponding to the pixels B1, B2, and B3 are 1, and 0, respectively.
In this embodiment, the first feature value may be used to reflect texture information of the corresponding window; the statistical histogram may represent local texture features for each window; the first feature vector is a texture feature vector of the whole suspected motion area and is obtained by connecting all the statistical histograms.
In this embodiment, the gradient histogram may represent local contour features of the respective image block; the communication interval consists of a preset number of image blocks; the intra-interval gradient histogram is obtained by the normalization processing of the gradient histogram corresponding to the image block, wherein the normalization processing is used for reducing the intensity variation range of the gradient and further compressing illumination, shadow and edges.
In this embodiment, the second feature vector refers to the shape and appearance features of the entire suspected motion region; the key feature information includes texture feature information, appearance information, and shape information of the suspected motion region.
In this embodiment, the preset contrast threshold value is typically 0.85.
In this embodiment, the sensor includes a position sensor, a temperature sensor, a gas sensor, and the like.
The beneficial effects of the technical scheme are as follows: extracting features of the suspected motion area to obtain key feature information; and judging whether a suspected moving object exists in the suspected moving area by comparing the similarity between the key feature information and the target feature information, eliminating the interference of other similar objects, and effectively improving the accuracy of detecting the moving object, thereby ensuring intelligent accurate monitoring.
The embodiment of the invention provides an intelligent monitoring method suitable for a coal yard, which is used for effectively responding according to the alarm condition and detection information of a corresponding sensor and comprises the following steps:
step 31: after determining that the suspected moving object exists in the suspected moving area, calling key position information of the suspected moving object confirmed by the adjacent position sensor in combination with the preset position of the camera;
step 32: selecting an associated first sensor according to the form category of the suspected moving target, and acquiring key data information and alarm information;
step 33: and analyzing the alarm information of the first sensor, and if no history alarm record exists before a preset time period, carrying out the return transmission of the key position information and the key data information to the server, and timely taking corresponding effective measures for processing.
In this embodiment, the position sensor is used to determine the displacement and position of the moving object; the key position information is mainly composed of longitude and latitude coordinate information.
In this embodiment, the morphology type of the suspected moving object mainly refers to a solid, solid-liquid mixture; the key data information is related to the sensor, for example, the key data information corresponding to the gas sensor comprises the name and the concentration of the gas possibly generated by the motion of the suspected moving object, and the key data information corresponding to the temperature sensor comprises the current temperature possibly generated by the motion of the suspected moving object and the temperature change trend; the alarm information comprises an alarm time record and an alarm source; the preset time period is set in advance, and is generally 30s.
The beneficial effects of the technical scheme are as follows: selecting an associated first sensor based on the suspected moving object; whether the first sensor has a history alarm record or not is analyzed to determine whether data return is carried out or not, so that effective measures are timely taken to solve potential safety hazards, intelligent monitoring is effectively realized, and the safety early warning capability of a coal yard is improved.
An embodiment of the present invention provides an intelligent monitoring system suitable for a coal yard, as shown in fig. 2, including:
and an image acquisition module: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
an image processing module: performing enhancement processing on the target frame image to obtain a first frame image;
the target detection module: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
a motion region segmentation module: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
and an alarm module: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
The beneficial effects of the technical scheme are as follows: image quality is improved by preprocessing an image acquired with a camera; detecting a moving target and dividing the region of the improved image to obtain a suspected moving region; and detecting whether a motion target exists in the suspected motion area, and making a relevant response by combining detection information of the sensor, so that intelligent monitoring is effectively realized, and the safety early warning capability of a coal yard is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. An intelligent monitoring method suitable for a coal yard is characterized by comprising the following steps:
step 1: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
step 2: performing enhancement processing on the target frame image to obtain a first frame image;
step 3: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
step 4: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
step 5: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
2. The intelligent monitoring method for coal yards according to claim 1, wherein the preset position is an optimal mounting point for shooting at an indoor and outdoor coal storage pile.
3. The intelligent monitoring method for coal yards according to claim 1, wherein the target frame image enhancement processing is performed to obtain a first frame image, comprising:
step 11: converting the target frame image from RGB to YUV format;
step 12: performing enhancement processing on the Y component of the target frame image in the YUV format by using weighting, and performing self-adaptive correction on the U, V component;
step 13: and converting the target frame image in the YUV format after the components are adjusted into an RGB space to obtain a first frame image.
4. The intelligent monitoring method for coal yards according to claim 1, wherein the moving object detection is performed on the first frame image by utilizing video continuity to obtain a detection image, and the method comprises the following steps:
J i (x,y)＝ i (x,y)- i (x,y)
wherein J is i (x, y) is expressed as a detection image; d (D) i (x, y) being represented as the current ith first frame image; b (B) i (x, y) is represented as a background image;
analysis detection image J i (x, Y) mean and variance of the corresponding histogram to obtain a threshold Y;
if the gray value of the detection image is larger than Y, determining that the detection image is a motion foreground image;
otherwise, it is defined as a background image.
5. The intelligent monitoring method for coal yards according to claim 1, wherein analyzing the detection image and dividing the detection image by morphological operation to obtain a suspected motion area image comprises the following steps:
step 21: carrying out corrosion and re-expansion on the detection image, and combining with connected domain analysis processing to obtain a first image;
step 22: acquiring target characteristic information of different moving targets to be detected;
step 23: according to the obtained target characteristic information, target pixel points are screened from the first image and reserved;
step 24: and collecting the target pixel points to obtain a suspected motion area.
6. The intelligent monitoring method for coal yards according to claim 5, wherein the steps of screening and retaining target pixels from the first image according to the obtained target characteristic information include:
based on different target characteristic information, acquiring an important value of each first pixel point in the first image, and collecting according to different moving targets to obtain a plurality of first sets D= { D cj J=1, 2,3,..n }, where d cj The important value is expressed as a j-th first pixel point aiming at a c-th moving object, and n represents the total number of the first pixel points corresponding to the c-th moving object;
wherein N is 1j The first pixel point denoted as j is based on the maximum value in the R, G, B channel; n (N) 2j Denoted as j-thThe first pixel is based on a minimum value in the R, G, B channel; n (N) 3j The first pixel point denoted as j is based on the average value of R, G, B channels; Δ1 is expressed as an influence coefficient of the corresponding first pixel point on the important value of the first pixel point based on the difference value between the maximum value and the minimum value in the R, G, B channel; Δ2 is an influence coefficient of the average value of R, G, B channels on the importance value of the first pixel point corresponding to the first pixel point; p (P) c A target feature value expressed as a class c moving target; Δ3 is expressed as a contrast coefficient corresponding to the importance value of the first pixel point matched by the target feature value pair, and Δ3>Δ2>Δ1；
A loss factor expressed as a calculated first pixel point importance value;
determining the duty ratio results of the important values larger than a preset threshold value in all the first sets D;
selecting a first set with the duty ratio result larger than a preset duty ratio threshold as a target set according to the obtained duty ratio result;
and extracting pixel points corresponding to all important values larger than a preset threshold value in the target set from the first image, and reserving the pixel points as suspected motion areas.
7. The intelligent monitoring method for coal yards according to claim 1, wherein detecting the suspected moving area, if a suspected moving object exists, effectively responding according to the alarm condition and detection information of the corresponding sensor, if no suspected moving object exists, updating the background image, and re-detecting whether the moving object exists, comprises:
calculating a gradient of each pixel in the suspected motion region;
dividing the suspected motion area into image blocks with preset sizes;
defining the image block as a window, comparing the gray value magnitude relation of the central pixel point and the surrounding pixel points of the window,
if the surrounding pixel values are all larger than the central pixel value, marking the position of the pixel point as 1, otherwise marking the position as 0, and sequentially arranging generated binary numbers to obtain binary numbers in the window;
converting the obtained binary digits into decimal digits, and taking the decimal digits as a first characteristic value of the central pixel point of the window;
determining the occurrence frequency of each first characteristic value, and carrying out normalization processing to obtain a statistical histogram;
connecting the obtained statistical histograms of each window to obtain a first feature vector;
counting a gradient histogram of each image block;
forming a communication interval by the preset number of image blocks, and normalizing the corresponding gradient histograms to obtain intra-interval gradient histograms;
collecting all the obtained intra-interval gradient histograms to obtain a second feature vector;
comparing the key feature information reflected by the first feature vector and the second feature vector with the target feature information of the suspected moving target to obtain a similarity result;
if the similarity result is larger than a preset comparison threshold, determining that a suspected moving object exists in the suspected moving area, calling relevant detection information of a corresponding sensor to carry out data feedback at the moment, and starting an alarm action;
otherwise, updating the background image, and extracting the motion foreground according to the corresponding detection image to re-detect whether the motion target exists.
8. The intelligent monitoring method for coal yards of claim 7, wherein the effective response according to the alarm condition and detection information of the corresponding sensor comprises:
step 31: after determining that the suspected moving object exists in the suspected moving area, combining the preset position of the camera set, and calling the key position information of the adjacent position sensor for confirming the existence of the suspected moving object;
step 32: selecting an associated first sensor according to the form category of the suspected moving target, and acquiring key data information and alarm information;
step 33: and analyzing the alarm information of the first sensor, and if no history alarm record exists before a preset time period, carrying out the return transmission of the key position information and the key data information to the server, and timely taking corresponding effective measures for processing.
9. An intelligent monitoring system suitable for coal yards, comprising:
and an image acquisition module: acquiring video images by using a high-definition camera installed at a preset position to obtain target frame images;
an image processing module: performing enhancement processing on the target frame image to obtain a first frame image;
the target detection module: detecting a moving target of the first frame image by utilizing video continuity to obtain a detection image;
a motion region segmentation module: analyzing the detection image, and dividing the detection image by morphological operation to obtain a suspected motion area image;
and an alarm module: and detecting the suspected moving area, calling detection information of a corresponding sensor if a suspected moving object exists, sending out the detection information together with alarm information, updating a background image if the suspected moving object does not exist, and detecting whether the moving object exists again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310111512.4A CN116342644A (en) | 2023-02-13 | 2023-02-13 | Intelligent monitoring method and system suitable for coal yard |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310111512.4A CN116342644A (en) | 2023-02-13 | 2023-02-13 | Intelligent monitoring method and system suitable for coal yard |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116342644A true CN116342644A (en) | 2023-06-27 |
Family
ID=86888427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310111512.4A Pending CN116342644A (en) | 2023-02-13 | 2023-02-13 | Intelligent monitoring method and system suitable for coal yard |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342644A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079219A (en) * | 2023-10-08 | 2023-11-17 | 山东车拖车网络科技有限公司 | Vehicle running condition monitoring method and device applied to trailer service |
-
2023
- 2023-02-13 CN CN202310111512.4A patent/CN116342644A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079219A (en) * | 2023-10-08 | 2023-11-17 | 山东车拖车网络科技有限公司 | Vehicle running condition monitoring method and device applied to trailer service |
| CN117079219B (en) * | 2023-10-08 | 2024-01-09 | 山东车拖车网络科技有限公司 | Vehicle running condition monitoring method and device applied to trailer service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018130016A1 (en) | Parking detection method and device based on monitoring video | |
| CN107085714B (en) | Forest fire detection method based on video | |
| CN111401284B (en) | Door opening and closing state identification method based on image processing | |
| CN110428450B (en) | Scale-adaptive target tracking method applied to mine tunnel mobile inspection image | |
| TWI382360B (en) | Object detection method and device threrof | |
| CN102799862A (en) | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image | |
| CN111462155B (en) | Motion detection method, device, computer equipment and storage medium | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN111611907A (en) | Image-enhanced infrared target detection method | |
| CN115170567B (en) | Method for detecting defects of waterproof steel plate for ship | |
| CN110610485A (en) | Ultra-high voltage transmission line channel hidden danger early warning method based on SSIM algorithm | |
| CN116342644A (en) | Intelligent monitoring method and system suitable for coal yard | |
| JP2006039689A (en) | Image processor, image processing method, image processing program, and recording medium with the program recorded thereon | |
| CN111985314B (en) | Smoke detection method based on ViBe and improved LBP | |
| CN111460964A (en) | Moving target detection method under low-illumination condition of radio and television transmission machine room | |
| CN116137022B (en) | Data enhancement method for underground mining remote monitoring | |
| CN113096103A (en) | Intelligent smoke image sensing method for emptying torch | |
| CN112560574A (en) | River black water discharge detection method and recognition system applying same | |
| CN115797775B (en) | Intelligent illegal building identification method and system based on near-to-ground video image | |
| CN109658405B (en) | Image data quality control method and system in crop live-action observation | |
| CN116703755A (en) | Omission risk monitoring system for medical waste refrigeration house | |
| CN111145219B (en) | Efficient video moving target detection method based on Codebook principle | |
| CN109118546A (en) | A kind of depth of field hierarchical estimation method based on single-frame images | |
| CN111402189B (en) | Video image color cast detection device and method | |
| CN112801963A (en) | Video image occlusion detection method and system |
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 |