CN110057316A - A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition - Google Patents
A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition Download PDFInfo
- Publication number
- CN110057316A CN110057316A CN201910336435.6A CN201910336435A CN110057316A CN 110057316 A CN110057316 A CN 110057316A CN 201910336435 A CN201910336435 A CN 201910336435A CN 110057316 A CN110057316 A CN 110057316A
- Authority
- CN
- China
- Prior art keywords
- rod piece
- unmanned plane
- tower crane
- image recognition
- flexion
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000012544 monitoring process Methods 0.000 title claims abstract description 14
- 238000010276 construction Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000005516 engineering process Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
- B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/08—Arrangements of cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The method for the tower crane rod piece buckling monitoring based on unmanned plane image recognition that the present invention provides a kind of, comprising: step 1, unmanned plane is made fly and shoot each main chord according to the route of setting, flying speed, shooting interval;Flight course sets shooting interval according to setting flying speed and picture-taking position as needed;Step 2, the photo obtained to shooting is transmitted to ground control platform;Step 3, after the ground control platform receives the photo, main chord range of flexion is identified using image recognition technology, if the range of flexion is greater than the critical value that construction party provides, issues early warning.The present invention can reduce the security risk that artificial detection needs to climb tower crane;Meanwhile image recognition can reduce the probability artificially judged by accident;Furthermore it is convenient, fast take pictures using unmanned plane, can greatly reduce detection time.
Description
Technical field
The present invention relates to a kind of monitoring methods of tower crane rod piece buckling, are a kind of based on unmanned plane figure specifically
As the method for the tower crane rod piece buckling monitoring of identification.
Background technique
Tower crane is the essential key equipment of construction, however due to the work of tower crane revolution, lifting and unloading
Make state, so that the main chord of tower crane is born the compression that biggish normal pressure and moment of flexure generate, to generate buckling.When rod piece is bent
When bent excessive, even overall collapse can occur for tower crane, so periodically should check that inspection method is at present to tower crane main chord
Artificial visual method.Check that frequency is monthly, this inspection method has several disadvantages in that first is that tower crane main chord quantity
More, consuming time is long for manual inspection;Second is that artificial climbing, increases security risk;Third is that human error is larger.Therefore nothing is utilized
Man-machine carry out tower crane safety monitoring is of great significance.
In recent years, unmanned plane industry development was swift and violent, and especially small-sized unmanned plane is widely used in taking photo by plane, survey and draw, electric power
The fields such as inspection.At this stage, image recognition technology is efficient, reliable, in structural safety monitoring field utilization and extention image recognition skill
Art will greatly save enterprise personnel spending, ensure that the objective of monitoring result.
Detailed description of the invention
Fig. 1 is the flow chart for the rod piece buckling monitoring that the embodiment of the present invention proposes.
Fig. 2 is monitored the conspectus of tower crane by the embodiment of the present invention, and wherein Fig. 2 (a) is tower body perspective view, Fig. 2 (b)
For tower body top view.
Fig. 3 is unmanned plane of the embodiment of the present invention and tower body spatial relation schematic diagram.
Fig. 4 is image recognition of embodiment of the present invention rod piece buckling characteristic principle schematic diagram.
Summary of the invention
Technical problem to be solved by the present invention lies in provide a kind of tower crane rod piece based on unmanned plane image recognition
The method of buckling monitoring, to save manpower, and ensures that result is reliable.
The technical solution adopted in the present invention is as follows:
A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition, comprising steps of
Step 1, unmanned plane is made fly and to each main chord according to the route of setting, flying speed, shooting interval
It is shot;Flight course sets shooting interval according to setting flying speed and picture-taking position as needed;
Step 2, the photo obtained to shooting is transmitted to ground control platform;
Step 3, after the ground control platform receives the photo, main chord buckling is identified using image recognition technology
Degree issues early warning if the range of flexion is greater than the critical value that construction party provides.
Further, in step 1, shooting time is determined by tower crane single-unit height and flying speed, it is ensured that photo just exists
Unmanned plane shoots to obtain when being in immediately ahead of each main chord of standard section.
Further, in step 1, during the unmanned plane during flying, camera lens are always towards the front of unmanned plane.
Further, the step 3 specifically includes:
For all photos taken in flight course, according to taking pictures, sequence is named each main chord;
Image preprocessing, image binaryzation and fracture profile detection are carried out to photo;
The calculating of rod piece range of flexion is carried out according to profile has been detected;
Calculated result is compared with the critical value that construction party provides finally, is constructed when detecting that rod piece range of flexion is greater than
When the critical value just provided, system is recorded the position of main chord and is sounded an alarm.
Further, the basis has detected profile progress rod piece range of flexion calculating and has specifically included step:
Contour detecting technology is used first, determines two points of buckling rod piece the right and left maximum curvature;
The midpoint for taking described two lines, will be in the midpoint of described two lines and the top edge of normal condition rod piece
Point, which is connected, obtains line;
The angle for calculating the line Yu normal condition rod piece central axes, the range of flexion as rod piece.
Compared with prior art, the beneficial effects of the present invention are:
The present invention can reduce the security risk that artificial detection needs to climb tower crane;Meanwhile image recognition can reduce people
For the probability of erroneous judgement;Furthermore it is convenient, fast take pictures using unmanned plane, can greatly reduce detection time, convenient for fast implementing
Buckling monitoring to tower crane rod piece.
Specific embodiment
The present invention is further illustrated with reference to the accompanying drawings and examples.
The tower crane tower body height that embodiment of the present invention is chosen is 11.2m, and tower body width is 1.665m, the height of tower crane single-unit
Degree is 2.8m.
As shown in Figure 1, a kind of method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition, including step
It is rapid:
1) unmanned plane fly and clap each main chord according to the route of setting, flying speed, shooting interval
It takes the photograph;Flight course sets shooting interval according to setting flying speed and picture-taking position as needed;
The technical requirements of shooting: shooting resolution ratio is 2mm, and camera lens installation should be towards unmanned plane heading.
If maximum opposite boat is away from being H, focal length f, Pixel size P, shooting resolution ratio is G, and CMOS dimension width is W,
The height of CMOS size is V, SWFor number of pixels corresponding on W, SVFor number of pixels corresponding on V.
This example use big boundary spirit Phantom 4Pro intelligent aerial photography robot, 8.8mm tight shot, CMOS having a size of
12.8 × 9.6mm, film size size are 5163 × 3873 (unit is pixel), can be calculated according to above-mentioned formula:
The barriers such as job platform, jack for considering tower crane top take opposite boat away from for 2m.
Flight line is specifically designed according to the parameter calculated and controls unmanned plane during flying shooting, specific as follows:
As shown in Fig. 2 (a), 2 (b) and Fig. 3, manipulation unmanned plane according to flight path A → B → C → D → E → F → G → H →
The completion of I → J → K → L → M → N → O → P sequence takes pictures: so that nobody is hovered over the front of A point, and keep with tower body away from
From for 2m or so, as shown in figure 4, camera lens are always towards flight front.Flying distance 11.2m is set, flying speed is
1m/s, shooting interval 2.8s, create aerial mission, and unmanned plane completes the secondary shooting task from A to B automatically, shoots to obtain 4 photographs
Piece, and hover over B point.Manual operation unmanned plane flies to C point and hovers from B, repeats previous step, until completing 8 longitudinal directions
Flight line.In entire flight course, Longitudinal Flight speed remains 1m/s, takes pictures once at interval of 2.8s.Vertically walk altogether
It crosses 8 times, each distance is 11.2m, total 89.6m, time-consuming 89.6s.Laterally pass by altogether 7 times, in addition the time used in setup parameter,
The whole flight time is within 150s.The number of pictures of shooting is 32 altogether.
2) photo that shooting obtains is transmitted to ground control platform.
3) unmanned plane fly and clap each main chord according to the route of setting, flying speed, shooting interval
It takes the photograph;Flight course sets shooting interval according to setting flying speed and picture-taking position as needed, specifically:
For all photos taken in flight course, according to taking pictures, sequence is named each main chord;Control
Piece carries out image preprocessing, image binaryzation and fracture profile detection;
The calculating of rod piece range of flexion is carried out according to profile has been detected, when calculating, contour detecting technology is used first, determines buckling
Two points of rod piece the right and left maximum curvature;The midpoint for taking described two lines, by the midpoint of described two lines with
The top edge midpoint of normal condition rod piece, which is connected, obtains line;The angle of the line Yu normal condition rod piece central axes is calculated,
Range of flexion as rod piece;
Calculated result is compared with the critical value that construction party provides finally, is constructed when detecting that rod piece range of flexion is greater than
When the critical value just provided, system is recorded the position of main chord and is sounded an alarm.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (5)
1. a kind of method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition characterized by comprising
Step 1, so that unmanned plane is carried out flight according to the route of setting, flying speed, shooting interval and each main chord is carried out
Shooting;Flight course sets shooting interval according to setting flying speed and picture-taking position as needed;
Step 2, the photo obtained to shooting is transmitted to ground control platform;
Step 3, after the ground control platform receives the photo, main chord range of flexion is identified using image recognition technology, if
The range of flexion is greater than the critical value that construction party provides, then issues early warning.
2. according to right want 1 described in a kind of method that tower crane rod piece buckling based on unmanned plane image recognition monitors,
It is characterized in that, in step 1, shooting time is determined by tower crane single-unit height and flying speed, it is ensured that photo is just at unmanned plane
It shoots to obtain when immediately ahead of each main chord of standard section.
3. according to right want 1 described in a kind of method that tower crane rod piece buckling based on unmanned plane image recognition monitors,
It is characterized in that, in step 1, during the unmanned plane during flying, camera lens are always towards the front of unmanned plane.
4. according to right want 1 described in a kind of method that tower crane rod piece buckling based on unmanned plane image recognition monitors,
It is characterized in that, the step 3 specifically includes:
For all photos taken in flight course, according to taking pictures, sequence is named each main chord;
Image preprocessing, image binaryzation and fracture profile detection are carried out to photo;
The calculating of rod piece range of flexion is carried out according to profile has been detected;
Finally calculated result is compared with the critical value that construction party provides, when detecting that rod piece range of flexion mentions greater than construction party
When the critical value of confession, system is recorded the position of main chord and is sounded an alarm.
5. according to right want 4 described in a kind of method that tower crane rod piece buckling based on unmanned plane image recognition monitors,
It is characterized in that, the basis has detected profile progress rod piece range of flexion calculating and specifically included step:
Contour detecting technology is used first, determines two points of buckling rod piece the right and left maximum curvature;
The midpoint for taking described two lines, by the top edge midpoint phase at the midpoint of described two lines and normal condition rod piece
Get line continuously;The angle for calculating the line Yu normal condition rod piece central axes, the range of flexion as rod piece.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910336435.6A CN110057316A (en) | 2019-04-25 | 2019-04-25 | A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910336435.6A CN110057316A (en) | 2019-04-25 | 2019-04-25 | A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110057316A true CN110057316A (en) | 2019-07-26 |
Family
ID=67320646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910336435.6A Pending CN110057316A (en) | 2019-04-25 | 2019-04-25 | A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110057316A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114234927A (en) * | 2021-12-16 | 2022-03-25 | 上海宝冶工程技术有限公司 | Unmanned aerial vehicle-based traditional wood structure tenon-and-mortise node tenon-pulling measurement method |
CN116578104A (en) * | 2023-07-14 | 2023-08-11 | 山东中建众力设备租赁有限公司 | Unmanned tower crane control method based on deep learning |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104344789A (en) * | 2013-07-23 | 2015-02-11 | 国家电网公司 | System and method for monitoring member deflection in bearing capacity test |
CN105512659A (en) * | 2015-12-10 | 2016-04-20 | 广东小天才科技有限公司 | Correction method and system for character line bending |
CN106683089A (en) * | 2016-12-30 | 2017-05-17 | 南京南瑞信息通信科技有限公司 | Pole tower deformation detection method with constraint registration |
CN106767506A (en) * | 2016-12-13 | 2017-05-31 | 智车优行科技(北京)有限公司 | Method, device and vehicle for detecting the bend curvature in road |
KR20170100990A (en) * | 2016-02-26 | 2017-09-05 | 울산과학기술원 | Apparatus and Method for Detecting Construction Crack |
CN109211132A (en) * | 2017-07-07 | 2019-01-15 | 北京林业大学 | A kind of photogrammetric method for obtaining tall and big object deformation information of unmanned plane high-precision |
JP2019036700A (en) * | 2017-08-15 | 2019-03-07 | 信越半導体株式会社 | Evaluation method and evaluation device for edge shape of silicon wafer, silicon wafer, and selection method and manufacturing method therefor |
CN109556521A (en) * | 2018-11-24 | 2019-04-02 | 华北理工大学 | A kind of railway track displacement detector and detection method based on unmanned plane |
CN109596053A (en) * | 2019-01-14 | 2019-04-09 | 中山大学 | A method of measurement high-speed rail bridge vertically moves degree of disturbing |
-
2019
- 2019-04-25 CN CN201910336435.6A patent/CN110057316A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104344789A (en) * | 2013-07-23 | 2015-02-11 | 国家电网公司 | System and method for monitoring member deflection in bearing capacity test |
CN105512659A (en) * | 2015-12-10 | 2016-04-20 | 广东小天才科技有限公司 | Correction method and system for character line bending |
KR20170100990A (en) * | 2016-02-26 | 2017-09-05 | 울산과학기술원 | Apparatus and Method for Detecting Construction Crack |
CN106767506A (en) * | 2016-12-13 | 2017-05-31 | 智车优行科技(北京)有限公司 | Method, device and vehicle for detecting the bend curvature in road |
CN106683089A (en) * | 2016-12-30 | 2017-05-17 | 南京南瑞信息通信科技有限公司 | Pole tower deformation detection method with constraint registration |
CN109211132A (en) * | 2017-07-07 | 2019-01-15 | 北京林业大学 | A kind of photogrammetric method for obtaining tall and big object deformation information of unmanned plane high-precision |
JP2019036700A (en) * | 2017-08-15 | 2019-03-07 | 信越半導体株式会社 | Evaluation method and evaluation device for edge shape of silicon wafer, silicon wafer, and selection method and manufacturing method therefor |
CN109556521A (en) * | 2018-11-24 | 2019-04-02 | 华北理工大学 | A kind of railway track displacement detector and detection method based on unmanned plane |
CN109596053A (en) * | 2019-01-14 | 2019-04-09 | 中山大学 | A method of measurement high-speed rail bridge vertically moves degree of disturbing |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114234927A (en) * | 2021-12-16 | 2022-03-25 | 上海宝冶工程技术有限公司 | Unmanned aerial vehicle-based traditional wood structure tenon-and-mortise node tenon-pulling measurement method |
CN116578104A (en) * | 2023-07-14 | 2023-08-11 | 山东中建众力设备租赁有限公司 | Unmanned tower crane control method based on deep learning |
CN116578104B (en) * | 2023-07-14 | 2023-09-19 | 山东中建众力设备租赁有限公司 | Unmanned tower crane control method based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110044594A (en) | A kind of elastic monitoring method of tower crane bolt based on unmanned plane image recognition | |
US11042755B2 (en) | Method for foreign object debris detection | |
CN112164015B (en) | Monocular vision autonomous inspection image acquisition method and device and power inspection unmanned aerial vehicle | |
CN113359810B (en) | Unmanned aerial vehicle landing area identification method based on multiple sensors | |
CN105807786A (en) | UAV automatic obstacle avoidance method and system | |
WO2023279695A1 (en) | Power transmission and transformation project acceptance method based on bim and point cloud measurement | |
CN103679674B (en) | Method and system for splicing images of unmanned aircrafts in real time | |
EP3249487A2 (en) | Uav and uav landing control device and method | |
CN109358648B (en) | Unmanned aerial vehicle autonomous flight method and device and unmanned aerial vehicle | |
CN110633629A (en) | Power grid inspection method, device, equipment and storage medium based on artificial intelligence | |
WO2021042668A1 (en) | Tunnel surrounding rock structure virtual reproduction system carried on tbm, and method thereof | |
CN105759834A (en) | System and method of actively capturing low altitude small unmanned aerial vehicle | |
CN110057316A (en) | A method of the tower crane rod piece buckling monitoring based on unmanned plane image recognition | |
KR101771492B1 (en) | Method and system for mapping using UAV and multi-sensor | |
CN110118531A (en) | Tower crane steel gusset plate Crack Monitoring method based on unmanned plane image recognition | |
CN111913492B (en) | Unmanned aerial vehicle safe landing method and device | |
CN115240093B (en) | Automatic power transmission channel inspection method based on visible light and laser radar point cloud fusion | |
CN114111799B (en) | Unmanned aerial vehicle aerial-shooting path planning method for high-macromonomer fine modeling | |
CN109660721B (en) | Unmanned aerial vehicle flight shooting quality optimization method, system, equipment and storage medium | |
CN105761257A (en) | Elimination method for gross error in unmanned aerial vehicle image matching on cross air strip and device thereof | |
CN106500699A (en) | A kind of position and orientation estimation method suitable for Autonomous landing in unmanned plane room | |
WO2022247597A1 (en) | Papi flight inspection method and system based on unmanned aerial vehicle | |
WO2020239088A1 (en) | Insurance claim processing method and apparatus | |
WO2022198508A1 (en) | Lens abnormality prompt method and apparatus, movable platform, and readable storage medium | |
WO2021146970A1 (en) | Semantic segmentation-based distance measurement method and apparatus, device and system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |