CN110262546A - A kind of tunnel intelligent unmanned plane cruising inspection system and method - Google Patents
A kind of tunnel intelligent unmanned plane cruising inspection system and method Download PDFInfo
- Publication number
- CN110262546A CN110262546A CN201910526199.4A CN201910526199A CN110262546A CN 110262546 A CN110262546 A CN 110262546A CN 201910526199 A CN201910526199 A CN 201910526199A CN 110262546 A CN110262546 A CN 110262546A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- tunnel
- point
- camera
- monocular
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007689 inspection Methods 0.000 title claims abstract description 26
- 238000005259 measurement Methods 0.000 claims abstract description 40
- 230000005484 gravity Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 4
- 241000184339 Nemophila maculata Species 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 4
- 230000004927 fusion Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 241000238631 Hexapoda Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of tunnel intelligent unmanned plane cruising inspection system and methods, and by combining unmanned air vehicle technique, image processing techniques, unmanned plane is applied in the inspection work in tunnel.The present invention is added to multiple sensors on the platform of unmanned plane, the data acquired using monocular black and white camera and Inertial Measurement Unit IMU, nomography is built according to VINS-Mono positioning, the accurate positioning navigation to unmanned plane in tunnel is realized by the way of Fusion simultaneously, point cloud data is acquired using two-dimensional laser radar, realize the estimation and unmanned plane avoidance to tunnel metope direction, tunnel image is acquired using high resolution camera simultaneously, restore camera motion track by SfM algorithm, the threedimensional model in tunnel is generated in conjunction with high-definition image, careful tunnel patrol task is realized with this.Personnel are relied on and vehicle carries out the mode of tunnel inspection relative to traditional, and high degree of automation of the present invention, work efficiency is high, can widely apply in tunnel inspection work.
Description
Technical field
The invention belongs to image procossing and air vehicle technique field, it is related to a kind of unmanned plane cruising inspection system and method, specifically
It is related to the autonomous positioning of unmanned plane under a kind of tunnel environment, ambient enviroment perception, unmanned plane path planning and avoidance, image three-dimensional
Reconstructing system and method.
Background technique
In recent years, with the continuous development in China, the horizontal annual rapid growth of domestic economy and overall national strength are constantly promoted,
The constructive ability of all kinds of infrastructure has obtained great promotion.With port Zhuhai and Macao bridge immersed tube tunnel, the Changjiang river San Yanglu, Wuhan
A series of completion of large tunnel engineerings such as tunnel, Qinghai-Tibet Railway Guanjiao Tunnel, China has become tunnel in the world and underground
Project scale is maximum, various geologic structure is the most complicated, all kinds of builds technology country with fastest developing speed.However, with the time
Passage, geologic change, traffic accident collide, and a variety of factors such as corrosion and damage and insect pest can all cause the shadow of obstructed degree to tunnel
It rings.Slight influence can cause tunnel surface crack, and serious influence then may result in the change of the Tunnel bodily form or even section hole
Plane materiel material is fallen.Tunnel maintenance personnel must have found immediately and effectively safeguard to prevent harm.Tunnel inspection
It is the indispensable important link for increasing tunnel life cycle.However conventional tunnel inspection relies on personnel and vehicle patrols
It looks into, not only takes time and effort, but also personnel cost and the cost of overhaul are also very high.The method of any poor efficiency, at home public affairs up to ten thousand
In tunnel overhaul in face of can all be amplified tens million of times, cause greatly waste and loss.
With being constantly progressive for unmanned air vehicle technique, the strong flexibility of manipulation and its high scalability of function are gradually by big
Crowd's favor is carried out inspection in tunnel using unmanned plane and has become possibility.Various kinds of sensors is carried, unmanned plane being capable of sense of autonomy
Know all kinds of tunnel environments, autonomous positioning and cruise are realized in tunnel.Only a small amount of personnel is needed to operate, unmanned plane can be certainly
The tunnel of main completion long range is patrolled.In addition, having benefited from the small size advantage of unmanned plane, in many inconvenient personnel's disengaging
Tunnel, such as large-sized launching road environment, unmanned plane can effectively increase the efficiency of inspection work.
However, tunnel internal environment it is extremely complex with it is severe, for unmanned machine operation, there are great challenges for this.Tunnel internal
Cause GPS signal that can not penetrate due to blocking, the common commercial unmanned plane system for relying on GPS signal and carrying out UAV position and orientation estimation
System can not all fly in tunnel.In addition, the electrical system of subway tunnel and near tunnel containing magnetosphere etc. factor,
It will lead to the magnetic field acute variation in the different sections in tunnel, unmanned plane can not calibrating direction.Also, the space structure in tunnel
Relatively common unmanned plane during flying scene, such as outdoor, all more narrow, when unmanned plane during flying, is easy by metope rebound air-flow
Interference, severe jamming unmanned plane from steady, may cause air crash when serious.It can be under tunnel environment therefore, it is necessary to design one
Stablize the Intelligent unattended machine cruising inspection system and method for cruise.
Summary of the invention
The purpose of the present invention is to provide a kind of tunnel intelligent unmanned plane cruising inspection system and methods, for replacing current people
Work tunnel inspection work, reduces human cost, improves operating efficiency.
Technical solution used by system of the invention is: a kind of tunnel intelligent unmanned plane cruising inspection system, it is characterised in that:
Including unmanned plane, flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, list
Dot laser rangefinder, barometer, two-dimensional laser radar and lighting apparatus；
The flight controller is for controlling taking off, move, landing for the unmanned plane；
The airborne computer, monocular black and white camera, Inertial Measurement Unit IMU are connect with the flight controller respectively,
For computation vision inertial navigation odometer, location navigation is carried out to unmanned plane itself；
The single-point laser rangefinder, barometer are connect with the flight controller respectively, for unmanned plane during flying height
Stabilized flight is realized in the measurement of degree；
The two-dimensional laser radar is connected with the airborne computer, for perceiving to tunnel ambient enviroment, is realized
Effectively avoidance, the estimation in tunnel complications direction and real-time routes are adjusted；
The lighting device is powered by the battery of unmanned plane for providing stable light environment for tunnel, is mounted on nothing
Man-machine front end of rack；
The high resolution camera is connected with the airborne computer, high-resolution image is acquired, for dense
Three-dimensional reconstruction；
The flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera,
Single-point laser rangefinder, barometer, two-dimensional laser radar are fixedly mounted on sensor rack, and the rack fixation is set
It sets above the rack of the unmanned plane.
Preferably, the flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high score
Resolution camera, single-point laser rangefinder, barometer, two-dimensional laser radar are fixedly mounted on sensor rack, the biography
Sensor rack passes through to flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high-resolution phase
Machine, single-point laser rangefinder, barometer, two-dimensional laser radar and the asymmetric layout of unmanned machine battery are placed, so that unmanned plane
Center of gravity be maintained at the geometric center of unmanned plane.
Technical solution used by method of the invention is: a kind of tunnel intelligent unmanned plane method for inspecting, which is characterized in that
The following steps are included:
Step 1: with monocular black and white camera and Inertial Measurement Unit IMU computation vision odometer, in combination with two-dimensional laser
Radar, single-point laser rangefinder, barometrical data realize positioning of the unmanned plane in tunnel and accurately navigation flight；
Step 2: tunnel being perceived using two-dimensional laser radar, including tunnel metope is estimated, obtains nobody
Barrier around the course angle that machine advances, and perception carries out unmanned plane avoidance；
Step 3: stable light environment is provided for tunnel using lighting device, by high resolution camera acquisition tunnel
Image, while restoring the motion profile of camera, in conjunction with the image that high resolution camera is shot, carry out the three-dimensional reconstruction in tunnel；
Step 4: in conjunction with GPS signal and two-dimensional laser radar, judging whether unmanned plane passes through tunnel；
If being landed using GPS signal level point of flying to, otherwise being continued according to tunnel metope direction forward by tunnel
Flight.
Preferably, airborne computer passes through the number of processing monocular black and white camera and Inertial Measurement Unit IMU in step 1
According to utilizing VINS-Mono algorithm computation vision inertia odometer to realize positioning of the unmanned plane in tunnel；
If monocular black and white camera acquired image is caused to can't detect characteristic point due to environmental factor, switching makes
The information acquired with two-dimensional laser radar guarantees unmanned plane by calculating distance of the unmanned plane apart from tunnel or so both walls face
It flies at center between two metopes of left and right；Meanwhile when can detect characteristic point in the image of monocular black and white camera shooting, weight
New initialization vision inertia odometer, is switched back into and is positioned using vision inertia odometer；
The elevation information of unmanned plane combines offer by single-point laser rangefinder and barometer.
Preferably, described realize unmanned plane in tunnel using VINS-Mono algorithm computation vision inertia odometer
Positioning；
The monocular position and orientation estimation method for using pure vision first, by initial several picture frames, in a micro-slip
Restore initial picture frame pose and three-dimensional point coordinate in window, completes to initialize the pose of unmanned plane；
Then by vision estimate result is aligned with the value of Inertial Measurement Unit IMU pre-integration, realize to gyroscope
The correction of biasing solves gravity vector direction, and restores the scale factor of monocular black and white camera, obtains monocular black and white camera and is used to
Property measuring unit IMU the constraint relationship, one or two of coordinate system of uniting, by monocular black and white camera coordinate system and Inertial Measurement Unit IMU
After coordinate system is aligned, all calculating on the image will be made using Inertial Measurement Unit IMU coordinate system as body coordinate system
There is consistent transformation after all coordinate conversions；
Monocular black and white camera pose and three-dimensional feature point are solved most finally by characteristic point re-projection error is minimized
Excellent estimation, meanwhile, it introduces the estimation of Inertial Measurement Unit IMU data numeral in line appearance and compensates, obtain better estimation effect.
Preferably, the monocular position and orientation estimation method using pure vision, by initial several picture frames, at one
Restore initial picture frame pose and three-dimensional point coordinate in micro-slip window, completes to initialize the pose of unmanned plane；
Firstly, traversing to frames all in sliding window, while Harris Corner Detection is carried out, the angle point detected is i.e.
For key point, selects and present frame has the picture frame of enough common keypoints and larger parallax as key frame, use later
LK optical flow method carries out angle point tracking, restores the basis matrix of the key frame and present frame using five-spot, restores this two interframe
Rotation and translation matrix, and trigonometric ratio restores the depth of viewpoint altogether；
Then the posture information and three-dimensional feature point information of remaining frame in sliding window are solved using the method for PNP；
Finally, carrying out minimum re-projection error using the BA method of part to characteristic points all in sliding window, obtaining
Camera pose and three-dimensional feature point after optimization complete the monocular pose estimation of pure vision.
Preferably, being acquired using two-dimensional laser radar to unmanned plane ambient enviroment, in step 2 to collected
Point cloud information is filtered, and is estimated using point cloud of the RANSAC algorithm to the right and left respectively later, is fitted current tunnel
The course of unmanned plane is modified in the direction of road metope, meanwhile, by the point cloud cluster information between metope, local cost map is established, it is real
The dynamic obstacle avoidance of existing unmanned plane.
Preferably, restoring the motion profile of camera by the SfM algorithm of increment type, in conjunction with high-resolution phase in step 3
The image of machine shooting carries out the three-dimensional reconstruction in tunnel by PMVS algorithm and TexRecon algorithm.
Tunnel intelligent unmanned plane cruising inspection system of the present invention, the effect completed is: unmanned plane is according to monocular black and white
The data of camera and Inertial Measurement Unit IMU acquisition, computation vision inertia odometer, in combination with other sensors data, into
The location navigation of row unmanned plane itself realizes the estimation to tunnel metope direction by two-dimensional laser radar in flight course
With the avoidance of unmanned plane, meanwhile, using lighting apparatus auxiliary high resolution camera shooting tunnel interior walls high-definition image, in conjunction with
The motion profile of camera carries out three-dimensional modeling, realizes and acquires to the data in tunnel, is convenient for subsequent detection.The present invention is by combining nothing
Unmanned plane is applied in tunnel inspection work, using multiple sensors, using VINS- by man-machine technology and image processing techniques
Nomography, RANSAC algorithm, SfM algorithm are built in Mono positioning, realize that stabilized flight and three-dimensional of the unmanned plane under tunnel environment are built
Mould.Personnel are relied on and vehicle carries out the mode of tunnel inspection relative to traditional, high degree of automation of the present invention, working efficiency
Height can widely apply in tunnel inspection work.
Detailed description of the invention
Fig. 1 is the system module schematic diagram of the embodiment of the present invention；
Fig. 2 is sensor rack schematic diagram in the embodiment of the present invention；
Fig. 3 is the method flow diagram of the embodiment of the present invention；
Fig. 4 is unmanned plane location algorithm frame diagram in the embodiment of the present invention；
Fig. 5 is that the monocular pose of vision in the embodiment of the present invention estimates flow chart；
Fig. 6 is vision and IMU alignment of data effect picture in the embodiment of the present invention；
Fig. 7 is the schematic diagram that RANSAC fitting a straight line is utilized in the embodiment of the present invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and embodiments to this hair
It is bright to be described in further detail, it should be understood that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
Referring to Fig.1, a kind of tunnel intelligent unmanned plane cruising inspection system provided by the invention, including unmanned plane, flight controller,
Airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point laser rangefinder, barometer, two
Tie up laser radar and lighting apparatus；
Flight controller is for controlling taking off, move, landing for unmanned plane；
Airborne computer, monocular black and white camera, Inertial Measurement Unit IMU are connect with flight controller respectively, for calculating
Vision inertial navigation odometer carries out location navigation to unmanned plane itself；
Single-point laser rangefinder, barometer are connect with flight controller respectively, for the measurement to drone flying height,
Realize stabilized flight；
Two-dimensional laser radar is connected with airborne computer, and for perceiving to tunnel ambient enviroment, realization is effectively kept away
Barrier adjusts the estimation in tunnel complications direction and real-time routes；
Lighting device is powered by the battery of unmanned plane for providing stable light environment for tunnel, is mounted on unmanned plane
Front end of rack；
High resolution camera is connected with airborne computer, acquires high-resolution image, for dense three-dimensional reconstruction；
Flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point
Laser range finder, barometer, two-dimensional laser radar are fixedly mounted on sensor rack, and rack is fixed at nobody
Above the rack of machine.
The unmanned plane of the present embodiment is using big 100 quadrotor drone of boundary Matrice.
See Fig. 2, the flight controller of the present embodiment, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera,
High resolution camera, single-point laser rangefinder, barometer, two-dimensional laser radar are fixedly mounted on sensor rack, are passed
Sensor rack passes through to flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high-resolution phase
Machine, single-point laser rangefinder, barometer, two-dimensional laser radar and the asymmetric layout of unmanned machine battery are placed, so that unmanned plane
Center of gravity be maintained at the geometric center of unmanned plane.
See Fig. 3, a kind of tunnel intelligent unmanned plane method for inspecting provided by the invention, comprising the following steps:
Step 1: with monocular black and white camera and Inertial Measurement Unit IMU computation vision odometer, in combination with two-dimensional laser
Radar, single-point laser rangefinder, barometrical data realize positioning of the unmanned plane in tunnel and accurately navigation flight；
The step be mainly utilize monocular black and white camera acquisition ambient enviroment image, by airborne computer extract and with
Characteristic point in track image, in conjunction with Inertial Measurement Unit IMU, using VINS-Mono algorithm computation vision inertia odometer, simultaneously
The data for merging multiple sensors guarantee unmanned plane because the other factors such as fugitive dust cause monocular vision to fail
Can stable position navigation, algorithm frame is as shown in Figure 4.
The step uses the monocular position and orientation estimation method of pure vision first, by initial several picture frames, in an office
Restore initial picture frame pose and three-dimensional point coordinate in portion's sliding window, completes to initialize the pose of unmanned plane, it is specific to walk
It is rapid as shown in Figure 5.Firstly, traversing to frames all in sliding window, while Harris Corner Detection is carried out, the angle detected
Point is key point, selects and present frame has the picture frame of enough common keypoints and larger parallax as key frame, later
Angle point tracking is carried out using LK optical flow method, restores the basis matrix of the key frame and present frame using five-spot, restores this two frame
Between rotation and translation matrix, and trigonometric ratio restore altogether viewpoint depth.Then using PNP method solve sliding window in its
The posture information and three-dimensional feature point information of remaining frame.In order to keep the pose of estimation more accurate, using the BA method of part, to cunning
All characteristic points carry out minimum re-projection error in dynamic window, and camera pose and three-dimensional feature point after being optimized are completed
The monocular pose of pure vision is estimated.Later, since the absolute measure of pose is unable to estimate in the pose estimation of pure vision, vision is estimated
Count result is aligned the correction, it can be achieved that offset of gyroscope with the value of Inertial Measurement Unit IMU pre-integration, solve gravity
Vector direction, and restore the scale factor of monocular camera, obtain the constraint relationship of camera and Inertial Measurement Unit IMU, unification two
A coordinate system, as shown in Figure 6.After camera coordinates system and Inertial Measurement Unit IMU coordinate system are aligned, later on the image
All calculating will have after converting all coordinates consistent using Inertial Measurement Unit IMU coordinate system as body coordinate system
Transformation.Then, the optimal estimation of camera pose and three-dimensional feature point is solved by minimizing characteristic point re-projection error, together
When, it introduces the estimation of Inertial Measurement Unit IMU data numeral in line appearance and compensates, obtain better estimation effect；
If monocular black and white camera acquired image can't detect characteristic point, switches adopted using two-dimensional laser radar immediately
The information of collection guarantees unmanned plane between two metopes of left and right by calculating distance of the unmanned plane apart from tunnel or so both walls face
It flies at center, meanwhile, when can detecte characteristic point in the image of monocular black and white camera shooting, it is used to reinitialize vision
Property odometer, switch back into using vision inertia odometer position；
Since tunnel inner wall surface structure is simple, existing characteristic point is less, and the large wind that unmanned plane rotor generates can
The dust on ground can be blown afloat, the image for causing monocular camera to shoot is more fuzzy, can't detect characteristic point, monocular vision letter
Breath failure, VINS-Mono algorithm can not just work.At this point it is possible to switch the information acquired using two-dimensional laser radar, pass through meter
Distance of the unmanned plane apart from tunnel or so both walls face is calculated, guarantees that unmanned plane flies at the center between two metopes of left and right, in this way,
Unmanned plane will not knock tunnel metope because of the drift positioned oneself, can be with temporary stabilization unmanned plane using two-dimensional laser radar
Flight, until monocular vision is re-effective, again initialize vision inertia odometer, switch back into using vision inertia mileage
Meter positioning, guarantees the stabilization of whole system；
The elevation information of unmanned plane combines offer by single-point laser rangefinder and barometer, when unmanned plane stabilized flight,
The elevation information of single-point laser stadia surveying is usually accurate, but works as and encounter certain special circumstances, such as unmanned plane top
It winnows with a dustpan, the variation of single-point laser radar is excessively violent, and stable compensation is done using barometrical data.
Step 2: tunnel being perceived using two-dimensional laser radar, including tunnel metope is estimated, obtains nobody
Barrier around the course angle that machine advances, and perception carries out unmanned plane avoidance；
The step mainly utilizes two-dimensional laser radar to realize that the laser that the radar may be implemented 360 ° in two-dimensional surface is swept
It penetrates, using the radar, the point cloud chart of available unmanned plane ambient enviroment is available by carrying out relevant treatment to point cloud chart
The direction of tunnel metope and the obstacle information around unmanned plane.It specifically includes:
Step 2.1: using two-dimensional laser radar acquisition unmanned plane around point cloud data, utilize " passing through filter " and
" circular filter " is filtered collected point cloud data.
Step 2.2: being two parts in left and right by filtered cloud cutting in step 2.1, respectively correspond tunnel or so two
The metope point cloud information on side fits one in the point cloud of the right and left respectively using random consistent sampling property (RANSAC) algorithm
Straight line determines the course angle of unmanned plane with this by the orientation angle of the available current tunnel metope of the straight line of fitting.
In the effect picture using RANSAC algorithm fitting a straight line as shown in fig. 7, left side is actual tunnel figure in figure, right side is
The point cloud chart picture of tunnel two sides metope.During fitting a straight line, if less than one definite value of angle of two straight lines in left and right
And the distance between be greater than a threshold value, it may be considered that successfully having estimated the direction of advance of current tunnel.Meanwhile it can be with
Unmanned plane is calculated to the distance in left and right face, unmanned plane can be determined with a distance from tunnel center of gravity, and to the position of unmanned plane
Real-time perfoming correction.
Step 2.3: unmanned plane avoidance passes through what is carried in ROS operating system by point cloud information filtered in step 2.1
Function constructs local cost map, generates avoidance route.
Step 3: stable light environment is provided for tunnel using lighting device, by high resolution camera acquisition tunnel
Image, while being led to by the motion profile of the SfM algorithm of increment type recovery camera in conjunction with the image that high resolution camera is shot
It crosses PMVS algorithm and TexRecon algorithm carries out the three-dimensional reconstruction in tunnel；
In the step, is powered by the battery of unmanned plane, use the LED light array of 6*8 as lighting device, illuminate unmanned plane
Metope within the scope of 10 meters of front acquires tunnel under current location by the high resolution camera that resolution ratio is 2440*2048 later
The image of metope.After collecting image, exercise recovery structure (Structure from Motion, SfM) algorithm is used first,
The algorithm restores the motion profile of camera using acquired image, while according to the Feature Points Matching between image to next life
At sparse scene point cloud.PMVS algorithm is used later, it is thick to obtain according to input picture and the camera motion track recovered
Close scene three-dimensional point cloud.Finally, realizing that resurfacing and texture reflect using the TexRecon algorithm provided in MVE open source library
It penetrates, converts dense point cloud to the wire side of triangle gridding composition, the texture being subsequently filled in correspondence image.
Step 4: in conjunction with GPS signal and two-dimensional laser radar, judging whether unmanned plane passes through tunnel；
If being landed using GPS signal level point of flying to, otherwise being continued according to tunnel metope direction forward by tunnel
Flight.
The step perceives the distance of unmanned plane the right and left metope using two-dimensional laser radar, if metope distance occurs to dash forward
Become, and unmanned plane can receive GPS signal, then judge that unmanned plane has flown out tunnel, can use GPS signal and returns to setting
Level point.
In conclusion a kind of tunnel intelligent unmanned plane cruising inspection system of the present invention, mainly passes through monocular black and white phase
The data of machine and Inertial Measurement Unit IMU acquisition build nomography according to VINS-Mono positioning, while using multi-sensor data
The mode of fusion is realized to the accurate positioning navigation of unmanned plane in tunnel, acquires point cloud data using two-dimensional laser radar later,
Realize the estimation and unmanned plane avoidance to tunnel metope direction.Meanwhile under the auxiliary of lighting device, high resolution camera is utilized
Tunnel image is acquired, camera motion track is restored by SfM algorithm, the three-dimensional mould in tunnel is generated in conjunction with high-definition image
Type realizes careful tunnel patrol task with this, finally combines GPS signal and two-dimensional laser radar, determines that unmanned plane passes through tunnel
Flight to preset is landed behind road.The present invention is applied to tunnel by combining unmanned air vehicle technique and image processing techniques, by unmanned plane
In road inspection work, using multiple sensors, nomography, RANSAC algorithm, SfM algorithm are built using same VINS-Mono positioning, it is real
Existing stabilized flight and three-dimensional modeling of the unmanned plane under tunnel environment.Tunnel is carried out relative to traditional dependence personnel and vehicle to patrol
The mode of inspection, high degree of automation of the present invention, work efficiency is high, can widely apply in tunnel inspection work.
It should be understood that the part that this specification does not elaborate belongs to the prior art.
It should be understood that the above-mentioned description for preferred embodiment is more detailed, can not therefore be considered to this
The limitation of invention patent protection range, those skilled in the art under the inspiration of the present invention, are not departing from power of the present invention
Benefit requires to make replacement or deformation under protected ambit, fall within the scope of protection of the present invention, this hair
It is bright range is claimed to be determined by the appended claims.
Claims (8)
1. a kind of tunnel intelligent unmanned plane cruising inspection system, it is characterised in that: including unmanned plane, flight controller, airborne computer,
Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point laser rangefinder, barometer, two-dimensional laser radar
And lighting apparatus；
The flight controller is for controlling taking off, move, landing for the unmanned plane；
The airborne computer, monocular black and white camera, Inertial Measurement Unit IMU are connect with the flight controller respectively, are used for
Computation vision inertial navigation odometer carries out location navigation to unmanned plane itself；
The single-point laser rangefinder, barometer are connect with the flight controller respectively, for drone flying height
Stabilized flight is realized in measurement；
The two-dimensional laser radar is connected with the airborne computer, for perceiving to tunnel ambient enviroment, is realized effective
Ground avoidance adjusts the estimation in tunnel complications direction and real-time routes；
The lighting device is powered by the battery of unmanned plane for providing stable light environment for tunnel, is mounted on unmanned plane
Front end of rack；
The high resolution camera is connected with the airborne computer, acquires high-resolution image, for dense three-dimensional
It rebuilds；
The flight controller, airborne computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point
Laser range finder, barometer, two-dimensional laser radar are fixedly mounted on sensor rack, and the rack is fixed at
Above the rack of the unmanned plane.
2. tunnel intelligent unmanned plane cruising inspection system according to claim 1, it is characterised in that: the flight controller, machine
Carry computer, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point laser rangefinder, barometer, two dimension
Laser radar is fixedly mounted on sensor rack, and the sensor rack passes through to flight controller, airborne calculating
Machine, Inertial Measurement Unit IMU, monocular black and white camera, high resolution camera, single-point laser rangefinder, barometer, two-dimensional laser thunder
It is placed up to the asymmetric layout of unmanned machine battery, so that the center of gravity of unmanned plane is maintained at the geometric center of unmanned plane.
3. a kind of tunnel intelligent unmanned plane method for inspecting, which comprises the following steps:
Step 1: with monocular black and white camera and Inertial Measurement Unit IMU computation vision odometer, in combination with two-dimensional laser radar,
Single-point laser rangefinder, barometrical data realize positioning of the unmanned plane in tunnel and accurately navigation flight；
Step 2: tunnel being perceived using two-dimensional laser radar, including tunnel metope is estimated, before obtaining unmanned plane
Into course angle, and perception around barrier, carry out unmanned plane avoidance；
Step 3: stable light environment is provided for tunnel using lighting device, by the shadow in high resolution camera acquisition tunnel
Picture, while restoring the motion profile of camera, in conjunction with the image that high resolution camera is shot, carry out the three-dimensional reconstruction in tunnel；
Step 4: in conjunction with GPS signal and two-dimensional laser radar, judging whether unmanned plane passes through tunnel；
If being landed using GPS signal level point of flying to, otherwise continuing to fly forward according to tunnel metope direction by tunnel
Row.
4. tunnel intelligent unmanned plane method for inspecting according to claim 3, it is characterised in that: in step 1, airborne computer
By handling the data of monocular black and white camera and Inertial Measurement Unit IMU, VINS-Mono algorithm computation vision inertia mileage is utilized
Meter realizes positioning of the unmanned plane in tunnel；
If monocular black and white camera acquired image is caused to can't detect characteristic point due to environmental factor, switch using two
The information for tieing up laser radar acquisition guarantees unmanned plane on a left side by calculating distance of the unmanned plane apart from tunnel or so both walls face
It flies at center between right two metopes；Meanwhile when can detect characteristic point in the image of monocular black and white camera shooting, again just
Beginningization vision inertia odometer is switched back into and is positioned using vision inertia odometer；
The elevation information of unmanned plane combines offer by single-point laser rangefinder and barometer.
5. tunnel intelligent unmanned plane method for inspecting according to claim 4, it is characterised in that: described to utilize VINS-Mono
Algorithm computation vision inertia odometer realizes positioning of the unmanned plane in tunnel；
The monocular position and orientation estimation method for using pure vision first, by initial several picture frames, in a micro-slip window
It is middle to restore initial picture frame pose and three-dimensional point coordinate, it completes to initialize the pose of unmanned plane；
Then by vision estimate result is aligned with the value of Inertial Measurement Unit IMU pre-integration, realize to offset of gyroscope
Correction, solve gravity vector direction, and restore the scale factor of monocular black and white camera, obtain monocular black and white camera and inertia is surveyed
The constraint relationship of unit IMU is measured, one or two of coordinate system of uniting, by monocular black and white camera coordinate system and Inertial Measurement Unit IMU coordinate
After system is aligned, all calculating on the image will make to own using Inertial Measurement Unit IMU coordinate system as body coordinate system
There is consistent transformation after coordinate conversion；
Optimal the estimating of monocular black and white camera pose and three-dimensional feature point is solved finally by characteristic point re-projection error is minimized
Meter, meanwhile, it introduces the estimation of Inertial Measurement Unit IMU data numeral in line appearance and compensates, obtain better estimation effect.
6. tunnel intelligent unmanned plane method for inspecting according to claim 5, it is characterised in that: the list using pure vision
Mesh position and orientation estimation method restores initial picture frame pose by initial several picture frames in a micro-slip window
And three-dimensional point coordinate, it completes to initialize the pose of unmanned plane；
Firstly, traversing to frames all in sliding window, while Harris Corner Detection is carried out, the angle point detected is to close
Key point, selects and present frame has the picture frame of enough common keypoints and larger parallax as key frame, uses LK light later
Stream method carries out angle point tracking, restores the basis matrix of the key frame and present frame using five-spot, restores the rotation of this two interframe
And translation matrix, and trigonometric ratio restores the depth of viewpoint altogether；
Then the posture information and three-dimensional feature point information of remaining frame in sliding window are solved using the method for PNP；
Finally, carrying out minimum re-projection error using the BA method of part to characteristic points all in sliding window, being optimized
Camera pose and three-dimensional feature point afterwards complete the monocular pose estimation of pure vision.
7. tunnel intelligent unmanned plane method for inspecting according to claim 3, it is characterised in that: in step 2, swashed using two dimension
Optical radar is acquired unmanned plane ambient enviroment, is filtered to collected point cloud information, utilizes RANSAC algorithm later
The point cloud of the right and left is estimated respectively, fits the direction of current tunnel metope, modifies the course of unmanned plane, is led to simultaneously
The point cloud cluster information between metope is crossed, local cost map is established, realizes the dynamic obstacle avoidance of unmanned plane.
8. tunnel intelligent unmanned plane method for inspecting according to claim 3, it is characterised in that: in step 3, pass through increment type
SfM algorithm restore the motion profile of camera, in conjunction with the image that high resolution camera is shot, by PMVS algorithm and
The three-dimensional reconstruction in TexRecon algorithm progress tunnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526199.4A CN110262546B (en) | 2019-06-18 | 2019-06-18 | Tunnel intelligent unmanned aerial vehicle inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526199.4A CN110262546B (en) | 2019-06-18 | 2019-06-18 | Tunnel intelligent unmanned aerial vehicle inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110262546A true CN110262546A (en) | 2019-09-20 |
| CN110262546B CN110262546B (en) | 2021-07-20 |
Family
ID=67918923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910526199.4A Expired - Fee Related CN110262546B (en) | 2019-06-18 | 2019-06-18 | Tunnel intelligent unmanned aerial vehicle inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262546B (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110514133A (en) * | 2019-09-30 | 2019-11-29 | 西南石油大学 | It is a kind of based on photogrammetric unmanned plane tunnel deformation detection method |
| CN110687919A (en) * | 2019-10-21 | 2020-01-14 | 同济大学 | Unmanned aerial vehicle autonomous flight control method for hydropower station water pipeline inspection |
| CN110717927A (en) * | 2019-10-10 | 2020-01-21 | 桂林电子科技大学 | Indoor robot motion estimation method based on deep learning and visual inertial fusion |
| CN110728288A (en) * | 2019-10-12 | 2020-01-24 | 上海高仙自动化科技发展有限公司 | Corner feature extraction method based on three-dimensional laser point cloud and application thereof |
| CN110825111A (en) * | 2019-11-15 | 2020-02-21 | 天津光电通信技术有限公司 | Unmanned aerial vehicle control method suitable for overhead warehouse goods inventory, goods inventory method, device, server and storage medium |
| CN110823225A (en) * | 2019-10-29 | 2020-02-21 | 北京影谱科技股份有限公司 | Positioning method and device under indoor dynamic situation |
| CN111426326A (en) * | 2020-01-17 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Navigation method, device, equipment, system and storage medium |
| CN111735445A (en) * | 2020-06-23 | 2020-10-02 | 煤炭科学研究总院 | Monocular vision and IMU (inertial measurement Unit) integrated coal mine tunnel inspection robot system and navigation method |
| CN111854756A (en) * | 2020-06-30 | 2020-10-30 | 同济大学 | Single line laser-based unmanned aerial vehicle positioning method in diversion culvert |
| CN112130579A (en) * | 2020-09-24 | 2020-12-25 | 国网智能科技股份有限公司 | Tunnel unmanned aerial vehicle inspection method and system |
| CN112254721A (en) * | 2020-11-06 | 2021-01-22 | 南京大学 | Attitude positioning method based on optical flow camera |
| CN112347840A (en) * | 2020-08-25 | 2021-02-09 | 天津大学 | Vision sensor laser radar integrated unmanned aerial vehicle positioning and image building device and method |
| CN112596071A (en) * | 2020-11-02 | 2021-04-02 | 中国兵器工业计算机应用技术研究所 | Unmanned aerial vehicle autonomous positioning method and device and unmanned aerial vehicle |
| CN113138594A (en) * | 2020-01-20 | 2021-07-20 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
| WO2021147546A1 (en) * | 2020-01-20 | 2021-07-29 | 深圳市普渡科技有限公司 | Multi-sensor fusion slam system, multi-sensor fusion method, robot, and medium |
| CN113359810A (en) * | 2021-07-29 | 2021-09-07 | 东北大学 | Unmanned aerial vehicle landing area identification method based on multiple sensors |
| CN113359862A (en) * | 2021-07-28 | 2021-09-07 | 北京理工大学 | Control method and device for unmanned aerial vehicle to enter closed environment |
| CN113390435A (en) * | 2021-05-13 | 2021-09-14 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113532283A (en) * | 2021-07-14 | 2021-10-22 | 中建八局南方建设有限公司 | Method for monitoring foundation pit displacement trend based on consumption-level unmanned aerial vehicle and GPS (global positioning system) |
| CN113721260A (en) * | 2021-08-26 | 2021-11-30 | 南京邮电大学 | Online combined calibration method for laser radar, binocular camera and inertial navigation |
| CN113791643A (en) * | 2021-10-15 | 2021-12-14 | 杭州云之盟科技有限公司 | Course angle correction method and device for indoor inspection multi-rotor unmanned aerial vehicle and storage medium |
| CN113820709A (en) * | 2021-11-25 | 2021-12-21 | 湖南华诺星空电子技术有限公司 | Through-wall radar detection system and detection method based on unmanned aerial vehicle |
| CN113819905A (en) * | 2020-06-19 | 2021-12-21 | 北京图森未来科技有限公司 | Multi-sensor fusion-based odometer method and device |
| CN113985910A (en) * | 2021-09-09 | 2022-01-28 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN114755693A (en) * | 2022-06-15 | 2022-07-15 | 天津大学四川创新研究院 | Infrastructure facility measuring system and method based on multi-rotor unmanned aerial vehicle |
| CN114779816A (en) * | 2022-05-17 | 2022-07-22 | 成都工业学院 | Searching and rescuing unmanned aerial vehicle for lifting in earthquake ruin environment and system thereof |
| CN115205997A (en) * | 2022-07-14 | 2022-10-18 | 西安建筑科技大学 | Heating ventilation air conditioner room unmanned inspection system and method based on artificial intelligence |
| CN116148614A (en) * | 2023-04-18 | 2023-05-23 | 江苏明月软件技术股份有限公司 | Cable partial discharge detection system and method based on unmanned mobile carrier |
| CN116539635A (en) * | 2023-05-17 | 2023-08-04 | 广州大学 | Unmanned aerial vehicle shield tunnel inspection method based on calculation vision and SLAM |
| DE202022106442U1 (en) | 2022-11-17 | 2024-02-20 | Herrenknecht Aktiengesellschaft | Tunnel boring machine |
| CN117870652A (en) * | 2024-03-13 | 2024-04-12 | 北京航空航天大学 | Land-air online co-location method based on radar, inertia and vision fusion |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106441286A (en) * | 2016-06-27 | 2017-02-22 | 上海大学 | Unmanned aerial vehicle tunnel inspection system based on BIM technology |
| CN107808133A (en) * | 2017-10-23 | 2018-03-16 | 中石化石油工程地球物理有限公司 | Oil-gas pipeline safety monitoring method, system and software memory based on unmanned plane line walking |
| CN108415453A (en) * | 2018-01-24 | 2018-08-17 | 上海大学 | Unmanned plane tunnel method for inspecting based on BIM technology |
| CN109002057A (en) * | 2018-08-28 | 2018-12-14 | 中北大学 | A kind of intelligent patrol detection UAV system of cable tunnel |
| CN109737951A (en) * | 2019-01-31 | 2019-05-10 | 中科院合肥技术创新工程院 | A kind of navigation system and its air navigation aid of cable duct crusing robot |
| CN109760837A (en) * | 2019-02-21 | 2019-05-17 | 西京学院 | A kind of cable duct and the patrol unmanned machine system in tunnel |
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
| CN109828572A (en) * | 2019-02-20 | 2019-05-31 | 广州供电局有限公司 | Cable tunnel inspection robot and its positioning system based on mark location |
-
2019
- 2019-06-18 CN CN201910526199.4A patent/CN110262546B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106441286A (en) * | 2016-06-27 | 2017-02-22 | 上海大学 | Unmanned aerial vehicle tunnel inspection system based on BIM technology |
| CN107808133A (en) * | 2017-10-23 | 2018-03-16 | 中石化石油工程地球物理有限公司 | Oil-gas pipeline safety monitoring method, system and software memory based on unmanned plane line walking |
| CN108415453A (en) * | 2018-01-24 | 2018-08-17 | 上海大学 | Unmanned plane tunnel method for inspecting based on BIM technology |
| CN109002057A (en) * | 2018-08-28 | 2018-12-14 | 中北大学 | A kind of intelligent patrol detection UAV system of cable tunnel |
| CN109737951A (en) * | 2019-01-31 | 2019-05-10 | 中科院合肥技术创新工程院 | A kind of navigation system and its air navigation aid of cable duct crusing robot |
| CN109828572A (en) * | 2019-02-20 | 2019-05-31 | 广州供电局有限公司 | Cable tunnel inspection robot and its positioning system based on mark location |
| CN109760837A (en) * | 2019-02-21 | 2019-05-17 | 西京学院 | A kind of cable duct and the patrol unmanned machine system in tunnel |
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
Cited By (45)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110514133A (en) * | 2019-09-30 | 2019-11-29 | 西南石油大学 | It is a kind of based on photogrammetric unmanned plane tunnel deformation detection method |
| CN110717927A (en) * | 2019-10-10 | 2020-01-21 | 桂林电子科技大学 | Indoor robot motion estimation method based on deep learning and visual inertial fusion |
| CN110728288A (en) * | 2019-10-12 | 2020-01-24 | 上海高仙自动化科技发展有限公司 | Corner feature extraction method based on three-dimensional laser point cloud and application thereof |
| CN110728288B (en) * | 2019-10-12 | 2022-06-28 | 上海高仙自动化科技发展有限公司 | Corner feature extraction method based on three-dimensional laser point cloud and application thereof |
| CN110687919A (en) * | 2019-10-21 | 2020-01-14 | 同济大学 | Unmanned aerial vehicle autonomous flight control method for hydropower station water pipeline inspection |
| CN110687919B (en) * | 2019-10-21 | 2021-06-04 | 同济大学 | Unmanned aerial vehicle autonomous flight control method for hydropower station water pipeline inspection |
| CN110823225A (en) * | 2019-10-29 | 2020-02-21 | 北京影谱科技股份有限公司 | Positioning method and device under indoor dynamic situation |
| CN110825111A (en) * | 2019-11-15 | 2020-02-21 | 天津光电通信技术有限公司 | Unmanned aerial vehicle control method suitable for overhead warehouse goods inventory, goods inventory method, device, server and storage medium |
| CN111426326A (en) * | 2020-01-17 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Navigation method, device, equipment, system and storage medium |
| CN113138594B (en) * | 2020-01-20 | 2024-04-19 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
| CN113138594A (en) * | 2020-01-20 | 2021-07-20 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
| WO2021147546A1 (en) * | 2020-01-20 | 2021-07-29 | 深圳市普渡科技有限公司 | Multi-sensor fusion slam system, multi-sensor fusion method, robot, and medium |
| CN113819905A (en) * | 2020-06-19 | 2021-12-21 | 北京图森未来科技有限公司 | Multi-sensor fusion-based odometer method and device |
| CN111735445A (en) * | 2020-06-23 | 2020-10-02 | 煤炭科学研究总院 | Monocular vision and IMU (inertial measurement Unit) integrated coal mine tunnel inspection robot system and navigation method |
| CN111735445B (en) * | 2020-06-23 | 2022-02-11 | 煤炭科学研究总院 | Monocular vision and IMU (inertial measurement Unit) integrated coal mine tunnel inspection robot system and navigation method |
| CN111854756A (en) * | 2020-06-30 | 2020-10-30 | 同济大学 | Single line laser-based unmanned aerial vehicle positioning method in diversion culvert |
| CN111854756B (en) * | 2020-06-30 | 2023-08-29 | 同济大学 | Single-line laser-based method for positioning unmanned aerial vehicle in diversion culvert |
| CN112347840B (en) * | 2020-08-25 | 2022-12-02 | 天津大学 | Vision sensor laser radar integrated unmanned aerial vehicle positioning and image building device and method |
| CN112347840A (en) * | 2020-08-25 | 2021-02-09 | 天津大学 | Vision sensor laser radar integrated unmanned aerial vehicle positioning and image building device and method |
| CN112130579A (en) * | 2020-09-24 | 2020-12-25 | 国网智能科技股份有限公司 | Tunnel unmanned aerial vehicle inspection method and system |
| CN112596071A (en) * | 2020-11-02 | 2021-04-02 | 中国兵器工业计算机应用技术研究所 | Unmanned aerial vehicle autonomous positioning method and device and unmanned aerial vehicle |
| CN112254721A (en) * | 2020-11-06 | 2021-01-22 | 南京大学 | Attitude positioning method based on optical flow camera |
| CN113390435B (en) * | 2021-05-13 | 2022-08-26 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113390435A (en) * | 2021-05-13 | 2021-09-14 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113532283A (en) * | 2021-07-14 | 2021-10-22 | 中建八局南方建设有限公司 | Method for monitoring foundation pit displacement trend based on consumption-level unmanned aerial vehicle and GPS (global positioning system) |
| CN113532283B (en) * | 2021-07-14 | 2023-02-28 | 中建八局南方建设有限公司 | Method for monitoring foundation pit displacement trend based on consumption-level unmanned aerial vehicle and GPS (global positioning system) |
| CN113359862A (en) * | 2021-07-28 | 2021-09-07 | 北京理工大学 | Control method and device for unmanned aerial vehicle to enter closed environment |
| CN113359810A (en) * | 2021-07-29 | 2021-09-07 | 东北大学 | Unmanned aerial vehicle landing area identification method based on multiple sensors |
| CN113721260A (en) * | 2021-08-26 | 2021-11-30 | 南京邮电大学 | Online combined calibration method for laser radar, binocular camera and inertial navigation |
| CN113721260B (en) * | 2021-08-26 | 2023-12-12 | 南京邮电大学 | Online combined calibration method for laser radar, binocular camera and inertial navigation |
| CN113985910A (en) * | 2021-09-09 | 2022-01-28 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN113985910B (en) * | 2021-09-09 | 2023-07-18 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN113791643A (en) * | 2021-10-15 | 2021-12-14 | 杭州云之盟科技有限公司 | Course angle correction method and device for indoor inspection multi-rotor unmanned aerial vehicle and storage medium |
| CN113820709A (en) * | 2021-11-25 | 2021-12-21 | 湖南华诺星空电子技术有限公司 | Through-wall radar detection system and detection method based on unmanned aerial vehicle |
| CN113820709B (en) * | 2021-11-25 | 2022-03-15 | 湖南华诺星空电子技术有限公司 | Through-wall radar detection system and detection method based on unmanned aerial vehicle |
| CN114779816A (en) * | 2022-05-17 | 2022-07-22 | 成都工业学院 | Searching and rescuing unmanned aerial vehicle for lifting in earthquake ruin environment and system thereof |
| CN114755693A (en) * | 2022-06-15 | 2022-07-15 | 天津大学四川创新研究院 | Infrastructure facility measuring system and method based on multi-rotor unmanned aerial vehicle |
| CN114755693B (en) * | 2022-06-15 | 2022-09-16 | 天津大学四川创新研究院 | Infrastructure facility measuring system and method based on multi-rotor unmanned aerial vehicle |
| CN115205997A (en) * | 2022-07-14 | 2022-10-18 | 西安建筑科技大学 | Heating ventilation air conditioner room unmanned inspection system and method based on artificial intelligence |
| DE202022106442U1 (en) | 2022-11-17 | 2024-02-20 | Herrenknecht Aktiengesellschaft | Tunnel boring machine |
| WO2024104640A1 (en) | 2022-11-17 | 2024-05-23 | Herrenknecht Aktiengesellschaft | Tunnel boring machine |
| CN116148614A (en) * | 2023-04-18 | 2023-05-23 | 江苏明月软件技术股份有限公司 | Cable partial discharge detection system and method based on unmanned mobile carrier |
| CN116539635A (en) * | 2023-05-17 | 2023-08-04 | 广州大学 | Unmanned aerial vehicle shield tunnel inspection method based on calculation vision and SLAM |
| CN117870652A (en) * | 2024-03-13 | 2024-04-12 | 北京航空航天大学 | Land-air online co-location method based on radar, inertia and vision fusion |
| CN117870652B (en) * | 2024-03-13 | 2024-05-14 | 北京航空航天大学 | Land-air online co-location method based on radar, inertia and vision fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262546B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262546A (en) | A kind of tunnel intelligent unmanned plane cruising inspection system and method | |
| CN111045017B (en) | Method for constructing transformer substation map of inspection robot by fusing laser and vision | |
| KR102001728B1 (en) | Method and system for acquiring three dimentional position coordinates in non-control points using stereo camera drone | |
| CN105865454B (en) | A kind of Navigation of Pilotless Aircraft method generated based on real-time online map | |
| CN103822635B (en) | The unmanned plane during flying spatial location real-time computing technique of view-based access control model information | |
| ES2876449T3 (en) | Multi-sensor environment mapping | |
| CN104217439B (en) | Indoor visual positioning system and method | |
| CN110221603A (en) | A kind of long-distance barrier object detecting method based on the fusion of laser radar multiframe point cloud | |
| CN109579843A (en) | Multirobot co-located and fusion under a kind of vacant lot multi-angle of view build drawing method | |
| CN102190081B (en) | Vision-based fixed point robust control method for airship | |
| CN105203084A (en) | 3D panoramic vision device for unmanned aerial vehicle | |
| CN106443687A (en) | Piggyback mobile surveying and mapping system based on laser radar and panorama camera | |
| CN106384353A (en) | Target positioning method based on RGBD | |
| CN105928493A (en) | Binocular vision three-dimensional mapping system and method based on UAV | |
| CN107807365A (en) | Small-sized digital photography there-dimensional laser scanning device for the unmanned airborne vehicle in low latitude | |
| McLeod et al. | Using video acquired from an unmanned aerial vehicle (UAV) to measure fracture orientation in an open-pit mine | |
| Steiner et al. | A vision-aided inertial navigation system for agile high-speed flight in unmapped environments: Distribution statement a: Approved for public release, distribution unlimited | |
| CN109282808A (en) | Unmanned plane and Multi-sensor Fusion localization method for the detection of bridge Cut-fill | |
| CN107346142A (en) | Flying vehicles control method, light stream module and aircraft | |
| CN109764869A (en) | A kind of positioning of autonomous crusing robot and the three-dimensional map construction method of binocular camera and inertial navigation fusion | |
| CN113189613B (en) | Robot positioning method based on particle filtering | |
| CN110162098A (en) | A kind of mining unmanned plane | |
| CN109801484A (en) | A kind of emergency communication UAV system and emergency communication system | |
| CN114923477A (en) | Multi-dimensional space-ground collaborative map building system and method based on vision and laser SLAM technology | |
| Eisenbeiss et al. | Photogrammetric recording of the archaeological site of Pinchango Alto (Palpa, Peru) using a mini helicopter (UAV) |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210720 |