CN113076883A - Blowout gas flow velocity measuring method based on image feature recognition - Google Patents
Blowout gas flow velocity measuring method based on image feature recognition Download PDFInfo
- Publication number
- CN113076883A CN113076883A CN202110379513.8A CN202110379513A CN113076883A CN 113076883 A CN113076883 A CN 113076883A CN 202110379513 A CN202110379513 A CN 202110379513A CN 113076883 A CN113076883 A CN 113076883A
- Authority
- CN
- China
- Prior art keywords
- image
- images
- blowout gas
- flow velocity
- blowout
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
- G01P5/18—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft by measuring the time taken to traverse a fixed distance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
- Image Analysis (AREA)
- Measuring Volume Flow (AREA)
Abstract
The invention provides a blowout gas flow velocity measuring method based on image feature recognition, which comprises the following steps of: step 1, collecting a large number of high-speed images of on-site blowout gas; step 2, carrying out feature recognition processing on the high-speed image in the step 1; step 3, selecting two adjacent frames of images with excellent characteristic points; step 4, processing the two frames of images in the step 3; and 5, calculating the flow rate of the blowout gas through displacement and time. The method of the invention can obtain the flow rate of the blowout gas under the condition of ensuring the safety of field operators, and reduce economic loss and casualties.
Description
Technical Field
The invention relates to the field of fluid detection, in particular to a blowout gas flow velocity measuring method based on image feature recognition.
Background
In the field of fluid detection, and in particular in designing blowout gas flow rate measurements based on image feature recognition. In recent years, with the increase of the demand of natural gas, the intensity of natural gas exploitation is increasing, when a blowout accident occurs, because of lack of grasp on the diffusion speed of toxic and harmful gas after leakage, the problems of blind evacuation, delayed evacuation and the like are caused, the optimal time for emergency treatment is missed, and a great amount of casualties, property loss and ecological environment damage are caused. Meanwhile, due to the lack of sufficient and effective data to be provided for decision-making personnel, emergency treatment is delayed and blindly treated. Therefore, the method has great significance in carrying out deep technical analysis on the blowout accident, researching the blowout gas flow rate and then making early warning measures of the blowout accident.
The existing methods cannot safely and accurately measure the flow velocity of the blowout gas, and aiming at the characteristic, the flow velocity of the blowout gas is measured by adopting image-based characteristic identification, and the characteristic point detection and matching of the image have wide application, such as image registration, image retrieval, image tracking, three-dimensional reconstruction, visual SLAM and the like. The characteristic points of the image generally refer to pixel points which have obvious textural features in the image and are easy to match and track in a continuous image sequence; the visual SLAM system is a system capable of locating a moving position of a camera and building a map of a scene being traveled according to a moving track of the camera during a movement of the camera.
The processing of the image feature points generally includes two aspects of detection of the image feature points, namely, positioning of the positions of the image feature points, and description of the image feature points, namely, calculation of features of the image feature points. The image feature point detection requires high repeatability of image feature points in different images, the description of the image feature points requires that the features of uniform image feature points in different images are similar, and the features of different image feature points have distinctiveness so as to be convenient for matching the image feature points.
However, the scheme for tracking the image feature points provided by the conventional technology mainly analyzes features based on manual design, generally only uses low-order features, is sensitive to adverse factors such as image noise and optical fiber change, and has the technical problem of low robustness for tracking the image feature points.
At present, after an improved Moracec angular point detection algorithm and an improved SUSAN algorithm are used for processing images, the flow velocity of blowout gas is accurately measured by an LK optical flow method, the damage of blowout is estimated better, and property safety and personal safety are maintained.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a blowout gas flow velocity measuring method based on image feature recognition, which can measure the blowout gas flow velocity in a safe environment, so that the harm caused by blowout is reduced.
The invention adopts the following technical scheme:
a blowout gas flow velocity measuring method based on image feature recognition comprises the following steps:
step 1, collecting a large number of high-speed images of on-site blowout gas;
step 2, carrying out feature recognition processing on the high-speed image in the step 1;
step 3, selecting two adjacent frames of images with excellent characteristic points;
step 4, processing the two frames of images in the step 3;
and 5, calculating the flow rate of the blowout gas through displacement and time.
Further, in step 1, the large number of on-site blowout gas high-speed images are acquired by a blowout gas high-speed image acquisition device fixed at a place far away from a wellhead, the blowout gas high-speed image acquisition device is composed of a long-focus objective lens and a high-definition high-speed camera, and the high-definition high-speed camera cannot move a lens and has a fixed focal length in the shooting process.
Further, in step 2, the feature identification process includes:
s201, preprocessing all images;
s202, storing all the images into the same two groups.
Further, the preprocessing is graying processing.
Further, step 3 includes processing a group of images respectively by using an improved Moravec corner detection algorithm and an improved SUSAN algorithm, wherein both groups of images obtain a series of feature points, and selecting two adjacent frames of images with clear feature points from the two groups of images.
Further, the improved Moravec corner point detection algorithm is as follows: calculating the square sum of gray differences of 8 direction adjacent pixel points by taking a certain interested pixel point in the image as a center, then selecting a pixel point feature candidate point with an interest value larger than a threshold value according to a set threshold value, and finally selecting a point with the maximum interest value as a feature point.
Further, the 8 directions are east, south, west, north, northwest, northeast, southwest and southeast, respectively.
Further, there is a principle that the threshold value is set so that as many feature points as possible are included in the feature point set.
The improved SUSAN algorithm takes the calculation of curvature values and gradients of pixel points of a gray image as a core, and determines angular points according to the transformation conditions of the curvature values and the gradients.
Specifically, a square template is required to slide on the image, and if the difference between the gray value of the pixel point of the original image and the gray value of the pixel point at the center of the template is smaller than a threshold value within the template, the gray value of the pixel point can be determined to be the same as the given gray value. Therefore, the region formed by the pixel points required by all symbols on one image is called 'improved USAN'. Then, according to the midpoint, size and order of the improved USAN, the corner points of the image can be obtained. The method has the main advantages of no need of improving the SUSAN algorithm when the difference calculation is carried out on the image to be processed, and has the characteristics of noise resistance and high operation speed.
In step 4, the image processing includes:
determining all feature points to be tracked of the previous frame image, wherein the feature points to be tracked are corresponding to the feature points found in the next frame image, calculating the displacement distance of every two corresponding feature points in the adjacent images according to an LK optical flow method, and averaging a series of distances to obtain the moving distance of the blowout gas. The calculation of the LK optical flow method comprises the steps of calculating optical flow values of feature points in a front frame image and a rear frame image to obtain an optical flow field of each point, and obtaining the displacement distance of every two corresponding feature points through optical flow field constraint.
In step 5, the displacement is the moving distance of the blowout gas; the time is the reciprocal of the number of the shot images in 1s, and the flow velocity of the blowout gas can be calculated according to the displacement and the time of the blowout gas.
The invention has the beneficial effects that:
the invention adopts the high-definition high-speed camera, can obtain the information of the well mouth when the blowout occurs under the non-contact condition, and can obtain the flow velocity of the blowout gas according to the information. The drilling site can evacuate nearby people and devices as soon as possible according to the flow rate of blowout gas, and the safety problem caused by blowout explosion is avoided.
Drawings
FIG. 1 is a flow chart of blowout gas flow rate measurement;
fig. 2(a) -fig. 2(b) are schematic diagrams illustrating a feature point displacement according to an embodiment of the present invention;
3(a) -3 (b) are two frames before and after a certain time of the blowout field;
fig. 4(a) to 4(b) are diagrams after feature recognition.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described below clearly and completely, and it is obvious that the described embodiments are some, not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The blowout gas flow velocity measuring method based on image feature recognition can accurately measure the flow velocity of blowout gas under the condition of guaranteeing personnel safety during blowout outbreak.
As shown in fig. 1, the method for measuring the flow rate of blowout gas based on image feature recognition of the present invention includes the following steps: step 1, collecting a large number of high-speed images of on-site blowout gas; step 2, carrying out feature recognition processing on the group of sequence images; step 3, selecting two adjacent frames of images with excellent characteristic points; step 4, processing the two images; and 5, calculating the flow rate of the blowout gas through displacement and time.
In the step 1, the large number of on-site blowout gas high-speed images are acquired by a blowout gas high-speed image acquisition device fixed at a place far away from a wellhead, the blowout gas high-speed image acquisition device is composed of a long-focus objective lens and a high-definition high-speed camera, and the high-definition high-speed camera cannot move a lens and has a fixed focal length in the shooting process. Because the position of the lens and the focal length are fixed, the shot image is actually an angle, so that the displacement error of the blowout gas caused by the change of the angle can be reduced, and the displacement of the blowout gas can be better calculated by using some characteristic points.
In the step 2 and the step 3, before image processing, the shot images are stored in the same two parts and stored in a computer, then the two parts of images are preprocessed, the preprocessing is graying processing, both the two parts of images are grayed, then an improved Moravec corner point detection algorithm is used for the first part of images, an improved SUSAN algorithm is used for the two parts of images, both the two groups of images can obtain a series of characteristic points, and two adjacent frames of images with clear characteristic points are selected from the two groups of images. The selection process comprises the steps that the computer selects two adjacent frames of images with the feature points with higher similarity, then the two adjacent frames of images are presented to field operators for selection, if the feature points of the two images are not clear enough after the image is artificially judged, the selection can be continued until two adjacent images which are artificially judged to be clear enough are selected.
As shown in fig. 2(a) -2 (b), the displacement of the feature point in the two frames of images before and after the feature point can be roughly expressed as the image, and the feature point may also appear as the case that the image exists in the previous frame of image and the image does not exist, if the case that the two frames of images before and after the feature point exists, the two frames of images before and after the feature point is avoided as much as possible, so the case that the feature point exists on the two frames of images before and after the feature point as many as possible is selected, in step 4, the image processing includes determining all the feature points to be tracked of the previous frame of image, the feature point to be tracked is the feature point that can find the corresponding feature point in the next frame of image, at least one group of feature points needs to be included, the distance of the displacement of the corresponding feature point in the two adjacent frames of images is calculated by the optical flow method, and the moving distance of, because the blowout gas moves upwards together with some characteristic points such as sand and stones when being sprayed, the displacement of the characteristic points is the displacement of the blowout gas.
In step 5, the displacement is the moving distance of the blowout gas; and (3) counting the reciprocal of the number of the images shot in one second, namely, m images shot in one second, wherein the time of the characteristic point moving in two adjacent frames of images is 1/m second, and the flow velocity of the blowout gas can be calculated according to the displacement and the time of the blowout gas.
Examples of specific applications
A blowout gas flow velocity measuring method based on image feature recognition can be applied to the environment of blowout at a drilling site, as shown in fig. 3(a) and 3(b), when a camera captures two frames of images, the former frame image is shown in fig. 3(a), the latter frame image is shown in fig. 3(b), the number of frames of the two frames of images used in the embodiment is 23, namely, the camera takes 23 images per second, so that the time for the feature point to move in the two adjacent frames of images is 1/23 seconds. As shown in fig. 4(a) and 4(b), the characteristics of the two images are extracted by using a Moravec corner detection algorithm, a blue small circle is used for drawing out, then the positions of characteristic points in the two frames of images before and after are identified by using an LK optical flow method and marked by red lines, then the displacement of the corresponding characteristic points is calculated, and finally the blowout gas flow rate is inverted. It should be noted that not all the feature points may be used in the calculation, as shown in fig. 4(a) -4 (b), the feature points of the previous frame image that are slowly moved a small distance in the positive y-axis direction are the available feature points, and assuming that the average displacement of the available feature points in the positive y-axis direction is a, the blowout gas flow rate is 23 a.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A blowout gas flow velocity measuring method based on image feature recognition is characterized by comprising the following steps:
step 1, collecting a large number of high-speed images of on-site blowout gas;
step 2, carrying out feature recognition processing on the high-speed image in the step 1;
step 3, selecting two adjacent frames of images with excellent characteristic points;
step 4, processing the two frames of images in the step 3;
and 5, calculating the flow rate of the blowout gas through displacement and time.
2. The method for measuring the flow rate of the blowout gas based on the image feature recognition is characterized in that in the step 1, the large number of high-speed images of the blowout gas in the field are acquired by a high-speed image acquisition device of the blowout gas fixed at a place far away from a wellhead, and the high-speed image acquisition device of the blowout gas consists of a long-focus objective lens and a high-definition high-speed camera, wherein the high-definition high-speed camera cannot move a lens and has a fixed focal length in the shooting process.
3. The blowout gas flow velocity measurement method based on image feature recognition according to claim 1, wherein in the step 2, the feature recognition process comprises:
s201, preprocessing all images;
s202, storing all the images into the same two groups.
4. The image feature recognition-based blowout gas flow velocity measurement method according to claim 3, wherein the preprocessing is a graying processing.
5. The blowout gas flow velocity measurement method based on image feature identification as claimed in claim 1, wherein the step 3 comprises processing a set of images respectively by using a modified Moravec corner detection algorithm and a modified SUSAN algorithm, wherein the two sets of images both obtain a series of feature points, and selecting two adjacent frames of images with clear feature points from the two sets of images.
6. The image feature recognition-based blowout gas flow velocity measurement method according to claim 5, wherein the improved Moravec corner detection algorithm is as follows: calculating the square sum of gray differences of 8 direction adjacent pixel points by taking a certain interested pixel point in the image as a center, selecting the pixel point with an interest value larger than a threshold value as a feature candidate point according to a set threshold value, and finally selecting the point with the maximum interest value as a feature point.
7. The image feature recognition based blowout gas flow velocity measurement method according to claim 6, wherein the 8 directions are east, south, west, north, northwest, northeast, southwest, and southeast, respectively.
8. The blowout gas flow velocity measurement method based on image feature identification as claimed in claim 5, wherein the improved SUSAN algorithm is centered on calculating curvature values and gradients of pixel points of the gray-scale image, and determining corner points according to transformation conditions of the curvature values and the gradients;
specifically, a square sample plate is adopted to slide on an image, if the difference between the gray values of the pixel point of the original image and the pixel point at the center of the sample plate in the sample plate is smaller than a threshold value, the gray value of the pixel point is determined to be the same as the given gray value, so that an area formed by the pixel points required by all symbols on an image is called 'improved USAN', and then the angular point of the image is obtained according to the midpoint, the size and the order of the improved USAN.
9. The blowout gas flow velocity measurement method based on image feature identification according to claim 1, wherein in step 4, the image processing comprises:
determining all feature points to be tracked of a previous frame image, wherein the feature points to be tracked are corresponding to feature points found in a next frame image, calculating the displacement distance of every two corresponding feature points in adjacent images according to an LK optical flow method, averaging a series of distances to obtain the moving distance of the blowout gas, wherein the LK optical flow method comprises calculating the optical flow values of the feature points in the previous frame image and the next frame image to obtain the optical flow field of each point, and obtaining the displacement distance of every two corresponding feature points through optical flow field constraint.
10. The blowout gas flow velocity measurement method based on image feature recognition according to claim 1, wherein in step 5, the displacement is a moving distance of the blowout gas; the time is the reciprocal of the number of the shot images in 1s, and the flow velocity of the blowout gas can be calculated according to the displacement and the time of the blowout gas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379513.8A CN113076883B (en) | 2021-04-08 | 2021-04-08 | Blowout gas flow velocity measuring method based on image feature recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379513.8A CN113076883B (en) | 2021-04-08 | 2021-04-08 | Blowout gas flow velocity measuring method based on image feature recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076883A true CN113076883A (en) | 2021-07-06 |
| CN113076883B CN113076883B (en) | 2022-05-06 |
Family
ID=76615725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110379513.8A Active CN113076883B (en) | 2021-04-08 | 2021-04-08 | Blowout gas flow velocity measuring method based on image feature recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076883B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332170A (en) * | 2021-12-24 | 2022-04-12 | 哈尔滨商业大学 | Novel capital construction site safety monitoring system |
| CN117074717A (en) * | 2023-08-14 | 2023-11-17 | 北京科技大学 | Solid-liquid two-phase flow image velocimetry method and system based on particle identification |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101661049A (en) * | 2009-10-14 | 2010-03-03 | 中国矿业大学(北京) | Method for counting propagation velocity of pipeline gas explosion flame |
| CN105654507A (en) * | 2015-12-24 | 2016-06-08 | 北京航天测控技术有限公司 | Vehicle outer contour dimension measuring method based on image dynamic feature tracking |
| CN106370817A (en) * | 2016-10-12 | 2017-02-01 | 西南石油大学 | Quantitative identification of fractures and caverns based on core analysis and electrical imaging logging |
| US20170097274A1 (en) * | 2015-10-06 | 2017-04-06 | Bridger Photonics, Inc. | Gas-mapping 3d imager measurement techniques and method of data processing |
| CN106845552A (en) * | 2017-01-31 | 2017-06-13 | 东南大学 | The low dynamic carrier speed calculation method of fusion light stream and SIFT feature Point matching under the uneven environment of light distribution |
| CN107705288A (en) * | 2017-09-04 | 2018-02-16 | 武汉工程大学 | Hazardous gas spillage infrared video detection method under pseudo- target fast-moving strong interferers |
| US9928655B1 (en) * | 2015-08-31 | 2018-03-27 | Amazon Technologies, Inc. | Predictive rendering of augmented reality content to overlay physical structures |
| CN110886604A (en) * | 2019-12-02 | 2020-03-17 | 中国石油大学(华东) | Efficient geothermal resource exploration method based on computer simulation technology |
| CN111783672A (en) * | 2020-07-01 | 2020-10-16 | 哈尔滨工业大学 | Image feature identification method for improving bridge dynamic displacement precision |
| CN111859750A (en) * | 2020-07-16 | 2020-10-30 | 中国石油大学(北京) | Analysis method for applying underwater emergency well plugging device to daily blowout flow gas field |
| CN112212922A (en) * | 2020-10-30 | 2021-01-12 | 天地伟业技术有限公司 | Emergency water flow velocity monitoring equipment based on artificial intelligence technology |
| CN112233177A (en) * | 2020-10-10 | 2021-01-15 | 中国安全生产科学研究院 | Unmanned aerial vehicle pose estimation method and system |
-
2021
- 2021-04-08 CN CN202110379513.8A patent/CN113076883B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101661049A (en) * | 2009-10-14 | 2010-03-03 | 中国矿业大学(北京) | Method for counting propagation velocity of pipeline gas explosion flame |
| US9928655B1 (en) * | 2015-08-31 | 2018-03-27 | Amazon Technologies, Inc. | Predictive rendering of augmented reality content to overlay physical structures |
| US20170097274A1 (en) * | 2015-10-06 | 2017-04-06 | Bridger Photonics, Inc. | Gas-mapping 3d imager measurement techniques and method of data processing |
| CN105654507A (en) * | 2015-12-24 | 2016-06-08 | 北京航天测控技术有限公司 | Vehicle outer contour dimension measuring method based on image dynamic feature tracking |
| CN106370817A (en) * | 2016-10-12 | 2017-02-01 | 西南石油大学 | Quantitative identification of fractures and caverns based on core analysis and electrical imaging logging |
| CN106845552A (en) * | 2017-01-31 | 2017-06-13 | 东南大学 | The low dynamic carrier speed calculation method of fusion light stream and SIFT feature Point matching under the uneven environment of light distribution |
| CN107705288A (en) * | 2017-09-04 | 2018-02-16 | 武汉工程大学 | Hazardous gas spillage infrared video detection method under pseudo- target fast-moving strong interferers |
| CN110886604A (en) * | 2019-12-02 | 2020-03-17 | 中国石油大学(华东) | Efficient geothermal resource exploration method based on computer simulation technology |
| CN111783672A (en) * | 2020-07-01 | 2020-10-16 | 哈尔滨工业大学 | Image feature identification method for improving bridge dynamic displacement precision |
| CN111859750A (en) * | 2020-07-16 | 2020-10-30 | 中国石油大学(北京) | Analysis method for applying underwater emergency well plugging device to daily blowout flow gas field |
| CN112233177A (en) * | 2020-10-10 | 2021-01-15 | 中国安全生产科学研究院 | Unmanned aerial vehicle pose estimation method and system |
| CN112212922A (en) * | 2020-10-30 | 2021-01-12 | 天地伟业技术有限公司 | Emergency water flow velocity monitoring equipment based on artificial intelligence technology |
Non-Patent Citations (3)
| Title |
|---|
| 刘灵: "基于深度学习的车型识别分析与研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 * |
| 田家林等: "井喷失控井天然气喷量测定计算与实验研究", 《天然气工业》 * |
| 黑尘子: "Moravec角点检测原理详解", 《个人图书馆》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332170A (en) * | 2021-12-24 | 2022-04-12 | 哈尔滨商业大学 | Novel capital construction site safety monitoring system |
| CN114332170B (en) * | 2021-12-24 | 2022-11-18 | 哈尔滨商业大学 | Novel capital construction site safety monitoring system |
| CN117074717A (en) * | 2023-08-14 | 2023-11-17 | 北京科技大学 | Solid-liquid two-phase flow image velocimetry method and system based on particle identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113076883B (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685066B (en) | Mine target detection and identification method based on deep convolutional neural network | |
| CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
| CN113076883B (en) | Blowout gas flow velocity measuring method based on image feature recognition | |
| CN110070010A (en) | A kind of face character correlating method identified again based on pedestrian | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN111899288A (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
| CN108596129A (en) | A kind of vehicle based on intelligent video analysis technology gets over line detecting method | |
| CN112085003A (en) | Automatic identification method and device for abnormal behaviors in public places and camera equipment | |
| CN111199556B (en) | Indoor pedestrian detection and tracking method based on camera | |
| CN109434251B (en) | Welding seam image tracking method based on particle filtering | |
| CN113379801B (en) | High-altitude parabolic monitoring and positioning method based on machine vision | |
| CN105654507A (en) | Vehicle outer contour dimension measuring method based on image dynamic feature tracking | |
| CN110111389B (en) | Mobile augmented reality tracking registration method and system based on SLAM | |
| CN102768022A (en) | Tunnel surrounding rock deformation detection method adopting digital camera technique | |
| CN110084830B (en) | Video moving object detection and tracking method | |
| CN101714256A (en) | Omnibearing vision based method for identifying and positioning dynamic target | |
| CN111667470B (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| KR20150049529A (en) | Apparatus and method for estimating the location of the vehicle | |
| CN109375211B (en) | Radar and multi-optical equipment-based mobile unmanned platform target searching method | |
| CN113947636B (en) | Laser SLAM positioning system and method based on deep learning | |
| CN111681275B (en) | Double-feature-fused semi-global stereo matching method | |
| CN113030244B (en) | Inversion imaging method and system for transmission line tower corrosion defect magnetic flux leakage detection signal | |
| CN106682674B (en) | A kind of pointer instrument automatic reading method based on intelligent inspection robot | |
| CN111652790A (en) | Sub-pixel image registration method | |
| CN104966302B (en) | A kind of detection localization method of any angle laser cross |
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 |