CN108132675A - Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory - Google Patents
Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory Download PDFInfo
- Publication number
- CN108132675A CN108132675A CN201711177545.XA CN201711177545A CN108132675A CN 108132675 A CN108132675 A CN 108132675A CN 201711177545 A CN201711177545 A CN 201711177545A CN 108132675 A CN108132675 A CN 108132675A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- line
- line segment
- barrier
- factory
- 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 52
- 230000004888 barrier function Effects 0.000 title claims abstract description 50
- 238000007689 inspection Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 7
- 239000004020 conductor Substances 0.000 claims abstract description 6
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims abstract description 5
- 238000002604 ultrasonography Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 238000013461 design Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
Classifications
-
- 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
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of autonomous cruises maked an inspection tour for factory safety and intelligent barrier avoiding method based on rotor wing unmanned aerial vehicle, and ID of trace route path line, and selected sampling area are shot using camera；Canny calculation process is carried out to binaryzation tag line, tag line edge is obtained, uses probability Hough transformation detection image middle conductor；Judge line segment number, if line segment number is 4, detected into quarter bend, otherwise arrival curve detects；Autonomous cruise is carried out according to different testing results；In flight course barrier data are obtained using depth map data, obstacle distance data and ultrasound data；Using the incomplete Artificial Potential Field Method automatic obstacle avoiding based on Follow Wall behaviors.The present invention can use algorithms of different to realize to path trace image procossing according to the true form of tag line；Based on the incomplete Artificial Potential Field Method of Follow Wall behaviors, the deficiency of Artificial Potential Field Method is avoided, along barrier border movement when enabling the unmanned plane encounter barrier, until the predetermined area.
Description
Technical field
The present invention relates to path cruise and intelligent barrier avoiding technical fields, and unmanned plane is maked an inspection tour certainly more particularly to a kind of factory
Main path cruises and intelligent barrier avoiding method.
Background technology
Safety patrol inspection is to ensure the premise that factory normally produces, and qualified reliable inspection tour system is to factory's circuit, equipment
It is the important measures for realizing enterprise information management Deng the means for realizing quantitative management.There are following drawbacks for conventional plant inspection：
Part inspection place and environment is severe, and may personnel be caused with the influences such as body, psychology；Manual inspection information is manually entered, and is existed
The problems such as heavy workload, speed are slow, error-prone, data management is inconvenient；Long-time inspection causes personnel tired out, reduces inspection quality
Deng.
To solve the above problems, the systems such as mobile unmanned plane, security protection patrol unmanned plane, unmanned plane are come into being.The U.S. is public
The security unmanned plane " security guard " of exploitation is taken charge of, is improved on the basis of DJI S-1000+, is added to spare calculating
The external hardwares such as machine, video camera can realize the functions such as intelligent barrier avoiding, autonomous flight.The country is using unmanned plane to rail track
Aerial inspection is carried out, reduces labor intensity.But for inspection in general factory floor room, since GPS signal is poor, by
Autonomous flight Shortcomings are realized in GPS navigation positioning.The present invention carries out path cruise using machine vision, realizes in unmanned plane room
Automatic obstacle avoiding.
Invention content
Above-mentioned in order to solve the problems, such as, the present invention provides a kind of factory and makes an inspection tour unmanned plane from main path cruise and intelligence
Energy barrier-avoiding method, the present invention are handled tag line with quarter bend detection method using curve detection method respectively, control program flow
Journey makes unmanned plane be cruised according to different path status, and uses the incomplete Artificial Potential Field Method based on Follow-Wall behaviors,
The deficiency of Artificial Potential Field Method is avoided, along barrier border movement when enabling the unmanned plane encounter barrier, until reaching predetermined
Place for this purpose, the present invention, which provides a kind of factory, makes an inspection tour unmanned plane from main path cruise and intelligent barrier avoiding method, utilizes
Machine vision technique and obstacle avoidance algorithm carry out autonomous cruise and avoidance, include the following steps：
Step 1：ID of trace route path line is shot using Guidance cameras, to image filtering, Threshold segmentation, morphology operations
Etc. a series of processing, reach ground as the binary image of background, tag line as target；
Step 2：To the binary image Canny calculation process that step 1 obtains, markings edge is obtained, using probability suddenly
Husband's change detection image middle conductor number；
Step 3：The line segment number detected in judgment step 2 enters quarter bend detection journey if line segment number is 4
Sequence, otherwise arrival curve detection program；
Step 4：Unmanned plane is worked normally under Ground coordinate systems, works as MdDuring [F]≤4m, aircraft enters prepared avoidance journey
Sequence.Md[F] is the obstacle distance that unmanned plane front measures；
Step 5：Using the incomplete Artificial Potential Field Method automatic obstacle avoiding based on Follow-Wall behaviors, until cut-through
Object.
Further improvement of the present invention, it is quadrotor unmanned plane or six rotor wing unmanned aerial vehicles that unmanned plane is maked an inspection tour by the factory.
Further improvement of the present invention, curve detection method is as follows in the step 3：
Step 3.1：The binary image that pointer traversal step 1 obtains, extraction sampling region internal standard are known line left and right edges and are sat
Mark, is denoted as L (i, j) and R (i, j), and calculate jth line identifier line center point coordinate respectively：
Wherein, i and j represents the row and column of image；
Step 3.2：Respectively repeat the above steps to image processing region 1 and image processing region 2 N1Secondary and N2It is secondary, it obtains
Point coordinates in sampling area goes out the center line l in image processing region 1 and 2 using least square fitting1And l2；
Step 3.3：By l1And l2Central point connects to obtain straight line l, as path fitting straight line, and straight line l is expressed as：
Step 3.4：Tag line is obtained relative to unmanned plane center relative to the position of picture centre using fitting a straight line
Yaw angle and offset distance：
Wherein, b=y1-ax1。
Further improvement of the present invention, quarter bend detection method is as follows in the step 3：
Step 3.5：Using the extreme coordinates of probability Hough transformation function extraction line segment, the equation of four line segments is calculated respectively
l1, l2, l3, l4；
Step 3.6：Judge whether four line segments are parallel two-by-two with x-axis angle using line segment, if parallel angle difference is ε α
=1 °, when ε α >=| | α 2 |-α 1 | | when meeting condition, illustrate line segment l1And l2It is parallel, it is otherwise not parallel；
Step 3.7：According to the extreme coordinates of four line segments be averaging two matching line segments extreme coordinates, obtain fitting
Line segment lf1And lf2Equation, and digital simulation line segment slope kfAnd angle αf：
Wherein, kf1And kf2For matching line segment lf1And lf2Slope；
Step 3.8：Further compare the relationship between the center of matching line segment and given threshold, judge unmanned plane institute
Locate the state of quarter bend：Before turn, turn round after, left quarter bend, right quarter bend；V is setx, vy, vyawRelevant parameter controls flight
System.
Further improvement of the present invention, intelligent barrier avoiding method is as follows in the step 5：
Step 5.1：Using depth map data, obstacle distance data and ultrasound data, barrier minimum range is designed
Back-and-forth method；
Step 5.2：Avoidance tables of data is established, is carried out using the incomplete Artificial Potential Field Method based on Follow-Wall behaviors
Intelligent barrier avoiding when unmanned plane reaches P points, selects a suitable direction, along the action of barrier edge, until unmanned plane around
It crosses barrier and reaches appointed place；
There is key data in avoidance tables of data：
Yaw：The yaw angle in body course in Ground systems；
YawAngle：In Ground systems target location relative to unmanned plane position drift angle；
Md[]：The barrier that D is measured under the right R of the left L of B after preceding F；
State：Unmanned plane state in which in avoidance program.
The present invention provides a kind of factory and makes an inspection tour unmanned plane from main path cruise and intelligent barrier avoiding method, is clapped using camera
Take the photograph ID of trace route path line, and selected sampling area；Canny calculation process is carried out to binaryzation tag line, tag line edge is obtained, makes
With probability Hough transformation detection image middle conductor；Judge line segment number, if line segment number is 4, detected into quarter bend, otherwise
Arrival curve detects；Autonomous cruise is carried out according to different testing results；In flight course using depth map data, barrier away from
Barrier data are obtained from data and ultrasound data；Using the incomplete Artificial Potential Field Method based on Follow-Wall behaviors certainly
Main avoidance.The present invention can use algorithms of different to realize to path trace image procossing according to the true form of tag line；Base
In the incomplete Artificial Potential Field Method of Follow-Wall behaviors, the deficiency of Artificial Potential Field Method is avoided, unmanned plane is made to encounter barrier
When can be along barrier border movement, until the predetermined area.
Description of the drawings
Fig. 1 is ID of trace route path line schematic diagram of the present invention；
Fig. 2 is quarter bend image sketch of the present invention；
Fig. 3 is navigation flowcharts of the present invention；
Fig. 4 is barrier minimum range back-and-forth method flow chart of the present invention；
Fig. 5 is present invention cruise avoidance figure；
Fig. 6 is the present invention not exclusively Artificial Potential Field Method avoidance flow chart.
Specific embodiment
The present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings：
The present invention provides a kind of factory and makes an inspection tour unmanned plane from main path cruise and intelligent barrier avoiding method, and the present invention uses bent
Line detecting method is handled tag line with quarter bend detection method respectively, is controlled program circuit, is made unmanned plane according to different paths
State is cruised, and uses the incomplete Artificial Potential Field Method based on Follow-Wall behaviors, avoids the deficiency of Artificial Potential Field Method,
Along barrier border movement when enabling the unmanned plane encounter barrier, until reaching the predetermined area.
It is a kind of for the unmanned plane autonomous cruise of factory's inspection and intelligent barrier avoiding method, specifically include following steps：
Step 1：For Guidance bottoms camera shooting ID of trace route path line as shown in Figure 1, image coordinate system is x0y, x is square
To towards the right side, y positive directions are downward.The wide a height of 320X240 pixels of image, on the image lower half portion respectively choose processing region 1 and place
Region 2 is managed as tag line edge coordinate extraction region.To a series of processing such as image filtering, Threshold segmentation, morphology operations,
Reach ground as the binary image of background, tag line as target.
Step 2：To the binary image Canny calculation process that step 1 obtains, markings edge is obtained, using probability suddenly
Husband's change detection image middle conductor number.Detect program to enter quarter bend as shown in Figure 2 if 4 if line segment number, otherwise into
Enter curve detection program.
Wherein navigation flowcharts are as shown in Figure 3；
Curve navigation step：
(1) using the method for pointer traversal image, tag line left and right edges coordinate in selection area in above-mentioned steps 1 is carried
It takes.Assuming that the path that can be detected in real image processing is to obtain (20≤j ＜ 100), image processing region in jth row
The left hand edge coordinate L (i, j) of jth row in 1, right hand edge coordinate are R (i, j), then jth line identifier line center point coordinate is：
Repeat above-mentioned (1) N1It is secondary to obtain path midpoint coordinate in image processing region 1, repeat N2It is secondary to obtain image procossing area
Path midpoint coordinate in domain 2.
(2) according to a series of path center point coordinates obtained above, go out image procossing area using least square fitting
Center line l in domain 1 and 21And l2, equation is respectively：
(3) by l1And l2Central pointWithIt connects
Straight line l, as path fitting straight line are obtained, obtains equation：
Y=4.72441x-723.334；
(4) in image coordinate system, central point C is unmanned plane position, yaw angle α of the path with respect to unmanned plane and yaw
Distance d is respectively：
Herein regulation straight line l in the picture half left axis deviation minus relative to y when α ＜ 0, otherwise α ＞ 0；Straight line l is in central point C
D ＞ 0 during the right, otherwise d ＜ 0.
Quarter bend navigation step：
(1) assume that probability Hough transformation detects that image middle conductor number is 4, if four line segments are respectively l1, l2, l3,
l4, utilize the extreme coordinates of probability Hough transformation function extraction line segment, respectively L1 (i, j), R1 (i, j), L2 (i, j), R2
(i, j), L3 (i, j), R3 (i, j), L4 (i, j), R4 (i, j), wherein with the approximately perpendicular line segment upper end point coordinates L of x-axis, under
Extreme coordinates are represented with R.Further acquire the slope k of every line segment1, k2, k3, k4, and line segment and x-axis angle α is obtained.
α=arctank；
For with the approximately perpendicular line segment of x-axis, due to picture size be 320 × 240 pixels, least unit be 1 pixel,
Therefore work as Ri=LiWhen；
(2) judge whether four line segments are parallel (or less parallel) two-by-two with x-axis angle using line segment.If judge the angle of parallelism
Degree difference be ε α=1 °, when ε α >=| | α 2 |-| α 1 | | when meeting condition, illustrate line segment l1And l2It is parallel, it is otherwise not parallel, it recalls
Quarter bend navigation function.Proving by the same methods open-wire line section l3And l4The depth of parallelism.
(3) if line segment is parallel two-by-two, the extreme coordinates of four line segments are averaging two-by-two, obtaining extreme coordinates is respectively
Lf1(i, j), Rf1(i, j), Lf2(i, j), Rf2(i, j), and then obtain two matching line segment lf1And lf2, seek matching line segment slope kf
And angle αf：
If αf>=85 °, illustrate lf1And lf2Near vertical illustrates that unmanned plane detects quarter bend.
(4) according to the position of matching line segment and pixel threshold TxAnd TyRelationship judge the curved state of unmanned plane opposing right angles.
If matching line segment lf1And lf2Centre coordinate Cf1(i, j) and Cf2(i, j), x-axis direction pixel threshold Tx=40, y-axis direction pixel
Threshold value Ty=40, when the equidirectional coordinate difference of central point is more than threshold value, to be considered as quarter bend effective.Two coordinate pairs than do well as
Following table：
(5) quarter bend angle [alpha]=88.321 ° are calculated using the above method, quarter bend state enters to turn left for 2
Before.
Step 3：Unmanned plane is worked normally under Ground coordinate systems.Work as MdDuring [F]≤4m, aircraft enters prepared avoidance journey
Sequence is as shown in Figure 6.Using the incomplete Artificial Potential Field Method automatic obstacle avoiding as shown in Figure 5 based on Follow-Wall behaviors, until around
Cross barrier.
Intelligent barrier avoiding method and step is as follows：
(1) unmanned plane obtains obstacle distance data.
The barrier data used in the present invention have depth map data, obstacle distance data and ultrasound data.For
The unstability of barrier data, present invention design barrier minimum range back-and-forth method are as shown in Figure 4.
The minimum obstacle distance being calculated every time is d, and the obstacle distance of fusion is dob, ultrasonic distance data are
dul, final minimum obstacle distance is dmin.Minimum range back-and-forth method process is as follows：
A. d is obtainedobAnd dul, and judge the two size, if dob＜ 10 or dulBoth ＞ 0 compares the two size, take
Smaller is d.
B. if dob＜ 10 or dul＜ 0, takes dobFor d.
C. if dob＞ 10 or dul＞ 0, takes dulFor d.
D. it repeats the above steps 10 times, takes wherein minimum value as final dmin。
Obstacle distance data are obtained using depth map.Image filtering, gradation conversion, morphology operations etc. are done to depth map
Operation；Pixel threshold, detection connected region number of pixels and threshold value relationship are set, to judge whether to encounter barrier.2.5
In rice, obstacle distance and grey scale pixel value approximation direct proportionality, i.e.,：
dobFor obstacle distance, vgrayRefer to the average pixel value of gray pixels in depth map.
(2) under Ground coordinate systems, Use barriers object range data judges state of flight.Work as MdDuring [F]≤4m, aircraft
Into avoidance program is prepared, aircraft forward speed Speed is reduced to 0.7m/s from 2m/s at this time.M in preparation avoidance programd[i]≤
2.5m or depth map detect that barrier can make C [i] put true, show that system enters avoidance program at this time.
(3) YawAngle is updated, makes Yaw=YawAngle.Judge C [R] value, unmanned plane is right at this time for C [R]=true explanations
There is barrier in side, and unmanned plane will turn left, State=TurnLeft；C [R]=false illustrates that right does not have barrier, unmanned plane
It will turn right, State=TurnRight.
(4) assume C [R]=false.Increase Yaw, unmanned plane is turned right, until C [F]=false.Due to the rotation of propeller
It is larger to turn range, Yaw=Yaw+10 ° at this time, then State=GoAfterRight.
(5) C [L] is judged, if C [L]=true, unmanned plane fly forward, until C [L]=false.At this time to ensure nothing
It is man-machine to fly over barrier completely, should also unmanned plane be allowed to move on 1.5m.
(6) judge YawAngle and Yaw, and enable Yaw=YawAngle, to change unmanned plane course angle.Unmanned plane is forward
Fly, until target point.If encountering barrier before reaching target point again, repeat above-mentioned (3), go successively to avoidance program.
The above described is only a preferred embodiment of the present invention, it is not the limit for making any other form to the present invention
System, and any modification that technical spirit according to the present invention is made or equivalent variations, still fall within present invention model claimed
It encloses.
Claims (5)
1. unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory, machine vision technique and avoidance is utilized to calculate
Method carries out autonomous cruise and avoidance, includes the following steps, it is characterised in that：
Step 1：ID of trace route path line is shot using Guidance cameras, to image filtering, Threshold segmentation, morphology operations etc. one
Series of processes reaches ground as the binary image of background, tag line as target；
Step 2：To the binary image Canny calculation process that step 1 obtains, markings edge is obtained, is become using probability Hough
Change detection image middle conductor number；
Step 3：The line segment number detected in judgment step 2 enters quarter bend if line segment number is 4 and detects program, no
Then arrival curve detection program；
Step 4：Unmanned plane is worked normally under Ground coordinate systems, works as MdDuring [F]≤4m, aircraft enters prepared avoidance program.Md
[F] is the obstacle distance that unmanned plane front measures；
Step 5：Using the incomplete Artificial Potential Field Method automatic obstacle avoiding based on Follow-Wall behaviors, until cut-through object.
2. unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory according to claim 1, special
Sign is：It is quadrotor unmanned plane or six rotor wing unmanned aerial vehicles that unmanned plane is maked an inspection tour by the factory.
3. a kind of factory's tour unmanned plane according to claim 1 or 2 cruises from main path and intelligent barrier avoiding method,
It is characterized in that：Curve detection method is as follows in the step 3：
Step 3.1：The binary image that pointer traversal step 1 obtains, extraction sampling region internal standard know line left and right edges coordinate, point
It is not denoted as L (i, j) and R (i, j), and calculates jth line identifier line center point coordinate：
Wherein, i and j represents the row and column of image；
Step 3.2：Respectively repeat the above steps to image processing region 1 and image processing region 2 N1Secondary and N2It is secondary, it is sampled
Point coordinates in region goes out the center line l in image processing region 1 and 2 using least square fitting1And l2；
Step 3.3：By l1And l2Central point connects to obtain straight line l, as path fitting straight line, and straight line l is expressed as：
Step 3.4：Using fitting a straight line yaw of the tag line relative to unmanned plane center is obtained relative to the position of picture centre
Angle and offset distance：
Wherein, b=y1-ax1。
4. a kind of factory's tour unmanned plane according to claim 1 or 2 cruises from main path and intelligent barrier avoiding method,
It is characterized in that：Quarter bend detection method is as follows in the step 3：
Step 3.5：Using the extreme coordinates of probability Hough transformation function extraction line segment, the equation l of four line segments is calculated respectively1,
l2, l3, l4；
Step 3.6：Judge whether four line segments are parallel two-by-two with x-axis angle using line segment, if parallel angle difference is ε α=1 °,
When ε α >=| | α 2 |-| α 1 | | when meeting condition, illustrate line segment l1And l2It is parallel, it is otherwise not parallel；
Step 3.7：According to the extreme coordinates of four line segments be averaging two matching line segments extreme coordinates, obtain matching line segment
lf1And lf2Equation, and digital simulation line segment slope kfAnd angle αf：
Wherein, kf1And kf2For matching line segment lf1And lf2Slope；
Step 3.8：Further compare the relationship between the center of matching line segment and given threshold, judge straight residing for unmanned plane
The curved state in angle：Before turn, turn round after, left quarter bend, right quarter bend；V is setx, vy, vyawRelevant parameter controls flight.
5. a kind of factory's tour unmanned plane according to claim 1 or 2 cruises from main path and intelligent barrier avoiding method,
It is characterized in that：Intelligent barrier avoiding method is as follows in the step 5：
Step 5.1：Use depth map data, obstacle distance data and ultrasound data, the minimum range selection of design barrier
Method；
Step 5.2：Avoidance tables of data is established, intelligence is carried out using the incomplete Artificial Potential Field Method based on Follow-Wall behaviors
Avoidance when unmanned plane reaches P points, selects a suitable direction, along the action of barrier edge, until unmanned plane is around barrier
Object is hindered to reach appointed place；
There is key data in avoidance tables of data：
Yaw：The yaw angle in body course in Ground systems；
YawAngle：In Ground systems target location relative to unmanned plane position drift angle；
Md[]：The barrier that D is measured under the right R of the left L of B after preceding F；
State：Unmanned plane state in which in avoidance program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711177545.XA CN108132675B (en) | 2017-11-23 | 2017-11-23 | Autonomous path cruising and intelligent obstacle avoidance method for factory inspection unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711177545.XA CN108132675B (en) | 2017-11-23 | 2017-11-23 | Autonomous path cruising and intelligent obstacle avoidance method for factory inspection unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108132675A true CN108132675A (en) | 2018-06-08 |
| CN108132675B CN108132675B (en) | 2020-02-21 |
Family
ID=62389754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711177545.XA Active CN108132675B (en) | 2017-11-23 | 2017-11-23 | Autonomous path cruising and intelligent obstacle avoidance method for factory inspection unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108132675B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002048A (en) * | 2018-06-12 | 2018-12-14 | 浙江大学 | A kind of scale centralization photovoltaic plant image data acquiring method based on multi-rotor unmanned aerial vehicle |
| CN109343528A (en) * | 2018-10-30 | 2019-02-15 | 杭州电子科技大学 | A kind of energy-efficient unmanned plane path planning barrier-avoiding method |
| CN109753081A (en) * | 2018-12-14 | 2019-05-14 | 中国矿业大学 | A kind of patrol unmanned machine system in tunnel based on machine vision and air navigation aid |
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
| CN110579768A (en) * | 2019-08-30 | 2019-12-17 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Method for designing power line-patrol route of fixed-wing unmanned aerial vehicle laser radar |
| CN110850889A (en) * | 2019-11-18 | 2020-02-28 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle autonomous inspection system based on RTK navigation |
| CN110852278A (en) * | 2019-11-12 | 2020-02-28 | 深圳创维数字技术有限公司 | Ground identification line recognition method, ground identification line recognition equipment and computer-readable storage medium |
| CN110968054A (en) * | 2018-10-01 | 2020-04-07 | 费希尔-罗斯蒙特***公司 | Operator shift for enabling unmanned aerial vehicle |
| CN111174790A (en) * | 2019-12-03 | 2020-05-19 | 河海大学 | Method for forming topographic profile tracking path |
| CN111213101A (en) * | 2019-04-26 | 2020-05-29 | 深圳市大疆创新科技有限公司 | Line patrol control method and device for movable platform, movable platform and system |
| CN111352417A (en) * | 2020-02-10 | 2020-06-30 | 合肥工业大学 | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path |
| CN111508282A (en) * | 2020-05-08 | 2020-08-07 | 沈阳航空航天大学 | Low-altitude unmanned farmland operation flight obstacle conflict detection method |
| CN113743330A (en) * | 2021-09-08 | 2021-12-03 | 新疆大学 | Transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation |
| CN114995507A (en) * | 2022-06-22 | 2022-09-02 | 中国人民公安大学 | Safety inspection method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102097860A (en) * | 2010-11-29 | 2011-06-15 | 广东峰杰科技有限公司 | Intelligent robot patrol system for safety detection of substation |
| CN103389733A (en) * | 2013-08-02 | 2013-11-13 | 重庆市科学技术研究院 | Vehicle line walking method and system based on machine vision |
| JP2014067406A (en) * | 2012-09-24 | 2014-04-17 | Ricoh Co Ltd | Method and apparatus for detecting continuous road partition |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| CN106843264A (en) * | 2016-12-28 | 2017-06-13 | 歌尔股份有限公司 | The indoor cruise method and system of unmanned plane |
| CN106873627A (en) * | 2017-03-31 | 2017-06-20 | 湘潭大学 | A kind of multi-rotor unmanned aerial vehicle and method of automatic detecting transmission line of electricity |
| CN106887004A (en) * | 2017-02-24 | 2017-06-23 | 电子科技大学 | A kind of method for detecting lane lines based on Block- matching |
| CN104751145B (en) * | 2015-04-10 | 2017-10-13 | 西安电子科技大学 | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology |
-
2017
- 2017-11-23 CN CN201711177545.XA patent/CN108132675B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102097860A (en) * | 2010-11-29 | 2011-06-15 | 广东峰杰科技有限公司 | Intelligent robot patrol system for safety detection of substation |
| JP2014067406A (en) * | 2012-09-24 | 2014-04-17 | Ricoh Co Ltd | Method and apparatus for detecting continuous road partition |
| CN103389733A (en) * | 2013-08-02 | 2013-11-13 | 重庆市科学技术研究院 | Vehicle line walking method and system based on machine vision |
| CN104751145B (en) * | 2015-04-10 | 2017-10-13 | 西安电子科技大学 | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology |
| CN105389988A (en) * | 2015-12-07 | 2016-03-09 | 北京航空航天大学 | Multi-unmanned aerial vehicle cooperation highway intelligent inspection system |
| CN106843264A (en) * | 2016-12-28 | 2017-06-13 | 歌尔股份有限公司 | The indoor cruise method and system of unmanned plane |
| CN106887004A (en) * | 2017-02-24 | 2017-06-23 | 电子科技大学 | A kind of method for detecting lane lines based on Block- matching |
| CN106873627A (en) * | 2017-03-31 | 2017-06-20 | 湘潭大学 | A kind of multi-rotor unmanned aerial vehicle and method of automatic detecting transmission line of electricity |
Non-Patent Citations (3)
| Title |
|---|
| SAEID FAZLI 等: "Wall following and obstacle avoidance results from a multi-DSP sonar ring on a mobile robot", 《PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS & AUTOMATION》 * |
| 王燕清 等: "基于启发式概率Hough变换的道路边缘检测方法", 《计算机科学》 * |
| 邸男 等: "提取直线特征实现机场跑道实时检测", 《光学精密工程》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002048A (en) * | 2018-06-12 | 2018-12-14 | 浙江大学 | A kind of scale centralization photovoltaic plant image data acquiring method based on multi-rotor unmanned aerial vehicle |
| CN109002048B (en) * | 2018-06-12 | 2020-06-09 | 浙江大学 | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method |
| CN110968054A (en) * | 2018-10-01 | 2020-04-07 | 费希尔-罗斯蒙特***公司 | Operator shift for enabling unmanned aerial vehicle |
| CN109343528A (en) * | 2018-10-30 | 2019-02-15 | 杭州电子科技大学 | A kind of energy-efficient unmanned plane path planning barrier-avoiding method |
| CN109753081B (en) * | 2018-12-14 | 2020-08-21 | 煤炭科学研究总院 | Roadway inspection unmanned aerial vehicle system based on machine vision and navigation method |
| CN109753081A (en) * | 2018-12-14 | 2019-05-14 | 中国矿业大学 | A kind of patrol unmanned machine system in tunnel based on machine vision and air navigation aid |
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
| CN111213101A (en) * | 2019-04-26 | 2020-05-29 | 深圳市大疆创新科技有限公司 | Line patrol control method and device for movable platform, movable platform and system |
| CN110579768A (en) * | 2019-08-30 | 2019-12-17 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Method for designing power line-patrol route of fixed-wing unmanned aerial vehicle laser radar |
| CN110579768B (en) * | 2019-08-30 | 2021-04-13 | 中国南方电网有限责任公司超高压输电公司贵阳局 | Method for designing power line-patrol route of fixed-wing unmanned aerial vehicle laser radar |
| CN110852278A (en) * | 2019-11-12 | 2020-02-28 | 深圳创维数字技术有限公司 | Ground identification line recognition method, ground identification line recognition equipment and computer-readable storage medium |
| CN110852278B (en) * | 2019-11-12 | 2022-08-30 | 深圳创维数字技术有限公司 | Ground identification line recognition method, ground identification line recognition equipment and computer-readable storage medium |
| CN110850889A (en) * | 2019-11-18 | 2020-02-28 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle autonomous inspection system based on RTK navigation |
| CN111174790A (en) * | 2019-12-03 | 2020-05-19 | 河海大学 | Method for forming topographic profile tracking path |
| CN111352417A (en) * | 2020-02-10 | 2020-06-30 | 合肥工业大学 | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path |
| CN111352417B (en) * | 2020-02-10 | 2022-08-02 | 合肥工业大学 | Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path |
| CN111508282A (en) * | 2020-05-08 | 2020-08-07 | 沈阳航空航天大学 | Low-altitude unmanned farmland operation flight obstacle conflict detection method |
| CN111508282B (en) * | 2020-05-08 | 2021-07-20 | 沈阳航空航天大学 | Low-altitude unmanned farmland operation flight obstacle conflict detection method |
| CN113743330A (en) * | 2021-09-08 | 2021-12-03 | 新疆大学 | Transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation |
| CN114995507A (en) * | 2022-06-22 | 2022-09-02 | 中国人民公安大学 | Safety inspection method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108132675B (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108132675A (en) | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory | |
| McGee et al. | Obstacle detection for small autonomous aircraft using sky segmentation | |
| CN102944224B (en) | Work method for automatic environmental perception systemfor remotely piloted vehicle | |
| CN104298248B (en) | Rotor wing unmanned aerial vehicle accurate vision positioning and orienting method | |
| CN110850403A (en) | Multi-sensor decision-level fused intelligent ship water surface target feeling knowledge identification method | |
| CN109556615A (en) | The driving map generation method of Multi-sensor Fusion cognition based on automatic Pilot | |
| CN111693050B (en) | Indoor medium and large robot navigation method based on building information model | |
| CN107422730A (en) | The AGV transportation systems of view-based access control model guiding and its driving control method | |
| CN109143259A (en) | High-precision cartography method towards the unmanned truck in harbour | |
| CN109282808B (en) | Unmanned aerial vehicle and multi-sensor fusion positioning method for bridge three-dimensional cruise detection | |
| CN112085003B (en) | Automatic recognition method and device for abnormal behaviors in public places and camera equipment | |
| CN112346463B (en) | Unmanned vehicle path planning method based on speed sampling | |
| WO2018215562A1 (en) | Device and method for detection and localization of vehicles | |
| CN104536009A (en) | Laser infrared composite ground building recognition and navigation method | |
| CN108122255A (en) | It is a kind of based on trapezoidal with circular combination terrestrial reference UAV position and orientation method of estimation | |
| CN108106617A (en) | A kind of unmanned plane automatic obstacle-avoiding method | |
| CN109901193A (en) | The light of short distance barrier reaches arrangement for detecting and its method | |
| CN111717244A (en) | Train automatic driving sensing method and system | |
| CN108564628A (en) | A kind of cutterhead vision positioning orientation system towards development machine automation | |
| Brenner | Vehicle localization using landmarks obtained by a lidar mobile mapping system | |
| CN103697883A (en) | Aircraft horizontal attitude determination method based on skyline imaging | |
| CN109490926A (en) | A kind of paths planning method based on binocular camera and GNSS | |
| Deng et al. | Research on target recognition and path planning for EOD robot | |
| CN113554705B (en) | Laser radar robust positioning method under changing scene | |
| CN113589848B (en) | Multi-unmanned aerial vehicle detection, positioning and tracking system and method based on machine vision |
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 |