CN110862033A - Intelligent early warning detection method applied to coal mine inclined shaft winch - Google Patents
Intelligent early warning detection method applied to coal mine inclined shaft winch Download PDFInfo
- Publication number
- CN110862033A CN110862033A CN201911100474.2A CN201911100474A CN110862033A CN 110862033 A CN110862033 A CN 110862033A CN 201911100474 A CN201911100474 A CN 201911100474A CN 110862033 A CN110862033 A CN 110862033A
- Authority
- CN
- China
- Prior art keywords
- detection
- winch
- point cloud
- track
- cloud data
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 239000003245 coal Substances 0.000 title claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 45
- 230000004927 fusion Effects 0.000 claims abstract description 13
- 238000007500 overflow downdraw method Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 230000004888 barrier function Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 230000036760 body temperature Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000001931 thermography Methods 0.000 claims description 3
- 235000002566 Capsicum Nutrition 0.000 claims description 2
- 102000002274 Matrix Metalloproteinases Human genes 0.000 claims description 2
- 108010000684 Matrix Metalloproteinases Proteins 0.000 claims description 2
- 239000006002 Pepper Substances 0.000 claims description 2
- 235000016761 Piper aduncum Nutrition 0.000 claims description 2
- 235000017804 Piper guineense Nutrition 0.000 claims description 2
- 244000203593 Piper nigrum Species 0.000 claims description 2
- 235000008184 Piper nigrum Nutrition 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000013136 deep learning model Methods 0.000 claims description 2
- 150000003839 salts Chemical class 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66D—CAPSTANS; WINCHES; TACKLES, e.g. PULLEY BLOCKS; HOISTS
- B66D1/00—Rope, cable, or chain winding mechanisms; Capstans
- B66D1/54—Safety gear
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Abstract
The invention relates to an intelligent early warning detection method applied to a coal mine inclined shaft winch. The three-dimensional point cloud data processing algorithm is used for acquiring three-dimensional point cloud data of scenes in inclined shaft tunnels through a multi-line laser sensor and realizing the detection of obstacles in front of the operation of the winch. The visible light image processing algorithm is used for detecting the personnel in the roadway, the winch running track and the obstacles by utilizing the collected visible light images. The infrared image processing algorithm is to utilize an infrared camera to acquire an infrared image in front of the running winch so as to realize personnel detection in the roadway. The multi-sensor data information fusion method realizes the fusion of the data acquired by the three sensors and the detection result, and realizes the safety early warning.
Description
Technical Field
The invention belongs to the field of coal mine safety, and particularly relates to an intelligent early warning detection method applied to a coal mine inclined shaft winch.
Background
In the lifting process of the conventional inclined shaft roadway winch, a winch driver can only indirectly detect the field safety through a protection signal of the winch, cannot intuitively master the field real-time information, and causes the problem of blind area driving to some extent, especially in the complex transportation environment with long distance, multiple variable slopes and large inclination angles, the winch is easy to cause safety accidents, such as the fact that the tramcar falls off the way due to obstacles such as wood blocks, stones and the like on a track.
Disclosure of Invention
The invention adopts three detection means of a three-dimensional point cloud processing algorithm, a visible light image processing algorithm and an infrared image processing algorithm, and utilizes a multi-sensor fusion technology to fuse three detection results, detect personnel intrusion and barriers on a track in real time, alarm in time when an abnormality is found, prompt a winch driver to pay attention to the abnormal condition occurring in a transportation field, ensure the safe and stable operation of the inclined shaft roadway winch lifting system, avoid the blind driving and prevent the accident.
In order to achieve the purpose, the invention adopts the following technical scheme:
a detection method applied to intelligent early warning of a coal mine inclined shaft winch comprises a three-dimensional point cloud data processing algorithm, a visible light image processing algorithm and an infrared image processing algorithm, and fusion of detection results of obstacles, personnel and the like is achieved by utilizing a multi-sensor data information fusion method.
The three-dimensional point cloud data processing algorithm is used for acquiring three-dimensional point cloud data of a scene in an inclined shaft roadway by using the multi-line laser sensor, realizing the detection of an obstacle in front of the running of the winch, acquiring information such as the distance and the size of the obstacle, and assisting an infrared camera and a visible light camera to detect personnel and foreign matters. The visible light image processing algorithm utilizes a visible light camera to collect a visible light image in front of the operation of the winch, so that the detection of personnel in a roadway, the detection of a winch operation track and the detection of obstacles on the track and obstacles in the middle of the track are realized. The infrared image processing algorithm utilizes an infrared camera to acquire an infrared image in front of the winch in operation, and realizes personnel detection in the roadway through thermal imaging of human body temperature. The multi-sensor data information fusion method realizes the fusion of the data acquired by the three sensors and the detection result, and three paths of signal data supplement each other, so that the detection is more accurate; and the detected emergency conditions such as obstacles, personnel and the like are alarmed, so that the intelligent early warning of factors influencing the safe operation of the winch is realized.
Compared with the existing method for indirectly detecting the field safety of a winch driver through the self protection signal of the winch, the method has the following beneficial effects:
1. the three-dimensional point cloud processing and the infrared image processing are not influenced by light change, and personnel detection can still be carried out in an inclined shaft roadway with poor illumination, so that the driving safety is effectively guaranteed;
2. the obstacle real-time detection function adopts a three-dimensional point cloud processing algorithm to detect obstacles, can detect information such as distance, size and the like of the obstacles, and can give an alarm in time when the obstacles are found;
3. the barrier identification function is used for automatically identifying people and foreign body types in a trip and automatically giving an alarm by analyzing the infrared image and the visible light image and combining barrier data detected by the multi-line laser;
4. by adopting a multi-sensor information fusion technology and adopting various detection strategies, the detection result is more accurate and the robustness is stronger.
Drawings
FIG. 1 is a schematic of the overall algorithm of the present invention;
FIG. 2 is a flow chart of an obstacle detection algorithm for a multi-line laser sensor of the present invention;
FIG. 3 is a flow chart of a ground point and obstacle point separation algorithm in the three-dimensional point cloud data processing algorithm of the present invention;
FIG. 4 is a flow chart of the visible light camera detection algorithm of the present invention;
FIG. 5 is a flow chart of the target detection and recognition of the visible light camera of the present invention;
FIG. 6 is a flow chart of an infrared camera people detection algorithm of the present invention;
fig. 7 is a schematic diagram of the inventive multisensor fusion.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
as shown in fig. 1, the intelligent early warning detection method applied to the coal mine inclined shaft winch comprises a three-dimensional point cloud data processing algorithm, a visible light image processing algorithm and an infrared image processing algorithm, and realizes the detection of obstacles and personnel by using a multi-sensor data information fusion method.
The three-dimensional point cloud data processing algorithm is used for acquiring three-dimensional point cloud data of a scene in an inclined shaft roadway by using a multi-line laser sensor, realizing the detection of an obstacle in front of the operation of a winch, acquiring information such as the distance and the size of the obstacle, and assisting an infrared camera and a visible light camera to detect personnel and foreign matters; the visible light image processing algorithm is characterized in that a visible light camera is used for collecting visible light images in front of the operation of the winch, so that the detection of personnel in a roadway, the detection of a winch operation track and the detection of obstacles on the track and obstacles in the middle of the track are realized; the infrared image processing algorithm is used for acquiring an infrared image in front of the winch in operation by using an infrared camera and realizing personnel detection in the roadway through thermal imaging of human body temperature; the multi-sensor data information fusion method fuses data acquired by three sensors and detection results, and three paths of signal data supplement each other, so that the detection is more accurate; and the detected emergency conditions such as obstacles, personnel and the like are alarmed, so that the intelligent early warning of factors influencing the safe operation of the winch is realized.
As shown in fig. 2, the three-dimensional point cloud data processing algorithm is used for detecting an obstacle in front of the winch in operation and acquiring information such as the distance and the size of the obstacle, and includes the following steps:
step 11: the method comprises the steps that a multi-line laser sensor collects original point cloud data of an inclined shaft tunnel in front of a winch in real time, sampling and filtering are conducted on the point cloud data, and sparse point cloud data are obtained;
step 12: carrying out ground point and obstacle point separation on the sparse point cloud data to obtain ground point cloud data and obstacle point cloud data;
step 13: clustering obstacle point cloud data to obtain distance information and size information of each obstacle;
step 14: carrying out line splitting operation on the original point cloud data to obtain laser point cloud data obtained by scanning each laser line, and detecting a track data point according to the height difference between a track driven by a winch and the ground for the point cloud data of each laser line;
step 15: based on orbital data points
Of axis coordinate values and obstacles
And (4) determining the coordinate value of the axis, judging whether the obstacle influences the forward running of the winch, and outputting an alarm result if the obstacle influences the forward running of the winch.
In step 12, the ground point is separated from the obstacle point, and a processing algorithm combining a grid height difference method and a ray angle difference method is adopted, as shown in fig. 3, the method includes the following steps:
step 121: carrying out chessboard grid division on the sparse point cloud data, and calculating the height difference of the point cloud data in each gridH diff If, ifH diff Less than a height difference threshold
All points in the grid are considered as ground points, and after each grid is calculated, a rough ground point set is obtained
；
Step 122: set of ground points
Fitting the point cloud data in a plane model by using a random sampling consistency algorithm
According to model parameters
，
，
Obtaining a normal vector of a plane
；
Step 123: calibrating point cloud data, i.e. by normal vector
Rotate to
Axial vector
According to the formula
Namely:
step 124: and (4) accurately separating ground points and obstacle points from the calibrated point cloud data by adopting a ray angle difference method. First, calculate each point and the front of the winch
Plane included angle of positive direction
(ii) a Then, scanning is carried out once every 0.178 degrees according to the characteristics of the multi-line laser sensor, the front 180 degrees of the winch is differentiated and divided into 1008 parts, and the angle occupied by each part interval is 0.178 degrees, and each point is divided into 1008 parts
Dividing the micro-partition into corresponding micro-partitions respectively, so that a point in each micro-partition can be approximately regarded as a ray; secondly, the distance from each point to the multi-line laser sensor is calculated
According to distance
Sorting each point in each micro-segment from near to far; finally, the vertical angle difference between two points in each differential is calculated in turn, if the angle threshold is exceededTh theat And if not, the point is considered as a ground point.
As shown in fig. 4, the visible light image processing algorithm is used for detecting a foreign object and assisting an infrared image to detect a pedestrian, and specifically includes the following steps:
step 21: collecting visible light image data; receiving visible light image signal data collected by a visible light camera;
step 22: preprocessing an image; firstly, denoising an image by adopting a Gaussian filter; secondly, performing image enhancement processing by adopting a histogram equalization algorithm, and solving the problem of low image brightness caused by weak light in an inclined shaft roadway;
step 23: detecting and identifying a target; the detection of unsafe factors influencing the normal operation of the winch, such as winch operation track detection, obstacle detection on the track, obstacle detection in the middle of the track, personnel detection and the like, is realized by adopting a technology combining an image processing algorithm and a deep learning algorithm;
step 24: outputting an alarm result; and determining an alarm area according to the position of the track, and selectively giving an alarm according to the position relation between the obstacle and the alarm area.
In step 23, the target detection and identification, referring to fig. 5, includes winch operation track detection, obstacle detection on the track, obstacle detection in the middle of the track, and personnel detection;
(1) the track detection is to perform straight line detection on the image by using Hough transform, screen the detected straight lines according to the position, the slope and the length, and finally fit the straight lines where the two tracks are located;
(2) the detection of the obstacles on the track is carried out by utilizing the technology of combining an image processing algorithm and a deep learning algorithm: on one hand, detecting the blob areas in the image, screening out the blob areas crossed with the straight line of the track, carrying out secondary screening on the screened blob areas through angles and areas, and storing the screening result as the barrier on the track; on the other hand, a pre-trained deep learning model is adopted for detection, and the detected result is stored as a rail obstacle; finally, overlapping the detection results at the two sides, and removing the repeatedly detected obstacles;
(3) the middle obstacle detection of the track comprises the steps of firstly, dividing the middle area of the track into a plurality of sections from top to bottom
Each part calculates the histogram of every two adjacent regions
、
By means of correlation comparison, using
Wherein:
comparing histograms of the two adjacent regions, and screening out a region with large difference of histogram comparison results as a candidate region of the obstacle; secondly, detecting the longitudinal position of the obstacle in the candidate area through the gradient change in the horizontal direction; finally, deep learning algorithm is adoptedAnd detecting a carrier roller positioned in the middle of the winch track, and rejecting a target overlapped with the carrier roller position in the barrier according to the position of the carrier roller.
(4) And the personnel detection adopts a deep learning detection algorithm and detects whether personnel exist in front of the operation of the winch or not through a pre-trained detection model.
As shown in fig. 6, the infrared image detection algorithm for realizing personnel detection specifically includes the following steps:
step 31: acquiring infrared image data; receiving infrared image signal data collected by an infrared camera;
step 32: preprocessing an image; firstly, denoising an image by adopting median filtering, and filtering salt and pepper noise generated in the image acquisition process; secondly, performing image enhancement processing by adopting linear gray scale conversion to improve the contrast of the image and enhance the contrast of a personnel area;
step 33: detecting personnel; adopting a deep learning technology, and utilizing a convolutional neural network and a pre-trained network model to detect and identify people;
step 34: confirming the detection result; comparing the temperature value of the personnel area detected in the step 33 with the normal human body temperature value, and confirming the detection result.
As shown in fig. 7, the multi-sensor information fusion technique is used for implementing information fusion between three detection results of three-dimensional point cloud processing, visible light image processing, and infrared image processing, and the implementation process includes the following steps:
step 41: calibrating the sensors for collecting three data in pairs, specifically, calibrating the sensors by using a conventional calibration method of a known calibration object to obtain an internal reference matrix between each group of sensors
External reference matrix
Wherein, in the step (A),
is a rotation matrix of a three-dimensional space,
is a translation vector in three-dimensional space;
step 42: the method comprises the following steps of calibrating and acquiring an internal parameter matrix and an external parameter matrix between each group of sensors by using the sensors, finishing data alignment acquired by different sensors, and realizing data information fusion;
step 43: and outputting a comprehensive detection result according to the detection result of the fused data information and the independent detection result of each sensor, so as to realize the fusion of the decision-making layer information.
Claims (5)
1. An intelligent early warning detection method applied to a coal mine inclined shaft winch is characterized by comprising the following steps: the monitoring method comprises a three-dimensional point cloud data processing algorithm, a visible light image processing algorithm and an infrared image processing algorithm, and realizes the detection of obstacles and personnel by utilizing a multi-sensor data information fusion method; the three-dimensional point cloud data processing algorithm is used for acquiring three-dimensional point cloud data of a scene in an inclined shaft roadway by using a multi-line laser sensor, realizing the detection of an obstacle in front of the operation of a winch, acquiring information such as the distance and the size of the obstacle, and assisting an infrared camera and a visible light camera to detect personnel and foreign matters; the visible light image processing algorithm is characterized in that a visible light camera is used for collecting visible light images in front of the operation of the winch, so that the detection of personnel in a roadway, the detection of a winch operation track and the detection of obstacles on the track and obstacles in the middle of the track are realized; the infrared image processing algorithm is used for acquiring an infrared image in front of the winch in operation by using an infrared camera and realizing personnel detection in the roadway through thermal imaging of human body temperature; the multi-sensor data information fusion method fuses data acquired by three sensors and detection results, and three paths of signal data supplement each other, so that the detection is more accurate; and the detected emergency conditions such as obstacles, personnel and the like are alarmed, so that the intelligent early warning of factors influencing the safe operation of the winch is realized.
2. The intelligent early warning detection method applied to the coal mine inclined shaft winch according to claim 1, characterized in that: the three-dimensional point cloud data processing algorithm comprises the following steps:
step 11: the method comprises the steps that a multi-line laser sensor collects original point cloud data of an inclined shaft tunnel in front of a winch in real time, sampling and filtering are conducted on the point cloud data, and sparse point cloud data are obtained;
step 12: carrying out ground point and obstacle point separation on the sparse point cloud data to obtain ground point cloud data and obstacle point cloud data;
step 13: clustering obstacle point cloud data to obtain distance information and size information of each obstacle;
step 14: carrying out line splitting operation on the original point cloud data to obtain laser point cloud data obtained by scanning each laser line, and detecting a track data point according to the height difference between a track driven by a winch and the ground for the point cloud data of each laser line;
step 15: based on orbital data points
Of axis coordinate values and obstacles
The axial coordinate value is used for judging whether the obstacle influences the forward running of the winch or not, and if so, outputting an alarm result;
in the step 12, the ground point is separated from the obstacle point, and a processing algorithm combining a grid height difference method and a ray angle difference method is adopted, and the method specifically includes the following steps:
step 121: carrying out chessboard grid division on the sparse point cloud data, and calculating the height difference H of the point cloud data in each griddiffIf H isdiffLess than a height difference threshold
All points in the grid are considered as ground points, and after each grid is calculated, a rough ground point set is obtained
；
Step 122: set of ground points
Fitting the point cloud data in a plane model by using a random sampling consistency algorithm
According to model parameters
，
，
Obtaining a normal vector of a plane
；
Step 123: calibrating point cloud data, i.e. by normal vector
Rotate to
Axial vector
According to the formula
Namely:
step 124: and (4) accurately separating ground points and obstacle points from the calibrated point cloud data by adopting a ray angle difference method. First, calculate each point and the front of the winch
Plane included angle of positive direction
(ii) a Then, scanning is carried out once every 0.178 degrees according to the characteristics of the multi-line laser sensor, the front 180 degrees of the winch is differentiated and divided into 1008 parts, and the angle occupied by each part interval is 0.178 degrees, and each point is divided into 1008 parts
Dividing the micro-partition into corresponding micro-partitions respectively, so that a point in each micro-partition can be approximately regarded as a ray; secondly, the distance from each point to the multi-line laser sensor is calculated
According to distance
Sorting each point in each micro-segment from near to far; finally, the vertical angle difference between two points in each differential is calculated in turn, if the angle difference exceeds an angle threshold ThtheatAnd if not, the point is considered as a ground point.
3. The intelligent early warning detection method applied to the coal mine inclined shaft winch according to claim 1, characterized in that: the visible light image processing algorithm comprises the following steps:
step 21: collecting visible light image data; receiving visible light image signal data collected by a visible light camera;
step 22: preprocessing an image; firstly, denoising an image by adopting a Gaussian filter; secondly, performing image enhancement processing by adopting a histogram equalization algorithm, and solving the problem of low image brightness caused by weak light in an inclined shaft roadway;
step 23: detecting and identifying a target; the detection of unsafe factors influencing the normal operation of the winch, such as winch operation track detection, obstacle detection on the track, obstacle detection in the middle of the track, personnel detection and the like, is realized by adopting a technology combining an image processing algorithm and a deep learning algorithm;
step 24: outputting an alarm result; determining an alarm area according to the position of the track, and selectively giving an alarm according to the position relation between the obstacle and the alarm area;
in the step 23, the target detection and identification comprises winch operation track detection, obstacle detection on a track, obstacle detection in the middle of the track and personnel detection;
the track detection is to perform straight line detection on the image by using Hough transform, screen the detected straight lines according to the position, the slope and the length, and finally fit the straight lines where the two tracks are located;
the detection of the obstacles on the track is carried out by utilizing the technology of combining an image processing algorithm and a deep learning algorithm: on one hand, detecting the blob areas in the image, screening out the blob areas crossed with the straight line of the track, carrying out secondary screening on the screened blob areas through angles and areas, and storing the screening result as the barrier on the track; on the other hand, a pre-trained deep learning model is adopted for detection, and the detected result is stored as a rail obstacle; finally, overlapping the detection results at the two sides, and removing the repeatedly detected obstacles;
the middle obstacle detection of the track comprises the steps of firstly, dividing the middle area of the track into a plurality of sections from top to bottom
Each part calculates the histogram of every two adjacent regions
、
By means of correlation comparison, using
Wherein:
comparing histograms of the two adjacent regions, and screening out a region with large difference of histogram comparison results as a candidate region of the obstacle; secondly, detecting the longitudinal position of the obstacle in the candidate area through the gradient change in the horizontal direction; finally, detecting a carrier roller in the middle of the winch track by adopting a deep learning algorithm, and removing a target overlapped with the carrier roller in the barrier according to the position of the carrier roller;
and the personnel detection adopts a deep learning detection algorithm and detects whether personnel exist in front of the operation of the winch or not through a pre-trained detection model.
4. The intelligent early warning detection method applied to the coal mine inclined shaft winch according to claim 1, characterized in that: the infrared image detection algorithm comprises the following steps:
step 31: acquiring infrared image data; receiving infrared image signal data collected by an infrared camera;
step 32: preprocessing an image; firstly, denoising an image by adopting median filtering, and filtering salt and pepper noise generated in the image acquisition process; secondly, performing image enhancement processing by adopting linear gray scale conversion to improve the contrast of the image and enhance the contrast of a personnel area;
step 33: detecting personnel; adopting a deep learning technology, and utilizing a convolutional neural network and a pre-trained network model to detect and identify people;
step 34: confirming the detection result; comparing the difference between the temperature value of the personnel area detected in the step 33 and the normal human body temperature value, and confirming the detection result;
5. the intelligent early warning detection method applied to the coal mine inclined shaft winch according to claim 1, characterized in that: the multi-sensor information fusion technology comprises the following steps:
step 41: calibrating the sensors for collecting three data in pairs, specifically, calibrating the sensors by using a conventional calibration method of a known calibration object to obtain an internal reference matrix between each group of sensors
External reference matrix
Wherein, in the step (A),
is a rotation matrix of a three-dimensional space,
is a translation vector in three-dimensional space;
step 42: the method comprises the following steps of calibrating and acquiring an internal parameter matrix and an external parameter matrix between each group of sensors by using the sensors, finishing data alignment acquired by different sensors, and realizing data information fusion;
step 43: and outputting a comprehensive detection result according to the detection result of the fused data information and the independent detection result of each sensor, so as to realize the fusion of the decision-making layer information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100474.2A CN110862033B (en) | 2019-11-12 | 2019-11-12 | Intelligent early warning detection method applied to inclined shaft winch of coal mine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100474.2A CN110862033B (en) | 2019-11-12 | 2019-11-12 | Intelligent early warning detection method applied to inclined shaft winch of coal mine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110862033A true CN110862033A (en) | 2020-03-06 |
| CN110862033B CN110862033B (en) | 2024-03-01 |
Family
ID=69653402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911100474.2A Active CN110862033B (en) | 2019-11-12 | 2019-11-12 | Intelligent early warning detection method applied to inclined shaft winch of coal mine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110862033B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553946A (en) * | 2020-04-17 | 2020-08-18 | 中联重科股份有限公司 | Method and device for removing ground point cloud and obstacle detection method and device |
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN112191353A (en) * | 2020-10-09 | 2021-01-08 | 北京北矿智能科技有限公司 | Device and method for improving safety of operation area of stone crusher |
| CN112348901A (en) * | 2020-11-27 | 2021-02-09 | 苏州感测通信息科技有限公司 | Vehicle-mounted sensor data processing system and method |
| CN112347953A (en) * | 2020-11-11 | 2021-02-09 | 上海伯镭智能科技有限公司 | Recognition device for road condition irregular obstacles of unmanned vehicle |
| CN113420698A (en) * | 2021-06-18 | 2021-09-21 | 北京盈迪曼德科技有限公司 | Robot-based environment identification method and device |
| WO2022183871A1 (en) * | 2021-03-04 | 2022-09-09 | 上海申传电气股份有限公司 | Construction method for dynamic envelope line for electric locomotive for mine railway |
| CN115272425A (en) * | 2022-08-29 | 2022-11-01 | 中铁云网信息科技有限公司 | Railway construction site area intrusion detection method and system based on three-dimensional point cloud |
| CN116189229A (en) * | 2022-11-30 | 2023-05-30 | 中信重工开诚智能装备有限公司 | Personnel tracking method based on coal mine auxiliary transportation robot |
| CN116448188A (en) * | 2023-06-13 | 2023-07-18 | 西安高商智能科技有限责任公司 | Abnormal state monitoring and early warning system for freight winch |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB648183A (en) * | 1948-11-11 | 1951-01-03 | Chapman Ltd A W | Improvements in or relating to slidable seats for vehicles and the like |
| US20050196034A1 (en) * | 1999-09-09 | 2005-09-08 | Kabushiki Kaisha Toshiba | Obstacle detection system and method therefor |
| CN104933708A (en) * | 2015-06-07 | 2015-09-23 | 浙江大学 | Barrier detection method in vegetation environment based on multispectral and 3D feature fusion |
| CN105159292A (en) * | 2015-08-19 | 2015-12-16 | 阜新博远科技有限公司 | Tramcar operating real-time obstacle automatic detection and video feedback system and method |
| CN106096561A (en) * | 2016-06-16 | 2016-11-09 | 重庆邮电大学 | Infrared pedestrian detection method based on image block degree of depth learning characteristic |
| CN109872329A (en) * | 2019-01-28 | 2019-06-11 | 重庆邮电大学 | A kind of ground point cloud fast partition method based on three-dimensional laser radar |
-
2019
- 2019-11-12 CN CN201911100474.2A patent/CN110862033B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB648183A (en) * | 1948-11-11 | 1951-01-03 | Chapman Ltd A W | Improvements in or relating to slidable seats for vehicles and the like |
| US20050196034A1 (en) * | 1999-09-09 | 2005-09-08 | Kabushiki Kaisha Toshiba | Obstacle detection system and method therefor |
| CN104933708A (en) * | 2015-06-07 | 2015-09-23 | 浙江大学 | Barrier detection method in vegetation environment based on multispectral and 3D feature fusion |
| CN105159292A (en) * | 2015-08-19 | 2015-12-16 | 阜新博远科技有限公司 | Tramcar operating real-time obstacle automatic detection and video feedback system and method |
| CN106096561A (en) * | 2016-06-16 | 2016-11-09 | 重庆邮电大学 | Infrared pedestrian detection method based on image block degree of depth learning characteristic |
| CN109872329A (en) * | 2019-01-28 | 2019-06-11 | 重庆邮电大学 | A kind of ground point cloud fast partition method based on three-dimensional laser radar |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553946B (en) * | 2020-04-17 | 2023-04-18 | 中联重科股份有限公司 | Method and device for removing ground point cloud and method and device for detecting obstacle |
| CN111553946A (en) * | 2020-04-17 | 2020-08-18 | 中联重科股份有限公司 | Method and device for removing ground point cloud and obstacle detection method and device |
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN111753741B (en) * | 2020-06-28 | 2024-03-15 | 北京小眼探索科技有限公司 | Special vehicle driving assisting method and device based on deep learning and storage medium |
| CN112191353A (en) * | 2020-10-09 | 2021-01-08 | 北京北矿智能科技有限公司 | Device and method for improving safety of operation area of stone crusher |
| CN112191353B (en) * | 2020-10-09 | 2022-01-28 | 北京北矿智能科技有限公司 | Device and method for improving safety of operation area of stone crusher |
| CN112347953A (en) * | 2020-11-11 | 2021-02-09 | 上海伯镭智能科技有限公司 | Recognition device for road condition irregular obstacles of unmanned vehicle |
| CN112347953B (en) * | 2020-11-11 | 2021-09-28 | 上海伯镭智能科技有限公司 | Recognition device for road condition irregular obstacles of unmanned vehicle |
| CN112348901A (en) * | 2020-11-27 | 2021-02-09 | 苏州感测通信息科技有限公司 | Vehicle-mounted sensor data processing system and method |
| WO2022183871A1 (en) * | 2021-03-04 | 2022-09-09 | 上海申传电气股份有限公司 | Construction method for dynamic envelope line for electric locomotive for mine railway |
| CN113420698A (en) * | 2021-06-18 | 2021-09-21 | 北京盈迪曼德科技有限公司 | Robot-based environment identification method and device |
| CN115272425A (en) * | 2022-08-29 | 2022-11-01 | 中铁云网信息科技有限公司 | Railway construction site area intrusion detection method and system based on three-dimensional point cloud |
| CN115272425B (en) * | 2022-08-29 | 2023-08-15 | 中铁云网信息科技有限公司 | Railway site area intrusion detection method and system based on three-dimensional point cloud |
| CN116189229A (en) * | 2022-11-30 | 2023-05-30 | 中信重工开诚智能装备有限公司 | Personnel tracking method based on coal mine auxiliary transportation robot |
| CN116189229B (en) * | 2022-11-30 | 2024-04-05 | 中信重工开诚智能装备有限公司 | Personnel tracking method based on coal mine auxiliary transportation robot |
| CN116448188A (en) * | 2023-06-13 | 2023-07-18 | 西安高商智能科技有限责任公司 | Abnormal state monitoring and early warning system for freight winch |
| CN116448188B (en) * | 2023-06-13 | 2023-08-18 | 西安高商智能科技有限责任公司 | Abnormal state monitoring and early warning system for freight winch |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110862033B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110862033A (en) | Intelligent early warning detection method applied to coal mine inclined shaft winch | |
| CN105809679B (en) | Mountain railway side slope rockfall detection method based on visual analysis | |
| CN104331910B (en) | A kind of track obstacle detecting system based on machine vision | |
| CN107025432B (en) | A kind of efficient lane detection tracking and system | |
| CN104573627B (en) | Lane line based on bianry image retains and detection method | |
| CN109359409A (en) | A kind of vehicle passability detection system of view-based access control model and laser radar sensor | |
| CN111563469A (en) | Method and device for identifying irregular parking behaviors | |
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN111626203B (en) | Railway foreign matter identification method and system based on machine learning | |
| CN111626207B (en) | Method and system for detecting intrusion of foreign matters in front of train based on image processing | |
| KR101224027B1 (en) | Method for dectecting front vehicle using scene information of image | |
| CN111626204B (en) | Railway foreign matter invasion monitoring method and system | |
| CN109522847A (en) | A kind of track and road barricade object detecting method based on depth map | |
| CN107274678B (en) | A kind of night vehicle flowrate and model recognizing method based on Kinect | |
| CN111626170B (en) | Image recognition method for railway side slope falling stone intrusion detection | |
| Raviteja et al. | Advanced driver assitance system (ADAS) | |
| CN103164958B (en) | Method and system for vehicle monitoring | |
| CN113484858A (en) | Intrusion detection method and system | |
| CN111259718A (en) | Escalator retention detection method and system based on Gaussian mixture model | |
| CN112230245A (en) | System and method for detecting active obstacles of train in tunnel based on laser radar | |
| CN111523386B (en) | High-speed railway platform door monitoring and protecting method and system based on machine vision | |
| CN103456123B (en) | A kind of video smoke detection method based on flowing with diffusion characteristic | |
| CN103177248A (en) | Rapid pedestrian detection method based on vision | |
| CN115755094A (en) | Obstacle detection method, apparatus, device and storage medium | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |