AU2021106241A4 - System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle - Google Patents
System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle Download PDFInfo
- Publication number
- AU2021106241A4 AU2021106241A4 AU2021106241A AU2021106241A AU2021106241A4 AU 2021106241 A4 AU2021106241 A4 AU 2021106241A4 AU 2021106241 A AU2021106241 A AU 2021106241A AU 2021106241 A AU2021106241 A AU 2021106241A AU 2021106241 A4 AU2021106241 A4 AU 2021106241A4
- Authority
- AU
- Australia
- Prior art keywords
- uav
- distance
- post
- unmanned aerial
- camera
- 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.)
- Ceased
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims description 45
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 19
- 239000004020 conductor Substances 0.000 claims abstract description 17
- 239000012212 insulator Substances 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 17
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical group C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 238000011161 development Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 5
- 230000009194 climbing Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 230000000284 resting effect Effects 0.000 claims description 3
- 238000012552 review Methods 0.000 claims 3
- 238000013528 artificial neural network Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 description 10
- 238000001514 detection method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000004429 Calibre Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000005303 weighing Methods 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 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
-
- 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
-
- 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
- G05D1/12—Target-seeking control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
- B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
- G01S13/08—Systems for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Abstract
The present invention generally relates to a system for aerial power lines
measurement using computer vision through an unmanned aerial vehicle
comprises a camera equipped with an unmanned aerial vehicle (UAV) for
capturing real-time image/video of electric lines, wherein a user interface
is interfaced for controlling operation of UAV and camera; a robot
operating system-based control unit configured with trained mask R
convolutional neural network for detecting objects from captured real
time image/video, wherein objects are post, insulator and the electric
line; and a pin hole model for estimating the distance between the UAV
and the objects, and determining wire gauge of the conductor (electric
line).
21
ItL
Description
ItL
FIELDOFTHEINVENTION The present disclosure relates to a system and method for aerial power lines measurement using computer vision through an unmanned aerial vehicle to facilitate and reduce measurement errors.
BACKGROUND OF THE INVENTION The electric distribution firms follow the ministry of electricity and renewable energy's regulations and recommendations. As a result, electrical distribution businesses must have geographic information systems (GIS) for their networks. Energy planning covers a wide range of topics, including the electrical, financial, and commercial sectors. This is why georeferenced data takes centre stage, transforming into a valuable tool for energy planning.
To aid decision-making in planning, leadership, and management, GISs must rely on reliable and accurate data. The issue for electric businesses is obtaining high-quality data. GISs help with this endeavour by providing information and facilitating external and internal communication. A geographic information system (GIS) is a computerised system that collects, saves, searches for, analyses, and displays geographical data. As a result, maintaining this geographic data up to date becomes a time and resource-intensive operation. It frequently includes processes that endanger human life. In the case of the electrical industry, a procedure is required for inspecting, testing, and upgrading the characteristics of electrical lines and buildings.
Currently, various techniques for inspecting electrical cables including manual examination and the use of helicopters and unmanned aerial vehicles (UAVs). Manual inspection has its own set of issues, including as logistics, expenses, and the possibility of accidents, all of which must be addressed. Manual examination of electrical wires is vulnerable to subjectivity because it is based on the technician's perspective. Because the technician usually only has practical knowledge, he may overlook technical flaws in components that aren't visible at first glance. In terms of loss assessment, the gathering and efficient use of data given by information systems should be utilised to quantify technical and non-technical losses with precision.
The inaccuracy of geographical data, such as the wire gauge of overhead wires, is one of the leading sources of technical energy losses.People working in the electrical industry, on the other hand, who interact directly with electrical energy generation, transmission, and distribution facilities are at risk of workplace accidents such as falls and electrical hazards, which can result in bodily damage, disability, or death. UAVs, in combination with technology such as machine vision, open up new possibilities and advantages for the inspection process, presenting new applications that allow people to do tasks more effectively while reducing human danger.
In the view of the forgoing discussion, it is clearly portrayed that there is a need to have a system and method for aerial power lines measurement using computer vision through an unmanned aerial vehicle.
SUMMARY OF THE INVENTION The present disclosure seeks to provide a system and method that facilitates flight control of the UAV, detection of objects using a mask of convolutional neural networks, distance estimation, and caliber measurement of aerial power lines without contact.
In an embodiment, a system for aerial power lines measurement using computer vision through an unmanned aerial vehicle is disclosed.
The system includes a camera equipped with an unmanned aerial vehicle (UAV) for capturing real-time image/video of electric lines, wherein a user interface is interfaced for controlling the operation of UAV and camera. The system further includes a robot operating system-based control unit configured with a trained mask R-convolutional neural network for detecting objects from captured real-time image/video, wherein objects are post, insulator, and the electric line. The system further includes a pin hole model for estimating the distance between the UAV and the objects, and so determining the wire gauge of the conductor (electric line).
In an embodiment, the robot operating system (ROS) robotic user interface is having a collection of frameworks for the development and control of UAV and provides a powerful alternative as a support platform for the interaction of the different processes, wherein the ROS is built using Open CV, Olympe, and Tensor Flow libraries.
In an embodiment, a display is connected with the system for displaying estimated distance between the UAV and the objects and determined wire gauge of the conductor.
In an embodiment, a flight control unit is configured with the user interface for controlling the operation of the UAV.
In an embodiment, flight control unit comprises a main control unit configured for controlling takeoff and landing of the UAV; a UAV monitoring unit configured for monitoring real-time state of the UAV, wherein real-time state are flying, landing, resting, and the like; and a positioning unit configured for calculating the distance of the UAV from land and object.
In another embodiment, a method for aerial power lines measurement using computer vision through an unmanned aerial vehicle is disclosed. The method includes starting an unmanned aerial vehicle (UAV) and controlling the operation of the UAV through a user interface. The method further includes capturing real-time image/video of electric lines using a camera connected with the UAV. The method further includes detecting electrical posts using a trained mask R-convolutional neural network thereby estimating distance using a pin hole model. The method further includes determining wire gauge of the conductor (electric line) thereby landing UAV . In an embodiment, controlling operation of UAV and camera comprises placing UAV at approximately 50 centimeters from the post with the electrical lines to be measured, wherein the UAV is maneuvered to climb to a height of approximately 8.50 meters once the flight starts; detecting the post to align the UAV while climbing parallel to the electrical post; wherein the UAV maintains a distance of 50 centimeters parallel with the electrical post using Pin-hole approach; modifying point in case a tilt in the post is detected; detecting the insulators on the post thereby the UAV proceeds to move to the right for detecting an electrical line and aligning the UAV with the electric line; and proceeding UAV with the wire gauge measurement through analysis of the images thereby descending and landing the UAV at an initial position.
In an embodiment, steps for training mask R-convolutional neural network comprises collecting captured image/video in a dataset and detecting different objects, wherein the dataset contains data for the training, development, and trials adding masks to the detected object manually in the group of training images (1800 images; and employing open access, pre-trained model mask R-CNN for training which is facilitated by Tensor Flow.
In an embodiment, estimation of distance comprises employing the/a Pin-hole model, which allows estimation of the distance of an object using the camera; reflecting the image related to the distance of the object by a focal length; and calculating the distance by allowing to keep the UAV controlled at a distance of 50 centimeters to avoid collision with the electrical line to prevent a short circuit and allowing the relationship between the size of the object in pixels and its real size to be known.
In an embodiment, the UAV selected herein is a light and resistant civilian-use drone configured to resist winds and provides optimum communication range.
An object of the present disclosure is tome a sure the calibre of power lines through the use of an unmanned aerial vehicle (UAV) and computer vision.
Another object of the present disclosure is to promote flight control of the UAV, detection of objects using a mask of convolutional neural networks, distance estimation, and caliber measurement of aerial power lines without contact.
Yet another object of the present invention is to deliver an expeditious and cost-effective system to improve data quality, reduces time and costs, and minimizes the risk of accidents.
To further clarify the advantages and features of the present disclosure, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEFDESCRIPTIONOFFIGURES These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
Figure lillustrates a block diagram of a system for aerial power lines measurement using computer vision through an unmanned aerial vehicle in accordance with an embodiment of the present disclosure; Figure 2 illustrates a block diagram of a flight control of the UAV in accordance with an embodiment of the present disclosure; Figure3illustrates a flow chart of a method for aerial power lines measurement using computer vision through an unmanned aerial vehicle in accordance with an embodiment of the present disclosure; Figure 4 illustrates a structure for the wire gauge measurement processin accordance with an embodiment of the present disclosure; Figure 5 illustrates a system architecture for the wire gauge measurement of overhead electrical conductors in accordance with an embodiment of the present disclosure; Figure 6 illustrates the UAV navigation plan in accordance with an embodiment of the present disclosure; Figure 7 illustrates pin hole model in accordance with an embodiment of the present disclosure; Figure 8 illustrates exemplary images captured by the camera in accordance with an embodiment of the present disclosure; and Figure 9 illustrates Table 1 depicts wire gauges and size in pixels from a distance of 50 cm in accordance with an embodiment of the present disclosure.
Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
DETAILED DESCRIPTION For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.
It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.
Reference throughout this specification to "an aspect", "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase "in an embodiment", "in another embodiment", and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.
The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises...a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.
Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.
Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.
Referring to Figure 1, a block diagram of a system for aerial power lines measurement using computer vision through an unmanned aerial vehicleis illustrated in accordance with an embodiment of the present disclosure. The system 100 includes a camera 102 equipped with an unmanned aerial vehicle (UAV) 104 for capturing real-time image/video of electric lines, wherein a user interface 106 is interfaced for controlling the operation of UAV 104 and camera 102.
In an embodiment, a robot operating system-based control unit 108is configured with trained mask R-convolutional neural network for detecting objects from captured real-time image/video, wherein objects are post, insulator, and the electric line.
In an embodiment, a pin hole model 110is employed for estimating the distance between the UAV 104 and the objects, and determining wire gauge of the conductor (electric line).
In an embodiment, the robot operating system (ROS) robotic user interface 106 is having a collection of frameworks for the development and control of UAV 104 and provides a powerful alternative as a support platform for the interaction of the different processes, wherein the ROS is built using Open CV, Olympe, and Tensor Flow libraries.
In an embodiment, a display is connected with the system for displaying the estimated distance between the UAV 104 and the objects and the determined wire gauge of the conductor.
In an embodiment, a flight control unit 112 is configured with the user interface 106 for controlling the operation of UAV 104.
Figure 2 illustrates a block diagram of a flight control unit 112 of the UAV 104 in accordance with an embodiment of the present disclosure. In an embodiment, the flight control unit 112includes a main control unit 202 configured for controlling takeoff and landing of the UAV 104.
In an embodiment, a UAV monitoring unit 204is configured for monitoring real-time state of the UAV 104, wherein real-time states are flying, landing, resting, and the like.
In an embodiment, a positioning unit 206is configured for calculating the distance of the UAV 104 from land and object.
Figure 3 illustrates a flow chart of a method for aerial power lines measurement using computer vision through an unmanned aerial vehicle in accordance with an embodiment of the present disclosure.At step 302, the method 300 includes starting an unmanned aerial vehicle (UAV) and controlling the operation of the UAV 104 through a user interface 106.
At step 304, the method 300 includes capturing real-time image/video of electric lines using a camera 102 connected with the UAV 104.
At step 306, the method 300 includes detecting an electrical post using a trained mask R-convolutional neural network thereby estimating distance using a pin hole model 110.
At step 308, the method 300 includes maneuvering UAV 104 for detecting power lines through image processing.
At step 310, the method 300 includes determining the wire gauge of the conductor (electric line) thereby landing UAV 104.
In an embodiment, controlling operation of UAV 104 and camera 102includes placing UAV 104 at approximately 50 centimeters from the post with the electrical lines to be measured, wherein the UAV 104 is maneuvered to climb to a height of approximately 8.50 meters once the flight starts. Then, detecting the post to align the UAV 104 while climbing parallel to the electrical post; wherein the UAV 104 maintains a distance of 50 centimeters parallel with the electrical post using Pin-hole approach. Then, modifying distance in case a tilt in the post is detected. Then, detecting the insulators on the post thereby the UAV 104 proceeds to move to the right for detecting an electrical line and aligning the UAV 104 with the electric line. Thereafter, proceeding UAV 104 with the wire gauge measurement through analysis of the images thereby descending and landing the UAV 104 at an initial position.
In an embodiment, steps for training mask R-convolutional neural network includes collecting captured image/video in a dataset and detecting different objects, wherein the dataset contains data for the training, development, and trials adding masks to the detected object manually in the group of training images (1800 images. Thereafter, employing open access, pre-trained model mask R-CNN for training which is facilitated by Tensor Flow.
In an embodiment, estimation of distance includes employing Pin hole model 110, which allows estimation of the distance of an object using the camera 102. Then, reflecting the image related to the distance of the object by a focal length. Thereafter, calculating the distance by allowing to keep the UAV 104 controlled at a distance of 50 centimeters to avoid collision with the electrical line to prevent a short circuit and allowing the relationship between the size of the object in pixels and its real size to be known.
In an embodiment, the UAV 104 selected herein is a light and resistant civilian-use drone configured to resist winds and provides optimum communication range.
Figure 4 illustrates a structure for the wire gauge measurement process in accordance with an embodiment of the present disclosure. The unmanned aerial vehicle (UAV) 104 is started and operation of the UAV 104 is controlled through a user interface 106. Real-time image/video of electric lines is captured using a camera 102 connected with the UAV 104.
The electrical post is detected using a trained mask R-convolutional neural network thereby estimating distance using a pin hole model 110. The UAV 104 is moved for detecting power lines through image processing. Wire gauge of the conductor (electric line) is determined thereby UAV 104 is landed at the end.
Figure 5 illustrates a system architecture for the wire gauge measurement of overhead electrical conductors in accordance with an embodiment of the present disclosure. The proposed system is sued for wire gauge measurement of overhead electrical conductors. The system is made up of four main processes including video streaming, flight control, object detection, and wire gauge calculation. The Robot Operating System (ROS) robotic software is chosen, which is a collection of frameworks for the development and control of robots. ROS is a powerful alternative as a support platform for the interaction of the different processes. The system is built using libraries such as Open CV, Olympe, and Tensor Flow, which all play an important role in the system.
The UAV 104 used herein is a light and resistant civilian-use drone, weighing 320 grams and boasting a flight time of 25 minutes. It has a 4K HDR video camera 102 and takes 21 MP photographs. It can resist winds of up to 50 kilometres per hour. It has a transmission range of 4 kilometres. The lens has a focal length of 35 millimetres. The UAV 104 has a library that provides an interface to connect the controller using the programming language Python.
Video resolutions provided by the camera 102 are 4K Cinema 4096x2160 24fps, 4K UHD 3840x2160 24/25/30fps, and FHD 1920x1080 24/25/30/48/50/60fps.
camera 102 resolution of the used camera 102 is Wide: 21MP (5344x4016) / 4:3 / HFOV 840, Rectilinear: 16MP (4608x3456) / 4:3/ HFOV 75.50.
Figure 6 illustrates UAV 104 navigation plan in accordance with an embodiment of the present disclosure. The UAV 104 has the library that provides a programming interface for its control from a computer. Command messages can be sent for flight control, to verify the current status, start or stop the video streaming, and record the video stream. Using this library, a script is developed that works within ROS. This framework is selected as it provides the standard operating services such as common-use functionality, sending messages between processes, and package maintenance. In this manner, the necessary processes for the flight control and navigation of the UAV 104 can be processed in various nodes. UAV 104 autonomous navigation is extremely complicated, however. Computation times need to be short. To achieve successful navigation of the UAV 104, the various pieces of information processed need to have real-time answers.
The flight plan is vertical. The drone should be placed at approximately 50 centimeters from the post with the electrical lines to be measured. Once the flight is started, the UAV 104 should climb to a height of approximately 8.50 meters, Point B. While the drone is climbing parallel to the post, it will detect the post to align itself. The condition is that it must keep parallel with the post and at a distance of 50 centi meters. To keep that distance, the Pin-hole method is used, which enables the calculation of the distance from the post. In this manner, if a tilt in the post is detected, Point B is modified. The destination is reached when the insulators on the post are detected. Once Point B is reached, the drone proceeds to move 5 meters to the right, detecting an electrical line. In this same manner as with the post, the UAV 104 detects an electrical line and aligns itself with it. The condition is that it must keep parallel at a distance of 50 centimeters. Once Position C is reached, the UAV 104 proceeds with the wire gauge measurement through analysis of the images. Once the wire gauge measurement is finished, the UAV 104 should descend and land at its start position, Point A.
Figure 7 illustrates pin hole model 110in accordance with an embodiment of the present disclosure. Machine vision is based on the capture, processing, and analysis of real-world images. An important part of this investigation is to use the video stream between the UAV 104 and the computer. The streaming starts from the moment the system starts and continues throughout the different phases of the measurement. The video capture is the input point for information into the system. Processing the information from the video will indicate the events and actions to be taken in different phases. Therefore, video streaming and processing must be carried out in parallel with each other.
The detection phase is performed for three objects in particular: the post, the insulator, and the electrical line. By means of Deep Learning approaches, the UAV 104 through its camera 102 is intended to be able to detect objects. Convolutional neural net- works (CNN) approaches are the main tool that is used in object detection. In our case, Mask R-CNN is used. The detection phase depends on the training of the model, which is carried out before the system is initiated and is essential to the proper functioning of the system. To carry out this training, a dataset of images of the different objects to be detected captured by the camera 102 of the UAV 104 must be acquired and used. The dataset must have data for the training, development, and trials. In the group of training images (1800 images), masks are added to the objects to be detected. The masks are added manually to the dataset. For the training, the open access, pre trained model mask R-CNN is used. This is facilitated by TensorFlow. As a prerequisite, its parameters must be set so that it will train our model with the objects of interest to us.
The UAV 104 perceives the real world through image capture. In this phase, the distance between the UAV 104 and the objects it recognizes is estimated. This task is performed using the Pin- hole model 110, which allows for the estimation of the distance of an object using a camera 102. The method is exceedingly simple, as the size of the image is related to the distance of the object that is reflected by the focal length. The calculation of the distance helps in two ways: Firstly, it allows us to keep the UAV 104 controlled at a distance of 50 centimeters so that it does not collide with the electrical line and thereby cause a short circuit. Secondly, it allows the relationship between the size of the object in pixels and its real size to be known.
Figure 8 illustrates exemplary images captured by the camera 102in accordance with an embodiment of the present disclosure. Once the UAV 104 is located in front of the electrical conductor, it goes on to determine the wire gauge of the conductor using the Pin-hole method. This is done through a pixel relationship; that is, the number of pixels for each AWG conductor. In Table 1, the specific values in millimeters and pixels for 6, 4, 2, 1/0, and 2/0 wire gauges when the drone is at a distance of 50 centimeters can be found. These values are determined from the image analysis.
The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no meanslimited by these specific examples.
Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.
Claims (10)
1. A system for aerial power lines measurement using computer vision through an unmanned aerial vehicle, the system comprises:
a camera equipped with an unmanned aerial vehicle (UAV) for capturing real-time image/video of electric lines, wherein a user interface is interfaced for controlling operation of UAV and camera; a robot operating system-based control unit configured with trained mask R-convolutional neural network for detecting objects from captured real-time image/video, wherein objects are post, insulator, and the electric line; and a pin hole model for estimating the distance between the UAV and the objects, and determining the wire gauge of the conductor (electric line).
2. The system as claimed in claim 1, wherein the robot operating system (ROS) robotic user interface is having a collection of frameworks for the development and control of UAV and provides a powerful alternative as a support platform for the interaction of the different processes, wherein the ROS is built using Open CV, Olympe, and Tensor Flow libraries.
3. The system as claimed in claim 1, wherein a display is connected with the system for displaying estimated distance between the UAV and the objects and determined wire gauge of the conductor.
4. The system as claimed in claim 1, wherein a flight control unit is configured with the user interface for controlling UAV operation.
5. The system as claimed in claim 4, wherein flight control unit comprises: a main control unit configured for controlling takeoff and landing of the UAV; a UAV monitoring unit configured for monitoring real-time state of the UAV, wherein real-time states are flying, landing, resting, and the like; and a positioning unit configured for calculating the distance of the UAV from land and object.
6. A method for aerial power lines measurement using computer vision through an unmanned aerial vehicle, the method comprises:
starting an unmanned aerial vehicle (UAV) and controlling operation of the UAV through a user interface; capturing real time image/video of electric lines using a camera connected with the UAV; detecting electrical post using trained mask R-convolutional neural network thereby estimating distance using a pin hole model; maneuvering UAV for detecting power lines through image processing; and determining wire gauge of the conductor (electric line) thereby landing UAV.
7. The method as claimed in claim 6, wherein controlling operation of UAV and camera comprises:
placing UAV at approximately 50 centimeters from the post with the electrical lines to be measured, wherein the UAV is maneuvered to climb to a height of approximately 8.50 meters once the flight starts; detecting the post to align the UAV while climbing parallel to the electrical post; wherein the UAV maintains distance of 50 centimeters parallel with the electrical post using Pin-hole approach; modifying point in case a tilt in the post is detected; detecting the insulators on the post thereby the UAV proceeds to move to the right for detecting an electrical line and aligning the UAV with the electric line; and proceeding UAV with the wire gauge measurement through analysis of the images thereby descending and landing the UAV at an initial position.
8. The method as claimed in claim 6, wherein steps for training mask R-convolutional neural network comprises:
collecting captured image/video in a dataset and detecting different objects, wherein the dataset contains data for the training, development, and trials; adding masks to the detected object manually in the group of training images (1800 images; and employing open access, pre-trained model mask R-CNNfor training which is facilitated by Tensor Flow.
9. The method as claimed in claim 6, wherein estimation of distance comprises:
employing Pin-hole model, which allows estimation of the distance of an object using the camera; reflecting the image related to the distance of the object by a focal length; and calculating the distance by allowing to keep the UAV controlled at a distance of 50 centimeters to avoid collision with the electrical line to prevent a short circuit and allowing the relationship between the size of the object in pixels and its real size to be known.
10. The method as claimed in claim 6, wherein the UAV selected herein is a light and resistant civilian-use drone configured to resist winds and provides optimum communication range.
A Camera 102 An Unmanned Aerial Vehicle 104
A User Interface 106 A Control Unit 108
A Flight Control Unit A Pin Hole Model 110 112
Figure 1
A Main Control Unit A Monitoring Unit 202 204
A Positioning Unit 206
Figure 2 removing noise from review comments and tweets thereby structuring review comments and 302 tweets in a single format upon removing special characters, symbols and other language fonts dividing preprocessed data into individual tokens for creating dictionary, wherein tokens are words 304 or features indexing sentences based on the dictionary thereby converting indexed sentences vector real 306 numbers performing sentiment analysis in Tamil text to classify the review comments and tweets into 308 positive and negative sentiment using deep neural network
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021106241A AU2021106241A4 (en) | 2021-08-20 | 2021-08-20 | System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021106241A AU2021106241A4 (en) | 2021-08-20 | 2021-08-20 | System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021106241A4 true AU2021106241A4 (en) | 2022-01-13 |
Family
ID=79180933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021106241A Ceased AU2021106241A4 (en) | 2021-08-20 | 2021-08-20 | System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2021106241A4 (en) |
-
2021
- 2021-08-20 AU AU2021106241A patent/AU2021106241A4/en not_active Ceased
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742125B (en) | Deep machine learning to predict and prevent adverse conditions at structural assets | |
| JP2019009919A (en) | Patrol inspection support system and patrol inspection support control program | |
| CN110865917A (en) | AR technology-based electric power machine room inspection operation method, system and application | |
| CN108872781B (en) | Analysis method and device based on intelligent inspection of electric power facilities | |
| CN114792319B (en) | Transformer substation inspection method and system based on transformer substation image | |
| CN112633380A (en) | Interest point feature extraction method and device, electronic equipment and storage medium | |
| CN112327906A (en) | Intelligent automatic inspection system based on unmanned aerial vehicle | |
| CN111244822B (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment | |
| Schofield et al. | Cloud to cable: A drone framework for autonomous power line inspection | |
| Ohta et al. | Image acquisition of power line transmission towers using UAV and deep learning technique for insulators localization and recognition | |
| CN110705452A (en) | Intelligent management and control method and system for facilities of expressway unattended toll station | |
| CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
| CN112949457A (en) | Maintenance method, device and system based on augmented reality technology | |
| CN109885091B (en) | Unmanned aerial vehicle autonomous flight control method and system | |
| AU2021106241A4 (en) | System and method for aerial power lines measurement using computer vision and unmanned aerial vehicle | |
| CN109445388A (en) | Industrial control system data analysis processing device and method based on image recognition | |
| CN116931596A (en) | Unmanned aerial vehicle flight system with flight program automatically arranged | |
| CN115861962A (en) | Point cloud filtering method and device, electronic equipment and storage medium | |
| CN113095160B (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
| CN115797824A (en) | Unmanned aerial vehicle power construction violation identification method and device based on artificial intelligence | |
| CN114419590A (en) | High-precision map verification method, device, equipment and storage medium | |
| CN114285374A (en) | Equipment positioning method and system for photovoltaic power station, electronic equipment and storage medium | |
| CN110516551B (en) | Vision-based line patrol position deviation identification system and method and unmanned aerial vehicle | |
| CN110989666A (en) | Unmanned aerial vehicle system for line inspection and control method thereof | |
| CN110597293A (en) | Unmanned aerial vehicle autonomous flight method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |