CN111123962A - Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection - Google Patents
Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection Download PDFInfo
- Publication number
- CN111123962A CN111123962A CN201911293115.3A CN201911293115A CN111123962A CN 111123962 A CN111123962 A CN 111123962A CN 201911293115 A CN201911293115 A CN 201911293115A CN 111123962 A CN111123962 A CN 111123962A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- current frame
- power tower
- rotor unmanned
- 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 30
- 238000007689 inspection Methods 0.000 title claims abstract description 25
- 238000013519 translation Methods 0.000 claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 10
- 230000008447 perception Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Abstract
The invention discloses a rotor unmanned aerial vehicle repositioning photographing method for power tower inspection, which comprises the steps of using a rotor unmanned aerial vehicle to carry a camera, flying to a fault point of a power tower to position and photograph a reference photo, and recording GPS (global positioning system) information of the fault point; when the tower is patrolled and examined, the GPS coordinates of the reference pictures are used for controlling the rotor wing unmanned aerial vehicle to fly to a fault point which is easy to occur so as to obtain a current frame, the shot reference pictures and the current frame are subjected to characteristic point matching, and the rotation amount and the translation amount of the rotor wing unmanned aerial vehicle relative to the shooting position of the reference pictures at the current shooting position are calculated so as to control the posture of the unmanned aerial vehicle to be finely adjusted to reach the position of the reference pictures, and the; after fine adjustment, the current frame is obtained again, similarity comparison is carried out on the current frame and the reference picture which is shot for the first time, the current frame can be stored when the requirement of the similarity is met, and relocation shooting is achieved. The method can be used for repositioning the shot pictures, can be directly used for deep learning and detecting the fault points of the electric power tower, reduces the calibration work of manual work on the fault points in the pictures, and improves the inspection efficiency of the electric power tower.
Description
Technical Field
The invention relates to the technical field of power inspection, in particular to a rotor unmanned aerial vehicle repositioning photographing method for power tower inspection.
Background
Electric power enterprises in China are important pillar type industries in economic development, necessary electric energy sources are provided for people every year, and power transmission lines are main components in electric power systems. In recent years, the scale of the power grid is gradually expanded, the number of lines for power transmission is increased, and some lines for transmission are arranged in areas with complex terrain. The electric power tower blows the sun through wind, can cause spare part to drop, and binding post is not hard up scheduling problem.
Because the geographical environment is abominable and the electric power tower trouble is difficult to discover, traditional artifical patrolling and examining can not adapt to the demand of development more and more. Rotor unmanned aerial vehicle has the take-off and land requirement and requires lowly, and characteristics such as the flight is nimble carry hot imaging equipment, can increase substantially the operating efficiency in the electric power field of patrolling and examining, reduce cost, more importantly has avoided the emergence of the artifical safety problem of patrolling and examining.
The electric power tower fault point that easily sends out patrols and examines and generally adopts the degree of depth study to specific fault point classification detection, because the route that unmanned aerial vehicle flown at every turn all is different, and fault point position change is undulant greatly in the photo, and the efficiency that leads to degree of depth study discernment is not high. Therefore, the fault points of the electric power tower in the picture are manually calibrated, then deep learning is carried out on the calibration area to generate a classification model, and whether faults exist is judged. However, the manual calibration work is tedious and heavy, and the inspection efficiency is indirectly reduced.
Disclosure of Invention
According to the defects in the prior art, the invention provides the rotor unmanned aerial vehicle repositioning photographing method for the inspection of the power tower, the photographing positions are approximately the same when the same easy-fault point is inspected, so that the specific fault point uses a specific calibration frame, the manual calibration work is removed, and the efficiency of deep learning and detection of the fault of the power tower is improved.
The technical scheme of the invention is concretely realized as follows:
a rotor unmanned aerial vehicle repositioning photographing method for power tower inspection comprises the following steps:
step 1, when the rotor unmanned aerial vehicle flies to the vicinity of a fault-prone point of an electric power tower for the first time to take a picture, a flyer controls a remote controller to find a proper position to take a reference picture, so that a position where the electric power tower is prone to fault exists in the picture, and GPS coordinates of the position where the picture is located are stored;
step 3, due to the existence of GPS errors, the difference between the shooting position of the current frame and the shooting position of the reference picture is large, the shooting position of the rotor unmanned aerial vehicle needs to be corrected during inspection, and the control algorithm is as follows:
s1, detecting the Oriented FAST corner positions of the reference picture and the current frame;
s2, calculating BRIEF descriptors of the reference picture and the current frame according to the corner positions;
s3, matching BRIEF descriptors of the reference picture and the current frame, and using Hamming distance;
s4, calculating the minimum distance between all the matching points, namely the distance between the most similar two groups of points;
s5, screening descriptors, and reserving matching points with the distance between the descriptors being less than twice the minimum distance;
s6, according to the epipolar geometric constraint
Solving a rotation matrix R and a translational vector t, where x1For reference to the coordinates of the feature points in the photograph, x2The characteristic point coordinates in the current frame are taken as the characteristic point coordinates;
s7, converting the rotation matrix R into Euler angles, namely Roll, Pitch and Yaw, converting the translation vector t into x, y and z, and taking the six quantities as control quantities of six degrees of freedom for controlling fine adjustment of the rotor unmanned aerial vehicle;
Further, the initial input of the unmanned aerial vehicle in the step 2 is the GPS coordinates of the reference picture, the GPS information of the current frame is acquired in real time when the power tower patrols and examines, and then the control quantity is output through the position controller. When the unmanned aerial vehicle does not reach the proper position, the disturbance R and t input should be 0, so that the unmanned aerial vehicle can be quickly positioned to be close to the GPS position of the reference picture; then starting feature point matching and screening of the current frame image and the reference picture, and resolving an R matrix and a t vector; and then converting the three-axis attitude angle and the three-axis translation amount according to a Rodrigues formula, inputting the three-axis attitude angle and the three-axis translation amount as disturbance to an attitude controller of the unmanned aerial vehicle, reading the angular speed and the acceleration of the unmanned aerial vehicle from the IMU module as feedback amount of attitude control, and controlling the attitude fine adjustment of the unmanned aerial vehicle.
Further, a Hash perception algorithm for calculating the similarity of the pictures uses Discrete Cosine Transform (DCT) to obtain the low-frequency components of the pictures.
Further, discrete cosine transform transforms the image from a pixel domain to a frequency domain, and calculates the fingerprint of the image through low frequency; the fingerprints of the two photos are compared to obtain the similarity information of the two photos.
Further, a Hash perception algorithm is adopted for calculating the similarity of the photos, and the algorithm comprises the following steps:
s1, reducing the picture size, 32 × 32 resolution is better. This is done to simplify the computation of the DCT, rather than to reduce the frequency.
And S2, simplifying colors, converting the picture into a gray image, and further simplifying the calculation amount.
And S3, calculating DCT transformation of the picture, and obtaining a 32 x 32 DCT coefficient matrix.
S4, the DCT is reduced, and although the result of the DCT is a matrix of 32 × 32 size, this part exhibits the lowest frequencies in the picture as long as the matrix of 8 × 8 in the upper left corner is retained.
S5, calculate the mean value, like the mean hash, calculate the mean value of the DCT.
And S6, calculating the hash value, which is the most important step, setting a 64-bit hash value of 0 or 1 according to the 8 x 8 DCT matrix, setting the hash value to be 1 when the hash value is larger than or equal to the DCT mean value, and setting the hash value to be 0 when the hash value is smaller than the DCT mean value. When combined, form a 64-bit integer, which is the fingerprint of the picture. The fingerprints of the two photos are compared to obtain the similarity information of the two photos.
Furthermore, the rotor unmanned aerial vehicle photographing device comprises a rotor unmanned aerial vehicle, a camera, a holder, a GPS positioning module, a data transmission and image transmission integrated transceiving module, a ground station image processing system and a handheld wireless remote controller; the unmanned aerial vehicle main control is a pixhawd flight control board; the holder is a three-axis controllable holder with a rotor unmanned aerial vehicle connected with a camera; the ground station image processing system is a ground computer which stores photos and GPS information, processes characteristic point matching and controls the flight of the unmanned aerial vehicle; the hand-held wireless remote controller is a ground hand-held remote controller connected with a receiver on the flight control in a frequency-opposite mode.
The rotor unmanned aerial vehicle repositioning photographing method for the inspection of the power tower can effectively reduce the workload of manual calibration, the current frame photographed during inspection provides different calibration frames according to different fault points, automatic calibration is controlled by a program, and the method can be directly used for a deep learning training model to detect whether faults exist, so that the inspection efficiency is greatly improved.
Drawings
FIG. 1 is a flowchart of the operation of a retargeting photographing method;
FIG. 2 is a block diagram of a rotor drone control system;
FIG. 3 is a flow chart of an image similarity comparison algorithm;
FIG. 4 is a diagram of the hardware architecture of the system for retargeting photographs;
fig. 5 is a characteristic extraction diagram of the power tower.
Rotor unmanned aerial vehicle 1, GPS orientation module 2, camera 3, the integrative transceiver module 4 of data transmission picture biography, cloud platform 5, ground station image processing system 6 and handheld wireless remote controller 7.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1 and 4, a rotor unmanned aerial vehicle repositioning photographing method for power tower inspection comprises a rotor unmanned aerial vehicle 1, a camera 3, a holder 5, a GPS positioning module 2, a data transmission and image transmission integrated transceiver module 4, a ground station image processing system 6 and a handheld wireless remote controller 7; the unmanned aerial vehicle main control is a pixhawd flight control board; the holder is a three-axis controllable holder with a rotor unmanned aerial vehicle connected with a camera; the ground station image processing system is a ground computer which stores photos and GPS information, processes characteristic point matching and controls the flight of the unmanned aerial vehicle; the hand-held wireless remote controller is a ground hand-held remote controller connected with a receiver on the flight control in a frequency-opposite mode.
As shown in fig. 1, when the electric power tower fixed point is patrolled and examined, the GPS coordinate of the reference photo of the point is read first, the rotor unmanned aerial vehicle is controlled to fly to hover to the GPS coordinate, the current frame image is obtained, the error between the current frame position and the reference photo position is caused due to the hardware precision of the GPS module, and the fault point which is easy to occur and is not recorded by the reference photo appears in the current frame image in serious conditions, so that the posture of the unmanned aerial vehicle is finely adjusted. The feature point matching is carried out through the current frame image and the reference picture, and the position deviation of the unmanned aerial vehicle relative to the reference picture can be calculated.
As shown in FIG. 5, the feature point matching requires less mismatching and faster matching speed, the invention selects ORB (organized FAST and Rotated BRIEF) feature points to calculate matching, which improves the problem that FAST detector has no directionality, and uses binary descriptor BRIEF with extremely FAST speed to greatly speed up the image feature extraction. After the feature points of the current frame image and the reference picture are extracted, feature matching is carried out, the simplest method is violent matching, the electric power tower inspection field environment is complex, the number of extracted feature points is large, and therefore the fast nearest neighbor (FLANN) algorithm is more suitable for carrying out feature matching. After matching, the invention adopts Hamming distance as the measure of the matching degree of two characteristic points, the matching is more reliable when the distance is smaller, in order to reduce mismatching, the minimum distance between all matching points, namely the distance between the most similar two groups of points, is calculated, the matching points with the descriptor spacing smaller than two times of the minimum distance are reserved, and the relatively reliable matching points are obtained.
As shown in fig. 1, the screening of the matching points is completed, and the position deviation of the position of the current frame image relative to the reference picture is solved through the robust matching points. Under the coordinate system of the reference picture, the spatial position coordinate of the point P is set as P ═ X, Y, Z]TTwo matched pixel points p can be obtained according to the pinhole camera model1，p2Has a pixel position of s1p1＝KP，s2p2K (RP + t). Where K is the camera reference matrix, R, t are the relative motion of the two camera coordinates, and s is the zoom factor. Now take x1＝K-1p1，x2＝K-1p2Here x1Is the normalized coordinate of two pixel points, and is substituted into the above formula to obtain x2＝Rx1+ t. Two-sided simultaneous left ride
An equation can be obtained
Due to t ^ x2Is and x2The vertical vector, with 0 on the left, results in a compact antipodal constraint:
matching points are selected through an RANSAC algorithm to solve R and t, then the R is decomposed into Euler angles through a Rodrigues formula, the t is decomposed into three-axis translation quantity, and the three-axis translation quantity is input into a control system of the rotor unmanned aerial vehicle to control and reduce position deviation. Reference to the Picture in Picture shown in FIG. 5
Obtaining a first frame camera coordinate system as a world coordinate system by adopting the normalized coordinates
t＝[-0.822 -0.033 0.568]TThat is, the position deviation of the position of the current frame image with respect to the reference picture is obtained.
As shown in fig. 2, the initial input of the unmanned aerial vehicle is the GPS coordinates of the reference picture, and the power tower acquires the GPS information of the current frame in real time during inspection, and then outputs the control quantity through the position controller. When the proper position is not reached, the disturbance R, t input should be 0, so that the unmanned aerial vehicle can be quickly positioned to be close to the GPS position of the reference picture. And then starting feature point matching and screening of the current frame image and the reference picture, and resolving an R matrix and a t vector. And then converting the three-axis attitude angle and the three-axis translation amount according to a Rodrigues formula, inputting the three-axis attitude angle and the three-axis translation amount as disturbance to an attitude controller of the unmanned aerial vehicle, reading the angular speed and the acceleration of the unmanned aerial vehicle from the IMU module as feedback amount of attitude control, and controlling the attitude fine adjustment of the unmanned aerial vehicle. In the fine adjustment process, the threshold output is controlled, and the extremely small attitude difference is not adjusted, so that the output ripple jitter is prevented from being severe. The R matrix and t vector of two-frame image solution shown in FIG. 5 are converted into three-axis control quantity by the Rodrigues formula
The three axes of translation are
As shown in fig. 3, after the position is finely adjusted, the unmanned aerial vehicle acquires the current frame image again, and in order to verify whether the current frame meets the inspection requirement, the invention adopts a picture similarity comparison method based on the hash perception algorithm. First the picture size is reduced and 32 x 32 resolution under the image pyramid is better. This is done to simplify the computation of the DCT. And then the reduced reference picture and the current frame image are converted into a gray image, so that the calculation amount is further simplified. And calculating DCT transformation of the two pictures to obtain a 32 x 32 DCT coefficient matrix. Although the result of the DCT is a matrix of 32 x 32 size, this part exhibits the lowest frequencies in the picture as long as the 8 x 8 matrix in the upper left corner is retained. Then, 8 × 8 DCT mean values are calculated, the hash value is set to 64 bits of 0 or 1 according to the DCT matrix, the number of bits greater than or equal to the DCT mean value is set to 1, and the number of bits smaller than the DCT mean value is set to 0. And combined together, form a 64-bit integer to obtain the fingerprint of the picture. The similarity of the current frame relative to the reference picture is defined as 1-abs (a-b)/64, wherein a and b are fingerprint information of the reference picture and the current frame image respectively. The example in fig. 5 calculated a similarity of 83.47%.
As shown in fig. 1, when the similarity does not meet the requirement, feature matching and screening need to be performed again according to the current frame image and the reference picture, the pose error of the unmanned aerial vehicle is solved, and the attitude is adjusted. When the similarity meets the given requirement, the current frame image can be stored to the local, and the subsequent analysis can detect whether the current frame image contains a fault point according to a model which is obtained by deep learning and training of the reference picture.
The above is a specific embodiment of the repositioning photographing method provided by the invention. The repositioning method provided by the invention effectively solves the problems of low fault finding speed and low fault inspection efficiency in the inspection problem of the power tower. The protection scope of the present invention is not limited thereto, and any person skilled in the art can modify or substitute the technical solutions of the foregoing embodiments within the technical scope of the present invention, and these modifications or substitutions should be covered within the protection scope of the present invention without departing from the essence of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. The utility model provides a rotor unmanned aerial vehicle relocation method of shooing for electric power tower patrols and examines which characterized in that: the method comprises the following steps:
step 1, when a photographing device of a rotor wing unmanned aerial vehicle flies to the vicinity of a fault-prone point of an electric power tower for the first time to take a picture, a flyer controls a remote controller to find a proper position to take a reference picture, so that a position where the electric power tower is prone to fault exists in the picture is ensured, and GPS coordinates of the position where the picture is located are stored;
step 2, sending a control instruction by a ground station to control the rotor unmanned aerial vehicle to automatically fly to the vicinity of a fault point easy to occur by utilizing the GPS position stored in the reference picture when the electric power tower patrols and examines, and acquiring a current frame image;
step 3, due to the existence of GPS errors, the difference between the shooting position of the current frame and the shooting position of the reference picture is large, the shooting position of the rotor unmanned aerial vehicle needs to be corrected during inspection, and the control algorithm is as follows:
s1, detecting the Oriented FAST corner positions of the reference picture and the current frame;
s2, calculating BRIEF descriptors of the reference picture and the current frame according to the corner positions;
s3, matching BRIEF descriptors of the reference picture and the current frame, and using Hamming distance;
s4, calculating the minimum distance between all the matching points, namely the distance between the most similar two groups of points;
s5, screening descriptors, and reserving matching points with the distance between the descriptors being less than twice the minimum distance;
s6, according to the epipolar geometric constraint
Solving a rotation matrix R and a translational vector t, where x1For reference to the coordinates of the feature points in the photograph, x2The characteristic point coordinates in the current frame are taken as the characteristic point coordinates;
s7, converting the rotation matrix R into Euler angles, namely Roll, Pitch and Yaw, converting the translation vector t into x, y and z, and taking the six quantities as control quantities of six degrees of freedom for controlling fine adjustment of the rotor unmanned aerial vehicle;
step 4, updating the position of the fine-tuned rotor unmanned aerial vehicle, re-shooting the current frame, calculating the similarity between the current frame and the reference picture by using a Hash perception algorithm, considering that the shooting position of the current frame is coincident with the shooting position of the reference picture when the similarity requirement is met, storing the current frame, and directly using the current frame for deep learning to detect whether a fault exists after the current frame is calibrated by using a specific calibration frame; if not, need finely tune rotor unmanned aerial vehicle position again according to the current frame of shooting at present, return to step 3.
2. The repositioning photographing method for the rotor unmanned aerial vehicle for the inspection of the power tower as claimed in claim 1, wherein the repositioning photographing method comprises the following steps: the initial input of the unmanned aerial vehicle in the step 2 is the GPS coordinates of the reference picture, the GPS information of the current frame is acquired in real time when the electric power tower patrols and examines, and then the control quantity is output through the position controller. When the unmanned aerial vehicle does not reach the proper position, the disturbance R and t input should be 0, so that the unmanned aerial vehicle can be quickly positioned to be close to the GPS position of the reference picture; then starting feature point matching and screening of the current frame image and the reference picture, and resolving an R matrix and a t vector; and then converting the three-axis attitude angle and the three-axis translation amount according to a Rodrigues formula, inputting the three-axis attitude angle and the three-axis translation amount as disturbance to an attitude controller of the unmanned aerial vehicle, reading the angular speed and the acceleration of the unmanned aerial vehicle from the IMU module as feedback amount of attitude control, and controlling the attitude fine adjustment of the unmanned aerial vehicle.
3. The repositioning photographing method for the rotor unmanned aerial vehicle for the inspection of the power tower as claimed in claim 1, wherein the repositioning photographing method comprises the following steps: the Hash perception algorithm for calculating the similarity of the pictures uses Discrete Cosine Transform (DCT) to obtain the low-frequency components of the pictures.
4. The repositioning photographing method for the rotor unmanned aerial vehicle for the electric power tower inspection according to claim 2, characterized in that: the discrete cosine transform transforms the image from a pixel domain to a frequency domain, and the fingerprint of the image is calculated through low frequency; the fingerprints of the two photos are compared to obtain the similarity information of the two photos.
5. The repositioning photographing method for the rotor unmanned aerial vehicle for the electric power tower inspection according to claim 3, characterized in that: the method for calculating the similarity of the photos adopts a Hash perception algorithm, and the algorithm comprises the following steps:
s1, reducing the picture size, 32 × 32 resolution is better, which is done to simplify the DCT computation, rather than to reduce the frequency;
s2, simplifying color, converting the picture into a gray image, and further simplifying the calculated amount;
s3, calculating DCT transformation of the picture, and obtaining a DCT coefficient matrix of 32 x 32;
s4, reducing the DCT, which presents the lowest frequency in the picture, although the result of the DCT is a matrix of 32 × 32 size, as long as the matrix of 8 × 8 in the upper left corner is retained;
s5, calculating an average value, and calculating the average value of DCT like the average value hash;
s6, calculating a hash value, which is the most important step, setting a 64-bit hash value of 0 or 1 according to the 8 x 8 DCT matrix, setting the value which is more than or equal to the DCT mean value as 1, and setting the value which is less than the DCT mean value as 0; combined together, form a 64-bit integer, which is the fingerprint of the picture; the fingerprints of the two photos are compared to obtain the similarity information of the two photos.
6. The repositioning photographing method for the rotor unmanned aerial vehicle for the inspection of the power tower as claimed in claim 1, wherein the repositioning photographing method comprises the following steps: the rotor unmanned aerial vehicle photographing device comprises a rotor unmanned aerial vehicle, a camera, a holder, a GPS positioning module, a data transmission and image transmission integrated transceiving module, a ground station image processing system and a handheld wireless remote controller; the unmanned aerial vehicle main control is a pixhawd flight control board; the holder is a three-axis controllable holder with a rotor unmanned aerial vehicle connected with a camera; the ground station image processing system is a ground computer which stores photos and GPS information, processes characteristic point matching and controls the flight of the unmanned aerial vehicle; the hand-held wireless remote controller is a ground hand-held remote controller connected with a receiver on the flight control in a frequency-opposite mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293115.3A CN111123962A (en) | 2019-12-16 | 2019-12-16 | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293115.3A CN111123962A (en) | 2019-12-16 | 2019-12-16 | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111123962A true CN111123962A (en) | 2020-05-08 |
Family
ID=70499014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911293115.3A Pending CN111123962A (en) | 2019-12-16 | 2019-12-16 | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111123962A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966110A (en) * | 2020-09-08 | 2020-11-20 | 天津海运职业学院 | Automatic navigation method and system for port unmanned transport vehicle |
| CN112037274A (en) * | 2020-07-23 | 2020-12-04 | 江苏方天电力技术有限公司 | Multi-rotor unmanned aerial vehicle viewpoint determining method based on solar illumination condition |
| CN113520172A (en) * | 2021-08-06 | 2021-10-22 | 广东福尔电子有限公司 | Pressure-resistant electric cooker temperature sensor detection device |
| CN113624133A (en) * | 2021-08-05 | 2021-11-09 | 合肥阳光智维科技有限公司 | Fault positioning method and device and electronic equipment |
| CN114578188A (en) * | 2022-05-09 | 2022-06-03 | 环球数科集团有限公司 | Power grid fault positioning method based on Beidou satellite |
| CN115219852A (en) * | 2022-09-19 | 2022-10-21 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141433A (en) * | 2018-09-20 | 2019-01-04 | 江阴市雷奥机器人技术有限公司 | A kind of robot indoor locating system and localization method |
| CN109615645A (en) * | 2018-12-07 | 2019-04-12 | 国网四川省电力公司电力科学研究院 | The Feature Points Extraction of view-based access control model |
| CN109634305A (en) * | 2018-12-21 | 2019-04-16 | 国网安徽省电力有限公司淮南供电公司 | UAV position and orientation method of adjustment and system based on visual aids positioning |
| CN110349191A (en) * | 2019-06-25 | 2019-10-18 | 昆明理工大学 | A kind of visual tracking method based on perceptual hash algorithm |
| CN110399047A (en) * | 2019-07-19 | 2019-11-01 | 常州大学 | It is a kind of that the mouse control method across screen is realized based on Face datection |
-
2019
- 2019-12-16 CN CN201911293115.3A patent/CN111123962A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141433A (en) * | 2018-09-20 | 2019-01-04 | 江阴市雷奥机器人技术有限公司 | A kind of robot indoor locating system and localization method |
| CN109615645A (en) * | 2018-12-07 | 2019-04-12 | 国网四川省电力公司电力科学研究院 | The Feature Points Extraction of view-based access control model |
| CN109634305A (en) * | 2018-12-21 | 2019-04-16 | 国网安徽省电力有限公司淮南供电公司 | UAV position and orientation method of adjustment and system based on visual aids positioning |
| CN110349191A (en) * | 2019-06-25 | 2019-10-18 | 昆明理工大学 | A kind of visual tracking method based on perceptual hash algorithm |
| CN110399047A (en) * | 2019-07-19 | 2019-11-01 | 常州大学 | It is a kind of that the mouse control method across screen is realized based on Face datection |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037274A (en) * | 2020-07-23 | 2020-12-04 | 江苏方天电力技术有限公司 | Multi-rotor unmanned aerial vehicle viewpoint determining method based on solar illumination condition |
| CN112037274B (en) * | 2020-07-23 | 2022-07-26 | 江苏方天电力技术有限公司 | Multi-rotor unmanned aerial vehicle viewpoint determining method based on solar illumination condition |
| CN111966110A (en) * | 2020-09-08 | 2020-11-20 | 天津海运职业学院 | Automatic navigation method and system for port unmanned transport vehicle |
| CN113624133A (en) * | 2021-08-05 | 2021-11-09 | 合肥阳光智维科技有限公司 | Fault positioning method and device and electronic equipment |
| CN113520172A (en) * | 2021-08-06 | 2021-10-22 | 广东福尔电子有限公司 | Pressure-resistant electric cooker temperature sensor detection device |
| CN114578188A (en) * | 2022-05-09 | 2022-06-03 | 环球数科集团有限公司 | Power grid fault positioning method based on Beidou satellite |
| CN114578188B (en) * | 2022-05-09 | 2022-07-08 | 环球数科集团有限公司 | Power grid fault positioning method based on Beidou satellite |
| WO2023216382A1 (en) * | 2022-05-09 | 2023-11-16 | 环球数科集团有限公司 | Power grid fault positioning method based on beidou satellite |
| CN115219852A (en) * | 2022-09-19 | 2022-10-21 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
| CN115219852B (en) * | 2022-09-19 | 2023-03-24 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111123962A (en) | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection | |
| CN111272148B (en) | Unmanned aerial vehicle autonomous inspection self-adaptive imaging quality optimization method for power transmission line | |
| CN106529538A (en) | Method and device for positioning aircraft | |
| CN108229587B (en) | Autonomous transmission tower scanning method based on hovering state of aircraft | |
| CN110799921A (en) | Shooting method and device and unmanned aerial vehicle | |
| CN108317953A (en) | A kind of binocular vision target surface 3D detection methods and system based on unmanned plane | |
| WO2021004416A1 (en) | Method and apparatus for establishing beacon map on basis of visual beacons | |
| CN108363946A (en) | Face tracking system and method based on unmanned plane | |
| CN106485753A (en) | Method and apparatus for the camera calibration of pilotless automobile | |
| WO2019104571A1 (en) | Image processing method and device | |
| CN109739254A (en) | Using the unmanned plane and its localization method of visual pattern positioning in a kind of electric inspection process | |
| CN113159466B (en) | Short-time photovoltaic power generation prediction system and method | |
| TW201926240A (en) | Panoramic photographing method for unmanned aerial vehicle and unmanned aerial vehicle using the same | |
| CN109214254B (en) | Method and device for determining displacement of robot | |
| CN112950667A (en) | Video annotation method, device, equipment and computer readable storage medium | |
| CN112947526B (en) | Unmanned aerial vehicle autonomous landing method and system | |
| CN111798373A (en) | Rapid unmanned aerial vehicle image stitching method based on local plane hypothesis and six-degree-of-freedom pose optimization | |
| CN114372992A (en) | Edge corner point detection four-eye vision algorithm based on moving platform | |
| CN104504691B (en) | Camera position and posture measuring method on basis of low-rank textures | |
| CN108648141A (en) | A kind of image split-joint method and device | |
| CN108320310A (en) | Extraterrestrial target 3 d pose method of estimation based on image sequence | |
| CN109883400B (en) | Automatic target detection and space positioning method for fixed station based on YOLO-SITCOL | |
| CN106461414A (en) | Attitude relationship calculation method for intelligent device, and the intelligent device | |
| CN114326771A (en) | Unmanned aerial vehicle shooting route generation method and system based on image recognition | |
| CN113436267A (en) | Visual inertial navigation calibration method and device, computer equipment and storage medium |
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 |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |