CN113959332A - Large aerostat volume real-time monitoring system based on binocular vision - Google Patents
Large aerostat volume real-time monitoring system based on binocular vision Download PDFInfo
- Publication number
- CN113959332A CN113959332A CN202111108119.7A CN202111108119A CN113959332A CN 113959332 A CN113959332 A CN 113959332A CN 202111108119 A CN202111108119 A CN 202111108119A CN 113959332 A CN113959332 A CN 113959332A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- real
- volume
- binocular vision
- 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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
A binocular vision-based large aerostat volume real-time monitoring system comprises a 5K image real-time acquisition and transmission subsystem and a volume calculation and visualization subsystem, wherein the 5K image real-time acquisition and transmission subsystem comprises a plurality of 5K image real-time acquisition devices which are arranged around an aerostat to be detected, and the 5K image real-time acquisition devices comprise a binocular vision module, a monitoring camera module and a laser ranging module; the volume calculation and visualization subsystem comprises a digital image processing module, a data exchange module and a display module, wherein the data exchange module is provided with an optical fiber switch, a serial port communication server and an image collector; the optical fiber switch and the serial port communication server are respectively connected with the digital image processing module, the display module comprises a first display and a second display, the first display is connected with the output end of the digital image processing module, and the second display is connected with the output end of the image collector. The system of the invention has simple structure, high data processing speed and accurate and reliable acquisition result.
Description
Technical Field
The invention belongs to the technical field of non-contact volume measurement, and particularly relates to a binocular vision-based real-time volume monitoring system for a large aerostat.
Background
Real-time monitoring of target volumes is of great value in daily production, life and engineering. The traditional target volume calculation method mainly comprises a weighing method, a liquid discharge method, a gas method, a precise measuring method and the like, but most of the methods belong to contact measurement methods, the requirements on the measured target volume and specification are strict, the method is usually only suitable for volume detection and measurement of small static targets, volume information cannot be effectively obtained in real time for targets with large volumes, and the volume monitoring task is difficult to complete. In an actual application scene, the traditional volume calculation method is lack of strength when facing irregular and large-volume targets, and the accurate volume information of the targets cannot be obtained many times, so that the traditional volume calculation method cannot well adapt to actual requirements.
With continuous progress and improvement of computer data processing capability and digital image vision processing application technology, binocular stereo vision has wide development space as a new volume calculation method. The volume calculation task is completed by using the target information contained in the image through machine vision, and the method has important significance in production and life.
Disclosure of Invention
The invention aims to solve the problems in the prior art, and provides a binocular vision-based real-time monitoring system for the volume of a large aerostat, which effectively realizes non-contact volume measurement and real-time dynamic management of the large aerostat.
In order to achieve the purpose, the invention has the following technical scheme:
a binocular vision-based large aerostat volume real-time monitoring system comprises a 5K image real-time acquisition and transmission subsystem and a volume calculation and visualization subsystem, wherein an optical fiber transmission line, a coaxial cable and a twisted pair cable are connected between the 5K image real-time acquisition and transmission subsystem and the volume calculation and visualization subsystem; the 5K image real-time acquisition and transmission subsystem comprises a plurality of 5K image real-time acquisition devices arranged around the aerostat to be detected, the 5K image real-time acquisition devices respectively comprise a binocular vision module, a monitoring camera module and a laser ranging module, the binocular vision module comprises a first digital camera, a second digital camera, a first photoelectric converter and a second photoelectric converter, and the first photoelectric converter and the second photoelectric converter are respectively connected to the first digital camera and the second digital camera; the 5K image real-time acquisition equipment is provided with a binocular vision module output interface, a monitoring camera module output interface and a laser ranging module output interface, wherein the binocular vision module output interface is connected with an optical fiber transmission line, the monitoring camera module output interface is connected with a coaxial cable, and the laser ranging module output interface is connected with a twisted pair cable; the volume calculation and visualization subsystem comprises a digital image processing module, a data exchange module and a display module, wherein the data exchange module is provided with an optical fiber switch, a serial communication server and an image collector, the optical fiber switch is provided with a switch multipath input interface connected with an optical fiber transmission line, the serial communication server is provided with a server multipath input interface connected with a twisted pair cable, and the image collector is provided with an image collection multipath input interface connected with a coaxial cable; the output ends of the optical fiber switch and the serial port communication server are respectively connected with the digital image processing module through Ethernet interfaces, the display module comprises a first display and a second display, the first display is connected with the output end of the digital image processing module through an HDMI data line, and the second display is connected with the output end of the image collector.
As a preferred embodiment of the real-time monitoring system of the present invention, the digital image processing module comprises, in sequence according to the data flow direction: the system comprises an image correction sub-module, an image segmentation sub-module, a stereo matching parallel acceleration calculation sub-module, a three-dimensional reconstruction sub-module, a point cloud splicing sub-module and a volume acceleration calculation sub-module.
As a preferred scheme of the real-time monitoring system, the image correction submodule receives an image acquired by the binocular vision module, calibrates the calibration plate by adopting a Zhang-Yongyou calibration method to acquire internal and external parameters of the binocular camera, and establishes a relation between a binocular vision imaging coordinate system and a world coordinate system.
As a preferred scheme of the real-time monitoring system, the image segmentation submodule performs image segmentation by adopting a binocular difference image segmentation algorithm based on mean shift.
As a preferred scheme of the real-time monitoring system, the stereo matching parallel acceleration calculation sub-module adopts a stereo matching algorithm based on self-adaptive threshold polar line distance transformation to realize stereo matching of binocular images, and obtains a disparity map.
As a preferred scheme of the real-time monitoring system of the present invention, the three-dimensional reconstruction sub-module solves the three-dimensional information corresponding to each pixel point in the disparity map by using the relationship between the camera coordinate system and the world coordinate system, thereby completing the three-dimensional reconstruction.
As a preferred scheme of the real-time monitoring system, the point cloud splicing submodule carries out point cloud splicing by adopting a slicing method, wherein the slicing method is to obtain a rotation matrix and a translation matrix of each group of point cloud data compared with a reference point based on the physical position relation among a plurality of pieces of 5K image real-time acquisition equipment, and the rotation matrix and the translation matrix are used for conversion, so that the point cloud splicing is completed.
As a preferred scheme of the real-time monitoring system, the volume acceleration calculation submodule slices the point cloud at equal intervals along the depth direction, regards the point in each slice as a point on the same plane, calculates an external polygon from the point in each slice, calculates the area of the polygon, and finally obtains the overall volume of the point cloud through integration; the volume acceleration calculation submodule comprises a heterogeneous calculation platform built by combining a CPU and a GPU, and real-time calculation is carried out in a CUDA parallel programming mode.
Compared with the prior art, the invention has the following beneficial effects:
for an aerostat with a large volume, under the condition that the target volume is difficult to measure directly, in order to obtain the target volume in real time, the monitoring system adopts a method of calculating a three-dimensional point cloud model of a target by binocular stereo vision and solving the target volume. Firstly, a certain amount of 5K image real-time acquisition equipment is arranged around the aerostat to be measured, and point cloud calculation is carried out by utilizing images obtained by each group of binocular vision modules. After point clouds of all photographing point positions are obtained, all calculated point clouds are spliced into a unified coordinate system by using a point cloud splicing technology, finally, solving of the volume is achieved under the unified coordinate system, meanwhile, regions photographed by each group of binocular vision modules are displayed in a unified mode, and a user can check the local state of a target conveniently in real time. Therefore, the target can be monitored in real time, and the volume data of the target can be output in real time. According to the laser ranging module, the distance data of the aerostat are collected and returned to the volume calculation and visualization subsystem by using the laser ranging principle, prior information is provided for a subsequent stereo matching algorithm, and the stereo matching efficiency is improved. The first display is connected with the output end of the digital image processing module and used for carrying out operation processing on binocular images acquired by all the binocular vision modules and displaying a target point cloud result and a volume calculation result which are obtained through calculation. And the second display is connected with the output end of the image collector and is used for displaying the position and the posture information of the aerostat to be detected in real time. The system of the invention has simple structure, high data processing speed and accurate and reliable acquisition result.
Drawings
FIG. 1 is a hardware connection diagram of a large aerostat volume real-time monitoring system based on binocular vision;
FIG. 2 is a block diagram of a 5K image real-time acquisition device according to the present invention;
FIG. 3 is a block diagram of the volume calculation and visualization subsystem of the present invention;
FIG. 4 is a schematic diagram of a digital image processing module according to the present invention;
FIG. 5 is a flow chart of a method for solving volumes by the volume acceleration calculation sub-module of the present invention.
In the drawings: a 1-5K image real-time acquisition and transmission subsystem; 2-volume calculation and visualization subsystem; 3-an optical fiber transmission line; 4-a coaxial cable; 5-twisted pair cable; 6-5K image real-time acquisition equipment; 7-binocular vision module; 8-monitoring camera module; 9-laser ranging module; 10-binocular vision module output interface; 11-monitoring camera module output interface; 12-laser ranging module output interface; 13-a first power interface; 14-a first digital camera; 15-a second digital camera; 16-a first photoelectric converter; 17-a second photoelectric converter; 18-an image syndrome module; 19-an image segmentation sub-module; 20-a stereo matching parallel accelerated computation submodule; 21-a three-dimensional reconstruction submodule; 22-point cloud splicing submodule; 23-volume acceleration calculation submodule; 221-a display interface; 222-gigabit ethernet interface; 223-ten gigabit Ethernet interface; 31-a fibre optic switch; 32-serial communication server; 33-an image collector; 311-switch multiple input interface; 312-switch output interface; 321-server multipath input interface; 322-server output interface; 331-image acquisition multi-path input interface; 332-image acquisition output interface; 41-a first display; 42-a second display; 25-a second power supply module.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1, the binocular vision-based large aerostat volume real-time monitoring system provided by the invention comprises a 5K image real-time acquisition and transmission subsystem 1, a volume calculation and visualization subsystem 2 and a plurality of connecting wires between the two subsystems, wherein the connecting wires comprise an optical fiber transmission line 3, a coaxial cable 4 and a twisted pair cable 5. The 5K image real-time acquisition and transmission subsystem 1 comprises eight sets of 5K image real-time acquisition equipment 6, and output interfaces of different modules in each set of 5K image real-time acquisition equipment 6 are connected with input interfaces of corresponding modules in the volume calculation and visualization subsystem 2 through corresponding connecting lines.
Referring to fig. 2, the 5K image real-time acquisition and transmission subsystem 1 in this embodiment includes eight sets of completely identical 5K image real-time acquisition devices 6, which include: the binocular vision module 7, the monitoring camera module 8, the laser ranging module 9 and the power module. Eight sets of 5K image real-time acquisition equipment 6 are all connected with the volume calculation and visualization subsystem 1. The binocular vision module output interface 10 is connected with the input interface of the volume calculation and visualization subsystem 2 through the optical fiber transmission line 3, the monitoring camera module output interface 11 through the coaxial cable 4 and the laser ranging module output interface 12 through the twisted pair cable 5. The first power interface is connected with a power module, and the power module meets the requirement of a power supply of the 5K image real-time acquisition equipment 6. The binocular vision module 7 includes: a first digital camera 14, a second digital camera 15, a first photoelectric converter 16, and a second photoelectric converter 17, the first digital camera 14 and the second digital camera 15 each being a GigE digital camera. The two GigE digital cameras are respectively connected with the input interfaces of the two photoelectric converters through Ethernet data lines, and the output interfaces of the two photoelectric converters are respectively connected with an SC flange of the equipment shell through optical fibers. The monitoring camera module 8 includes: a monitoring camera and a BNC connecting line; wherein, the output interface of surveillance camera machine is connected with the BNC ring flange of equipment shell through the BNC connecting wire. The laser ranging module 9 includes: a laser range finder and a connected RS485 port data line; and an RS485 output interface of the laser range finder is connected with an RS485 flange of the equipment shell through a data line. The laser ranging module 9 collects distance data of the target aerostat and returns the data to the volume calculation and visualization subsystem 2 by using the principle of laser ranging, so that prior information is provided for a subsequent stereo matching algorithm, and the stereo matching efficiency is improved.
Referring to fig. 3, the volume calculation and visualization subsystem 2 in this example includes: the device comprises a digital image processing module, a data exchange module, a display module and a power supply part. The digital image processing module is mainly realized by four paths of RTX3090 display cards/artificial intelligence GPU servers cabinet type assembly workstations, which comprise RTX 309024G 4+128G memory +2T solid state, and the data interface comprises: one each of gigabit ethernet interface 222 and gigabit ethernet interface 223 and display interface 221. The gigabit ethernet interface 223 is connected to the switch output interface 312 of the optical fiber switch 31 via a gigabit network cable, the gigabit ethernet interface 222 is connected to the server output interface 322 of the serial communication server 32 via a gigabit network cable, and stores eight paths of image data in the digital image processing module, and the digital image processing module undertakes processing of the image data in the processes of image correction, image segmentation, stereo matching, three-dimensional reconstruction, point cloud splicing, volume calculation, and the like. The data exchange module comprises: a fiber switch 31, a serial communication server 32 and an image collector 33. Eight input interfaces of the optical fiber switch 31 are connected with the SC flange plates on the eight sets of 5K image real-time acquisition equipment 6 through optical fibers to acquire image data in the binocular vision module 7. The eight input interfaces of the serial communication server 32 are connected with the RS484 flange plate of the eight sets of 5K image real-time acquisition devices 6 through twisted-pair lines, and acquire distance data in the laser ranging module 9. The eight input interfaces of the image collector 33 are connected with the BNC flange on the eight sets of 5K image real-time collecting equipment 6 through monitoring lines, and collect the video data in the monitoring camera module 8 in real time. The data exchange module receives digital image signals output by the 5K image real-time acquisition and transmission subsystem 1, the switch output interface 312 and the server output interface 322 of the data exchange module are respectively connected with the gigabit ethernet interface 222 and the gigabit ethernet interface 223 of the digital image processing module, and the display interface 221 of the digital image processing module is connected with the display module through a data bus, so that data interaction can be conveniently carried out with the display module. The display module includes: the first display 41 is connected with a display interface 221 in the digital image processing module through the HDMI data line, and is configured to perform a series of arithmetic processing on eight groups of binocular images and display a target point cloud result and a volume calculation result obtained through calculation. The second display 42 is also connected to the image acquisition output interface 332 in the data exchange module through an HDMI data line, and is configured to display the position and posture information of the target aerostat in real time. The power supply part is connected to the second power interface 25, and the power supply part meets the power utilization requirement for the volume calculation and visualization subsystem 2.
Referring to fig. 4, the digital image processing module in the volume calculation and visualization subsystem 2 in this example comprises: the system comprises an image correction submodule 18, an image segmentation submodule 19, a stereo matching parallel acceleration calculation submodule 20, a three-dimensional reconstruction submodule 21, a point cloud splicing submodule 22 and a volume acceleration calculation submodule 23. The image data acquired by the binocular vision module 7 in the 5K image real-time acquisition and transmission subsystem 1 sequentially passes through the image correction submodule 18, the image segmentation submodule 19, the stereo matching parallel acceleration calculation submodule 20, the three-dimensional reconstruction submodule 21, the point cloud splicing submodule 22 and the volume acceleration calculation submodule 23 to perform data calculation, and finally the output end of the volume acceleration calculation submodule 23 is connected with the output end of the digital image processing module, namely is connected to the input end of the display module through the display interface 221.
The input end of the image correction submodule 18 is a binocular vision module 7 in the 5K image real-time acquisition and transmission subsystem 1, the output end is an image segmentation submodule 19, and the image correction submodule 18 calibrates a large calibration plate by adopting a Zhang-Yongyou calibration method to obtain the inside and outside parameters of a binocular camera, so that the relationship between a binocular vision imaging coordinate system and a world coordinate system is established.
The input of the image segmentation submodule 19 is the output of the image correction submodule 18, and the output is the stereo matching parallel acceleration computation submodule 20. The image segmentation submodule 19 is realized by adopting a binocular differential image segmentation algorithm based on mean shift.
The input end of the stereo matching parallel acceleration computation submodule 20 is an image segmentation submodule 19, and the output end is a three-dimensional reconstruction submodule 21. The stereo matching parallel acceleration calculation sub-module 20 is mainly implemented by a stereo matching algorithm based on adaptive threshold polar line distance transformation. After the image is preprocessed to obtain a target area, in order to realize three-dimensional reconstruction of the target, stereo matching needs to be carried out on the binocular image. In order to save computing resources and obtain a dense disparity map, a local stereo matching algorithm based on gray information is selected. Meanwhile, in order to improve the computing efficiency, the parallel computing of the CPU is called under the python compiling environment, and the stereo matching time is greatly shortened.
The input end of the three-dimensional reconstruction submodule 21 is a stereo matching parallel acceleration calculation submodule 20, and the output end is a point cloud splicing submodule 22. And obtaining a disparity map after the stereo matching is finished, and solving three-dimensional information corresponding to each pixel point in the disparity map by utilizing the relation between a camera coordinate system and a world coordinate system to finish the three-dimensional reconstruction.
The input end of the point cloud splicing submodule 22 is a three-dimensional reconstruction submodule 21, and the output end is a volume acceleration calculation submodule 23. After eight groups of point clouds with different visual angles are generated, a rotation matrix and a translation matrix of each group of point cloud data compared with a reference point can be obtained based on the physical position relation among eight groups of 5K image real-time acquisition equipment, and the two matrixes are utilized for conversion to complete point cloud splicing.
The input end of the volume acceleration calculation submodule 23 is a point cloud splicing submodule 22, and the output end is a display module.
Referring to fig. 5, the volume acceleration calculation sub-module 23 is implemented based on a slicing method, and after three-dimensional point cloud data of the target aerostat is acquired, the point cloud is gridded along the depth direction, equidistant "slices" are implemented, and points in each slice are regarded as points located on the same plane. In order to reduce the calculation amount on the premise of ensuring the precision, point clouds in the grids are sampled down, then missing parts in the grids are supplemented by a quadratic interpolation method, then external polygons are obtained for points in each slice, the area of the polygons is calculated, and finally the integral volume of the point clouds is obtained through integration. Meanwhile, in order to accelerate the slicing volume solving, a CPU + GPU heterogeneous computing platform is set up to serve as computing resources, and real-time computing is carried out in a CUDA parallel programming mode.
The above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the technical solution of the present invention, and it should be understood by those skilled in the art that the technical solution can be modified and replaced by a plurality of simple modifications and replacements without departing from the spirit and principle of the present invention, and the modifications and replacements also fall into the protection scope covered by the claims.
Claims (8)
1. The utility model provides a large-scale aerostat volume real-time monitoring system based on binocular vision which characterized in that: the system comprises a 5K image real-time acquisition and transmission subsystem (1) and a volume calculation and visualization subsystem (2), wherein an optical fiber transmission line (3), a coaxial cable (4) and a twisted pair cable (5) are connected between the 5K image real-time acquisition and transmission subsystem (1) and the volume calculation and visualization subsystem (2); the system comprises a 5K image real-time acquisition and transmission subsystem (1) and a control subsystem, wherein the 5K image real-time acquisition and transmission subsystem (1) comprises a plurality of 5K image real-time acquisition devices (6) arranged around a aerostat to be detected, each 5K image real-time acquisition device (6) comprises a binocular vision module (7), a monitoring camera module (8) and a laser ranging module (9), each binocular vision module (7) comprises a first digital camera (14), a second digital camera (15), and a first photoelectric converter (16) and a second photoelectric converter (17) which are respectively connected to the first digital camera (14) and the second digital camera (15); the 5K image real-time acquisition equipment (6) is provided with a binocular vision module output interface (10), a monitoring camera module output interface (11) and a laser ranging module output interface (12), the binocular vision module output interface (10) is connected with the optical fiber transmission line (3), the monitoring camera module output interface (11) is connected with the coaxial cable (4), and the laser ranging module output interface (12) is connected with the twisted pair cable (5); the volume calculation and visualization subsystem (2) comprises a digital image processing module, a data exchange module and a display module, wherein the data exchange module is provided with an optical fiber switch (31), a serial communication server (32) and an image collector (33), the optical fiber switch (31) is provided with a switch multipath input interface (311) connected with an optical fiber transmission line (3), the serial communication server (32) is provided with a server multipath input interface (321) connected with a twisted pair cable (5), and the image collector (33) is provided with an image collection multipath input interface (331) connected with a coaxial cable (4); the output ends of the optical fiber switch (31) and the serial port communication server (32) are respectively connected with the digital image processing module through Ethernet interfaces, the display module comprises a first display (41) and a second display (42), the first display (41) is connected with the output end of the digital image processing module, and the second display (42) is connected with the output end of the image collector (33).
2. The binocular vision based large aerostat volume real-time monitoring system according to claim 1, wherein the digital image processing module comprises, in sequence according to the data flow direction:
the system comprises an image correction submodule (18), an image segmentation submodule (19), a stereo matching parallel acceleration calculation submodule (20), a three-dimensional reconstruction submodule (21), a point cloud splicing submodule (22) and a volume acceleration calculation submodule (23).
3. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: the image correction submodule (18) receives the image acquired by the binocular vision module (7), calibrates the calibration plate by adopting a Zhang-Zhengyou calibration method to acquire the internal and external parameters of the binocular camera, and establishes the relation between a binocular vision imaging coordinate system and a world coordinate system.
4. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: the image segmentation submodule (19) performs image segmentation by adopting a binocular difference image segmentation algorithm based on mean shift.
5. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: the stereo matching parallel accelerated computation submodule (20) adopts a stereo matching algorithm based on self-adaptive threshold polar line distance transformation to realize stereo matching of binocular images, and obtains a disparity map.
6. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: and the three-dimensional reconstruction submodule (21) solves the three-dimensional information corresponding to each pixel point in the disparity map by utilizing the relation between the camera coordinate system and the world coordinate system, thereby completing three-dimensional reconstruction.
7. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: the point cloud splicing submodule (22) performs point cloud splicing by adopting a slicing method, wherein the slicing method is to obtain a rotation matrix and a translation matrix of each group of point cloud data compared with a reference point based on the physical position relation among a plurality of pieces of 5K image real-time acquisition equipment (6) by using point clouds with different visual angles, and the rotation matrix and the translation matrix are used for conversion, so that the point cloud splicing is completed.
8. The binocular vision-based large aerostat volume real-time monitoring system according to claim 2, wherein: the volume acceleration calculation submodule (23) slices the point cloud at equal intervals along the depth direction, regards the point in each slice as a point on the same plane, calculates an external polygon from the point in each slice, calculates the area of the polygon, and finally obtains the integral volume of the point cloud through integration; the volume acceleration calculation submodule (23) comprises a heterogeneous calculation platform built by combining a CPU and a GPU, and real-time calculation is carried out in a CUDA parallel programming mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111108119.7A CN113959332B (en) | 2021-09-22 | 2021-09-22 | Large aerostat volume real-time monitoring system based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111108119.7A CN113959332B (en) | 2021-09-22 | 2021-09-22 | Large aerostat volume real-time monitoring system based on binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113959332A true CN113959332A (en) | 2022-01-21 |
| CN113959332B CN113959332B (en) | 2023-04-07 |
Family
ID=79461887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111108119.7A Active CN113959332B (en) | 2021-09-22 | 2021-09-22 | Large aerostat volume real-time monitoring system based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113959332B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936760A (en) * | 2009-06-30 | 2011-01-05 | 宝山钢铁股份有限公司 | Vision measuring system for large stockyard and stockpile |
| CN103307980A (en) * | 2013-06-04 | 2013-09-18 | 中国科学院遥感与数字地球研究所 | Automatic measuring device for volume of grain pile and measuring method thereof |
| CN104457575A (en) * | 2014-12-18 | 2015-03-25 | 郑州长河电子工程有限公司 | Monitoring system and method for barn storage amount |
| CN106767399A (en) * | 2016-11-11 | 2017-05-31 | 大连理工大学 | The non-contact measurement method of the logistics measurement of cargo found range based on binocular stereo vision and dot laser |
| US20190026914A1 (en) * | 2017-07-24 | 2019-01-24 | Deere & Company | Estimating a volume of contents in a container of a work vehicle |
| CN111912352A (en) * | 2020-07-15 | 2020-11-10 | 深圳融荟智能科技有限公司 | Volume scanning method and device |
| CN113093216A (en) * | 2021-06-07 | 2021-07-09 | 山东捷瑞数字科技股份有限公司 | Irregular object measurement method based on laser radar and camera fusion |
-
2021
- 2021-09-22 CN CN202111108119.7A patent/CN113959332B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936760A (en) * | 2009-06-30 | 2011-01-05 | 宝山钢铁股份有限公司 | Vision measuring system for large stockyard and stockpile |
| CN103307980A (en) * | 2013-06-04 | 2013-09-18 | 中国科学院遥感与数字地球研究所 | Automatic measuring device for volume of grain pile and measuring method thereof |
| CN104457575A (en) * | 2014-12-18 | 2015-03-25 | 郑州长河电子工程有限公司 | Monitoring system and method for barn storage amount |
| CN106767399A (en) * | 2016-11-11 | 2017-05-31 | 大连理工大学 | The non-contact measurement method of the logistics measurement of cargo found range based on binocular stereo vision and dot laser |
| US20190026914A1 (en) * | 2017-07-24 | 2019-01-24 | Deere & Company | Estimating a volume of contents in a container of a work vehicle |
| CN111912352A (en) * | 2020-07-15 | 2020-11-10 | 深圳融荟智能科技有限公司 | Volume scanning method and device |
| CN113093216A (en) * | 2021-06-07 | 2021-07-09 | 山东捷瑞数字科技股份有限公司 | Irregular object measurement method based on laser radar and camera fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113959332B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114693785A (en) | Target positioning method, system and related equipment | |
| CN103743352B (en) | A kind of 3 D deformation measuring method based on polyphaser coupling | |
| CN114638909A (en) | Substation semantic map construction method based on laser SLAM and visual fusion | |
| CN112506476B (en) | Method and device for quickly constructing digital twin workshop system | |
| CN110189400A (en) | A kind of three-dimensional rebuilding method, three-dimensional reconstruction system, mobile terminal and storage device | |
| CN111241615A (en) | Highly realistic multi-source fusion three-dimensional modeling method for transformer substation | |
| CN109829973A (en) | A kind of three-dimension visible sysem based on light application | |
| CN115082254A (en) | Lean control digital twin system of transformer substation | |
| CN103716399A (en) | Remote interaction fruit picking cooperative asynchronous control system and method based on wireless network | |
| CN111915723A (en) | Indoor three-dimensional panorama construction method and system | |
| CN107179069A (en) | Satellite sun windsurfing flexible movement parameter measuring apparatus and method based on binocular stereo vision | |
| CN113099242A (en) | Power transmission line video monitoring data processing method and system | |
| CN113959332B (en) | Large aerostat volume real-time monitoring system based on binocular vision | |
| CN110702015B (en) | Method and device for measuring icing thickness of power transmission line | |
| CN116704046B (en) | Cross-mirror image matching method and device | |
| CN115761142B (en) | High-performance live-action modeling method based on multi-GPU cooperation | |
| CN107274449B (en) | Space positioning system and method for object by optical photo | |
| CN116205561A (en) | Material management method and system based on digital twinning | |
| CN115731345A (en) | Human body three-dimensional reconstruction method based on binocular vision | |
| Ma et al. | Multi-robot collaborative SLAM and scene reconstruction based on RGB-D camera | |
| CN109472862A (en) | A kind of substation's 3 d modeling system | |
| CN115035252A (en) | Three-dimensional reconstruction method and device for gas plant station based on nerve radiation field | |
| CN113971721A (en) | Lightweight characterization method for digital twins of substation equipment | |
| Meng et al. | Transmission Line Sag Measurement Algorithm Based on Binocular Vision 3D Reconstruction | |
| CN110850235A (en) | Multi-terminal positioning algorithm and positioning system based on cable topology and fault transient traveling wave |
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 |